CN109714378A - The recommended method and system of application program - Google Patents
The recommended method and system of application program Download PDFInfo
- Publication number
- CN109714378A CN109714378A CN201711016613.4A CN201711016613A CN109714378A CN 109714378 A CN109714378 A CN 109714378A CN 201711016613 A CN201711016613 A CN 201711016613A CN 109714378 A CN109714378 A CN 109714378A
- Authority
- CN
- China
- Prior art keywords
- application program
- user terminal
- recommendation
- user
- application
- 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.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Present disclose provides a kind of recommended method of application program and systems, are related to field of communication technology.This method comprises: obtaining network packet in network side, network packet is parsed, and each user terminal that multiple user terminals are calculated uses time interval, number and the flow number of each application program in multiple application programs;The application recommendation for using each application program is calculated using the time interval of each application program, number and flow number according to each user terminal;According to the applicating category for determining user's preferences using recommendation for using each application program;According to the whole network recommendation that each application program is calculated using recommendation, and the whole network recommendation according to each application program, the recommendation for obtaining the application program under the applicating category sort;And it is sorted according to recommendation and recommends application program to user terminal.Disclosed method and system can be than accurately recommending application program to user.
Description
Technical field
This disclosure relates to field of communication technology, the in particular to recommended method and system of a kind of application program.
Background technique
To meet the different application demand of user, the various application programs that can run on intelligent terminal are come into being, and are people
Working Life bring great convenience.Existing application type, quantity are various, are quickly found and think for the ease of user
The application wanted much can recommend current download maximum or the maximum popular application of volumes of searches using download platform to user.Respectively
Kind application provider, service provider etc. can also be pushed away by other channels such as application message, short message or page pop-ups for user
Recommending it may interested application program.
Such as in order to recommend the application of its love style to user, be promoted and recommend success rate, it is known that there is application in technology
Recommended method.Such as the usage log that terminal has installed application is obtained, the application of less classification is recommended to use for user.But
Existing application recommended method has the following deficiencies:
(1) it is needed on mobile terminal with application message acquisition/monitoring modular, usually separately installed APP (application).
Since terminal applies acquisition of information/monitoring APP needs additional installation, existing scheme Difficulty, and application letter is installed
Breath acquisition/monitoring APP terminal quantity is limited, and the application message data limitation of acquisition is very big.
(2) in view of there may be following situations: a certain application of user installation but from being not used;Or a certain application warp
It is often opened but user's reality and is not used from the background;Or certain applications booting self-startings, but user and not actually used production
Raw flow, etc..In these cases, only by terminal obtain certain dimension using data, it is a certain to be unable to accurate judgement
Whether applicating category is the classification of user's preferences, precisely recommends so that being likely to realize for user.For example, Video Applications
Flow is usually bigger than the flow of other application, but does not necessarily mean that user more has a preference for video class application.In another example social category
It determines frequently to wake up from the background using by its property, frequent starting, but does not necessarily mean that user more has a preference for such and answers
With.
Summary of the invention
The technical problem that the disclosure solves is: a kind of recommended method of application program is provided, thus than accurately
Recommend application program to user.
According to the one aspect of the embodiment of the present disclosure, a kind of recommended method of application program is provided, comprising: in network side
Network packet is obtained, the network packet is parsed, and each user terminal of multiple user terminals is calculated
Use time interval, number and the flow number of each application program in multiple application programs;It is whole according to the multiple user
Each user terminal at end uses time interval, number and the flow number of each application program in the multiple application program
The application recommendation that each user terminal uses each application program is calculated;It is used according to the user terminal
The applicating category that the user's preferences are determined using recommendation of each application program;According to the every of the multiple user terminal
A user terminal is recommended using the whole network that each application program is calculated using recommendation of each application program
Degree, and the whole network recommendation according to each application program, obtain the recommendation of the application program under the applicating category
Sequence;And it is sorted according to the recommendation of the application program under the applicating category and is recommended to the user terminal using journey
Sequence.
Optionally, network packet is obtained in network side, the network packet is parsed, and is calculated multiple
Each user terminal of user terminal uses all time intervals, number and the stream of each application program in multiple application programs
The step of numerical quantity includes: to obtain the network packet of user terminal in network side, by parsing the network packet, is obtained
Purpose uniform resource position mark URL, time started, end time, uninterrupted, the type of service of the network packet are compiled
Code, server network Protocol IP address and apply characteristic information;According to the purpose URL, type of service coding, server ip
Address and the application program or the corresponding function of the application program that user terminal access is determined using characteristic information;According to institute
At the beginning of stating network packet and the end time obtains the time interval and access times for accessing the application program;And
The flow information used is obtained according to the uninterrupted;And according to time interval, the access time for accessing the application program
Several and flow information calculates the user terminal and uses all time intervals of the application program, using the application program
Number and the flow number that is generated using the application program.
Optionally, the application recommendation R of each application program is calculatediFormula are as follows:
Ri=WuU′IUF+WfF′IUF-WiI′IUF,
Wherein, U'IUFThe standardized value of the number of single application program, F' are used for the multiple user terminalIUFFor institute
It states multiple user terminals and uses the standardized value of the flow number of the single application program, I'IUFFor the multiple user terminal
Use the standardized value of the time interval of the single application program, WuThe single application is used for the multiple user terminal
The weight of the number of program, WfThe weight of the flow number of the single application program, W are used for the multiple user terminaliFor
The multiple user terminal uses the weight of the time interval of the single application program.
Optionally, it is calculated by the following formula to obtain the U' respectivelyIUF, the F'IUFWith the I'IUF:
Wherein, UiThe number of the single application program, F are used for each user terminaliIt is whole for each user
Flow number of the end using the single application program consumption, IiThe single application program is used for each user terminal
Time interval, N is the total number of users using the single application program;Described in all user terminal uses for monitoring
The number average value of single application program,The flow number of the single application program is used for all user terminals of monitoring
It is worth average value,The time-interval averaging value of the single application program is used for all user terminals of monitoring.
Optionally, it is calculated by the following formula to obtain respectively describedIt is describedWith it is described
Wherein, M is the quantity of the user terminal monitored.
Optionally, which is determined using the application recommendation of each application program according to the user terminal
Applicating category the step of include: according to applicating category belonging to application program, the application program used to user terminal carries out
Classification, and the sum using recommendation of the application program under each applicating category is calculated, the classification that is applied recommendation, according to
The applicating category recommendation determines the applicating category that the user is had a preference for.
Optionally, it is pushed away according to each user terminal of the multiple user terminal using the application of each application program
It includes: to calculate all users for each application program that degree of recommending, which is calculated the step of the whole network recommendation of the application program,
Terminal uses the sum using recommendation of the application program, obtains the whole network recommendation of the application program.
Optionally, it is sorted according to the recommendation of the application program under the applicating category and is answered to user terminal recommendation
It include: the applicating category being had a preference for according to determining user with the step of program, in the applicating category for selecting single user's preference
Temporary original application program establishes user and recommends association table;Wherein, the user recommend association table include with
The corresponding temporarily original the whole network recommendation application program in the top of the user terminal;And the user is recommended
Application program in association table recommends the user terminal.
According to the other side of the embodiment of the present disclosure, a kind of recommender system of application program is provided, comprising: acquisition mould
Block, for obtaining network packet in network side;Identification module for parsing to the network packet, and calculates
To multiple user terminals each user terminal using the time interval of each application program in multiple application programs, number and
Flow number;Recommendation computing module, for being answered according to each user terminal of the multiple user terminal using the multiple
Each user terminal is calculated with time interval, number and the flow number of each application program in program to use often
The application recommendation of a application program;Application class module, for using each application according to the user terminal
The applicating category that the user's preferences are determined using recommendation of program;Using selecting module, for whole according to the multiple user
The complete of each application program is calculated using recommendation using each application program in each user terminal at end
Net recommendation, and the whole network recommendation according to each application program, obtain the application program under the applicating category
Recommendation sequence;And apply pushing module, for the recommendation according to application program under the applicating category sort to
The user terminal recommends application program.
Optionally, the acquisition module is used to obtain the network packet of user terminal in network side;The identification module
The network packet is parsed for passing through, when obtaining the purpose uniform resource position mark URL of the network packet, starting
Between, the end time, uninterrupted, type of service coding, server network Protocol IP address and apply characteristic information;According to institute
State purpose URL, type of service coding, server ip address and the application program that user terminal access is determined using characteristic information
Or the corresponding function of the application program;It is answered according to being accessed at the beginning of the network packet with the end time
With the time interval and access times of program;And the flow information used is obtained according to the uninterrupted;And according to visit
Ask that the time interval, access times and flow information of the application program calculate the user terminal and use the application program
All time intervals, the number using the application program and the flow number that is generated using the application program.
Optionally, the recommendation computing module calculates the application recommendation R of each application programiFormula are as follows:
Ri=WuU′IUF+WfF′IUF-WiI′IUF,
Wherein, U'IUFThe standardized value of the number of single application program, F' are used for the multiple user terminalIUFFor institute
It states multiple user terminals and uses the standardized value of the flow number of the single application program, I'IUFFor the multiple user terminal
Use the standardized value of the time interval of the single application program, WuThe single application is used for the multiple user terminal
The weight of the number of program, WfThe weight of the flow number of the single application program, W are used for the multiple user terminaliFor
The multiple user terminal uses the weight of the time interval of the single application program.
Optionally, the recommendation computing module is calculated by the following formula to obtain the U' respectivelyIUF, the F'IUFWith
The I'IUF:
Wherein, UiThe number of the single application program, F are used for each user terminaliIt is whole for each user
Flow number of the end using the single application program consumption, IiThe single application program is used for each user terminal
Time interval, N is the total number of users using the single application program;Described in all user terminal uses for monitoring
The number average value of single application program,The flow number of the single application program is used for all user terminals of monitoring
It is worth average value,The time-interval averaging value of the single application program is used for all user terminals of monitoring.
Optionally, the recommendation computing module is calculated by the following formula to obtain respectively describedIt is describedAnd institute
It states
Wherein, M is the quantity of the user terminal monitored.
Optionally, the application class module is used to use user terminal according to applicating category belonging to application program
Application program classify, and calculate the sum using recommendation of application program under each applicating category, be applied
Classification recommendation determines the applicating category that the user is had a preference for according to the applicating category recommendation.
Optionally, the application selecting module is used to that each application program to be calculated all user terminals and answered using this
With the sum using recommendation of program, the whole network recommendation of the application program is obtained.
Optionally, the applicating category for being used to be had a preference for according to determining user using pushing module selects single use
Temporary original application program in the applicating category of family preference, establishes user and recommends association table;Wherein, the user pushes away
Recommending association table includes temporarily original the whole network recommendation application program in the top corresponding with the user terminal;
And the application program in association table is recommended to recommend the user terminal user.
According to the other side of the embodiment of the present disclosure, a kind of recommender system of application program is provided, comprising: storage
Device;And it is coupled to the processor of the memory, the processor is configured to based on the instruction for being stored in the memory
Execute foregoing method.
According to the other side of the embodiment of the present disclosure, a kind of computer readable storage medium is provided, is stored thereon with
The step of computer program instructions, which realizes foregoing method when being executed by processor.
In above-described embodiment of the disclosure, answered in network side by obtaining each user terminal to network data Packet analyzing
With the service condition of program, all time interval I, number U and the flow number F of application program are used including user;According to end
The service condition for holding application program, calculates the application recommendation that each user respectively applies using IUF model;It is respectively applied according to each user
The applicating category that user's preferences are determined using recommendation;Respectively apply recommendation that some application is calculated according to whole users
The whole network recommendation, obtain under applicating category respectively apply the whole network recommendation sequence;According to the application under applicating category
The recommendation of program, which sorts, recommends application program to user terminal, so as to than accurately recommending application program to user.
The recommended method and system of the application program of the embodiment of the present disclosure can be implemented in carrier network side, without changing
Into terminal, scheme is easily promoted, and data acquisition is not limited to by terminal;As far as possible not by differentia influence is applied in recommendation process, accurately
Judge the applicating category of user's preferences;It is more acurrate to reasonably determine application program to be recommended.
By the detailed description referring to the drawings to the exemplary embodiment of the disclosure, the other feature of the disclosure and its
Advantage will become apparent.
Detailed description of the invention
The attached drawing for constituting part of specification describes embodiment of the disclosure, and together with the description for solving
Release the principle of the disclosure.
The disclosure can be more clearly understood according to following detailed description referring to attached drawing, in which:
Fig. 1 is the flow chart for showing the recommended method of the application program according to some embodiments of the disclosure.
Fig. 2 is the IUF model schematic schematically shown according to some embodiments of the disclosure.
Fig. 3 is the structure chart for schematically showing the recommender system of the application program according to some embodiments of the disclosure.
Fig. 4 is the structure chart for schematically showing the recommender system of the application program according to the disclosure other embodiments.
Fig. 5 is the structure chart for schematically showing the recommender system of the application program according to the disclosure other embodiments.
Specific embodiment
The various exemplary embodiments of the disclosure are described in detail now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
Scope of disclosure.
Simultaneously, it should be appreciated that for ease of description, the size of various pieces shown in attached drawing is not according to reality
Proportionate relationship draw.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the disclosure
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, without
It is as limitation.Therefore, the other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
Fig. 1 is the flow chart for showing the recommended method of the application program according to some embodiments of the disclosure.
In step S102, network packet is obtained in network side, which is parsed, and is calculated more
Each user terminal of a user terminal uses time interval, number and the flow of each application program in multiple application programs
Numerical value.
Optionally, step S102 may include: to obtain the network packet of user terminal in network side, by parsing net
Network data packet obtains the purpose URL (Uniform Resource Locator, uniform resource locator) of network packet, opens
Begin time, end time, uninterrupted (such as may include at least one of uplink traffic and downlink traffic), type of service
Coding, server ip (Internet Protocol, network protocol) address and apply characteristic information.
Optionally, step S102 can also include: according to purpose URL, type of service coding, server ip address and
The application program or the corresponding function of the application program of user terminal access are determined using characteristic information;According to network packet
At the beginning of and the end time obtain access the application program time interval and access times;And it is obtained according to uninterrupted
The flow information that must be used.
For example, by taking wechat as an example according to purpose URL, type of service coding, server ip address and feature can be applied
Information determines that the application program of user terminal access is wechat or the corresponding function of the wechat.For example, certain URL of wechat are corresponding
Its payment function, some URL correspond to its social functions.In some embodiments, application program or application program be can establish
The corresponding relationship of the information such as function and above-mentioned purpose URL, type of service coding, server ip address and application feature.One
In a little embodiments, the corresponding relationship for increasing new application or function and above- mentioned information can also be constantly identified.
Optionally, step S102 can also include: the time interval, access times and flow according to access application
Information calculates all time interval Is (Interval) of the user terminal using the application program, time using the application program
Number U (Usage) and the flow number F (Flow) generated using the application program.
In some embodiments, as shown in Fig. 2, time interval I may include between time using the uplink traffic of application
Every IUplinkWith the time interval I for the downlink traffic for using applicationDownlink;Access times U may include the uplink traffic using application
Access times UUplinkWith the access times U for the downlink traffic for using applicationDownlink;Flow number F may include the uplink using application
The flow number F of flowUplinkWith the flow number F for the downlink traffic for using applicationDownlink。
In step S104, each application in multiple application programs is used according to each user terminal of multiple user terminals
Each user terminal is calculated in time interval, number and the flow number of program is recommended using the application of each application program
Degree.
In some embodiments, the application recommendation R of each application program is calculatediFormula are as follows:
Ri=WuU′IUF+WfF′IUF-WiI′IUF, (1)
Wherein, U'IUFThe standardized value of the number of single application program, F' are used for the multiple user terminalIUFFor institute
It states multiple user terminals and uses the standardized value of the flow number of the single application program, I'IUFMake for the multiple user terminal
With the standardized value of the time interval of the single application program, WuThe single application program is used for the multiple user terminal
The weight of number, WfThe weight of the flow number of the single application program, W are used for the multiple user terminaliIt is the multiple
User terminal uses the weight of the time interval of the single application program.Wu、WfAnd WiIt can determine according to the actual situation, example
It can such as be obtained by training.
In some embodiments, it is calculated by the following formula to obtain U' respectivelyIUF、F'IUFAnd I'IUF:
Wherein, UiThe number of the single application program, F are used for each user terminaliThe list is used for each user terminal
The flow number of a application program consumption, IiThe time interval of the single application program is used for each user terminal, N is to use
The total number of users of the single application program;It is average using the number of the single application program for all user terminals of monitoring
Value,The flow number average value of the single application program is used for all user terminals of monitoring,It is useful for monitoring
Family terminal uses the time-interval averaging value of the single application program.
In some embodiments, it is calculated by the following formula to obtain respectivelyWith
Wherein, M is the quantity of the user terminal monitored.
In some embodiments, single-user application recommendation can be calculated by following procedure: by formula (5),
(6) and (7) calculate all single application program index average values for monitoring user (such as M user terminal)WithThen single-user application index is standardized using formula (2), (3) and (4), that is, calculates separately standard
Change value U'IUF、F'IUFAnd I'IUF;The application recommendation R of application program is finally calculated using formula (1)i.Above-mentioned computation model can
With referred to as IUF model, the application recommendation an of application program has been calculated by IUF model here.And so on, it can be with
Calculate the application recommendation of each application program of multiple users.
In step S106, answering for the user's preferences is determined using recommendation using each application program according to user terminal
Use classification.
In some embodiments, step S106 may include: according to applicating category belonging to application program, to user's end
It holds the application program used to classify, and calculates the sum using recommendation of the application program under each applicating category, obtain
To applicating category recommendation, the applicating category which is had a preference for is determined according to applicating category recommendation.The applicating category is recommended
Degree can reflect out the preference degree for the applicating category that user is had a preference for.
The application recommendation and applicating category recommendation of certain application programs of 1 some user of table
Table 1 is the application recommendation and applicating category recommendation for the certain application programs being illustratively calculated.With this
For table 1, as it can be seen from table 1 video traffic and the applicating category recommendation of payment application are bigger, therefore user more has a preference for
Use the application program of video and payment class.
In step S108, the application recommendation of each application program is used according to each user terminal of multiple user terminals
The whole network recommendation of each application program, and the whole network recommendation according to each application program is calculated, obtains using class
The recommendation of application program under not sorts.
In some embodiments, it is pushed away according to each user terminal of multiple user terminals using the application of each application program
It may include: to calculate all users for each application program that degree of recommending, which is calculated the step of the whole network recommendation of application program,
Terminal uses the sum using recommendation of the application program, obtains the whole network recommendation of the application program.
In some embodiments, respectively apply recommendation that some application is calculated according to whole users in specified range
The whole network recommendation, can recommend under applicating category (such as user had a preference for applicating category) according to the whole network of each application program
Degree sequence obtains the recommendation sequence of the applicating category.Further, it is also possible to carry out classification classification according to applicating category.
For example, the whole network user of acquisition assumes there are 20000, the certain applications being calculated such as the following table 2 may be generated
The whole network recommendation of program.Here, the whole network recommendation of some application program (such as wechat), be by all users (such as
20000 users) the application recommendation of the application program be added and obtain, such as finally obtain the whole network recommendation of wechat and be
12033, it is other similar.
The whole network recommendation for certain application programs that table 2 is calculated
As can be seen from Table 2, for social category application, the sequence of popular application under the category can be obtained are as follows: wechat, new
Unrestrained microblogging, YY voice, footpath between fields footpath between fields and Fetion;For paying class application, popular application sequence also can be obtained: Alipay, the wing pay, are micro-
Letter payment and Jingdone district wallet.
In step S110, is sorted according to the recommendation of the application program under applicating category and recommended to user terminal using journey
Sequence.
In some embodiments, step S110 may include: the applicating category being had a preference for according to determining user, selection
Temporary original application program in the applicating category of single user's preference, establishes user and recommends association table;Wherein, the use
It includes temporarily original the whole network recommendation application journey in the top corresponding with the user terminal that association table is recommended at family
Sequence;And the application program in association table is recommended to recommend the user terminal user.In embodiment, realize for
Temporary uninstalled the whole network recommendation application program in the top under the applicating category that user recommends it to have a preference for.
In step S110, according to the application type of predetermined each user's preferences, answering for single user preference is selected
With original application program temporary in type, establishes user and association table, such as a upper user is recommended to pay class application and make
It is more, but it does not install the wing payment using class payment hot topic second, then recommends the application for it.
Mode about recommendation can be there are many mode.For example, user can be recommended to the application journey in association table
Sequence is pushed to user terminal with short message mode, and user independently selects to install.In another example user can be recommended association information
It is sent to application shop with application program recommendation information, when user logs in application shop, homepage shows that the user is generic
The application program of recommendation.Certainly, it will be understood by those skilled in the art that can also be in such a way that other be recommended, therefore this public affairs
The range opened is not limited to that.
So far, the recommended method of the application program according to some embodiments of the disclosure is provided.In the method, in network
Side uses application program by obtaining the service condition of each user terminal application program to network data Packet analyzing, including user
All time interval I, number U and flow number F;According to the service condition of end application, each use is calculated using IUF model
The application recommendation that family is respectively applied;The applicating category that user's preferences are determined using recommendation respectively applied according to each user;According to
Whole users respectively apply recommendation that the whole network recommendation of some application is calculated, and obtain respectively applying under the applicating category
The sequence of the whole network recommendation;It is sorted according to the recommendation of the application program under applicating category and recommends application program to user terminal,
So as to than accurately recommending application program to user.
The recommended method of the application program of the embodiment of the present disclosure can be implemented in carrier network side, without improving eventually
End, scheme are easily promoted, and data acquisition is not limited to by terminal;As far as possible not by using differentia influence, accurate judgement in recommendation process
The applicating category of user's preferences;It is more acurrate to reasonably determine application to be recommended.
Fig. 3 is the structure chart for schematically showing the recommender system of the application program according to some embodiments of the disclosure.?
In Fig. 3, other than the recommender system 30 for showing application program, further it is shown that user terminal 32, wireless access network 33, core
Net 34, bearer network 35 and application server 36.User terminal 32 can be mobile terminal, such as may include mobile phone, plate etc.
Mobile device.User is connected to carrier network (including wireless access network 33, core net 34 and bearer network by user terminal 32
35), so as to accessing application server (such as SP (Service Provider, service provider) application server) 36.
For application server 36 for providing service business, for example, user provides the mobile applications such as web page browsing, instant messaging, video,
Such as wechat, Sina, iqiyi.com etc..
As shown in figure 3, the recommender system 30 of the application program may include: acquisition module 302, identification module 304, recommend
Spend computing module 306, application class module 308, using selecting module 310 and using pushing module 312.
The acquisition module 302 can be used for obtaining network packet in network side.For example, acquisition module 302 can acquire
The data on flows of user terminal may include size, terminal operating system type of data flow and data traffic etc..
The identification module 304 can be used for parsing network packet, and the every of multiple user terminals is calculated
A user terminal uses time interval, number and the flow number of each application program in multiple application programs.For example, identification
Module 304 can parse the data on flows of user terminal, extract the application type of user data flow direction, application request connection when
Between point, the uninterrupted of types of applications etc..
The recommendation computing module 306 can be used for according to each user terminal use of the multiple user terminal
Time interval, number and the flow number of each application program in multiple application programs are calculated each user terminal and use
The application recommendation of each application program.For example, recommendation computing module 306 can be based on the output of identification module 304, monthly
Calculating user accesses the number of application server daily, daily application program uses uninterrupted, owning using application program
Time interval, and with IUF model calculate user application program recommendation.
The application class module 308 can be used for being determined according to user terminal using the application recommendation of each application program
The applicating category of the user's preferences.For example, application class module 308 can will be used based on the output of recommendation computing module 306
The application program that family uses is classified, and marks the application recommendation and applicating category recommendation of user terminal.
This can be used for being answered according to each user terminal of the multiple user terminal using each using selecting module 310
With the whole network recommendation that each application program is calculated using recommendation of program, and the whole network according to each application program pushes away
Degree of recommending obtains the recommendation sequence of the application program under applicating category.For example, can be based on recommendation using selecting module 310
The output for spending computing module 306 and application class module 308, analyzes the output of multiple user terminals as a result, selecting generic push away
The relatively high application program of degree of recommending.
This can be used for being sorted according to the recommendation of the application program under applicating category to user using pushing module 312
Terminal recommends application program.For example, can be by the application recommendation of the application program of user terminal, flat using pushing module 312
Similar recommendation is sent to application shop, and when user logs in application shop, homepage shows the relatively high application journey of recommendation
Sequence.
In the recommender system of the application program of above-described embodiment, acquisition module obtains network packet in network side;Know
Other module parses network packet, and be calculated each user terminal using each application program time interval,
Number and flow number;Recommendation computing module uses the time interval of each application program, number according to each user terminal
The application recommendation that each user terminal uses each application program is calculated with flow number;Application class module according to
Family terminal using each application program the applicating category that the user's preferences are determined using recommendation;Using selecting module according to every
The whole network recommendation that using recommendation is calculated each application program of a user terminal using each application program, and foundation
The whole network recommendation of each application program obtains the recommendation sequence of the application program under applicating category;And application push
Module sorts according to the recommendation of the application program under applicating category recommends application program to user terminal, so as to compare
Accurately recommend application program to user.
The recommender system of the application program of the embodiment of the present disclosure can be implemented in carrier network side, without improving eventually
End, scheme are easily promoted, and data acquisition is not limited to by terminal;As far as possible not by using differentia influence, accurate judgement in recommendation process
The applicating category of user's preferences;It is more acurrate to reasonably determine application to be recommended.
In some embodiments, acquisition module 302 and identification module 304 can form collection terminal, can be by the collection terminal
Be arranged between wireless access network 33 and core net 34, thus network side obtain network packet, and to network packet into
Row parsing and calculating obtain time interval, number and flow number that each user terminal uses each application program.
In some embodiments, can by recommendation computing module 306, application class module 308, using selecting module
310 and application pushing module 312 setting beyond the clouds, be conducive in this way implement calculate recommendation and recommend application program.
In some embodiments, acquisition module 302 can be used for obtaining the network packet of user terminal in network side.Know
Other module 304 can be used for obtaining purpose URL, the time started, end of the network packet by parsing the network packet
Time, uninterrupted, type of service coding, server ip address and apply characteristic information;According to purpose URL, service class
Type coding, server ip address and application program or the application program pair that user terminal access is determined using characteristic information
The function of answering;At the beginning of according to the network packet and the end time obtains the time interval and visit for accessing the application program
Ask number;And the flow information used is obtained according to uninterrupted;And according to time interval, the visit for accessing the application program
Ask that number and flow information calculate all time intervals of the user terminal using the application program, time using the application program
Number and the flow number generated using the application program.
In some embodiments, recommendation computing module 306 calculates the application recommendation R of each application programiFormula
Are as follows:
Ri=WuU′IUF+WfF′IUF-WiI′IUF,
Wherein, U'IUFThe standardized value of the number of single application program, F' are used for the multiple user terminalIUFFor institute
It states multiple user terminals and uses the standardized value of the flow number of the single application program, I'IUFMake for the multiple user terminal
With the standardized value of the time interval of the single application program, WuThe single application program is used for the multiple user terminal
The weight of number, WfThe weight of the flow number of the single application program, W are used for the multiple user terminaliIt is the multiple
User terminal uses the weight of the time interval of the single application program.
In some embodiments, recommendation computing module 306 is calculated by the following formula to obtain U' respectivelyIUF、F'IUFWith
I'IUF:
Wherein, UiThe number of single application program, F are used for each user terminaliIt is single using this for each user terminal
The flow number of application program consumption, IiThe time interval of the single application program is used for each user terminal, N is to use to be somebody's turn to do
The total number of users of single application program;The number average value of the single application program is used for all user terminals of monitoring,The flow number average value of the single application program is used for all user terminals of monitoring,It is whole for all users of monitoring
End uses the time-interval averaging value of the single application program.
In some embodiments, recommendation computing module 306 is calculated by the following formula to obtain respectivelyWith
Wherein, M is the quantity of the user terminal monitored.
In some embodiments, application class module 308 can be used for according to applicating category belonging to application program, to
The application program that family terminal uses is classified, and calculate application program under each applicating category using recommendation
With the classification that is applied recommendation determines the applicating category that the user is had a preference for according to the applicating category recommendation.
In some embodiments, can be used for that it is whole to calculate all users for each application program using selecting module 310
End uses the sum using recommendation of the application program, obtains the whole network recommendation of the application program.
In some embodiments, the applicating category that can be used for being had a preference for according to determining user using pushing module 312,
Temporary original application program in the applicating category of single user's preference is selected, user is established and recommends association table;Wherein,
It includes that corresponding with the user terminal temporarily original the whole network recommendation is in the top answers that the user, which recommends association table,
Use program;And the application program in association table is recommended to recommend the user terminal user.
The recommended method and system of the application program of the embodiment of the present disclosure can include at least following advantages:
(1) recommended method of the application program of the embodiment of the present disclosure and system rely on the technical advantage of operator, by network
Side obtains the use information of terminal applies, and application message is additionally installed without terminal and obtains/monitor APP, scheme promotes difficulty ratio
It is smaller;Operator can get whole network data, and the acquisition of data is not limited to substantially by terminal.
(2) service condition applied with the index characterization of some dimensions, and by the service condition of a certain application of user and entirely
Network users use the service condition lateral comparison of the application, can more accurately determine user to the preference degree of the application, avoid
In the prior art it cannot accurately confirm that user is inclined using situation according only to a certain user using caused by difference as each
The case where applicating category of love.
(3) recommended method of the application program of the embodiment of the present disclosure and the prior art according to downloading of all categories or installation
Scheme to determine popular application is different, and the technical solution of the embodiment of the present disclosure determines in such a way that each user's recommendation is added
The whole network recommendation of a certain application the number of user installation is considered, it is contemplated that each user is used for preference degree;?
The application program of installation can no longer recommend, more accurate using recommending, and avoid bothering user.
Fig. 4 is the structure chart for schematically showing the recommender system of the application program according to the disclosure other embodiments.
The recommender system includes memory 410 and processor 420.Wherein:
Memory 410 can be disk, flash memory or other any non-volatile memory mediums.Memory is for storing Fig. 1
Instruction in corresponding embodiment.
Processor 420 is coupled to memory 410, can be used as one or more integrated circuits to implement, such as micro process
Device or microcontroller.The processor 420 is for executing the instruction stored in memory, so as to than accurately pushing away to user
Recommend application program.
It in one embodiment, can be as shown in figure 5, the recommender system 500 includes memory 510 and processor 520.
Processor 520 is coupled to memory 510 by BUS bus 530.The recommender system 500 can also be connected by memory interface 540
To external memory 550 to call external data, network or one other can also be connected to by network interface 560
Computer system (not shown), no longer describes in detail herein.
In this embodiment, it is instructed by memory stores data, then above-metioned instruction is handled by processor, so as to
Than accurately recommending application program to user.
In another embodiment, the disclosure additionally provides a kind of computer readable storage medium, is stored thereon with calculating
The step of machine program instruction, which realizes the method in embodiment corresponding to Fig. 1 when being executed by processor.Skill in the art
Art personnel are it should be appreciated that embodiment of the disclosure can provide as method, apparatus or computer program product.Therefore, the disclosure can adopt
With the form of complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects.Moreover, this public affairs
Opening, which can be used, can use non-transient storage medium in the computer that one or more wherein includes computer usable program code
The form for the computer program product implemented in (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.).
The disclosure is reference according to the method for the embodiment of the present disclosure, the flow chart of equipment (system) and computer program product
And/or block diagram describes.It should be understood that each process in flowchart and/or the block diagram can be realized by computer program instructions
And/or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer programs to refer to
Enable the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to generate
One machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
So far, the disclosure is described in detail.In order to avoid covering the design of the disclosure, it is public that this field institute is not described
The some details known.Those skilled in the art as described above, completely it can be appreciated how implementing technology disclosed herein
Scheme.
Disclosed method and system may be achieved in many ways.For example, can by software, hardware, firmware or
Software, hardware, firmware any combination realize disclosed method and system.The said sequence of the step of for the method
Merely to be illustrated, the step of disclosed method, is not limited to sequence described in detail above, special unless otherwise
It does not mentionlet alone bright.
Although being described in detail by some specific embodiments of the example to the disclosure, the skill of this field
Art personnel it should be understood that above example merely to be illustrated, rather than in order to limit the scope of the present disclosure.The skill of this field
Art personnel are it should be understood that can modify to above embodiments in the case where not departing from the scope of the present disclosure and spirit.This public affairs
The range opened is defined by the following claims.
Claims (18)
1. a kind of recommended method of application program, comprising:
Network packet is obtained in network side, the network packet is parsed, and multiple user terminals are calculated
Each user terminal uses time interval, number and the flow number of each application program in multiple application programs;
Each application program in the multiple application program is used according to each user terminal of the multiple user terminal
Each user terminal is calculated in time interval, number and flow number is recommended using the application of each application program
Degree;
The applicating category that the user's preferences are determined using recommendation of each application program is used according to the user terminal;
It is calculated according to each user terminal of the multiple user terminal using the application recommendation of each application program
To the whole network recommendation of each application program, and the whole network recommendation according to each application program, it obtains described
The recommendation of application program under applicating category sorts;And
It is sorted according to the recommendation of the application program under the applicating category and recommends application program to the user terminal.
2. obtain network packet in network side according to the method described in claim 1, wherein, to the network packet into
Row parsing, and each user terminal that multiple user terminals are calculated uses each application program in multiple application programs
The step of all time intervals, number and flow number includes:
The network packet of user terminal is obtained in network side, by parsing the network packet, obtains the network data
The purpose uniform resource position mark URL of packet, time started, end time, uninterrupted, type of service coding, server network
Protocol IP address and apply characteristic information;
According to the purpose URL, type of service coding, server ip address and characteristic information is applied to determine user terminal access
Application program or the corresponding function of the application program;It is obtained at the beginning of according to the network packet with the end time
Access the time interval and access times of the application program;And the flow information used is obtained according to the uninterrupted;
And
The user terminal, which is calculated, according to the time interval, access times and the flow information that access the application program uses institute
State all time intervals, the number using the application program and the flow number that generates using the application program of application program
Value.
3. according to the method described in claim 1, wherein,
Calculate the application recommendation R of each application programiFormula are as follows:
Ri=WuU′IUF+WfF′IUF-WiI′IUF,
Wherein, U 'IUFThe standardized value of the number of single application program, F ' are used for the multiple user terminalIUFIt is described more
Standardized value of a user terminal using the flow number of the single application program, I 'IUFFor the use of the multiple user terminal
The standardized value of the time interval of the single application program, WuThe single application program is used for the multiple user terminal
Number weight, WfThe weight of the flow number of the single application program, W are used for the multiple user terminaliIt is described
Multiple user terminals use the weight of the time interval of the single application program.
4. according to the method described in claim 3, wherein,
It is calculated by the following formula to obtain the U ' respectivelyIUF, the F 'IUFWith the I 'IUF:
Wherein, UiThe number of the single application program, F are used for each user terminaliMake for each user terminal
With the flow number of the single application program consumption, IiFor each user terminal using the single application program when
Between be spaced, N is the total number of users using the single application program;For monitoring all user terminals use it is described single
The number average value of application program,It is flat using the flow number of the single application program for all user terminals of monitoring
Mean value,The time-interval averaging value of the single application program is used for all user terminals of monitoring.
5. according to the method described in claim 4, wherein,
It is calculated by the following formula to obtain respectively describedIt is describedWith it is described
Wherein, M is the quantity of the user terminal monitored.
6. according to the method described in claim 1, wherein, the application of each application program is used according to the user terminal
Recommendation determines that the step of applicating category of the user's preferences includes:
According to applicating category belonging to application program, classify to the application program that user terminal uses, and calculates each
The sum using recommendation of application program under applicating category, the classification that is applied recommendation are recommended according to the applicating category
Spend the applicating category for determining that the user is had a preference for.
7. according to the method described in claim 1, wherein, being used according to each user terminal of the multiple user terminal each
The step of the whole network recommendation that the application program is calculated using recommendation of the application program includes:
For each application program, the sum using recommendation that all user terminals use the application program is calculated, this is obtained and answers
With the whole network recommendation of program.
8. according to the method described in claim 1, wherein, being sorted according to the recommendation of the application program under the applicating category
Include: to the step of user terminal recommendation application program
According to the applicating category that determining user is had a preference for, temporarily original in the applicating category of single user's preference answer is selected
With program, establishes user and recommend association table;Wherein, the user recommends the association table to include and the user terminal pair
The temporary original the whole network recommendation answered application program in the top;And
The application program in association table is recommended to recommend the user terminal user.
9. a kind of recommender system of application program, comprising:
Acquisition module, for obtaining network packet in network side;
Identification module, for parsing to the network packet, and each user that multiple user terminals are calculated is whole
End uses time interval, number and the flow number of each application program in multiple application programs;
Recommendation computing module, for using the multiple application program according to each user terminal of the multiple user terminal
In each application program time interval, number and flow number be calculated each user terminal use it is each described
The application recommendation of application program;
Application class module, for determining the use using the application recommendation of each application program according to the user terminal
The applicating category of family preference;
Using selecting module, for using each application program according to each user terminal of the multiple user terminal
The whole network recommendation of each application program is calculated using recommendation, and the whole network according to each application program pushes away
Degree of recommending obtains the recommendation sequence of the application program under the applicating category;And
Using pushing module, for being sorted according to the recommendation of the application program under the applicating category to the user terminal
Recommend application program.
10. system according to claim 9, wherein
The acquisition module is used to obtain the network packet of user terminal in network side;
The identification module is used for by parsing the network packet, and the purpose unified resource for obtaining the network packet is fixed
Position symbol URL, time started, end time, uninterrupted, type of service coding, server network Protocol IP address and application
Characteristic information;According to the purpose URL, type of service coding, server ip address and characteristic information is applied to determine user's end
Hold the application program or the corresponding function of the application program of access;At the beginning of according to the network packet at the end of
Between obtain the time interval and access times for accessing the application program;And the flow used is obtained according to the uninterrupted
Information;And the user terminal is calculated according to the time interval, access times and the flow information that access the application program
It is generated using all time intervals of the application program, using the number of the application program and using the application program
Flow number.
11. system according to claim 9, wherein
The recommendation computing module calculates the application recommendation R of each application programiFormula are as follows:
Ri=WuU′IUF+WfF′IUF-WiI′IUF,
Wherein, U 'IUFThe standardized value of the number of single application program, F ' are used for the multiple user terminalIUFIt is described more
Standardized value of a user terminal using the flow number of the single application program, I 'IUFFor the use of the multiple user terminal
The standardized value of the time interval of the single application program, WuThe single application program is used for the multiple user terminal
Number weight, WfThe weight of the flow number of the single application program, W are used for the multiple user terminaliIt is described
Multiple user terminals use the weight of the time interval of the single application program.
12. system according to claim 11, wherein
The recommendation computing module is calculated by the following formula to obtain the U ' respectivelyIUF, the F 'IUFWith the I 'IUF:
Wherein, UiThe number of the single application program, F are used for each user terminaliMake for each user terminal
With the flow number of the single application program consumption, IiFor each user terminal using the single application program when
Between be spaced, N is the total number of users using the single application program;For monitoring all user terminals use it is described single
The number average value of application program,It is average using the flow number of the single application program for all user terminals of monitoring
Value,The time-interval averaging value of the single application program is used for all user terminals of monitoring.
13. system according to claim 12, wherein
The recommendation computing module is calculated by the following formula to obtain respectively describedIt is describedWith it is described
Wherein, M is the quantity of the user terminal monitored.
14. system according to claim 9, wherein
The application class module is used for according to applicating category belonging to application program, the application program that user terminal is used into
Row classification, and calculate the sum using recommendation of the application program under each applicating category, the classification that is applied recommendation, root
The applicating category that the user is had a preference for is determined according to the applicating category recommendation.
15. system according to claim 9, wherein
The application selecting module is used to calculate each application program the application that all user terminals use the application program
The sum of recommendation obtains the whole network recommendation of the application program.
16. system according to claim 9, wherein
The applicating category for being used to be had a preference for according to determining user using pushing module, selects the application of single user's preference
Temporary original application program in classification establishes user and recommends association table;Wherein, the user recommends association table
Include temporarily original the whole network recommendation application program in the top corresponding with the user terminal;And by the use
The application program in association table is recommended to recommend the user terminal in family.
17. a kind of recommender system of application program, comprising:
Memory;And
It is coupled to the processor of the memory, the processor is configured to based on the instruction execution for being stored in the memory
Method as described in claim 1 to 8 any one.
18. a kind of computer readable storage medium, is stored thereon with computer program instructions, real when which is executed by processor
Now the step of method as described in claim 1 to 8 any one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711016613.4A CN109714378A (en) | 2017-10-26 | 2017-10-26 | The recommended method and system of application program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711016613.4A CN109714378A (en) | 2017-10-26 | 2017-10-26 | The recommended method and system of application program |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109714378A true CN109714378A (en) | 2019-05-03 |
Family
ID=66253021
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711016613.4A Pending CN109714378A (en) | 2017-10-26 | 2017-10-26 | The recommended method and system of application program |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109714378A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114760622A (en) * | 2022-04-20 | 2022-07-15 | 四川酷比通信设备有限公司 | Activity-based software preloading method, terminal and preloading system |
WO2023286019A1 (en) * | 2021-07-16 | 2023-01-19 | Atphizyom Limited | Investment platform |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104504149A (en) * | 2015-01-08 | 2015-04-08 | 中国联合网络通信集团有限公司 | Application recommendation method and device |
CN104750807A (en) * | 2015-03-25 | 2015-07-01 | 百度在线网络技术(北京)有限公司 | Application recommending method and device |
CN105227445A (en) * | 2015-10-23 | 2016-01-06 | 中国联合网络通信集团有限公司 | Platform is recommended in application recommend method and application |
WO2018227334A1 (en) * | 2017-06-12 | 2018-12-20 | 深圳市乃斯网络科技有限公司 | Housing source recommendation method and system for second-hand house app |
-
2017
- 2017-10-26 CN CN201711016613.4A patent/CN109714378A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104504149A (en) * | 2015-01-08 | 2015-04-08 | 中国联合网络通信集团有限公司 | Application recommendation method and device |
CN104750807A (en) * | 2015-03-25 | 2015-07-01 | 百度在线网络技术(北京)有限公司 | Application recommending method and device |
CN105227445A (en) * | 2015-10-23 | 2016-01-06 | 中国联合网络通信集团有限公司 | Platform is recommended in application recommend method and application |
WO2018227334A1 (en) * | 2017-06-12 | 2018-12-20 | 深圳市乃斯网络科技有限公司 | Housing source recommendation method and system for second-hand house app |
Non-Patent Citations (1)
Title |
---|
东彻: ""数据标准化方法"", 《百度文库》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023286019A1 (en) * | 2021-07-16 | 2023-01-19 | Atphizyom Limited | Investment platform |
CN114760622A (en) * | 2022-04-20 | 2022-07-15 | 四川酷比通信设备有限公司 | Activity-based software preloading method, terminal and preloading system |
CN114760622B (en) * | 2022-04-20 | 2023-09-26 | 四川酷比通信设备有限公司 | Software preloading method, terminal and preloading system based on liveness |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104765751B (en) | Using recommended method and device | |
CN102801817B (en) | Subscriber context-based pushing method and device | |
CN107786601B (en) | Information processing method, terminal and server | |
CN103530175B (en) | The classification processing method and device of application program | |
CN103607691A (en) | Flow package recommendation method and device | |
WO2012075898A1 (en) | Method and device for automatic classification of applications in mobile terminal | |
CN108920675A (en) | A kind of method, apparatus of information processing, computer storage medium and terminal | |
CN102158541B (en) | Shared information acquisition method, device, mobile terminal and server | |
CN104216698B (en) | A kind of registration web page method and relevant apparatus | |
Mitra et al. | QoE modelling, measurement and prediction: A review | |
CN103905482B (en) | Method, push server and the system of pushed information | |
CN104918203B (en) | The based reminding method and device of mobile subscriber's online residual flow | |
CN106202465B (en) | A kind of method for pushing of terminal wallpaper, device and mobile terminal | |
CN106162805A (en) | The connection control method of WIFI hot spot service and device | |
CN105187514B (en) | The management method and its system of cloud application program | |
CN109714378A (en) | The recommended method and system of application program | |
CN109408737B (en) | User recommendation method, device and storage medium | |
CN104540109A (en) | Method and device for pushing information during call | |
CN106528066B (en) | Business process operation method and device | |
CN113037510A (en) | Charging method, charging device and computer readable storage medium | |
CN103634470A (en) | Human-computer interaction prediction method based on terminal mobile data access network Qos | |
CN102804176A (en) | Method and arrangement in a communication network | |
CN109829033A (en) | Method for exhibiting data and terminal device | |
CN107643858A (en) | A kind of information processing method, terminal and server | |
CN110377838A (en) | Recruitment data recommendation method and its device on block chain |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190503 |