CN106846094A - A kind of method and apparatus for recommending application message based on application has been installed - Google Patents
A kind of method and apparatus for recommending application message based on application has been installed Download PDFInfo
- Publication number
- CN106846094A CN106846094A CN201611242501.6A CN201611242501A CN106846094A CN 106846094 A CN106846094 A CN 106846094A CN 201611242501 A CN201611242501 A CN 201611242501A CN 106846094 A CN106846094 A CN 106846094A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- expression
- application
- users
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
- G06Q30/0627—Directed, with specific intent or strategy using item specifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention provides a kind of method and apparatus for recommending application message based on application has been installed.Methods described includes:Determine that user has been installed using the similarity from the different information in information flow storehouse;Obtained similarity is utilized to obtain matching degree of the user to different information;A number of information is chosen according to matching degree order from big to small to recommend to user as candidate information and by matching degree descending order.
Description
Technical field
The present invention relates to technical field of information processing, recommended using letter based on application has been installed in particular to one kind
The method and apparatus of breath.
Background technology
With the fast development of Internet technology and intelligent mobile terminal technology, the work(much realized on computer terminals
(can for example do shopping, read) can also realize on intelligent mobile terminal, for example, use smart mobile phone or panel computer etc..Separately
Outward, the realization of these functions needs to install corresponding application program on intelligent mobile terminal.For example, shopping online is, it is necessary to pacify
Dress such as Taobao's client, listens music to need to install music player client etc..Thus, many software companys provide application
Shop or application market, such as pea pods or PP assistant etc..User can be opened using shop or application market, so as to
Various application programs required for enough fast searchs and download, including audio-visual broadcast message class, system tool class, the social class of communication, net
Upper shopping class, reading class etc., certainly can be with amusement and recreation class application program such as download games (APP).
In order to constantly lift good experience sense of the user using application shop or application market, current developer develops
The function that many convenient users are used, one of them is recommendation function, i.e., recommend some to apply to user, to help user to find
More applications interested.Applied for how to show to user, traditional way is that application is exposed directly to user, is such as schemed
Shown in 1A.This way is direct to be worked as, but there is major defect:Lack the introduction to recommending application.When user sees
During a unknown application, because without detailed introduction, most users can be short in understanding without producing because of to it
Click on and download behavior.In order to solve this problem, a kind of new Application issuance mode is occurred in that at present:Increase in application shop
Information flow, is introduced and promoted, as illustrated in figures ib and 1 c by interesting article, video to application.
But, for this application shop by way of information flow issues application, during to user's recommendation information,
Because different users has different interest, so needing to consider to recommend different application messages to different user, this is just right
Targetedly precisely recommend to propose very high request, what is otherwise shown to user is not his application interested, it will significantly
Reduce the experience sense of user.
The content of the invention
It is an object of the invention to provide a kind of method and apparatus for recommending application message based on application has been installed, to change
Kind above mentioned problem.
A kind of method for recommending application message based on application has been installed is the embodiment of the invention provides, including:
Determine that user has been installed using the similarity from the different information in information flow storehouse;
Obtained similarity is utilized to obtain matching degree of the user to different information;
According to matching degree order from big to small choose a number of information as candidate information and by matching degree from
Small order is arrived greatly to recommend to user.
Preferably, corresponding information is chosen from candidate information according to predetermined information quality rule to recommend to user.
The embodiment of the present invention additionally provide it is a kind of based on having installed using recommending the device of application message, including:
Similarity determining unit, for determining that user has been installed using the similarity from the different information in information flow storehouse;
Matching degree determining unit, matching degree of the user to different information is obtained for utilizing obtained similarity;
Unit is chosen, a number of information is chosen as candidate information for the order according to matching degree from big to small;
Recommendation unit, for by matching degree descending order to user's recommended candidate information.
Preferably, the recommendation unit can be also used for choosing phase from candidate information according to predetermined information quality rule
Information is answered to recommend to user.
Wherein, the similarity is calculated using following equation:
Wherein:
si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., n j=1,2 ..., m,
bi,jThe number of users of information j was clicked in expression in the user using i has been installed, i=1,2 ..., n j=1,
2 ..., m,
aiThe number of users using i has been installed in expression, i=1,2 ..., n,
KiThe set of the label included using i has been installed in expression, i=1,2 ..., n,
LjThe set of the label that expression information j is included, j=1,2 ..., m;
N represents that certain user keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
N is the integer more than 0.
Wherein, the matching degree is calculated using following equation:
Wherein:
ujRepresent matching degree of certain user to information j, j=1,2 ..., m,
oiRepresent certain user to application i interest-degree, i=1,2 ..., n,
si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., nj=1,2 ..., m,
N represents that certain user keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
Interest-degree o of certain the described user to application iiComputational methods it is as follows:
tiRepresent the last number of days installed using i and remain to today of certain user, i=1,2 ..., n;
N represents that certain user keeps the quantity of the application of installation in N days to today;
N is the integer more than 0.
Wherein, it is described that the mistake that corresponding information is recommended to user is chosen from candidate information according to predetermined information quality rule
Journey is as described below:One of clicking rate, thumb up rate and conversion ratio according to candidate information or according to arbitrarily two-by-two parameter combination,
Or the comprehensive quality desired value calculated according to three parameters, choose phase by comprehensive quality desired value order from big to small
Information is answered to recommend to user, wherein the computational methods of the comprehensive quality desired value are:
qulj=θ * ctrj+γ*gtrj+β*dtrjJ=1,2 ..., m
Wherein:
quljThe comprehensive quality index of expression information j, j=1,2 ..., m,
ctrjThe clicking rate of expression information j, j=1,2 ..., m,
gtrjThe thumb up rate of expression information j, j=1,2 ..., m,
dtrjThe conversion ratio of expression information j, j=1,2 ..., m,
M represents the information content in information flow storehouse;
θ, γ and β are the weights for adjusting each factor, wherein β+γ+θ=1, and β, γ and θ ∈ [0,1], by taking
β, γ and θ different value determine to calculate the comprehensive quality desired value by those parameter indexs;
The clicking rate of described information j
cjThe number of users of information j was clicked in expression;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The thumb up rate of described information j
gjRepresent that thumb up crosses the number of users of information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The conversion ratio of described information j
djRepresent and produce the number of users for downloading application behavior by information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse.
It is of the invention to have taken into full account user's come the method and apparatus for recommending application message based on application has been installed
Interest and hobby, by determining to have installed the similarity using from the different information in information flow storehouse, then determine user to not
With the matching degree of information, so as to select a number of candidate information, can be pushed away to user by matching degree descending order
Recommend corresponding candidate information, it is also possible to suitable information is chosen from these candidate informations according to quality indicator message and is pushed away to user
Recommend, this different application information that can be recommended according to the hobby of different user difference, so as to realize personalized recommendation, this
Greatly improve the experience sense of user.
Brief description of the drawings
Figure 1A is the example sectional drawing that application is recommended in existing application shop;
Figure 1B is the example sectional drawing that application is recommended in existing application shop using message stream mode;
Fig. 1 C are an example sectional drawings of the details page of an information of information flow;
Fig. 2 is provided in an embodiment of the present invention based on having installed using recommending the flow chart of the method for application message;
Fig. 3 is click on an information of information flow and opens the example sectional drawing that correspondence is applied;
Fig. 4 is provided in an embodiment of the present invention based on having installed using recommending the schematic frame of the device of application message
Figure.
Specific embodiment
Below in conjunction with the embodiment of the present invention and accompanying drawing, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground description, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Generally herein
The component of the embodiment of the present invention described and illustrated in place's accompanying drawing can be arranged and designed with a variety of configurations.Therefore,
The detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit the model of claimed invention below
Enclose, but be merely representative of selected embodiment of the invention.Based on embodiments of the invention, those skilled in the art are not making
The every other embodiment obtained on the premise of creative work, belongs to the scope of protection of the invention.
Fig. 2 is provided in an embodiment of the present invention based on having installed using recommending the flow chart of the method for application message.It is false
If certain user A is clicked to enter using the information flow column in shop in the terminal that it is used, now need to recommend one to user A
Criticize application message, it is possible to use the method for recommending application message based on application has been installed of the invention as shown in Figure 2, the party
Method is comprised the following steps:
S1:Determine that user has been installed using the similarity from the different information in information flow storehouse.
Application of having installed described here refers to have pacified in the terminal that user uses when application message is recommended to user
The application being filled with.
Generally it can be thought that, that is installed in the terminal such as such as smart mobile phone or panel computer that user uses or computer is each
Kind application, such as game class, leisure, office class, are user applications interested, and are based on user and have installed application to push away
Degree of association application message high is recommended, then recommends its application message interested for different user, realize personalized recommendation
Purpose.
How the application message applied to recommend the degree of association high has so been installed based on userUser will be determined first
Install using the similarity from the different information in information flow storehouse.Concrete methods of realizing is as follows:
Each application can include the label of 1-3 or more in application shop or application market, and these labels are used
In the type belonging to mark application, it is possible thereby to the interest by judging user using the label having, i.e., known by label
Other user has installed the classification of application to judge the interest of user.For the information in information flow storehouse, it is also possible to by the information
The label that the application promoted has is used as the type belonging to the information, as shown in figure 3, for example opening the application that information is promoted
" Himalaya ", it can be seen that the details of application " Himalaya ", bottom position is that 2 labels that the application has are " new
Hear and read " and " listening to storytelling ".The present invention be namely based on whether the method with identical label, installed according to user using seeking
The application message that the degree of association is high is looked for, user is then calculated and has been installed using the similarity from the different information in information flow storehouse.
From the foregoing, user described here has installed to apply includes that user downloads peace by application shop or application market
The application of dress and the application that can be found in application shop or application market.Information flow storehouse is application and development shop or application
Preset during market, the information in storehouse can update often.
It refer to just label that the set of label included using i is included with another information j with same label
Set has occurs simultaneously.
User is calculated using following equation to have installed using the similarity from the different information in information flow storehouse:
Wherein:
Si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., n j=1,2 ..., m,
bi,jThe number of users of information j was clicked in expression in the user using i has been installed, i=1,2 ..., n j=1,
2 ..., m,
aiThe number of users using i has been installed in expression, i=1,2 ..., n,
KiThe set of the label included using i has been installed in expression, i=1,2 ..., n,
LjThe set of the label that expression information j is included, j=1,2 ..., m;
N represents that certain user keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
N is the integer more than 0.
The formula represent be meant that when installed there is no same label using i and information j when, its similarity is 0;When having
It is that similarity is the number of users of information j to be clicked in the user using i has been installed and has been installed using i during same label
The ratio of number of users, the ratio is bigger, and similarity is higher.
N represents that certain user keeps being meant that for the quantity of the application installed in N days to today:As upper
State like that, when preparing to recommend a collection of application message to certain user A, first carry out this method and find recommendation information, now count
The quantity of the application being installed with the terminal that the user A is just being used.When the N for representing number of days is sufficiently large, the installation of statistics should
Quantity is exactly the quantity of the whole applications installed in terminal, preferably refers to third-party application;N can certainly be set as
Specific limited number of days, such as 60 days, 90 days etc..
S2:Obtained similarity is utilized to obtain matching degree of the user to different information.
Installed using from after the similarity of the different information in information flow storehouse user is obtained, used due to user
Multiple applications can be usually installed it is necessary to determine matching degrees of the user A to different information from the plurality of application in terminal, so as to
Find matching degree information high.
The matching degree is calculated using following equation:
Wherein:
ujRepresent matching degrees of certain user A to information j, j=1,2 ..., m,
oiRepresent certain user A to application i interest-degree, i=1,2 ..., n,
si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., nj=1,2 ..., m,
N represents that certain user A keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
N is the integer more than 0.
The formula is represented and is meant that:User is multiplied by this to the interest-degree installed using i similar to information using i
Degree, then determines matching degree of the user to different information by way of superposition.
Here n is identical with the n in step S1, no longer does repeated explanation.
And certain described user A is to the interest-degree o of application iiComputational methods it is as follows:
tiRepresent the last number of days installed using i and remain to today of certain user A, i=1,2 ..., n;
N represents that certain user A keeps the quantity of the application of installation in N days to today;
N is the integer more than 0, and it represents number of days.
Interest-degree oiIt is meant that the interest for considering user can be changed over time, the time gap of user installation application is present
It is nearer, can more represent the present interest of user.
Here n is identical with the n in step S1, no longer does repeated explanation.
tiRepresent certain user A it is the last install using i and the number of days for remaining to today be meant that:From user A
The last time is mounted with to start using that day of i and midway did not unload but was maintained in the terminal that user is just using
In, until the number of days of today.
S3:A number of information is chosen as candidate information and by matching degree according to matching degree order from big to small
Descending order is recommended to user.
After obtained matching degrees of the user A to different information, the size according to matching angle value chooses ranking above
A number of information as user candidate information interested.For example, choosing corresponding letter of the matching degree ranking at first 50
Breath, or ranking is in first 100 corresponding information etc..Then can recommend to user by matching degree descending order corresponding
Candidate information.
In a preferred embodiment, in order to further recommend its application message interested to user, realize more smart
True personalized recommendation, it is of the invention to include step come the method for recommending application message based on application has been installed:
S4:Corresponding information is chosen from candidate information according to predetermined information quality rule to recommend to user.
The predetermined information quality rule can be to determine the comprehensive quality desired value of information, and comprehensive quality index can
Being one of clicking rate, thumb up rate and conversion ratio of candidate information, or according between clicking rate, thumb up rate and conversion ratio
The comprehensive quality desired value of the candidate information that any combination of two is calculated or according to clicking rate, thumb up rate and conversion ratio this
The comprehensive quality desired value of the candidate information that three parameters are calculated, phase is chosen by comprehensive quality desired value order from big to small
Information is answered to recommend to user.
Specifically, according to candidate information one of clicking rate, thumb up rate and conversion ratio or according to appointing between them
Meaning combination of two or calculates comprehensive quality desired value according to three parameters, by comprehensive quality desired value from big to small
Order is chosen corresponding information and is recommended to user, wherein the computational methods of the comprehensive quality desired value are:
qulj=θ * ctrj+γ*gtrj+β*dtrjJ=1,2 ..., m
Wherein:
quljThe comprehensive quality index of expression information j, j=1,2 ..., m,
ctrjThe clicking rate of expression information j, j=1,2 ..., m,
gtrjThe thumb up rate of expression information j, j=1,2 ..., m,
dtrjThe conversion ratio of expression information j, j=1,2 ..., m,
M represents the information content in information flow storehouse;
θ, γ and β are the weights for adjusting each factor, wherein β+γ+θ=1, and β, γ and θ ∈ [0,1], by taking
β, γ and θ different value determine to calculate the comprehensive quality desired value by those parameter indexs;
The clicking rate of described information j
cjThe number of users of information j was clicked in expression;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The thumb up rate of described information j
gjRepresent that thumb up crosses the number of users of information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The conversion ratio of described information j
djRepresent and produce the number of users for downloading application behavior by information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse.
Above-mentioned formula considers the factor of the clicking rate of candidate information, thumb up rate and conversion ratio as scaling information quality,
The weight of each factor is adjusted by θ, γ and β, using according to putting into practice needs stress which 1 or 2 factor as quality considered
Principal measure factor.Described in detail below by citing.
β+γ+θ=1, and β, γ and θ ∈ [0,1], when θ=1, γ=0 and β=0, then the comprehensive quality of candidate information
Index is the clicking rate of the information, and when θ=0, γ=1 and β=0, then the comprehensive quality index of candidate information is the information
Thumb up rate, when θ=0, γ=0 and β=1, then the comprehensive quality index of candidate information is the conversion ratio of the information;When θ=
0.5th, γ=0.5 and β=0 (θ and γ can also negated 0 other values, and when meeting θ+γ=1), candidate information it is comprehensive
Close the combination of clicking rate and thumb up rate that quality index is the information to consider, it is also possible to allow θ=0, γ=0.5 and β=0.5 (γ
With β can also negated 0 other values, and meet γ+β=1, or (θ and β can also θ=0.5, γ=0 and β=0.5
Negated 0 other values, and meet θ+β=1), by that analogy, other combination of two can also be chosen, no longer illustrate here;
If this 3 kinds of factors are considered simultaneously, β+γ+θ=1, and β, γ and θ ∈ (0,1), i.e. β, γ and θ are not 0 and 1, when recognizing
For certain factor as quality principal measure factor when, the weighted value of the factor can be made bigger, such as θ=0.5, γ=
0.3 and β=0.2, now think clicking rate be as the principal measure factor of the quality index of candidate information, thumb up rate secondly,
Conversion ratio comes finally;By that analogy, it is also possible to choose different β, γ and θ values to enumerate clicking rate, thumb up rate and conversion ratio
As the tandem of the principal measure factor of the quality index of candidate information, naturally it is also possible to so that clicking rate, thumb up rate and
Conversion ratio is of equal importance as the factor of measurement, here no longer citing description.
It is of the invention based on having installed using the interest for having taken into full account the method for recommending application message user and
Hobby, by determining to have installed the similarity using from the different information in information flow storehouse, then determines user to different information
Matching degree, so as to select a number of candidate information, can recommend to user by matching degree descending order corresponding
Candidate information, it is also possible to according to quality indicator message chosen from these candidate informations suitable information to user recommend, this
The different application information for can be different according to the hobby of different user and recommending, so as to realize personalized recommendation, this is significantly
Improve the experience sense of user.
Fig. 4 is provided in an embodiment of the present invention based on having installed using recommending the schematic frame of the device of application message
Figure.As shown in figure 4, of the invention included based on application has been installed come the device for recommending application message:
Similarity determining unit, for determining that user has been installed using the similarity from the different information in information flow storehouse;
Matching degree determining unit, matching degree of the user to different information is obtained for utilizing obtained similarity;
Unit is chosen, a number of information is chosen as candidate information for the order according to matching degree from big to small;
Recommendation unit, for by matching degree descending order to user's recommended candidate information.
In a preferred scheme, the similarity determining unit calculates the similarity using following equation:
Wherein:
si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., n j=1,2 ..., m,
bi,jThe number of users of information j was clicked in expression in the user using i has been installed, i=1,2 ..., n j=1,
2 ..., m,
aiThe number of users using i has been installed in expression, i=1,2 ..., n,
KiThe set of the label included using i has been installed in expression, i=1,2 ..., n,
LjThe set of the label that expression information j is included, j=1,2 ..., m;
N represents that certain user keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
N is the integer more than 0.
In a preferred scheme, the matching degree determining unit calculates the matching degree using following equation:
Wherein:
ujRepresent matching degree of certain user to information j, j=1,2 ..., m,
oiRepresent certain user to application i interest-degree, i=1,2 ..., n,
si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., n j=1,2 ..., m,
N represents that certain user keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
Interest-degree o of certain the described user to application iiComputational methods it is as follows:
tiRepresent the last number of days installed using i and remain to today of certain user, i=1,2 ..., n;
N represents that certain user keeps the quantity of the application of installation in N days to today;
N is the integer more than 0.
In a preferred embodiment, in order to further recommend its application message interested to user, realize more smart
True personalized recommendation, it is of the invention based on having installed using may be used also come the recommendation unit in the device for recommending application message
Recommend to user for choosing corresponding information from candidate information according to predetermined information quality rule.
In a preferred scheme, in the recommendation unit, clicking rate, thumb up rate and conversion ratio according to candidate information
One of or according to arbitrarily parameter combination or the comprehensive quality desired value calculated according to three parameters two-by-two, by synthesis
Quality indicator value order from big to small is chosen corresponding information and is recommended to user, wherein the calculating side of the comprehensive quality desired value
Method is:
qulj=θ * ctrj+γ*gtrj+β*dtrjJ=1,2 ..., m
Wherein:
quljThe comprehensive quality index of expression information j, j=1,2 ..., m,
ctrjThe clicking rate of expression information j, j=1,2 ..., m,
gtrjThe thumb up rate of expression information j, j=1,2 ..., m,
dtrjThe conversion ratio of expression information j, j=1,2 ..., m,
M represents the information content in information flow storehouse;
θ, γ and β are the weights for adjusting each factor, wherein β+γ+θ=1, and β, γ and θ ∈ [0,1], by taking
β, γ and θ different value determine to calculate the comprehensive quality desired value by those parameter indexs;
The clicking rate of described information j
cjThe number of users of information j was clicked in expression;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The thumb up rate of described information j
gjRepresent that thumb up crosses the number of users of information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The conversion ratio of described information j
djRepresent and produce the number of users for downloading application behavior by information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse.
It is apparent to those skilled in the art that, for convenience and simplicity of description, the device of foregoing description
Specific work process, may be referred to the corresponding process in preceding method embodiment, row illustrated example in preceding method embodiment
And associated description, the course of work of interpreting means is equally applicable to, description is not repeated herein.
It is of the invention based on having installed using the interest for having taken into full account the device of recommending application message user and
Hobby, by determining to have installed the similarity using from the different information in information flow storehouse, then determines user to different information
Matching degree, so as to select a number of candidate information, can recommend to user by matching degree descending order corresponding
Candidate information, it is also possible to according to quality indicator message chosen from these candidate informations suitable information to user recommend, this
The different application information for can be different according to the hobby of different user and recommending, so as to realize personalized recommendation, this is significantly
Improve the experience sense of user.
What the embodiment of the present invention was provided is produced based on application has been installed come the computer program for recommending the method for application message
Product, including the computer-readable recording medium of program code is stored, before the instruction that described program code includes can be used to perform
Method described in the embodiment of the method for face, implements and can be found in embodiment of the method, will not be repeated here.
If the function is to realize in the form of SFU software functional unit and as independent production marketing or when using, can be with
Storage is in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used to so that a computer equipment (can be individual
People's computer, panel computer, smart mobile phone, server, or network equipment etc.) perform each embodiment methods described of the invention
All or part of step.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM), arbitrary access are deposited
Reservoir (RAM), magnetic disc or CD etc. are various can be with the medium of store program codes.
The above, specific embodiment only of the invention, but protection scope of the present invention is not limited thereto, and it is any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all contain
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of based on having installed using come the method for recommending application message, including:
Determine that user has been installed using the similarity from the different information in information flow storehouse;
Obtained similarity is utilized to obtain matching degree of the user to different information;
According to matching degree order from big to small choose a number of information as candidate information and by matching degree from greatly to
Small order is recommended to user.
2. method according to claim 1, it is characterised in that it is determined that user installed using with information flow storehouse in not
With information similarity the step of in, calculate the similarity using following equation:
Wherein:
si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., n j=1,2 ..., m,
bi,jThe number of users of information j was clicked in expression in the user using i has been installed, i=1,2 ..., n j=1,2 ..., m,
aiThe number of users using i has been installed in expression, i=1,2 ..., n,
KiThe set of the label included using i has been installed in expression, i=1,2 ..., n,
LjThe set of the label that expression information j is included, j=1,2 ..., m;
N represents that certain user keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
N is the integer more than 0.
3. method according to claim 1, it is characterised in that utilizing obtained similarity to obtain user to difference
In the step of matching degree of information, the matching degree is calculated using following equation:
Wherein:
ujRepresent matching degree of certain user to information j, j=1,2 ..., m,
oiRepresent certain user to application i interest-degree, i=1,2 ..., n,
si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., n j=1,2 ..., m,
N represents that certain user keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
Interest-degree o of certain the described user to applicationiComputational methods it is as follows:
tiRepresent the last number of days installed using i and remain to today of certain user, i=1,2 ..., n;
N represents that certain user keeps the quantity of the application of installation in N days to today;
N is the integer more than 0.
4. method according to claim 1, it is characterised in that also include:According to predetermined information quality rule from candidate's letter
Corresponding information is chosen in breath to recommend to user.
5. method according to claim 4, it is characterised in that according to predetermined information quality rule from candidate information
During corresponding information is chosen the step of recommend to user, one of clicking rate, thumb up rate and conversion ratio according to candidate information or root
According to arbitrarily parameter combination or the comprehensive quality desired value calculated according to three parameters two-by-two, by comprehensive quality desired value
Order from big to small is chosen corresponding information and is recommended to user, wherein the computational methods of the comprehensive quality desired value are:
qulj=θ * ctrj+γ*gtrj+β*dtrjJ=1,2 ..., m
Wherein:
quljThe comprehensive quality index of expression information j, j=1,2 ..., m,
ctrjThe clicking rate of expression information j, j=1,2 ..., m,
gtrjThe thumb up rate of expression information j, j=1,2 ..., m,
dtrjThe conversion ratio of expression information j, j=1,2 ..., m,
M represents the information content in information flow storehouse;
θ, γ and β are the weights for adjusting each factor, wherein β+γ+θ=1, and β, γ and θ ∈ [0,1], by taking β, γ
Determine to calculate the comprehensive quality desired value by those parameter indexs with θ different values;
The clicking rate of described information j
cjThe number of users of information j was clicked in expression;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The thumb up rate of described information j
gjRepresent that thumb up crosses the number of users of information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The conversion ratio of described information j
djRepresent and produce the number of users for downloading application behavior by information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse.
6. a kind of based on having installed using recommending the device of application message, including:
Similarity determining unit, for determining that user has been installed using the similarity from the different information in information flow storehouse;
Matching degree determining unit, matching degree of the user to different information is obtained for utilizing obtained similarity;
Unit is chosen, a number of information is chosen as candidate information for the order according to matching degree from big to small;
Recommendation unit, for by matching degree descending order to user's recommended candidate information.
7. device according to claim 6, it is characterised in that the similarity determining unit calculates institute using following equation
State similarity:
Wherein:
si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., n j=1,2 ..., m,
bi,jThe number of users of information j was clicked in expression in the user using i has been installed, i=1,2 ..., n j=1,2 ..., m,
aiThe number of users using i has been installed in expression, i=1,2 ..., n,
KiThe set of the label included using i has been installed in expression, i=1,2 ..., n,
LjThe set of the label that expression information j is included, j=1,2 ..., m;
N represents that certain user keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
N is the integer more than 0.
8. device according to claim 6, it is characterised in that the matching degree determining unit calculates institute using following equation
State matching degree:
Wherein:
ujRepresent matching degree of certain user to information j, j=1,2 ..., m,
oiRepresent certain user to application i interest-degree, i=1,2 ..., n,
si,jExpression has been installed using the similarity of i and information j, i=1,2 ..., n j=1,2 ..., m,
N represents that certain user keeps the quantity of the application of installation in N days to today;
M represents the information content in information flow storehouse;
Interest-degree o of certain the described user to applicationiComputational methods it is as follows:
tiRepresent the last number of days installed using i and remain to today of certain user, i=1,2 ..., n;
N represents that certain user keeps the quantity of the application of installation in N days to today;
N is the integer more than 0.
9. device according to claim 6, it is characterised in that the recommendation unit is additionally operable to according to predetermined information quality
Rule is chosen corresponding information from candidate information and is recommended to user.
10. device according to claim 9, it is characterised in that in the recommendation unit, according to the click of candidate information
One of rate, thumb up rate and conversion ratio or according to arbitrarily parameter combination or the synthesis calculated according to three parameters two-by-two
Quality indicator value, chooses corresponding information and recommends to user, wherein the synthesis by comprehensive quality desired value order from big to small
The computational methods of quality indicator value are:
qulj=θ * ctrj+γ*gtrj+β*dtrjJ=1,2 ..., m
Wherein:
quljThe comprehensive quality index of expression information j, j=1,2 ..., m,
ctrjThe clicking rate of expression information j, j=1,2 ..., m,
gtrjThe thumb up rate of expression information j, j=1,2 ..., m,
dtrjThe conversion ratio of expression information j, j=1,2 ..., m,
M represents the information content in information flow storehouse;
θ, γ and β are the weights for adjusting each factor, wherein β+γ+θ=1, and β, γ and θ ∈ [0,1], by taking β, γ
Determine to calculate the comprehensive quality desired value by those parameter indexs with θ different values;
The clicking rate of described information j
cjThe number of users of information j was clicked in expression;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The thumb up rate of described information j
gjRepresent that thumb up crosses the number of users of information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse;
The conversion ratio of described information j
djRepresent and produce the number of users for downloading application behavior by information j;
fjRepresent all numbers of users for showing information j to user;
M represents the information content in information flow storehouse.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611242501.6A CN106846094A (en) | 2016-12-29 | 2016-12-29 | A kind of method and apparatus for recommending application message based on application has been installed |
PCT/CN2017/119610 WO2018121700A1 (en) | 2016-12-29 | 2017-12-28 | Method and device for recommending application information based on installed application, terminal device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611242501.6A CN106846094A (en) | 2016-12-29 | 2016-12-29 | A kind of method and apparatus for recommending application message based on application has been installed |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106846094A true CN106846094A (en) | 2017-06-13 |
Family
ID=59113161
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611242501.6A Pending CN106846094A (en) | 2016-12-29 | 2016-12-29 | A kind of method and apparatus for recommending application message based on application has been installed |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106846094A (en) |
WO (1) | WO2018121700A1 (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108052671A (en) * | 2017-12-29 | 2018-05-18 | 北京奇虎科技有限公司 | A kind of method and system that content item push is carried out based on Dynamic Matching |
WO2018121700A1 (en) * | 2016-12-29 | 2018-07-05 | 广州优视网络科技有限公司 | Method and device for recommending application information based on installed application, terminal device, and storage medium |
WO2018149244A1 (en) * | 2017-02-20 | 2018-08-23 | 广州优视网络科技有限公司 | Method and device for recommending applications associated with target application on basis of target application |
CN108510352A (en) * | 2018-02-09 | 2018-09-07 | 广州优视网络科技有限公司 | Application issue recommends method, apparatus and computer equipment |
CN108769125A (en) * | 2018-04-28 | 2018-11-06 | 广州优视网络科技有限公司 | Using recommendation method, apparatus, storage medium and computer equipment |
CN108809987A (en) * | 2018-06-14 | 2018-11-13 | 广州任天游网络科技有限公司 | A kind of online game extension method based on big data analysis |
CN109242643A (en) * | 2018-09-30 | 2019-01-18 | 武汉斗鱼网络科技有限公司 | The method, apparatus and storage medium of game recommdation applied to live streaming platform |
CN110020152A (en) * | 2017-12-04 | 2019-07-16 | 中国移动通信集团终端有限公司 | Using recommended method and device |
CN110134410A (en) * | 2019-05-17 | 2019-08-16 | 北京百度网讯科技有限公司 | It is cold-started customized information correlating method, device and the storage medium of user |
CN111611143A (en) * | 2020-05-20 | 2020-09-01 | 浙江每日互动网络科技股份有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN111796883A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Device control method, device, storage medium and electronic device |
CN112328935A (en) * | 2020-10-29 | 2021-02-05 | 胡培培 | Application program pushing system and method based on big data |
CN115150346A (en) * | 2022-07-04 | 2022-10-04 | 中国银行股份有限公司 | Information pushing method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103679502A (en) * | 2013-11-14 | 2014-03-26 | 青岛海信传媒网络技术有限公司 | Application recommendation method and system thereof |
CN105426514A (en) * | 2015-11-30 | 2016-03-23 | 扬州大学 | Personalized mobile APP recommendation method |
CN105989108A (en) * | 2015-02-12 | 2016-10-05 | 广东欧珀移动通信有限公司 | Information recommendation method and device |
CN105989074A (en) * | 2015-02-09 | 2016-10-05 | 北京字节跳动科技有限公司 | Method and device for recommending cold start through mobile equipment information |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105912550A (en) * | 2015-12-15 | 2016-08-31 | 乐视网信息技术(北京)股份有限公司 | Method and device for information recommendation of mobile terminal |
CN106846094A (en) * | 2016-12-29 | 2017-06-13 | 广州优视网络科技有限公司 | A kind of method and apparatus for recommending application message based on application has been installed |
-
2016
- 2016-12-29 CN CN201611242501.6A patent/CN106846094A/en active Pending
-
2017
- 2017-12-28 WO PCT/CN2017/119610 patent/WO2018121700A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103679502A (en) * | 2013-11-14 | 2014-03-26 | 青岛海信传媒网络技术有限公司 | Application recommendation method and system thereof |
CN105989074A (en) * | 2015-02-09 | 2016-10-05 | 北京字节跳动科技有限公司 | Method and device for recommending cold start through mobile equipment information |
CN105989108A (en) * | 2015-02-12 | 2016-10-05 | 广东欧珀移动通信有限公司 | Information recommendation method and device |
CN105426514A (en) * | 2015-11-30 | 2016-03-23 | 扬州大学 | Personalized mobile APP recommendation method |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018121700A1 (en) * | 2016-12-29 | 2018-07-05 | 广州优视网络科技有限公司 | Method and device for recommending application information based on installed application, terminal device, and storage medium |
WO2018149244A1 (en) * | 2017-02-20 | 2018-08-23 | 广州优视网络科技有限公司 | Method and device for recommending applications associated with target application on basis of target application |
CN110020152B (en) * | 2017-12-04 | 2021-03-19 | 中国移动通信集团终端有限公司 | Application recommendation method and device |
CN110020152A (en) * | 2017-12-04 | 2019-07-16 | 中国移动通信集团终端有限公司 | Using recommended method and device |
CN108052671A (en) * | 2017-12-29 | 2018-05-18 | 北京奇虎科技有限公司 | A kind of method and system that content item push is carried out based on Dynamic Matching |
CN108510352A (en) * | 2018-02-09 | 2018-09-07 | 广州优视网络科技有限公司 | Application issue recommends method, apparatus and computer equipment |
CN108769125A (en) * | 2018-04-28 | 2018-11-06 | 广州优视网络科技有限公司 | Using recommendation method, apparatus, storage medium and computer equipment |
CN108769125B (en) * | 2018-04-28 | 2021-08-17 | 阿里巴巴(中国)有限公司 | Application recommendation method and device, storage medium and computer equipment |
CN108809987A (en) * | 2018-06-14 | 2018-11-13 | 广州任天游网络科技有限公司 | A kind of online game extension method based on big data analysis |
CN108809987B (en) * | 2018-06-14 | 2020-10-23 | 江苏果米文化发展有限公司 | Online game popularization method based on big data analysis |
CN109242643A (en) * | 2018-09-30 | 2019-01-18 | 武汉斗鱼网络科技有限公司 | The method, apparatus and storage medium of game recommdation applied to live streaming platform |
CN111796883A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Device control method, device, storage medium and electronic device |
CN110134410A (en) * | 2019-05-17 | 2019-08-16 | 北京百度网讯科技有限公司 | It is cold-started customized information correlating method, device and the storage medium of user |
CN110134410B (en) * | 2019-05-17 | 2022-11-15 | 北京百度网讯科技有限公司 | Personalized information association method and device for cold-start user and storage medium |
CN111611143A (en) * | 2020-05-20 | 2020-09-01 | 浙江每日互动网络科技股份有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN111611143B (en) * | 2020-05-20 | 2023-06-30 | 每日互动股份有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN112328935A (en) * | 2020-10-29 | 2021-02-05 | 胡培培 | Application program pushing system and method based on big data |
CN112328935B (en) * | 2020-10-29 | 2021-11-12 | 朱理薇 | Application program pushing system and method based on big data |
CN115150346A (en) * | 2022-07-04 | 2022-10-04 | 中国银行股份有限公司 | Information pushing method and device |
Also Published As
Publication number | Publication date |
---|---|
WO2018121700A1 (en) | 2018-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106846094A (en) | A kind of method and apparatus for recommending application message based on application has been installed | |
CN103020845B (en) | A kind of method for pushing and system of mobile application | |
CN103823908B (en) | Content recommendation method and server based on user preference | |
CN105975472A (en) | Method and device for recommendation | |
CN105095219B (en) | Micro-blog recommendation method and terminal | |
CN103327045B (en) | User recommendation method and system in social network | |
CN106484777A (en) | A kind of multimedia data processing method and device | |
CN105975641A (en) | Video recommendation method ad device | |
CN106951571A (en) | A kind of method and apparatus for giving application mark label | |
CN106713965A (en) | Information display method and device | |
CN104102696A (en) | Content recommendation method and device | |
CN106326391A (en) | Method and device for recommending multimedia resources | |
CN106446189A (en) | Message-recommending method and system | |
CN107895213A (en) | Forecasting Methodology, device and the electronic equipment of spending limit | |
CN106202073A (en) | Music recommends method and system | |
CN106776859A (en) | Mobile solution App commending systems based on user preference | |
CN106909688A (en) | A kind of method and apparatus that search word is recommended based on input search word | |
CN109064283B (en) | Commodity recommendation method and device and computer-readable storage medium | |
CN106960033A (en) | A kind of method and apparatus that label is marked to information flow | |
CN107103028A (en) | A kind of information processing method and device | |
CN106844724A (en) | It is a kind of that the method and apparatus applied to recommend application have been installed based on user | |
CN107045413A (en) | Application program image target display methods and device | |
CN107454346A (en) | Movie data analytic method, video production template recommend method, apparatus and equipment | |
CN107707940A (en) | Video sequencing method, device, server and system | |
CN107729552A (en) | User behavior method for tracing, device, user terminal and server |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200903 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510627 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |