CN108596711A - Using recommendation method, apparatus and electronic equipment - Google Patents
Using recommendation method, apparatus and electronic equipment Download PDFInfo
- Publication number
- CN108596711A CN108596711A CN201810266636.9A CN201810266636A CN108596711A CN 108596711 A CN108596711 A CN 108596711A CN 201810266636 A CN201810266636 A CN 201810266636A CN 108596711 A CN108596711 A CN 108596711A
- Authority
- CN
- China
- Prior art keywords
- event
- application
- candidate
- uncertainty
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
Abstract
The invention discloses a kind of applications to recommend method, apparatus and electronic equipment.This method includes：Obtain the historical context degree between candidate application concentration any two candidate application；Obtain the historical usage behavioral data of target user；Recommendation novelty degree of the candidate application for target user is obtained according to the historical context degree and historical usage behavioral data between candidate application and any other candidate application for each candidate application；The candidate application for recommending novelty degree to meet preset recommendation condition is chosen, as intended application, recommends target user.According to the present invention it is possible to avoid recommending popular degree or the higher application of popularization degree, the probability for recommending the higher application of novelty degree is improved.It realizes the accurate recommendation of application, promotes user experience.
Description
Technical field
The present invention relates to Internet technical fields, recommend method, apparatus and electronics to set more particularly, to a kind of application
It is standby.
Background technology
With the rapid development of Internet technology, universal, more and more users' habit of the intelligent movable of electronic equipment
It is used to download and installed using (application program, abbreviation APP) by such as this class of electronic devices of mobile phone, tablet device, to obtain
The service that the application provides.Therefore, the application platform that installation is downloaded for user is widely applied in convergence, is also come into being therewith.
With the explosive growth of Internet user's scale, in current application platform, a large amount of application is often summarized,
And application update or newly-increased speed are also exponentially increased, to avoid user from being difficult to quickly select in the application of substantial amounts
The experience lf being influenced using download for meeting demand is selected, application platform, which usually provides, applies recommendation service, recommends to accord with for user
Some the similar or related applications for closing user demand are saved a large amount of application searches work for user, are promoted using body with this
It tests.
Therefore, the similarity (degree of association) obtained between application is to provide the key using recommendation service.Traditional application
Similarity calculation is typically based on the methods of cosine similarity, Euclidean distance, Jie Lade algorithms, Pearson correlation coefficient, but these
Method, which is all only based on, recommends user using similarity, is easy that user will be recommended using the higher application of similarity,
But these are all that temperature is higher, the higher application of popularization degree using correspondence, ultimately form the application presence for recommending different user
Convergent phenomenon can not be directed to different user and recommend the higher application of novelty degree, influence, using the precision recommended, to cause user
Real experiences are poor.
Invention content
It is an object of the present invention to provide a kind of new solutions for recommending application.
According to the first aspect of the invention, a kind of application recommendation method is provided, wherein including：
Obtain the historical context degree between any two candidate application in candidate set of applications；
Wherein, the candidate set of applications includes multiple candidate applications；The historical context degree is described in corresponding two
Candidate applies the metric that associated application event occurs in preset measurement period；The associated application event is corresponding two
The event of application affairs occurs for a candidate association；The application affairs are that corresponding application practices row by user
For event；
Obtain the historical usage behavioral data of target user；
Wherein, the historical usage behavioral data, be the target user in the measurement period to each time
Select the historical data that behavior is applied described in application implementation；
For each candidate application, according between candidate application and any other candidate application
It is novel for the recommendation of the target user to obtain candidate application for historical context degree and the historical usage behavioral data
Degree；
The candidate application that the recommendation novelty degree meets preset recommendation condition is chosen, as intended application, recommendation
To the target user.
Optionally, described to obtain the step of historical context is spent and include：
For the corresponding two candidate applications, the corresponding associated application occurs in the measurement period for statistics
The event times of event；
According to the event times, the historical context degree of the described corresponding two candidate applications is calculated.
Optionally,
The corresponding two candidate applications include that the first candidate application is applied with the second candidate；
The associated application event includes the first correlating event, the second correlating event, third correlating event, the 4th association thing
Part；First correlating event is the thing that corresponding application affairs all occur with the second candidate application for the described first candidate application
Part；Second correlating event is that application affairs occur for the described first candidate application and the second candidate application does not occur pair
The event for the application affairs answered；The third correlating event be the described first candidate application application affairs do not occur and described the
The event of corresponding application affairs but occurs for two candidate applications；4th correlating event is the described first candidate application and second
The event of corresponding application affairs does not all occur for candidate's application；
The event times include first event number, second correlating event hair that first correlating event occurs
What the third event times of raw second event number, third correlating event generation and the 4th correlating event occurred
4th event times.
Optionally, described the step of being spent according to the event times calculating historical context, includes：
According to the first event number, second event number, third event times, the 4th event times, calculate separately
First event is associated with uncertainty, second event association uncertainty and whole event correlation uncertainty；
Wherein, the first event is associated with uncertainty, is the item that application affairs occur based on the described first candidate application
Under part, the uncertainty of the associated application event generation；The second event is associated with uncertainty, is waited based on described second
Under conditions of application affairs occur for choosing application, the uncertainty of the associated application event generation；The entirety event correlation is not
Degree of certainty is the whole uncertainty that the associated application event occurs；
It is not true it to be associated with uncertainty, second event association uncertainty and whole event correlation according to the first event
Fixed degree, calculates the historical context degree.
Optionally, the calculating first event association uncertainty, second event association uncertainty and whole event
Be associated with uncertainty the step of include：
The entropy that will be calculated according to the first event number and the second event number, and according to the third
Event times are summed with the entropy that the 4th event times are calculated, and obtain the first event degree of association；
The entropy that will be calculated according to the first event number and the third event times, and according to described second
Event times are summed with the entropy that the 4th event times are calculated, and obtain the second event degree of association；
According to the first event number, second event number, third event times, the 4th event times this calculating
Entropy, the obtained whole event correlation uncertainty.
Optionally, described to calculate the step of historical context is spent and include：
It is uncertain according to the whole event correlation uncertainty, first event association uncertainty, second event association
Degree calculates uncertainty difference；
According to preset association factor and the uncertainty difference, the historical context degree is calculated.
Optionally, the step of calculating uncertainty difference includes：
The whole event uncertainty is subtracted into the first event association uncertainty, second event association not
Degree of certainty obtains the uncertainty difference；
And/or
Respectively the first event association uncertainty, second event association are handled using preset Optimization Factor not
Degree of certainty, the first event association uncertainty after being optimized, the second event are associated with uncertainty；
The whole event uncertainty is subtracted into the association of the first event after optimization uncertainty, described the
Two event correlation uncertainties obtain the uncertainty difference.
Optionally, described recommendation novelty the step of spending for obtaining that candidate apply, includes：
Any other one candidate application except being applied with the candidate is applied as a comparison, from the historical behavior
Historical behavior value of the target user to the preset intended application behavior of the comparison application implementation is obtained in data；
It is applied for each comparison, candidate application is applied with the comparison and intended application behavior pair
The historical context degree answered is multiplied with the corresponding historical behavior value, obtains the corresponding opposite comparison application of the candidate
Recommend novel value；
Greatest measure is chosen in the novel value of the whole recommendation of acquisition, as the recommendation novelty degree.
Optionally,
The recommendation condition is that the recommendation novelty degree carries out the ranking value after descending sort in preset numberical range
It is interior；
And/or
The application behavior include at least click application, download application, installation application, using application this wherein it
One.
According to the second aspect of the invention, it provides a kind of using recommendation apparatus, wherein including：
Degree of association acquiring unit, for obtaining the historical context in candidate set of applications between any two candidate application
Degree；
Wherein, the candidate set of applications includes multiple candidate applications；The historical context degree is described in corresponding two
Candidate applies the metric that associated application event occurs in preset measurement period；The associated application event is corresponding two
The event of application affairs occurs for a candidate association；The application affairs are that corresponding application practices row by user
For event；
Data capture unit, the historical usage behavioral data for obtaining target user；
Wherein, the historical usage behavioral data, be the target user in the measurement period to each time
Select the historical data that behavior is applied described in application implementation；
Novel degree acquiring unit, for for each candidate application, according to candidate application described in this with it is any other
The candidate application between the historical context degree and the historical usage behavioral data, obtain candidate apply for
The recommendation novelty degree of the target user；
Using recommendation unit, the candidate application that preset recommendation condition is met for choosing the recommendation novelty degree is made
For intended application, the target user is recommended.
According to the third aspect of the invention we, a kind of electronic equipment is provided, wherein including：
Memory, for storing executable instruction；
Processor runs the electronic equipment and executes such as the present invention for the control according to the executable instruction
Any one application recommendation method described in first aspect.
According to one embodiment of present invention, by obtaining going through between any two candidate application in candidate set of applications
The history degree of association, target user historical usage behavioral data, calculate each candidate recommendation novelty degree for applying relative target user,
It chooses the candidate application for recommending novelty degree to meet recommendation condition and is used as intended application, recommend target user.It avoids recommending public
Change degree or the higher application of popularization degree improve the probability for recommending the higher application of novelty degree.The accurate recommendation for realizing application, carries
Rise user experience.
By referring to the drawings to the detailed description of exemplary embodiment of the present invention, other feature of the invention and its
Advantage will become apparent.
Description of the drawings
It is combined in the description and the attached drawing of a part for constitution instruction shows the embodiment of the present invention, and even
With its explanation together principle for explaining the present invention.
Fig. 1 is the frame of the example for the hardware configuration for showing the electronic equipment 1000 that can be used for realizing the embodiment of the present invention
Figure.
Fig. 2 shows the flow charts using recommendation method of the present embodiment.
Fig. 3 shows the flow for the step of historical context between the corresponding two candidate applications of the acquisition of the present embodiment is spent
Figure.
Fig. 4 shows the flow chart for the step of historical context of the corresponding two candidate applications of the calculating of the present embodiment is spent.
Fig. 5 shows the flow of the specific steps of the historical context degree of the corresponding two candidate applications of the calculating of the present embodiment
Figure.
Fig. 6 shows the flow for the step of recommendation novelty of target user is spent in the acquisition of the present embodiment candidate application
Figure.
Fig. 7 shows the block diagram using recommendation apparatus 3000 of the present embodiment.
Fig. 8 shows the block diagram of the electronic equipment 4000 of the present embodiment.
Specific implementation mode
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should be noted that：Unless in addition having
Body illustrates that the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The range of invention.
It is illustrative to the description only actually of at least one exemplary embodiment below, is never used as to the present invention
And its application or any restrictions that use.
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.
In shown here and discussion all examples, any occurrence should be construed as merely illustrative, without
It is as limitation.Therefore, other examples of exemplary embodiment can have different values.
It should be noted that：Similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined, then it need not be further discussed in subsequent attached drawing in a attached drawing.
<Hardware configuration>
Fig. 1 is the block diagram for showing may be implemented the hardware configuration of the electronic equipment 1000 of the embodiment of the present invention.
Electronic equipment 1000 can be portable computer, desktop computer, mobile phone, tablet computer etc..As shown in Figure 1, electric
Sub- equipment 1000 may include processor 1100, memory 1200, interface arrangement 1300, communication device 1400, display device
1500, input unit 1600, loud speaker 1700, microphone 1800 etc..Wherein, processor 1100 can be central processing unit
CPU, Micro-processor MCV etc..Memory 1200 is for example including ROM (read-only memory), RAM (random access memory), such as
The nonvolatile memory etc. of hard disk.Interface arrangement 1300 is such as including USB interface, earphone interface.Communication device 1400
Wired or wireless communication can be such as carried out, may include specifically Wifi communications, Bluetooth communication, 2G/3G/4G/5G communications etc..It is aobvious
Showing device 1500 is, for example, liquid crystal display, touch display screen etc..Input unit 1600 for example may include touch screen, keyboard,
Body-sensing input etc..User can pass through 1800 inputting/outputting voice information of loud speaker 1700 and microphone.
Electronic equipment shown in FIG. 1 is merely illustrative and is in no way intended to the invention, its application, or uses
Any restrictions.Using in an embodiment of the present invention, the memory 1200 of electronic equipment 1000 is for storing instruction, described
Instruction is operated for controlling the processor 1100 to execute any one provided in an embodiment of the present invention using recommendation side
Method.It will be appreciated by those skilled in the art that although showing multiple devices to electronic equipment 1000 in Fig. 1, the present invention
Partial devices therein can be only related to, for example, electronic equipment 1000 pertains only to processor 1100 and storage device 1200.Technology
Personnel can instruct according to presently disclosed conceptual design.How control processor is operated for instruction, this is this field public affairs
Know, therefore is not described in detail herein.
<Embodiment>
<Method>
In the present embodiment, a kind of application recommendation method is provided, for recommending to apply to user.
The application be by can by such as this class of electronic devices of mobile phone, tablet device download, installation after run or
Application program directly run, that corresponding service is provided.
This applies recommendation method, as shown in Fig. 2, including：Step S2100-S2400.
Step S2100 obtains the historical context degree between any two candidate application in candidate set of applications.
Candidate's set of applications includes multiple candidate applications.Candidate's set of applications is to recommend use for therefrom choosing
The set of applications of the intended application at family can be built according to actual application scenarios or application demand.
Historical context degree between any two candidate application, is that corresponding two candidates apply in preset measurement period
The interior metric that associated application event occurs.The historical context degree can be used for measuring the generation between any two candidate application
The degree of association of corresponding application affairs can not only embody the degree of association between application based on the historical context degree, moreover it is possible to embody
Novel degree (or popular index or popularization degree) difference between candidate's application so that it is subsequently based on the historical context degree, it can
To obtain any one opposite recommendation novelty degree with target user of candidate's application.
The measurement period can be arranged according to actual application scenarios or application demand, for example, could be provided as 1
Month.
Associated application event is the event that application affairs occur for corresponding two candidate associations.
Application affairs are the corresponding events applied and practiced behavior by user.This is that user is real to application using behavior
The behavior applied.In one example, using behavior include at least click application, download application, installation application, using application this four
One of person.
In one example, corresponding two candidate applications include that the first candidate application is applied with the second candidate.Association is answered
Include the first correlating event, the second correlating event, third correlating event, the 4th correlating event with event.First correlating event is
The event of identical application affairs all occurs with the second candidate application for the first candidate application；Second correlating event is that the first candidate answers
With generation application affairs, the event of the application affairs does not occur for the second candidate application；Third correlating event is that the first candidate answers
With not occurring application affairs and the events of the application affairs occurs for the second candidate application；4th correlating event is the first candidate
Using the event that identical application affairs all do not occur with the second candidate application.
For example, the first candidate application is to apply A, the second candidate application is to apply B, application affairs be corresponding application by with
The event that family is clicked.First correlating event is using A and the event for applying B all to be clicked by user.Second correlating event is to apply A
The event clicked by user, do not clicked by user using B.Third correlating event be using A not by user click, using B by with
The event that family is clicked.4th correlating event is using A and the event for applying B all not clicked by user.
In the present embodiment, it is used between measurement application between any two application by obtaining in candidate set of applications
The historical context degree of associated application event occurs, the historical context degree combination subsequent step can be based on, obtain any one time
The opposite recommendation novelty degree with target user of choosing application avoids recommending big based on recommending novelty degree to be that target user recommends application
Manyization degree or the higher application of popularization degree improve the probability for recommending the higher application of novelty degree to user, realize the essence of application
Standard is recommended, and user experience is promoted.
In one example, the step S2100 for obtaining the historical context degree between corresponding two candidate applications can be as
Shown in Fig. 3, including step S2110-S2120.
Step S2110, for corresponding two candidate applications, corresponding associated application thing occurs in measurement period for statistics
The event times of part.
It in the present embodiment, can be each according to what is recorded in measurement period by providing the candidate application platform applied
A application such as is clicked, installs, downloading, using at the historical datas, and statistics obtains the event times that the associated application event occurs.
In one example, corresponding two candidate applications include that the first candidate application is applied with the second candidate；Association is answered
Include the first correlating event, the second correlating event, third correlating event, the 4th correlating event with event.
First correlating event is the event that corresponding application affairs all occur with the second candidate application for the first candidate application.The
Two correlating events are the things that application affairs occur for the first candidate application and corresponding application affairs do not occur for the second candidate application
Part.Third correlating event is that application affairs do not occur for the first candidate application and the second candidate application occurs corresponding to apply thing
The event of part.4th correlating event is the thing that corresponding application affairs all do not occur with the second candidate application for the first candidate application
Part.
Accordingly, event times include the first correlating event occur first event number, the second correlating event occurs
The 4th event time that the third event times and the 4th correlating event that second event number, third correlating event occur occur
Number.
For example, the first candidate application is to apply A, the second candidate application is to apply B, it is assumed that the application affairs occurred using A
EventA is corresponding with the application B generations event of EventB.First correlating event is the event that EventA and EventB occur, right
The first event number answered is the number K11 that EventA and EventB occur；Second correlating event be EventA occur but
The nonevent events of EventB, corresponding second event number are EventA generations but the nonevent number K12 of EventB；Third
Correlating event be EventA do not occur but EventB occur event, corresponding third event times be EventA do not occur but
The number K21 that EventB occurs；4th correlating event is all nonevent event of EventA and EventB, corresponding 4th event
Number is all nonevent number K22 of EventA and EventB.
Step S2120 calculates the historical context degree of corresponding two candidate applications according to the event times.
In one example, step S2120 can be with as shown in figure 4, include step S2121-S2122.
Step S2121 divides according to first event number, second event number, third event times, the 4th event times
It Ji Suan not first event association uncertainty, second event association uncertainty and whole event correlation uncertainty.
First event is associated with uncertainty, is corresponding pass under conditions of application affairs occur based on the first candidate application
Join the uncertainty that application affairs occur.
Calculating the step of first event is associated with uncertainty may include：
The entropy that will be calculated according to first event number and second event number, and according to third event times and the
The entropy summation that four event times are calculated, obtains the first event degree of association.
In this example, by above application A and for applying the examples that B is corresponding two candidate applications, it is assumed that the first thing
Piece number K11, second event number K12, third event times K21, the 4th event times K22.
Accordingly, the entropy Entropy (K11, K12) being calculated according to first event number and second event number
For：
Entropy (K 11, K 12)=lg (K 11+K 12)-lg (K 11)-lg (K 12)；
It is according to third event times and the entropy Entropy (K21, K22) that the 4th event times are calculated：
Entropy (K21, K22)=lg (K21+K22)-lg (K21)-lg (K22)；
The first event degree of association rowEntropy being calculated is：
RowEntropy=Entropy (K 11, K 12)+Entropy (K21, K22).
Second event is associated with uncertainty, is associated application under conditions of application affairs occur based on the second candidate application
The uncertainty that event occurs.
Calculating the step of second event is associated with uncertainty may include：
The entropy that will be calculated according to first event number and third event times, and according to second event number and the
The entropy summation that four event times are calculated, obtains the second event degree of association.
Continue based on above-mentioned event times include first event number K11, second event number K12,
For third event times K21, the 4th event times K22.
Accordingly, the entropy Entropy (K11, K21) being calculated according to first event number and third event times
For：
Entropy (K 11, K21)=lg (K 11+K21)-lg (K 11)-lg (K21)；
The entropy Entropy (K12, K22) being calculated according to second event number and the 4th event times is：
Entropy (K 12, K22)=lg (K 12+K22)-lg (K 12)-lg (K22)；
The second event degree of association columnEntropy being calculated is：
ColumnEntropy=Entropy (K 11, K21)+Entropy (K 12, K22).
Whole event correlation uncertainty is the whole uncertainty that corresponding associated application event occurs.
Calculating the step of arranging event correlation uncertainty includes：
According to first event number, second event number, third event times, the 4th event times this calculate entropy
Value, obtained whole event correlation uncertainty.
Continue to be based on above-mentioned event times to include first event number K11, second event number K12, third event time
For number K21, the 4th event times K22.
Accordingly, whole event correlation uncertainty matrixEntropy is：
MatrixEntropy=Entropy (K 11, K 12, K21, K22)
=lg (K 11+K 12+K21+K22)-lg (K 11)-lg (K 12)-lg (K21)-lg (K22).
Step S2122 is associated with uncertainty, second event association uncertainty and whole event according to first event and closes
Join uncertainty, calculates historical context degree.
First event uncertainty is corresponding associated application under conditions of application affairs occur based on the first candidate application
The uncertainty that event occurs can embody the degree of association of the first candidate application and the second candidate application；Second event is associated with not
Degree of certainty is under conditions of application affairs occur based on the second candidate application, and corresponding associated application event occurs uncertain
Degree can embody the novel degree of second the relatively first candidate application of candidate application；Whole event correlation uncertainty, is corresponding
The whole uncertainty that associated application event occurs can embody two whole degrees of association of candidate application.Based on above-mentioned three
Uncertainty calculates historical context degree, can make the historical context degree calculated that can not only embody corresponding two candidate applications
Between the degree of association, moreover it is possible to embody the novel degree difference between corresponding two candidate applications.
In one example, calculating the step of historical context is spent can be with as shown in figure 5, includes：Step S21221-
S21222。
Step S21221 is associated with according to whole event correlation uncertainty, first event association uncertainty, second event
Uncertainty calculates uncertainty difference.
In one example, the step of calculating uncertainty difference includes：
Whole event uncertainty is subtracted into first event association uncertainty, second event association uncertainty, is obtained
Uncertainty difference.
First event degree of association rowEntropy, second event degree of association columnEntropy, whole event in the above example
It is associated with for uncertainty matrixEntropy.
Uncertainty difference Delta is：
Delta=matrixEntropy-rowEntropy-columnEntropy.
First event uncertainty is corresponding associated application under conditions of application affairs occur based on the first candidate application
The uncertainty that event occurs can embody the degree of association of the first candidate application and the second candidate application；Second event is associated with not
Degree of certainty is under conditions of application affairs occur based on the second candidate application, and corresponding associated application event occurs uncertain
Degree can embody the novel degree of second the relatively first candidate application of candidate application；Whole event correlation uncertainty, is corresponding
The whole uncertainty that associated application event occurs can embody two whole degrees of association of candidate application.
First event uncertainty, second event association uncertainty are subtracted using whole uncertainty, it can be by not
Degree of certainty difference, the recommended uncertainty of the second candidate application of assessment whether be more than be not provided with it is any under the conditions of recommend application
Average value.
Historical context degree is calculated according to preset association factor and uncertainty difference in step S21222.
Association factor apha can be pre-set according to concrete application scene or application demand, for example, can be with
It is set as 2.
In the above example for Delta=matrixEntropy-rowEntropy-columnEntropy, according to association because
The historical context degree HILLR that sub- apha and uncertain difference Delta is calculated：
HILLR=apha × Delta
=apha × (matrixEntropy-rowEntropy-columnEntropy)
In practical applications, when being carried out using recommending based on the above-mentioned uncertain difference Delta historical context degree calculated, meeting
Occur recommending the probability of the second candidate application by first candidate's application and the first candidate application is recommended by the second candidate application
Probability be the same, it may appear that recommend the higher application of popular degree by the high application of some novelty degree, reduction pushes away
Recommend the probability of the higher application of novel degree so that user experience is impacted.
Therefore, in one example, the step of above-mentioned calculating uncertainty difference may include：
It is associated with uncertainty using preset Optimization Factor processing first event association uncertainty, second event respectively,
First event association uncertainty after being optimized, second event are associated with uncertainty；
Whole event uncertainty is subtracted into the first event association uncertainty after optimization, second event association is not known
Degree, obtains uncertainty difference.
Optimization Factor Beta can be pre-set according to concrete application scene or application demand, for example, can be with
It is set greater than 0 numerical value for being less than association factor apha.
First event degree of association rowEntropy, second event degree of association columnEntropy, whole event in the above example
It is associated with for uncertainty matrixEntropy, is associated with uncertainty using Optimization Factor Beta processing first events, obtains excellent
First event association uncertainty after change is (apha-beta) × rowEntropy；Utilize Optimization Factor Beta processing second
Event correlation uncertainty, the second event association uncertainty after being optimized is Beta × columnEntropy.
Accordingly, uncertainty difference Delta is：
Delta=matrixEntropy- (apha-beta) × rowEntropy-Beta × columnEntropy
The historical context degree HILLR being calculated according to association factor apha and uncertain difference Delta：
HILLR=apha × Delta
=apha × (matrixEntropy- (apha-beta) × rowEntropy-Beta × columnEntropy)
First event is handled by Optimization Factor Beta and is associated with uncertainty, second event association uncertainty so that body
The second event of the novel degree of existing the relatively first candidate application of second candidate application is associated with uncertainty, is calculating historical context degree
Shi Suozhan weights are more so that the recommendation novelty degree subsequently based on historical context degree is more accurate, is answered based on novelty degree is recommended
With recommendation, it is easier to recommend the high application of novel degree.
Step S2200 obtains the historical usage behavioral data of target user.
The historical usage behavioral data is that target user goes to each candidate application implementation application in above-mentioned measurement period
For historical data.In one example, this is included at least using behavior clicks application, downloads application, installation application, using answering
With one of this.
The historical usage behavioral data of target user can be by providing the candidate application platform applied, according to the use of record
Family log statistic obtains, and is not limited herein.
Step S2300, for each candidate application, according to going through between candidate application and any other candidate application
The history degree of association and historical usage behavioral data obtain recommendation novelty degree of the candidate application for target user.
In one example, step S2300 can be with as shown in fig. 6, include step S2310-S2330.
Step S2310, any other one candidate application except being applied with the candidate is applied as a comparison, from history row
To obtain historical behavior value of the target user to the preset intended application behavior of the comparison application implementation in data.
Assuming that the candidate set of applications I={ Item (n) } (n=1 ... ..., N) in the present embodiment includes that N number of candidate answers
With for candidate using Item (i), selection candidate applies as a comparison using Item (j) (j ≠ i).Assuming that intended application behavior
Whether k, corresponding then historical behavior value Y (j, k) marked targeted customer u have occurred k behaviors to candidate using Item (j), if
K behaviors have occurred, Y (j, k) value is 1, otherwise, value 0.
Method described above can calculate the history row that the candidate that each is applied as a comparison applies Item (j) (j ≠ i)
For value Y (j, k).
Step S2320 is applied for each comparison, candidate application is applied with the comparison and intended application behavior
Corresponding historical context degree is multiplied with corresponding historical behavior value, and the recommendation for obtaining the corresponding opposite comparison application of the candidate is new
Grain husk value.
Based on above-mentioned candidate application, for Item (i), comparison is using for Item (j) (j ≠ i).Candidate's application is right with this
Than historical context degree HILLR application, corresponding with intended application behavior kk(i, j), can be based on above-mentioned meter as described in Figure 3
The method for calculating historical context degree calculates.
Wherein, apply Item (j) (j ≠ i) as the first candidate application using comparison, Item (i) is as the second candidate application.
Associated application event includes the first correlating event, the second correlating event, third correlating event, the 4th correlating event.First association
Event is the event that corresponding intended application behavior k occurs with Item (i) for Item (j).Second correlating event is Item (j) hairs
It is raw using behavior k and the corresponding event using behavior k does not occur for Item (i).Third correlating event is that Item (j) does not occur
The corresponding events using behavior k of Item (i) using behavior k.4th correlating event is Item (j) with Item (i) all not
The corresponding event using behavior k occurs.Accordingly, it can count to obtain corresponding first, second, third and fourth correlating event number
K11、K12、K21、K22.And then it can be based on method as discussed above, above-mentioned HILLR is calculatedk(i, j), herein no longer
It repeats.
It is possible to further obtain recommendation novelty value RNs of the Item (i) with respect to Item (j)k(i,j)：
RNk(i, j)=Y (j, k) × HILLRk(i,j)。
Based on above-mentioned example, it can be directed to each Item (j) (j ≠ i) applied as a comparison, calculate candidate application
Item (i) is based on intended application behavior k, the novel value RN of corresponding recommendationk(i,j)。
Step S2330, whole in acquisition recommend to choose greatest measure in novel value, as recommendation novelty degree.
In this example, the candidate recommendation novelty degree H (u, i) for applying relative target user u：
H (u, i)=max (RNk(i,j))(j≠i,j∈I,k∈K)；
Wherein, I is candidate set of applications, including a variety of candidate applications, in the candidate set of applications of Item (j) (j ≠ i) traversals
Any one candidate's application；K be using behavior set, including it is a variety of apply behavior, it is arbitrary in behavior k traversal applications behavior set
It is a kind of to apply behavior, such as click application, download application, installation application, using application etc..
Step S2400 chooses the candidate application for recommending novelty degree to meet preset recommendation condition, as intended application, pushes away
It recommends to target user.
The recommendation condition can be pre-set according to specific application scenarios or application demand.
In one example, recommendation condition can be that recommendation novelty degree carries out the ranking value after descending sort in preset number
It is worth in range.Accordingly, it is exactly that descending sort is carried out according to the recommendation novelty degree of each candidate application, by order after sequence pre-
If numberical range in candidate application, be chosen for intended application.
For example, numberical range is 1-3, when just selection recommends novelty degree to sort from big to small, sequence is answered in preceding 3 candidates
It is used as intended application.
<Device>
In the present embodiment, a kind of application recommendation apparatus 3000 is also provided, as shown in fig. 7, comprises：Degree of association acquiring unit
3100, data capture unit 3200, novelty degree acquiring unit 3300 and application recommendation unit 3400, for implementing the present embodiment
Any one of middle offer applies recommendation method, and details are not described herein.
Degree of association acquiring unit 3100 is closed for obtaining the history in candidate set of applications between any two candidate application
Connection degree；
Wherein, the candidate set of applications includes multiple candidate applications；The historical context degree is described in corresponding two
Candidate applies the metric that associated application event occurs in preset measurement period；The associated application event is corresponding two
The event of application affairs occurs for a candidate association；The application affairs are that corresponding application practices row by user
For event；
Data capture unit 3200, the historical usage behavioral data for obtaining target user；
Wherein, the historical usage behavioral data, be the target user in the measurement period to each time
Select the historical data that behavior is applied described in application implementation；
Novel degree acquiring unit 3300, for being applied for each candidate, according to candidate application described in this and other
The historical context degree between the arbitrary candidate application and the historical usage behavioral data, obtain candidate application
For the recommendation novelty degree of the target user；
Using recommendation unit 3400, make for choosing the candidate application for recommending novelty degree to meet preset recommendation condition
For intended application, target user is recommended.
Optionally, degree of association acquiring unit 3100 is used for：
For the corresponding two candidate applications, the corresponding associated application occurs in the measurement period for statistics
The event times of event；
According to the event times, the historical context degree of the described corresponding two candidate applications is calculated.
Optionally,
The corresponding two candidate applications include that the first candidate application is applied with the second candidate；
The associated application event includes the first correlating event, the second correlating event, third correlating event, the 4th association thing
Part；First correlating event is the thing that corresponding application affairs all occur with the second candidate application for the described first candidate application
Part；Second correlating event is that application affairs occur for the described first candidate application and the second candidate application does not occur pair
The event for the application affairs answered；The third correlating event be the described first candidate application application affairs do not occur and described the
The event of corresponding application affairs but occurs for two candidate applications；4th correlating event is the described first candidate application and second
The event of corresponding application affairs does not all occur for candidate's application；
The event times include first event number, second correlating event hair that first correlating event occurs
What the third event times of raw second event number, third correlating event generation and the 4th correlating event occurred
4th event times.
Optionally, degree of association acquiring unit 3100 is used for：
According to the first event number, second event number, third event times, the 4th event times, calculate separately
First event is associated with uncertainty, second event association uncertainty and whole event correlation uncertainty；
Wherein, the first event is associated with uncertainty, is the item that application affairs occur based on the described first candidate application
Under part, the uncertainty of the associated application event generation；The second event is associated with uncertainty, is waited based on described second
Under conditions of application affairs occur for choosing application, the uncertainty of the associated application event generation；The entirety event correlation is not
Degree of certainty is the whole uncertainty that the associated application event occurs；
It is not true it to be associated with uncertainty, second event association uncertainty and whole event correlation according to the first event
Fixed degree, calculates the historical context degree.
Optionally, uncertainty, second event association uncertainty and whole event are associated with according to the first event
It is associated with uncertainty, calculating the historical context degree includes：
The entropy that will be calculated according to the first event number and the second event number, and according to the third
Event times are summed with the entropy that the 4th event times are calculated, and obtain the first event degree of association；
The entropy that will be calculated according to the first event number and the third event times, and according to described second
Event times are summed with the entropy that the 4th event times are calculated, and obtain the second event degree of association；
According to the first event number, second event number, third event times, the 4th event times this calculating
Entropy, the obtained whole event correlation uncertainty.
Optionally, the calculating historical context degree includes：
It is uncertain according to the whole event correlation uncertainty, first event association uncertainty, second event association
Degree calculates uncertainty difference；
According to preset association factor and the uncertainty difference, the historical context degree is calculated.
Optionally, calculating uncertainty difference includes：
The whole event uncertainty is subtracted into the first event association uncertainty, second event association not
Degree of certainty obtains the uncertainty difference；
And/or
Respectively the first event association uncertainty, second event association are handled using preset Optimization Factor not
Degree of certainty, the first event association uncertainty after being optimized, the second event are associated with uncertainty；
The whole event uncertainty is subtracted into the association of the first event after optimization uncertainty, described the
Two event correlation uncertainties obtain the uncertainty difference.
Novel degree acquiring unit 3300 is additionally operable to：
Any other one candidate application except being applied with the candidate is applied as a comparison, from the historical behavior
Historical behavior value of the target user to the preset intended application behavior of the comparison application implementation is obtained in data；
It is applied for each comparison, candidate application is applied with the comparison and intended application behavior pair
The historical context degree answered is multiplied with the corresponding historical behavior value, obtains the corresponding opposite comparison application of the candidate
Recommend novel value；
Greatest measure is chosen in the novel value of the whole recommendation of acquisition, as the recommendation novelty degree.
Optionally,
The recommendation condition is that the recommendation novelty degree carries out the ranking value after descending sort in preset numberical range
It is interior；
And/or
The application behavior include at least click application, download application, installation application, using application this wherein it
One.
In the present embodiment, the application platform software using recommendation service can be to provide using recommendation apparatus 3000, transported
That implements to provide in the present embodiment after row applies recommendation method, recommends to apply to user.
It will be appreciated by those skilled in the art that can realize by various modes using recommendation apparatus 3000.For example, can
To be realized using recommendation apparatus 3000 by instructing configuration processor.For example, instruction can be stored in the ROM, and work as
When starting device, instruction is read from ROM and is realized in programming device using recommendation apparatus 3000.For example, can will answer
It is cured in dedicated devices (such as ASIC) with recommendation apparatus 3000.It can will be divided into using recommendation apparatus 3000 mutually independent
Unit, or they can be merged to realization.It can be by above-mentioned various realization methods using recommendation apparatus 3000
One kind realize, or can be realized by the combination of two or more modes in above-mentioned various realization methods.
<Electronic equipment>
In the present embodiment, a kind of electronic equipment 4000 is also provided, as shown in figure 8, including：
Memory 4100, for storing executable instruction；
Processor 4200 runs the electronic equipment and executes such as this reality for the control according to the executable instruction
Any one application recommendation method provided in example is provided.
In the present embodiment, electronic equipment 4000 can be mobile phone, tablet computer, laptop, palm PC, notes
The electronic equipments such as this computer.Electronic equipment 4000 can also include other hardware modules, for example, in an example, electronic equipment
4000 can be as shown in Figure 1 electronic equipment 1000.
Attached drawing is had been combined above and describes the embodiment of the present invention, according to the present embodiment, provides a kind of application recommendation side
Method, device and electronic equipment pass through the historical context degree between any two candidate application in the candidate set of applications of acquisition, target
The historical usage behavioral data of user calculates each candidate recommendation novelty degree for applying relative target user, and selection is recommended novel
The candidate application that degree meets recommendation condition is used as intended application, recommends target user.It avoids recommending popular degree or universal
Higher application is spent, the probability for recommending the higher application of novelty degree is improved.It realizes the accurate recommendation of application, promotes user experience.
It is well known by those skilled in the art that the development of the electronic information technology with such as large scale integrated circuit technology
With the trend of hardware and software, clearly to divide computer system soft and hardware boundary has seemed relatively difficult.Because appointing
What operation can be realized with software, can also be realized by hardware.The execution of any instruction can be completed by hardware, equally also may be used
To be completed by software.Hardware implementations or software implement scheme are used for a certain machine function, depend on price, speed
The Non-technical factors such as degree, reliability, memory capacity, change cycle.Therefore, for the ordinary skill of electronic information technical field
For personnel, mode more direct and that a technical solution is explicitly described is each operation described in the program.Knowing
In the case of road institute operation to be performed, those skilled in the art can directly set based on the considerations of to the Non-technical factor
Count out desired product.
The present invention can be system, method and/or computer program product.Computer program product may include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the invention.
Computer readable storage medium can be can keep and store the instruction used by instruction execution equipment tangible
Equipment.Computer readable storage medium for example can be-- but be not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electromagnetism storage device, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer readable storage medium
More specific example (non exhaustive list) includes：Portable computer diskette, random access memory (RAM), read-only is deposited hard disk
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static RAM (SRAM), portable
Compact disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above
Machine readable storage medium storing program for executing is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations lead to
It crosses the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or is transmitted by electric wire
Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, LAN, wide area network and/or wireless network
Portion's storage device.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, fire wall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
For execute the computer program instructions that operate of the present invention can be assembly instruction, instruction set architecture (ISA) instruction,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
Arbitrarily combine the source code or object code write, the programming language include the programming language-of object-oriented such as
Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions can be executed fully, partly execute on the user computer, is only as one on the user computer
Vertical software package executes, part executes or on the remote computer completely in remote computer on the user computer for part
Or it is executed on server.In situations involving remote computers, remote computer can pass through network-packet of any kind
It includes LAN (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as profit
It is connected by internet with ISP).In some embodiments, by using computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can execute computer-readable program instructions, to realize each side of the present invention
Face.
Referring herein to according to the method for the embodiment of the present invention, the flow chart of device (system) and computer program product and/
Or block diagram describes various aspects of the invention.It should be appreciated that flowchart and or block diagram each box and flow chart and/
Or in block diagram each box combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to all-purpose computer, special purpose computer or other programmable datas
The processor of processing unit, to produce a kind of machine so that these instructions are passing through computer or other programmable datas
When the processor of processing unit executes, work(specified in one or more of implementation flow chart and/or block diagram box is produced
The device of energy/action.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
It enables so that computer, programmable data processing unit and/or other equipment work in a specific way, to be stored with instruction
Computer-readable medium includes then a manufacture comprising in one or more of implementation flow chart and/or block diagram box
The instruction of the various aspects of defined function action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment so that series of operation steps are executed on computer, other programmable data processing units or miscellaneous equipment, with production
Raw computer implemented process, so that executed on computer, other programmable data processing units or miscellaneous equipment
Instruct function action specified in one or more of implementation flow chart and/or block diagram box.
Flow chart and block diagram in attached drawing show the system, method and computer journey of multiple embodiments according to the present invention
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
One module of table, program segment or a part for instruction, the module, program segment or a part for instruction include one or more use
The executable instruction of the logic function as defined in realization.In some implementations as replacements, the function of being marked in box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can essentially be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, this is depended on the functions involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart can use function or dynamic as defined in executing
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.It is right
It is well known that, realized by hardware mode for those skilled in the art, realized by software mode and by software and
It is all of equal value that the mode of combination of hardware, which is realized,.
Various embodiments of the present invention are described above, above description is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes will be apparent from for the those of ordinary skill in art field.The selection of term used herein, purport
In principle, the practical application or to the technological improvement in market for best explaining each embodiment, or make the art its
Its those of ordinary skill can understand each embodiment disclosed herein.The scope of the present invention is defined by the appended claims.
Claims (11)
1. method is recommended in a kind of application, wherein including：
Obtain the historical context degree between any two candidate application in candidate set of applications；
Wherein, the candidate set of applications includes multiple candidate applications；The historical context degree is corresponding two candidates
Apply the metric that associated application event occurs in preset measurement period；The associated application event is corresponding two institutes
State the event that application affairs occur for candidate association；The application affairs are that corresponding application practices behavior by user
Event；
Obtain the historical usage behavioral data of target user；
Wherein, the historical usage behavioral data is that the target user answers each candidate in the measurement period
With the implementation historical data using behavior；
For each candidate application, according to the history between candidate application and any other candidate application
The degree of association and the historical usage behavioral data obtain recommendation novelty degree of the candidate application for the target user；
The candidate application that the recommendation novelty degree meets preset recommendation condition is chosen, as intended application, recommends institute
State target user.
It is described to obtain the step of historical context is spent and include 2. according to the method described in claim 1, wherein：
For the corresponding two candidate applications, the corresponding associated application event occurs in the measurement period for statistics
Event times；
According to the event times, the historical context degree of the described corresponding two candidate applications is calculated.
3. according to the method described in claim 2, wherein,
The corresponding two candidate applications include that the first candidate application is applied with the second candidate；
The associated application event includes the first correlating event, the second correlating event, third correlating event, the 4th correlating event；
First correlating event is the event that corresponding application affairs all occur with the second candidate application for the described first candidate application；Institute
It is that corresponding answer does not occur for described first candidate the second candidate application described using generation application affairs to state the second correlating event
With the event of event；The third correlating event is that application affairs do not occur for the described first candidate application and second candidate
Using the event that corresponding application affairs but occur；4th correlating event is that the described first candidate application is answered with the second candidate
With the event that corresponding application affairs all do not occur；
The event times include that first event number, second correlating event of the first correlating event generation occur
The 4th of third event times and the 4th correlating event generation that second event number, the third correlating event occur
Event times.
4. according to the method described in claim 3, wherein, the step that the historical context degree is calculated according to the event times
Suddenly include：
According to the first event number, second event number, third event times, the 4th event times, first is calculated separately
Event correlation uncertainty, second event association uncertainty and whole event correlation uncertainty；
Wherein, the first event is associated with uncertainty, is based under conditions of the described first candidate application generation application affairs,
The uncertainty that the associated application event occurs；The second event is associated with uncertainty, is answered based on second candidate
Under conditions of application affairs occur, the uncertainty of the associated application event generation；The entirety event correlation is uncertain
Degree is the whole uncertainty that the associated application event occurs；
It is uncertain it to be associated with uncertainty, second event association uncertainty and whole event correlation according to the first event
Degree, calculates the historical context degree.
5. according to the method described in claim 4, wherein, the calculating first event association uncertainty, second event are associated with
The step of uncertainty and whole event correlation uncertainty includes：
The entropy that will be calculated according to the first event number and the second event number, and according to the third event
Number is summed with the entropy that the 4th event times are calculated, and obtains the first event degree of association；
The entropy that will be calculated according to the first event number and the third event times, and according to the second event
Number is summed with the entropy that the 4th event times are calculated, and obtains the second event degree of association；
According to the first event number, second event number, third event times, the 4th event times this calculate entropy
Value, the obtained whole event correlation uncertainty.
It is described to calculate the step of historical context is spent and include 6. according to the method described in claim 4, wherein：
It is associated with uncertainty, meter according to the whole event correlation uncertainty, first event association uncertainty, second event
Calculate uncertainty difference；
According to preset association factor and the uncertainty difference, the historical context degree is calculated.
7. according to the method described in claim 6, wherein, the step of calculating uncertainty difference, includes：
The whole event uncertainty is subtracted into the first event association uncertainty, second event association is not known
Degree, obtains the uncertainty difference；
And/or
The first event association uncertainty is handled using preset Optimization Factor, the second event is associated with and does not know respectively
Degree, the first event association uncertainty after being optimized, the second event are associated with uncertainty；
The whole event uncertainty is subtracted into the association of the first event after optimization uncertainty, second thing
Part is associated with uncertainty, obtains the uncertainty difference.
It is described to obtain the step of recommendation novelty that candidate applies is spent and include 8. according to the method described in claim 1, wherein：
Any other one candidate application except being applied with the candidate is applied as a comparison, from the historical behavior data
It is middle to obtain historical behavior value of the target user to the preset intended application behavior of the comparison application implementation；
It is applied for each comparison, it is that candidate application and the comparison are applied, corresponding with the intended application behavior
The historical context degree is multiplied with the corresponding historical behavior value, obtains the recommendation of the corresponding opposite comparison application of the candidate
Novelty value；
Greatest measure is chosen in the novel value of the whole recommendation of acquisition, as the recommendation novelty degree.
9. according to the method described in claim 1, wherein,
The recommendation condition is that the recommendation novelty degree carries out the ranking value after descending sort in preset numberical range；
And/or
The application behavior includes at least to click and applies, downloads application, installation application, using using one of this.
10. a kind of applying recommendation apparatus, wherein including：
Degree of association acquiring unit, for obtaining the historical context degree in candidate set of applications between any two candidate application；
Wherein, the candidate set of applications includes multiple candidate applications；The historical context degree is corresponding two candidates
Apply the metric that associated application event occurs in preset measurement period；The associated application event is corresponding two institutes
State the event that application affairs occur for candidate association；The application affairs are that corresponding application practices behavior by user
Event；
Data capture unit, the historical usage behavioral data for obtaining target user；
Wherein, the historical usage behavioral data is that the target user answers each candidate in the measurement period
With the implementation historical data using behavior；
Novel degree acquiring unit, for being applied for each candidate, according to candidate application and any other institute described in this
The historical context degree between candidate application and the historical usage behavioral data are stated, obtains candidate application for described
The recommendation novelty degree of target user；
Using recommendation unit, the candidate application that preset recommendation condition is met for choosing the recommendation novelty degree is used as mesh
Mark application, recommends the target user.
11. a kind of electronic equipment, wherein including：
Memory, for storing executable instruction；
Processor runs the electronic equipment and executes such as claim 1-9 institutes for the control according to the executable instruction
Any one application recommendation method stated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810266636.9A CN108596711B (en) | 2018-03-28 | 2018-03-28 | Application recommendation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810266636.9A CN108596711B (en) | 2018-03-28 | 2018-03-28 | Application recommendation method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108596711A true CN108596711A (en) | 2018-09-28 |
| CN108596711B CN108596711B (en) | 2021-04-23 |
Family
ID=63623850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810266636.9A Active CN108596711B (en) | 2018-03-28 | 2018-03-28 | Application recommendation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596711B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111061979A (en) * | 2018-10-17 | 2020-04-24 | 北京字节跳动网络技术有限公司 | User label pushing method and device, electronic equipment and medium |
| CN111222030A (en) * | 2018-11-27 | 2020-06-02 | 阿里巴巴集团控股有限公司 | Information recommendation method and device and electronic equipment |
| CN111782925A (en) * | 2019-04-04 | 2020-10-16 | 阿里巴巴集团控股有限公司 | Item recommendation method, device, equipment, system and readable storage medium |
| CN111782925B (en) * | 2019-04-04 | 2024-05-14 | 阿里巴巴集团控股有限公司 | Item recommendation method, device, equipment, system and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100161619A1 (en) * | 2008-12-18 | 2010-06-24 | Lamere Paul B | Method and Apparatus for Generating Recommendations From Descriptive Information |
| CN105868279A (en) * | 2016-03-21 | 2016-08-17 | 广东欧珀移动通信有限公司 | Application recommendation method and server |
| CN106126537A (en) * | 2016-06-14 | 2016-11-16 | 中国联合网络通信集团有限公司 | Method and device is recommended in a kind of application |
| CN106682054A (en) * | 2016-05-24 | 2017-05-17 | 腾讯科技（深圳）有限公司 | Terminal application recommendation method, terminal application recommendation device and terminal application recommendation system |
| CN107767228A (en) * | 2017-10-31 | 2018-03-06 | 广东欧珀移动通信有限公司 | Using recommendation method, apparatus, terminal device and storage medium |
| CN107766546A (en) * | 2017-10-31 | 2018-03-06 | 广东欧珀移动通信有限公司 | Using recommendation method, apparatus, storage medium and terminal device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880501B (en) * | 2012-07-24 | 2016-05-25 | 北京奇虎科技有限公司 | Implementation method, device and system that application is recommended |
| CN106777354A (en) * | 2017-01-17 | 2017-05-31 | 腾讯科技（深圳）有限公司 | Promotion message freshness determines method and device |
| CN107562830A (en) * | 2017-08-22 | 2018-01-09 | 广东小天才科技有限公司 | One kind applies recommendation method and application server |
| CN107729542B (en) * | 2017-10-31 | 2021-05-04 | 咪咕音乐有限公司 | Information scoring method and device and storage medium |
-
2018
- 2018-03-28 CN CN201810266636.9A patent/CN108596711B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100161619A1 (en) * | 2008-12-18 | 2010-06-24 | Lamere Paul B | Method and Apparatus for Generating Recommendations From Descriptive Information |
| CN105868279A (en) * | 2016-03-21 | 2016-08-17 | 广东欧珀移动通信有限公司 | Application recommendation method and server |
| CN106682054A (en) * | 2016-05-24 | 2017-05-17 | 腾讯科技（深圳）有限公司 | Terminal application recommendation method, terminal application recommendation device and terminal application recommendation system |
| CN106126537A (en) * | 2016-06-14 | 2016-11-16 | 中国联合网络通信集团有限公司 | Method and device is recommended in a kind of application |
| CN107767228A (en) * | 2017-10-31 | 2018-03-06 | 广东欧珀移动通信有限公司 | Using recommendation method, apparatus, terminal device and storage medium |
| CN107766546A (en) * | 2017-10-31 | 2018-03-06 | 广东欧珀移动通信有限公司 | Using recommendation method, apparatus, storage medium and terminal device |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111061979A (en) * | 2018-10-17 | 2020-04-24 | 北京字节跳动网络技术有限公司 | User label pushing method and device, electronic equipment and medium |
| CN111061979B (en) * | 2018-10-17 | 2023-04-21 | 北京字节跳动网络技术有限公司 | User tag pushing method and device, electronic equipment and medium |
| CN111222030A (en) * | 2018-11-27 | 2020-06-02 | 阿里巴巴集团控股有限公司 | Information recommendation method and device and electronic equipment |
| CN111222030B (en) * | 2018-11-27 | 2023-10-20 | 阿里巴巴集团控股有限公司 | Information recommendation method and device and electronic equipment |
| CN111782925A (en) * | 2019-04-04 | 2020-10-16 | 阿里巴巴集团控股有限公司 | Item recommendation method, device, equipment, system and readable storage medium |
| CN111782925B (en) * | 2019-04-04 | 2024-05-14 | 阿里巴巴集团控股有限公司 | Item recommendation method, device, equipment, system and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108596711B (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10044862B1 (en) | Dynamic topic guidance in the context of multi-round conversation | |
| US10021169B2 (en) | Mobile application daily user engagement scores and user profiles | |
| CN110832511A (en) | System and method for learning on distributed devices with data dependent availability | |
| CN111222030B (en) | Information recommendation method and device and electronic equipment | |
| CN108156205A (en) | Information push method, client, server-side and programmable device | |
| CN105653737A (en) | Method, equipment and electronic equipment for content document sorting | |
| US20170017908A1 (en) | Churn risk scoring using call network analysis | |
| CN108259546A (en) | Information push method, equipment and programmable device | |
| CN110166276A (en) | A kind of localization method, device, terminal device and the medium of frame synchronization exception | |
| CN110096496A (en) | A kind of form validation method, relevant apparatus and equipment | |
| CN109388674A (en) | Data processing method, device, equipment and readable storage medium storing program for executing | |
| CN111311030B (en) | User credit risk prediction method and device based on influence factor detection | |
| US20170372347A1 (en) | Sequence-based marketing attribution model for customer journeys | |
| CN105228243A (en) | Determine the method and apparatus of the position of mobile device users | |
| EP3138067A1 (en) | Platform for contextual marketing based on transactional behavioral data | |
| CN106599191B (en) | User attribute analysis method and device | |
| CN109062963B (en) | Self-media recommendation method and device and electronic equipment | |
| CN108596711A (en) | Using recommendation method, apparatus and electronic equipment | |
| JPWO2016002133A1 (en) | Prediction system and prediction method | |
| US10699450B2 (en) | Interactive tool for causal graph construction | |
| CN113065882A (en) | Commodity processing method and device and electronic equipment | |
| CN107870912A (en) | Article quality score method, equipment, client, server and programmable device | |
| US20160085889A1 (en) | Probabilistic simulation scenario design by using multiple conditional and nested probability distribution input functions | |
| CN113836437B (en) | Method for post recommendation, electronic device and storage medium | |
| US20180198749A1 (en) | Time and sentiment based messaging |
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 |
Effective date of registration: 20200527 Address after: 310051 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, room 146-150, first floor, No. 07, Whampoa Avenue, Tianhe District, Guangdong, Guangzhou Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |