CN106202242A - A kind of application program recommends method and apparatus - Google Patents
A kind of application program recommends method and apparatus Download PDFInfo
- Publication number
- CN106202242A CN106202242A CN201610496462.6A CN201610496462A CN106202242A CN 106202242 A CN106202242 A CN 106202242A CN 201610496462 A CN201610496462 A CN 201610496462A CN 106202242 A CN106202242 A CN 106202242A
- Authority
- CN
- China
- Prior art keywords
- application program
- rank
- rank value
- default
- weight coefficient
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present application provides a kind of application program and recommends method, including: obtain user behavior information;Calculate the first similarity presetting application program with described user behavior information, use described first similarity, generate the first rank value of described default application program;Calculate the second similarity of described default application program and default characteristic, use described second similarity, generate the second rank value of described default application program;Use described first rank value, described second rank value and default weight coefficient, generate the Rank scores of described default application program;Described application program is represented according to described Rank scores.What the embodiment of the present application provided uses weight coefficient to merge user behavior information and the Rank scores computational methods of default characteristic, energy preferably association reaction user behavior information and the dependency of default characteristic so that the application program of recommendation more meets user preference.
Description
Technical field
The application relates to field of computer technology, particularly relates to a kind of application program and recommends method and a kind of application program
Recommendation apparatus.
Background technology
Along with the quick increase of application program, each application platform is to solve user to select the problem of difficulty, opens one after another
Send out the recommendation function of " related application ".
On the whole the associated recommendation function of current application generates based on following three kinds of modes: 1, similarity based on user behavior
Function calculates;2, temperature ranking based on application content calculates, 3, similarity based on user behavior and the temperature of application content
The simple weighted average algorithm of ranking.
First kind of way considers the similarity between user behavior, is weaker than based on application in the interpretability of associated recommendation
The temperature ranking of content calculates, simultaneously need to face cold start-up problem.Second way novelty degree in recommendation results is not enough, meeting
Duplicate recommendation a certain application situation repeatedly.The third mode avoids and individually uses what a kind of way of recommendation brought to ask
Topic, but the feelings that the dependency span of the similarity of user behavior and the temperature ranking of application content is differed greatly
Condition, is difficult to provide dependency accurately only with simple linear weighted function and describes so that the application program of recommendation can not be accurate
Coupling user preference.
Summary of the invention
In view of the above problems, it is proposed that the embodiment of the present application is to provide one to overcome the problems referred to above or at least in part
A kind of application program solving the problems referred to above recommends method and corresponding a kind of application program recommendation apparatus.
In order to solve the problems referred to above, the embodiment of the present application discloses a kind of application program and recommends method, including:
Obtain user behavior information;
Calculate the first similarity presetting application program with described user behavior information, use described first similarity, raw
Become the first rank value of described default application program;
Calculate the second similarity of described default application program and default characteristic, use described second similarity, raw
Become the second rank value of described default application program;
Use described first rank value, described second rank value and default weight coefficient, generate described default application
The Rank scores of program;
Described application program is represented according to described Rank scores.
Preferably, described default weight coefficient includes: the first weight coefficient and the second weight coefficient;Described in described employing
First rank value, described second rank value and default weight coefficient, generate the Rank scores of described default application program
Step includes:
First rank value of application program is multiplied by described first weight coefficient, obtains the first weighting rank value;
Second rank value of application program is multiplied by described second weight coefficient, obtains the second weighting rank value;
By the product of described first weighting rank value with described second weighting rank value, divided by described first weighting rank value
With described second weighting rank value and, obtain Rank scores.
Preferably, described represent the step of described application program according to described Rank scores and include:
By the Rank scores of described default application program, carry out ranking by little to big order;
By the rank order of Rank scores, the application program of forward predetermined number is as destination application;
Represent described destination application.
Preferably, also include:
Obtain the content temperature ranking of application program;
Using the content of the application program of temperature top ranked as described default characteristic.
Preferably, also include:
Obtain input search content;
Using described input search content as described default characteristic.
Meanwhile, the embodiment of the present application also discloses a kind of application program recommendation apparatus, including:
Behavioural information acquisition module, is used for obtaining user behavior information;
First rank value computing module, similar to the first of described user behavior information for calculating default application program
Degree, uses described first similarity, generates the first rank value of described default application program;
Second rank value computing module, similar to the second of default characteristic for calculating described default application program
Degree, uses described second similarity, generates the second rank value of described default application program;
Rank scores computing module, for using described first rank value, described second rank value and default weighting
Coefficient, generates the Rank scores of described default application program;
Represent module, for representing described application program according to described Rank scores.
Preferably, described default weight coefficient includes: the first weight coefficient and the second weight coefficient;Rank scores calculates
Module includes:
First weighting rank value calculating sub module, for being multiplied by described first weighting system by the first rank value of application program
Number, obtains the first weighting rank value;
Second weighting rank value calculating sub module, for being multiplied by described second weighting system by the second rank value of application program
Number, obtains the second weighting rank value;
Weighted calculation submodule, for the product by described first weighting rank value with described second weighting rank value, removes
With described first weighting rank value with described second weighting rank value and, obtain Rank scores.
Preferably, represent module described in include:
Scoring ranking submodule, for by the Rank scores of described default application program, being arranged to big order as little
Name;
Destination application determines submodule, for by the rank order of Rank scores, the application of forward predetermined number
Program is as destination application;
Destination application represents submodule, is used for representing described destination application.
Preferably, also include:
Temperature ranking acquisition module, for obtaining the content temperature ranking of application program;
First presets characteristic determines module, is used for the content of the application program of temperature top ranked as described pre-
If characteristic.
Preferably, also include:
Search content obtaining module, is used for obtaining input search content;
Second presets characteristic determines module, for described input is searched for content as described default characteristic.
The embodiment of the present application includes advantages below:
The embodiment of the present application is by using based on application program and the first of the first similarity of described user behavior information
Rank value, the second rank value based on application program Yu the second similarity of default characteristic (such as, Hot Contents), and
The weight coefficient preset, the Rank scores of calculated application program, is that user recommends application program by Rank scores.This Shen
Please merge user behavior information and the Rank scores computational methods of default characteristic, energy by the weight coefficient that uses that provides of embodiment
Preferably association reaction user behavior information and the dependency of default characteristic so that the application program of recommendation more meets user
Preference.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of a kind of application program recommendation embodiment of the method 1 of the application;
Fig. 2 is the flow chart of steps of a kind of application program recommendation embodiment of the method 2 of the application;
Fig. 3 is the flow chart of steps of a kind of application program recommendation embodiment of the method 3 of the application;
Fig. 4 is the structured flowchart of a kind of application program recommendation apparatus embodiment of the application.
Detailed description of the invention
Understandable for enabling the above-mentioned purpose of the application, feature and advantage to become apparent from, real with concrete below in conjunction with the accompanying drawings
The application is described in further detail by mode of executing.
One of core idea of the embodiment of the present application is, uses based on application program and described user behavior information the
First rank value of one similarity, and the second rank value based on application program Yu the second similarity of default characteristic, meter
The Rank scores of the application program obtained, is that user recommends application program by Rank scores.
With reference to Fig. 1, it is shown that a kind of application program of the application recommends the flow chart of steps of embodiment of the method 1, specifically may be used
To comprise the steps:
Step 101, obtains user behavior information;
User behavior information is, the user preferences letter obtained according to the service condition analysis of application program in user terminal
Breath.
Concrete, application platform, can be according to the use duration of each application program, it is judged that obtain the happiness of user
Good.Such as, user uses time of certain net cast application program the longest, then may determine that user likes watching video straight
Broadcast.The most such as, user uses time of game class application program the longest, then may determine that user likes playing game.
Furthermore it is also possible to the quantity of the various types of application programs according to user installation, it is judged that the application that user likes
Program Type.Such as, the game class application program installed in the terminal of user is most, then judge that user likes playing game.
Step 102, calculates the first similarity presetting application program with described user behavior information, uses described first phase
Like degree, generate the first rank value of described default application program;
User behavior information can be the hobby of user, and application platform can calculate the application program that some are to be promoted
And the similarity between user preferences.Such as, user preferences is culinary art class application program;Application A is that picture editting should
Use program;Application program B is culinary art class application program;Application program C is dietary management application program.According to certain similarity
Algorithm, the similarity being calculated between application A, B, C and user preferences is respectively 0%, and 100%, 50%.According to application
Similarity between program and user preferences is ranked up from big to small, the rank value of the program that is applied.Rank value, is ranking
The value of order.Such as, be ranked up from big to small according to the similarity between application program and user preferences, application A, B,
The rank order of C is: application program B, application program C, application A.Application program B rank order is the 1st, i.e. its ranking
Value is 1;Application program C rank order is the 2nd, i.e. its rank value is 2;Application A rank order is the 3rd, i.e. its row
Name value is 3.
Step 103, calculates the second similarity of described default application program and default characteristic, uses described second phase
Like degree, generate the second rank value of described default application program;
In the embodiment of the present application, default characteristic can be the application program that in application platform, download is most
Type, it is also possible to be the last search content in application platform input of user.
Such as, most application category of downloading of current application program platform is game class application program.Application journey
Sequence A is game class application program;Application program B is video application;Application program C is healthy class application program.According to one
Fixed similarity algorithm, the similarity being calculated application A, B, C and game class application program is respectively 100%, and 0%,
0%.It is ranked up from big to small with the similarity of game class application program according to application A, B, C, program A that is applied,
The rank value of B, C.
The such as rank order of application A, B, C is: application A, application program B and application program C.Application program
A rank order is the 1st, i.e. its rank value is 1;The rank order of application program B and application program C is the 2nd, i.e. its ranking
Value is 2.
Step 104, uses described first rank value, described second rank value and default weight coefficient, generates described
Preset the Rank scores of application program;
Use the first rank value of application program, the second rank value and default weight coefficient, calculate application program
Rank scores.
Step 105, represents described application program according to described Rank scores.
According to the Rank scores of application program, recommend application program to user.
The embodiment of the present application is by using based on application program and the first of the first similarity of described user behavior information
Rank value, the second rank value based on application program Yu the second similarity of default characteristic, and the weight coefficient preset,
The Rank scores of calculated application program, is that user recommends application program by Rank scores.The embodiment of the present application provides
Weight coefficient is used to merge user behavior information and the Rank scores computational methods of default characteristic, can more preferable association reaction
User behavior information and the dependency of default characteristic so that the application program of recommendation more meets user preference.
With reference to Fig. 2, it is shown that a kind of application program of the application recommends the flow chart of steps of embodiment of the method 2, specifically may be used
To comprise the steps:
Step 201, obtains the content temperature ranking of application program;
The content focus ranking of application program, can be the download ranking of classification belonging to application program.
Concrete, application platform can be added up in a period of time, be downloaded the application program that number of times is more;Application journey
Sequence platform the classification belonging to the application program more by being downloaded number of times can carry out ranking, the content focus of the program that is applied
Ranking.
Step 202, using the content of the application program of temperature top ranked as default characteristic;
The content of the application program of temperature top ranked is specifically as follows, and is downloaded the application category that number of times is most.
The application category that application platform is most by being downloaded number of times, as default characteristic.
Step 203, obtains user behavior information;
Step 204, calculates the first similarity presetting application program with described user behavior information, uses described first phase
Like degree, generate the first rank value of described default application program;
Step 205, calculates the second similarity of described default application program and default characteristic, uses described second phase
Like degree, generate the second rank value of described default application program;
Step 206, uses described first rank value, described second rank value and default weight coefficient, generates described
Preset the Rank scores of application program;
In a kind of preferred exemplary of the embodiment of the present application, described default weight coefficient includes: the first weight coefficient and
Second weight coefficient;Described step 206 specifically can include following sub-step:
Sub-step S11, is multiplied by described first weight coefficient by the first rank value of application program, obtains the first weighting ranking
Value;
Sub-step S12, is multiplied by described second weight coefficient by the second rank value of application program, obtains the second weighting ranking
Value;
Sub-step S13, by the product of described first weighting rank value with described second weighting rank value, divided by described first
Weighting rank value with described second weighting rank value and, obtain Rank scores.
In the embodiment of the present application, regulate with the first weight coefficient and the second weight coefficient, the first rank value and second row
The impact of name-value pair Rank scores.
Concrete, if the first rank value based on application program Yu the first similarity of user behavior information is r1;If base
The second rank value in application program Yu the second similarity of default characteristic is r2;First weight coefficient is α;Second weighting
Coefficient is β.
The Rank scores of application program is:
First weight coefficient is α and the second weight coefficient is that β should not differ too big, concrete, can be by the first weighting system
Number is set to 0-1. for the span of α and the second weight coefficient β
Such as, the first weight coefficient is that α is set to 0.4;Second weight coefficient β is set to 0.6;If the of application A
One rank value is 1;Second rank value is 3;Then the Rank scores of application A is: 0.33;
If first rank value of application program B is 2;Second rank value is 1;Then the Rank scores of application program B is 0.34;
If first rank value of application program C is 3;Second rank value is 2;Then the Rank scores of application program C is 0.6.
Step 207, represents described application program according to described Rank scores.
In a kind of preferred exemplary of the embodiment of the present application, described step 207 specifically can include following sub-step:
Sub-step S21, by the Rank scores of described default application program, carries out ranking by little to big order;
Such as, the Rank scores of user program A is 0.33;The Rank scores of application program B is 0.34;Application program C's
Rank scores is 0.6.By being ranked up from small to large, then the first entitled application A, the second entitled application program B, third
For application program C.
Sub-step S22, by the rank order of Rank scores, the application program of forward predetermined number is as intended application journey
Sequence;
Predetermined number can be by application platform sets itself.Such as, using two forward application programs as target
Program, will carry out ranking from small to large by Rank scores, ranks the first, two application programs of second are as intended application
Program.
Sub-step S23, represents described destination application.
Application platform recommends destination application to user.
Rank scores computational methods according to the embodiment of the present application, when certain application program is only at a certain similarity meter
When there is ranking in calculation, its final ranking keeps constant;When this is applied and all has ranking in two kinds of Similarity Measure, it is final
Rank value is less than the least rank value.
With reference to Fig. 3, it is shown that a kind of application program of the application recommends the flow chart of steps of embodiment of the method 3, specifically may be used
To comprise the steps:
Step 301, obtains input search content;
Application platform obtains the search content of user's input.
Step 302, using described input search content as described default characteristic;
Such as user's input: browser;Then application platform using browser as default characteristic.
Step 303, obtains user behavior information;
Step 304, calculates the first similarity presetting application program with described user behavior information, uses described first phase
Like degree, generate the first rank value of described default application program;
Step 305, calculates the second similarity of described default application program and default characteristic, uses described second phase
Like degree, generate the second rank value of described default application program;
Step 306, uses described first rank value, described second rank value and default weight coefficient, generates described
Preset the Rank scores of application program;
In a kind of preferred exemplary of the embodiment of the present application, described default weight coefficient includes: the first weight coefficient and
Second weight coefficient;Described step 306 specifically can include following sub-step:
Sub-step S31, is multiplied by described first weight coefficient by the first rank value of application program, obtains the first weighting ranking
Value;
Sub-step S32, is multiplied by described second weight coefficient by the second rank value of application program, obtains the second weighting ranking
Value;
Sub-step S33, by the product of described first weighting rank value with described second weighting rank value, divided by described first
Weighting rank value with described second weighting rank value and, obtain Rank scores.
Step 307, represents described application program according to described Rank scores.
In a kind of preferred exemplary of the embodiment of the present application, described step 307 specifically can include following sub-step:
Sub-step S41, by the Rank scores of described default application program, carries out ranking by little to big order;
Sub-step S42, by the rank order of Rank scores, the application program of forward predetermined number is as intended application journey
Sequence;
Sub-step S43, represents described destination application.
It should be noted that for embodiment of the method, in order to be briefly described, therefore it is all expressed as a series of action group
Closing, but those skilled in the art should know, the embodiment of the present application is not limited by described sequence of movement, because depending on
According to the embodiment of the present application, some step can use other orders or carry out simultaneously.Secondly, those skilled in the art also should
Knowing, embodiment described in this description belongs to preferred embodiment, and involved action not necessarily the application implements
Necessary to example.
With reference to Fig. 4, it is shown that the structured flowchart of a kind of application program recommendation apparatus embodiment of the application, specifically can wrap
Include such as lower module:
Behavioural information acquisition module 41, is used for obtaining user behavior information;
First rank value computing module 42, similar to the first of described user behavior information for calculating default application program
Degree, uses described first similarity, generates the first rank value of described default application program;
Second rank value computing module 43, similar to the second of default characteristic for calculating described default application program
Degree, uses described second similarity, generates the second rank value of described default application program;
Rank scores computing module 44, for using described first rank value, described second rank value and default adding
Weight coefficient, generates the Rank scores of described default application program;
Represent module 45, for representing described application program according to described Rank scores.
In a kind of preferred exemplary of the embodiment of the present application, described default weight coefficient includes: the first weight coefficient and
Second weight coefficient;Rank scores computing module 44 may include that
First weighting rank value calculating sub module, for being multiplied by described first weighting system by the first rank value of application program
Number, obtains the first weighting rank value;
Second weighting rank value calculating sub module, for being multiplied by described second weighting system by the second rank value of application program
Number, obtains the second weighting rank value;
Weighted calculation submodule, for the product by described first weighting rank value with described second weighting rank value, removes
With described first weighting rank value with described second weighting rank value and, obtain Rank scores.
In a kind of preferred exemplary of the embodiment of the present application, described in represent module 45 and may include that
Scoring ranking submodule, for by the Rank scores of described default application program, being arranged to big order as little
Name;
Destination application determines submodule, for by the rank order of Rank scores, the application of forward predetermined number
Program is as destination application;
Destination application represents submodule, is used for representing described destination application.
In a kind of preferred exemplary of the embodiment of the present application, described device can also include:
Temperature ranking acquisition module, for obtaining the content temperature ranking of application program;
First presets characteristic determines module, is used for the content of the application program of temperature top ranked as described pre-
If characteristic.
In the another kind of preferred exemplary of the embodiment of the present application, described device can also include:
Search content obtaining module, is used for obtaining input search content;
Second presets characteristic determines module, for described input is searched for content as described default characteristic.
For device embodiment, due to itself and embodiment of the method basic simlarity, so describe is fairly simple, relevant
Part sees the part of embodiment of the method and illustrates.
Each embodiment in this specification all uses the mode gone forward one by one to describe, what each embodiment stressed is with
The difference of other embodiments, between each embodiment, identical similar part sees mutually.
Those skilled in the art are it should be appreciated that the embodiment of the embodiment of the present application can be provided as method, device or calculate
Machine program product.Therefore, the embodiment of the present application can use complete hardware embodiment, complete software implementation or combine software and
The form of the embodiment of hardware aspect.And, the embodiment of the present application can use one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) of program code
The form of the computer program implemented.
The embodiment of the present application is with reference to method, terminal unit (system) and the computer program according to the embodiment of the present application
The flow chart of product and/or block diagram describe.It should be understood that can be by computer program instructions flowchart and/or block diagram
In each flow process and/or the flow process in square frame and flow chart and/or block diagram and/or the combination of square frame.These can be provided
Computer program instructions sets to general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to produce a machine so that held by the processor of computer or other programmable data processing terminal equipment
The instruction of row produces for realizing in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame
The device of the function specified.
These computer program instructions may be alternatively stored in and can guide computer or other programmable data processing terminal equipment
In the computer-readable memory worked in a specific way so that the instruction being stored in this computer-readable memory produces bag
Including the manufacture of command device, this command device realizes in one flow process of flow chart or multiple flow process and/or one side of block diagram
The function specified in frame or multiple square frame.
These computer program instructions also can be loaded on computer or other programmable data processing terminal equipment so that
On computer or other programmable terminal equipment, execution sequence of operations step is to produce computer implemented process, thus
The instruction performed on computer or other programmable terminal equipment provides for realizing in one flow process of flow chart or multiple flow process
And/or the step of the function specified in one square frame of block diagram or multiple square frame.
Although having been described for the preferred embodiment of the embodiment of the present application, but those skilled in the art once knowing base
This creativeness concept, then can make other change and amendment to these embodiments.So, claims are intended to be construed to
The all changes including preferred embodiment and falling into the embodiment of the present application scope and amendment.
Finally, in addition it is also necessary to explanation, in this article, the relational terms of such as first and second or the like be used merely to by
One entity or operation separate with another entity or operating space, and not necessarily require or imply these entities or operation
Between exist any this reality relation or order.And, term " includes ", " comprising " or its any other variant meaning
Containing comprising of nonexcludability, so that include that the process of a series of key element, method, article or terminal unit not only wrap
Include those key elements, but also include other key elements being not expressly set out, or also include for this process, method, article
Or the key element that terminal unit is intrinsic.In the case of there is no more restriction, by wanting that statement " including ... " limits
Element, it is not excluded that there is also other identical element in including the process of described key element, method, article or terminal unit.
Above a kind of application program provided herein is recommended method and a kind of application program recommendation apparatus, carries out
Being discussed in detail, principle and the embodiment of the application are set forth by specific case used herein, above example
Illustrate that being only intended to help understands the present processes and core concept thereof;Simultaneously for one of ordinary skill in the art, depend on
According to the thought of the application, the most all will change, in sum, this specification content
Should not be construed as the restriction to the application.
Claims (10)
1. an application program recommends method, it is characterised in that including:
Obtain user behavior information;
Calculate the first similarity presetting application program with described user behavior information, use described first similarity, generate institute
State the first rank value of default application program;
Calculate the second similarity of described default application program and default characteristic, use described second similarity, generate institute
State the second rank value of default application program;
Use described first rank value, described second rank value and default weight coefficient, generate described default application program
Rank scores;
Described application program is represented according to described Rank scores.
Method the most according to claim 1, it is characterised in that described default weight coefficient includes: the first weight coefficient
With the second weight coefficient;Described first rank value of described employing, described second rank value and default weight coefficient, generate institute
The step of the Rank scores stating default application program includes:
First rank value of application program is multiplied by described first weight coefficient, obtains the first weighting rank value;
Second rank value of application program is multiplied by described second weight coefficient, obtains the second weighting rank value;
By the product of described first weighting rank value with described second weighting rank value, divided by described first weighting rank value and institute
State the sum of the second weighting rank value, obtain Rank scores.
Method the most according to claim 1 and 2, it is characterised in that described represent described application according to described Rank scores
The step of program includes:
By the Rank scores of described default application program, carry out ranking by little to big order;
By the rank order of Rank scores, the application program of forward predetermined number is as destination application;
Represent described destination application.
Method the most according to claim 1, it is characterised in that also include:
Obtain the content temperature ranking of application program;
Using the content of the application program of temperature top ranked as described default characteristic.
Method the most according to claim 1, it is characterised in that also include:
Obtain input search content;
Using described input search content as described default characteristic.
6. an application program recommendation apparatus, it is characterised in that including:
Behavioural information acquisition module, is used for obtaining user behavior information;
First rank value computing module, for calculating the first similarity of default application program and described user behavior information, adopts
By described first similarity, generate the first rank value of described default application program;
Second rank value computing module, for calculating the second similarity of described default application program and default characteristic, adopts
By described second similarity, generate the second rank value of described default application program;
Rank scores computing module, for using described first rank value, described second rank value and default weight coefficient,
Generate the Rank scores of described default application program;
Represent module, for representing described application program according to described Rank scores.
Device the most according to claim 6, it is characterised in that described default weight coefficient includes: the first weight coefficient
With the second weight coefficient;Rank scores computing module includes:
First weighting rank value calculating sub module, for the first rank value of application program is multiplied by described first weight coefficient,
Obtain the first weighting rank value;
Second weighting rank value calculating sub module, for the second rank value of application program is multiplied by described second weight coefficient,
Obtain the second weighting rank value;
Weighted calculation submodule, for the product by described first weighting rank value with described second weighting rank value, divided by institute
State the first weighting rank value with described second weighting rank value and, obtain Rank scores.
8. according to the device described in claim 6 or 7, it is characterised in that described in represent module and include:
Scoring ranking submodule, for by the Rank scores of described default application program, carrying out ranking by little to big order;
Destination application determines submodule, for by the rank order of Rank scores, the application program of forward predetermined number
As destination application;
Destination application represents submodule, is used for representing described destination application.
Device the most according to claim 6, it is characterised in that also include:
Temperature ranking acquisition module, for obtaining the content temperature ranking of application program;
First presets characteristic determines module, is used for the content of the application program of temperature top ranked as described default spy
Levy data.
Device the most according to claim 6, it is characterised in that also include:
Search content obtaining module, is used for obtaining input search content;
Second presets characteristic determines module, for described input is searched for content as described default characteristic.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610496462.6A CN106202242A (en) | 2016-06-28 | 2016-06-28 | A kind of application program recommends method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610496462.6A CN106202242A (en) | 2016-06-28 | 2016-06-28 | A kind of application program recommends method and apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106202242A true CN106202242A (en) | 2016-12-07 |
Family
ID=57462643
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610496462.6A Pending CN106202242A (en) | 2016-06-28 | 2016-06-28 | A kind of application program recommends method and apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106202242A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503269A (en) * | 2016-12-08 | 2017-03-15 | 广州优视网络科技有限公司 | Method, device and server that application is recommended |
CN107832859A (en) * | 2017-10-27 | 2018-03-23 | 广东欧珀移动通信有限公司 | Subscription list of playing generation method, device and server |
CN109064276A (en) * | 2018-07-25 | 2018-12-21 | 中国联合网络通信集团有限公司 | A kind of mobile terminal application sort method and system |
CN110163460A (en) * | 2018-03-30 | 2019-08-23 | 腾讯科技(深圳)有限公司 | A kind of method and apparatus determined using score value |
CN114003826A (en) * | 2021-12-31 | 2022-02-01 | 思创数码科技股份有限公司 | Resource directory recommendation method and device, readable storage medium and electronic equipment |
CN114860918A (en) * | 2022-05-25 | 2022-08-05 | 重庆邮电大学 | Mobile application recommendation method and device fusing multi-source reliable information |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103235815A (en) * | 2013-04-25 | 2013-08-07 | 北京小米科技有限责任公司 | Display method and display device for application software |
CN103678584A (en) * | 2013-12-11 | 2014-03-26 | 中国联合网络通信集团有限公司 | Application sequencing method and device based on application searching |
CN105468222A (en) * | 2014-08-21 | 2016-04-06 | 深圳富泰宏精密工业有限公司 | Application arrangement system and method |
-
2016
- 2016-06-28 CN CN201610496462.6A patent/CN106202242A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103235815A (en) * | 2013-04-25 | 2013-08-07 | 北京小米科技有限责任公司 | Display method and display device for application software |
CN103678584A (en) * | 2013-12-11 | 2014-03-26 | 中国联合网络通信集团有限公司 | Application sequencing method and device based on application searching |
CN105468222A (en) * | 2014-08-21 | 2016-04-06 | 深圳富泰宏精密工业有限公司 | Application arrangement system and method |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503269A (en) * | 2016-12-08 | 2017-03-15 | 广州优视网络科技有限公司 | Method, device and server that application is recommended |
CN107832859A (en) * | 2017-10-27 | 2018-03-23 | 广东欧珀移动通信有限公司 | Subscription list of playing generation method, device and server |
CN107832859B (en) * | 2017-10-27 | 2020-07-24 | Oppo广东移动通信有限公司 | Game reservation list generation method and device and server |
CN110163460A (en) * | 2018-03-30 | 2019-08-23 | 腾讯科技(深圳)有限公司 | A kind of method and apparatus determined using score value |
CN110163460B (en) * | 2018-03-30 | 2023-09-19 | 腾讯科技(深圳)有限公司 | Method and equipment for determining application score |
CN109064276A (en) * | 2018-07-25 | 2018-12-21 | 中国联合网络通信集团有限公司 | A kind of mobile terminal application sort method and system |
CN114003826A (en) * | 2021-12-31 | 2022-02-01 | 思创数码科技股份有限公司 | Resource directory recommendation method and device, readable storage medium and electronic equipment |
CN114860918A (en) * | 2022-05-25 | 2022-08-05 | 重庆邮电大学 | Mobile application recommendation method and device fusing multi-source reliable information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106202242A (en) | A kind of application program recommends method and apparatus | |
CN107515909B (en) | Video recommendation method and system | |
Schnabel et al. | Using shortlists to support decision making and improve recommender system performance | |
EP4181026A1 (en) | Recommendation model training method and apparatus, recommendation method and apparatus, and computer-readable medium | |
CN104239440B (en) | Search result shows method and apparatus | |
CN105893561A (en) | Ordering method and device | |
CN107341272A (en) | A kind of method for pushing, device and electronic equipment | |
CN106131601A (en) | Video recommendation method and device | |
US8463174B2 (en) | System and methods for sequencing learning objects based upon query and user relevancy | |
CN108122611B (en) | Information recommendation method and device, storage medium and program product | |
CN114007710A (en) | Content item recommendation | |
CN106127506B (en) | recommendation method for solving cold start problem of commodity based on active learning | |
CN110737859A (en) | UP main matching method and device | |
CN109033233B (en) | Live broadcast room recommendation method, storage medium, electronic device and system | |
CN112307344A (en) | Object recommendation model, object recommendation method and device and electronic equipment | |
CN112395496A (en) | Information recommendation method and device, electronic equipment and storage medium | |
Liu et al. | Towards automatic experimentation of educational knowledge | |
CN109493138A (en) | Information recommendation method, device, server and storage medium | |
CN110147514B (en) | Resource display method, device and equipment thereof | |
CN110766513A (en) | Information sorting method and device, electronic equipment and readable storage medium | |
CN107707940A (en) | Video sequencing method, device, server and system | |
CN109636530B (en) | Product determination method, product determination device, electronic equipment and computer-readable storage medium | |
JP6644290B1 (en) | Information processing device and program | |
JP7085486B2 (en) | User behavior data processing method and equipment | |
CN110570271A (en) | information recommendation method and device, electronic equipment and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |
|
RJ01 | Rejection of invention patent application after publication |