CN109040164A - Using recommended method, device, storage medium and computer equipment - Google Patents
Using recommended method, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN109040164A CN109040164A CN201810486760.6A CN201810486760A CN109040164A CN 109040164 A CN109040164 A CN 109040164A CN 201810486760 A CN201810486760 A CN 201810486760A CN 109040164 A CN109040164 A CN 109040164A
- Authority
- CN
- China
- Prior art keywords
- application
- recommended
- user
- matrix
- theme
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention provides a kind of application recommended method, device, storage medium and computer equipment, and the method includes: to obtain the mounted application of user, generates set of applications；It obtains to be recommended using the corresponding application preferences matrix using theme；Wherein, described using theme is the set being made of multiple related applications, preference angle value of the element characterization theme in the application preferences matrix to application；According to application, the set of applications and the application preferences matrix to be recommended, the user is obtained to the preference value of the application to be recommended；Recommend to apply to the user according to the preference value.It is above-mentioned apply recommended method, according to the preference value of application to user recommend in application, can the interested application of recommended user, to improve the competitiveness of product in market.
Description
Technical field
The present invention relates to field of computer technology, specifically, the present invention relates to a kind of application recommended method, device, depositing
Storage media and computer equipment.
Background technique
With the development of internet technology and people correspond to types of applications program demand it is growing day by day, application program fortune
The application program that battalion's platform provides the user with is more and more.However, being limited to the amount of storage of user terminal, user can not be unlimited
Application program is installed, but some interested application programs are selected according to hobby and are installed.
Therefore, application shop needs to recommend good apply to meet the hobby of user to user during operation.So
And how to give user's recommendation interested application program, become the one of application program operation to provide the competitiveness of product in market
A hang-up.
Summary of the invention
The present invention proposes a kind of application recommended method, device, storage medium and computer equipment, to recommend sense emerging to user
The application program of interest improves the competitiveness of product in market.
The present invention provides following scheme:
It is a kind of to apply recommended method, comprising steps of obtaining the mounted application of user, generate set of applications；It obtains wait push away
It recommends using the corresponding application preferences matrix using theme；Wherein, described using theme is the collection being made of multiple related applications
It closes, preference angle value of the element characterization theme in the application preferences matrix to application；According to the application to be recommended, described answer
With set and the application preferences matrix, the user is obtained to the preference value of the application to be recommended；According to described
Preference value recommends to apply to the user.
It is described in one of the embodiments, to recommend to apply to the user according to the preference value, comprising: to obtain
Preference value of the user to all applications to be recommended in application resources bank；According to user in the application resource library each to
The size for recommending the preference value of application, all applications to be recommended are sorted from large to small；It pushes and arranges to the user
The application to be recommended of the forward preset quantity of sequence.
In one of the embodiments, according to application, the set of applications and the application preferences square to be recommended
Battle array, obtains the user to the preference value of the application to be recommended, comprising: described in obtaining from the application preferences matrix
Application to be recommended generates the theme vector of application to be recommended to the preference value of different themes；It is obtained from the application preferences matrix
Each application in the set of applications is taken to generate the corresponding theme vector of each application to the preference value of different themes；According to institute
State the corresponding theme vector of each application and the application collection in the theme vector and the set of applications of application to be recommended
It closes, obtains the user to the preference value of the application to be recommended.
It is described according to every in the theme vector of the application to be recommended and the set of applications in one of the embodiments,
The corresponding theme vector of a application and the set of applications, obtain the user to the preference of the application to be recommended
Value, comprising: obtain the user according to the following formula to the preference value of the application to be recommended:
Wherein, the set of applications of the user u is Su, | Su| indicate the quantity of mounted application in set of applications,
Application to be recommended is that the theme vector using a, using a is Ba, j expression SuIn one application, using j theme vector be Bj,
(u a) indicates user u to the preference value of application a, cos (B to likej,Ba) indicate to seek BjWith BaCosine value.
The corresponding application preferences matrix for applying theme of the application to be recommended in one of the embodiments, by following
Mode obtains: obtaining the installation application message of the sample of users of preset quantity, generates application installation matrix；The sample of users
Installation application message includes the mount message that sample of users installs the application to be recommended；Input matrix master is installed into the application
Preference pattern is inscribed, is obtained to be recommended using the corresponding application preferences matrix using theme；Wherein, the subject matter preferences model is used
In the incidence relation of characterization application installation matrix and the application preferences matrix.
The subject matter preferences model includes subject matter preferences matrix norm of the user to subject matter preferences in one of the embodiments,
The application preferences matrix model of type and theme to application preferences；Input matrix subject matter preferences model is installed into the application, is obtained
It is to be recommended using the corresponding application preferences matrix using theme, comprising: by the application installation Input matrix according to the master
In the loss function that topic preference pattern constructs in advance；The minimum value that the loss function is solved by preset algorithm obtains described
The corresponding subject matter preferences matrix of subject matter preferences matrix model and the corresponding application preferences matrix of the application preferences matrix model, will
The application preferences matrix is as to be recommended using the corresponding application preferences matrix using theme.
The preset algorithm is gradient descent method in one of the embodiments,.
It is a kind of to apply recommendation apparatus, comprising: generation module generates set of applications for obtaining the mounted application of user；
First obtains module, to be recommended using the corresponding application preferences matrix using theme for obtaining；Wherein, described to apply theme
For the set being made of multiple related applications, the preference angle value of element characterization theme in the application preferences matrix to application；
Second obtains module, for obtaining described according to application, the set of applications and the application preferences matrix to be recommended
Preference value of the user to the application to be recommended；Recommending module, for being pushed away according to the preference value to the user
Recommend application.
A kind of storage medium, is stored thereon with computer program；When the computer program is executed by processor, in realization
State application recommended method described in any embodiment.
A kind of computer equipment comprising: one or more processors；Memory；One or more application program, wherein
One or more of application programs are stored in the memory and are configured as being held by one or more of processors
Row, one or more of application programs are configured to carry out the application recommended method according to any of the above-described embodiment.
It is provided by the above embodiment to apply recommended method, the mounted set of applications of user and to be recommended is obtained respectively
Using the corresponding application preferences matrix using theme, further according to it is to be recommended application, the mounted set of applications of user with
And the application preferences matrix of application theme, user is obtained to the preference value of application to be recommended.According to the preference of application
Value can determine whether out that user recommends to user in application, can for the preference of application, therefore according to the preference value of application
The interested application of recommended user, to improve the market competitiveness of application product.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is the interaction in an a kind of embodiment using recommended method provided by the invention between server and client
Schematic diagram；
Fig. 2 is flow chart in an a kind of embodiment using recommended method provided by the invention；
Fig. 3 is flow chart in an embodiment of step S200 provided by the invention；
Fig. 4 is flow chart in an embodiment of step S230 provided by the invention；
Fig. 5 is flow chart in an embodiment of step S300 provided by the invention；
Fig. 6 is the flow chart in a kind of another embodiment using recommended method provided by the invention；
Fig. 7 is the structural schematic diagram in an a kind of embodiment using recommendation apparatus of the present invention；
Fig. 8 is the schematic diagram in one embodiment of computer equipment structure provided by the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form, " first " used herein, " second " are only used for distinguishing same technology special
Sign, is not limited the sequence of the technical characteristic and quantity etc..It is to be further understood that in specification of the invention
The wording " comprising " used refers to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that depositing
Or add other one or more features, integer, step, operation, element, component and/or their group.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term), there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless idealization or meaning too formal otherwise will not be used by specific definitions as here
To explain.
It is provided by the invention a kind of using recommended method, application proposed algorithm of this method based on topic model, it is assumed that every
A user has difference preference to different themes, and each theme has difference preference, preference of the user to different application to each application
It can be obtained by the subject matter preferences matrix of user and the application preferences matrix multiple of theme.This is applied to such as using recommended method
In application environment shown in FIG. 1.
As shown in Figure 1, server 100 and user terminal 300 are located in same 200 environment of network, server 100 and use
Family terminal 300 carries out the interaction of data information by network 200.Server 100 and the quantity of user terminal 300 are not construed as limiting,
It is only used as illustrating shown in Fig. 1.Client is installed, client is third-party application software, is such as applied in user terminal 300
Shop APP (Application, using) etc..User can pass through client end AP P in user terminal 300 and corresponding service
Device 100 carries out information exchange.Client is corresponding with server (Server) end, follows same set of data protocol jointly, so that
Server end can parse mutually the data of other side with client, provide for user using recommendation service.
Server 100 may be, but not limited to, network server, management server, application server, database service
Device, cloud server etc..User terminal 300 may be, but not limited to, smart phone, PC (personal
Computer, PC), tablet computer, personal digital assistant (personal digital assistant, PDA), mobile Internet access set
Standby (mobile Internet device, MID) etc..The operating system of user terminal 300 may be, but not limited to, Android
(Android) system, IOS (iPhone operating system) system, Windows phone system, Windows system
Deng.
In one embodiment, as shown in Fig. 2, application recommended method of the present invention the following steps are included:
S100 obtains the mounted application of user, generates set of applications.
In the present embodiment, server obtains the mounted application of user, and generating includes answering for the mounted application of user
With set.Specifically, server can determine user by obtaining user to the application downloading installation record in application resources bank
Mounted application, and generate corresponding set of applications.Server can obtain default according to the application downloading installation record of user
The mounted application of user in period.
In one embodiment, server can obtain the quantity that the user applied in resources bank was accessed in nearest one day,
Assuming that the quantity of user herein is n.The quantity of all applications is m in resources bank.
Matrix y indicates the matrix of all user installation application messages, size n*m.Every a line indicates the peace of a user
Applicable cases are filled, each column indicates the user installation situation of each application, and 0 indicates to be fitted without, and 1 indicates to be mounted with, such as:
S200 is obtained to be recommended using the corresponding application preferences matrix using theme；Wherein, the application theme is served as reasons
The set of multiple related applications composition, the preference angle value of element characterization theme in the application preferences matrix to application.
Server is obtained with to be recommended using the corresponding application preferences matrix using theme.Wherein, using theme by more
The set of a related application composition.Related application is each application under same subject.Application preferences matrix is indicated in the matrix
In, each element characterizes the preference angle value using theme for application.It indicates: obtaining using the application preferences matrix of theme
Using theme to the preference value of each application under the theme, the application preferences matrix comprising multiple preference values is generated.
In the present embodiment, theme is applied for application to be recommended corresponding one, in the application preferences matrix using theme
Apply theme to the preference value of the application to be recommended including this.
In one embodiment, as shown in figure 3, the corresponding application preferences matrix for applying theme of the application to be recommended, passes through
Following steps obtain:
S210 obtains the installation application message of the sample of users of preset quantity, generates application installation matrix；The sample is used
The installation application message at family includes the mount message that sample of users installs the application to be recommended.
In this embodiment, installation application message includes the information of the application of user terminal installation.Preset quantity sample is used
The installation application message at family includes the application whether each sample of users is equipped in resources bank, is mounted with which of resources bank
Using.Server obtains and records the installation application message of each sample of users, the title of the specific application for obtaining user installation,
And determine which is not installed using user in resources bank.Further, server is believed according to the installation of sample of users application
Breath generates corresponding application and installs matrix.It should be noted that the installation application message packet of sample of users described in the present embodiment
Include the mount message that application to be recommended of the present invention is mounted in sample of users.
The application is installed Input matrix subject matter preferences model by S230, and it is corresponding using theme to obtain application to be recommended
Application preferences matrix；Wherein, the subject matter preferences model is used to characterize using installation matrix and the application preferences matrix
Incidence relation.
In the present embodiment, the subject matter preferences model is used to characterize using installing being associated with for matrix and application preferences matrix
Relationship.It that is to say, the corresponding application using theme will can be obtained partially using installation Input matrix into the subject matter preferences model
Good matrix.
In one embodiment, the subject matter preferences model includes user to the subject matter preferences matrix model of subject matter preferences and master
Inscribe the application preferences matrix model to application preferences.As shown in figure 4, step S230 includes:
S231, in the loss function that application installation Input matrix is constructed in advance according to the subject matter preferences model.
S233 solves the minimum value of the loss function by preset algorithm, obtains the subject matter preferences matrix model pair
The subject matter preferences matrix and the corresponding application preferences matrix of the application preferences matrix model answered make the application preferences matrix
To be to be recommended using the corresponding application preferences matrix using theme.
Wherein, preset algorithm herein is gradient descent method.User characterizes the subject matter preferences matrix model of subject matter preferences
Difference preference degree of each user to different themes.Theme characterizes the application preferences matrix model of application preferences each
Difference preference degree of the theme to each application.Subject matter preferences model can be by user to the subject matter preferences matrix of subject matter preferences
Model is multiplied to obtain with application preferences matrix model of the theme to application preferences.Pass through the corresponding loss of building subject matter preferences model
Function, and when solving loss function minimum value, the above-mentioned subject matter preferences matrix of institute and an application preferences matrix can be found out.The application
Preference matrix is to be recommended using the corresponding application preferences matrix using theme.
In this embodiment, the application installation preparatory structure of Input matrix that will be generated according to the installation application message of sample of users
The subject matter preferences model built up can be obtained to be recommended using the corresponding application preferences matrix using theme.
S300 obtains the user according to application, the set of applications and the application preferences matrix to be recommended
To the preference value of the application to be recommended.
In the present embodiment, by step S100 and step S200, server gets that application to be recommended, user installed
Using the set of applications of formation and to be recommended using the corresponding application preferences matrix using theme.Further, server
According to above three parameter, user can get to the preference value of application to be recommended.
In one embodiment, as shown in figure 5, step S300 the following steps are included:
S310 obtains the application to be recommended to the preference value of different themes from the application preferences matrix, generate to
Recommend the theme vector of application.
In the present embodiment, the application preferences matrix is to be recommended using the corresponding application preferences square using theme
Battle array.Server obtains the preference value that application to be recommended corresponds to different themes from the application preferences matrix.According to each preference value
Generate the theme vector of application to be recommended.
S330 obtains in the set of applications each application to the preference of different themes from the application preferences matrix
Value generates the corresponding theme vector of each application.
It in the present embodiment, include the mounted application of user in the set of applications.Generally, user is mounted answers
With being multiple.It is corresponding not that server obtains each application in the set of applications respectively from the application preferences matrix of application theme
With the preference value of theme, this is generated using corresponding theme vector.For example, the mounted application of user includes using A, using B
With apply C.Server obtains the preference value that different themes are corresponded to using A from the application preferences matrix of application theme, and generation is answered
With the corresponding theme vector a of A.The preference value that different themes are corresponded to using B is obtained from the application preferences matrix of application theme, it is raw
At the corresponding theme vector b of application B.The preference that different themes are corresponded to using C is obtained from the application preferences matrix of application theme
Value generates and applies the corresponding theme vector c of C.
S350, according to the corresponding theme of each application in the theme vector of the application to be recommended and the set of applications to
Amount and the set of applications, obtain the user to the preference value of the application to be recommended.
In the present embodiment, the theme vector of server application to be recommended, user's corresponding theme of mounted application to
Amount and user have installed using corresponding set of applications, obtain user to the preference value of application to be recommended.Specifically,
Server has been installed according to user using the quantitative value of all applications and the theme of application to be recommended in corresponding set of applications
Vector, the corresponding theme vector of the mounted application of user, obtains the preference value of application to be recommended.
In a specific embodiment, server obtains the user to the inclined of the application to be recommended according to the following formula
Good degree value:
Wherein, the set of applications of the user u is Su, | Su| indicate the quantity of mounted application in set of applications,
Application to be recommended is that the theme vector using a, using a is Ba, j expression SuIn one application, using j theme vector be Bj,
(u a) indicates user u to the preference value of application a, cos (B to likej,Ba) indicate to seek BjWith BaCosine value.
S400 recommends to apply according to the preference value to the user.
In the present embodiment, server is according to the preferences of step S100 multiple applications into step S300 available resource library
Degree value recommends to apply according to the preference value of each application to user.
In one embodiment, as shown in fig. 6, step S400 the following steps are included:
S410 obtains user to the preference value of all applications to be recommended in application resources bank.
S430, according to user to the size of the preference value of each application to be recommended in the application resource library, by institute
All applications to be recommended are stated to sort from large to small.
S450 pushes the application to be recommended for the forward preset quantity that sorts to the user.
In the present embodiment, server can get each application in application resource library according to step S100 to step S300
Preference angle value for a user, further according to user for the preference angle value of each application size to it is all apply into
Row sorts from large to small, the application for the preset quantity for recommending sequence forward to user.Preset quantity can be 100, can also be with
It is other numerical value.Alternatively, server obtain preference value highest before preset quantity application according to preference value by greatly to
Small sequence is shown on the terminal screen of user.
It is provided by the above embodiment to apply recommended method, the mounted set of applications of user and to be recommended is obtained respectively
Using the corresponding application preferences matrix using theme, further according to it is to be recommended application, the mounted set of applications of user with
And the application preferences matrix of application theme, user is obtained to the preference value of application to be recommended.According to the preference of application
Value can determine whether out that user recommends to user in application, can for the preference of application, therefore according to the preference value of application
The interested application of recommended user, to improve the competitiveness of product in market.
A specific embodiment presented below, server is described in detail using of the present invention using recommended method
Recommend to apply to user in application environment as shown in Figure 1.
Step 1, server obtains the data information of user installation application, and the application data information of user installation is converted
For real number matrix.Detailed process is as follows:
Variable-definition:
Accessed within n nearest 1 day the number of users of application
The quantity of all applications in m resources bank
Matrix y indicates the matrix of all user installation application messages, size n*m, and every a line indicates the peace of a user
Applicable cases are filled, each column indicates the user installation situation of each application, and 0 indicates to be fitted without, and 1 indicates installation.Such as:
Step 2, subject matter preferences model is defined.
The definition of subject matter preferences model: the thought of subject matter preferences model assumes that each user is different to different application theme
Preference, each application theme have difference preference to each application, and user can be by user to difference to the preference of different application
The application preferences matrix multiple of each application is obtained using the subject matter preferences matrix and theme of theme.It is assumed that using number of topics
Measuring k is manually to preset, and generally takes 100.Subject matter preferences model is as follows:
Y=UV
Wherein, (1) matrix Y indicates the matrix that user forms the preference value of different application.
(2) subject matter preferences matrix of the matrix U expression user to application theme, matrix size n*k, every a line indicate one
Preference of the user to different application theme, the preference of one application theme of each column expression among different users,
The matrix needs to pass through model solution.
(3) matrix V indicates each application preferences matrix using theme to also each application, matrix size k*m, each
Row indicates an application theme to the preference of different application, and each column indicate one and apply between different application theme
Preference, the matrix need to pass through model solution.
Step 3, above-mentioned subject matter preferences matrix and application preferences matrix are solved by building pattern function.In the embodiment party
In formula, above-mentioned subject matter preferences matrix and application preferences matrix are solved by building loss function.It is specific as follows:
The actual installation situation y of available user in step 1 can pass through subject matter preferences model meter in step 2
The installation applicable cases Y of user in predicting is calculated, loss function is defined as follows:
Wherein
It minimizes loss function and finds out U={ ui,, V={ vl,jIt is required model.
Model parameter solves as follows:
To los function, U={ u is solved by gradient descent methodi,, V={ vl,j}
Gradient descent method is as follows:
Step 1: the unified note of all parameters of model is gathered to one, θ={ θ might as well be denoted asi, random given one group in 0-
Between 1, it is set as θ(0), initialize iterative steps k=0
Step 2: iterative calculation
Wherein ρ is used for control convergence speed, takes 0.01
Step 3: judge whether to restrain
IfSo it is returned to θ(k+1), otherwise return to step 2 and continue to calculate, wherein α be one very
Small value can take the ρ of α=0.01
Step 4: generating and apply theme vector
Pass through the available matrix V of the above method={ vl,j, using theme vector are as follows:
Bj={ v1,,v2,,…,vk,}
Step 5: calculating user to the preference of application
If the set of applications of user u installation is Su, a is applied for any one, can be calculated by the above method using a
Theme vector be Ba, user u is calculated to the preference of application a, formula are as follows:
Wherein, (u a) indicates user u to the preference value of application a to like.cos(Bj,Ba) it is to seek vector BjWith vector
BaCosine value.| Su | expression set of applications is SuThe quantity of middle application.
Step 6: recommending to apply to user.
For the user u given, the application of full library all calculated like by above-mentioned formula, and (u a) takes preference value highest
Preceding 100 applications are shown on the user's screen according to the descending sequence of preference.
This motion proposes a kind of application proposed algorithm based on application topic model, on the one hand solves manually to recommend to expend big
The problem of measuring human cost.On the other hand, compared with traditional content-based recommendation method, this method may not need label i.e.
Achievable application is recommended, the good effect taken in practice.
Recommendation apparatus is applied the present invention also provides a kind of.As shown in fig. 7, this using recommendation apparatus include generation module 100,
First, which obtains module 200, second, obtains module 300 and recommending module 400.
Generation module 100 generates set of applications for obtaining the mounted application of user.In the present embodiment, server
The mounted application of user is obtained, the set of applications including the mounted application of user is generated.Specifically, server can pass through
User is obtained to the application downloading installation record in application resources bank, determines the mounted application of user, and generate corresponding answer
With set.Server can obtain the mounted application of user in preset time period according to the application downloading installation record of user.
In one embodiment, server can obtain the quantity that the user applied in resources bank was accessed in nearest one day,
Assuming that the quantity of user herein is n.The quantity of all applications is m in resources bank.
Matrix y indicates the matrix of all user installation application messages, size n*m.Every a line indicates the peace of a user
Applicable cases are filled, each column indicates the user installation situation of each application, and 0 indicates to be fitted without, and 1 indicates to be mounted with, such as:
First acquisition module 200 is to be recommended using the corresponding application preferences matrix using theme for obtaining；Wherein, institute
Stating using theme is the set being made of multiple related applications, and the element characterization theme in the application preferences matrix is to application
Preference angle value.Server is obtained with to be recommended using the corresponding application preferences matrix using theme.Wherein, using theme by more
The set of a related application composition.Related application is each application under same subject.Application preferences matrix is indicated in the matrix
In, each element characterizes the preference angle value using theme for application.It indicates: obtaining using the application preferences matrix of theme
Using theme to the preference value of each application under the theme, the application preferences matrix comprising multiple preference values is generated.
In the present embodiment, theme is applied for application to be recommended corresponding one, in the application preferences matrix using theme
Apply theme to the preference value of the application to be recommended including this.
Second, which obtains module 300, is used for according to application, the set of applications and the application preferences square to be recommended
Battle array, obtains the user to the preference value of the application to be recommended.In the present embodiment, pass through generation module 100 and
One obtains module 200, and server gets application to be recommended, user has installed using the set of applications and to be recommended formed
Using the corresponding application preferences matrix using theme.Further, server can get user couple according to above three parameter
The preference value of application to be recommended.
Recommending module 400 is used to recommend to apply to the user according to the preference value.In the present embodiment, it services
The preference value that device obtains multiple applications in 300 available resource library of module according to second, according to the preference journey of each application
Angle value recommends to apply to user.
In other embodiments, the modules provided by the invention using in recommendation apparatus are also used to execute institute of the present invention
In the application recommended method stated, the operation that corresponding each step executes no longer is described in detail herein.
The present invention also provides a kind of storage mediums.Computer program is stored on the storage medium；The computer program
When being executed by processor, application recommended method described in any of the above-described embodiment is realized.The storage medium can be memory.Example
Such as, built-in storage or external memory, or including both built-in storage and external memory.Built-in storage may include read-only storage
Device (ROM), programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash
Device or random access memory.External memory may include hard disk, floppy disk, ZIP disk, USB flash disk, tape etc..It is disclosed in this invention to deposit
Storage media includes but is not limited to the memory of these types.Memory disclosed in this invention is only used as example rather than as limit
It is fixed.
The present invention also provides a kind of computer equipments.A kind of computer equipment includes: one or more processors；Storage
Device；One or more application program.Wherein one or more of application programs are stored in the memory and are configured
To be executed by one or more of processors, one or more of application programs are configured to carry out any of the above-described embodiment
The application recommended method.
Fig. 8 is the structural schematic diagram of the computer equipment in one embodiment of the invention.Computer equipment described in the present embodiment
It can be server, personal computer and the network equipment.As shown in figure 8, equipment include processor 803, it is memory 805, defeated
Enter the devices such as unit 807 and display unit 809.It will be understood by those skilled in the art that the device structure device shown in Fig. 8 is simultaneously
The restriction to all devices is not constituted, may include than illustrating more or fewer components, or the certain components of combination.Memory
805 can be used for storing application program 801 and each functional module, and processor 803 runs the application program for being stored in memory 805
801, thereby executing the various function application and data processing of equipment.Memory can be built-in storage or external memory, or
Person includes both built-in storage and external memory.Built-in storage may include read-only memory (ROM), programming ROM (PROM),
Electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory or random access memory.External storage
Device may include hard disk, floppy disk, ZIP disk, USB flash disk, tape etc..Memory disclosed in this invention includes but is not limited to these types
Memory.Memory disclosed in this invention is only used as example rather than as restriction.
Input unit 807 is used to receive the input of signal, and receives the keyword of user's input.Input unit 807 can
Including touch panel and other input equipments.Touch panel collects the touch operation of user on it or nearby and (for example uses
Family uses the operations of any suitable object or attachment on touch panel or near touch panel such as finger, stylus), and root
According to the corresponding attachment device of preset driven by program；Other input equipments can include but is not limited to physical keyboard, function
One of key (such as broadcasting control button, switch key etc.), trace ball, mouse, operating stick etc. are a variety of.Display unit
809 can be used for showing the information of user's input or be supplied to the information of user and the various menus of computer equipment.Display is single
The forms such as liquid crystal display, Organic Light Emitting Diode can be used in member 809.Processor 803 is the control centre of computer equipment, benefit
With the various pieces of various interfaces and the entire computer of connection, by running or executing the software being stored in memory 803
Program and/or module, and the data being stored in memory are called, perform various functions and handle data.
In one embodiment, equipment includes one or more processors 803, and one or more memories 805, and one
A or multiple application programs 801.Wherein one or more of application programs 801 are stored in memory 805 and are configured
To be executed by one or more of processors 803, one or more of application programs 801 are configured to carry out the above implementation
Application recommended method described in example.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, which can store in a computer-readable storage medium
In matter, storage medium may include memory, disk or CD etc..
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
It should be understood that each functional unit in various embodiments of the present invention can be integrated in a processing module,
It can be physically existed alone, can also be integrated in two or more units in a module with each unit.It is above-mentioned integrated
Module both can take the form of hardware realization, can also be realized in the form of software function module.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of apply recommended method, which is characterized in that comprising steps of
The mounted application of user is obtained, set of applications is generated；
It obtains to be recommended using the corresponding application preferences matrix using theme；Wherein, the application theme is by multiple correlations
Using the set of composition, the element in the application preferences matrix characterizes theme to the preference angle value of application；
According to the application to be recommended, the set of applications and the application preferences matrix, obtain the user to it is described to
Recommend the preference value of application；
Recommend to apply to the user according to the preference value.
2. according to claim 1 apply recommended method, which is characterized in that it is described according to the preference value to described
User recommends application, comprising:
User is obtained to the preference value of all applications to be recommended in application resources bank；
According to user to the size of the preference value of each application to be recommended in the application resource library, need to be pushed away by described
It recommends to apply and sort from large to small；
The application to be recommended for the forward preset quantity that sorts is pushed to the user.
3. the method according to claim 1, wherein according to it is described it is to be recommended application, the set of applications and
The application preferences matrix obtains the user to the preference value of the application to be recommended, comprising:
The application to be recommended is obtained from the application preferences matrix to the preference value of different themes, generates application to be recommended
Theme vector；
Each application in the set of applications is obtained from the application preferences matrix to generate each the preference value of different themes
Using corresponding theme vector；
According to the corresponding theme vector of application each in the theme vector of the application to be recommended and the set of applications, Yi Jisuo
Set of applications is stated, obtains the user to the preference value of the application to be recommended.
4. according to the method described in claim 3, it is characterized in that, the theme vector and institute according to the application to be recommended
The corresponding theme vector of each application and the set of applications in set of applications are stated, obtains the user to described to be recommended
The preference value of application, comprising: obtain the user according to the following formula to the preference value of the application to be recommended:
Wherein, the set of applications of the user u is Su, | Su| the quantity for indicating mounted application in set of applications, wait push away
It recommends using for using a, the theme vector using a is Ba, j expression SuIn one application, using j theme vector be Bj, like
(u a) indicates user u to the preference value of application a, cos (Bj,Ba) indicate to seek BjWith BaCosine value.
5. according to claim 1 apply recommended method, which is characterized in that the application to be recommended is corresponded to using theme
Application preferences matrix obtains in the following manner:
The installation application message of the sample of users of preset quantity is obtained, application installation matrix is generated；The installation of the sample of users
Application message includes the mount message that sample of users installs the application to be recommended；
Input matrix subject matter preferences model is installed into the application, is obtained to be recommended using the corresponding application preferences using theme
Matrix；Wherein, the subject matter preferences model is used to characterize the incidence relation using installation matrix and the application preferences matrix.
6. according to the method described in claim 5, it is characterized in that, the subject matter preferences model includes user to subject matter preferences
The application preferences matrix model of subject matter preferences matrix model and theme to application preferences；Input matrix theme is installed into the application
Preference pattern obtains to be recommended using the corresponding application preferences matrix using theme, comprising:
In the loss function that application installation Input matrix is constructed in advance according to the subject matter preferences model；
It is inclined to obtain the corresponding theme of the subject matter preferences matrix model for the minimum value that the loss function is solved by preset algorithm
Good matrix and the corresponding application preferences matrix of the application preferences matrix model, are answered using the application preferences matrix as to be recommended
With the corresponding application preferences matrix using theme.
7. according to the method described in claim 6, it is characterized in that, the preset algorithm is gradient descent method.
8. a kind of apply recommendation apparatus characterized by comprising
Generation module generates set of applications for obtaining the mounted application of user；
First obtains module, to be recommended using the corresponding application preferences matrix using theme for obtaining；Wherein, the application
Theme is the set being made of multiple related applications, preference of the element characterization theme in the application preferences matrix to application
Value；
Second obtains module, for obtaining according to application, the set of applications and the application preferences matrix to be recommended
Preference value of the user to the application to be recommended；
Recommending module, for recommending to apply to the user according to the preference value.
9. a kind of storage medium, which is characterized in that be stored thereon with computer program；The computer program is executed by processor
When, realize application recommended method described in any one of the claims 1-7.
10. a kind of computer equipment, characterized in that it comprises:
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be executed by one or more of processors, one or more of application programs are configured to carry out according to claim 1
It is described in any item using recommended method to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486760.6A CN109040164B (en) | 2018-05-21 | 2018-05-21 | Application recommendation method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486760.6A CN109040164B (en) | 2018-05-21 | 2018-05-21 | Application recommendation method and device, storage medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109040164A true CN109040164A (en) | 2018-12-18 |
| CN109040164B CN109040164B (en) | 2021-11-26 |
Family
ID=64611616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810486760.6A Active CN109040164B (en) | 2018-05-21 | 2018-05-21 | Application recommendation method and device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040164B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113268655A (en) * | 2020-02-17 | 2021-08-17 | 北京搜狗科技发展有限公司 | Information recommendation method and device and electronic equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7953676B2 (en) * | 2007-08-20 | 2011-05-31 | Yahoo! Inc. | Predictive discrete latent factor models for large scale dyadic data |
| CN103425799A (en) * | 2013-09-04 | 2013-12-04 | 北京邮电大学 | Personalized research direction recommending system and method based on themes |
| CN105635480A (en) * | 2016-01-19 | 2016-06-01 | 广州彩瞳网络技术有限公司 | Application program recommendation method and corresponding device |
| US20160171036A1 (en) * | 2014-12-10 | 2016-06-16 | Industry-University Cooperation Foundation Hanyang University | Item recommendation method and apparatus |
| CN106844724A (en) * | 2017-02-10 | 2017-06-13 | 广州优视网络科技有限公司 | It is a kind of that the method and apparatus applied to recommend application have been installed based on user |
| CN107103036A (en) * | 2017-03-22 | 2017-08-29 | 广州优视网络科技有限公司 | Using acquisition methods, equipment and the programmable device for downloading probability |
| CN107239993A (en) * | 2017-05-24 | 2017-10-10 | 海南大学 | A kind of matrix decomposition recommendation method and system based on expansion label |
| CN107305559A (en) * | 2016-04-21 | 2017-10-31 | 中国移动通信集团广东有限公司 | Method and apparatus are recommended in one kind application |
| CN107885852A (en) * | 2017-11-13 | 2018-04-06 | 上海交通大学 | A kind of APP based on APP usage records recommends method and system |
-
2018
- 2018-05-21 CN CN201810486760.6A patent/CN109040164B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7953676B2 (en) * | 2007-08-20 | 2011-05-31 | Yahoo! Inc. | Predictive discrete latent factor models for large scale dyadic data |
| CN103425799A (en) * | 2013-09-04 | 2013-12-04 | 北京邮电大学 | Personalized research direction recommending system and method based on themes |
| US20160171036A1 (en) * | 2014-12-10 | 2016-06-16 | Industry-University Cooperation Foundation Hanyang University | Item recommendation method and apparatus |
| CN105635480A (en) * | 2016-01-19 | 2016-06-01 | 广州彩瞳网络技术有限公司 | Application program recommendation method and corresponding device |
| CN107305559A (en) * | 2016-04-21 | 2017-10-31 | 中国移动通信集团广东有限公司 | Method and apparatus are recommended in one kind application |
| CN106844724A (en) * | 2017-02-10 | 2017-06-13 | 广州优视网络科技有限公司 | It is a kind of that the method and apparatus applied to recommend application have been installed based on user |
| CN107103036A (en) * | 2017-03-22 | 2017-08-29 | 广州优视网络科技有限公司 | Using acquisition methods, equipment and the programmable device for downloading probability |
| CN107239993A (en) * | 2017-05-24 | 2017-10-10 | 海南大学 | A kind of matrix decomposition recommendation method and system based on expansion label |
| CN107885852A (en) * | 2017-11-13 | 2018-04-06 | 上海交通大学 | A kind of APP based on APP usage records recommends method and system |
Non-Patent Citations (3)
| Title |
|---|
| DHEERAJ KUMAR BOKDE: ""Role of Matrix Factorization Model in Collaborative Filtering Algorithm: A Survey"", 《PROCEDIA COMPUTER SCIENCE》 * |
| 李迎晨: ""基于社交网络的移动应用推荐系统研究及应用"", 《中国优秀硕士学位论文-信息科技辑》 * |
| 黄璐等: ""融合主题模型和协同过滤的多样化移动应用推荐"", 《软件学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113268655A (en) * | 2020-02-17 | 2021-08-17 | 北京搜狗科技发展有限公司 | Information recommendation method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109040164B (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109657138B (en) | Video recommendation method and device, electronic equipment and storage medium | |
| US10475102B2 (en) | Providing personalized item recommendations using scalable matrix factorization with randomness | |
| CN110139162B (en) | Media content sharing method and device, storage medium and electronic device | |
| US20190354555A1 (en) | Dynamic faceting for personalized search and discovery | |
| CN108491540B (en) | Text information pushing method and device and intelligent terminal | |
| KR20200030252A (en) | Apparatus and method for providing artwork | |
| US8626607B1 (en) | Generating media recommendations based upon beats per minute | |
| CN110688476A (en) | Text recommendation method and device based on artificial intelligence | |
| US10956470B2 (en) | Facet-based query refinement based on multiple query interpretations | |
| CN109597973A (en) | A kind of recommendation, generation method and the device of official documents and correspondence information | |
| CN107729473B (en) | Article recommendation method and device | |
| CN102934113A (en) | Information provision system, information provision method, information provision device, program, and information recording medium | |
| CN112040339A (en) | Method and device for making video data, computer equipment and storage medium | |
| CN116821475B (en) | Video recommendation method and device based on client data and computer equipment | |
| CN114417157B (en) | Data pushing method and device, computer equipment and computer medium | |
| CN109493138A (en) | Information recommendation method, device, server and storage medium | |
| US10790053B2 (en) | Appetite improvement system through memory association | |
| US11250468B2 (en) | Prompting web-based user interaction | |
| CN109117442A (en) | A kind of application recommended method and device | |
| Jiang et al. | A clickstream data analysis of the differences between visiting behaviors of desktop and mobile users | |
| CN110020108A (en) | Network resource recommended method, device, computer equipment and storage medium | |
| CN109819002B (en) | Data pushing method and device, storage medium and electronic device | |
| US20170262869A1 (en) | Measuring social media impact for brands | |
| CN111859147A (en) | Object recommendation method, object recommendation device and electronic equipment | |
| CN109040164A (en) | Using recommended method, device, storage medium and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200424 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510640 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |