CN108230104A - Using category feature generation method, mobile terminal and readable storage medium storing program for executing - Google Patents
Using category feature generation method, mobile terminal and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN108230104A CN108230104A CN201711498338.4A CN201711498338A CN108230104A CN 108230104 A CN108230104 A CN 108230104A CN 201711498338 A CN201711498338 A CN 201711498338A CN 108230104 A CN108230104 A CN 108230104A
- Authority
- CN
- China
- Prior art keywords
- category feature
- application
- intended application
- operation behavior
- predetermined registration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a kind of application category feature generation method, mobile terminal and readable storage medium storing program for executing.The application category feature generation method includes the following steps：The number of operations that each single user end carries out intended application predetermined registration operation behavior is obtained, according to the number of operations of predetermined registration operation behavior weight corresponding with predetermined registration operation behavior, calculates whole interest value of each single user end for intended application；According to the whole interest value, classification model construction is carried out, and obtain the eigenmatrix of intended application according to classification model construction with default modeler model；According to the characteristic value that different characteristic is classified in eigenmatrix is applied, the category feature of intended application is obtained.The present invention, for the operation behavior of application, establishes user and the classification model construction of application, and the category feature being applied according to classification model construction, generating process improves the accuracy using feature without manually carrying out subjective judgement by counting user.
Description
Technical field
The present invention relates to field of mobile terminals more particularly to a kind of application category feature generation method, mobile terminals and can
Read storage medium.
Background technology
With reaching its maturity for smart mobile phone technology, the quantity of mobile phone application also becomes very huge, and how to mobile phone
It carries out accurately classification and then becomes a problem.At present for the component of mobile phone application rely primarily on artificial addition label come into
Row classification, but can be because personal like error occur with the factors such as judging by manually adding label, and certain applications
Function is more, it is therefore desirable to multiple labels carry out compressive classification, at this time artificially add tagged error can bigger, so as to occur
Accurate label and weight can not be provided, the services such as search, the recommendation of user is caused to be affected.
Invention content
It is a primary object of the present invention to provide it is a kind of application category feature generation method, it is intended to solve obtain using feature with
During classification, due to the problem of subjectivity caused by manual sort is excessively high and human cost is excessive.
To achieve the above object, the present invention provides a kind of application category feature generation method, the application category feature generation side
Method includes the following steps：
The number of operations that each single user end carries out intended application predetermined registration operation behavior is obtained, according to predetermined registration operation behavior
Number of operations weight corresponding with predetermined registration operation behavior, calculate whole interest value of each single user end for intended application；
According to the whole interest value, classification model construction is carried out, and obtain target according to classification model construction with default modeler model
The eigenmatrix of application；
According to the characteristic value that different characteristic is classified in eigenmatrix is applied, the category feature of intended application is obtained.
Optionally, it is described to obtain the step of each single user end carries out the number of operations of predetermined registration operation behavior to intended application
Include before：
When detecting that predetermined registration operation behavior occurs for intelligent terminal, the intended application of predetermined registration operation behavior is obtained, and to target
The number of the predetermined registration operation row of application is updated.
Optionally, the number of operations according to predetermined registration operation behavior weight corresponding with predetermined registration operation behavior calculates each
Single user end for intended application whole interest value the step of include：
The product of each predetermined registration operation behavior number and weight is obtained, by multiplying for all predetermined registration operation behavior numbers and weight
Product is added and obtains whole interest value of the user for intended application.
Optionally, it is described according to the whole interest value, classification model construction is carried out, and build according to classification with default modeler model
The step of eigenmatrix that mould is applied, includes：
According to the whole interest value, data set of the user to intended application is obtained；
Data set is modeled using default latent factor model, obtains the data of the eigenmatrix comprising intended application
Model.
Optionally, it is described to include using the step of carrying out modeling modeling to data set using default latent factor model：
When carrying out classification model construction, preset classification number is obtained, the corresponding number for dividing tagsort quantity is established according to classification number
According to model.
Optionally, it is described according to the characteristic value that different characteristic is classified in eigenmatrix is applied, obtain the class of intended application
The step of feature, includes：
According to the characteristic value, characteristic value is brought into the form of vectors, generates intended application category feature.
Optionally, it is described according to the characteristic value, characteristic value is brought into the form of vectors, generation intended application class is special
Include after the step of sign：
When generating intended application category feature, the current time of category feature and the quantity of current preset operation behavior are recorded, and
It is set as the update quantity of renewal time and predetermined registration operation behavior；
When detecting that intended application renewal time or update quantity meet update condition, to the category feature of intended application
It is updated.
Optionally, it is described when detecting that intended application renewal time or update quantity meet update condition, to target
The step of category feature of application is updated includes：
When current time and the time interval of the renewal time are more than default minimum renewal time interval, judgement meets
Update condition；
When the quantity of current preset operation behavior and the difference of the update quantity, which are more than default minimum, updates quantity, sentence
Surely meet update condition.
In addition, to achieve the above object, the present invention also provides a kind of mobile terminal, the mobile terminal includes：Memory,
Processor and the application category feature that is stored on the memory and can run on the processor generate program, the application
The step of category feature generation program is realized as described above when being performed by the processor using category feature generation method.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
It is stored on storage medium and generates program using category feature, the application category feature generation program is realized such as when being executed by processor
Above the step of application category feature generation method.
Application category feature generation method proposed by the present invention, is the various usage behaviors based on user for application, including
It downloads, install, update, share and comments on, interest value of the user for each application is calculated, then further according to LFM
(latent factor model, latent factor model) models, then be applied by way of matrix decomposition application
Then weight in different classifications calculates the weight in obtained different classifications, you can obtain in vector form
The feature of application.The present invention is to utilize machine term algorithm using category feature generation method, corresponding with user's usage behavior data
It is calculated with feature, subjective impact during so as to avoid manual sort, and can be caused according to the behavioral data of user
The feature of application is more accurate so that the business such as search, recommendation of application are more accurate.
Description of the drawings
Fig. 1 is the terminal structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is a kind of communications network system Organization Chart that inventive embodiments provide；
Fig. 3 is the flow diagram that the present invention applies category feature generation method first embodiment；
Fig. 4 is the refinement flow diagram that the present invention applies another embodiment of category feature generation method；
Fig. 5 is modeling schematic diagram of the present invention using the classification model construction of category feature generation method；
Fig. 6 is the effect diagram that the present invention is searched using category feature generation method reading class using similar application；
Fig. 7 is the effect diagram that the present invention is searched using category feature generation method live streaming class using similar application.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
In subsequent description, using for representing that the suffix of such as " module ", " component " or " unit " of element is only
Be conducive to the explanation of the present invention, itself there is no a specific meaning.Therefore, " module ", " component " or " unit " can mix
Ground uses.
Terminal can be implemented in a variety of manners.For example, terminal described in the present invention can include such as mobile phone, tablet
Computer, laptop, palm PC, personal digital assistant (Personal Digital Assistant, PDA), portable
The shiftings such as media player (Portable Media Player, PMP), navigation device, wearable device, Intelligent bracelet, pedometer
The dynamic fixed terminals such as terminal and number TV, desktop computer.
It will be illustrated by taking mobile terminal as an example in subsequent descriptions, it will be appreciated by those skilled in the art that in addition to special
For moving except the element of purpose, construction according to the embodiment of the present invention can also apply to the terminal of fixed type.
Referring to Fig. 1, a kind of hardware architecture diagram of its mobile terminal of each embodiment to realize the present invention, the shifting
Dynamic terminal 100 can include：RF (Radio Frequency, radio frequency) unit 101, WiFi module 102, audio output unit
103rd, A/V (audio/video) input unit 104, sensor 105, display unit 106, user input unit 107, interface unit
108th, the components such as memory 109, processor 110 and power supply 111.It will be understood by those skilled in the art that shown in Fig. 1
Mobile terminal structure does not form the restriction to mobile terminal, and mobile terminal can be included than illustrating more or fewer components,
Either combine certain components or different components arrangement.
The all parts of mobile terminal are specifically introduced with reference to Fig. 1：
Radio frequency unit 101 can be used for receive and send messages or communication process in, signal sends and receivees, specifically, by base station
Downlink information receive after, handled to processor 110；In addition, the data of uplink are sent to base station.In general, radio frequency unit 101
Including but not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier, duplexer etc..In addition, it penetrates
Frequency unit 101 can also communicate with network and other equipment by radio communication.Above-mentioned wireless communication can use any communication
Standard or agreement, including but not limited to GSM (Global System of Mobile communication, global system for mobile telecommunications
System), GPRS (General Packet Radio Service, general packet radio service), CDMA2000 (Code
Division Multiple Access 2000, CDMA 2000), WCDMA (Wideband Code Division
Multiple Access, wideband code division multiple access), TD-SCDMA (Time Division-Synchronous Code
Division Multiple Access, TD SDMA), FDD-LTE (Frequency Division
Duplexing-Long Term Evolution, frequency division duplex long term evolution) and TDD-LTE (Time Division
Duplexing-Long Term Evolution, time division duplex long term evolution) etc..
WiFi belongs to short range wireless transmission technology, and mobile terminal can help user to receive and dispatch electricity by WiFi module 102
Sub- mail, browsing webpage and access streaming video etc., it has provided wireless broadband internet to the user and has accessed.Although Fig. 1 shows
Go out WiFi module 102, but it is understood that, and must be configured into for mobile terminal is not belonging to, it completely can be according to need
It to be omitted in the range for the essence for not changing invention.
Audio output unit 103 can be in call signal reception pattern, call mode, record mould in mobile terminal 100
Formula, speech recognition mode, broadcast reception mode when under isotypes, it is that radio frequency unit 101 or WiFi module 102 are received or
The audio data stored in memory 109 is converted into audio signal and exports as sound.Moreover, audio output unit 103
The relevant audio output of specific function performed with mobile terminal 100 can also be provided (for example, call signal receives sound, disappears
Breath receives sound etc.).Audio output unit 103 can include loud speaker, buzzer etc..
A/V input units 104 are used to receive audio or video signal.A/V input units 104 can include graphics processor
(Graphics Processing Unit, GPU) 1041 and microphone 1042, graphics processor 1041 is in video acquisition mode
Or the static images or the image data of video obtained in image capture mode by image capture apparatus (such as camera) carry out
Reason.Treated, and picture frame may be displayed on display unit 106.Through graphics processor 1041, treated that picture frame can be deposited
Storage is sent in memory 109 (or other storage mediums) or via radio frequency unit 101 or WiFi module 102.Mike
Wind 1042 can connect in telephone calling model, logging mode, speech recognition mode etc. operational mode via microphone 1042
Quiet down sound (audio data), and can be audio data by such acoustic processing.Audio that treated (voice) data can
To be converted to the form output that mobile communication base station can be sent to via radio frequency unit 101 in the case of telephone calling model.
Microphone 1042 can implement various types of noises elimination (or inhibition) algorithms and send and receive sound to eliminate (or inhibition)
The noise generated during frequency signal or interference.
Mobile terminal 100 further includes at least one sensor 105, such as optical sensor, motion sensor and other biographies
Sensor.Specifically, optical sensor includes ambient light sensor and proximity sensor, wherein, ambient light sensor can be according to environment
The light and shade of light adjusts the brightness of display panel 1061, and proximity sensor can close when mobile terminal 100 is moved in one's ear
Display panel 1061 and/or backlight.As one kind of motion sensor, accelerometer sensor can detect in all directions (general
For three axis) size of acceleration, size and the direction of gravity are can detect when static, can be used to identify the application of mobile phone posture
(such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, percussion) etc.；
The fingerprint sensor that can also configure as mobile phone, pressure sensor, iris sensor, molecule sensor, gyroscope, barometer,
The other sensors such as hygrometer, thermometer, infrared ray sensor, details are not described herein.
Display unit 106 is used to show by information input by user or be supplied to the information of user.Display unit 106 can wrap
Display panel 1061 is included, liquid crystal display (Liquid Crystal Display, LCD), Organic Light Emitting Diode may be used
Display panel 1061 is configured in forms such as (Organic Light-Emitting Diode, OLED).
User input unit 107 can be used for receiving the number inputted or character information and generation and the use of mobile terminal
The key signals input that family is set and function control is related.Specifically, user input unit 107 may include touch panel 1071 with
And other input equipments 1072.Touch panel 1071, also referred to as touch screen collect user on it or neighbouring touch operation
(for example user uses any suitable objects such as finger, stylus or attachment on touch panel 1071 or in touch panel 1071
Neighbouring operation), and corresponding attachment device is driven according to preset formula.Touch panel 1071 may include touch detection
Two parts of device and touch controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect touch operation band
The signal come, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and by it
Contact coordinate is converted into, then gives processor 110, and the order that processor 110 is sent can be received and performed.It in addition, can
To realize touch panel 1071 using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic waves.In addition to touch panel
1071, user input unit 107 can also include other input equipments 1072.Specifically, other input equipments 1072 can wrap
It includes but is not limited to physical keyboard, in function key (such as volume control button, switch key etc.), trace ball, mouse, operating lever etc.
It is one or more, do not limit herein specifically.
Further, touch panel 1071 can cover display panel 1061, when touch panel 1071 detect on it or
After neighbouring touch operation, processor 110 is sent to determine the type of touch event, is followed by subsequent processing device 110 according to touch thing
The type of part provides corresponding visual output on display panel 1061.Although in Fig. 1, touch panel 1071 and display panel
1061 be the component independent as two to realize the function that outputs and inputs of mobile terminal, but in certain embodiments, it can
The function that outputs and inputs of mobile terminal is realized so that touch panel 1071 and display panel 1061 is integrated, is not done herein specifically
It limits.
Interface unit 108 be used as at least one external device (ED) connect with mobile terminal 100 can by interface.For example,
External device (ED) can include wired or wireless head-band earphone port, external power supply (or battery charger) port, wired or nothing
Line data port, memory card port, the port for device of the connection with identification module, audio input/output (I/O) end
Mouth, video i/o port, ear port etc..Interface unit 108 can be used for receiving the input from external device (ED) (for example, number
It is believed that breath, electric power etc.) and the input received is transferred to one or more elements in mobile terminal 100 or can be with
For transmitting data between mobile terminal 100 and external device (ED).
Memory 109 can be used for storage software program and various data.Memory 109 can mainly include storing program area
And storage data field, wherein, storing program area can storage program area, application program (such as the sound needed at least one function
Sound playing function, image player function etc.) etc.；Storage data field can store according to mobile phone use created data (such as
Audio data, phone directory etc.) etc..In addition, memory 109 can include high-speed random access memory, can also include non-easy
The property lost memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Processor 110 is the control centre of mobile terminal, utilizes each of various interfaces and the entire mobile terminal of connection
A part is stored in storage by running or performing the software program being stored in memory 109 and/or module and call
Data in device 109 perform the various functions of mobile terminal and processing data, so as to carry out integral monitoring to mobile terminal.Place
Reason device 110 may include one or more processing units；Preferably, processor 110 can integrate application processor and modulatedemodulate is mediated
Device is managed, wherein, the main processing operation system of application processor, user interface and application program etc., modem processor is main
Processing wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 110.
Mobile terminal 100 can also include the power supply 111 (such as battery) powered to all parts, it is preferred that power supply 111
Can be logically contiguous by power-supply management system and processor 110, so as to realize management charging by power-supply management system, put
The functions such as electricity and power managed.
Although Fig. 1 is not shown, mobile terminal 100 can also be including bluetooth module etc., and details are not described herein.
For the ease of understanding the embodiment of the present invention, below to the communications network system that is based on of mobile terminal of the present invention into
Row description.
Referring to Fig. 2, Fig. 2 is a kind of communications network system Organization Chart provided in an embodiment of the present invention, the communication network system
The LTE system united as universal mobile communications technology, the LTE system include the UE (User Equipment, the use that communicate connection successively
Family equipment) 201, E-UTRAN (Evolved UMTS Terrestrial Radio Access Network, evolved UMTS lands
Ground wireless access network) 202, EPC (Evolved Packet Core, evolved packet-based core networks) 203 and operator IP operation
204。
Specifically, UE201 can be above-mentioned terminal 100, and details are not described herein again.
E-UTRAN202 includes eNodeB2021 and other eNodeB2022 etc..Wherein, eNodeB2021 can be by returning
Journey (backhaul) (such as X2 interface) is connect with other eNodeB2022, and eNodeB2021 is connected to EPC203,
ENodeB2021 can provide the access of UE201 to EPC203.
EPC203 can include MME (Mobility Management Entity, mobility management entity) 2031, HSS
(Home Subscriber Server, home subscriber server) 2032, other MME2033, SGW (Serving Gate Way,
Gateway) 2034, PGW (PDN Gate Way, grouped data network gateway) 2035 and PCRF (Policy and
Charging Rules Function, policy and rate functional entity) 2036 etc..Wherein, MME2031 be processing UE201 and
The control node of signaling, provides carrying and connection management between EPC203.HSS2032 is all to manage for providing some registers
Such as the function of home location register (not shown) etc, and some are preserved in relation to use such as service features, data rates
The dedicated information in family.All customer data can be sent by SGW2034, and PGW2035 can provide the IP of UE 201
Address is distributed and other functions, and PCRF2036 is business data flow and the strategy of IP bearing resources and charging control strategic decision-making
Point, it selects and provides available strategy and charging control decision with charge execution function unit (not shown) for strategy.
IP operation 204 can include internet, Intranet, IMS (IP Multimedia Subsystem, IP multimedia
System) or other IP operations etc..
Although above-mentioned be described by taking LTE system as an example, those skilled in the art it is to be understood that the present invention not only
Suitable for LTE system, be readily applicable to other wireless communication systems, such as GSM, CDMA2000, WCDMA, TD-SCDMA with
And following new network system etc., it does not limit herein.
Based on above-mentioned mobile terminal hardware configuration and communications network system, each embodiment of the method for the present invention is proposed.
The present invention provides a kind of application category feature generation method.
In the present invention generates section method first embodiment using category feature, with reference to Fig. 3, using category feature generation method packet
It includes：
Step S10 obtains the number of operations that each single user end carries out intended application predetermined registration operation behavior, according to default
The number of operations of operation behavior weight corresponding with predetermined registration operation behavior calculates entirety of each single user end for intended application
Interest value；
Specifically, user selection with use in application, various operations can be carried out, such as download, peace loading, unloading, update,
Comment on, share etc., and different operation behaviors can represent interest level of the user for application, therefore be used by counting
Family calculates the operation behavior of an application (i.e. intended application) by each operation behavior and corresponding weight,
It can obtain whole interest value of the user for the application.
According to the whole interest value, classification model construction is carried out, and according to classification model construction with default modeler model by step S20
Obtain the eigenmatrix of intended application；
Specifically, can be divided by the whole interest value and disaggregated model that are calculated by user's operation behavior
Class models, such as carries out classification model construction by LFM (latent factor model, latent factor model), can obtain difference
User is for the model matrix of each application, and different application weight in each feature can be obtained by then carrying out matrix decomposition, i.e.,
Each eigenmatrix for applying the characteristic value in each feature.
Step S30, according to the characteristic value that different characteristic is classified in eigenmatrix is applied, the class for obtaining intended application is special
Sign.
Specifically, it by the eigenmatrix for obtaining data model progress matrix decomposition, can be obtained from eigenmatrix
To the characteristic value each applied in each feature, it will come out using all characteristics extractions, then carry out in vector form
It represents, the category feature of the corresponding vector form that can be applied is to get to the feature of application.
With the development of smart mobile phone, the performance of smart mobile phone is more powerful, and function is also more and more, at the same with intelligent hand
The quantity of the corresponding mobile phone application of machine is also to greatly increase.When recommending to user or user scans for, the class of application
Type classification be a key property, only accurately to application classify under the premise of, can to user recommend or
Person user can search desired application.Otherwise user possibly can not be rapidly obtained the application of needs, lead to making for user
It is adversely affected with experience.
At present to application classify when, mainly by manually use with observation, then will application addition mark
It signs or classifies, it, can be with meet demand, but current using the method for manual sort when early stage mobile phone number of applications is less
When number of applications has reached million grades or more, then need to pay a large amount of human cost using the mode manually classified.
And during due to manually being classified, judgement is carried out according to the subjective of sorter, is also resulted in so carrying out manual sort
Classification results are not accurate enough.In addition to this, manually carry out classification with add label when, it may appear that single label it is impossible to meet
Using actual effect or the situation of diversified user demand, such as ' there are four mark by starting point reading ' app (application program)
Label：Reading, books, e-book, novel, and four labels are of equal value in a management system, i.e., the weight of 4 labels is the same
's.It is serious by for the function of label and classified weight accuracy for search, recommendation etc. in this way, result can be caused to miss
The consequences such as difference so that usage experience of the user when using correlation function significantly declines.
And the present invention is using category feature generation method, is to use the various operation rows in application, being carried out by user
To calculate interest level of the user for application.The operation behavior that user carries out application includes：Search is downloaded, peace
Fill, update, commenting on, sharing, unloading etc., and different operation behaviors, the user's interest level that can be experienced are different, therefore
The weight of different operation behavior is also different.Such as the weight of installation can be set as 1, and the weight commented on can be set as 0.5,
Newer weight can also be set as 0.5, and user can generally be commented after an application interested and satisfied has been used
By and rear extended meeting be updated and carry out the new function of experience application, and the weight unloaded can be set as -1, represent that user does not feel emerging
Interest is not enough satisfied with because other reasons are whole to application.Then according to the number of operations and power of user's operations behavior
Weight, can calculate whole interest value of the user for application.Whole interest value represents interested journey of the user for application
Degree and favorable rating, whole interest value is higher, represent user for application it is interested, using more.
After the whole interest value of user is obtained, pass through LFM (latent factor model, latent factor model)
To the operation behavior collection of user, (that data set includes is all users, all applications and each user couple to model algorithm
The whole interest value list of application) carry out classification model construction, schematic diagram such as Fig. 5 of the data model after modeling.Classification model construction can be with
Obtain three matrixes, wherein R matrixes are user_item matrixes (user i.e. user, item are applied), each entry value in matrix
Ri,jThat represent is useriTo itemjInterest-degree or scoring.LFM algorithms extract several themes or classification from data set,
As the bridge of user and item, while R matrixes can be decomposed into P matrixes and Q matrix multiples.By R matrixes using it is common most
Small two multiply or gradient descent method can acquire P, Q matrix.Wherein P matrixes are that (class applies theme to user_class matrixes
Or classification), each entry value P in matrixi,jThat represent is useriTo classjInterest-degree；Q matrixes are class_item matrixes
(i.e. eigenmatrix), each entry value Q in matrixi,jThat represent is itemjBelong to classiThe weight of classification.
By classification model construction to eigenmatrix, after Q matrixes, can be applied corresponding each theme or classification
Interest value, then by the form of vector, calculate the feature of application, for example, item1 feature vector for (Q11, Q21,
Q31), item2 can use (Q12, Q22, Q32).And need scan for recommendation etc. need to inquire it is similar in application, similar
Degree can be represented, therefore the similarity of item1 and item2 can be expressed as using the cosine value between two applications：
The cosine value being calculated is bigger (i.e. closer to 1), then it represents that the similarity degree between two applications is higher, instead
It, cosine value is smaller then to represent that the similarity degree of two applications is lower.And so on, any two in application market can be found
Similarity between, it is so similar that apply so as to find content, user behavior extreme, by calculating looking into application for similarity
Using renderings such as Fig. 6 and Fig. 7 of application are looked for, wherein Fig. 6 is to read class, the lookup effect of application, and Fig. 7 is that answering for class is broadcast live
With.
The present invention is using category feature generation method, and the application feature being calculated is without using manually being calculated, data
Behavioral statistics obtain by the operation of user.And when carrying out classification model construction, do not need to that (granularity is classified to granularity of classification
Quantity, the careful degree of presentation class) controlled and adjusted, it is only necessary to the classification quantity of LFM is set, according to reality
Classification number can be adjusted in the demand on border, and the quantity for number of classifying is bigger, then granularity is thinner.Divide simultaneously to application
It is not the clearly classification that application is added to label type during class, but by calculating, it is applied and belongs to a certain classification
Degree size belongs to a kind of fuzzy classification.And fuzzy classification can when classify more precisely, so as to scan for user
The application of corresponding type is accurately obtained when business.For different classification, each apply in classification can be obtained
Interest value, interest value are bigger, then it represents that application can more represent this classification, i.e. application more has the representativeness of classification.The same time-division
The process of class by technical staff without being intervened so that producer can save a large amount of human cost.Therefore the present invention is using greatly
Operation behavior data when scale group of subscribers is using application, then by classification model construction, calculate the feature vector of each application, lead to
The operations such as cluster analysis or associated recommendation can be carried out to application by crossing feature vector, the service provision technologies branch such as to search for, recommending
It holds, and high, at low cost into a process efficiency.
Further, step S10 obtains the number of operations that each single user end carries out intended application predetermined registration operation behavior
The step of before include：
Step S11 when detecting that predetermined registration operation behavior occurs for intelligent terminal, obtains the intended application of predetermined registration operation behavior,
And the number of the predetermined registration operation row of intended application is updated.
Specifically, when intelligent terminal detects that user carries out preset operation behavior, predetermined registration operation behavior includes：Search,
Download, installation etc. obtain the intended application of operation behavior, then by the corresponding operation behavior statistics number root of intended application first
Corresponding update is carried out according to the operation behavior that this is detected.
The whole interest-degree of application is calculated based on the default application operating behavior of user.In statistics,
When intelligent terminal is detected with predetermined registration operation behavior, the intended application of operation behavior is got, then getting target should
It with the quantity of corresponding operation behavior, is being preserved after quantity is updated, such as is detecting and currently answered in download " bucket fish "
With primary, then the download time of " bucket fish " is added 1, so as to complete this statistics.Simultaneously in order to ensure the operation row of same user
For data statistics can be complete, can be associated by related account, i.e., whether operation behavior in user logs in related account
It carries out, such as is detected when having down operation using shop on the basis of family, then detect using whether shop is login status, if
It has been logged in that, be then associated the account for counting with logging in, the operation behavior of statistics is kept to belong to same user；If being not logged in,
Then using this equipment as default account, i.e., according to relevant informations such as device identifications, the data detected in all same equipment are regarded
To belong to same user.
Further, step S10 is according to the number of operations weight corresponding with predetermined registration operation behavior of predetermined registration operation behavior, meter
The step of calculating whole interest value of each single user end for intended application includes：
Step S12 obtains the product of each predetermined registration operation behavior number and weight, by all predetermined registration operation behavior numbers with
The product addition of weight obtains whole interest value of the user for intended application.
Specifically, when calculating whole interest value of the user for application, by time of the operations to application counted on
Number is multiplied by corresponding weight, and whole interest value of the user for application can be calculated by then by the product of gained be added.
User is for the whole interest value of application, the number of operations of each predetermined registration operation behavior obtained by detection, with
And it is obtained with the corresponding weight calculation of operations behavior.Circular is that the number of each predetermined registration operation behavior multiplies
With corresponding weight, it then will obtain product and be added, finally obtain whole interest value of the user to application.Whole interest
The calculating simple, intuitive of value, can according to user carry out predetermined registration operation row number from different, intuitively judge user for
The interest level of application.
Further, step step 20 carries out classification model construction, and root according to the whole interest value with default modeler model
The step of eigenmatrix being applied according to classification model construction, includes：
Step S21 according to the whole interest value, obtains data set of the user to intended application；
Step S22 models data set using default latent factor model, obtains including the feature square of intended application
The data model of battle array.
Specifically, classification model construction is carried out by the whole interest value, obtains data set of the user to application interest value.Again
User builds the data set of application interest value by LFM (latent factor model, latent factor model) algorithms
Mould obtains data matrix, and then using common least square or gradient descent method, the data set matrix got is carried out
Matrix decomposition finally obtains user for different types of interests matrix and the eigenmatrix of application.
User about the data set of application interest value is modeled by LFM, one can be obtained and corresponded to about user
The data matrix of interest value, this matrix can intuitively embody interest value size of each user for different application.
And the data set matrix can carry out matrix decomposition in a manner that least square or gradient decline, and be obtained after matrix decomposition
Two matrixes are that (type is with applying square with class_item matrixes for user_class matrixes (matrix of user and type) respectively
Battle array, that is, the eigenmatrix applied), schematic diagram such as Fig. 5 of matrix decomposition.Wherein eigenmatrix is the power applied in each classification
Weight values can be rapidly obtained the feature vector of each application by eigenmatrix.
Further, step S21 is gone back using the step of default latent factor model is used to carry out modeling modeling to data set
Including：
Step S211 when carrying out classification model construction, obtains preset classification number, establishes correspondence according to classification number and divides tagsort
The data model of quantity.
Specifically, when carrying out classification model construction, the classification quantity of modeling is determined according to preset LFM classification numbers, and is divided
Class quantity is the parameter of control tactics granularity, it is therefore desirable to get preset LFM classification number, can accurately classify
Modeling.
When carrying out classification model construction, different according to the classification number of modeling, the model granularity of foundation is also different, be that is to say
Model is different for the degree of refinement of data, and degree of refinement is higher, and granularity is smaller；Degree of refinement is lower, and granularity is bigger.Granularity compared with
Gao Shi, the model of foundation is also more accurate for the calculating of application feature, and reaches million grades or more of feelings in current number of applications
Under condition, when degree of refinement is excessive, the calculation amount in calculating process can be caused also excessive, and calculation amount crosses conference leads to calculating speed
It reduces.Therefore in the case where disclosure satisfy that preset function, the classification number of classification model construction is without excessive, and technical staff can lead to
It crosses setting FLM and classifies number to adjust the granule size of classification model construction.The refinement journey of calculating speed and classification model construction is controlled with this
Balance between degree so that under the premise of feature calculation mode disclosure satisfy that system various functions, keep higher computational efficiency.
Further, step S30 obtains intended application according to the characteristic value that different characteristic is classified in eigenmatrix is applied
Category feature the step of include：
Characteristic value is brought into according to the characteristic value, generates intended application category feature by step S31 in the form of vectors.
Specifically, by eigenmatrix, characteristic value of the intended application in different classifications is brought into vector form, then may be used
To obtain the category feature of intended application, that is, the characteristic value applied.
The category feature of intended application is finally the feature vector that a vector form represents, and is not the table in the form of value
The characteristic value shown, category feature are formed by applying the characteristic value in each classification in eigenmatrix, such as item1 is in feature
The characteristic values of corresponding three classification are Q11, Q21 and Q31 respectively in matrix, then the category feature of item1 then by Q11, Q21 with
Q31 composition characteristics vector, is expressed as (Q11, Q21, Q31).The category feature of intended application is represented by the form of feature vector,
Rather than it is to when carrying out the calculating using similarity, can more accurately calculate different application using characteristic value
Between similarity degree, the present invention can be carried out, example by the cosine value of two category features of calculating when calculating similarity degree
Such as vectorial 1item (Q11, Q21, Q31), 2 (Q12, Q22, Q23) of vector, then by calculate two vectorial cosine values come
To the similarity of the two, cosine value is
Cosine value closer to 1 when, then show it is more similar between two applications, conversely, cosine value it is closer -1 when, show
It is more dissimilar between two applications.Calculated by the cosine value of two category features, can be simple and fast get two applications
Similarity, so as to meet such as search, recommend correlation function the needs of.
Further, characteristic value is brought into the form of vectors, life according to the characteristic value with reference to Fig. 4, step S31
Include into after the step of intended application category feature：
Step S32 when generating intended application category feature, records the current time of category feature and current preset operation behavior
Quantity, and it is set as the update quantity of renewal time and predetermined registration operation behavior；
Specifically, when generating the category feature of intended application, when system can record generated time and the generation of category feature
Predetermined registration operation behavior quantity, and by the two amounts be set as renewal time with update quantity, to update judge when use.
Step S33, when detecting that intended application renewal time or update quantity meet update condition, to intended application
Category feature be updated.
Specifically, as the number of users of application increases the increase with user's usage time, user is for the interest of application
It can change, therefore the category feature applied is also required to be updated.And due to the enormous amount of application, to category feature into
Row real-time update can cause system operations amount excessive, and so as to cause the adverse consequences such as operation efficiency reduction, therefore there is provided updates
Condition, then category feature is updated when meeting update condition.When category feature is calculated, record is calculated when completing
Time and the quantity of predetermined registration operation behavior, are sentenced by the time interval of renewal time or the quantity incrementss of predetermined registration operation behavior
The disconnected update for whether carrying out category feature.
In order to ensure the accuracy of category feature, therefore category feature is after generation, it is also necessary to constantly updated,
With the increase of usage time and the increase of number of users, the interest level of different applications may occur for user
Variation.And it can be good at embodying the variation that user carries out the interest level of different application by update.But
If just carrying out the update of category feature in predetermined registration operation behavior of every increase, the calculation amount of system can be caused to become larger, particularly
Using more application, data volume can reach hundreds of millions of.Therefore renewal frequency can seriously affect the operation efficiency of system too much,
It may result in system running speed decline when serious.Lead to adverse consequences in order to avoid system operations amount is excessive, pass through setting
Update condition effectively reduces number, while avoids the update feelings that caused feature limitation accuracy rate reduces not in time
Condition, under the premise of system operations speed is not influenced, the accuracy rate for maintaining category feature grows with each passing hour.
Further, step S33 is right when detecting that intended application renewal time or update quantity meet update condition
The step of category feature of intended application is updated includes：
Step S331, when current time and the time interval of the renewal time are more than default interval of minimum renewal time
When, then judgement meets update condition；
Specifically, when each preset time period of feature vector, judgement meets update condition, and carry out feature vector more
Newly.
Step S332, when the quantity of current preset operation behavior and the difference of the update quantity are more than default minimum and update
During quantity, then judgement meets update condition；
Specifically, when the quantity incrementss of predetermined registration operation behavior are more than preset operation behavior quantity incrementss, judgement
Meet update condition, and carry out the update of feature vector.
Judge whether there are two the conditions being updated to category feature, by newer time interval, i.e., currently one is
The time interval of time and renewal time last time if time interval is more than preset minimum renewal time interval, then carry out
Category feature it is more capable.The update condition to set interval mainly carries out category feature more to not newer application for a long time
Newly, the feature vector accuracy caused by not updating for a long time is avoided to reduce.
Other than time interval, also the update using category feature can be carried out according to the quantity incrementss of operation behavior,
By the quantity incrementss of operation behavior to determine whether newer purpose is to avoid popular application by the larger operation of quantity
Behavioral implications, leads to the category feature accuracy of application to reduce, therefore is more than default increase in the quantity incrementss of predetermined registration operation behavior
It during dosage, needs to be updated category feature, to keep the accuracy of category feature.Pass through time interval and operation behavior quantity
Incrementss judge whether to update, and can keep the accuracy using category feature so that user is carried out with system in use, can obtain
Take better usage experience and effect.
The present invention also provides a kind of devices based on application category feature generation.
Device the present invention is based on application category feature generation includes：It memory, processor and is stored on the memory
And the application category feature that can be run on the processor generates authoring program, the application category feature generates program by the place
It manages and is realized when device performs as described above using category feature generation method step.
Wherein, the prompt message run on the processor is performed what is realized using category feature generation program
Method can refer to the present invention using each embodiment of category feature generation method, and details are not described herein.
In addition the embodiment of the present invention also proposes a kind of computer readable storage medium.
It is stored on computer readable storage medium of the present invention and generates program, the application category feature generation using category feature
The step of applying category feature generation method as described above is realized when program is executed by processor.
Wherein, the display program of the prompt message run on the processor is performed realized method and can refer to
The present invention is using each embodiment of category feature generation method, and details are not described herein.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or device including a series of elements not only include those elements, and
And it further includes other elements that are not explicitly listed or further includes intrinsic for this process, method, article or device institute
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
Also there are other identical elements in the process of element, method, article or device.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), used including some instructions so that a station terminal (can be mobile phone, computer services
Device, air conditioner or network equipment etc.) perform method described in each embodiment of the present invention.
The embodiment of the present invention is described above in conjunction with attached drawing, but the invention is not limited in above-mentioned specific
Embodiment, above-mentioned specific embodiment is only schematical rather than restricted, those of ordinary skill in the art
Under the enlightenment of the present invention, present inventive concept and scope of the claimed protection are not being departed from, can also made very much
Form, these are belonged within the protection of the present invention.
Claims (10)
1. a kind of application category feature generation method, which is characterized in that the application category feature generation method includes the following steps：
The number of operations that each single user end carries out intended application predetermined registration operation behavior is obtained, according to the behaviour of predetermined registration operation behavior
Make number weight corresponding with predetermined registration operation behavior, calculate whole interest value of each single user end for intended application；
According to the whole interest value, classification model construction is carried out, and obtain intended application according to classification model construction with default modeler model
Eigenmatrix；
According to the characteristic value that different characteristic is classified in eigenmatrix is applied, the category feature of intended application is obtained.
2. category feature generation method is applied as described in claim 1, which is characterized in that described to obtain each single user end to mesh
Include before the step of mark application carries out the number of operations of predetermined registration operation behavior：
When detecting that predetermined registration operation behavior occurs for intelligent terminal, the intended application of predetermined registration operation behavior is obtained, and to intended application
The number of predetermined registration operation row be updated.
3. category feature generation method is applied as described in claim 1, which is characterized in that the behaviour according to predetermined registration operation behavior
The step of making number weight corresponding with predetermined registration operation behavior, calculating whole interest value of each single user end for intended application
Including：
The product of each predetermined registration operation behavior number and weight is obtained, by all predetermined registration operation behavior numbers and the product phase of weight
Add, obtain whole interest value of the user for intended application.
4. category feature generation method is applied as described in claim 1, which is characterized in that it is described according to the whole interest value,
Classification model construction is carried out with default modeler model, and be applied according to classification model construction eigenmatrix the step of include：
According to the whole interest value, data set of the user to intended application is obtained；
Data set is modeled using default latent factor model, obtains the data mould of the eigenmatrix comprising intended application
Type.
5. category feature generation method is applied as claimed in claim 4, which is characterized in that described to use using default latent factor
The step of model carries out to data set and models modeling includes：
When carrying out classification model construction, preset classification number is obtained, the corresponding data mould for dividing tagsort quantity is established according to classification number
Type.
6. category feature generation method is applied as described in claim 1, which is characterized in that described according to applying in eigenmatrix
The step of characteristic value of different characteristic classification, the category feature for obtaining intended application, includes：
According to the characteristic value, characteristic value is brought into the form of vectors, generates intended application category feature.
7. apply category feature generation method as claimed in claim 6, which is characterized in that it is described according to the characteristic value, with to
Include after the step of amount form brings characteristic value into, generation intended application category feature：
When generating intended application category feature, the current time of category feature and the quantity of current preset operation behavior are recorded, and be set as
Renewal time and the update quantity of predetermined registration operation behavior；
When detecting that intended application renewal time or update quantity meet update condition, the category feature of intended application is carried out
Update.
8. category feature generation method the use as claimed in claim 7, which is characterized in that described to detect that intended application updates
Time or update quantity is when meeting update condition, and the step of being updated to the category feature of intended application includes：
When current time and the time interval of the renewal time are more than default minimum renewal time interval, then judge to meet more
New Terms；
When the quantity of current preset operation behavior and the difference of the update quantity, which are more than default minimum, updates quantity, then judge
Meet update condition.
9. a kind of mobile terminal, which is characterized in that the mobile terminal includes：Memory, processor and it is stored in the storage
On device and what can be run on the processor generates program using category feature, and the application category feature generates program by the place
It manages and is realized when device performs such as the step of application category feature generation method described in any item of the claim 1 to 8.
10. a kind of computer readable storage medium, which is characterized in that be stored on the computer readable storage medium using class
Feature generates program, and the application category feature generation program is realized when being executed by processor such as any one of claim 1 to 8 institute
The step of application category feature generation method stated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711498338.4A CN108230104A (en) | 2017-12-29 | 2017-12-29 | Using category feature generation method, mobile terminal and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711498338.4A CN108230104A (en) | 2017-12-29 | 2017-12-29 | Using category feature generation method, mobile terminal and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108230104A true CN108230104A (en) | 2018-06-29 |
Family
ID=62644865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711498338.4A Pending CN108230104A (en) | 2017-12-29 | 2017-12-29 | Using category feature generation method, mobile terminal and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108230104A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110012485A (en) * | 2019-04-10 | 2019-07-12 | 惠州Tcl移动通信有限公司 | A kind of base station classification control method, system, storage medium and mobile terminal |
| CN111081090A (en) * | 2019-06-09 | 2020-04-28 | 广东小天才科技有限公司 | Information output method and learning device in click-to-read scene |
| CN112221154A (en) * | 2020-10-10 | 2021-01-15 | 陈夏焱 | Game data processing method based on artificial intelligence and cloud computing and game cloud center |
| CN113572785A (en) * | 2021-08-05 | 2021-10-29 | 中国电子信息产业集团有限公司第六研究所 | Honeypot defense method and device for nuclear power industrial control system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7685232B2 (en) * | 2008-06-04 | 2010-03-23 | Samsung Electronics Co., Ltd. | Method for anonymous collaborative filtering using matrix factorization |
| CN103023977A (en) * | 2012-11-19 | 2013-04-03 | 华南理工大学 | Recommendation system and method based on positional information |
| CN105740430A (en) * | 2016-01-29 | 2016-07-06 | 大连理工大学 | Personalized recommendation method with socialization information fused |
| CN105976070A (en) * | 2016-05-27 | 2016-09-28 | 北京交通大学 | Key-element-based matrix decomposition and fine tuning method |
| CN106022865A (en) * | 2016-05-10 | 2016-10-12 | 江苏大学 | Goods recommendation method based on scores and user behaviors |
| CN106294752A (en) * | 2016-08-10 | 2017-01-04 | 广州优视网络科技有限公司 | The application method of special recommendation, device and server |
| CN106776906A (en) * | 2016-11-30 | 2017-05-31 | 努比亚技术有限公司 | One kind application clustering method and device |
-
2017
- 2017-12-29 CN CN201711498338.4A patent/CN108230104A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7685232B2 (en) * | 2008-06-04 | 2010-03-23 | Samsung Electronics Co., Ltd. | Method for anonymous collaborative filtering using matrix factorization |
| CN103023977A (en) * | 2012-11-19 | 2013-04-03 | 华南理工大学 | Recommendation system and method based on positional information |
| CN105740430A (en) * | 2016-01-29 | 2016-07-06 | 大连理工大学 | Personalized recommendation method with socialization information fused |
| CN106022865A (en) * | 2016-05-10 | 2016-10-12 | 江苏大学 | Goods recommendation method based on scores and user behaviors |
| CN105976070A (en) * | 2016-05-27 | 2016-09-28 | 北京交通大学 | Key-element-based matrix decomposition and fine tuning method |
| CN106294752A (en) * | 2016-08-10 | 2017-01-04 | 广州优视网络科技有限公司 | The application method of special recommendation, device and server |
| CN106776906A (en) * | 2016-11-30 | 2017-05-31 | 努比亚技术有限公司 | One kind application clustering method and device |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110012485A (en) * | 2019-04-10 | 2019-07-12 | 惠州Tcl移动通信有限公司 | A kind of base station classification control method, system, storage medium and mobile terminal |
| CN111081090A (en) * | 2019-06-09 | 2020-04-28 | 广东小天才科技有限公司 | Information output method and learning device in click-to-read scene |
| CN112221154A (en) * | 2020-10-10 | 2021-01-15 | 陈夏焱 | Game data processing method based on artificial intelligence and cloud computing and game cloud center |
| CN112221154B (en) * | 2020-10-10 | 2021-06-25 | 深圳市有仙气科技有限公司 | Game data processing method based on artificial intelligence and cloud computing and game cloud center |
| CN113572785A (en) * | 2021-08-05 | 2021-10-29 | 中国电子信息产业集团有限公司第六研究所 | Honeypot defense method and device for nuclear power industrial control system |
| CN113572785B (en) * | 2021-08-05 | 2023-05-30 | 中国电子信息产业集团有限公司第六研究所 | Honeypot defense method and device for nuclear power control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107273011A (en) | Application program fast switch over method and mobile terminal | |
| CN109582821A (en) | A kind of music object recommendation method, terminal and computer readable storage medium | |
| CN108334539A (en) | Object recommendation method, mobile terminal and computer readable storage medium | |
| CN107194732A (en) | One kind application method for pushing, mobile terminal and computer-readable recording medium | |
| CN108230104A (en) | Using category feature generation method, mobile terminal and readable storage medium storing program for executing | |
| CN107230133A (en) | A kind of data processing method, equipment and computer-readable storage medium | |
| CN107704571A (en) | Information intelligent recommends method, apparatus and computer-readable recording medium | |
| CN107169150A (en) | Picture method for pushing, mobile terminal and computer-readable medium | |
| CN108288171A (en) | Advertisement insertion, server and computer readable storage medium | |
| CN108573064A (en) | Information recommendation method, mobile terminal, server and computer readable storage medium | |
| CN108536490A (en) | A kind of application program launching method, mobile terminal and computer storage media | |
| CN108551520A (en) | A kind of phonetic search response method, equipment and computer readable storage medium | |
| CN108170817A (en) | Differentiation video acquiring method, device and the readable storage medium storing program for executing of photo main body | |
| CN108241752A (en) | Photo display methods, mobile terminal and computer readable storage medium | |
| CN108230270A (en) | A kind of noise-reduction method, terminal and computer readable storage medium | |
| CN108600325A (en) | A kind of determination method, server and the computer readable storage medium of push content | |
| CN108197215A (en) | A kind of recommendation method, server and computer readable storage medium | |
| CN108521500A (en) | A kind of voice scenery control method, equipment and computer readable storage medium | |
| CN108763478A (en) | User's recessive character computational methods, server and computer readable storage medium | |
| CN108769126A (en) | Using recommendation method, mobile terminal and computer readable storage medium | |
| CN108984590A (en) | A kind of page data methods of exhibiting, terminal and computer readable storage medium | |
| CN108234893A (en) | A kind of brightness adjusting method, equipment and computer readable storage medium | |
| CN108184106A (en) | Image processing method, mobile terminal and computer readable storage medium | |
| CN107688639A (en) | Using recommendation method, server and computer-readable recording medium | |
| CN107506468A (en) | Application program searching method, terminal, server, computer-readable recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180629 |
|
| RJ01 | Rejection of invention patent application after publication |