CN106326369A - Application special topic recommendation method, application special topic recommendation device and server - Google Patents
Application special topic recommendation method, application special topic recommendation device and server Download PDFInfo
- Publication number
- CN106326369A CN106326369A CN201610661824.2A CN201610661824A CN106326369A CN 106326369 A CN106326369 A CN 106326369A CN 201610661824 A CN201610661824 A CN 201610661824A CN 106326369 A CN106326369 A CN 106326369A
- Authority
- CN
- China
- Prior art keywords
- application
- user
- list
- recommended
- correspondence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides an application special topic recommendation method, an application special topic recommendation device and a server. The application special topic recommendation method comprises the following steps: calculating a characteristic vector of a user needing recommendation according to an application list of the user needing recommendation; respectively calculating the characteristic vector of each preset application special topic; and generating an application special topic recommendation list for the user needing recommendation based on the characteristic vector of the user needing recommendation and the characteristic vector of each preset application special topic. The method is capable of being used for automatically matching preset special topics with the user, recommending different special topics for different users, and improving the user experience; as for a platform or an application store for providing application special topic recommendation service, since operation personnel does not need to judge which special topics should be recommended to which users, the working efficiency of the operation personnel is improved, further the labor cost of the whole platform or application store for providing the application special topic recommendation service is lowered, and the overall operation efficiency is improved.
Description
Technical field
The present invention relates to computer application field, in particular to one application special recommendation method, device and service
Device.
Background technology
Along with developing rapidly of mobile terminal technology and network technology, increasing user selects at mobile phone or flat board electricity
Downloading application software on the mobile terminals such as brain, various aim at the application that mobile phone users makes and obtains platform, such as, apply business
Also arise at the historic moment in shop.
During the operation of application shop, it will usually select some relevant application packages and become a special topic, mix a series of
Problem and pattern, be pushed to user, download with the application facilitating user to select in relevant application oneself to like.More conventional
Be the homepage being directly illustrated in mobile phone assistant, abundant page elements, increase Consumer's Experience, and expand the download of application.But
Being that the current special topic recommended to each user is just as, do not have specific aim, Consumer's Experience is poor.
Summary of the invention
In view of this, the purpose of the embodiment of the present invention is to provide a kind of application special recommendation method, device and server,
To solve the problems referred to above.
To achieve these goals, the technical scheme that the embodiment of the present invention uses is as follows:
First aspect, embodiments provides a kind of application special recommendation method, and described method includes: push away according to waiting
Recommend the list of application of user, calculate the characteristic vector of user to be recommended；Calculate each characteristic vector presetting application special topic respectively；
Characteristic vector based on described user to be recommended generates described use to be recommended with each characteristic vector presetting application special topic described
The application special recommendation list at family.
Second aspect, embodiments provides a kind of application special recommendation device, and described device includes: first calculates
Module, for the list of application according to user to be recommended, calculates the characteristic vector of user to be recommended；Second computing module, is used for
Calculate each characteristic vector presetting application special topic respectively；Generation module, for characteristic vector based on described user to be recommended
With the application special recommendation list that each characteristic vector presetting application special topic described generates described user to be recommended.
The third aspect, embodiments provides a kind of server, and described server includes processor and memorizer, institute
State memorizer and be couple to described processor, described memory store instruction, make institute when executed by the processor
State processor and perform following operation: according to the list of application of user to be recommended, calculate the characteristic vector of user to be recommended；Count respectively
Calculate each characteristic vector presetting application special topic；Characteristic vector based on described user to be recommended presets application specially with described each
The characteristic vector of topic generates the application special recommendation list of described user to be recommended.
Compared with prior art, a kind of application special recommendation method, device and the server that the embodiment of the present invention provides is logical
Cross and calculate described in the characteristic vector of user to be recommended each matching degree presetting application special topic characteristic of correspondence vector respectively, and root
Recommend the application special topic being suitable for according to described matching degree to user, in this way, default special topic can be carried out with user
Auto-matching, it is possible to recommend different special topics for different users, improves Consumer's Experience, and for improving application special topic
For the platform of recommendation service or application shop, go to judge which user to which recommends special owing to need not operation personnel
Topic, therefore improves the work efficiency of operation personnel, and then makes platform that whole application special recommendation service or apply business
The human cost in shop is reduced, and overall operation efficiency is improved.
For making the above-mentioned purpose of the present invention, feature and advantage to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below by embodiment required use attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, and it is right to be therefore not construed as
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to this
A little accompanying drawings obtain other relevant accompanying drawings.
Fig. 1 is the schematic diagram that the user terminal that the embodiment of the present invention provides interacts with server.
Fig. 2 is the structural representation of the server that the embodiment of the present invention provides.
Fig. 3 is a kind of flow chart applying special recommendation method that the embodiment of the present invention provides.
Fig. 4 is the detail flowchart of a kind of step S400 applying special recommendation method that the embodiment of the present invention provides.
Fig. 5 is the detail flowchart of a kind of step S410 applying special recommendation method that the embodiment of the present invention provides.
Fig. 6 is the detail flowchart of a kind of step S420 applying special recommendation method that the embodiment of the present invention provides.
Fig. 7 is the detail flowchart of a kind of step S500 applying special recommendation method that the embodiment of the present invention provides.
Fig. 8 is the detail flowchart of a kind of step S520 applying special recommendation method that the embodiment of the present invention provides.
Fig. 9 is the detail flowchart of a kind of step S600 applying special recommendation method that the embodiment of the present invention provides.
Figure 10 is a kind of structured flowchart applying special recommendation device that the embodiment of the present invention provides.
Figure 11 is that a kind of of embodiment of the present invention offer applies the structured flowchart of the first computing module in special recommendation device.
Figure 12 is that a kind of of embodiment of the present invention offer applies the structured flowchart of the first processing module in special recommendation device.
Figure 13 is that a kind of of embodiment of the present invention offer applies the structured flowchart of the second processing module in special recommendation device.
Figure 14 is that a kind of of embodiment of the present invention offer applies the structured flowchart of the second computing module in special recommendation device.
Figure 15 is that a kind of of embodiment of the present invention offer applies the structured flowchart of generation module in special recommendation device.
Detailed description of the invention
Below in conjunction with accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments.Generally exist
Can arrange and design with various different configurations with the assembly of the embodiment of the present invention that illustrates described in accompanying drawing herein.Cause
This, be not intended to limit claimed invention to the detailed description of the embodiments of the invention provided in the accompanying drawings below
Scope, but it is merely representative of the selected embodiment of the present invention.Based on embodiments of the invention, those skilled in the art are not doing
The every other embodiment obtained on the premise of going out creative work, broadly falls into the scope of protection of the invention.
It should also be noted that similar label and letter represent similar terms, therefore, the most a certain Xiang Yi in following accompanying drawing
Individual accompanying drawing is defined, then need not it be defined further and explains in accompanying drawing subsequently.Meanwhile, the present invention's
In description, term " first ", " second " etc. are only used for distinguishing and describe, and it is not intended that indicate or hint relative importance.
Fig. 1 shows the schematic diagram that the server 200 that the embodiment of the present invention provides interacts with user terminal 100.Institute
State server 200 to be communicatively coupled with one or more user terminals 100 by network 300, to carry out data communication or friendship
Mutually.Described server 200 can be the webserver, database server etc..Described user terminal 100 can be PC
(personal computer, PC), panel computer, smart mobile phone, personal digital assistant (personal digital
Assistant, PDA), mobile unit, wearable device etc..
As in figure 2 it is shown, be the block diagram of described server 200.Described server 200 includes memorizer 201, processes
Device 202 and mixed-media network modules mixed-media 203.
Memorizer 201 can be used for storing software program and module, such as the application special recommendation side in the embodiment of the present invention
Method and programmed instruction/module corresponding to device, processor 202 by operation be stored in the software program in memorizer 201 and
Module, thus perform the application of various function and data process, i.e. realize the application special recommendation method in the embodiment of the present invention.
Memorizer 201 can include high speed random access memory, may also include nonvolatile memory, as one or more magnetic storage fills
Put, flash memory or other non-volatile solid state memories.Further, the software program in above-mentioned memorizer 201 and module
May also include that operating system 221 and service module 222.Wherein operating system 221, can be such as LINUX, UNIX,
WINDOWS, it can include various for managing system task (such as memory management, storage device control, power management etc.)
Component software and/or driving, and can communication mutual with various hardware or component software, thus provide the operation of other component softwares
Environment.On the basis of service module 222 operates in operating system 221, and by the network service of operating system 221 monitor from
The request of network, completes corresponding data according to request and processes, and return result to client.It is to say, service mould
Block 222 is for providing network service to client.
Mixed-media network modules mixed-media 203 is used for receiving and sending network signal.Above-mentioned network signal can include wireless signal or have
Line signal.
Be appreciated that the structure shown in Fig. 2 be only signal, described server 200 may also include more more than shown in Fig. 2 or
The assembly that person is less, or there is the configuration different from shown in Fig. 2.Each assembly shown in Fig. 2 can use hardware, software or
A combination thereof realizes.It addition, the server in the embodiment of the present invention can also include the server of multiple concrete difference in functionality.
In the embodiment of the present invention, being provided with client in user terminal 100, this client can be that third-party application is soft
Part, such as, apply shop, holds corresponding with server (Server), jointly follows same set of data protocol so that service end with
Client can parse mutually the data of the other side, provides the user application special recommendation service.
Fig. 3 shows a kind of flow chart applying special recommendation method that the embodiment of the present invention provides, and refers to Fig. 3, this
What embodiment described is the handling process of server, and described method includes:
Step S400, according to the list of application of user to be recommended, calculates the characteristic vector of user to be recommended.
Wherein, the list of application of described user to be recommended includes that user to be recommended has installed list of application and Preset Time
In the browse application list downloaded in list of application and described preset time period in Duan and described preset time period more
New opplication list.
Server can get the list of application corresponding with user to be recommended from the user terminal of user to be recommended, it is possible to
With each user terminal from server download/browse/more new opplication time, described user terminal downloaded by server with it/clear
The application look at/update carries out mating and record, when needing to obtain list of application corresponding to described user to be recommended, and can be direct
Obtain from server.
Preferably, can obtain user to be recommended installed list of application, nearest n days download list of application, nearest n days clear
Look at list of application, nearest n days update list of application, totally four class list of applications.It is understood that according to nearest number to be recommended
According to being analyzed, the application special recommendation list obtained also will be more accurate.
According to the list of application corresponding with user to be recommended, the embodiment of the characteristic vector calculating user to be recommended has many
Kind, following is a brief introduction of two kinds of embodiments, but it is understood that, it is not limited to described embodiment.
As a kind of embodiment, the Apply Names in list of application corresponding for user to be recommended can be carried out Hash meter
Calculate, each Apply Names is calculated a cryptographic Hash, treat described in cryptographic Hash composition corresponding for the plurality of application name
Recommend the characteristic vector of user.
As another embodiment, referring to Fig. 4, described step S400 may include that
Step S410, calculates the probability distribution of the default label of the application correspondence of described user to be recommended.
Referring to Fig. 5, as a kind of embodiment, step S410 may include that
Step S411, obtains the list of application of described user to be recommended.
Preferably, can obtain user to be recommended installed list of application, nearest n days download list of application, nearest n days clear
Look at list of application, nearest n days update list of application, totally four class list of applications.It is understood that according to be recommended the most up-to-date
Data be analyzed, the application special recommendation list obtained also will be more accurate.
Step S412, inquires about the default label applying correspondence in described list of application.
Mapping table can be pre-set, application is got up with corresponding tag match, can find by the way of tabling look-up
The default label that application is corresponding.For example, it is possible to " XX store " applied and preset label " net purchase " and mate, and it is added to reflect
In firing table." XX music player " can also be applied and preset label " music " and mate, and be added in mapping table.
Step S413, according to applying corresponding number of operations and predetermined registration operation weight in described list of application, calculates institute
State the score value applying correspondence in list of application.
When the application update times of i, number of visits, download time and installation number of times are respectively as follows: update_appi、view_
appi、download_appi、install_appi, update operation weight, the weight of browse operation, the weight of down operation and
The weight installing operation is respectively as follows: wupdate、wview、wdownload、winstall。
Therefore corresponding for application i score value is:
score i=
update_app i×wupdate
+view_app i×wviewe
+download_app i×wdownload
+install_app i×winstadll
Step S414, according to applying application correspondence in corresponding score value and described list of application in described list of application
Preset label, calculate the probit of default label corresponding to described user to be recommended, it is thus achieved that the application of described user to be recommended is right
The probability distribution of the default label answered.
Being added by the score value belonging to the application of default label respectively, draw the score value that described default label is corresponding, each is pre-
The score value that bidding label are corresponding is normalized, it is thus achieved that the probit of each default label, thus obtains described use to be recommended
The probability distribution of the default label of the application correspondence at family.
Such as:
(1) list of application and each number of operations applying correspondence and the predetermined registration operation weight of user are first got
As shown in table 1 below.
Table 1
(2) the default label applying correspondence is inquired about in described list of application, as shown in table 2 below:
Table 2
(3) according to the score value applying correspondence in the step S413 described list of application of calculating:
Apply score score1=0.5*1+0.5*1=1 of 1 correspondence；
Apply score score2=1*1=1 of 2 correspondences；
Apply score score3=*1=1 of 3 correspondences.
Result of calculation is as shown in table 3 below:
Table 3
(4) according to the probability distribution applying corresponding default label of the step S414 described user to be recommended of acquisition:
The probit presetting label " social " corresponding is: 1/3；
The probit presetting label " net purchase " corresponding is: 1/3；
The probit presetting label " music " corresponding is: 1/3；
Therefore, the probability distribution of the default label of the application correspondence of described user to be recommended is as shown in table 4 below, wherein, and p
(cj|ui) represent the probit of label j of user i:
Table 4
Step S420, calculates the probability distribution of the described default label of the application correspondence of whole user.
Referring to Fig. 6, as a kind of embodiment, step S420 may include that
Step S421, obtains the list of application of described whole user.
Step S422, inquires about the default label applying correspondence in described list of application.
Step S423, according to applying corresponding number of operations and predetermined registration operation weight in described list of application, calculates institute
State the score value that the application in list of application is corresponding.
Step S424, according to applying application correspondence in corresponding score value and described list of application in described list of application
Preset label, calculate the probit of default label corresponding to described whole user, it is thus achieved that the application correspondence of described whole users
The probability distribution of described default label.
It is understood that step S421 is to step S424, identical with the embodiment of step S411 to step S414, only
It is that the list of application obtained is different, the most just repeats no more.
Step S430, according to the probability distribution of default label corresponding to the application of described user to be recommended and described all
The probability distribution of the described default label of the application correspondence of user, calculates the characteristic vector of described calculating user to be recommended.
Assuming total N number of label, the characteristic vector of user i is Vi=[vi,1,vi,2,...,vi,j,...,vi,N], whereinp(cj) represent the probability distribution of label j corresponding to the application of whole user, p (cj|ui) represent user
The probit of the label j of i.
For example, it is assumed that the pre-bidding applying correspondence of the user described to be recommended drawn according to step S421 to step S424
The probability distribution signed is as shown in table 5 below, wherein, and p (cj|ui) represent the probit of label j of user i:
Table 5
The described default label that the application of the described whole users drawn according to step S421 to step S424 is corresponding general
Rate is distributed, as shown in table 6 below:
Table 6
| Label | Distribution Value |
| Music | 3.03% |
| Net purchase | 16.16% |
| Social | 15.29% |
| ....... | 0.15% |
| ....... | 0.42% |
| ....... | 0.09% |
| ....... | 0.30% |
| ....... | 0.54% |
| ....... | 0.18% |
| ....... | 4.77% |
| ....... | 1.38% |
| ....... | 0.70% |
| ....... | 0.80% |
| ....... | 0.50% |
| ....... | 0.19% |
| ....... | 0.08% |
Then according to the probability distribution of default label corresponding to the application of described user to be recommended and described whole user
The probability distribution of the described default label that application is corresponding, the characteristic vector of the described calculating user to be recommended calculated, such as table 7 below
Shown in:
Table 7
| Label | Vi, j |
| Social | 2.18 |
| Net purchase | 2.06 |
| Music | 11.00 |
That is, the characteristic vector of user to be recommended is: V=(2.18,2.06,11.00).
Further, may be otherwise on the basis of shown characteristic vector, use machine learning method, generate new to
Measure the characteristic vector as user.
Step S500, calculates each characteristic vector presetting application special topic respectively.
Wherein, application special topic refer to can according to certain rule, will have at least an aspect and certain theme or subject matter or
Much-talked-about topic etc. have dependency application integrating get up formed set of applications.Described dependency can be that name is correlated with or merit
Can be relevant etc..Such as, if current hotspot topic is " woman that dissipates a family fortune more understands life ", due to " the preferential application of XX ", " XX net purchase should
With " all relevant to this much-talked-about topic, therefore can form application special topic " woman that dissipates a family fortune more understands life ", this application is specially
Topic includes " the preferential application of XX " and " XX net purchase application ".
Calculate each embodiment presetting application special topic characteristic of correspondence vector and also have a variety of, such as can be according to meter
Calculate the cryptographic Hash of each Apply Names in each application special topic, cryptographic Hash corresponding for the plurality of application name is constituted correspondence
The characteristic vector of application special topic；The general of each default label corresponding to application special topic can also be preset respectively according to described each
Rate, it is thus achieved that described each presets application special topic characteristic of correspondence vector.
As a kind of embodiment, referring to Fig. 7, step S500 may include that
Step S510, obtains described each and presets the default label applying the application included by special topic.
Step S520, calculate described each preset the probability of all kinds of default label under application special topic, obtain described respectively
The characteristic vector of individual default application special topic.
Wherein, refer to Fig. 8, the probability of all kinds of default label under each presets application special topic described in described calculating,
Including:
Step S521, according to described each number of operations presetting the application correspondence that application special topic includes and predetermined registration operation
Weight, calculates described each respectively and presets the score value that the thematic application included of application is corresponding.
Step S522, presets according to each score value presetting the application correspondence that application special topic includes described and described each
The default label of the application correspondence that application special topic includes, calculates described each and presets thematic each the corresponding default label of application
Probability.
It is understood that described step S521 is similar to step S424 to step S423 to step S522, the most not
Repeat again.
Step S600, characteristic vector based on described user to be recommended presets, with described each, the characteristic vector that application is thematic
Generate the application special recommendation list of described user to be recommended.
As a kind of embodiment, referring to Fig. 9, described step S600 may include that
Step S610, the characteristic vector calculating described user to be recommended respectively is corresponding with each default application special topic described
The matching degree of characteristic vector.
Calculate the characteristic vector of described user to be recommended with described each preset application special topic characteristic of correspondence vector
The mode of degree of joining also has multiple, for example, it is possible to calculate matching degree, also by calculating the Euclidean distance between two characteristic vectors
Matching degree can be calculated, it is also possible to by calculating two features by calculating the Chebyshev's distance between two characteristic vectors
COS distance between vector calculates matching degree, it is not limited to described embodiment.
As a kind of embodiment, by each element of the characteristic vector of described user to be recommended respectively with described each is pre-
If the element multiplication of application special topic characteristic of correspondence vector correspondence position is also sued for peace, it is thus achieved that the characteristic vector of described user to be recommended
The matching degree that application special topic characteristic of correspondence is vectorial is preset with described each.
I.e. user i and the matching degree of special topic j, can calculate according to the following equation:
In above formula, (i j) represents the matching degree between user i and special topic j, V to fiIt it is the feature of described user to be recommended
Vector, TiDescribed each presets the matching degree that application special topic characteristic of correspondence is vectorial.
Step S620, according to described matching degree, generates application special recommendation list.
Can be by described matching degree according to being ranked up, the mode of sequence can be descending or ascending sort, according to row
Sequence result, generates application special recommendation list.
As a kind of embodiment, by described matching degree according to descending sort, according to ranking results, generate application special topic and push away
Recommend list.
The characteristic vector assuming user to be recommended is: V=(2.18,2.06,11.00), and described each obtained is preset
Application special topic characteristic of correspondence vector is as shown in table 8 below:
Table 8
After calculating matching degree, and the matching degree of its corresponding all special topics is sorted from high to low, i.e. obtain
Special recommendation list to each user, can select the special topic of predetermined number to put in special recommendation list, it is assumed that to be 2, then
The special recommendation sequence calculating this user is:
(1) music too late to meet
(2) woman dissipated a family fortune more understands life
It is understood that after application special recommendation list, special topic list can be applied to be sent to institute described generation
State the user terminal that user to be recommended is corresponding, so that described user to be recommended receives described application special recommendation by user terminal
After list, carry out applying the selection of application in special topic to download.
A kind of application special recommendation method that the embodiment of the present invention provides, by calculate respectively the feature of user to be recommended to
Described each of amount presets the matching degree applying special topic characteristic of correspondence vector, and recommends to be suitable for user according to described matching degree
Application special topic, in this way, default special topic and user can be carried out Auto-matching, it is not necessary to operation personnel goes to judge
Which user to recommend which special topic to, the work efficiency of operation personnel can be improved, further, it is also possible to improve user and click on
Download conversion ratio, improve Consumer's Experience.
Refer to Figure 10, be the high-level schematic functional block diagram of the application special recommendation device 700 that the embodiment of the present invention provides.Institute
State application special recommendation device 700 and include the first computing module 710, the second computing module 720, and generation module 730.
Described first computing module 710, for the list of application according to user to be recommended, calculates the feature of user to be recommended
Vector.
Described second computing module 720, for calculating each characteristic vector presetting application special topic respectively.
Described generation module 730, presets application specially for characteristic vector based on described user to be recommended with described each
The characteristic vector of topic generates the application special recommendation list of described user to be recommended.
Wherein, refer to Figure 11, be described first meter in the application special recommendation device 700 of embodiment of the present invention offer
Calculate the high-level schematic functional block diagram of module 710.Described first computing module 710 includes the first processing module 711, the second processing module
712 and the 3rd processing module 713,
Described first processing module 711, for calculating the probability of default label corresponding to the application of described user to be recommended
Distribution.
Described second processing module 712, divides for calculating the probability of described default label corresponding to the application of whole user
Cloth.
Described 3rd processing module 713, for the probability of the default label of the application correspondence according to described user to be recommended
The probability distribution of the described default label of the application correspondence of distribution and described whole user, calculates the spy of described user to be recommended
Levy vector.
Wherein, refer to Figure 12, be at described first in the application special recommendation device 700 of embodiment of the present invention offer
The high-level schematic functional block diagram of reason module 711.Described first processing module 711 includes the first acquisition submodule 7111, the first inquiry
Submodule 7112, the first calculating sub module 7113 and the second calculating sub module 7114.
Described first obtains submodule 7111, for obtaining the list of application of described user to be recommended.
Described first inquiry submodule 7112, for inquiring about the default label applying correspondence in described list of application.
Described first calculating sub module 7113, for according to applying the number of operations of correspondence and pre-in described list of application
If operation weight, calculate the score value applying correspondence in described list of application.
Described second calculating sub module 7114, for according to described list of application is applied correspondence score value and described should
With list is applied corresponding default label, calculate the probit of default label corresponding to described user to be recommended, it is thus achieved that described
The probability distribution of the default label of the application correspondence of user to be recommended.
Wherein, refer to Figure 13, be at described second in the application special recommendation device 700 of embodiment of the present invention offer
The high-level schematic functional block diagram of reason module 712.Described second processing module 712 includes the second acquisition submodule 7121, the second inquiry
Submodule 7122, the 3rd calculating sub module 7123 and the 4th calculating sub module 7124.
Described second obtains submodule 7121, for obtaining the list of application of described whole user.
Described second inquiry submodule 7122, for inquiring about the default label applying correspondence in described list of application.
Described 3rd calculating sub module 7123, for according to applying the number of operations of correspondence and pre-in described list of application
If operation weight, calculate the score value that the application in described list of application is corresponding.
Described 4th calculating sub module 7124, for according to described list of application is applied correspondence score value and described should
With list is applied correspondence default label, calculate the probit of default label corresponding to described whole user, it is thus achieved that described entirely
The probability distribution of the described default label of the application correspondence of portion user.
Refer to Figure 14, be the second computing module 720 in the application special recommendation device 700 of embodiment of the present invention offer
High-level schematic functional block diagram.Described second computing module 720 includes the 3rd acquisition submodule 721 and the 5th calculating sub module
722。
Described 3rd obtains submodule 721, presets presetting of application application included by special topic for obtaining described each
Label.
Wherein, the probability of all kinds of default label under each presets application special topic described in described calculating, including: according to institute
Stating number of operations corresponding to each default application applying special topic to include and predetermined registration operation weight, described in calculating, each is pre-respectively
If the score value that the application that application special topic includes is corresponding；According to described each preset score value corresponding to application that application special topic includes with
And described each preset default label that application that application special topic includes is corresponding, calculating described each, to preset application special topic corresponding
The probability of each default label.
Described 5th calculating sub module 722, for calculating all kinds of default label under each default application special topic described
Probability, obtain described each and preset characteristic vector of application special topic.
Refer to Figure 15, be the merit of generation module 730 in the application special recommendation device 700 that provides of the embodiment of the present invention
Can module diagram.Described generation module 730 includes the 6th calculating sub module 731 and generates submodule 732.
Described 6th calculating sub module 731, for calculate respectively the characteristic vector of described user to be recommended with described each
Preset the matching degree of application special topic characteristic of correspondence vector.
As a kind of embodiment, described 6th calculating sub module 731, specifically for the feature by described user to be recommended
Each element of vector is preset the element multiplication of application special topic characteristic of correspondence vector correspondence position with described each and asks respectively
With, it is thus achieved that the characteristic vector of described user to be recommended presets, with described each, the matching degree that application special topic characteristic of correspondence is vectorial.
Described generation submodule 732, for according to described matching degree, generates application special recommendation list.
As a kind of embodiment, described generation submodule 732, specifically for by described matching degree according to descending sort,
According to ranking results, generate application special recommendation list.
The most each module can be by software code realization, and now, above-mentioned each module can be stored in depositing of server 200
In reservoir 201.The most each module is equally realized by hardware such as IC chip.
It should be noted that each embodiment in this specification all uses the mode gone forward one by one to describe, each embodiment weight
Point explanation is all the difference with other embodiments, and between each embodiment, identical similar part sees mutually.
The application special recommendation device that the embodiment of the present invention is provided, it realizes principle and the technique effect of generation and aforementioned
Embodiment of the method is identical, for briefly describing, and the not mentioned part of device embodiment part, refer in preceding method embodiment corresponding
Content.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, it is also possible to pass through
Other mode realizes.Device embodiment described above is only schematically, such as, and the flow chart in accompanying drawing and block diagram
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this, each square frame in flow chart or block diagram can represent a module, program segment or the one of code
Part, a part for described module, program segment or code comprises holding of one or more logic function for realizing regulation
Row instruction.It should also be noted that at some as in the implementation replaced, the function marked in square frame can also be to be different from
The order marked in accompanying drawing occurs.Such as, two continuous print square frames can essentially perform substantially in parallel, and they are the most also
Can perform in the opposite order, this is depending on involved function.It is also noted that every in block diagram and/or flow chart
The combination of the square frame in individual square frame and block diagram and/or flow chart, can be with function or the special base of action performing regulation
System in hardware realizes, or can realize with the combination of specialized hardware with computer instruction.
It addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation
Point, it is also possible to it is modules individualism, it is also possible to two or more modules are integrated to form an independent part.
If described function is using the form realization of software function module and as independent production marketing or use, permissible
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is the most in other words
The part contributing prior art or the part of this technical scheme can embody with the form of software product, this meter
Calculation machine software product is stored in a storage medium, including some instructions with so that a computer equipment (can be individual
People's computer, server, or the network equipment etc.) perform all or part of step of method described in each embodiment of the present invention.
And aforesaid storage medium includes: USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as memorizer (RAM, Random Access Memory), magnetic disc or CD.Need
Being noted that in this article, the relational terms of such as first and second or the like is used merely to an entity or operation
Separate with another entity or operating space, and exist any this between not necessarily requiring or imply these entities or operating
Actual relation or order.And, term " includes ", " comprising " or its any other variant are intended to nonexcludability
Comprise, so that include that the process of a series of key element, method, article or equipment not only include those key elements, but also wrap
Include other key elements being not expressly set out, or also include want intrinsic for this process, method, article or equipment
Element.In the case of there is no more restriction, statement " including ... " key element limited, it is not excluded that including described wanting
Process, method, article or the equipment of element there is also other identical element.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.All within the spirit and principles in the present invention, that is made any repaiies
Change, equivalent, improvement etc., should be included within the scope of the present invention.It should also be noted that similar label and letter exist
Figure below represents similar terms, therefore, the most a certain Xiang Yi accompanying drawing is defined, is then not required in accompanying drawing subsequently
It is defined further and explains.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art, in the technical scope that the invention discloses, can readily occur in change or replace, should contain
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should described be as the criterion with scope of the claims.
Claims (20)
1. an application special recommendation method, it is characterised in that described method includes:
According to the list of application of user to be recommended, calculate the characteristic vector of user to be recommended；
Calculate each characteristic vector presetting application special topic respectively；
Characteristic vector based on described user to be recommended and each characteristic vector presetting application special topic described are waited to push away described in generating
Recommend the application special recommendation list of user.
Method the most according to claim 1, it is characterised in that the described list of application according to user to be recommended, calculating is treated
Recommend the characteristic vector of user, including:
Calculate the probability distribution of the default label of the application correspondence of described user to be recommended；
Calculate the probability distribution of the described default label of the application correspondence of whole user；
The probability distribution of the default label of the application correspondence according to described user to be recommended and the application of described whole user are right
The probability distribution of the described default label answered, calculates the characteristic vector of described calculating user to be recommended.
Method the most according to claim 2, it is characterised in that calculate the pre-bidding that the application of described user to be recommended is corresponding
The probability distribution signed, including:
Obtain the list of application of described user to be recommended；
Inquire about the default label applying correspondence in described list of application；
According to applying corresponding number of operations and predetermined registration operation weight in described list of application, calculating should in described list of application
With corresponding score value；
According to described list of application is applied the default label applying correspondence in corresponding score value and described list of application, calculate
The probit of the default label that described user to be recommended is corresponding, it is thus achieved that the default label of the application correspondence of described user to be recommended
Probability distribution.
Method the most according to claim 2, it is characterised in that the described of application correspondence of the whole user of described calculating is preset
The probability distribution of label, including:
Obtain the list of application of described whole user；
Inquire about the default label applying correspondence in described list of application；
According to described list of application is applied corresponding number of operations and predetermined registration operation weight, calculate in described list of application
The score value that application is corresponding；
According to described list of application is applied the default label applying correspondence in corresponding score value and described list of application, calculate
The probit of the default label that described whole user is corresponding, it is thus achieved that the described default label of the application correspondence of described whole users
Probability distribution.
Method the most according to claim 1, it is characterised in that described calculate respectively each preset application special topic feature to
Amount, including:
Obtain described each and preset the default label applying the application included by special topic；
The probability of all kinds of default label under each presets application special topic described in calculating, obtains each default application special topic described
Characteristic vector.
Method the most according to claim 5, it is characterised in that described in described calculating each preset application special topic under each
Class presets the probability of label, including:
According to described each number of operations presetting the application correspondence that application special topic includes and predetermined registration operation weight, calculate respectively
Described each presets the score value applying correspondence that application special topic includes；
Preset application special topic according to each score value presetting the application correspondence that application special topic includes described and described each to include
Default label corresponding to application, calculate described each and preset probability of each default label corresponding to application special topic.
Method the most according to claim 1, it is characterised in that described characteristic vector based on described user to be recommended and institute
State each and preset application special topic characteristic of correspondence vector, generate the application special recommendation list obtaining described user to be recommended, bag
Include:
Calculate respectively the characteristic vector of described user to be recommended with described each preset application special topic characteristic of correspondence vector
Degree of joining；
According to described matching degree, generate application special recommendation list.
Method the most according to claim 7, it is characterised in that calculate the characteristic vector of described user to be recommended with described respectively
The matching degree of individual default application special topic characteristic of correspondence vector, including:
Each element of the characteristic vector of described user to be recommended is preset with described each respectively application special topic characteristic of correspondence
The vector element multiplication of correspondence position is also sued for peace, it is thus achieved that the characteristic vector of described user to be recommended presets application specially with described each
The matching degree of topic characteristic of correspondence vector.
Method the most according to claim 7, it is characterised in that described according to described matching degree, generates application special recommendation
List, including:
By described matching degree according to descending sort, according to ranking results, generate application special recommendation list.
Method the most according to claim 1, it is characterised in that list of application corresponding to described and user to be recommended includes
Described user to be recommended has installed the download list of application in list of application and preset time period and described preset time period
Renewal list of application in interior browse application list and described preset time period.
11. 1 kinds of application special recommendation devices, it is characterised in that described device includes:
First computing module, for the list of application according to user to be recommended, calculates the characteristic vector of user to be recommended；
Second computing module, for calculating each characteristic vector presetting application special topic respectively；
Generation module, presets, with described each, the characteristic vector that application is thematic for characteristic vector based on described user to be recommended
Generate the application special recommendation list of described user to be recommended.
12. devices according to claim 11, it is characterised in that described first computing module includes the first processing module,
Second processing module and the 3rd processing module,
Described first processing module, for calculating the probability distribution of default label corresponding to the application of described user to be recommended；
Described second processing module, for calculating the probability distribution of described default label corresponding to the application of whole user；
Described 3rd processing module, for default label corresponding to the application according to described user to be recommended probability distribution and
The probability distribution of the described default label of the application correspondence of described whole user, calculates the characteristic vector of described user to be recommended.
13. devices according to claim 12, it is characterised in that described first processing module includes the first acquisition submodule
Block, the first inquiry submodule, the first calculating sub module and the second calculating sub module,
Described first obtains submodule, for obtaining the list of application of described user to be recommended；
Described first inquiry submodule, for inquiring about the default label applying correspondence in described list of application；
Described first calculating sub module, for according to number of operations and the predetermined registration operation power applying correspondence in described list of application
Weight, calculates the score value applying correspondence in described list of application；
Described second calculating sub module, for according in score value and the described list of application of applying correspondence in described list of application
The default label that application is corresponding, calculates the probit of default label corresponding to described user to be recommended, it is thus achieved that described use to be recommended
The probability distribution of the default label of the application correspondence at family.
14. devices according to claim 12, it is characterised in that described second processing module includes the second acquisition submodule
Block, the second inquiry submodule, the 3rd calculating sub module and the 4th calculating sub module,
Described second obtains submodule, for obtaining the list of application of described whole user；
Described second inquiry submodule, for inquiring about the default label applying correspondence in described list of application；
Described 3rd calculating sub module, for according to number of operations and the predetermined registration operation power applying correspondence in described list of application
Weight, calculates the score value that the application in described list of application is corresponding；
Described 4th calculating sub module, for according in score value and the described list of application of applying correspondence in described list of application
The default label that application is corresponding, calculates the probit of default label corresponding to described whole user, it is thus achieved that described whole users'
The probability distribution of the described default label that application is corresponding.
15. devices according to claim 11, it is characterised in that described second computing module, obtain submodule including the 3rd
Block and the 5th calculating sub module,
Described 3rd obtains submodule, for obtaining the default label of each default application application included by special topic described；
Described 5th calculating sub module, for calculating the probability of all kinds of default label under each default application special topic described,
Obtain described each and preset the characteristic vector that application is thematic.
16. devices according to claim 15, it is characterised in that under each presets application special topic described in described calculating
The probability of all kinds of default labels, including:
According to described each number of operations presetting the application correspondence that application special topic includes and predetermined registration operation weight, calculate respectively
Described each presets the score value applying correspondence that application special topic includes；
Preset application special topic according to each score value presetting the application correspondence that application special topic includes described and described each to include
Default label corresponding to application, calculate described each and preset probability of each default label corresponding to application special topic.
17. devices according to claim 11, it is characterised in that described generation module, including the 6th calculating sub module with
And generation submodule,
Described 6th calculating sub module, presets application for calculating the characteristic vector of described user to be recommended respectively with described each
The matching degree of special topic characteristic of correspondence vector；
Described generation submodule, for according to described matching degree, generates application special recommendation list.
18. devices according to claim 17, it is characterised in that described 6th calculating sub module, specifically for by described
Each element of the characteristic vector of user to be recommended presets the application special topic corresponding position of characteristic of correspondence vector respectively with described each
The element multiplication put also is sued for peace, it is thus achieved that the characteristic vector of described user to be recommended and described each preset spy that application special topic is corresponding
Levy the matching degree of vector.
19. devices according to claim 17, it is characterised in that described generation submodule, specifically for by described coupling
Spend according to descending sort, according to ranking results, generate application special recommendation list.
20. 1 kinds of servers, it is characterised in that described server includes that processor and memorizer, described memorizer are couple to institute
State processor, described memory store instruction, make below described processor execution when executed by the processor
Operation:
According to the list of application of user to be recommended, calculate the characteristic vector of user to be recommended；
Calculate each characteristic vector presetting application special topic respectively；
Characteristic vector based on described user to be recommended and each characteristic vector presetting application special topic described are waited to push away described in generating
Recommend the application special recommendation list of user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610661824.2A CN106326369B (en) | 2016-08-12 | 2016-08-12 | Application topic recommendation method and device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610661824.2A CN106326369B (en) | 2016-08-12 | 2016-08-12 | Application topic recommendation method and device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106326369A true CN106326369A (en) | 2017-01-11 |
| CN106326369B CN106326369B (en) | 2019-12-31 |
Family
ID=57740087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610661824.2A Expired - Fee Related CN106326369B (en) | 2016-08-12 | 2016-08-12 | Application topic recommendation method and device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106326369B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107315780A (en) * | 2017-06-06 | 2017-11-03 | 广州市动景计算机科技有限公司 | Application software method for pushing and device |
| CN107705156A (en) * | 2017-10-16 | 2018-02-16 | 深圳大宇无限科技有限公司 | User feature analysis method and device |
| CN107743151A (en) * | 2017-11-29 | 2018-02-27 | 广东欧珀移动通信有限公司 | Content delivery method, device, mobile terminal and server |
| CN107862016A (en) * | 2017-10-30 | 2018-03-30 | 江西博瑞彤芸科技有限公司 | A kind of collocation method of the thematic page |
| CN107885572A (en) * | 2017-12-11 | 2018-04-06 | 广东欧珀移动通信有限公司 | Classification card generation method, system, server and computer-readable recording medium |
| CN107958056A (en) * | 2017-11-29 | 2018-04-24 | 广东欧珀移动通信有限公司 | Using recommendation method, apparatus and mobile terminal |
| CN108460073A (en) * | 2017-12-27 | 2018-08-28 | 广州市百果园信息技术有限公司 | Group recommending method, storage medium and server |
| CN108510352A (en) * | 2018-02-09 | 2018-09-07 | 广州优视网络科技有限公司 | Application issue recommends method, apparatus and computer equipment |
| CN109902222A (en) * | 2018-11-30 | 2019-06-18 | 华为技术有限公司 | Recommendation method and device |
| CN110569422A (en) * | 2018-03-29 | 2019-12-13 | 广州市动景计算机科技有限公司 | application recommendation method and device based on application vector |
| WO2020015112A1 (en) * | 2018-07-20 | 2020-01-23 | 平安科技（深圳）有限公司 | Product function recommendation method, terminal device and computer-readable storage medium |
| CN116017070A (en) * | 2022-12-01 | 2023-04-25 | 四川长虹电器股份有限公司 | Method for improving clicking rate of television homepage based on operation strategy |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102495872A (en) * | 2011-11-30 | 2012-06-13 | 中国科学技术大学 | Method and device for conducting personalized news recommendation to mobile device users |
| CN102591942A (en) * | 2011-12-27 | 2012-07-18 | 奇智软件（北京）有限公司 | Method and device for automatic application recommendation |
| CN103246672A (en) * | 2012-02-09 | 2013-08-14 | 中国科学技术大学 | Method and device for performing personalized recommendation on users |
| CN103744849A (en) * | 2011-12-27 | 2014-04-23 | 北京奇虎科技有限公司 | Method and device for automatic recommendation application |
| CN105069106A (en) * | 2015-08-07 | 2015-11-18 | 小米科技有限责任公司 | Application group recommendation method and device |
| CN105117440A (en) * | 2015-08-11 | 2015-12-02 | 北京奇虎科技有限公司 | Method and apparatus for determining to-be-recommended application (APP) |
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
-
2016
- 2016-08-12 CN CN201610661824.2A patent/CN106326369B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102495872A (en) * | 2011-11-30 | 2012-06-13 | 中国科学技术大学 | Method and device for conducting personalized news recommendation to mobile device users |
| CN102591942A (en) * | 2011-12-27 | 2012-07-18 | 奇智软件（北京）有限公司 | Method and device for automatic application recommendation |
| CN103744849A (en) * | 2011-12-27 | 2014-04-23 | 北京奇虎科技有限公司 | Method and device for automatic recommendation application |
| CN103246672A (en) * | 2012-02-09 | 2013-08-14 | 中国科学技术大学 | Method and device for performing personalized recommendation on users |
| CN105069106A (en) * | 2015-08-07 | 2015-11-18 | 小米科技有限责任公司 | Application group recommendation method and device |
| CN105117440A (en) * | 2015-08-11 | 2015-12-02 | 北京奇虎科技有限公司 | Method and apparatus for determining to-be-recommended application (APP) |
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107315780B (en) * | 2017-06-06 | 2020-09-04 | 阿里巴巴（中国）有限公司 | Application software pushing method and device |
| CN107315780A (en) * | 2017-06-06 | 2017-11-03 | 广州市动景计算机科技有限公司 | Application software method for pushing and device |
| CN107705156A (en) * | 2017-10-16 | 2018-02-16 | 深圳大宇无限科技有限公司 | User feature analysis method and device |
| CN107862016A (en) * | 2017-10-30 | 2018-03-30 | 江西博瑞彤芸科技有限公司 | A kind of collocation method of the thematic page |
| CN107862016B (en) * | 2017-10-30 | 2021-06-15 | 北京博瑞彤芸科技股份有限公司 | Configuration method of special topic page |
| CN107743151A (en) * | 2017-11-29 | 2018-02-27 | 广东欧珀移动通信有限公司 | Content delivery method, device, mobile terminal and server |
| CN107958056A (en) * | 2017-11-29 | 2018-04-24 | 广东欧珀移动通信有限公司 | Using recommendation method, apparatus and mobile terminal |
| CN107885572A (en) * | 2017-12-11 | 2018-04-06 | 广东欧珀移动通信有限公司 | Classification card generation method, system, server and computer-readable recording medium |
| CN108460073A (en) * | 2017-12-27 | 2018-08-28 | 广州市百果园信息技术有限公司 | Group recommending method, storage medium and server |
| CN108510352A (en) * | 2018-02-09 | 2018-09-07 | 广州优视网络科技有限公司 | Application issue recommends method, apparatus and computer equipment |
| CN110569422A (en) * | 2018-03-29 | 2019-12-13 | 广州市动景计算机科技有限公司 | application recommendation method and device based on application vector |
| CN110569422B (en) * | 2018-03-29 | 2022-06-17 | 阿里巴巴（中国）有限公司 | Application recommendation method and device based on application vector |
| WO2020015112A1 (en) * | 2018-07-20 | 2020-01-23 | 平安科技（深圳）有限公司 | Product function recommendation method, terminal device and computer-readable storage medium |
| CN109902222A (en) * | 2018-11-30 | 2019-06-18 | 华为技术有限公司 | Recommendation method and device |
| WO2020107806A1 (en) * | 2018-11-30 | 2020-06-04 | 华为技术有限公司 | Recommendation method and device |
| US11586941B2 (en) | 2018-11-30 | 2023-02-21 | Huawei Technologies Co., Ltd. | Recommendation method and apparatus |
| CN116017070A (en) * | 2022-12-01 | 2023-04-25 | 四川长虹电器股份有限公司 | Method for improving clicking rate of television homepage based on operation strategy |
| CN116017070B (en) * | 2022-12-01 | 2024-04-12 | 四川长虹电器股份有限公司 | Method for improving clicking rate of television homepage based on operation strategy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106326369B (en) | 2019-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326369A (en) | Application special topic recommendation method, application special topic recommendation device and server | |
| CN106294752A (en) | The application method of special recommendation, device and server | |
| CN108604222B (en) | System and method for deploying customized machine learning services | |
| CN106250532A (en) | Application recommendation method, device and server | |
| CN101840410B (en) | Learning apparatus, learning method, information processing apparatus, method and program | |
| CN108574706B (en) | Media file pushing method and device | |
| CN106372961A (en) | Commodity recommendation method and device | |
| Liu et al. | A hybrid VNS-HS algorithm for a supply chain scheduling problem with deteriorating jobs | |
| CN104092555B (en) | A kind of methods, devices and systems of undated parameter value | |
| CN104636955A (en) | Merchant management information integration method and merchant management information integration system based on mobile internet | |
| Zandi et al. | Green parallel machines scheduling problem: A bi-objective model and a heuristic algorithm to obtain Pareto frontier | |
| US20140379488A1 (en) | Advertisement distribution management apparatus, advertisement distribution system, and advertisement distribution management method | |
| CN114625976B (en) | Data recommendation method, device, equipment and medium based on federal learning | |
| Xu et al. | Dynamic order acceptance and scheduling problem with sequence-dependent setup time | |
| Zaman et al. | Sustainable operator assignment in an assembly line using genetic algorithm | |
| WO2012115965A1 (en) | Entity fingerprints | |
| CN105930390A (en) | Relation-type database expansion method and relation-type database expansion system | |
| CN106534180A (en) | Electric appliance control method and system | |
| CN107632971A (en) | Method and apparatus for generating multidimensional form | |
| CN105677880B (en) | Dynamic divides the implementation method and device of display area | |
| CN108874808A (en) | A kind of page elements interlock method, device and server | |
| Wang et al. | A scatter search approach with dispatching rules for a joint decision of cell formation and parts scheduling in batches | |
| CN106210810A (en) | A kind of advertisement information processing method and device | |
| CN110275866A (en) | Exchange method, device, server and the user terminal of file generated process | |
| Leung et al. | Minimizing sum of completion times for batch scheduling of jobs with deteriorating processing times |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200526 Address after: 310051 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Patentee after: Alibaba (China) Co.,Ltd. Address before: 510627 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 Patentee before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191231 Termination date: 20200812 |