CN103744849A - Method and device for automatic recommendation application - Google Patents
Method and device for automatic recommendation application Download PDFInfo
- Publication number
- CN103744849A CN103744849A CN201310462445.7A CN201310462445A CN103744849A CN 103744849 A CN103744849 A CN 103744849A CN 201310462445 A CN201310462445 A CN 201310462445A CN 103744849 A CN103744849 A CN 103744849A
- Authority
- CN
- China
- Prior art keywords
- application
- classification
- user
- label
- access information
- 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
Images
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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
Abstract
The invention provides a method and device for automatic recommendation application. The method includes the steps of collecting user access information, dividing categories which the user access information belongs to, searching for matched applications in an application data set of preset corresponding categories according to the user access information and the categories of the user access information, generating application files corresponding to the categories and putting the searched applications of the categories in the corresponding application files to carry out recommendation. According to the method and device, individualized demands of users can be met, and recommendation efficiency and the coverage rate are improved.
Description
Patented claim of the present invention is to be the divisional application that Dec 27, application number in 2011 are 201110444074.0, name is called the Chinese invention patent application of " a kind of method and device of applying automatic recommendation " applying date.
Technical field
The application relates to technical field of information processing, particularly relates to a kind of method and a kind of device of applying automatic recommendation of applying automatic recommendation.
Background technology
Internet is an important channel of people's obtaining information, when the principal feature of conventional internet is that user finds own interested things, need to carry out a large amount of search by browser, need artificially to filter out a large amount of incoherent results simultaneously, complex operation, and expend time in and energy.
Along with the develop rapidly of Internet technology, people are also more and more extensive to the demand of diverse network application (Application), but along with the increase of demand, the terminal applies that people install in terminal clientsaconnect is also more and more, the various deployment that are applied in client are more and more too fat to move huge, this not only causes the waste to terminal resource, nor is convenient to management.Even if adopt client-server architecture to dispose management, server end also lacks the managerial ability to follow-up use after the deployment that completes client.
Although there is now the concept of so-called " thin-client (Thin Client) ", thin-client is sent to server process by inputs such as its mouse, keyboards, and server is back to client result again and shows.But this tupe is limited by network transfer speeds, and the restriction such as the processing power of server, therefore, be to be more applied in the commercial LAN (Local Area Network) of enterprise-level, be also not suitable for the amusement demand of domestic consumer at present.
For making user obtain better experience, the scheme that provides interested application automatically to recommend for user has been provided prior art, by knowing user's interest place, initiatively for it recommends, provides its interested application.But, the mode that this application is recommended, main all by the manual recommendation of editorial staff,, mainly there is following defect in the manual mode of recommending of this editorial staff:
1, efficiency is too low, too low for the recommendation coverage rate of application, for example, for application hundreds thousand of on platform, adopts artificial recommendation every day, also can only recommend hundreds of.If want to recommend whole application in fact cannot realize, and coverage rate is too low, because proportion is too low.
2, this recommendation is that the unified principle of recommending based on editorial staff is carried out completely, the same for each user, cannot meet the demand of user individual.Because the application of some recommendation is suitable for certain user, and does not like for certain user.
Therefore, need at present the urgent technical matters solving of those skilled in the art to be exactly: to propose a kind of mechanism of applying automatic recommendation, to meet user's individual demand, and improve and recommend efficiency and coverage rate.
Summary of the invention
The application's technical matters to be solved is to provide a kind of method of applying automatic recommendation, in order to meet user's individual demand, and improves and recommends efficiency and coverage rate.
The application also provides a kind of device of applying automatic recommendation, in order to guarantee said method application and realization in practice.
In order to address the above problem, the embodiment of the present application discloses a kind of method of applying automatic recommendation, specifically can comprise:
Gather user's visit information;
Divide the classification that described user access information belongs to;
According to described user access information and classification thereof, in the application data sets of preset corresponding classification, search the application of coupling;
Generate application file folder corresponding to each classification, the application of each found classification is put into corresponding application file folder and recommend.
Preferably, described user's visit information comprises user's local operation visit information, and/or, user's online operational access information.
The step of the classification that preferably, described division user access information belongs to can comprise:
Extract Main classification label in described user access information and the corresponding operation frequency;
Described Main classification label is converted to corresponding applicating category by default correlation rule; Described default correlation rule is the transformation rule of Main classification label and applicating category;
The operation frequency of adding up the corresponding Main classification label of each applicating category, sorts each applicating category from high to low by the added up operation frequency;
Extract front n applicating category of predetermined number, the classification belonging to for active user's visit information; Wherein, described n is greater than 1 positive integer.
Preferably, the application of described application data sets has Main classification label and one-level subclassification label at least, and various types of other application data set is comprised of the application with same Main classification label respectively;
Described according to user access information and classification thereof, the step of searching the application of coupling in the application data sets of preset corresponding classification may further include:
The classification belonging to according to described user access information is determined the application data set of corresponding classification;
Extract the subclassification label of described user access information;
In the application data sets of described corresponding classification, adopt the subclassification label of described user access information and the subclassification label of the corresponding level of application to mate, obtain application and the corresponding weight of coupling;
According to described weight, choose from high to low the application of front m application as the application data sets coupling of current classification, wherein, described m is greater than 1 positive integer.
Preferably, described weight can comprise: the matching value between subclassification label, or, the matching value between subclassification label and the correlation of application.
Preferably, described method, can also comprise:
By the operation frequency of the corresponding Main classification label of each applicating category, the order that represents of application file folder is set;
By the described order that represents, on the desktop of subscriber equipment, represent described application file folder;
In each application file folder, by the weight of application, represent from high to low described application.
Preferably, described method, can also comprise:
Obtain the operation information of user for institute's exemplary application, the weight of the corresponding application of corresponding adjustment.
Preferably, described method, can also comprise:
Obtain the operation information of user for application file folder, what corresponding adjustment application file pressed from both sides represents sequentially.
Preferably, described method, can also comprise:
According to gathered user access information, set up user characteristics storehouse;
Operation information by user for institute's exemplary application, writes described user characteristics storehouse.
The application discloses a kind of device of applying automatic recommendation simultaneously, specifically can comprise:
User accesses acquisition module, for gathering user's visit information;
User's access level is divided module, the classification belonging to for dividing described user access information;
Module is searched in coupling application, for according to described user access information and classification thereof, searches the application of coupling in the application data sets of preset corresponding classification;
Coupling application recommending module, for generating application file folder corresponding to each classification, puts into corresponding application file folder by the application of each found classification and recommends.
Preferably, described user's visit information comprises user's local operation visit information, and/or, user's online operational access information.
Preferably, described user's access level division module can comprise:
Feature information extraction submodule, for extracting the Main classification label of described user access information and the corresponding operation frequency;
The corresponding submodule of classification, for being converted to corresponding applicating category by described Main classification label by default correlation rule; Described default correlation rule is the transformation rule of Main classification label and applicating category;
Sequence submodule, for adding up the operation frequency of the corresponding Main classification label of each applicating category, sorts each applicating category by the added up operation frequency from high to low;
Sort out submodule, for extracting front n applicating category of predetermined number, the classification belonging to for active user's visit information; Wherein, described n is greater than 1 positive integer.
Preferably, the application of described application data sets has Main classification label and one-level subclassification label at least, and various types of other application data set is comprised of the application with same Main classification label respectively;
Described coupling application is searched module and be may further include:
Application data set is determined submodule, determines the application data set of corresponding classification for the classification belonging to according to described user access information;
Tag extraction submodule, for extracting the subclassification label of described user access information;
Tag match submodule, for the application data sets in described corresponding classification, adopts the subclassification label of described user access information and the subclassification label of the corresponding level of application to mate, and obtains application and the corresponding weight of coupling;
Submodule is chosen in application, and for choose from high to low the application of front m application as the application data sets coupling of current classification according to described weight, wherein, described m is greater than 1 positive integer.
Preferably, described weight can comprise: the matching value between subclassification label, or, the matching value between subclassification label and the correlation of application.
Preferably, described device, can also comprise:
The sequence of application file folder represents module, for by the operation frequency of the corresponding Main classification label of each applicating category, the order that represents of application file folder is set; And on the desktop of subscriber equipment, represent described application file folder by the described order that represents;
Application sequence represents module, at each application file folder, by the weight of application, represents from high to low described application.
Preferably, described device, can also comprise:
Weight adjusting module, for obtaining the operation information of user for institute's exemplary application, the weight of the corresponding application of corresponding adjustment.
Preferably, described device, can also comprise:
Application file folder order adjusting module, for obtaining the operation information of user for application file folder, what corresponding adjustment application file pressed from both sides represents sequentially.
Preferably, described device, can also comprise:
Feature database is set up module, for setting up user characteristics storehouse according to gathered user access information;
Feature database writing module, for the operation information for institute's exemplary application by user, writes described user characteristics storehouse.
Compared with prior art, the application has the following advantages:
The application sorts out according to user's visit information, form the application file folder of respective classes, then based on described classification, in the application data sets of corresponding classification, search the application of coupling, these application being put into the file of corresponding classification recommends, thereby between application and user, set up contact, fully meet user's individual demand, and effectively improved recommendation efficiency and the coverage rate of application.
Moreover the application is using user interface as entrance, directly on interface or by the link on interface by application file clip icon to user's exemplary application so that user is faster easier, obtain required application, be convenient for users to operate; And, by icon, as the mode of application entrance, can point out user the use to this application, but before the real choice for use of user, the not configuration file of this application correspondence of actual installation, like this, can before use and exceed and take client resource.In addition, the icon in user interface can be concentrated and be disposed or push by network side central server, and this has just prevented that rogue program from arbitrarily adding malice icon in interface, further improved security.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of embodiment of the method 1 of applying automatic recommendation of the application;
Fig. 2 is the process flow diagram of a kind of embodiment of the method 2 of applying automatic recommendation of the application;
Fig. 3 is the structured flowchart of a kind of device embodiment that applies automatic recommendation of the application.
Embodiment
For the above-mentioned purpose, the feature and advantage that make the application can become apparent more, below in conjunction with the drawings and specific embodiments, the application is described in further detail.
The core idea of the embodiment of the present application is, according to user's visit information, sort out, form the application file folder of respective classes, then based on described classification, in the application data sets of corresponding classification, search the application of coupling, these application are put into the file of corresponding classification and recommend, thereby set up contact between application and user.
With reference to Fig. 1, the flow chart of steps that it shows a kind of embodiment of the method for applying automatic recommendation of the application, specifically can comprise the steps:
As a kind of example of the concrete application of the embodiment of the present application, described user's visit information can comprise user's local operation visit information, and/or, user's online operational access information.
Described user access information can be gathered by the client software being arranged on subscriber equipment, and wherein, described subscriber equipment can comprise all kinds of intelligent terminals such as computing machine, notebook computer, mobile phone, PDA, panel computer.Several collection users' local operation visit information is below provided, and/or, the example of user's online operational access information:
Example 1, gathers the online operational access information in user's a period of time by browser, comprises the network address of access and corresponding access times etc.;
As the online operational access information gathering by browser in user 15 days is:
| Access network address | Access times |
| 4939.com | 31 |
| Qiyi.com | 2 |
| Youku.com | 7 |
| 7k7k.com | 4 |
Example 2, by being arranged on the local operation visit information of the fail-safe software collection user on subscriber equipment, as by the online operational access information and the local IP access information that gather in user 15 days being: open MPC and number of times thereof, open certain game and number of times thereof etc.
Certainly, the method for above-mentioned collection and the information of collection are all only as example, and it is all feasible that those skilled in the art adopt any mode to gather required user access information according to actual conditions, the embodiment of the present application to this without being limited.
In a preferred embodiment of the present application, described step 102 specifically can comprise following sub-step:
Sub-step S11, extract Main classification label in described user access information and the corresponding operation frequency;
Sub-step S12, described Main classification label is converted to corresponding applicating category by default correlation rule; Described default correlation rule is the transformation rule of Main classification label and applicating category;
Sub-step S13, the operation frequency of adding up the corresponding Main classification label of each applicating category, sort each applicating category from high to low by the added up operation frequency;
Sub-step S14, extract front n applicating category of predetermined number, the classification belonging to for active user's visit information; Wherein, described n is greater than 1 positive integer.
In practice, can, according to the basic classification (applicating category) that is set in advance application file folder by technician, by analysis user visit information, obtain the application file folder basic classification that user access information meets.For example, the application file folder basic classification setting in advance has 20, and by analysis user visit information, finding that there is some basic classification is unwanted for active user, can divide classification that user access information belongs to and be access habits before being more close to the users 3 or 5.For example, video, game, education etc.
Described user's local operation visit information and online operational access information conventionally can be with label (tag) information, for example, the video of opening at local operation for user, with label informations such as the fiery shadow person of bearing, animation, serial, illusion, risk, bank Ben Qishi; Or as, the network address accessed on the net for user, with label informations such as the kings of video, film, comedy movie, comedy.
The label obtaining from described user access information, determine Main classification label, the as above animation in example or film, mates with the application file folder basic classification setting in advance, and judges which kind of application file folder classification Main classification label should belong in.For example, the transformation rule of Main classification label and applicating category is set as shown in the table:
Apply above-mentioned transformation rule, go up Main classification label " animation " or " film " in example, all can be exchanged into corresponding applicating category for " video ", determine the application file folder that adopts visual classification.
For example: (1) extracts user's net shield data of nearest 15 days: data11, in data11, can comprise Main classification label interest and operation frequency weight: as:
| interest | weight |
| novel-dm | 1 |
| comic-dm | 4 |
| 4399-dm | 1 |
(2) by the Main classification label from net shield extracting data, the basic classification that is converted into the user interest under application file folder taxonomic hierarchies by default transformation rule table (yunCatToZhuoMianCat.conf), is about to Main classification label and is converted to corresponding applicating category.In described default transformation rule table yunCatToZhuoMianCat.conf form, can comprise: the information of Main classification label, applicating category title and applicating category id.As:
| Main classification label | Applicating category title | Applicating category id |
| 4399-dm | Game | 5 |
| comic-dm | Fashion amusement | 8 |
| novel-dm | Novel | 11 |
(3) add up the operation frequency of the corresponding Main classification label of each applicating category, each applicating category is sorted from high to low by the added up operation frequency; Extracting front 9 applicating categories, is the classification that active user's visit information belongs to, the i.e. final classification application file of showing.As:
| Main classification label | Applicating category title | Applicating category id | weight |
| comic-dm | Fashion amusement | 8 | 4 |
| novel-dm | Novel | 11 | 1 |
| 4399-dm | Game | 5 | 1 |
According to this example, determine that the classification that active user's visit information belongs to is fashion amusement, novel, game, i.e. the application file folder of the rear corresponding generation fashion of extended meeting amusement, novel, three kinds of classification of game.
In specific implementation, if being analyzed to divided classification, user access information cannot reach specified quantity, as adopt upper example can only generate three classifications, cannot meet the demand of 9 applicating categories, maximum applicating category or the most newly-installed applicating categories of the actual access times of the network user that can add up according to high in the clouds carries out polishing as the applicating category of recommending, for example, for upper example, can increase again video, education, picture, music, children, these 6 applicating categories of utility.
Certainly, the method of above-mentioned division user access information institute belonging kinds is only as example, it is all feasible that those skilled in the art adopt a kind of mode according to actual conditions, for example, do not extract Main classification label, directly by user access information with label according to presetting rule, be converted to applicating category; Or, directly extracting Main classification label as applicating category etc., the application is not restricted this.
Described application (Application) refers to the various services that user uses on network, as application program, webpage, video, novel, music, game, news, shopping and mailbox etc.Application data set comprises multiple application, derives from each open platform.Application itself can be with some labels, in the embodiment of the present application, can classify to described label, is divided into Main classification label and subclassification label, and wherein, described subclassification label can Further Division be multiple ranks.For example, Main classification label is video, and first order subclassification label is film, and second level subclassification label is comedy movie, horrow movie or action movie etc.That is to say, the application of described application data sets has Main classification label and one-level subclassification label at least, various types of other application data set is comprised of the application with same Main classification label respectively, for example, some applies all Main classification labels with video, these set of applications are combined, form other application data set of video class.
In a kind of preferred embodiment of application, described step 103 may further include following sub-step:
Sub-step S21, the classification belonging to according to described user access information are determined the application data set of corresponding classification;
For example, the classification that active user's visit information belongs to is fashion amusement, novel, game, and definite application data set comprises the application data set of fashion amusement classification, the data set forming with the application of the Main classification label of fashion amusement; The application data set of novel classification, the data set forming with the application of the Main classification label of novel; Other application data set of game class, the data set forming with the application of the Main classification label of playing.
Sub-step S22, extract the subclassification label of described user access information;
As previously mentioned, described user's local operation visit information and online operational access information conventionally can be with label (tag) information, for example, the video of opening at local operation for user, with label informations such as the fiery shadow person of bearing, animation, serial, illusion, risk, bank Ben Qishi; Or as, the network address accessed on the net for user, with label informations such as the kings of video, film, comedy movie, comedy.
In the label information of these user access informations, extract subclassification label, as above in example, can extract one-level subclassification label: serial, animation, film, secondary subclassification label: illusion, risk, comedy movie, three grades of subclassification labels: the king of the fiery shadow person of bearing, bank Ben Qishi, comedy.The subclassification label that those skilled in the art divide multiple ranks according to actual conditions is all feasible, and the application is not restricted this.It should be noted that, application the present embodiment, need to divide at least subclassification label of one-level, to carry out follow-up tag match.
Sub-step S23, in the application data sets of described corresponding classification, adopt the subclassification label of described user access information and the subclassification label of the corresponding level of application to mate, obtain the application of coupling and corresponding weight; According to described weight, choose from high to low the application of front m application as the application data sets coupling of current classification, wherein, described m is greater than 1 positive integer.
Due to the application data sets in certain classification, often there are thousands of application, the application that described sub-step S23 mates in the application data sets of corresponding classification by the subclassification label of tag match algorithm calculating user access information.As the concrete example of the embodiment of the present application, described weight can comprise: the matching value between subclassification label, for example, calculate the matching value of the subclassification label of the subclassification label of user access information and the application of the application data sets of corresponding classification, or, matching value between subclassification label and the correlation of application, described correlation refers to every daily downloads of application and the assessment parameter of user's scoring.
As another example of the concrete application of the present embodiment, described sub-step S23 may further include following sub-step:
Sub-step S23-1, according to the subclassification label of user access information, in the application data sets retrieval character related application of described corresponding classification, described feature related application is identical with the subclassification label segment of user access information or all application of identical subclassification labels;
In the present embodiment, user's visit information all comprises subclassification label, and by with application subclassification tag match, retrieve feature related application.
Sub-step S23-2, calculate the matching value of the subclassification label of described feature related application and the subclassification label of active user's visit information;
In concrete realization, can give certain matching value by the subclassification label of user access information, and these subclassification labels are divided into different groups, the matching value of subclassification label is the same on the same group.
For example, the subclassification label of active user's visit information is as shown in the table:
| TV play | Comedy | Love | The story of a play or opera | Bao Jianfeng | Jin Sha | Li Jichang |
Next matching value of subclassification label distribution to each group, as above example, a little by this
Tag along sort be divided into 4 groups and give matching value of each subclassification label after obtain:
TV play 60
Comedy 6, love 6, the story of a play or opera 6
Protect sword cutting edge of a knife or a sword 2, Jin Sha 2
Li Ji prosperous 1
Next, the subclassification label of the subclassification label of the feature related application of finding and active user's visit information is contrasted, by subclassification tag hit situation, calculate the matching value of each feature related application, wherein, hit rate (tag group number/total tag group of hitting) and hit matching value ratio (the weights sum/weights sum hitting) weight separately and can adjust according to business rule, summation is 100.Wherein tag refers to subclassification label.Such as video is 50:50, the matching value computing formula of the feature related application of video class is:
Weight=(tag group number/total tag group of hitting) * 50+ (the matching value sum/matching value sum hitting) * 50;
It should be noted that in tag group, have one to hit and can be regarded as this group and hit, matching value can round up.
As above example, the tag that searches certain feature related application is:
| TV play | Other | Love | The story of a play or opera | Liu Dehua | Jin Sha | Li An | Other | 2011 | Continent |
The subclassification label contrast of itself and active user's visit information can be found to the tag hitting has TV play, love, the story of a play or opera, Jin Sha, there is (the classification of 3 groups, type, acts the leading role) hit, the matching value of this application is exactly weight=3/4*50+74/83*50=68 (67.17 round up 68).
Sub-step S23-3, feature related application is sorted according to matching value is descending;
Calculated after the matching value of each feature related application, can sort from big to small by matching value.For each application of taking out is unlikely to focus on, certain is several, application after allowing those relatively lean on also can recommendedly be arrived, can be respectively from several matching values interval of reserving in advance, choose some matching values and drop on the recommendation that should be used in this interval, for example from mate interval 100-88, select 3, from 87-73, select 2, from 72-16, select 1.Wherein, in same interval, what matching value was high is preferentially selected.If the not enough quantity of application, chooses and supplies from the low interval of closing in certain is interval.
Sub-step S23-4, the described sequence of foundation, the default number of extraction, matching value meets respectively the feature related application of multiple pre-set interval, as the application of coupling.
In specific implementation, when the matching value of multiple feature related application equates, described sub-step S23 can also comprise:
Sub-step S23-5, calculate the matching value of the subclassification label of described feature related application and user access information, and the correlation of the subclassification label of each feature related application of equating of matching value and active user's visit information.
In the case of the matching value of multiple feature related application is the same, need to calculate the correlation of the feature related application of identical match value and the subclassification label of active user's visit information.
For example, suppose the application A relevant to the subclassification label of active user's visit information, application B, the matching value of application C is identical, and computation process can be as follows:
The download of download+C of download+B of total download=A;
The scoring of scoring+C of scoring+B of overall score=A;
The correlativity of application A is: scoring/overall score * 40 of download/total download * 60+A of A.assoc=A;
The correlativity of application B is: scoring/overall score * 40 of download/total download * 60+B of B.assoc=B;
The correlativity of application C is: scoring/overall score * 40 of download/total download * 60+C of C.assoc=C.
Sub-step S22-5, feature related application is sorted from big to small according to matching value, wherein, the feature related application that matching value is equal sorts according to correlation is descending;
Sub-step S22-6, the described sequence of foundation, the default number of extraction, matching value meets respectively the feature related application of multiple pre-set interval, as exemplary application.
For the situation of feature related application that has identical match value, calculated after matching value and correlativity, first according to matching value size, all feature related application are sorted, for the application of identical match value, according to correlation size, sort.Then can be respectively from several matching values interval of reserving in advance, choose some matching values and drop on the recommendation that should be used in this interval, in same interval, what matching value was high is preferentially selected, and it is high that identical weights are preferentially chosen the degree of correlation.
For example, searched 10 feature related application, corresponding matching value and correlation are as follows:
| ? | A1 | A2 | B | C | D1 | D2 | E | F | G | H |
| Matching value | 93 | 93 | 89 | 83 | 57 | 57 | 50 | 49 | 32 | 23 |
| Correlation | 239 | 234 | ? | ? | 2334 | 455 | ? | ? | ? | ? |
Pre-set interval and corresponding default number are: 3 [100-88], 2 [87-73], 1 [72-16], can be from [100-88] from choosing A1, A2 and B according to the order in table, chooses C and D1(because this interval only has an application from [87-73], from [72-16] interval, choose the highest supplying, D1 is consistent with D2 matching value, but D1 correlation is greater than D2, so choose D1), from 72-16, choose E, totally 6 application are as exemplary application.
In practice, if according to described user access information and classification thereof, the coupling application finding in the application data sets of corresponding classification does not meet predetermined number, can extract the application data sets access times of respective classes maximum and/or the application of up-to-date warehouse-in as exemplary application, for example, in the application data sets of current classification, extract 20 application the most popular as exemplary application.
Certainly, the above-mentioned method of mating application with user access information of searching is only as example, it is also feasible that those skilled in the art adopt other computing method, for example, by calculating the similarity etc. of the subclassification label that subclassification label and the respective classes application data sets of user access information apply, the application to this without being limited.
It should be noted that, in the embodiment of the present application, described Main classification label and subclassification label can mark voluntarily by person skilled or user, also can adopt computing machine clustering technique, by the semanteme to webpage word or key word analysis, obtain, can also for example, from network (official), gather the descriptor of corresponding software or application.
Application the embodiment of the present application, generates application file folder by category, under respective classes, in the application file folder of corresponding classification, to user, recommend with the application of user access information coupling, thus the resource that is conducive to save subscriber equipment.
With reference to Fig. 2, the flow chart of steps that it shows a kind of embodiment of the method for applying automatic recommendation of the application, specifically can comprise the steps:
In specific implementation, for the application file folder of recommending user, can in the different split screens of desktop, represent, preferably, and can also be according to the height of user's split screen and width, determine the number of the application file folder of recommending in each split screen.Application the embodiment of the present application, the order that represents of described application file folder is to arrange from high to low according to the operation frequency of the corresponding Main classification label of each applicating category, therefore application file folder is to represent from high to low to user according to the matching degree of user interest; And the application in application file folder is also sorted by weight, is also to represent to user from high to low according to the matching degree of user interest, thereby the more convenient user's of energy operation makes user obtain better experience.
In a preferred embodiment of the present application, can also comprise the steps:
Obtain the operation information of user for institute's exemplary application, the weight of the corresponding application of corresponding adjustment.
When after user's exemplary application, user may open this application, check details, also may further the application of recommendation be added in the use of oneself, in this case, can also be according to user the visit information for exemplary application, improve the weight of the operated application of user, thereby change the sequence of application in application file folder.
In specific implementation, can also by obtaining the operation information of user for application file folder, for example, according to user, click the operation frequency of application file folder, according to each application file, press from both sides the order that represents of the corresponding adjustment application file folder of the operated frequency.
In specific implementation, can in the user interface of terminal desktop, unify to show and press from both sides corresponding icon with multiple application files, each icon represents application file folder, by icon as with the mode of applying entrance.This patterned exhibition method is very directly perceived for user, and easy to use and management.For example, the icon of showing application file folder in user interface comprises " video ", " novel ", " education " and " game ", user, click after the icon of " video " application file folder, enter the subwindow of this application file folder, in subwindow, show and have multiple application icons such as TV play, film, animation, variety.By icon, as the mode of application entrance, can point out user the use to this application, but before the real choice for use of user, the not configuration file of this application correspondence of actual installation, like this, not only can be user-friendly, and before use and exceed and take client resource.
Icon in user interface can be concentrated and be disposed or push by network side central server, and this has just prevented that rogue program from arbitrarily adding malice icon in interface, further improved security.There is the configuration file of central server centralized management can comprise the corresponding reference address of applying, present specification, and the unfolding mode of described application, or their any combination.
For example, for web application, the address of web access is sent to end side by central server by the mode of configuration file, and this has just prevented rogue program the distorting reference address of end side.
And, network side central server can be by the profile information upgrading with the mutual acquisition of third party content server, for example, if the reference address of certain application changes, server can be by the address information after upgrading with the mutual acquisition of content server, and send over by configuration file, stopped to change because of reference address the opportunity staying to rogue program.
In addition, subscriber equipment is obtaining after the configuration file of the application corresponding with described icon, can also upgrade the display state of this icon, further to point out user.For example, do not obtain before configuration file, icon can be black and white, or dark-coloured, and after acquisition, can become colour or light tone.
Also it should be noted that, the application file clip icon of showing in end side user interface, can be one or more, can determine according to different displaying rules.For example, when using an icon, this icon can be used as the unified entrance of the application of multiple subordinates or subordinate's icon, when wherein any one application obtains lastest imformation, at this entrance icon place, all can obtain prompting.
In a preferred embodiment of the present application, can also comprise the steps:
According to gathered user access information, set up user characteristics storehouse;
Operation information by user for institute's exemplary application, writes described user characteristics storehouse.
By setting up user characteristics storehouse, user access information can be unified in to server end or high in the clouds is processed, in such an embodiment, can in user characteristics storehouse, work as inferior operational access information by recording user, and determine the application file folder that should recommend to user and apply accordingly according to the previous operational access information in user characteristics storehouse.It should be noted that, in the present embodiment, described user access information also comprises the operation information of user for institute's exemplary application.
It should be noted that, for embodiment of the method, for simple description, therefore it is all expressed as to a series of combination of actions, but those skilled in the art should know, the application is not subject to the restriction of described sequence of movement, because according to the application, some step can adopt other orders or carry out simultaneously.Secondly, those skilled in the art also should know, the embodiment described in instructions all belongs to preferred embodiment, and related action and module might not be that the application is necessary.
With reference to Fig. 3, show the structured flowchart of a kind of device embodiment that applies automatic recommendation of the application, specifically can comprise as lower module:
User accesses acquisition module 301, for gathering user's visit information;
User's access level is divided module 302, the classification belonging to for dividing described user access information;
Module 303 is searched in coupling application, for according to described user access information and classification thereof, searches the application of coupling in the application data sets of preset corresponding classification;
Coupling application recommending module 304, for generating application file folder corresponding to each classification, puts into corresponding application file folder by the application of each found classification and recommends.
In specific implementation, described user's visit information can comprise user's local operation visit information, and/or, user's online operational access information.
In a preferred embodiment of the present application, described user's access level is divided module 302 can comprise following submodule:
Feature information extraction submodule, for extracting the Main classification label of described user access information and the corresponding operation frequency;
The corresponding submodule of classification, for being converted to corresponding applicating category by described Main classification label by default correlation rule; Described default correlation rule is the transformation rule of Main classification label and applicating category;
Sequence submodule, for adding up the operation frequency of the corresponding Main classification label of each applicating category, sorts each applicating category by the added up operation frequency from high to low;
Sort out submodule, for extracting front n applicating category of predetermined number, the classification belonging to for active user's visit information; Wherein, described n is greater than 1 positive integer.
As a kind of example of the concrete application of the embodiment of the present application, the application of described application data sets has Main classification label and one-level subclassification label at least, and various types of other application data set is comprised of the application with same Main classification label respectively; In this case, described coupling application is searched module 303 and be may further include following sub-step:
Application data set is determined submodule, determines the application data set of corresponding classification for the classification belonging to according to described user access information;
Tag extraction submodule, for extracting the subclassification label of described user access information;
Tag match submodule, for the application data sets in described corresponding classification, adopts the subclassification label of described user access information and the subclassification label of the corresponding level of application to mate, and obtains application and the corresponding weight of coupling;
Submodule is chosen in application, and for choose from high to low the application of front m application as the application data sets coupling of current classification according to described weight, wherein, described m is greater than 1 positive integer.
Preferably, described weight can comprise: the matching value between subclassification label, or, the matching value between subclassification label and the correlation of application.
In a preferred embodiment of the present application, described device embodiment can also comprise as lower module:
The sequence of application file folder represents module, for by the operation frequency of the corresponding Main classification label of each applicating category, the order that represents of application file folder is set; And on the desktop of subscriber equipment, represent described application file folder by the described order that represents;
Application sequence represents module, at each application file folder, by the weight of application, represents from high to low described application.
More preferably, described device embodiment can also comprise as lower module:
Weight adjusting module, for obtaining the operation information of user for institute's exemplary application, the weight of the corresponding application of corresponding adjustment.
More preferably, described device embodiment can also comprise as lower module:
Application file folder order adjusting module, for obtaining the operation information of user for application file folder, what corresponding adjustment application file pressed from both sides represents sequentially.
More preferably, described device embodiment can also comprise as lower module:
Feature database is set up module, for setting up user characteristics storehouse according to gathered user access information;
Feature database writing module, for the operation information for institute's exemplary application by user, writes described user characteristics storehouse.
The embodiment of the present application not only can be applied in the applied environment of single device, can also be applied to the applied environment of client-server, or is further applied in the applied environment based on cloud.
Because described device embodiment is substantially corresponding to preceding method embodiment, therefore not detailed part in the description of the present embodiment can, referring to the related description in previous embodiment, just not repeat at this.In the application's device embodiment and system embodiment, related module, submodule and unit can be software, can be hardware, can be also the combination of software and hardware.Each embodiment in this instructions stresses is all and the difference of other embodiment, between each embodiment identical similar part mutually referring to.
The application can be used in numerous general or special purpose computingasystem environment or configuration.For example: personal computer, server computer, handheld device or portable set, plate equipment, multicomputer system, the system based on microprocessor, set top box, programmable consumer-elcetronics devices, network PC, small-size computer, mainframe computer, comprise distributed computing environment of above any system or equipment etc.
The application can describe in the general context of the computer executable instructions of being carried out by computing machine, for example program module.Usually, program module comprises and carries out particular task or realize routine, program, object, assembly, data structure of particular abstract data type etc.Also can in distributed computing environment, put into practice the application, in these distributed computing environment, by the teleprocessing equipment being connected by communication network, be executed the task.In distributed computing environment, program module can be arranged in the local and remote computer-readable storage medium including memory device.
A kind of method and a kind of device of applying automatic recommendation of applying automatic recommendation above the application being provided is described in detail, applied principle and the embodiment of specific case to the application herein and set forth, the explanation of above embodiment is just for helping to understand the application's method and core concept thereof; , for one of ordinary skill in the art, according to the application's thought, all will change in specific embodiments and applications, in sum, this description should not be construed as the restriction to the application meanwhile.
Claims (10)
1. the method that application is recommended automatically, is characterized in that, comprising:
Gather user's visit information;
Divide the classification that described user access information belongs to;
According to described user access information and classification thereof, in the application data sets of preset corresponding classification, search the application of coupling;
Generate application file folder corresponding to each classification, the application of each found classification is put into corresponding application file folder and recommend.
2. the method for claim 1, is characterized in that, described user's visit information comprises user's local operation visit information, and/or, user's online operational access information.
3. the method for claim 1, is characterized in that, the step of the classification that described division user access information belongs to comprises:
Extract Main classification label in described user access information and the corresponding operation frequency;
Described Main classification label is converted to corresponding applicating category by default correlation rule; Described default correlation rule is the transformation rule of Main classification label and applicating category;
The operation frequency of adding up the corresponding Main classification label of each applicating category, sorts each applicating category from high to low by the added up operation frequency;
Extract front n applicating category of predetermined number, the classification belonging to for active user's visit information; Wherein, described n is greater than 1 positive integer.
4. method as claimed in claim 3, is characterized in that, the application of described application data sets has Main classification label and one-level subclassification label at least, and various types of other application data set is comprised of the application with same Main classification label respectively;
Described according to user access information and classification thereof, the step of searching the application of coupling in the application data sets of preset corresponding classification further comprises:
The classification belonging to according to described user access information is determined the application data set of corresponding classification;
Extract the subclassification label of described user access information;
In the application data sets of described corresponding classification, adopt the subclassification label of described user access information and the subclassification label of the corresponding level of application to mate, obtain application and the corresponding weight of coupling;
According to described weight, choose from high to low the application of front m application as the application data sets coupling of current classification, wherein, described m is greater than 1 positive integer.
5. method as claimed in claim 4, is characterized in that, described weight comprises: the matching value between subclassification label, or, the matching value between subclassification label and the correlation of application.
6. method as claimed in claim 3, is characterized in that, also comprises:
By the operation frequency of the corresponding Main classification label of each applicating category, the order that represents of application file folder is set;
By the described order that represents, on the desktop of subscriber equipment, represent described application file folder;
In each application file folder, by the weight of application, represent from high to low described application.
7. the method as described in claim 4 or 5 or 6, is characterized in that, also comprises:
Obtain the operation information of user for institute's exemplary application, the weight of the corresponding application of corresponding adjustment.
8. the method as described in claim 4 or 5 or 6, is characterized in that, also comprises:
Obtain the operation information of user for application file folder, what corresponding adjustment application file pressed from both sides represents sequentially.
9. the method for claim 1, is characterized in that, also comprises:
According to gathered user access information, set up user characteristics storehouse;
Operation information by user for institute's exemplary application, writes described user characteristics storehouse.
10. the device that application is recommended automatically, is characterized in that, comprising:
User accesses acquisition module, for gathering user's visit information;
User's access level is divided module, the classification belonging to for dividing described user access information;
Module is searched in coupling application, for according to described user access information and classification thereof, searches the application of coupling in the application data sets of preset corresponding classification;
Coupling application recommending module, for generating application file folder corresponding to each classification, puts into corresponding application file folder by the application of each found classification and recommends.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310462445.7A CN103744849B (en) | 2011-12-27 | 2011-12-27 | Method and device for automatic recommendation application |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104440740A CN102591942B (en) | 2011-12-27 | 2011-12-27 | Method and device for automatic application recommendation |
| CN201310462445.7A CN103744849B (en) | 2011-12-27 | 2011-12-27 | Method and device for automatic recommendation application |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011104440740A Division CN102591942B (en) | 2011-12-27 | 2011-12-27 | Method and device for automatic application recommendation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103744849A true CN103744849A (en) | 2014-04-23 |
| CN103744849B CN103744849B (en) | 2017-04-12 |
Family
ID=50501867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310462445.7A Expired - Fee Related CN103744849B (en) | 2011-12-27 | 2011-12-27 | Method and device for automatic recommendation application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103744849B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653655A (en) * | 2015-12-25 | 2016-06-08 | Tcl集团股份有限公司 | Application pushing method and device |
| CN105824923A (en) * | 2016-03-17 | 2016-08-03 | 海信集团有限公司 | Movie and video resource recommendation method and device |
| CN105916054A (en) * | 2015-10-23 | 2016-08-31 | 乐视致新电子科技（天津）有限公司 | Desktop display control method and device |
| CN106326369A (en) * | 2016-08-12 | 2017-01-11 | 广州优视网络科技有限公司 | Application special topic recommendation method, application special topic recommendation device and server |
| CN106792175A (en) * | 2016-12-22 | 2017-05-31 | 深圳Tcl数字技术有限公司 | Program data processing method and system |
| CN108428189A (en) * | 2018-02-27 | 2018-08-21 | 上海掌门科技有限公司 | A kind of social resource processing method, equipment and readable medium |
| CN109145280A (en) * | 2017-06-15 | 2019-01-04 | 北京京东尚科信息技术有限公司 | The method and apparatus of information push |
| CN109213413A (en) * | 2017-07-07 | 2019-01-15 | 阿里巴巴集团控股有限公司 | A kind of recommended method, device, equipment and storage medium |
| CN109325003A (en) * | 2018-09-27 | 2019-02-12 | 维沃移动通信有限公司 | A kind of application program classifying method and system based on terminal device |
| CN109831532A (en) * | 2019-03-18 | 2019-05-31 | 北京字节跳动网络技术有限公司 | Data sharing method, device, equipment and medium |
| CN110069320A (en) * | 2019-04-29 | 2019-07-30 | 努比亚技术有限公司 | A kind of category correction method, terminal, system and the storage medium of application program |
| CN110555135A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555157A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555131A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110766493A (en) * | 2018-07-26 | 2020-02-07 | 阿里巴巴集团控股有限公司 | Business object providing method, server, electronic device and storage medium |
| CN111858688A (en) * | 2020-07-20 | 2020-10-30 | 海尔优家智能科技（北京）有限公司 | Textile material, color chart recommendation method and device and storage medium |
| WO2020238744A1 (en) * | 2019-05-24 | 2020-12-03 | 华为技术有限公司 | Processing method, device and apparatus for split-screen display, and storage medium |
| CN112684953A (en) * | 2020-12-24 | 2021-04-20 | 方正株式(武汉)科技开发有限公司 | Mobile terminal application icon arrangement method |
| WO2021217470A1 (en) * | 2020-04-29 | 2021-11-04 | Citrix Systems, Inc. | Computer resource allocation based on categorizing computing processes |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551825A (en) * | 2009-05-15 | 2009-10-07 | 中国科学技术大学 | Personalized film recommendation system and method based on attribute description |
| CN101770520A (en) * | 2010-03-05 | 2010-07-07 | 南京邮电大学 | User interest modeling method based on user browsing behavior |
| CN102141986A (en) * | 2010-01-28 | 2011-08-03 | 北京邮电大学 | Individualized information providing method and system based on user behaviors |
-
2011
- 2011-12-27 CN CN201310462445.7A patent/CN103744849B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551825A (en) * | 2009-05-15 | 2009-10-07 | 中国科学技术大学 | Personalized film recommendation system and method based on attribute description |
| CN102141986A (en) * | 2010-01-28 | 2011-08-03 | 北京邮电大学 | Individualized information providing method and system based on user behaviors |
| CN101770520A (en) * | 2010-03-05 | 2010-07-07 | 南京邮电大学 | User interest modeling method based on user browsing behavior |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105916054A (en) * | 2015-10-23 | 2016-08-31 | 乐视致新电子科技（天津）有限公司 | Desktop display control method and device |
| WO2017067194A1 (en) * | 2015-10-23 | 2017-04-27 | 乐视控股（北京）有限公司 | Desktop display control method and device |
| CN105653655A (en) * | 2015-12-25 | 2016-06-08 | Tcl集团股份有限公司 | Application pushing method and device |
| CN105824923A (en) * | 2016-03-17 | 2016-08-03 | 海信集团有限公司 | Movie and video resource recommendation method and device |
| CN106326369A (en) * | 2016-08-12 | 2017-01-11 | 广州优视网络科技有限公司 | Application special topic recommendation method, application special topic recommendation device and server |
| CN106326369B (en) * | 2016-08-12 | 2019-12-31 | 广州优视网络科技有限公司 | Application topic recommendation method and device and server |
| CN106792175A (en) * | 2016-12-22 | 2017-05-31 | 深圳Tcl数字技术有限公司 | Program data processing method and system |
| CN109145280A (en) * | 2017-06-15 | 2019-01-04 | 北京京东尚科信息技术有限公司 | The method and apparatus of information push |
| CN109145280B (en) * | 2017-06-15 | 2023-05-12 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
| CN109213413A (en) * | 2017-07-07 | 2019-01-15 | 阿里巴巴集团控股有限公司 | A kind of recommended method, device, equipment and storage medium |
| CN108428189A (en) * | 2018-02-27 | 2018-08-21 | 上海掌门科技有限公司 | A kind of social resource processing method, equipment and readable medium |
| CN110555131A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555157B (en) * | 2018-03-27 | 2023-04-07 | 阿里巴巴（中国）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555157A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555135A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555135B (en) * | 2018-03-27 | 2023-04-07 | 阿里巴巴（中国）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555131B (en) * | 2018-03-27 | 2023-04-07 | 阿里巴巴（中国）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110766493B (en) * | 2018-07-26 | 2023-04-28 | 阿里巴巴集团控股有限公司 | Service object providing method, server, electronic device, and storage medium |
| CN110766493A (en) * | 2018-07-26 | 2020-02-07 | 阿里巴巴集团控股有限公司 | Business object providing method, server, electronic device and storage medium |
| CN109325003A (en) * | 2018-09-27 | 2019-02-12 | 维沃移动通信有限公司 | A kind of application program classifying method and system based on terminal device |
| CN109831532A (en) * | 2019-03-18 | 2019-05-31 | 北京字节跳动网络技术有限公司 | Data sharing method, device, equipment and medium |
| CN110069320A (en) * | 2019-04-29 | 2019-07-30 | 努比亚技术有限公司 | A kind of category correction method, terminal, system and the storage medium of application program |
| CN110069320B (en) * | 2019-04-29 | 2023-06-30 | 努比亚技术有限公司 | Classification correction method, terminal, system and storage medium for application program |
| WO2020238744A1 (en) * | 2019-05-24 | 2020-12-03 | 华为技术有限公司 | Processing method, device and apparatus for split-screen display, and storage medium |
| US11822784B2 (en) | 2019-05-24 | 2023-11-21 | Huawei Technologies Co., Ltd. | Split-screen display processing method and apparatus, device, and storage medium |
| WO2021217470A1 (en) * | 2020-04-29 | 2021-11-04 | Citrix Systems, Inc. | Computer resource allocation based on categorizing computing processes |
| CN111858688A (en) * | 2020-07-20 | 2020-10-30 | 海尔优家智能科技（北京）有限公司 | Textile material, color chart recommendation method and device and storage medium |
| CN111858688B (en) * | 2020-07-20 | 2024-05-24 | 海尔优家智能科技（北京）有限公司 | Textile material, color card recommendation method and device and storage medium |
| CN112684953A (en) * | 2020-12-24 | 2021-04-20 | 方正株式(武汉)科技开发有限公司 | Mobile terminal application icon arrangement method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103744849B (en) | 2017-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102591942B (en) | Method and device for automatic application recommendation | |
| CN103744849A (en) | Method and device for automatic recommendation application | |
| CN103488788B (en) | It is a kind of to apply the method and device recommended automatically | |
| CN102567511B (en) | Method and device for automatically recommending application | |
| CN103455559B (en) | A kind of method and device applying recommendation automatically | |
| Lee et al. | MONERS: A news recommender for the mobile web | |
| CN102073699B (en) | For improving the method for Search Results, device and equipment based on user behavior | |
| CN110059249B (en) | Personalized recommendation method, terminal device and system | |
| CN102360364A (en) | Automatic application recommendation method and device | |
| US8650198B2 (en) | Systems and methods for facilitating the gathering of open source intelligence | |
| CN102708174B (en) | Method and device for displaying rich media information in browser | |
| CN105898209A (en) | Video platform monitoring and analyzing system | |
| CN105095187A (en) | Search intention identification method and device | |
| CN106326391A (en) | Method and device for recommending multimedia resources | |
| CN106326413A (en) | Personalized video recommending system and method | |
| US20100100443A1 (en) | User classification apparatus, advertisement distribution apparatus, user classification method, advertisement distribution method, and program used thereby | |
| CN102708130A (en) | Scalable engine that computes user micro-segments for offer matching | |
| CN102037464A (en) | Search results with most clicked next objects | |
| CN104899315A (en) | Method and device for pushing user information | |
| CN104156356B (en) | Personalized Navigation page generation method and device | |
| CN104503988B (en) | searching method and device | |
| CN105916032A (en) | Video recommendation method and video recommendation terminal equipment | |
| CN104090923A (en) | Method and device for displaying rich media information in browser | |
| CN109597899A (en) | The optimization method of media personalized recommendation system | |
| CN109559152A (en) | A kind of network marketing method, system and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170412 Termination date: 20211227 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |