CN108595599A - Using label generating method, device, storage medium and computer equipment - Google Patents
Using label generating method, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN108595599A CN108595599A CN201810356223.XA CN201810356223A CN108595599A CN 108595599 A CN108595599 A CN 108595599A CN 201810356223 A CN201810356223 A CN 201810356223A CN 108595599 A CN108595599 A CN 108595599A
- Authority
- CN
- China
- Prior art keywords
- label
- frequency
- application
- user
- tag
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Present invention offer is a kind of using label generating method, including：Obtain the access data of user and preset tag library；According to the access data of user, generates user and apply relation table；Obtain the original tag that user accesses application；Relation table and original tag are applied according to user, calculates all frequency of occurrences for accessing label in the corresponding tag library of application of user；Relation table and frequency of occurrence are applied according to user, calculates the reverse document-frequency that intended application corresponds to label in the frequency and tag library of label in the tag library；According to the frequency and the reverse document-frequency, the weighted value that intended application corresponds to label in the tag library is calculated；According to the weighted value, generate intended application applies label.This method can be automatically, efficiently that intended application generates and accurately applies label, avoid the problem that previous manually generated application label need to take considerable time and manpower, improve efficiency of operation and cut operating costs.
Description
Technical field
The present invention relates to field of computer technology, specifically, the present invention relates to a kind of application label generating method, dresses
It sets, computer readable storage medium and computer equipment.
Background technology
As the fast development of Internet technology and the quick of intelligent terminal are popularized, the application for meeting user's application demand is soft
Part is continuously developed, and quantity is very huge.Therefore in scene is distributed in application, a, side especially prominent using the importance of label
Face can allow the tonality of user's intuitive aware application in numerous applications, music of e.g. missing old times or old friends class application, or be tower
On the other hand the applications such as anti-game apply label that can show that user can be jumped to by label using details page
Other corresponding similar applications under the label, using label to the application class of the application platforms such as such as application shop or application market
Displaying plays important function using operations such as recommendations.
In the prior art, application platform determines that its application is marked by obtaining the description content information of application software
Label, however, it is limited in that, for the description content information of each application software there is no unified standard, message subject is irregular not
Together, it is realized by tool larger using the determination difficulty of label and relatively low using the accuracy of label.And pass through application platform
Operation personnel determined in a manner of manual screening and then need to take considerable time using label and manpower, generate and imitate using label
Rate is low, and the operation cost of application platform is high.
Invention content
It is that can at least solve above-mentioned one of technological deficiency, the present invention provides the application labels of following technical scheme to generate
Method, apparatus and computer equipment.
The embodiment of the present invention is a kind of using label generating method according on one side, providing, including：
Obtain the access data of user and preset tag library；
According to the access data of user, generates user and apply relation table；Wherein, the user is used to record using relation table
User accesses the incidence relation of application with it；
Obtain the original tag that user accesses application；Relation table and the original tag are applied according to the user, is calculated
All frequency of occurrences for accessing label in the corresponding tag library of application of user；
Relation table and the frequency of occurrence are applied according to the user, intended application is calculated and corresponds to label in the tag library
Frequency；Relation table and the frequency of occurrence are applied according to the user, calculates the reverse file frequency of label in the tag library
Rate；According to the frequency and the reverse document-frequency, the weighted value that intended application corresponds to label in the tag library is calculated；Its
In, the intended application is to access to be intended to generate the application using label in application；
According to the weighted value, generate intended application applies label.
Preferably, described that relation table and the frequency of occurrence are applied according to the user, it calculates described in intended application correspondence
The frequency of label in tag library, including：
Relation table and the frequency of occurrence are applied according to the user, the intended application is calculated and corresponds in the tag library
The frequency of occurrence of label；
The frequency of occurrence for the intended application being corresponded to label in the tag library is normalized, and calculates the mesh
The frequency of label in the corresponding tag library of mark application；
Wherein, the frequency for indicate the intended application correspond in the tag library frequency of occurrence of label with it is described
The ratio of the frequency of occurrence of all labels in tag library.
Preferably, described that relation table and the frequency of occurrence are applied according to the user, it calculates the intended application and corresponds to
The frequency of label, is realized by following formula in the tag library：
Wherein, describedFor the frequency；It is describedIt is answered for all access with intended application i association users
With label Tag in the correspondence tag libraryjThe sum of frequency of occurrence；The Tag is all labels in the tag library.
Preferably, described that relation table and the frequency of occurrence are applied according to the user, calculate label in the tag library
Reverse document-frequency, including：
Relation table and the frequency of occurrence are applied according to the user, total number of users is obtained and the frequency of occurrence is more than 0
Number of users；
According to the total number of users and the number of users, the reverse document-frequency of label in the tag library is calculated；
Wherein, the frequency of occurrence includes the label for characterizing during all access of user are applied more than 0 number of users
The quantity of the user of label in library；The reverse document-frequency is general in all users for measuring label in the tag library
All over property.
Further, described according to the total number of users and the number of users, calculate the reverse of label in the tag library
Document-frequency, including：
According to the total number of users and the number of users, the ratio of the total number of users and the number of users is calculated；
Exponentiation processing is carried out to the ratio, calculates the reverse document-frequency of label in the tag library.
Preferably, described according to the total number of users and the number of users, calculate the reverse text of label in the tag library
Part frequency, is realized by following formula：
Wherein,It is describedFor the reverse document-frequency；The U
For the total number of users；It is describedFor all frequency of occurrences for accessing label in the corresponding tag library of application of user.
Further, described according to the frequency and the reverse document-frequency, it calculates intended application and corresponds to the label
The weighted value of label, is realized by following formula in library：
Wherein, describedLabel Tag in the tag library is corresponded to for intended application ijThe frequency；It is describedFor label Tag in the tag libraryjThe reverse document-frequency.
Preferably, the original tag for obtaining user and accessing application, including：
Judge that user accesses whether application includes at least one original tag；
If so, extracting an original tag from least one original tag that user accesses application；
It is described that relation table and the original tag are applied according to the user, it calculates all access of user and applies described in correspondence
The frequency of occurrence of label in tag library, including：
According to the customer relationship application table and the original tag, an original described in all access applications of user is calculated
Beginning label is the quantity of the access application of label in the tag library；
Using the quantity as all frequency of occurrences for accessing label in the corresponding tag library of application of user.
Preferably, described that the label of applying of intended application is generated according to the weighted value, including：
The weighted value for intended application being corresponded to all labels in the tag library is ranked up by sequence from big to small, is obtained
Take the corresponding label of the weights for the preset quantity for coming foremost；
Label is applied using the label of the preset quantity as intended application.
The embodiment of the present invention additionally provides a kind of application recommendation method according to one side, including：
According to above application label generating method, generate intended application applies label；
Label is applied according to described, obtains application associated with the intended application；
Recommend the application to user.
The embodiment of the present invention additionally provides a kind of application label generating means according on the other hand, including：
Data obtaining module, the access data for obtaining user and preset tag library；
User applies relation table generation module, for the access data according to user, generates user and applies relation table；Its
In, the user accesses the incidence relation of application for recording user using relation table with it；
First computing module accesses the original tag of application for obtaining user；According to the user using relation table and
The original tag calculates all frequency of occurrences for accessing label in the corresponding tag library of application of user；
Second computing module calculates intended application pair for applying relation table and the frequency of occurrence according to the user
Answer the frequency of label in the tag library；Relation table and the frequency of occurrence are applied according to the user, calculates the tag library
The reverse document-frequency of middle label；According to the frequency and the reverse document-frequency, calculates intended application and correspond to the label
The weighted value of label in library；Wherein, the intended application is to access to be intended to generate the application using label in application；
Tag generation module, for according to the weighted value, generate intended application to apply label.
The embodiment of the present invention is a kind of using recommendation apparatus according on the other hand, additionally providing, including：
Using tag generation module, for according to above application label generating method, generate intended application to apply label；
Associated application acquisition module obtains application associated with the intended application for applying label according to described；
Using recommending module, for recommending the application to user.
The embodiment of the present invention additionally provides a kind of computer readable storage medium, the calculating according to another aspect
Computer program is stored on machine readable storage medium storing program for executing, the computer program realizes above-mentioned application mark when being executed by processor
Sign generation method.
The embodiment of the present invention additionally provides a kind of computer readable storage medium, the calculating according to another aspect
Computer program is stored on machine readable storage medium storing program for executing, the computer program realizes that above-mentioned application pushes away when being executed by processor
Recommend method.
The embodiment of the present invention additionally provides a kind of computer equipment according to another aspect, and the terminal includes one
Or multiple processors；Memory；One or more computer programs, wherein one or more of computer programs are stored in
It in the memory and is configured as being executed by one or more of processors, one or more of computer program configurations
For：Execute above-mentioned application label generating method.
The embodiment of the present invention additionally provides a kind of computer equipment according to another aspect, and the terminal includes one
Or multiple processors；Memory；One or more computer programs, wherein one or more of computer programs are stored in
It in the memory and is configured as being executed by one or more of processors, one or more of computer program configurations
For：Execute above-mentioned application recommendation method.
Compared with prior art, the present invention having the advantages that：
Application label generating method, device, storage medium and computer equipment provided by the invention, do not have in intended application
In the case of any description content, the original mark that user accesses the history of application data and user's access application may be based on
Label are automatically, efficiently that label is accurately applied in intended application generation, and effectively preventing manually generated application label in the past needs to consume
It the problem of taking plenty of time and manpower significantly improves platform operation efficiency and cuts operating costs.
In addition, application label generating method, device, storage medium and computer equipment provided by the invention, also by taking
The mode of power calculates the reverse document-frequency of label in the tag library, can effectively enhance to popular label in current application scene
Inhibition, and then improve generated intended application the accuracy using label.
Method, apparatus, storage medium and computer equipment are recommended in application provided by the invention, and what is provided through the invention answers
The application label of application is generated with label generating method, and then may be implemented in practical application scene according to application label come high
The associated application with same label is recommended in effect ground to user, improves the efficiency of operation of platform.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obviously, or practice through the invention is recognized.
Description of the drawings
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, wherein：
Fig. 1 is the method flow diagram provided in an embodiment of the present invention using label generating method；
Fig. 2 is the method flow diagram that method is recommended in application provided in an embodiment of the present invention；
Fig. 3 is the structural schematic diagram provided in an embodiment of the present invention using label generating means；
Fig. 4 is the structural schematic diagram provided in an embodiment of the present invention using recommendation apparatus；
Fig. 5 is the structural schematic diagram of computer equipment provided in an embodiment of the present invention.
Specific implementation mode
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the present invention, and is not construed as limiting the claims.
Embodiment one
Label generating method is applied an embodiment of the present invention provides a kind of, as shown in Figure 1, this method includes：
Step S101：Obtain the access data of user and preset tag library.
For the present embodiment, the access data for obtaining user, specifically, obtaining the historical behavior daily record or visit of user
It asks daily record, the access data of user is extracted from the historical behavior daily record or access log, wherein the access data include
User accesses the related data of application with it.The access application can be the application software that user has it navigation patterns,
Can also be after user browses it has the application software for being further downloaded and/or installing behavior, the present embodiment to this not
It limits.
In practical application scene, it is applied to show multiple application software to user with the embodiment of the present invention and application is provided
For the application platform for downloading channel, by obtaining current application platform, such as the history using user in store or application market
User behaviors log or access log extract access of the user in current application platform from the historical behavior daily record or access log
Data, wherein the data that access include the related data that user applies with it in the access of current application platform.
Include preset multiple labels for the present embodiment, in the preset tag library.In practical applications, may be used
Tag library tag set is generated according to the multiple label, it then is pressed in tag library tag set to the multiple label
It puts in order and is numbered, such as when the quantity of tag library label is n, the serial number of label is right respectively in tag library tag set
Answer 1~n.
Step S102：According to the access data of user, generates user and apply relation table；Wherein, the user applies relationship
Table accesses the incidence relation of application for recording user with it.
For the present embodiment, application is accessed with it in the access data of the user obtained in the step S101 comprising user
Related data, the related data of application is accessed according to user and its, produce user apply relation table, wherein the user
Using relation table the incidence relation of application is accessed with it for recording user.The user can not only embody use using relation table
The correspondence at family and application can also be embodied using the correspondence with user, specifically, relation table be applied according to described, can
Know which any user is corresponding with and accesses application, is applied according to user and its corresponding access, produce the access of the user
Set of applications；In addition, applying relation table according to described, it also would know that any application is the access application of which user, according to answering
With and its corresponding association user, produce having navigation patterns to it or further having download after navigation patterns for the application
And/or the association user set of installation behavior.
Step S103：Obtain the original tag that user accesses application；According to the user using relation table and described original
Label calculates all frequency of occurrences for accessing label in the corresponding tag library of application of user.
For the present embodiment, it is that the application software in the application platform has and do not include original tag, remaining is then wrapped
Containing one or more original tags.The original tag for obtaining user and accessing application, specifically, according in the step S102
The user of generation applies relation table, obtains user and its corresponding accesss and applies, and from including one or more original tags
Access application in extract its original tag.
For the present embodiment, relation table is applied according to the user, user and its corresponding access application is obtained, then leads to
It crosses and judges whether the corresponding original tag of all access applications of user is that label is all to calculate user in the tag library
Access the frequency of occurrence of label in the corresponding tag library of application.Specifically, when corresponding original mark is applied in a certain access of user
Label are label in the tag library, i.e. the access is applied comprising when label, the increment of the frequency of occurrence is remembered in the tag library
It is 1；It is not label in the tag library when a certain access application of user does not include original tag or its corresponding original tag, i.e.,
The access is applied not comprising when label, the increment of the frequency of occurrence is denoted as 0 in the tag library；By by all access of user
Using corresponding original tag corresponding institute is applied with all access after label is matched one by one in the tag library, are obtained
The increment of frequency of occurrence is stated, increment progress accumulation calculating is then obtained into the frequency of occurrence, wherein the frequency of occurrence
Initial value ought to be 0.
Step S104：Relation table and the frequency of occurrence are applied according to the user, intended application is calculated and corresponds to the mark
Sign the frequency of label in library；Relation table and the frequency of occurrence are applied according to the user, calculates label in the tag library
Reverse document-frequency；According to the frequency and the reverse document-frequency, calculates intended application and correspond to label in the tag library
Weighted value；Wherein, the intended application is to access to be intended to generate the application using label in application.
For the present embodiment, the intended application is to be intended to generate answering using label during the access of at least one user is applied
With the either one or more application of intended application.
For the present embodiment, the frequency is used to indicate that the intended application to correspond to the appearance frequency of label in the tag library
The ratio of the frequency of occurrence of all labels in the secondary tag library corresponding with the intended application.The frequency is calculated, specifically,
The association user of intended application is obtained using relation table according to the user, i.e., it includes the intended application that it, which accesses application,
User then obtains the frequency of occurrence of each association user, and calculating target according to each frequency of occurrence answers
With the frequency of label in the correspondence tag library.Wherein, the frequency goes out with label in the tag library in intended application
Frequency of occurrence is directly proportional；When the frequency of occurrence that label goes out in intended application in the tag library is higher, intended application corresponds to should
The frequency of label is then higher in tag library；Conversely, when the frequency of occurrence is lower, intended application corresponds to label in the tag library
Frequency is then lower.
For the present embodiment, the reverse document-frequency is for indicating that label is general in all users in the tag library
All over property.The reverse document-frequency is calculated, specifically, it is described to apply relation table and the frequency of occurrence to obtain according to the user
User's coating ratio of label in tag library, the reverse text of label in the tag library is calculated according to user's coating ratio
Part frequency.Wherein, user's coating ratio of the reverse document-frequency and label in the tag library is inversely proportional；When the label
User's coating ratio of label is higher in library, and the reverse document-frequency of label is then lower in the tag library；When the tag library
User's coating ratio of middle label is lower, and the reverse document-frequency of label is then higher in the tag library.
For the present embodiment, the intended application corresponds to the weighted value of label in the tag library for indicating the label
For the significance level of the intended application, the significance level passes through in conjunction with the frequency and the reverse file label in library
Frequency obtains.The weighted value is calculated, specifically, corresponding to the frequency of label and institute in the tag library according to the intended application
The reverse document-frequency for stating label in tag library, the frequency, which is multiplied with the reverse document-frequency, to be calculated the target and answers
With the weighted value of label in the correspondence tag library.Wherein, calculated weighted value is bigger, then in current label library label for
Current goal application is more important.
Step S105：According to the weighted value, generate intended application applies label.
For the present embodiment, according to the size of the weighted value, one or more labels are chosen from the tag library and are made
Label is applied for the intended application.Wherein, selected one or more labels compare other labels for current goal
The importance higher of application.
In practical application scene, it is preferably generally intended application and generates one to three using label, so as to give birth to
At can play effective mark action to type, the feature of application software using label, and then be the application of application platform
Classification displaying provides strong support using operations such as recommendations.
It is provided by the invention also in the case where intended application does not have any description content using label generating method
Data are accessed to the history of application based on user and user accesses the original tag of application, are automatically, efficiently that intended application is given birth to
At label is accurately applied, effectively preventing previous manually generated application label need to take considerable time and the problem of manpower, aobvious
Work improves platform operation efficiency and cuts operating costs.
Embodiment two
The alternatively possible realization method of the embodiment of the present invention further includes implementing on the basis of shown in embodiment one
Step shown in example two, wherein
Relation table and the frequency of occurrence are applied according to the user described in the step S104, calculate intended application pair
The frequency of label in the tag library is answered, including：
Relation table and the frequency of occurrence are applied according to the user, the intended application is calculated and corresponds in the tag library
The frequency of occurrence of label；The frequency of occurrence for the intended application being corresponded to label in the tag library is normalized, meter
Calculate the frequency that the intended application corresponds to label in the tag library；Wherein, the frequency is for indicating the intended application pair
Answer the ratio of the frequency of occurrence of label and the frequency of occurrence of all labels in the tag library in the tag library.
For the present embodiment, an example for calculating the frequency has been shown in particular.In the preferred example, the frequency
For indicating that the intended application corresponds to the label corresponding with the intended application of the frequency of occurrence of label in the tag library
The ratio of the frequency of occurrence of all labels in library.The frequency is calculated, specifically, obtaining mesh using relation table according to the user
The association user of application is marked, i.e., it accesses the user that application includes the intended application, then obtains to obtain each association use
The frequency of occurrence at family, wherein the frequency of occurrences is that all access applications of the calculated users of step S103 correspond to
The frequency of occurrence of label in the tag library；Each frequency of occurrence is added up, is calculated in access application comprising described
The sum of corresponding described frequency of occurrence of all association users of intended application, i.e., the described intended application correspond to the tag library acceptance of the bid
The frequency of occurrence of label；Then, it repeats the above steps and corresponds to the appearance frequency of all labels in the tag library to the intended application
It is secondary to be counted, obtain the sum of the frequency of occurrence of all labels in the tag library in intended application；Finally, the target is answered
It is normalized with the frequency of occurrence of label in the correspondence tag library, i.e., by calculating described in the intended application correspondence
The frequency of occurrence of all labels is compared in the frequency of occurrence of the label tag library corresponding with the intended application in tag library
Value, obtains the frequency that intended application corresponds to label in the tag library.
Need it is clear that, calculate intended application correspond to the specific implementation of the frequency of label in the tag library simultaneously
It is not limited, can also be realized by other means according to the User relationship table and the frequency of occurrence by the present embodiment
The frequency that the intended application corresponds to label in the tag library calculates.
Embodiment three
The alternatively possible realization method of the embodiment of the present invention further includes implementing on the basis of shown in embodiment one
Step shown in example three, wherein
Relation table and the frequency of occurrence are applied according to the user described in the step S104, calculate the tag library
The reverse document-frequency of middle label, including：
Relation table and the frequency of occurrence are applied according to the user, total number of users is obtained and the frequency of occurrence is more than 0
Number of users；According to the total number of users and the number of users, the reverse document-frequency of label in the tag library is calculated；Its
In, it includes label in the tag library that the frequency of occurrence is used to characterize all access in application of user more than 0 number of users
The quantity of user；The reverse document-frequency is for measuring generality of the label in all users in the tag library.
For the present embodiment, an example for calculating the reverse document-frequency has been shown in particular.In the preferred example,
The reverse document-frequency is for measuring generality of the label in all users in the tag library.Calculate the reverse file
Frequency then obtains the appearance of each user in all users specifically, obtaining all users according to the User relationship table
The frequency, wherein the frequency of occurrences is in all corresponding tag libraries of access application of the calculated users of step S103
The frequency of occurrence of label；Judge whether each frequency of occurrence is more than 0, is indicated more than 0 in all access applications of active user
Including label in the tag library, indicates not including label in the tag library in all access applications of active user equal to 0,
Then the number of users that the frequency of occurrence is more than 0 is counted, i.e. its all access application summarize comprising label in the tag library
The quantity of user the reverse of label in the tag library is calculated according to the total number of users of the quantity of the user and acquisition
Document-frequency.
Need it is clear that, calculate the specific implementation of the reverse document-frequency of label in the tag library not by
The limitation of the present embodiment, can also be by other means according to the User relationship table and the frequency of occurrence, described in realization
The reverse document-frequency of label calculates in tag library.
Example IV
The alternatively possible realization method of the embodiment of the present invention further includes implementing on the basis of shown in embodiment three
Step shown in example four, wherein
It is described that the reverse document-frequency of label in the tag library is calculated according to the total number of users and the number of users,
Including：According to the total number of users and the number of users, the ratio of the total number of users and the number of users is calculated；To the ratio
Value carries out exponentiation processing, calculates the reverse document-frequency of label in the tag library.
For the present embodiment, by way of exponentiation, the ratio of the total number of users and the number of users is handled,
Calculate the reverse document-frequency of label in the tag library.Can effectively it be enhanced in current application scene by way of exponentiation
The inhibition of popular label, and then improve the accuracy using label of generated intended application.
Embodiment five
The alternatively possible realization method of the embodiment of the present invention further includes implementing on the basis of shown in embodiment one
Step shown in example five, wherein
The original tag that user accesses application is obtained described in the step S103, including：Judge that user accesses application and is
No includes at least one original tag；If so, extracting an original from least one original tag that user accesses application
Beginning label；
It is described that relation table and the original tag are applied according to the user, it calculates all access of user and applies described in correspondence
The frequency of occurrence of label in tag library, including：According to the customer relationship application table and the original tag, it is all to calculate user
Access the quantity for the access application that an original tag described in application is label in the tag library；Using the quantity as use
All frequency of occurrences for accessing label in the corresponding tag library of application in family.
For the present embodiment, it is that the application software in the application platform has and do not include original tag, remaining is then wrapped
Containing one or more original tags.The original tag for obtaining user and accessing application, specifically, according in the step S102
The user of generation applies relation table, obtains user and its corresponding accesss application, judge each access of user apply whether include
At least one original tag, then filter out include one or more original tags access application, and answered from these access
An original tag is respectively extracted in, corresponding original tag is applied in each access for obtaining active user, wherein part accesses and answers
With no corresponding original tag.
It is described that relation table and the original tag are applied according to the user, it calculates all access of user and applies described in correspondence
The frequency of occurrence of label in tag library is then obtained and is used specifically, obtaining the access application of user according to the User relationship table
Family respectively accesses the corresponding original tag of application, and it is label in the tag library to apply corresponding original tag when a certain access of user,
I.e. the access is applied comprising when label, the increment of the frequency of occurrence is denoted as 1 in the tag library；When a certain access application of user
It is not label in the tag library not comprising original tag or its corresponding original tag, i.e., the access, which is applied, does not include the mark
When signing label in library, the increment of the frequency of occurrence is denoted as 0；By the way that corresponding original tag and institute are applied in all access of user
It states label in tag library to carry out after matching one by one, obtains all increments for accessing the corresponding frequency of occurrence of application, wherein
The initial value of the frequency of occurrence ought to be 0；Then increment progress accumulation calculating is obtained in all access applications of user
One original tag is the quantity of the access application of label in the tag library, and using the quantity as all visits of user
Ask the frequency of occurrence using label in the corresponding tag library.
It, can be to described by extracting an original tag from least one original tag that user accesses application
In the case that the accuracy of frequency of occurrence influences less, the operation time of the frequency of occurrence is greatly shortened, life is further increased
At the efficiency of application label.
Embodiment six
The alternatively possible realization method of the embodiment of the present invention further includes implementing on the basis of shown in embodiment one
Step shown in example six, wherein
The step S105, including：
The weighted value for intended application being corresponded to all labels in the tag library is ranked up by sequence from big to small, is obtained
Take the corresponding label of the weights for the preset quantity for coming foremost；Using the label of the preset quantity as intended application
Using label.
For the present embodiment, S101 to S104, institute in the tag library is corresponded to the intended application through the above steps
There is the weighted value of label to be calculated, obtains the multiple weighted values equal with all number of labels in the tag library, it will be described
Multiple weighted values are ranked up by sequence from big to small, and then filter out the weighted value for the preset quantity for coming front, and will
The corresponding label of weighted value of the preset quantity applies label as intended application.Wherein, the preset quantity is according to answering
Can be the numerical value such as 1,3,8, it is not limited in the embodiment of the present invention with the practical application request of platform.And in practical application
In scene, the preferably described preset quantity is usually the numerical value between 1~3, and generated application label can be enable to application
Type, the feature of software play effective mark action, and are the application class displaying of application platform in turn, using fortune such as recommendations
Offer strong support is made in work as a hired labourer.
Need it is clear that, it is described according to weighted value generate intended application the specific implementation using label not
It is limited by the present embodiment, in other embodiments, can also be answered by other means to generate target according to the weighted value
Apply label, as described in judging weighted value whether more than preset threshold value, if so, using the corresponding label of the weighted value as
The modes such as the application label of intended application.
Embodiment seven
The alternatively possible realization method of the embodiment of the present invention, on the basis of shown in embodiment one, combined method is real
Existing algorithm, to being described in detail using label generating method in practical application scene comprising following steps：
Step1. it generates user and applies relation table：
Obtain the access data of user and preset tag library；According to the access data of user, generates user and apply relationship
Table；Wherein, the user accesses the incidence relation of application for recording user using relation table with it, in the application relation table
Including user and its access application.
User i and its k access application are represented by：Ui=(I1,I2……Ik)；
Step2. all frequency of occurrences for accessing label in the corresponding tag library of application of user：
Relation table is applied according to the user, user and its corresponding access application are obtained, then by judging user institute
Have whether the corresponding original tag of access application is that label corresponds to calculate all access applications of user in the tag library
The frequency of occurrence of label in the tag library.Specifically, when the corresponding original tag of a certain access application of user is the label
Label in library, the i.e. access are applied comprising when label, the increment of the frequency of occurrence is denoted as 1 in the tag library；As user
One accesses using being not label in the tag library not comprising original tag or its corresponding original tag, i.e., the access is not using
Including in the tag library when label, the increment of the frequency of occurrence is denoted as 0；By the way that corresponding original is applied in all access of user
Beginning label with after label is matched one by one in the tag library, obtain all application corresponding frequency of occurrences of accessing
Increment progress accumulation calculating is then obtained the frequency of occurrence, wherein the initial value of the frequency of occurrence ought to by increment
It is 0.Its calculating process formula is represented by：
Wherein,It is describedFor all access applications pair of user
Answer the frequency of occurrence of label in the tag library.
Step3. the frequency that intended application corresponds to label in the tag library is calculated：
Relation table and the frequency of occurrence are applied according to the user, the intended application is calculated and corresponds in the tag library
The frequency of occurrence of label；The frequency of occurrence for the intended application being corresponded to label in the tag library is normalized, meter
Calculate the frequency that the intended application corresponds to label in the tag library；Wherein, the frequency is for indicating the intended application pair
Answer the ratio of the frequency of occurrence of label and the frequency of occurrence of all labels in the tag library in the tag library.Its calculating process
Formula is represented by：
Wherein,Indicate all user's set related with application i；
Wherein, describedFor the frequency；It is describedFor with intended application i
Label Tag in the corresponding tag library of all access application of association userjThe sum of frequency of occurrence；The Tag is the mark
Sign all labels in library.
Step4. the reverse document-frequency of label in the tag library is calculated：
Relation table and the frequency of occurrence are applied according to the user, total number of users is obtained and the frequency of occurrence is more than 0
Number of users；According to the total number of users and the number of users, the reverse document-frequency of label in the tag library is calculated；Its
In, it includes label in the tag library that the frequency of occurrence is used to characterize all access in application of user more than 0 number of users
The quantity of user；The reverse document-frequency is for indicating generality of the label in all users in the tag library.As
One preferred embodiment calculates the reverse document-frequency by way of exponentiation, and calculating process formula can indicate
For：
Wherein,It is describedFor the reverse document-frequency；The U
For the total number of users；It is describedFor all frequency of occurrences for accessing label in the corresponding tag library of application of user.
Step5. the weighted value that intended application corresponds to label in the tag library is calculated：
The reverse text of label in the frequency of label and the tag library in the tag library is corresponded to according to the intended application
The frequency and the reverse document-frequency multiplication are calculated label in the corresponding tag library of the intended application by part frequency
Weighted value.Its calculating process formula can be expressed as：
Wherein, describedLabel Tag in the tag library is corresponded to for intended application ijThe frequency；It is describedFor label Tag in the tag libraryjThe reverse document-frequency.
Finally, according to the size of the weighted value, one or more labels are chosen from the tag library as the mesh
Label is applied in mark application, that is, the application label for realizing intended application generates.
It is provided by the invention also in the case where intended application does not have any description content using label generating method
Data are accessed to the history of application based on user and user accesses the original tag of application, are automatically, efficiently that intended application is given birth to
At label is accurately applied, effectively preventing previous manually generated application label need to take considerable time and the problem of manpower, aobvious
Work improves platform operation efficiency and cuts operating costs.
In addition, an embodiment of the present invention provides a kind of applications to recommend method, as shown in Fig. 2, this method includes：
Step S201：Label generating method is applied according to one embodiment of any of the above, generates answering for intended application
Use label.
For the present embodiment, can be realized by one embodiment of the method using label generating method of any of the above
The application label of application target generates, and specific implementation is referring to the explanation of above method embodiment, and details are not described herein.
Step S202：Label is applied according to described, obtains application associated with the intended application.
For the present embodiment, label is applied according to what is generated in the step S201, is obtained related to the intended application
The one or more application of connection, wherein described with the associated application of the intended application be with intended application includes identical answer
With the application of label.
Step S203：Recommend the application to user.
For the present embodiment, recommend acquired one or more application associated with the intended application to user.
Method is recommended in application provided by the invention, and what is provided through the invention generates application using label generating method
Using label, and then it may be implemented in practical application scene and efficiently recommended to user with same label according to application label
Associated application, improve the efficiency of operation of platform.
In addition, an embodiment of the present invention provides a kind of application label generating means, as shown in figure 3, described device includes：
Data obtaining module 301, the access data for obtaining user and preset tag library；
User applies relation table generation module 302, for the access data according to user, generates user and applies relation table；
Wherein, the user accesses the incidence relation of application for recording user using relation table with it；
First computing module 303 accesses the original tag of application for obtaining user；Relation table is applied according to the user
With the original tag, all frequency of occurrences for accessing label in the corresponding tag library of application of user are calculated；
Second computing module 304 calculates intended application for applying relation table and the frequency of occurrence according to the user
The frequency of label in the corresponding tag library；Relation table and the frequency of occurrence are applied according to the user, calculates the label
The reverse document-frequency of label in library；According to the frequency and the reverse document-frequency, calculates intended application and correspond to the mark
Sign the weighted value of label in library；Wherein, the intended application is to access to be intended to generate the application using label in application；
Tag generation module 305, for according to the weighted value, generate intended application to apply label.
Application label generating means provided by the invention, it can be achieved that：There is no the case where any description content in intended application
Under, it may be based on user and data and the original tag of user's access application accessed to the history of application, be automatically, efficiently target
Using generating label is accurately applied, effectively prevents previous manually generated need to be taken considerable time using label and asked with manpower
Topic, significantly improves platform operation efficiency and cuts operating costs.It can also be achieved：The tag library is calculated by way of exponentiation
The reverse document-frequency of middle label can effectively enhance the inhibition to popular label in current application scene, and then improve and be generated
Intended application the accuracy using label.
The embodiment of the method provided in an embodiment of the present invention that above-mentioned offer is provided using label generating means, specific work(
It can realize the explanation referred in embodiment of the method, details are not described herein.
Recommendation apparatus is applied an embodiment of the present invention provides a kind of, as shown in figure 4, described device includes：
Using tag generation module 401, for according to above application label generating method, generating the application mark of intended application
Label；
Associated application acquisition module 402 obtains answer associated with the intended application for applying label according to described
With；
Using recommending module 403, for recommending the application to user.
Application recommendation apparatus provided by the invention, it can be achieved that：What is provided through the invention applies label generating method next life
Label is applied at application, and then may be implemented in practical application scene and efficiently recommend to have to user according to application label
The associated application of same label improves the efficiency of operation of platform.
The embodiment of the method provided in an embodiment of the present invention that above-mentioned offer may be implemented using recommendation apparatus, concrete function are real
Referring now to the explanation in embodiment of the method, details are not described herein.
In addition, an embodiment of the present invention provides a kind of computer readable storage medium, deposited on computer readable storage medium
Computer program is contained, is realized when the computer program is executed by processor and applies label described in above example one to seven
Generation method and above application recommend method.Wherein, the computer readable storage medium is including but not limited to any kind of
Disk (including floppy disk, hard disk, CD, CD-ROM and magneto-optic disk), ROM (Read-Only Memory, read-only memory), RAM
(Random AcceSS Memory, immediately memory), EPROM (EraSable Programmable Read-Only
Memory, Erarable Programmable Read only Memory), EEPROM (Electrically EraSable Programmable
Read-Only Memory, Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or light card.It is, storage
Equipment includes by any medium of equipment (for example, computer, mobile phone) storage or transmission information in the form of it can read, Ke Yishi
Read-only memory, disk or CD etc..
Computer readable storage medium provided by the invention can be realized when for the application label generating method：
In the case that intended application does not have any description content, it may be based on user and the history access data of application and user's access answered
Original tag is automatically, efficiently that intended application generates accurately using label, effectively prevents in the past manually generated answer
It need to be taken considerable time with label and the problem of manpower, significantly improve platform operation efficiency and cut operating costs；Also pass through
The mode of exponentiation calculates the reverse document-frequency of label in the tag library, can effectively enhance to popular mark in current application scene
The inhibition of label, and then improve the accuracy using label of generated intended application.When recommending method for the application
It can be achieved：What is provided through the invention generates the application label of application using label generating method, and then may be implemented in reality
The associated application with same label is efficiently recommended to user according to application label in application scenarios, improves the fortune of platform
Seek efficiency.
The embodiment of the method for above-mentioned offer may be implemented in computer readable storage medium provided in an embodiment of the present invention, specifically
Function realizes the explanation referred in embodiment of the method, and details are not described herein.
In addition, the embodiment of the present invention additionally provides a kind of computer equipment, as shown in Figure 5.Calculating described in the present embodiment
Machine equipment can be the equipment such as server, personal computer and the network equipment.The computer equipment include processor 502,
The devices such as memory 503, input unit 504 and display unit 505.It will be understood by those skilled in the art that setting shown in Fig. 5
Standby structure devices do not constitute the restriction to all devices, may include components more more or fewer than diagram, or combine certain
A little components.Memory 503 can be used for storing computer program 501 and each function module, and the operation of processor 502 is stored in storage
The computer program 501 of device 503, to execute various function application and the data processing of equipment.Memory can be memory
Reservoir or external memory, or including both built-in storage and external memory.Built-in storage may include read-only memory
(ROM), programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash
Device or random access memory.External memory may include hard disk, floppy disk, ZIP disks, USB flash disk, tape etc..It is disclosed in this invention to deposit
Reservoir includes but not limited to the memory of these types.Memory disclosed in this invention is only used as example rather than as restriction.
Input unit 504 is used to receive the input of signal, and receives keyword input by user.Input unit 504 can
Including touch panel and other input equipments.Touch panel collects user on it or neighbouring touch operation (for example is used
Family uses the operations of any suitable object or attachment on touch panel or near touch panel such as finger, stylus), and root
According to the corresponding attachment device of preset driven by program；Other input equipments can include but is not limited to physical keyboard, function
It is one or more in key (such as broadcasting control button, switch key etc.), trace ball, mouse, operating lever etc..Display unit
505 can be used for showing information input by user or be supplied to the information of user and the various menus of computer equipment.Display is single
The forms such as liquid crystal display, Organic Light Emitting Diode can be used in member 505.Processor 502 is the control centre of computer equipment, profit
With the various pieces of various interfaces and the entire computer of connection, by running or executing the software being stored in memory 502
Program and/or module, and the data being stored in memory are called, perform various functions and handle data.
As one embodiment, the computer equipment includes：One or more processors 502, memory 503, one
Or multiple computer programs 501, wherein one or more of computer programs 501 be stored in memory 503 and by with
It is set to and is executed by one or more of processors 502, one or more of computer programs 501 are configured to carry out above
Label generating method is applied described in embodiment one to seven.
As another embodiment, the computer equipment includes：One or more processors 502, memory 503, one
A or multiple computer programs 501, wherein one or more of computer programs 501 are stored in memory 503 and quilt
It is configured to be executed by one or more of processors 502, one or more of computer programs 501 are configured to carry out
It states and applies recommendation method.
Computer equipment provided by the invention can be realized when executing the application label generating method：In intended application
In the case of there is no any description content, it may be based on user and the original of application accessed to the history access data of application and user
Label, automatic, efficiently accurate using label for intended application generation, effectively preventing previous manually generated application label need to
It takes considerable time and the problem of manpower, significantly improves platform operation efficiency and cut operating costs；Also pass through the side of exponentiation
Formula calculates the reverse document-frequency of label in the tag library, can effectively enhance the suppression to popular label in current application scene
System, and then improve the accuracy using label of generated intended application.It can be realized when executing the application and recommending method：
What is provided through the invention generates the application label of application using label generating method, and then may be implemented in practical application scene
It is middle that the associated application with same label is efficiently recommended to user according to application label, improve the efficiency of operation of platform.
The embodiment of the method for above-mentioned offer may be implemented in computer equipment provided in an embodiment of the present invention, and concrete function is realized
The explanation in embodiment of the method is referred to, details are not described herein.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, it can also
That each unit physically exists alone, can also two or more units be integrated in a module.Above-mentioned integrated mould
The form that hardware had both may be used in block is realized, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and when sold or used as an independent product, can also be stored in a computer
In read/write memory medium.One of ordinary skill in the art will appreciate that realizing that all or part of step of above-described embodiment can be with
It is completed by hardware, relevant hardware can also be instructed to complete by program, which can be stored in a computer can
It reads in storage medium, storage medium may include memory, disk or CD etc..
The above is only some embodiments of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (16)
1. a kind of applying label generating method, which is characterized in that include the following steps：
Obtain the access data of user and preset tag library；
According to the access data of user, generates user and apply relation table；Wherein, the user is used to record user using relation table
The incidence relation of application is accessed with it；
Obtain the original tag that user accesses application；Relation table and the original tag are applied according to the user, calculates user
All frequency of occurrences for accessing label in the corresponding tag library of application；
Relation table and the frequency of occurrence are applied according to the user, calculates the frequency that intended application corresponds to label in the tag library
Rate；Relation table and the frequency of occurrence are applied according to the user, calculates the reverse document-frequency of label in the tag library；Root
According to the frequency and the reverse document-frequency, the weighted value that intended application corresponds to label in the tag library is calculated；Wherein, institute
It is to access to be intended to generate the application using label in application to state intended application；
According to the weighted value, generate intended application applies label.
2. according to claim 1 apply label generating method, which is characterized in that described to apply relationship according to the user
Table and the frequency of occurrence calculate the frequency that intended application corresponds to label in the tag library, including：
Relation table and the frequency of occurrence are applied according to the user, the intended application is calculated and corresponds to label in the tag library
Frequency of occurrence；
The frequency of occurrence for the intended application being corresponded to label in the tag library is normalized, and calculates the target and answers
With the frequency of label in the correspondence tag library；
Wherein, the frequency is for indicating that the intended application corresponds to the frequency of occurrence of label and the label in the tag library
The ratio of the frequency of occurrence of all labels in library.
3. according to claim 1 or 2 apply label generating method, which is characterized in that described to be applied according to the user
Relation table and the frequency of occurrence calculate the frequency that the intended application corresponds to label in the tag library, pass through following formula
It realizes：
Wherein, describedFor the frequency；It is describedFor all access application pair with intended application i association users
Answer label Tag in the tag libraryjThe sum of frequency of occurrence；The Tag is all labels in the tag library.
4. according to claim 1 apply label generating method, which is characterized in that described to apply relationship according to the user
Table and the frequency of occurrence calculate the reverse document-frequency of label in the tag library, including：
Relation table and the frequency of occurrence are applied according to the user, obtains the use of total number of users and the frequency of occurrence more than 0
Amount；
According to the total number of users and the number of users, the reverse document-frequency of label in the tag library is calculated；
Wherein, the frequency of occurrence includes in the tag library for characterizing during all access of user are applied more than 0 number of users
The quantity of the user of label；The reverse document-frequency is universal in all users for measuring label in the tag library
Property.
5. according to claim 4 apply label generating method, which is characterized in that described according to the total number of users and institute
Number of users is stated, the reverse document-frequency of label in the tag library is calculated, including：
According to the total number of users and the number of users, the ratio of the total number of users and the number of users is calculated；
Exponentiation processing is carried out to the ratio, calculates the reverse document-frequency of label in the tag library.
6. according to claim 4 or 5 apply label generating method, which is characterized in that described according to the total number of users
With the number of users, the reverse document-frequency of label in the tag library is calculated, is realized by following formula：
Wherein,It is describedFor the reverse document-frequency；The U is institute
State total number of users；It is describedFor all frequency of occurrences for accessing label in the corresponding tag library of application of user.
7. according to claim 1 apply label generating method, which is characterized in that described according to the frequency and described inverse
To document-frequency, the weighted value that intended application corresponds to label in the tag library is calculated, is realized by following formula：
Wherein, describedLabel Tag in the tag library is corresponded to for intended application ijThe frequency；It is described
For label Tag in the tag libraryjThe reverse document-frequency.
8. according to claim 1 apply label generating method, which is characterized in that the original for obtaining user and accessing application
Beginning label, including：
Judge that user accesses whether application includes at least one original tag；
If so, extracting an original tag from least one original tag that user accesses application；
It is described that relation table and the original tag are applied according to the user, calculate all corresponding labels of access application of user
The frequency of occurrence of label in library, including：
According to the customer relationship application table and the original tag, an original mark described in all access applications of user is calculated
Label are the quantity of the access application of label in the tag library；
Using the quantity as all frequency of occurrences for accessing label in the corresponding tag library of application of user.
9. according to claim 1 apply label generating method, which is characterized in that it is described according to the weighted value, it generates
The application label of intended application, including：
The weighted value for intended application being corresponded to all labels in the tag library is ranked up by sequence from big to small, the row of acquisition
The corresponding label of the weights of preset quantity up front；
Label is applied using the label of the preset quantity as intended application.
10. method is recommended in a kind of application, which is characterized in that including：
Label generating method is applied according to claim 1 to 9 any one, generate intended application applies label；
Label is applied according to described, obtains application associated with the intended application；
Recommend the application to user.
11. a kind of application label generating means, which is characterized in that including：
Data obtaining module, the access data for obtaining user and preset tag library；
User applies relation table generation module, for the access data according to user, generates user and applies relation table；Wherein, institute
It states user and accesses the incidence relation of application with it for recording user using relation table；
First computing module accesses the original tag of application for obtaining user；According to the user using relation table and described
Original tag calculates all frequency of occurrences for accessing label in the corresponding tag library of application of user；
Second computing module calculates intended application and corresponds to institute for applying relation table and the frequency of occurrence according to the user
State the frequency of label in tag library；Relation table and the frequency of occurrence are applied according to the user, calculates the tag library acceptance of the bid
The reverse document-frequency of label；According to the frequency and the reverse document-frequency, calculates intended application and correspond in the tag library
The weighted value of label；Wherein, the intended application is to access to be intended to generate the application using label in application；
Tag generation module, for according to the weighted value, generate intended application to apply label.
12. a kind of applying recommendation apparatus, which is characterized in that including：
It is generated using tag generation module for applying label generating method according to claim 1 to 9 any one
Intended application applies label；
Associated application acquisition module obtains application associated with the intended application for applying label according to described；
Using recommending module, for recommending the application to user.
13. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes claim 1 to 9 any one of them application label generation side when the computer program is executed by processor
Method.
14. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, the computer program realize that method is recommended in application according to any one of claims 10 when being executed by processor.
15. a kind of computer equipment, which is characterized in that it includes：
One or more processors；
Memory；
One or more computer programs, wherein one or more of computer programs are stored in the memory and quilt
It is configured to be executed by one or more of processors, one or more of computer programs are configured to：It executes according to power
Profit requires 1 to 9 any one of them application label generating method.
16. a kind of computer equipment, which is characterized in that it includes：
One or more processors；
Memory；
One or more computer programs, wherein one or more of computer programs are stored in the memory and quilt
It is configured to be executed by one or more of processors, one or more of computer programs are configured to：It executes according to power
Profit requires to apply recommendation method described in 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810356223.XA CN108595599A (en) | 2018-04-19 | 2018-04-19 | Using label generating method, device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810356223.XA CN108595599A (en) | 2018-04-19 | 2018-04-19 | Using label generating method, device, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108595599A true CN108595599A (en) | 2018-09-28 |
Family
ID=63613268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810356223.XA Pending CN108595599A (en) | 2018-04-19 | 2018-04-19 | Using label generating method, device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108595599A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246027A (en) * | 2019-05-29 | 2019-09-17 | 阿里巴巴集团控股有限公司 | It honours an agreement based reminding method, device and electronic equipment |
| CN111427900A (en) * | 2020-03-20 | 2020-07-17 | 政采云有限公司 | Label library updating method, device, equipment and readable storage medium |
| CN111797282A (en) * | 2020-06-03 | 2020-10-20 | 中国建设银行股份有限公司 | Product label weight determination method and device, electronic equipment and readable storage medium |
| CN112579663A (en) * | 2019-09-30 | 2021-03-30 | 北京国双科技有限公司 | Information processing method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101984437A (en) * | 2010-11-23 | 2011-03-09 | 亿览在线网络技术（北京）有限公司 | Music resource individual recommendation method and system thereof |
| US20170091274A1 (en) * | 2015-09-30 | 2017-03-30 | Linkedin Corporation | Organizational data enrichment |
| CN107506398A (en) * | 2017-08-02 | 2017-12-22 | 杭州东信北邮信息技术有限公司 | A kind of method that tag attributes are added for books |
-
2018
- 2018-04-19 CN CN201810356223.XA patent/CN108595599A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101984437A (en) * | 2010-11-23 | 2011-03-09 | 亿览在线网络技术（北京）有限公司 | Music resource individual recommendation method and system thereof |
| US20170091274A1 (en) * | 2015-09-30 | 2017-03-30 | Linkedin Corporation | Organizational data enrichment |
| CN107506398A (en) * | 2017-08-02 | 2017-12-22 | 杭州东信北邮信息技术有限公司 | A kind of method that tag attributes are added for books |
Non-Patent Citations (1)
| Title |
|---|
| 骆彬: "基于用户评论的Flickr图像标签推荐方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246027A (en) * | 2019-05-29 | 2019-09-17 | 阿里巴巴集团控股有限公司 | It honours an agreement based reminding method, device and electronic equipment |
| CN112579663A (en) * | 2019-09-30 | 2021-03-30 | 北京国双科技有限公司 | Information processing method and device |
| CN112579663B (en) * | 2019-09-30 | 2024-06-25 | 北京国双科技有限公司 | Information processing method and device |
| CN111427900A (en) * | 2020-03-20 | 2020-07-17 | 政采云有限公司 | Label library updating method, device, equipment and readable storage medium |
| CN111427900B (en) * | 2020-03-20 | 2023-05-02 | 政采云有限公司 | Label library updating method, device, equipment and readable storage medium |
| CN111797282A (en) * | 2020-06-03 | 2020-10-20 | 中国建设银行股份有限公司 | Product label weight determination method and device, electronic equipment and readable storage medium |
| CN111797282B (en) * | 2020-06-03 | 2024-03-29 | 中国建设银行股份有限公司 | Product tag weight determining method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108595599A (en) | Using label generating method, device, storage medium and computer equipment | |
| CN105630977B (en) | Application program recommended method, apparatus and system | |
| CN107909428A (en) | Electronic device, Products Show method and computer-readable recording medium | |
| CN109461023B (en) | Loss user retrieval method and device, electronic equipment and storage medium | |
| CN106875206A (en) | Acquisition of information, assessment, questionnaire method, device and server | |
| CN104077339A (en) | Multimedia data user preference degree acquiring method, device and system | |
| CN109729395A (en) | Video quality evaluation method, device, storage medium and computer equipment | |
| CN106454536B (en) | The determination method and device of information recommendation degree | |
| CN108399565A (en) | Financial product recommendation apparatus, method and computer readable storage medium | |
| CN108182502A (en) | The generation method of growing quality evaluation index, the statistical method of business growth value | |
| CN108734587A (en) | The recommendation method and terminal device of financial product | |
| WO2016137426A1 (en) | Navigation menu based on crowd data | |
| CN107644100A (en) | Information processing method, device and system and computer-readable recording medium | |
| CN107818491A (en) | Electronic installation, Products Show method and storage medium based on user's Internet data | |
| JP7429102B2 (en) | Quiz-type question and answer service providing method and system | |
| CN109636084A (en) | Consumer's risk type evaluation method, storage medium and equipment based on big data | |
| CN103608807A (en) | Path length selector | |
| CN109729433A (en) | A kind of video playing appraisal procedure and device | |
| CN112365367A (en) | Regional portrait method and device based on device electric quantity and storage medium | |
| CN108269196A (en) | Add in the method, apparatus and computer equipment of network social association | |
| CN110414926A (en) | Account management method, device and computer readable storage medium | |
| CN108564220A (en) | User gender prediction method, apparatus, storage medium and computer equipment | |
| CN110267086B (en) | Anchor label establishing method and device, live broadcast network interface engine interface and medium | |
| CN110019774A (en) | Label distribution method, device, storage medium and electronic device | |
| CN110276650A (en) | Advertisement arrival rate determines method, advertisement delivery method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200422 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510640 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180928 |
|
| RJ01 | Rejection of invention patent application after publication |