CN110069695A - Label processing method and device - Google Patents
Label processing method and device Download PDFInfo
- Publication number
- CN110069695A CN110069695A CN201710818950.9A CN201710818950A CN110069695A CN 110069695 A CN110069695 A CN 110069695A CN 201710818950 A CN201710818950 A CN 201710818950A CN 110069695 A CN110069695 A CN 110069695A
- Authority
- CN
- China
- Prior art keywords
- user
- label
- target labels
- users
- web browsing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention discloses a kind of label processing method and devices, the label for extending user.The method comprise the steps that obtaining the label of the first user and the label of second user, the label of first user and the label of the second user include identical label；Determine that target labels, the target labels are the label that the label of first user does not include from the label of the second user；The target labels are distributed for first user.Because the first user and second user include identical label, so the first user and second user have similitude, the label of the label of the first user and second user can be associated thus, to, include by second user and target labels that the first user does not include are determined, to distribute to the first user, the extension to the first user tag is realized.Because of the characteristics of the first user and second user have similitude, and the target labels that the first user obtains in this way meet the first user.
Description
Technical field
The present invention relates to data processing field more particularly to a kind of label processing method and devices.
Background technique
Advertisement accurately dispensing, video recommendations etc. are carried out in internet to generally require to know user's some labels accordingly, example
Such as whether paying close attention to automobile, whether needing Expert English language training by qualified teachers, whether like the labels such as animation.
The existing mode for user setting label is: browsing situation of the user on network is obtained, according to the browsing feelings
Condition analyzes the label of user.
But for majority of case, it tends to be difficult to be collected into the most browsing situation of user, such as only know
Some user browsed some car website, it is unclear that the user, which has, did not browsed digital class website, so according to number is collected into
It is relatively fewer according to obtained label, it cannot reflect some user's feature comprehensively.
Summary of the invention
The embodiment of the invention provides a kind of label processing method and devices, the label for extending user.
In order to solve the above-mentioned technical problem, the embodiment of the invention provides following technical schemes:
A kind of label processing method, comprising:
Obtain the label of the first user and the label of second user, the label of first user and the second user
It include identical label in label；
From the label of the second user determine target labels, the target labels be first user label not
Including label；
The target labels are distributed for first user.
In order to solve the above-mentioned technical problem, the embodiment of the invention also provides following technical schemes:
A kind of label processing device, comprising:
Acquiring unit, for obtaining the label of the first user and the label of second user, the label of first user and
It include identical label in the label of the second user；
First determination unit, for determining target labels from the label of the second user, the target labels are institute
State the label that the label of the first user does not include；
Allocation unit, for distributing the target labels for first user.
In order to solve the above-mentioned technical problem, the embodiment of the invention also provides following technical schemes:
A kind of storage medium, the storage medium include the program of storage, wherein in described program operation described in control
Equipment executes label processing method as described above where storage medium.
In order to solve the above-mentioned technical problem, the embodiment of the invention also provides following technical schemes:
A kind of processor, the processor is for running program, wherein mark as described above is executed when described program is run
Sign processing method.
As can be seen from the above technical solutions, the embodiment of the present invention has the advantage that
Obtain the label of the first user and the label of second user, wherein the label of the first user and the mark of second user
It include identical label in label.Then, determine that target labels, target labels are the mark of the first user from the label of second user
The label for not including is signed, to distribute target labels for the first user.Because the first user and second user include identical label,
So the first user and second user have similitude, the label of the label of the first user and second user can be closed thus
Connection, thus, include by second user and target labels that the first user does not include are determined, it is real to distribute to the first user
The extension to the first user tag is showed.Because the first user and second user have similitude, the side of the first user in this way
The characteristics of target labels that formula obtains meet the first user.
Detailed description of the invention
Fig. 1 is a kind of method flow diagram of label processing method provided in an embodiment of the present invention；
Fig. 2 is a kind of method flow diagram of label processing method provided in an embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of label processing device provided in an embodiment of the present invention.
Specific embodiment
The embodiment of the invention provides a kind of label processing method and devices, the label for extending user.
In the label processing method to the embodiment of the present invention and before device is described in detail, in order to more convenient geography
The label processing method and device for solving the embodiment of the present invention, are first introduced some terms and technical method.
1) label
The label processing method and device of the embodiment of the present invention are related to the label of user, and the label of user is used for user
The characteristics of be identified, can reflect the attribute of identified user.The concrete form of label for example can be text information etc..
One user can have one or more labels, and different users can have identical or different label.
Label can be used for the concern information to user and be identified, for example, label can be with are as follows: sport, amusement, automobile, dynamic
The information such as unrestrained, for reflecting the perpetual object of user.
2) recommended engine
Some concrete implementation means can be utilized in the realization of the label processing method of the embodiment of the present invention, for example, using
Recommended engine.
Recommended engine can comprehensively utilize the behavior of user, attribute, between the attribute of object, content, classification and user
Social networks etc. excavate the hobby and demand of user, the object actively recommended its interested to user or needed.Recommendation is drawn
Method, such as content-based recommendation, the recommendation based on user behavior, the recommendation based on social networks network etc. there are many holding up.
Content-based recommendation is " gene " for analyzing the Web content that user is browsing, and is selected similar to having in current network "
Gene " object recommendation to user." gene " for the Web content that also analysis user browsed in the past simultaneously, to get it
Then preference will meet the object recommendation of user preference to user.For example, user recommends when browsing a packet for it
The similar packet of other shapes.Recommendation based on user behavior is then to analyze the group behavior of user using group intelligence algorithm, comprehensive
Similarity between analysis user and user, user are closed to the individual demands of minority's commodity, to improve the essence of recommendation simultaneously
Parasexuality, diversity and novelty.For example, finding that party A-subscriber and party B-subscriber's purchase commodity are much like according to existing purchaser record, in addition
Learn that party B-subscriber has purchased M commodity and A is not bought, then M commodity can be recommended to A.Recommendation based on social networks network is
By the social networks network where analysis user, its user for being best able to influence is found, or be best able to influence the use
The user at family, then integrate the personalization preferences of every user and recommend.
The label processing method of the embodiment of the present invention is used for the label of extending user, is one based on user tag similitude
Kind extended method.The similitude for inquiring the label between user can use recommended engine realization, and the use of recommended engine be to use
Family provides expansible label.
Fig. 1 is a kind of method flow diagram of label processing method provided in an embodiment of the present invention, refering to above content, this hair
The label processing method of bright embodiment includes:
Step 101: obtaining the label of the first user and the label of second user.
It include identical label in the label of first user and the label of second user；
Step 102: target labels are determined from the label of second user.
Target labels are the label that the label of the first user does not include；
Step 103: distributing target labels for the first user.
Optionally,
The quantity of second user be it is multiple,
Target labels are determined from the label of second user, comprising:
Determine target labels, from the label of multiple second users to obtain multiple and different target labels；
After determining target labels in the label of second user, the label processing method of the embodiment of the present invention further include:
Calculate the number of users of second user belonging to each target labels；
According to number of users, extension tag is determined from multiple and different target labels；
Target labels are distributed for the first user, comprising:
Extension tag is distributed for the first user.
Optionally,
According to number of users, extension tag is determined from multiple and different target labels, comprising:
It obtains and chooses quantity；
Determine that quantity is equal to the extension tag for choosing quantity from multiple and different target labels, wherein extension tag
Number of users be greater than the number of users of remaining label, remaining label be in multiple and different target labels in addition to extension tag it
Outer label.
Optionally,
Obtain the label of the first user and the label of second user, comprising:
Obtain the web browsing data of the first user and second user；
According to the corresponding relationship of preset web browsing data and label, the determining web browsing data pair with the first user
The label answered；
According to the corresponding relationship of preset web browsing data and label, the determining web browsing data pair with second user
The label answered.
Optionally,
The quantity of the label of first user is less than default classification thresholds, and the quantity of the label of second user is greater than or equal to pre-
If classification thresholds.
Optionally,
Label is for being identified the concern information of user.
In conclusion obtaining the label of the first user and the label of second user, wherein the label of the first user and second
It include identical label in the label of user.Then, target labels, target labels first are determined from the label of second user
The label that the label of user does not include, to distribute target labels for the first user.Because the first user and second user include phase
With label thus can be by the label of the first user and second user so the first user and second user have similitude
Label is associated, thus, include by second user and target labels that the first user does not include are determined, to distribute to
One user realizes the extension to the first user tag.Because the first user and second user have similitude, the first user passes through
The characteristics of target labels that such mode obtains meet the first user.
Fig. 2 is a kind of method flow diagram of label processing method provided in an embodiment of the present invention, refering to above content and
The label processing method of embodiment shown in FIG. 1, the embodiment of the present invention includes:
Step 201: obtaining the web browsing data of the first user and second user.
User, when carrying out browse operation on network, can generate web browsing number by tools such as browser or social softwares
According to the characteristics of these web browsing datas reflect user.These web browsing datas are obtained, it can be clear by analyzing the network
Data of looking at obtain some characteristic informations of user.
The specific implementation method for obtaining web browsing data may is that user passes through user account login service device, clothes
Then the browse operation of business device detection user records the web browsing data to generate the web browsing data of the user
In the database, equipment for processing is obtained and is analyzed.
For example, user A, which is successively clicked, has browsed automobile webpage and entertainment news webpage, user B is successively clicked and has been browsed vapour
Vehicle webpage, entertainment news webpage, sport webpage and health webpage.After server detects these behaviors of user, to user A and
The browsing behavior of user B records, and obtains the web browsing data of user A and user B, then by these web browsing datas
Storage is in the database.Processing equipment reads user A and use when needing the label of extending user A and user B from database
These web browsing datas of family B obtain the web browsing data of selected user from database.For example, obtaining the net of user A
Network browses data: automobile webpage, entertainment news webpage, obtains the web browsing data of user B: automobile webpage, entertainment news net
Page, sport webpage and health webpage.
In embodiments of the present invention, it is said so that processing equipment executes the label processing method of the embodiment of the present invention as an example
Bright, wherein the processing equipment can be for example the equipment such as computer, server.
Step 202: according to the corresponding relationship of preset web browsing data and label, determining user with user network
Browse the corresponding label of data.
Processing equipment prestores the corresponding relationship of web browsing data and label, obtains the web browsing data of user
Afterwards, the label of the user corresponding with the web browsing data of user can be determined from the corresponding relationship.Label can be used for
The concern information of user is identified.
Using the web browsing data of each user, the label of each user can be obtained by the corresponding relationship, at this
During invention is implemented, according to the corresponding relationship of preset web browsing data and label, the determining web browsing number with the first user
According to corresponding label, which is the label of the first user；According to the corresponding relationship of preset web browsing data and label, really
Fixed label corresponding with the web browsing data of second user, the label are the label of second user.
Specifically, it is preset with a label system, which includes that web browsing data and the corresponding of label are closed
System, thus, after the web browsing data for obtaining user, it can be mapped according to the web browsing data of the label system and user
Obtain the label of user.
For example, getting the web browsing data of user A: automobile webpage, entertainment news webpage, the web browsing of user B
Data: automobile webpage, entertainment news webpage, sport webpage and health webpage.The web browsing number that the label system prestored includes
Have according to the corresponding relationship of-label: automobile webpage-automobile, entertainment news webpage-amusement, sport webpage-sport, health webpage-are supported
It is raw.It is handled by mapping, the label that user A can be obtained is automobile, amusement, and the label of user B is automobile, amusement, sport, supports
It is raw.
In embodiments of the present invention, in order to determine the similitude of user, needing different users includes the identical mark in part
Label.It include identical label i.e. in the label of the first user and the label of second user.Concrete implementation mode, which may is that, to be obtained
To after the label of multiple and different users, the user including same label is selected from these users.In embodiments of the present invention,
The label of one user can be partially identical with the label of second user, or the label of the first user is the mark of second user
The subset of label.
It is appreciated that realizing there there is more the mode including identical label in the label of the first user and the label of second user
Kind, for example, whether identical being matched using the label of different user, select the different user of same label.Alternatively, its
When its equipment sends the label of different user to processing equipment, the label of the user including same label is as sent.Alternatively, work
Make personnel in step 201, selection prejudges out the first user of label having the same and second user, and then processing equipment obtains again
Take the web browsing data of the first user and second user.
By step 201 and step 202, the label of the label and second user that obtain the first user is realized.Certainly, exist
It is also possible to the label that processing equipment directly obtains different user from other equipment in the embodiment that the present invention has.Alternatively, passing through
Other modes generate the label of different user.
It should be noted that in processing, in order to determine the corresponding relationship of outgoing label and user, that is, determining outgoing label
Which user belonged to, Ke Yiwei when determining the label corresponding with the web browsing data of user of user, is obtained in step 202
To the corresponding relationship of user identifier and label, wherein for being identified to user, user identifier for example can be user identifier
User account, user's sequence number, user's phone number etc..It is closed using the user identifier and the corresponding of label in subsequent step
System is operated.
Step 203: from the first user and second user, determining that label expands user and label provides user.
In the embodiment that the present invention has, the user in the label of user is obtained to step 202 and is classified, one kind is mark
Label expand user, such user is the user for needing to carry out label expansion；Another kind of to provide user for label, such user is mark
Label expand user and provide the label of expansion.
There are many specific mode classifications, such as passes through the number of tags of user, the activity of the user, account of user etc.
Grade etc..
The embodiment of the present invention classifies to the first user and second user using the number of labels of user as foundation, with mark
Signing quantity to be less than the user of default classification thresholds is that label expands user, is greater than or equal to default classification thresholds with number of labels
User provides user for label.In embodiments of the present invention, default classification thresholds are less than with the quantity of the label of the first user, the
The quantity of the label of two users is illustrated for being greater than or equal to default classification thresholds.
For example, default classification thresholds are 3, then in above-mentioned specific example, the user A with 2 labels is label expansion
Use is filled, expandtabs are needed；User B with 4 labels provides user for label, can provide the label of extension for user A.
In this way, the expansion that label can be carried out according to having the user data for the enriching label certain user less to label, so that more
Reflect the less user of this part labels well.
Step 204: determining target labels, from the label of multiple second users to obtain multiple and different target labels.
Wherein, target labels be the first user label in do not include label.
Because including identical label in the label of the first user and the label of second user, thus, the first user and second
User has similitude, and the label that the first user and second user can be used is expanded mutually, and the label of expansion can be anti-
Reflect the characteristics of being expanded user.Again because the quantity of the label of the first user is less than default classification thresholds, the label of second user
Quantity is greater than or equal to default classification thresholds, and the quantity of the label of second user is greater than the quantity of the label of the first user, thus
The expansion of label can be carried out to the first user with the label of second user.It is few with user's extension tag quantity more than number of labels
The label of user, such mode can make the expansion of label more accurate.
For example, in label for when being identified to the concern information of user, the first user and second user to include identical
Label, then the focus of the first user and second user is more similar, the first user and second user can be seen as have altogether
With the people of interest.The target labels that second user includes but the first user does not include can reflect the focus of second user, because
The focus of first user and second user is more similar, thus the first user pay close attention to target labels instruction concern information can
Energy property is very big, so as to which target labels are distributed to the first user, is extended with the label to the first user.
By taking the quantity of second user is multiple as an example, step 204 specific implementation is, from the label of multiple second users
Middle determining target labels, the target labels are the label that second user includes, which is also in the label of the first user
The label for not including.The quantity of obtained target labels can be one or more, in embodiments of the present invention with target labels
It is illustrated to be multiple.
Specifically, by the analysis of recommended engine, recommended engine can determine that each label for needing label to expand expands
User is filled, it is a from the user data of acquisition then by identical label, it finds out and expands user with same label with label
Label user is provided, then, determine that outgoing label expands user's target labels for not including from the label that label provides user.
For example, because user A and user B include identical label: automobile and amusement, so as to use the label of user B
The label for carrying out extending user A, sport and health are the label that user A does not include in the label of user B, may thereby determine that body
Educating with health is target labels, which can be used for the label of extending user A.
It is appreciated that target labels are determined from the label of second user, it can be for from one or more second users
Determine target labels.Available one or more target labels, the present invention is not especially limit this.
It is appreciated that the label of second user includes label identical with the label of the first user, the label of second user
Further include the label different from the label of the first user, the mark of the first user of tag extension of second user could be used in this way
Label.
Step 205: calculating the number of users of second user belonging to each target labels.
When the quantity of second user is multiple, in order to enable the label of extension can more meet the spy that label expands user
Point.In an embodiment of the present invention, target labels can be further processed.
Target labels are acquired from second user, and target labels may belong to one or more second users, can be counted
The quantity of second user belonging to target labels is calculated, which is referred to as number of users.In this way, target labels can be realized
Quantity statistics.
For example, each second user has target labels F there are three second users, thus the number of users of target labels F
It is 3.
For example, execution through the above steps obtains the label of user A to D, wherein user A is that label expands user (i.e.
First user), user B, C, D provide user for label.It is as follows:
The label of label expansion user A are as follows: automobile, amusement；
The label of label offer user B are as follows: automobile, amusement, sport, health；
The label of label offer user C are as follows: automobile, amusement, sport, animation；
The label of label offer user D are as follows: amusement, sport, shopping.
Wherein, user B, user C and user A include identical label automobile and amusement, i.e., label provide user B and C and
User A has similitude, expands the label of user A so as to use the label of user B and user C.User B or user C include
And the target labels that user A does not include are as follows: sport, health and animation.The number of users difference of target labels is wherein calculated
Are as follows: sport -2, health -1, animation -1.
Step 206: according to number of users, determining extension tag from multiple and different target labels.
The label of the extension provided for the first user is extension tag, which selects from target labels
It arrives, specific selection mode is the number of users according to target labels, and extension mark is determined from multiple and different target labels
Label.
In embodiments of the present invention, the quantity of second user is multiple, obtains multiple and different target labels.These targets
Some in label are, more can accurately reflect first user the characteristics of more related to the first user, some blips may be with
First End-user relevance is smaller, distributes to the first use with the biggish target labels of the first End-user relevance for this reason, it may be necessary to select
Family, so that the characteristics of label for first user's extension more meets the first user.Second user belonging to target labels
Quantity is number of users, and the number of users of target labels, which reflects how many second user and the first user, has the target mark
Label, because of similar user with the characteristics of second user and the first user, thus the phase of the number of users of target labels and the first user
Closing property is positively correlated.
About step 206 specific implementation there are many, for example, determining that the most target labels of number of users are extension
Label；The target labels for determining that number of users is greater than preset quantity are extension tag etc..
Alternatively, enumerating one of specific example below to step 206:
It first obtains and chooses quantity, then, determine that quantity is equal to the expansion for choosing quantity from multiple and different target labels
Open up label.Wherein, the number of users of extension tag is greater than the number of users of remaining label, which is multiple different
Label in target labels other than extension tag.
There are many implementations of the specific example, for example, to multiple target labels obtained in step 204 according to user
Quantity carries out sequence from high to low, and selecting arrangement position for the forward N number of label of selection quantity is extension tag.Wherein, it selects
Access amount can be the quantity of user's input.In this way, user can set the selection number being defined to the quantity that label expands
Amount obtains the label for choosing quantity extension with descending.For example, user set choose quantity be 1, then processing equipment be return
The most target labels of number of users are as extension tag.
In multiple and different target labels, the correlation of the extension tag that obtains through the above way and the first user are more
Greatly, thus the characteristics of extension tag can more reflect the first user.
Step 207: distributing extension tag for the first user.
After getting extension tag.The extension tag can be distributed for the first user.Distribution, which refers to, assigns the extension tag
To the first user.For example, adding the extension tag again on the basis of the list of labels that the first user included originally.In this way,
Realization effectively extends the label of the first user, and the label that extension obtains, because of the phase of the first user and second user
Like property, the extension tag is enabled to react the attribute of the first user, so as to have using the extension tag to the first user
The operation of effect.
It is appreciated that in the embodiment that has of the present invention, step 205 and step 206 can not be executed, but be directly the
One user distributes target labels.
It is appreciated that step 206 can be executed by other specific implementations in the embodiment that the present invention has,
I.e. according to screening conditions are preset, extension tag is determined from multiple and different target labels.Number of users is the default screening
One of condition.
In conclusion obtaining the label of the first user and the label of second user, wherein the label of the first user and second
It include identical label in the label of user.Then, target labels, target labels first are determined from the label of second user
The label that the label of user does not include, to distribute target labels for the first user.Because the first user and second user include phase
With label thus can be by the label of the first user and second user so the first user and second user have similitude
Label is associated, thus, include by second user and target labels that the first user does not include are determined, to distribute to
One user realizes the extension to the first user tag.Because the first user and second user have similitude, the first user passes through
The characteristics of target labels that such mode obtains meet the first user.To, the method for the embodiment of the present invention, from being collected into
The obtained label of data it is less, thus when the characteristics of cannot reflect the first user comprehensively, the label of second user can be passed through
Data expand the label of the first user, are comprehensively described with realizing to the first user.
Fig. 3 is a kind of structural schematic diagram of label processing device provided in an embodiment of the present invention, which can
For executing above-mentioned Fig. 1 and label processing method shown in Fig. 2, with reference to above-described content, refering to Fig. 3, the present invention is implemented
A kind of label processing device of example, comprising:
Acquiring unit 301, for obtaining the label of the first user and the label of second user, the label of the first user and
It include identical label in the label of two users；
First determination unit 302, for determining that target labels, target labels are the first user from the label of second user
The label label that does not include；
Allocation unit 303, for distributing target labels for the first user.
Optionally,
The quantity of second user be it is multiple,
First determination unit 302, be also used to from the label of multiple second users determine target labels, with obtain it is multiple not
Same target labels；
The label processing device of the embodiment of the present invention further includes computing unit 304 and the second determination unit 305；
Computing unit 304, for calculating the number of users of second user belonging to each target labels；
Second determination unit 305, for determining extension mark from multiple and different target labels according to number of users
Label；
Allocation unit 303 is also used to distribute extension tag for the first user.
Optionally,
Second determination unit 305, including quantity obtain module 306 and extension determining module 307；
Quantity obtains module 306, chooses quantity for obtaining；
Determining module 307 is extended, for determining that quantity is equal to the expansion of selection quantity from multiple and different target labels
Open up label, wherein the number of users of extension tag is greater than the number of users of remaining label, and remaining label is multiple and different target
Label in label other than extension tag.
Optionally,
Acquiring unit 301, including data acquisition module 308 and label determining module 309；
Data acquisition module 308, for obtaining the web browsing data of the first user and second user；
Label determining module 309 determines and first for the corresponding relationship according to preset web browsing data and label
The corresponding label of the web browsing data of user；
Label determining module 309, is also used to the corresponding relationship according to preset web browsing data and label, determines and the
The corresponding label of the web browsing data of two users.
Optionally,
The quantity of the label of first user is less than default classification thresholds, and the quantity of the label of second user is greater than or equal to pre-
If classification thresholds.
Optionally,
Label is for being identified the concern information of user.
In conclusion acquiring unit 301 obtains the label of the first user and the label of second user, wherein the first user
Label and second user label in include identical label.Then, the first determination unit 302 is from the label of second user
Determine target labels, target labels are the label that the label of the first user does not include, so that allocation unit 303 is the first user point
With target labels.Because the first user and second user include identical label, so the first user and second user are with similar
Property, the label of the label of the first user and second user can be associated thus, thus, include and the first use by second user
The target labels that family does not include are determined, to distribute to the first user, realize the extension to the first user tag.Because of first
User and second user have similitude, and the target labels that the first user obtains in this way meet the spy of the first user
Point.
The label processing device includes processor and memory, and above-mentioned acquiring unit, the first determination unit, distribution are single
Member, computing unit and second determination unit etc. store in memory as program unit, are stored in by processor execution
Above procedure unit in reservoir realizes corresponding function.
Include kernel in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
Or more, the label of extending user is carried out by adjusting kernel parameter.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flash RAM), memory include that at least one is deposited
Store up chip.
The embodiment of the invention provides a kind of storage mediums, are stored thereon with program, real when which is executed by processor
The existing label processing method, i.e. label processing method shown in the various embodiments described above.
The embodiment of the invention provides a kind of processor, the processor is for running program, wherein described program operation
Label processing method described in Shi Zhihang, i.e. label processing method shown in the various embodiments described above.
The embodiment of the invention provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor perform the steps of when executing program
Obtain the label of the first user and the label of second user, wherein the label of first user and described second
It include identical label in the label of user；
From the label of the second user determine target labels, the target labels be first user label not
Including label；
The target labels are distributed for first user.
Optionally, when the quantity of the second user is multiple, processor also performs the steps of when executing program
Determine target labels, from the label of multiple second users to obtain multiple and different target labels；
Calculate the number of users of second user belonging to each target labels；
According to the number of users, extension tag is determined from the plurality of different target labels；
The extension tag is distributed for first user.
Optionally, it is also performed the steps of when processor executes program
It obtains and chooses quantity；
Determine that quantity is equal to the extension tag for choosing quantity from the plurality of different target labels, wherein
The number of users of the extension tag is greater than the number of users of remaining label, and the residue label is the plurality of different target
Label in label other than the extension tag.
Optionally, it is also performed the steps of when processor executes program
Obtain the web browsing data of the first user and second user；
According to the corresponding relationship of preset web browsing data and label, the determining web browsing number with first user
According to corresponding label；
According to the corresponding relationship of preset web browsing data and label, the determining web browsing number with the second user
According to corresponding label.
Optionally,
The quantity of the label of first user is less than default classification thresholds, and the quantity of the label of the second user is greater than
Or it is equal to the default classification thresholds.
Optionally,
The label is for being identified the concern information of user.
Wherein, equipment herein can be server, PC, PAD, mobile phone etc..
Present invention also provides a kind of computer program products, when executing on data processing equipment, are adapted for carrying out just
The program code of beginningization there are as below methods step:
Obtain the label of the first user and the label of second user, the label of first user and the second user
It include identical label in label；
From the label of the second user determine target labels, the target labels be first user label not
Including label；
The target labels are distributed for first user.
Optionally, when the quantity of the second user is multiple, which, which is further adapted for executing initializing, has
The program code of following method and step:
Determine target labels, from the label of multiple second users to obtain multiple and different target labels；
Calculate the number of users of second user belonging to each target labels；
According to the number of users, extension tag is determined from the plurality of different target labels；
The extension tag is distributed for first user.
Optionally, which is further adapted for executing the program code of initialization there are as below methods step:,
It obtains and chooses quantity；
Determine that quantity is equal to the extension tag for choosing quantity from the plurality of different target labels, wherein
The number of users of the extension tag is greater than the number of users of remaining label, and the residue label is the plurality of different target
Label in label other than the extension tag.
Optionally, when the quantity of the second user is multiple, which, which is further adapted for executing initializing, has
The program code of following method and step:
Obtain the web browsing data of the first user and second user；
According to the corresponding relationship of preset web browsing data and label, the determining web browsing number with first user
According to corresponding label；
According to the corresponding relationship of preset web browsing data and label, the determining web browsing number with the second user
According to corresponding label.
Optionally,
The quantity of the label of first user is less than default classification thresholds, and the quantity of the label of the second user is greater than
Or it is equal to the default classification thresholds.
Optionally,
The label is for being identified the concern information of user.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (10)
1. a kind of label processing method characterized by comprising
Obtain the label of the first user and the label of second user, the label of first user and the label of the second user
In include identical label；
Determine that target labels, the target labels are that the label of first user does not include from the label of the second user
Label；
The target labels are distributed for first user.
2. the method according to claim 1, wherein
The quantity of the second user be it is multiple,
It is described that target labels are determined from the label of the second user, comprising:
Determine target labels, from the label of multiple second users to obtain multiple and different target labels；
It is described from the label of the second user determine target labels after, the method also includes:
Calculate the number of users of second user belonging to each target labels；
According to the number of users, extension tag is determined from the plurality of different target labels；
It is described to distribute the target labels for first user, comprising:
The extension tag is distributed for first user.
3. according to the method described in claim 2, it is characterized in that,
It is described according to the number of users, determine extension tag from the plurality of different target labels, comprising:
It obtains and chooses quantity；
Determine that quantity is equal to the extension tag for choosing quantity from the plurality of different target labels, wherein described
The number of users of extension tag is greater than the number of users of remaining label, and the residue label is the plurality of different target labels
In label other than the extension tag.
4. the method according to claim 1, wherein
The label of the label for obtaining the first user and second user, comprising:
Obtain the web browsing data of the first user and second user；
According to the corresponding relationship of preset web browsing data and label, the determining web browsing data pair with first user
The label answered；
According to the corresponding relationship of preset web browsing data and label, the determining web browsing data pair with the second user
The label answered.
5. the method according to claim 1, wherein
The quantity of the label of first user is less than default classification thresholds, and the quantity of the label of the second user is greater than or waits
In the default classification thresholds.
6. method according to any one of claims 1 to 5, which is characterized in that
The label is for being identified the concern information of user.
7. a kind of label processing device characterized by comprising
Acquiring unit, for obtaining the label of the first user and the label of second user, the label of first user and described
It include identical label in the label of second user；
First determination unit, for determining that target labels, the target labels are described the from the label of the second user
The label that the label of one user does not include；
Allocation unit, for distributing the target labels for first user.
8. device according to claim 7, which is characterized in that
The quantity of the second user be it is multiple,
First determination unit is also used to determine target labels from the label of multiple second users, multiple to obtain
Different target labels；
Described device further includes computing unit and the second determination unit；
The computing unit, for calculating the number of users of second user belonging to each target labels；
Second determination unit, for determining to expand from the plurality of different target labels according to the number of users
Open up label；
The allocation unit is also used to distribute the extension tag for first user.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment execute such as label processing method of any of claims 1-6.
10. a kind of processor, which is characterized in that the processor is for running program, wherein executed such as when described program is run
Label processing method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710818950.9A CN110069695A (en) | 2017-09-12 | 2017-09-12 | Label processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710818950.9A CN110069695A (en) | 2017-09-12 | 2017-09-12 | Label processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110069695A true CN110069695A (en) | 2019-07-30 |
Family
ID=67364568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710818950.9A Pending CN110069695A (en) | 2017-09-12 | 2017-09-12 | Label processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110069695A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598091A (en) * | 2019-08-09 | 2019-12-20 | 阿里巴巴集团控股有限公司 | User tag mining method, device, server and readable storage medium |
| CN110825911A (en) * | 2019-09-25 | 2020-02-21 | 云知声智能科技股份有限公司 | Content display method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184199A (en) * | 2011-04-22 | 2011-09-14 | 北京志腾新诺科技有限公司 | Network information recommending method and system |
| CN103810192A (en) * | 2012-11-09 | 2014-05-21 | 腾讯科技（深圳）有限公司 | User interest recommending method and device |
| US20140337272A1 (en) * | 2012-09-21 | 2014-11-13 | Sas Institute Inc. | Systems and methods for interactive displays based on associations for machine-guided rule creation |
| CN106649347A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Interest information identification method and apparatus |
| CN106649316A (en) * | 2015-10-29 | 2017-05-10 | 北京国双科技有限公司 | Video pushing method and device |
-
2017
- 2017-09-12 CN CN201710818950.9A patent/CN110069695A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184199A (en) * | 2011-04-22 | 2011-09-14 | 北京志腾新诺科技有限公司 | Network information recommending method and system |
| US20140337272A1 (en) * | 2012-09-21 | 2014-11-13 | Sas Institute Inc. | Systems and methods for interactive displays based on associations for machine-guided rule creation |
| CN103810192A (en) * | 2012-11-09 | 2014-05-21 | 腾讯科技（深圳）有限公司 | User interest recommending method and device |
| CN106649316A (en) * | 2015-10-29 | 2017-05-10 | 北京国双科技有限公司 | Video pushing method and device |
| CN106649347A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Interest information identification method and apparatus |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598091A (en) * | 2019-08-09 | 2019-12-20 | 阿里巴巴集团控股有限公司 | User tag mining method, device, server and readable storage medium |
| CN110825911A (en) * | 2019-09-25 | 2020-02-21 | 云知声智能科技股份有限公司 | Content display method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Esmeli et al. | Towards early purchase intention prediction in online session based retailing systems | |
| CN109688469B (en) | Advertisement display method and device | |
| US10977711B1 (en) | Artificial intelligence system with hierarchical machine learning for interaction session optimization | |
| US20190244253A1 (en) | Target identification using big data and machine learning | |
| US20130263181A1 (en) | Systems and methods for defining video advertising channels | |
| CN108563680A (en) | Resource recommendation method and device | |
| US20100082428A1 (en) | Display advertising inventory estimation | |
| CN109213802B (en) | User portrait construction method and device, terminal and computer readable storage medium | |
| CN108777701A (en) | A kind of method and device of determining receiver | |
| CN110392155B (en) | Notification message display and processing method, device and equipment | |
| CN111008335B (en) | Information processing method, device, equipment and storage medium | |
| CN104965863B (en) | A kind of clustering objects method and apparatus | |
| CN105678335B (en) | It estimates the method, apparatus of clicking rate and calculates equipment | |
| CN108550046A (en) | A kind of resource and market recommendation method, apparatus and electronic equipment | |
| CN109598171A (en) | A kind of data processing method based on two dimensional code, apparatus and system | |
| CN106909567B (en) | Data processing method and device | |
| CN106649347A (en) | Interest information identification method and apparatus | |
| CN110069695A (en) | Label processing method and device | |
| US20220366299A1 (en) | Provisioning interactive content based on predicted user-engagement levels | |
| CN112989182B (en) | Information processing method, information processing device, information processing apparatus, and storage medium | |
| CN109471639A (en) | The monitoring method and device in a kind of application downloading source | |
| WO2020162833A1 (en) | Method and system for generating content data | |
| CN106897412A (en) | A kind of method and apparatus for recommending associated application based on intended application | |
| US20220335331A1 (en) | Method and system for behavior vectorization of information de-identification | |
| Coba et al. | Replicating and improving Top-N recommendations in open source packages |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100080 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: Beijing Guoshuang Technology Co.,Ltd. Address before: 100086 Beijing city Haidian District Shuangyushu Area No. 76 Zhichun Road cuigongfandian 8 layer A Applicant before: Beijing Guoshuang Technology Co.,Ltd. |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190730 |