CN110097407A - A kind of generation method and system of user tag - Google Patents
A kind of generation method and system of user tag Download PDFInfo
- Publication number
- CN110097407A CN110097407A CN201910388399.8A CN201910388399A CN110097407A CN 110097407 A CN110097407 A CN 110097407A CN 201910388399 A CN201910388399 A CN 201910388399A CN 110097407 A CN110097407 A CN 110097407A
- Authority
- CN
- China
- Prior art keywords
- data
- label
- user
- keyword
- access data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
Abstract
The present invention provides a kind of generation method of user tag and systems.The generation method of the user tag includes: to collect the access data of user on multiple platforms；Extract the keyword of the access data；User tag is generated according to the keyword of the access data.The generation method of user tag of the present invention targetedly can carry out operation push, advertisement pushing, after-sale service etc. to different users according to user tag, operation push and advertisement pushing is avoided to will cause unnecessary interference to certain customers, customer complaint is reduced, to improve user experience.
Description
Technical field
The present invention relates to Internet technical fields, in particular to the generation method and system of a kind of user tag.
Background technique
With the fast development of internet, especially electric business, more and more people have been accustomed to new by internet browsing
It hears, watch movie, do shopping.
At present internet platform, businessman user information there was only the essential information filled in when registering, without other important letters
Breath, such as occupation, income, age etc., so being one to each user when doing operation push, advertisement pushing, after-sale service
Benevolence is treated as, is not different and treats.This make operation push and advertisement pushing may be junk information for certain customers, to
Family will cause unnecessary interference, reduce user experience.
It can be seen that researching and developing a kind of generation method of the user tag that can effectively solve the above problem and system is current urgency
Technical problem to be solved.
Summary of the invention
Problems solved by the invention is when doing operation push, advertisement pushing, after-sale service, and it is unnecessary to will cause to user
Interference, reduce user experience.
To solve the above problems, the present invention provides a kind of generation method of user tag, which is characterized in that including following step
It is rapid:
S100, the access data of user on multiple platforms are collected；
S200, the keyword for extracting the access data；
S300, user tag is generated according to the keyword of the access data.
In this way, operation push, advertisement pushing, after sale targetedly can be carried out to different users according to user tag
Service etc. avoids operation push and advertisement pushing from will cause unnecessary interference to certain customers, customer complaint is reduced, to mention
High user experience.
Optionally, the step S200 extracts the keyword of the access data, comprising:
S210, valid data are filtered out from the access data；
S220, the pass for extracting the valid data from the multiple platform according to different platform keyword-extraction rules
Key word；
If S230, the keyword for not extracting the valid data from the multiple platform, according to public keyword
Extracting rule extracts the keyword of the valid data.
In this way, can first filter out invalid data when extracting the keyword of access data, reduce extraction workload, mention
High efficiency；And keyword targetedly is extracted by different keyword-extraction rules, more accurately, science, it ensure that visit
Ask the authenticity and reliability of data key words.
Optionally, the step S210 filters out valid data from the access data, comprising:
S211, according to the type of the access data, data are carried out to the access data of the multiple platform respectively
Classification；
S212, by it is sorted it is described access data format conversion be unified specification；
S213, valid data are filtered out from the access data after unified specification.
In this way, when carrying out valid data screening first classification and unified specification can be carried out to access data, convenient for same
The access data of type carry out unified screening, optimize screening process, improve screening efficiency.
Optionally, the step S300 generates user tag according to the keyword of the access data, comprising:
S310, by it is described access data keyword be compared with the keyword of default label, judge the two whether phase
Together；
S320, if so, by the default label be set as it is described access data specified label；If it is not, then will be described
The key combination of access data generates the specified label of the access data；
S330, the quantity for counting every group of user data respectively, and the quantity of user data described in calculating separately every group is in institute
State the accounting in the total quantity of access data, wherein the user data is to specify label identical described in the access data
Data set；
S340, the user data according to multiple groups accounting and multiple groups described in user data label attribute generate user
Label.
In this way, user tag can be generated according to the keyword of access data.
Optionally, the step S340, the mark of user data described in the accounting and multiple groups of the user data according to multiple groups
The attribute of label generates user tag, comprising:
S341, the accounting of user data described in multiple groups is compared respectively with default ratio, judges the user data
Accounting whether be not less than the default ratio；
If the accounting of S342, the user data is not less than the default ratio, the label of the user data is judged
Classification be single choice class or multiselect class；
If the classification of the label of S343, the user data is multiselect class, the label deposit of the user data is extracted
In label pond；If the classification of the label of the user data is single choice class, the attribute of the label of the user data is judged
Whether type is unique；
If S344, unique, the label for extracting the user data is stored in the label pond；If not unique, judge
Whether the accounting size of the identical multiple user data of label classification is identical；
S345, if so, the label for extracting end data is stored in the label pond, wherein the end data are mark
It signs in the identical multiple user data of classification, the data finally received；If it is not, it is identical then to extract label classification
In multiple user data, the label of the maximum user data of accounting is stored in the label pond；
S346, the label in the label pond is set as user tag.
This way it is possible to avoid occurring multiple single choice class labels in the user tag finally obtained, to further increase life
At the accuracy and correctness of user tag.
Optionally, the range of the default ratio is 8%-12%.
Default ratio within the scope of this, that is, can guarantee label pond in label it is comprehensive, in turn avoid the label of redundancy.
Compared with the existing technology, user tag generation method of the present invention has the advantage that
User tag generation method of the present invention can according to user tag targetedly to different users into
Row operation push, advertisement pushing, after-sale service etc. avoid operation push and advertisement pushing from will cause certain customers unnecessary
Interference reduces customer complaint, to improve user experience.
Another object of the present invention is to provide a kind of user tags to generate system, to solve doing operation push, advertisement
When push, after-sale service, the problem of will cause unnecessary interference to user, reduce user experience.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A kind of user tag generation system characterized by comprising
Data collection module is used to collect the access data of user on multiple platforms；
Data analysis unit is used to extract the keyword of the access data；
User tag generation unit is used to generate user tag according to the keyword of the access data.
Optionally, the data analysis unit includes:
Data filtering module is used to filter out valid data from the access data；
Platform keyword-extraction module is used for according to different platform keyword-extraction rules from the multiple platform
Extract the keyword of the valid data；
Public keyword extraction module, if being used to not extract the key of the valid data from the multiple platform
Word then extracts the keyword of the valid data according to public keyword extracting rule.
Optionally, the data filtering module includes:
Data classification submodule is used for the type according to the access data, respectively to described in the multiple platform
It accesses data and carries out data classification；
Format transform subblock is used to the format conversion of the sorted access data be unified specification；
Data screening submodule is used to filter out valid data from the access data after unified specification.
Optionally, the user tag generation unit includes:
Keyword comparison module is used to compare the keyword of the keyword and default label of the access data
It is right；
Data label generation module, if the keyword for being used for the access data is identical as the keyword of default label,
The default label is then set to the specified label of the access data；
Computing module, is used to count the quantity of multiple user data respectively, and calculates separately multiple user data
Quantity it is described access data total quantity in accounting, wherein the user data be the access data described in finger
Identical data are signed in calibration；
User tag generation module is used for according to the accountings of multiple user data and multiple user data
The attribute of label generates user tag.
Optionally, the user tag generation unit further include:
Key combination module, if the keyword for being used for the access data is different from the keyword of default label,
The key combination of the access data is generated to the specified label of the access data.
The generation system of the user tag and the generation method of above-mentioned user tag are possessed compared with the existing technology
Advantage is identical, and details are not described herein.
Detailed description of the invention
Fig. 1 is the flow chart of the generation method of user tag in the embodiment of the present invention；
Fig. 2 is the flow chart of step S200 in the embodiment of the present invention；
Fig. 3 is the flow chart of step S210 in the embodiment of the present invention；
Fig. 4 is the flow chart of step S300 in the embodiment of the present invention；
Fig. 5 is the flow chart of step S340 in the embodiment of the present invention；
Fig. 6 is the schematic diagram of the generation system of user tag in the embodiment of the present invention；
Fig. 7 is the schematic diagram of data analysis unit in the embodiment of the present invention；
Fig. 8 is the schematic diagram of data filtering module in the embodiment of the present invention；
Fig. 9 is the schematic diagram of user tag generation unit in the embodiment of the present invention；
Figure 10 is the schematic diagram of user tag generation module in the embodiment of the present invention.
Description of symbols:
10- data collection module, 20- data analysis unit, 21- data filtering module, 211- data classification submodule,
212- data screening submodule, 213- format conversion submodule, 22- platform keyword-extraction module, 23- public keyword extract
Module, 30- user tag generation unit, 31- keyword comparison module, 32- data label generation module, 33- computing module,
34- user tag generation module, the first judging submodule of 341-, 342- second judgment submodule, 343- tag extraction submodule,
Submodule, 35- key combination module is arranged in 344- third judging submodule, 345- label.
Specific embodiment
To make the above purposes, features and advantages of the invention more obvious and understandable, with reference to the accompanying drawing to the present invention
Specific embodiment be described in detail.
In the description of the present invention, it should be noted that the instruction such as term " on ", "lower", "left", "right", "high", " low "
Direction or positional relationship be based on the orientation or positional relationship shown in the drawings, be merely for convenience of description the present invention and simplification retouch
It states, rather than the device of indication or suggestion meaning must have a particular orientation, be constructed and operated in a specific orientation, therefore not
It can be interpreted as limitation of the present invention.
As shown in connection with fig. 1, the present embodiment provides a kind of generation methods of user tag, comprising the following steps:
Step S100, the access data of user on multiple platforms are collected；
In the step s 100, the access data of user are collected on multiple platforms by cell-phone number, wherein platform include but
It is not limited to shopping network, audio-video net, social network and News Network etc..Such as using reptile instrument in microblogging, Baidu, the heat such as know
The platform of door according to cell-phone number searching user's information, comment on, publish an article, pay close attention to the data such as topic.User is in access shopping network
When platform, the operation on platform can all generate relevant operation log, be stored in elk Log Analysis System, these operations
Log include but is not limited to shopping network platform basic function usage log, interface usage log, electric business under single log, message push away
Send click logs, intelligent function usage log etc.；When accessing audio-video net platform, the access data of collection include but not user
The users such as comment, barrage, downloading, collection or the sharing that the video ID and user for being limited to user's access are carried out for the video
Behavior.
Step S200, the keyword of the access data is extracted；
Specifically, being mentioned using the participle function of elasticsearch (full-text search engine of distributed multi-user ability)
Take out the keyword of access data.In addition, it is necessary to illustrate yes, above and hereinafter described keyword all refers to one
The phrase of a word or multiple words.
Step S300, user tag is generated according to the keyword of the access data.
The generation method of user tag in the present embodiment, can be according to user tag targetedly to different users
Operation push, advertisement pushing, after-sale service etc. are carried out, avoids operation push and advertisement pushing from will cause certain customers unnecessary
Interference, reduce customer complaint, to improve user experience.
Optionally, as shown in connection with fig. 2, step S200 is specifically included:
Step S210, valid data are filtered out from the access data；
Data screening rule list is pre-set in step S210, in database, if access data keyword with
Keyword match in data screening rule list just directly sets invalid data for this access data.Optionally, if number
It is subsequent the data to be handled when according to being judged as invalid, directly delete.And those are not set to invalid data
Data be valid data.Wherein, the keyword for needing to screen is provided in data screening rule list, for example, screening is not literary
When bright comment, phrase relevant to dirty word, anti-revolutionary, passiveness etc. can be set in data screening rule list；In screening rubbish
When rubbish advertisement, phrase relevant to wechat, Taobao, web site url, discounting etc. can be set in data screening rule list.
Step S220, the valid data are extracted from the multiple platform according to different platform keyword-extraction rules
Keyword；
In step S220, the access data of different platform can go extraction in the keyword extraction system of corresponding platform crucial
Word, such as, the data of shopping platform can go shopping and extract keyword, after sale the data meeting of platform in net keyword extraction system
It goes to extract keyword etc. in keyword extraction system after sale.The keyword of each platform is previously provided with corresponding keyword and mentions
Rule is taken, and the platform keyword-extraction rules of different platform are different, for example, can set in the keyword-extraction rules of shopping platform
It sets marque, price, quantity, shipping address etc. then, fault type, phenomenon of the failure can be set in keyword-extraction rules after sale
Deng.
If step S230, not extracting the keyword of the valid data from the multiple platform, according to public pass
Key word extracting rule extracts the keyword of the valid data.
In step S230, if a certain valid data do not extract keyword according to platform keyword-extraction rules,
Then keyword can be extracted according to public keyword extracting rule.If according to public keyword extracting rule again without extraction
To keyword, just data are transferred in backup database, when resetting platform keyword-extraction rules, then from Backup Data
The keyword of access data is extracted in library.
In this way, the present embodiment can first filter out nothing when extracting the keyword of access data by step S210-S230
Data are imitated, extraction workload is reduced, improves efficiency；And key targetedly is extracted by different keyword-extraction rules
Word, more accurately, science, ensure that access data key words authenticity and reliability.
Optionally, as shown in connection with fig. 3, step S210 is specifically included:
Step S211, according to the type of the access data, the access data of the multiple platform are carried out respectively
Data classification；
Wherein, the access data of multiple platforms can be first sent in Message Queuing Services, and different types of data can be sent
To different message subjects to data classification, such as daily record data can be sent to log topic, electric business order data can be sent
To electric business order theme etc., system can subscribe to the message subject of Message Queuing Services, as long as there is access data to be sent to message team
Column service, system will obtain the data.
It step S212, is unified specification by the format conversion of the sorted access data；
Step S213, valid data are filtered out from the access data after unified specification.
In this way, by step S211-S213, the present embodiment when carrying out valid data screening, can first to access data into
Row classification and unified specification optimize screening process, improve sieve convenient for carrying out unified screening to same type of access data
Select efficiency.
Optionally, as shown in connection with fig. 4, step S300 is specifically included:
Step S310, the keyword of the access data is compared with the keyword of default label, judges that the two is
It is no identical；
Wherein, presetting label is pre-set label, and keyword can real-time update.
Step S320, if so, setting the default label on the specified label of the access data；If it is not, then will
The key combination of the access data generates the specified label of the access data；
Wherein, the keyword of each access data is compared with the keyword of each default label, if a certain
The keyword that item accesses data is identical as some default keyword of label, then this is preset label and be arranged as this access data
Specified label.Such as presetting the keyword of label " male " is " shaver ", if the keyword of a certain item access data
It also is " shaver " that then the specified label of this access data is " male ".
Step S330, the quantity of every group of user data is counted respectively, and the quantity of user data described in calculating separately every group
Accounting in the total quantity of the access data, wherein the user data is that label is specified described in the access data
The set of identical data；
For example, this 10 access data are one group of number of users if the access data that specified label is " male " have 10
According to.
Step S340, according to multiple groups, the attribute of the label of user data described in the accounting and multiple groups of user data is generated
User tag.
In this way, the present embodiment can generate user tag according to the keyword of access data by step S310-S340.
Optionally, as shown in connection with fig. 5, step S340 is specifically included:
Step S341, the accounting of multiple user data is compared respectively with default ratio, judges the user
Whether the accounting of data is not less than the default ratio；
If the accounting of step S342, the described user data is not less than the default ratio, the user data is judged
The classification of label is single choice class or multiselect class；
Wherein, single choice class label refers to that tag attributes only have a kind of possible label, such as gender (can only be male and female
One of), age level (can only be one of teenager, adult, the elderly), income (can only be in high, medium and low
One kind) etc., and multiselect class label refers to that tag attributes can be there are many possible label, such as occupation (can have simultaneous
Duty), hobby (can have multiple hobbies) etc..
If the classification of the label of step S343, the described user data is multiselect class, the label of the user data is extracted
It is stored in label pond；If the classification of the label of the user data is single choice class, the category of the label of the user data is judged
Whether the type of property is unique；
If step S344, unique, the label for extracting the user data is stored in the label pond；If not unique,
Compare the accounting size of the identical multiple user data of label classification；
Step S345, if so, the label for extracting end data is stored in the label pond, wherein the end data
For the data in the identical multiple user data of label classification, finally received；If it is not, then extracting label classification phase
In same multiple user data, the label of the maximum user data of accounting is stored in the label pond；
Step S346, the label in the label pond is set as user tag.
It, can be to avoid occurring multiple single choice categories in the user tag finally obtained in this way, by step S341-S346
Label, to further increase the accuracy and correctness for generating user tag.
Optionally, the range for presetting ratio is 8%-12%.If default ratio is too small, label pond can have excessively superfluous
Remaining label；If default ratio is too big, the range that label covers in label pond not can guarantee.Through actual verification, within the scope of this
Ratio is preset, i.e., label is comprehensive in certifiable label pond, in turn avoids the label of redundancy.
As shown in connection with fig. 6, the present embodiment also provides a kind of user tag generation system, comprising:
Data collection module 10 is used to collect the access data of user on multiple platforms；
Data analysis unit 20 is used to extract the keyword of the access data；
User tag generation unit 30 is used to generate user tag according to the keyword of the access data.
The generation system of user tag in the present embodiment can be according to user tag targetedly to different users
Operation push, advertisement pushing, after-sale service etc. are carried out, avoids operation push and advertisement pushing from will cause certain customers unnecessary
Interference, reduce customer complaint, to improve user experience.
Optionally, as shown in connection with fig. 7, data analysis unit 20 includes:
Data filtering module 21 is used to filter out valid data from the access data；
Platform keyword-extraction module 22 is used for according to different platform keyword-extraction rules from the multiple platform
The middle keyword for extracting the valid data；
Public keyword extraction module 23, if being used to not extract the pass of the valid data from the multiple platform
Key word then extracts the keyword of the valid data according to public keyword extracting rule.
In this way, the present embodiment can first filter out invalid data, reduce extraction work when extracting the keyword of access data
It measures, improves efficiency；And keyword targetedly is extracted by different keyword-extraction rules, more accurately, science, protect
The authenticity and reliability of access data key words are demonstrate,proved.
Optionally, as shown in connection with fig. 8, data filtering module 21 includes:
Data classification submodule 211 is used for the type according to the access data, respectively to the institute of the multiple platform
It states access data and carries out data classification；
Format transform subblock 212 is used to the format conversion of the sorted access data be unified specification；
Data screening submodule 213 filters out valid data from the access data after unified specification.
In this way, the present embodiment when carrying out valid data screening, first can carry out classification and unified specification to access data, just
In carrying out unified screening to same type of access data, screening process is optimized, screening efficiency is improved.
Optionally, as shown in connection with fig. 9, user tag generation unit 30 includes:
Keyword comparison module 31 is used to compare the keyword of the keyword and default label of the access data
It is right；
Data label generation module 32, if being used for the keyword phase of the keyword and default label of the access data
Together, then the default label is set to the specified label of the access data；
Computing module 33, is used to count the quantity of every group of user data respectively, and number of users described in calculating separately every group
According to quantity it is described access data total quantity in accounting, wherein the user data be the access data described in
The set of the specified identical data of label；
User tag generation module 34, be used for the user data according to multiple groups accounting and multiple user data
Label attribute generate user tag.
In this way, user tag can be generated according to the keyword of access data.
Optionally, as shown in connection with fig. 9, user tag generation unit 30 further include:
Key combination module 35, if the keyword for being used for the access data is different from the keyword of default label,
The key combination of the access data is then generated to the specified label of the access data.
Optionally, as shown in connection with fig. 10, user tag generation module 34 includes:
First judging submodule 341 is used to respectively compare the accounting of multiple user data with default ratio
Compared with judging whether the accounting of the user data is not less than the default ratio；
Second judgment submodule 342, if the accounting for being used for the user data judges not less than the default ratio
The classification of the label of the user data is single choice class or multiselect class；
Tag extraction submodule 343, if being used for the classification of the label of the user data for multiselect class, described in extraction
In the label deposit label pond of user data；Third judging submodule 344, if being used for the classification of the label of the user data
For single choice class, then judge whether the type of the attribute of the label of the user data is unique；
Tag extraction submodule 343 extracts if the type for being also used to the attribute of the label of the user data is unique
The label of the user data is stored in the label pond；If not unique, the identical multiple users of label classification are judged
Whether the accounting size of data is identical；
Tag extraction submodule 343, if being also used to the accounting size of the identical multiple user data of label classification
Identical, then the label for extracting end data is stored in the label pond, wherein the end data are that label classification is identical more
In a user data, the data that finally receives；If the accounting of the identical multiple user data of label classification
It is of different sizes, then it extracts in the identical multiple user data of label classification, the label of the maximum user data of accounting
It is stored in the label pond；
Submodule 345 is arranged in label, is used to the label in the label pond being set as user tag.
In this way, the present embodiment can extract the label of different classes of user data respectively.
Although present disclosure is as above, present invention is not limited to this.Anyone skilled in the art are not departing from this
It in the spirit and scope of invention, can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
Subject to the range of restriction.
Claims (11)
1. a kind of generation method of user tag, which comprises the following steps:
S100, the access data of user on multiple platforms are collected；
S200, the keyword for extracting the access data；
S300, user tag is generated according to the keyword of the access data.
2. generation method according to claim 1, which is characterized in that the step S200 extracts the access data
Keyword, comprising:
S210, valid data are filtered out from the access data；
S220, the key for extracting the valid data from the multiple platform according to different platform keyword-extraction rules
Word；
If S230, the keyword for not extracting the valid data from the multiple platform, are extracted according to public keyword
The keyword of valid data described in Rule Extraction.
3. generation method according to claim 2, which is characterized in that the step S210 is sieved from the access data
Select valid data, comprising:
S211, according to the type of the access data, data classification is carried out to the access data of the multiple platform respectively；
S212, by it is sorted it is described access data format conversion be unified specification；
S213, valid data are filtered out from the access data after unified specification.
4. generation method according to claim 1, which is characterized in that the step S300, according to the access data
Keyword generates user tag, comprising:
S310, the keyword of the access data is compared with the keyword of default label, judges whether the two is identical；
S320, if so, by the default label be set as it is described access data specified label；If it is not, then by the access
The key combination of data generates the specified label of the access data；
S330, the quantity for counting every group of user data respectively, and the quantity of user data described in calculating separately every group is in the visit
Ask the accounting in the total quantity of data, wherein the user data is that the identical number of label is specified described in the access data
According to set；
S340, the user data according to multiple groups accounting and multiple groups described in user data label attribute generate user mark
Label.
5. generation method according to claim 4, which is characterized in that the step S340, the number of users according to multiple groups
According to accounting and multiple groups described in user data label attribute generate user tag, comprising:
S341, the accounting of user data described in multiple groups is compared respectively with default ratio, judges accounting for for the user data
Than whether being not less than the default ratio；
If the accounting of S342, the user data is not less than the default ratio, the class of the label of the user data is judged
It Wei not single choice class or multiselect class；
If the classification of the label of S343, the user data is multiselect class, the label deposit label of the user data is extracted
Chi Zhong；If the classification of the label of the user data is single choice class, the type of the attribute of the label of the user data is judged
It is whether unique；
If S344, unique, the label for extracting the user data is stored in the label pond；If not unique, label is judged
Whether the accounting size of the identical multiple user data of classification is identical；
S345, if so, the label for extracting end data is stored in the label pond, wherein the end data are tag class
In not identical multiple user data, the data that finally receives；If it is not, it is identical multiple then to extract label classification
In the user data, the label of the maximum user data of accounting is stored in the label pond；
S346, the label in the label pond is set as user tag.
6. generation method according to claim 5, which is characterized in that the range of the default ratio is 8%-12%.
7. a kind of user tag generates system characterized by comprising
Data collection module (10) is used to collect the access data of user on multiple platforms；
Data analysis unit (20) is used to extract the keyword of the access data；
User tag generation unit (30) is used to generate user tag according to the keyword of the access data.
8. generation system according to claim 7, which is characterized in that the data analysis unit (20) includes:
Data filtering module (21) is used to filter out valid data from the access data；
Platform keyword-extraction module (22) is used for according to different platform keyword-extraction rules from the multiple platform
Extract the keyword of the valid data；
Public keyword extraction module (23), if being used to not extract the key of the valid data from the multiple platform
Word then extracts the keyword of the valid data according to public keyword extracting rule.
9. generation system according to claim 8, which is characterized in that the data filtering module (21) includes:
Data classification submodule (211) is used for the type according to the access data, respectively to described in the multiple platform
It accesses data and carries out data classification；
Format transform subblock (212) is used to the format conversion of the sorted access data be unified specification；
Data screening submodule (213) is used to filter out valid data from the access data after unified specification.
10. generation system according to claim 7, which is characterized in that the user tag generation unit (30) includes:
Keyword comparison module (31) is used to compare the keyword of the keyword and default label of the access data
It is right；
Data label generation module (32), if the keyword for being used for the access data is identical as the keyword of default label,
The default label is then set to the specified label of the access data；
Computing module (33), is used to count the quantity of multiple user data respectively, and calculates separately multiple user data
Quantity it is described access data total quantity in accounting, wherein the user data be the access data described in finger
Identical data are signed in calibration；
User tag generation module (34) is used for according to the accountings of multiple user data and multiple user data
The attribute of label generates user tag.
11. user tag according to claim 8 or claim 9 generates system, which is characterized in that the user tag generation unit
(30) further include:
Key combination module (35), if the keyword for being used for the access data is different from the keyword of default label,
The key combination of the access data is generated to the specified label of the access data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910388399.8A CN110097407A (en) | 2019-05-10 | 2019-05-10 | A kind of generation method and system of user tag |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910388399.8A CN110097407A (en) | 2019-05-10 | 2019-05-10 | A kind of generation method and system of user tag |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110097407A true CN110097407A (en) | 2019-08-06 |
Family
ID=67447607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910388399.8A Pending CN110097407A (en) | 2019-05-10 | 2019-05-10 | A kind of generation method and system of user tag |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097407A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111163078A (en) * | 2019-12-26 | 2020-05-15 | 珠海格力电器股份有限公司 | Network link interception method, device, equipment and medium |
| CN111401995A (en) * | 2020-03-09 | 2020-07-10 | 成都欧魅时尚科技有限责任公司 | System for realizing automatic material preparation by utilizing internet advertisement |
| CN111932315A (en) * | 2020-09-02 | 2020-11-13 | 上海优扬新媒信息技术有限公司 | Data display method and device, electronic equipment and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100036888A1 (en) * | 2008-08-06 | 2010-02-11 | International Business Machines Corporation | Method and system for managing tags |
| CN103218355A (en) * | 2012-01-18 | 2013-07-24 | 腾讯科技（深圳）有限公司 | Method and device for generating tags for user |
| CN107463711A (en) * | 2017-08-22 | 2017-12-12 | 山东浪潮云服务信息科技有限公司 | A kind of tag match method and device of data |
| CN109241529A (en) * | 2018-08-29 | 2019-01-18 | 中国联合网络通信集团有限公司 | The determination method and apparatus of viewpoint label |
-
2019
- 2019-05-10 CN CN201910388399.8A patent/CN110097407A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100036888A1 (en) * | 2008-08-06 | 2010-02-11 | International Business Machines Corporation | Method and system for managing tags |
| CN103218355A (en) * | 2012-01-18 | 2013-07-24 | 腾讯科技（深圳）有限公司 | Method and device for generating tags for user |
| CN107463711A (en) * | 2017-08-22 | 2017-12-12 | 山东浪潮云服务信息科技有限公司 | A kind of tag match method and device of data |
| CN109241529A (en) * | 2018-08-29 | 2019-01-18 | 中国联合网络通信集团有限公司 | The determination method and apparatus of viewpoint label |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111163078A (en) * | 2019-12-26 | 2020-05-15 | 珠海格力电器股份有限公司 | Network link interception method, device, equipment and medium |
| CN111401995A (en) * | 2020-03-09 | 2020-07-10 | 成都欧魅时尚科技有限责任公司 | System for realizing automatic material preparation by utilizing internet advertisement |
| CN111932315A (en) * | 2020-09-02 | 2020-11-13 | 上海优扬新媒信息技术有限公司 | Data display method and device, electronic equipment and computer readable storage medium |
| CN111932315B (en) * | 2020-09-02 | 2023-10-24 | 度小满科技(北京)有限公司 | Method and device for data display, electronic equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102208992B (en) | The malicious information filtering system of Internet and method thereof | |
| Ratkiewicz et al. | Truthy: mapping the spread of astroturf in microblog streams | |
| CN104717185B (en) | Displaying response method, device, server and the system of short uniform resource locator | |
| US7788293B2 (en) | Generating structured information | |
| US20110082848A1 (en) | Systems, methods and computer program products for search results management | |
| US20130304726A1 (en) | Methods and systems useful for identifying the most influent social media users in query-based social data streams | |
| CN110097407A (en) | A kind of generation method and system of user tag | |
| Bhagat et al. | Applying link-based classification to label blogs | |
| CN104685495A (en) | A system and method for automatic generation of information-rich content from multiple microblogs, each microblog containing only sparse information | |
| Hu et al. | Event detection in online social network: Methodologies, state-of-art, and evolution | |
| Takemura et al. | Tweet classification based on their lifetime duration | |
| CN104838662A (en) | Filtering stream of content | |
| Wongthongtham et al. | Ontology and trust based data warehouse in new generation of business intelligence: State-of-the-art, challenges, and opportunities | |
| Sun et al. | Efficient event detection in social media data streams | |
| CN114915468B (en) | Intelligent analysis and detection method for network crime based on knowledge graph | |
| Hoang et al. | Crowdsensing and analyzing micro-event tweets for public transportation insights | |
| Bani-Hani et al. | A semantic model for context-based fake news detection on social media | |
| CN114637903A (en) | Public opinion data acquisition system for directional target data expansion | |
| ES2900746T3 (en) | Systems and methods to effectively distribute warning messages | |
| Kandasamy et al. | Detecting and filtering rumor in social media using news media event | |
| CN111447575A (en) | Short message pushing method, device, equipment and storage medium | |
| Korovesis et al. | Leveraging aspect-based sentiment prediction with textual features and document metadata | |
| KR101673372B1 (en) | Multi-media network service system and method based on template | |
| WO2018037006A1 (en) | Method for selecting second messages for online inserting said second messages in social network content | |
| Li et al. | Discovering associations between news and contents in social network sites with the D-Miner service framework |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190806 |