CN104268214B - A kind of user's gender identification method and system based on microblog users relation - Google Patents
A kind of user's gender identification method and system based on microblog users relation Download PDFInfo
- Publication number
- CN104268214B CN104268214B CN201410494539.7A CN201410494539A CN104268214B CN 104268214 B CN104268214 B CN 104268214B CN 201410494539 A CN201410494539 A CN 201410494539A CN 104268214 B CN104268214 B CN 104268214B
- Authority
- CN
- China
- Prior art keywords
- mrow
- user
- userid
- msub
- microblog users
- 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.)
- Active
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- 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
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The present invention provides a kind of user's gender identification method and system based on microblog users relation, and the inventive method comprises the following steps.S1, the api interface provided according to microblogging website, collect the user profile of microblog users, and different user is classified.S2, the userid of both its follower and bean vermicelli obtained according to the userid of sorted users, and the userid of both the follower and bean vermicelli is organized into text.S3, use information gain are carried out feature extraction to training sample, and sample to be sorted are classified using maximum entropy classifiers.The present invention has more preferable microblog users Gender Classification effect compared to microblogging text is used.
Description
Technical field
The invention belongs to natural language processing technique field, and in particular to a kind of user's sex based on microblog users relation
Recognition methods and system.
Background technology
At present, microblogging is a kind of integrated, Opening the internet social interaction server newly risen in the web2.0 epoch.It gets through
The boundary of mobile radio communication and internet, user can by approach such as mobile phone, IM softwares and outside api interfaces, immediately to
Text within 140 words of outer issue, therefore increasingly favored by Internet user.Data are shown, by the end of in May, 2011
Bottom, only in microblogging registered user online Twitter just up to 300,000,000.By taking Sina weibo as an example, from the Sina weibo of in August, 2009
Start to issue, in April, 2011, the only time of 20 months, Sina weibo registered user just reaches 1.42 hundred million.After in Sina weibo
After line, the also numerous and confused microblogging service such as Tengxun, Netease, Sohu.Microblogging has become one of main activities of Chinese netizen's online,
Under this environment, microblogging analytical technology is paid close attention to by numerous researchers gradually.
Automatically analyzing for microblogging is generally concentrated above two basic tasks：Microblog users are analyzed and content of microblog analysis.
Wherein, microblog users analysis is the basis of content of microblog analysis.Identification for microblog users sex, existing research are mainly
It is most of by various analyses, the processing to text message for foreign language websites such as Twitter, realisation other classification, this
One kind is mainly to be realized by content of microblog analysis.Due to Twitter message unlike traditional text, its content are short and small and more
With colloquial style, and often there are some emoticons in message, traditional file classification method, do not reach classification effect well
Fruit.
In consideration of it, the present invention proposes a kind of user's gender identification method and system based on microblog users relation, to solve
Above mentioned problem.
The content of the invention
The present invention provides a kind of user's gender identification method based on microblog users relation, comprises the following steps.
S1：The api interface provided according to microblogging website, the user profile of microblog users is collected, and different user is carried out
Classification.
S2：Obtain the userid of both its follower and bean vermicelli according to the userid of sorted users, and by the concern
The userid of both person and bean vermicelli is organized into text.
S3：Use information gain carries out feature extraction to training sample, and uses maximum entropy classifiers by sample to be sorted
Classified.
Preferably, in step sl, the follower of the user profile including user and the userid of both beans vermicelli and
Gender fields, and different user is classified according to gender fields.
Preferably, in step sl, the user profile process for collecting microblog users comprises the following steps：
As seed user, the api interface provided using microblogging captures the user of user by one S101, random selection user
Information；
S102, the follower in the user profile captured and both beans vermicelli userid, continue to capture the pass
The user profile of both note person and bean vermicelli, until crawl quantity reaches required scale.
Preferably, in step sl, it is the gender field values in the user profile captured, user type is entered
Row classification, wherein gender field values include m, f and n, and m represents man, and f represents female, and n represents unknown.
Preferably, step S2 also includes：After the userid of both the follower and bean vermicelli is organized into text, deposit respectively
Two rows of file are placed on, and choose male and the female user text formation training sample of equivalent, choose the male of equivalent in addition
And female user text forms test sample.
Preferably, step S3 also includes, and maximum entropy classifiers is built using training sample, wherein the maximum entropy used is
MALLET Machine learning tools bags.
Preferably, the information gain calculation described in step S3 is：
Wherein, P (cj) represent cjThe probability that class document occurs in language material, P (ti) represent to include characteristic item t in language materiali's
The probability of document, P (cj|ti) represent that document includes characteristic item tiWhen belong to CjConditional probability during class,Represent in language material not
Include characteristic item tiDocument probability,Represent that document does not include characteristic item tiWhen belong to CjConditional probability, M tables
Show classification number.
Preferably, after calculating information gain, selection information gain value comes the userid of first 4000.
The present invention also provides a kind of user's sex identifying system based on microblog users relation, including language material obtains and pre- place
Module, information processing module of user's, training classifier modules and user's sort module to be measured are managed, the language material obtains and pretreatment
Module connects information processing module of user's, the information processing module of user's connection training classifier modules, the training classification
Device module connects user's sort module to be measured.The language material obtains and pretreatment module, is used for obtaining microblogging according to api interface
The user profile at family.The information processing module of user's, for user to be classified according to user's gender field values, further according to
Customer relationship is organized into the text of corresponding format by family userid, and therefrom selects training sample, test sample at random.The instruction
Practice classifier modules, for building maximum entropy classifiers.User's sort module to be measured, for being classified according to the maximum entropy
Device is classified to testing data.
According to user's gender identification method and system provided by the invention based on microblog users relation, microblog users are collected
User profile, and different user is classified, without carrying out complex process to the text message of microblogging.According to use of having classified
The userid at family obtains the userid of both its follower and bean vermicelli, and after both userid are organized into text, uses letter
Cease gain and feature extraction is carried out to training sample, and sample to be sorted is classified using maximum entropy classifiers.In this way, compare
Using microblogging text, there is more preferable microblog users Gender Classification effect.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is user's gender identification method flow chart based on microblog users relation that present pre-ferred embodiments provide；
Fig. 2 is user's sex identifying system schematic diagram based on microblog users relation that present pre-ferred embodiments provide.
Embodiment
Describe the present invention in detail below with reference to accompanying drawing and in conjunction with the embodiments.It should be noted that do not conflicting
In the case of, the feature in embodiment and embodiment in the application can be mutually combined.
Fig. 1 is user's gender identification method flow chart based on microblog users relation that present pre-ferred embodiments provide.
As shown in figure 1, user's gender identification method based on microblog users relation that present pre-ferred embodiments provide includes step S1
~S3.
Step S1：The api interface provided according to microblogging website, the user profile of microblog users is collected, and to different user
Classified.
Specifically, microblogging website described in the present embodiment is Sina weibo, in other embodiments, can as needed voluntarily
Setting, to this present invention and it is not construed as limiting.
The user profile process that microblog users are collected described in the present embodiment comprises the following steps.
As seed user, the api interface provided using microblogging captures the user of user by one S101, random selection user
Information.
In this, the user profile includes the follower of user and userid the and gender fields of both beans vermicelli, and
Different user is classified according to gender fields.Wherein, gender field values include m, f and n, and m represents man, and f represents female,
N represents unknown, and user is divided into above-mentioned three class by sex accordingly.
S102, the follower in the user profile captured and both beans vermicelli userid, continue to capture the pass
The user profile of both note person and bean vermicelli, until crawl quantity reaches required scale.
Step S2：The userid of both its follower and bean vermicelli are obtained according to the userid of sorted users, and by described in
The userid of both follower and bean vermicelli is organized into text.
Specifically, in this step, after the userid of both the follower and bean vermicelli is organized into text, deposit respectively
In two rows of file.Wherein, it can be split between each userid using special symbol, be divided in the present embodiment using space
Cut.In this, if the follower of certain user or bean vermicelli number are zero, behavior null is corresponded to.
In addition, need to choose equivalent male and female user text formed training sample, in addition choose equivalent male and
Female user text forms test sample, forms sample to be sorted.The present embodiment chooses male, each 1000 formation of female user
Training sample, male, each 1000 formation test sample of female user.
Step S3：Use information gain carries out feature extraction to training sample, and will be to be sorted using maximum entropy classifiers
Sample is classified.
Specifically, the present embodiment is that the maximum entropy used is MALLET using training sample structure maximum entropy classifiers
Machine learning tools bag.
Wherein, information gain calculation is：
Wherein, P (cj) represent cjThe probability that class document occurs in language material, P (ti) represent to include characteristic item t in language materiali's
The probability of document, P (cj|ti) represent that document includes characteristic item tiWhen belong to CjConditional probability during class,Represent in language material not
Include characteristic item tiDocument probability,Represent that document does not include characteristic item tiWhen belong to CjConditional probability, M tables
Show classification number.
Wherein, under maximum entropy model, the formula of predicted condition probability P (c | d) is：
Wherein Z (d) is normalization factor.Fi,cIt is characteristic function, is defined as：
After said process calculates information gain, the present embodiment selection information gain value comes the userid of first 4000.
As it was previously stated, take each 1000 of training sample male, female user, male, female user in test sample
The experimental data of each 1000, the accuracy rate that the inventive method is classified to microblog users are 0.843.
Fig. 2 is user's sex identifying system schematic diagram based on microblog users relation that present pre-ferred embodiments provide.
As shown in Fig. 2 user's sex identifying system based on microblog users relation that present pre-ferred embodiments provide obtains including language material
Take and pretreatment module 1, information processing module of user's 2, training classifier modules 3 and user's sort module 4 to be measured, the language material
Acquisition is connected information processing module of user's 2, the connection of the information processing module of user's 2 training grader mould with pretreatment module 1
Block 3, the training classifier modules 3 connect user's sort module 4 to be measured.The language material obtains and pretreatment module 1, for root
The user profile of microblog users is obtained according to api interface.The information processing module of user's 2, for according to user's gender fields
Value classifies user, customer relationship is organized into the text of corresponding format further according to user userid, and therefrom select instruction at random
Practice sample, test sample.The training classifier modules 3, for building maximum entropy classifiers.User's sort module to be measured
4, for being classified according to the maximum entropy classifiers to testing data.Operating process and side of the present invention on said system
Method is similar, therefore is repeated no more in this.
The user's gender identification method and system based on microblog users relation provided according to present pre-ferred embodiments, with
The customer relationship (i.e. user follower and the userid of bean vermicelli) of microblog users is that source resource forms text, has been taken into full account micro-
The importance of customer relationship in rich.Meanwhile combining information gain carries out feature extraction to training sample, greatly reduces feature dimensions
Degree, so as to avoid the harmful effect brought in assorting process using Twitter message, and has more preferable classifying quality.
The foregoing description of the disclosed embodiments, professional and technical personnel in the field are enable to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
Embodiment illustrated herein is not intended to be limited to, and is to fit to consistent with principles disclosed herein and features of novelty
Most wide scope.The foregoing description of the disclosed embodiments, professional and technical personnel in the field are enable to realize or use this hair
It is bright.A variety of modifications to these embodiments will be apparent for those skilled in the art, determine herein
The General Principle of justice can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, originally
Invention is not intended to be limited to embodiment illustrated herein, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (8)
1. a kind of user's gender identification method based on microblog users relation, it is characterised in that comprise the following steps：
S1, the api interface provided according to microblogging website, collect the user profile of microblog users, and different user is classified；
In step sl, the user profile process for collecting microblog users comprises the following steps：
As seed user, the user that the api interface provided using microblogging captures user believes by one S101, random selection user
Breath；
S102, the follower in the user profile captured and both beans vermicelli userid, continue to capture the follower
With the user profile of both beans vermicelli, reach required scale up to capturing quantity；
S2, the userid for obtaining according to the userid of sorted users both its follower and bean vermicelli, and by the follower and
The userid of both beans vermicelli is organized into text；
S3, use information gain are carried out feature extraction to training sample, and are carried out sample to be sorted using maximum entropy classifiers
Classification.
2. according to the method for claim 1, it is characterised in that in step sl, the user profile includes the pass of user
Userid the and gender fields of both note person and bean vermicelli, and different user is classified according to gender fields.
3. method according to claim 1 or 2, it is characterised in that be according to the user profile captured in step sl
In gender field values, user type is classified, wherein gender field values include m, f and n, and m represents man, and f is represented
Female, n represent unknown.
4. according to the method for claim 1, it is characterised in that step S2 also includes：By both the follower and bean vermicelli
Userid be organized into text after, be stored in two rows of file respectively, and choose the male of equivalent and female user text is formed
Training sample, the male and female user text for choosing equivalent in addition form test sample.
5. according to the method for claim 1, it is characterised in that step S3 also includes, and maximum entropy is built using training sample
Grader, wherein the maximum entropy used is MALLET Machine learning tools bags.
6. according to the method for claim 1, it is characterised in that the information gain calculation described in step S3 is：
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>G</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mrow>
<mo>{</mo>
<mrow>
<mo>-</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</msubsup>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>c</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mi>log</mi>
<mi> </mi>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>c</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mo>}</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>+</mo>
<mo>{</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</msubsup>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>c</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<mi>t</mi>
</mrow>
<mo>)</mo>
</mrow>
<mi>log</mi>
<mi> </mi>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>c</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<mi>t</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mo>&rsqb;</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>+</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mover>
<mi>t</mi>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</msubsup>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>c</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<mover>
<mi>t</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
<mo>)</mo>
</mrow>
<mi>log</mi>
<mi> </mi>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>c</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<mover>
<mi>t</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mo>}</mo>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein, P (cj) represent cjThe probability that class document occurs in language material, P (ti) represent to include characteristic item t in language materialiDocument
Probability, P (cj|ti) represent that document includes characteristic item tiWhen belong to CjConditional probability during class,Represent not including in language material
Characteristic item tiDocument probability,Represent that document does not include characteristic item tiWhen belong to CjConditional probability, m represent class
Shuo not.
7. according to the method for claim 6, it is characterised in that after calculating information gain, before selecting information gain value to come
The userid of 4000.
8. a kind of user's sex identifying system based on microblog users relation, it is characterised in that obtain and pre-process including language material
Module, information processing module of user's, training classifier modules and user's sort module to be measured, the language material obtain and pretreatment mould
Block connects information processing module of user's, the information processing module of user's connection training classifier modules, the training grader
Module connects user's sort module to be measured,
The language material obtains and pretreatment module, for obtaining the user profile of microblog users according to api interface；
The information processing module of user's, for user to be classified according to user's gender field values, further according to user userid
Customer relationship is organized into the text of corresponding format, and therefrom selects training sample, test sample at random；
The training classifier modules, for building maximum entropy classifiers；
User's sort module to be measured, for being classified according to the maximum entropy classifiers to testing data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410494539.7A CN104268214B (en) | 2014-09-24 | 2014-09-24 | A kind of user's gender identification method and system based on microblog users relation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410494539.7A CN104268214B (en) | 2014-09-24 | 2014-09-24 | A kind of user's gender identification method and system based on microblog users relation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104268214A CN104268214A (en) | 2015-01-07 |
| CN104268214B true CN104268214B (en) | 2018-01-19 |
Family
ID=52159736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410494539.7A Active CN104268214B (en) | 2014-09-24 | 2014-09-24 | A kind of user's gender identification method and system based on microblog users relation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104268214B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654131A (en) * | 2015-12-30 | 2016-06-08 | 小米科技有限责任公司 | Classification model training method and device |
| CN106126607B (en) * | 2016-06-21 | 2019-12-31 | 重庆邮电大学 | User relationship analysis method facing social network |
| CN106327341A (en) * | 2016-08-15 | 2017-01-11 | 首都师范大学 | Weibo user gender deduction method and system based on combined theme |
| CN106682118A (en) * | 2016-12-08 | 2017-05-17 | 华中科技大学 | Social network site false fan detection method achieved on basis of network crawler by means of machine learning |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663027A (en) * | 2012-03-22 | 2012-09-12 | 浙江盘石信息技术有限公司 | Method for predicting attributes of webpage crowd |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8457605B2 (en) * | 2010-10-04 | 2013-06-04 | Telefonica, S.A. | Method for gender identification of a cell-phone subscriber |
-
2014
- 2014-09-24 CN CN201410494539.7A patent/CN104268214B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663027A (en) * | 2012-03-22 | 2012-09-12 | 浙江盘石信息技术有限公司 | Method for predicting attributes of webpage crowd |
Non-Patent Citations (4)
| Title |
|---|
| 《"Gender predication on twitter using stream algorithms with N-gram character features"Gender predication on twitter using stream algorithms with N-gram character features》;Miller Z等;《International Journal of Intelligence Science》;20121031(第02期);第143-148页 * |
| 《A Framework of Feature Selection Methods for Text Categorization》;Li S等;《In Proceedings of ACL-IJCNLP-09》;20090807;第692-700页 * |
| 《基于最大熵模型的中文网页分类器设计和实现》;杨芹;《中国优秀硕士学位论文全文数据库（信息科技辑）》;20120215(第02期);第I139-496页 * |
| 《基于语义角色标注的微博人物关系抽取》;廉营;《中国优秀硕士学位论文全文数据库（信息科技辑）》;20130115(第01期);第I138-2289页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104268214A (en) | 2015-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Karthikeyan et al. | Personalized content extraction and text classification using effective web scraping techniques | |
| CN108804512B (en) | Text classification model generation device and method and computer readable storage medium | |
| CN105808526B (en) | Commodity short text core word extracting method and device | |
| CN104537341B (en) | Face picture information getting method and device | |
| CN108199951A (en) | A kind of rubbish mail filtering method based on more algorithm fusion models | |
| CN104268160A (en) | Evaluation object extraction method based on domain dictionary and semantic roles | |
| CN104268214B (en) | A kind of user's gender identification method and system based on microblog users relation | |
| CN103458042A (en) | Microblog advertisement user detection method | |
| CN107688576B (en) | Construction and tendency classification method of CNN-SVM model | |
| CN102169496A (en) | Anchor text analysis-based automatic domain term generating method | |
| WO2017118333A1 (en) | Method and device for predicting user problem based on data drive | |
| CN109145180B (en) | Enterprise hot event mining method based on incremental clustering | |
| CN102279890A (en) | Sentiment word extracting and collecting method based on micro blog | |
| CN104317784A (en) | Cross-platform user identification method and cross-platform user identification system | |
| CN102663001A (en) | Automatic blog writer interest and character identifying method based on support vector machine | |
| CN104778283B (en) | A kind of user's occupational classification method and system based on microblogging | |
| CN104504024A (en) | Method and system for mining keywords based on microblog content | |
| CN103020645A (en) | System and method for junk picture recognition | |
| CN104281694A (en) | Analysis system of emotional tendency of text | |
| US20150286706A1 (en) | Forensic system, forensic method, and forensic program | |
| CN104598648A (en) | Interactive gender identification method and device for microblog user | |
| CN108984514A (en) | Acquisition methods and device, storage medium, the processor of word | |
| CN107545075B (en) | Restaurant recommendation method based on online comments and context awareness | |
| CN104866606B (en) | A kind of MapReduce parallelization big data file classification method | |
| CN106202312B (en) | A kind of interest point search method and system for mobile Internet |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |