CN103886097A - Chinese microblog viewpoint sentence recognition feature extraction method based on self-adaption lifting algorithm - Google Patents
Chinese microblog viewpoint sentence recognition feature extraction method based on self-adaption lifting algorithm Download PDFInfo
- Publication number
- CN103886097A CN103886097A CN201410135746.3A CN201410135746A CN103886097A CN 103886097 A CN103886097 A CN 103886097A CN 201410135746 A CN201410135746 A CN 201410135746A CN 103886097 A CN103886097 A CN 103886097A
- Authority
- CN
- China
- Prior art keywords
- microblogging
- training sample
- feature
- chinese
- viewpoint sentence
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a Chinese microblog viewpoint sentence recognition feature extraction method based on a self-adaption lifting algorithm. The method comprises the steps that firstly, features related to recognizing a microblog viewpoint sentence are set and recognized, weak classifiers with single features form a strong classifier with a plurality of features, and critical recognition features are selected in the construction process of the strong classifier; finally, an effective subjective sentence recognition feature set and the strong classifier formed by the recognition feature set are output, and effective recognition bases can be provided for recognition of the Chinese microblog viewpoint sentence through the subjective sentence recognition feature set.
Description
Technical field
The present invention relates to a kind of extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm.
Background technology
In Chinese microblogging, effectively differentiate whether comprise the viewpoint of people to things, the information such as suggestion or tendency, are the important foundations of automatic Collection and analysis network Chinese public opinion data.From the angle of text mining, identify subjective statement and can improve the accuracy of viewpoint classification, reduce the interference of non-subjective statement to follow-up natural language processing inter-related tasks such as viewpoint summary, tendency statistics and sentiment analysis.
Along with developing rapidly of internet and popularizing of Web2.0, the issue of information is no longer the patent of newpapers and periodicals, periodical publisher, TV station and news website, and microblogging website has become the publication medium of public information.Than traditional blog, the feature of microblogging maximum is its micro-, within single piece of blog length is generally limited in 140 words.In microblogging, not only can comprise news, also may comprise the information such as viewpoint or suggestion of microblog users individual to things.
Viewpoint sentence is based on asserting or commenting on and expressing with a guy's emotion and purpose.Can trace back to the classification of the subjective and objective sentence in opinion mining about the classification of viewpoint sentence, it is the classification of carrying out on the media data of comment on commodity mostly, and the maximum feature of carrying out the differentiation of viewpoint sentence on microblogging is the restriction of its number of words and the freedom of language construction.Because the restriction of number of words, the frequency of its word and part of speech thereof, dependence greatly reduces with respect to plain text; Because the freedom of language construction, the analysis on syntactic structure is carried out just relatively difficultly.For the subjective composition characteristics identification of this short text of Chinese microblogging, also lack the combined optimization method of the effective sorting technique of system and feature extraction at present.
Adaptive boosting algorithm is a kind ofly to combine multiple Weak Classifiers and become the method for a strong classifier.Weak Classifier is the binary classifier that the probability of error is less than 0.5, and using it to differentiate the random conjecture that two class problem ratio error probability are 0.5 will get well, and the probability of error of strong classifier H can be arbitrarily small.With reference to the thought of the combination multi-categorizer of adaptive boosting algorithm, we have proposed a kind of effective feature selection approach for subjective sentence identification in Chinese microblogging.
Summary of the invention
The extracting method that the invention provides a kind of Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm, it has overcome the deficiency described in background technology.
The technical scheme adopting that the present invention solves its technical matters is:
The extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm, it comprises:
Step 1, whether be the microblogging training sample of viewpoint sentence mark, input this microblogging training sample set S={ (x if having band
i, y
i), i=1 ..., n}, wherein x
i∈ X, y
i∈ Y, Y={-1 ,+1}, X is m feature of this n microblogging training sample, Y is the classification results that each microblogging training sample is corresponding, if this microblogging training sample x
ibe viewpoint sentence, this microblogging training sample is labeled as y
i=+1, otherwise be y
i=-1;
The stopping criterion for iteration of setting feature selecting is: error in classification ε
jbe less than threshold value beta with 0.5 gap, wherein, β can according to circumstances set voluntarily;
Set the initial weight distribution D of microblogging training sample set
1for being evenly distributed,
Setting selecteed initial characteristics set is empty set;
Set iteration variable initial value j=1, maximum iteration time is m;
Step 2,21-27 carries out loop iteration according to the following steps, comprising:
Step 21 is D in weight distribution
jmicroblogging training sample concentrate, find with feature f
jfor the Weak Classifier h of single features
j, this Weak Classifier h
jto the error in classification ε of this microblogging training sample set
jwith 0.5 disparity,
wherein: the error in classification of this Weak Classifier to this microblogging training sample set
h is all single features Weak Classifiers that are output as Y;
Step 22, writes down this Weak Classifier h
jparameter: feature f
j, two points of these weight distribution microblogging training sample sets threshold value and binary relation operational symbol;
Step 23, upgrades selected characteristic set F=F ∪ { f
j, the selected feature f of this iteration
jin iteration afterwards, do not re-use;
Step 24, calculates this Weak Classifier h
jweight in strong classifier H
Step 25, if error in classification | ε
j-0.5|≤β, maximum iteration time T=j, exits iteration, finishes feature selecting, otherwise, proceed step 26;
Step 26, iteration variable j value adds 1, if j is greater than m, has selected whole features, exits iteration, otherwise, proceed step 27;
Step 27, upgrade the weight distribution of this microblogging training sample set:
i=1 ..., n, wherein:
return to step 21;
Step
3, the selected characteristic set F={f of output
j| j=1 ..., T} and strong classifier
Among one embodiment: this error in classification ε
jcan be set with 0.5 gap β.
Among one embodiment: the recognition feature of Chinese microblogging viewpoint sentence comprises the part of speech in Chinese microblogging statement.
Among one embodiment: the recognition feature of Chinese microblogging viewpoint sentence comprises the emotion set of words in sentiment dictionary.
Among one embodiment: the recognition feature of Chinese microblogging viewpoint sentence comprises the interdependent feature between word and word.
Among one embodiment: the recognition feature of Chinese microblogging viewpoint sentence comprises the position feature between word and word.
The technical program is compared with background technology, and its tool has the following advantages:
The present invention provides a kind of effective feature selecting solution for the identification of the subjective sentence of Chinese microblogging, the Weak Classifier with single feature is built into the strong classifier with multiple features, and in the building process of strong classifier, carry out the selection of crucial recognition feature, effectively subjective sentence recognition feature set of output, can provide effective basis of characterization for the identification of Chinese microblogging viewpoint sentence by this subjectivity sentence recognition feature set.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described.
Fig. 1 is the process flow diagram of the extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm.
Embodiment
Please refer to Fig. 1, identify Chinese microblogging viewpoint beginning of the sentence and first will set the feature relevant to identifying microblogging viewpoint sentence, then from numerous correlated characteristics, extract the feature most with identification effect according to the Chinese microblogging viewpoint sentence recognition feature extracting method based on adaptive boosting algorithm.
In the present embodiment, adopting the emotion set of words in part of speech and the sentiment dictionary in Chinese microblogging is basic recognition feature, part of speech comprises adjective, verb, interjection etc., part of speech adopts in the ICTPOS Chinese part of speech label sets of the Computer Department of the Chinese Academy of Science 23 kinds of parts of speech that connect etc. except punctuation mark and front and back, in the recognition feature leaching process of viewpoint sentence, we have set up Weak Classifier for each part of speech, and each parts of speech classification device is used for mating a kind of part of speech.Emotion word adopts multiple for judging the emotion set of words of emotion classification of word in sentiment dictionary, and in like manner, we also set up Weak Classifier for each emotion set of words.Interdependent feature adopts the dependence collection of Stanford university, and totally 57 kinds, in like manner, we also set up Weak Classifier for each dependence, for mating a kind of dependence.Finally can also add the relevant position feature in appearance position between word and word, in the present embodiment, construct two class word position features and describe the syntactic structure of Chinese microblogging.To sum up, can build the Weak Classifier corresponding with these more than 100 features and carry out the identification of microblogging viewpoint sentence.By adaptive boosting algorithm, above more than 100 features are further extracted, find out the recognition feature of the microblogging viewpoint sentence with identification effect, find out the identification Weak Classifier of the microblogging viewpoint sentence with identification effect, form strong classifier microblogging viewpoint sentence is identified by the Weak Classifier filtering out being carried out to linear combination, or its recognition effect is by better than adopting the single feature effect that optionally several features or all features are classified.
The extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm, it comprises:
Step 1, whether be the microblogging training sample of viewpoint sentence mark, input this microblogging training sample set S={ (x if having band
i, y
i), i=1 ..., n}, wherein x
i∈ X, y
i∈ Y, Y={-1 ,+1}, X is m feature of this n microblogging training sample, Y is the classification results that each microblogging training sample is corresponding, if this microblogging training sample x
ibe viewpoint sentence, this microblogging training sample is labeled as y
i=+1, otherwise be y
i=-1;
The stopping criterion for iteration of setting feature selecting is: error in classification ε
jbe less than threshold value beta with 0.5 gap, wherein, β can according to circumstances set voluntarily;
Set the initial weight distribution D of microblogging training sample set
1for being evenly distributed,
Setting selecteed initial characteristics set is empty set;
Set iteration variable initial value j=1, maximum iteration time is m;
Step 2,21-27 carries out loop iteration according to the following steps, comprising:
Step 21 is D in weight distribution
jmicroblogging training sample concentrate, find with feature f
jfor the Weak Classifier h of single features
j, this Weak Classifier h
jto the error in classification ε of this microblogging training sample set
jwith 0.5 disparity,
wherein: the error in classification of this Weak Classifier to this microblogging training sample set
h is all single features Weak Classifiers that are output as Y;
Step 22, writes down this Weak Classifier h
jparameter: feature f
j, two points of these weight distribution microblogging training sample sets threshold value and binary relation operational symbol;
Step 23, upgrades selected characteristic set F=F ∪ { f
j, the selected feature f of this iteration
jin iteration afterwards, do not re-use;
Step 25, if error in classification | ε
j-0.5|≤β, maximum iteration time T=j, exits iteration, finishes feature selecting, otherwise, continue execution step 26;
Step 26, iteration variable j value adds 1, if j is greater than m, has selected whole features, exits iteration, otherwise, continue execution step 27;
Step 27, upgrade the weight distribution of this microblogging training sample set:
i=1 ..., n, wherein:
return to step 21;
Step 3, the selected characteristic set F={f of output
j| j=1 ..., T} and strong classifier
the selected characteristic set of this last output is the set of the subjective sentence of effective microblogging recognition feature, and conventionally, T is less than m, just can reach the object of feature selecting.
In the present embodiment, adopt accuracy rate, recall rate and F value (F1-Measure) to analyze the identification effect of this feature to viewpoint sentence as statistical indicator.In one preferred embodiment, choose the data of the Chinese microblogging sentiment analysis evaluation and test of NLP & CC2012 and carry out training and testing as this microblogging training sample set, select 6 part of speech features can obtain the effect of 80% F1 value overall target by this method.Use part of speech to add that position feature screens the strong classifier drawing and carries out the screening of subjective sentence, its classifying quality drawing is better.
The above, only for preferred embodiment of the present invention, therefore can not limit according to this scope of the invention process, the equivalence of doing according to the scope of the claims of the present invention and description changes and modifies, and all should still belong in the scope that the present invention contains.
Claims (6)
1. the extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm, is characterized in that: comprising:
Step 1, whether be the microblogging training sample of viewpoint sentence mark, input this microblogging training sample set S={ (x if having band
i, y
i), i=1 ..., n}, wherein x
i∈ X, y
i∈ Y, Y={-1 ,+1}, X is m feature of this n microblogging training sample, Y is the classification results that each microblogging training sample is corresponding, if this microblogging training sample x
ibe viewpoint sentence, this microblogging training sample is labeled as y
i=+1, otherwise be y
i=-1;
The stopping criterion for iteration of setting feature selecting is: error in classification ε
jbe less than threshold value beta with 0.5 gap, wherein, β can according to circumstances set voluntarily;
Set the initial weight distribution D of microblogging training sample set
1for being evenly distributed,
Setting selecteed initial characteristics set is empty set;
Set iteration variable initial value j=1, maximum iteration time is m;
Step 2,21-27 carries out loop iteration according to the following steps, comprising:
Step 21 is D in weight distribution
jmicroblogging training sample concentrate, find with feature f
jfor the Weak Classifier h of single features
j, this Weak Classifier h
jto the error in classification ε of this microblogging training sample set
jwith 0.5 disparity,
wherein: the error in classification of this Weak Classifier to this microblogging training sample set
h is all single features Weak Classifiers that are output as Y;
Step 22, writes down this Weak Classifier h
jparameter: feature f
j, two points of these weight distribution microblogging training sample sets threshold value and binary relation operational symbol;
Step 23, upgrades selected characteristic set F=F ∪ { f
j, the selected feature f of this iteration
jin iteration afterwards, do not re-use;
Step 25, if error in classification | ε
j-0.5|≤β, maximum iteration time T=j, exits iteration, finishes feature selecting, otherwise, proceed step 26;
Step 26, iteration variable j value adds 1, if j is greater than m, has selected whole features, exits iteration, otherwise, proceed step 27;
Step 27, upgrade the weight distribution of this microblogging training sample set:
i=1 ..., n, wherein,
return to step 21;
Step 3, the selected characteristic set F={f of output
j| j=1 ..., T} and strong classifier
2. the extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm according to claim 1, is characterized in that: this error in classification ε
jcan be set with 0.5 gap β.
3. the extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm according to claim 1, is characterized in that: the recognition feature of Chinese microblogging viewpoint sentence comprises the part of speech in Chinese microblogging statement.
4. the extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm according to claim 1, is characterized in that: the recognition feature of Chinese microblogging viewpoint sentence comprises the emotion set of words in sentiment dictionary.
5. the extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm according to claim 1, is characterized in that: the recognition feature of Chinese microblogging viewpoint sentence comprises the interdependent feature between word and word.
6. the extracting method of the Chinese microblogging viewpoint sentence recognition feature based on adaptive boosting algorithm according to claim 1, is characterized in that: the recognition feature of Chinese microblogging viewpoint sentence comprises the position feature between word and word.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410135746.3A CN103886097A (en) | 2014-04-04 | 2014-04-04 | Chinese microblog viewpoint sentence recognition feature extraction method based on self-adaption lifting algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410135746.3A CN103886097A (en) | 2014-04-04 | 2014-04-04 | Chinese microblog viewpoint sentence recognition feature extraction method based on self-adaption lifting algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103886097A true CN103886097A (en) | 2014-06-25 |
Family
ID=50954989
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410135746.3A Pending CN103886097A (en) | 2014-04-04 | 2014-04-04 | Chinese microblog viewpoint sentence recognition feature extraction method based on self-adaption lifting algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103886097A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106055633A (en) * | 2016-05-30 | 2016-10-26 | 国家计算机网络与信息安全管理中心 | Chinese microblog subjective and objective sentence classification method |
CN107341428A (en) * | 2016-04-28 | 2017-11-10 | 财团法人车辆研究测试中心 | Image recognition system and adaptive learning method |
CN108334605A (en) * | 2018-02-01 | 2018-07-27 | 腾讯科技(深圳)有限公司 | File classification method, device, computer equipment and storage medium |
CN111768041A (en) * | 2020-07-02 | 2020-10-13 | 上海积成能源科技有限公司 | System model for predicting short-term power load based on adaptive lifting algorithm |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101060443A (en) * | 2006-04-17 | 2007-10-24 | 中国科学院自动化研究所 | An improved adaptive boosting algorithm based Internet intrusion detection method |
CN101398893A (en) * | 2008-10-10 | 2009-04-01 | 北京科技大学 | Adaboost arithmetic improved robust human ear detection method |
CN102129565A (en) * | 2011-03-01 | 2011-07-20 | 北京航空航天大学 | Object detection method based on feature redundancy elimination AdaBoost classifier |
CN102184388A (en) * | 2011-05-16 | 2011-09-14 | 苏州两江科技有限公司 | Face and vehicle adaptive rapid detection system and detection method |
CN102521622A (en) * | 2011-11-18 | 2012-06-27 | 常州蓝城信息科技有限公司 | Face detecting system based on advertisement putting |
CN102819745A (en) * | 2012-07-04 | 2012-12-12 | 杭州电子科技大学 | Hyper-spectral remote sensing image classifying method based on AdaBoost |
US20130163829A1 (en) * | 2011-12-21 | 2013-06-27 | Electronics And Telecommunications Research Institute | System for recognizing disguised face using gabor feature and svm classifier and method thereof |
CN103400471A (en) * | 2013-08-12 | 2013-11-20 | 电子科技大学 | Detecting system and detecting method for fatigue driving of driver |
-
2014
- 2014-04-04 CN CN201410135746.3A patent/CN103886097A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101060443A (en) * | 2006-04-17 | 2007-10-24 | 中国科学院自动化研究所 | An improved adaptive boosting algorithm based Internet intrusion detection method |
CN101398893A (en) * | 2008-10-10 | 2009-04-01 | 北京科技大学 | Adaboost arithmetic improved robust human ear detection method |
CN102129565A (en) * | 2011-03-01 | 2011-07-20 | 北京航空航天大学 | Object detection method based on feature redundancy elimination AdaBoost classifier |
CN102184388A (en) * | 2011-05-16 | 2011-09-14 | 苏州两江科技有限公司 | Face and vehicle adaptive rapid detection system and detection method |
CN102521622A (en) * | 2011-11-18 | 2012-06-27 | 常州蓝城信息科技有限公司 | Face detecting system based on advertisement putting |
US20130163829A1 (en) * | 2011-12-21 | 2013-06-27 | Electronics And Telecommunications Research Institute | System for recognizing disguised face using gabor feature and svm classifier and method thereof |
CN102819745A (en) * | 2012-07-04 | 2012-12-12 | 杭州电子科技大学 | Hyper-spectral remote sensing image classifying method based on AdaBoost |
CN103400471A (en) * | 2013-08-12 | 2013-11-20 | 电子科技大学 | Detecting system and detecting method for fatigue driving of driver |
Non-Patent Citations (1)
Title |
---|
潘艳茜 等: "基于多分类器集成的中文微博情感分析", 《HTTP://TCCI.CCF.ORG.CN/CONFERENCE/2012/DLDOC/NLPCC2012PAPERS/WORKSHOPPAPERS/SEN/012.PDF》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107341428A (en) * | 2016-04-28 | 2017-11-10 | 财团法人车辆研究测试中心 | Image recognition system and adaptive learning method |
CN106055633A (en) * | 2016-05-30 | 2016-10-26 | 国家计算机网络与信息安全管理中心 | Chinese microblog subjective and objective sentence classification method |
CN108334605A (en) * | 2018-02-01 | 2018-07-27 | 腾讯科技(深圳)有限公司 | File classification method, device, computer equipment and storage medium |
WO2019149200A1 (en) * | 2018-02-01 | 2019-08-08 | 腾讯科技(深圳)有限公司 | Text classification method, computer device, and storage medium |
US11562145B2 (en) | 2018-02-01 | 2023-01-24 | Tencent Technology (Shenzhen) Company Limited | Text classification method, computer device, and storage medium |
CN111768041A (en) * | 2020-07-02 | 2020-10-13 | 上海积成能源科技有限公司 | System model for predicting short-term power load based on adaptive lifting algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108804512B (en) | Text classification model generation device and method and computer readable storage medium | |
Pane et al. | A multi-lable classification on topics of quranic verses in english translation using multinomial naive bayes | |
Gain et al. | Low-code AutoML-augmented data pipeline–a review and experiments | |
CN109145216A (en) | Network public-opinion monitoring method, device and storage medium | |
CN103207913B (en) | The acquisition methods of commercial fine granularity semantic relation and system | |
CN105183717B (en) | A kind of OSN user feeling analysis methods based on random forest and customer relationship | |
CN111310476B (en) | Public opinion monitoring method and system using aspect-based emotion analysis method | |
CN106250513A (en) | A kind of event personalization sorting technique based on event modeling and system | |
CN106776538A (en) | The information extracting method of enterprise's noncanonical format document | |
Halibas et al. | Application of text classification and clustering of Twitter data for business analytics | |
CN101645083B (en) | Acquisition system and method of text field based on concept symbols | |
CN106445919A (en) | Sentiment classifying method and device | |
CN102541838B (en) | Method and equipment for optimizing emotional classifier | |
CN104572958A (en) | Event extraction based sensitive information monitoring method | |
CN104199972A (en) | Named entity relation extraction and construction method based on deep learning | |
CN105260356A (en) | Chinese interactive text emotion and topic identification method based on multitask learning | |
CN104298665A (en) | Identification method and device of evaluation objects of Chinese texts | |
CN104408093A (en) | News event element extracting method and device | |
CN104598535A (en) | Event extraction method based on maximum entropy | |
CN104850617A (en) | Short text processing method and apparatus | |
CN103294817A (en) | Text feature extraction method based on categorical distribution probability | |
CN104199845B (en) | Line Evaluation based on agent model discusses sensibility classification method | |
CN107463703A (en) | English social media account number classification method based on information gain | |
CN107194617A (en) | A kind of app software engineers soft skill categorizing system and method | |
CN104346326A (en) | Method and device for determining emotional characteristics of emotional texts |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140625 |
|
RJ01 | Rejection of invention patent application after publication |