CN104317965B - Sentiment dictionary construction method based on language material - Google Patents
Sentiment dictionary construction method based on language material Download PDFInfo
- Publication number
- CN104317965B CN104317965B CN201410649358.7A CN201410649358A CN104317965B CN 104317965 B CN104317965 B CN 104317965B CN 201410649358 A CN201410649358 A CN 201410649358A CN 104317965 B CN104317965 B CN 104317965B
- Authority
- CN
- China
- Prior art keywords
- word
- list
- adjective
- polarity
- language material
- 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.)
- Expired - Fee Related
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of sentiment dictionary construction method based on language material, by the adjective that Sentiment orientation known to a part is obtained ahead of time, including two kinds positive with passiveness, recycle adversative and negative word, extract and analyze the adjective of unknown Sentiment orientation, constantly extension seed dictionary, is finally judged.This method does not need manual intervention, and belongs to unsupervised learning method, can greatly improve operating efficiency.The sentiment dictionary of this method construction, can be used for comment and analysis, can be quickly obtained its Sentiment orientation, reach the purpose quickly analyzed.
Description
Technical field
The invention belongs to artificial intelligence inventive technique, and in particular to a kind of sentiment dictionary construction method based on language material.
Background technology
Existing part Chinese sentiment dictionary, all it is to be built by artificially summarizing some conventional adjectives, efficiency is low
Under, do not have territoriality again.And Chinese can not build feelings without the dictionary similar to English wordnet by existing dictionary
Feel word dictionary.Sentiment dictionary construction method based on language material, the speech habits of people is applied in the analysis of text, constructed
Positive and passive two class dictionaries.Labor cost is saved, there is territoriality and the judgment to neologisms emotion again.
It is relatively early according to language rule to analyze language material, structure sentiment dictionary is Hazivassiloglou and McKeown,
They utilize a corpus and adjective emotion word subset, according to language rule, find out other adjectival emotions and point to.
For example utilize the conjunction such as " AND ", " BUT ".They also determine that the word that two conjunctions connect has phase using clustering algorithm
Same or opposite polarity, so as to produce two set of words.Kanayama is with Nasukawa using emotion is consistent between sentence in sentence
Property concept generate sentiment dictionary, between sentence uniformity is because the sentence of usual phase feeling of sympathy is ined succession.Feeling changes lead to
It is often to be caused by adversative, such as " but ".But their utilization rates of the emotion word to being obtained during algorithm performs are poor.
The content of the invention
It is an object of the invention to provide a kind of sentiment dictionary generation method based on large-scale corpus, this method has standard
True rate is high, the advantages that saving the time, and important reference can be provided for comment and analysis.
The technical scheme for realizing the object of the invention is：A kind of sentiment dictionary construction method based on language material, including following step
Suddenly：
The first step, using Chinese word segmentation instrument, language material is pre-processed, continuous Chinese sentence in language material is divided into
Word or word one by one, are separated with space, and the part of speech of tagged words or word；
Second step, count in language material all adjectival word frequency and by being ranked up from high to low, take preceding 5%-10%
There is the adjective for determining feeling polarities to form emotion dictionary as seed words, and analyze the feeling polarities of seed words, front is commented
The polarity of the word of valency is referred to as positive, and it is passive that the polarity of the word of unfavorable ratings is referred to as, and respectively constitutes two seed word lists,
The two initial lists of seed word list as emotion dictionary, initial word frequency are 1；
3rd step, learnt from else's experience pretreatment language material in text, the language material analyzed if necessary, text is entered according to punctuate
Row punctuate, obtains multiple subordinate sentences, is free of punctuate in subordinate sentence, continues executing with the 4th step；If not needing the language material analyzed, go to
6th step；
4th step, the adjective searched in obtained each subordinate sentence, a threshold k is set, in adjective position
Preceding K word or word in the range of travel through, according to the word with Negation pointed out in Chinese dictionary, determine whether negate
Word, if so, then according to polarity transition rule being added in respective list, otherwise stop finding negative word；Further according to Chinese dictionary
In point out have turnover meaning word, judge the subordinate sentence whether started with adversative, if so, then according to polarity transition rule
Change current polarity, otherwise polarity is constant；Then the adjective in subordinate sentence is added to two row by polarity transition rule respectively
In table s and a；
5th step, two lists s and a that the 4th step of analysis obtains polarity, i.e., examined with the seed words in emotion dictionary
List s and a polarity, if the number containing positive seed words is no less than passive seed words, the row in one of list
All words are classified as positive in table, and the word in another list is then classified as passiveness；If respectively containing identical in two lists
The passive seed words and positive seed words of quantity, then return to the 3rd step；Otherwise, the shape that polarity is judged in two lists s and a
Appearance word, which is added in the initial list of emotion dictionary, is used as seed words, if adjective in initial list, its word frequency
Add 1, it is 1 otherwise to set the adjectival word frequency, returns to the 3rd step；
6th step, obtained final emotion dictionary is traveled through, pair simultaneously be judged as positive and passive word, take
Its word frequency, if belonging to positive word frequency height, the word is positive, otherwise to be passive.
Of the invention to be compared with existing emotion word construction method, its remarkable advantage is：(1) save time and labour into
This.This method can extract adjective automatically as emotion word according to language material, and differentiate its feeling polarities, generate positive and passiveness two
Individual sentiment dictionary.Time and efforts is greatlyd save than artificial mark.(2) it is highly reliable.The sentiment dictionary construction method is repeatedly abided by
Majority principle is followed, is handled for some disturbed conditions being likely to occur, to ensure the accuracy of algorithm.(3) it is versatile.
The algorithm can generate field emotion word according to the language material of every field.(4) sentiment dictionary of generation can be comment and analysis, natural
Language Processing provides important reference frame.
Brief description of the drawings
Fig. 1 is that emotion word list ownership differentiates flow chart.
Fig. 2 is sentiment dictionary product process figure.
Embodiment
The inventive method comprises the following steps：
The first step：Using the language material for having carried out word segmentation processing, these language materials are usually subjective comment, and what be will appear from describes
Word sorts from high to low by word frequency, and 5%~10% has the adjective for determining feeling polarities before extraction, is marked according to Hownet (Hownet)
Its feeling polarities is noted as seed words, forms emotion dictionary；
Second step：Make pauses in reading unpunctuated ancient writings by punctuation mark, generate short sentence one by one；
3rd step：Short sentence scans one by one, extracts adjective.Two temporary tables are built, for storing two feeling polarities
Adjective.For adjective, judge whether it has negative word modification, if then polarity negates, be stored in corresponding temporary table；
Judge whether short sentence is started with adversative again, if it is, polarity negates again, be stored in corresponding temporary table；
4th step：For obtained temporary table, go to judge with existing seed dictionary.Contain the row more than positive emotion word
Table is then positive emotion word list, is otherwise Negative Affect word list.Go to judge unknown feelings here with existing emotion word
Word is felt, according to majority principle, because the word in list all has phase feeling of sympathy, if the word list of a unknown feeling polarities contains
There are the seed words of more positive emotion, then the emotion word being considered as in list is all positive, if instead containing more
Negative Affect seed words, then all words in list think it is all passive, this can suitably be reduced because language material is not advised indirectly
Model and caused by error；
5th step：The new emotion word that 4th step obtains is added in seed words, the foundation judged as next time.So
Constantly expand original emotion dictionary so that with increasing for language material is read, the accuracy rate of judgement improves constantly.
6th step：After having read all language materials, two emotion word dictionaries to the end are obtained.May wherein there are some words,
I.e. in the dictionary of positive emotion, and in the dictionary of Negative Affect.Because language material there may be lack of standard, list may be caused
Word misjudgment, now according to majority principle, according to the word, generic judges in most cases.
The present invention is described in further detail below in conjunction with the accompanying drawings.
Sentiment dictionary building method of the invention based on language material, first with existing participle instrument, enters to original language material
Row participle and part-of-speech tagging processing.Then 5%~10% before extraction word frequency highest, and the feelings provided according to Hownet (Hownet)
Feel analysis word collection, feeling polarities are marked, as seed words.Then make pauses in reading unpunctuated ancient writings to language material according to punctuate, then scan corpus, pin
Each is commented on, adjective is divided into opposite polarity two class, then judged with existing seed words.Obtain its emotion pole
Property, continue to judge comment below using them as seed words.The situation for belonging to two classes simultaneously is finally eliminated, obtains final feelings
Feel dictionary.This method is all suitable under any field, only need to provide corresponding language material.
Fig. 1 is the generating process for describing word list, it can be seen that for an adjective, it is necessary to according to whetheing there is negative word,
Whether there is adversative, integral polarity three conditions that whether change are judged.With reference to Fig. 2, the emotion of the invention based on language material
Dictionary construction algorithm, step are as follows：
The first step：Original language material is segmented, part-of-speech tagging processing, language material is usually the comments with subjective colo(u)r
Sentence.Some Open-Source Tools may be used herein, such as：Knot, ICTCLAS etc., obtain word separated one by one or word and
Its part of speech, punctuate are also taken as a word processing.
Second step：All comments are scanned, obtain all adjective word frequency, are taken 5%~10% before word frequency highest, utilize
In ' sentiment analysis word collection ' that Hownet (Hownet) provides《Positive evaluates word (Chinese)》With《Unfavorable ratings word
(Chinese)》, its feeling polarities is marked, as seed words, forms initial emotion dictionary.
3rd step：Learnt from else's experience pretreatment language material in text, if so, making pauses in reading unpunctuated ancient writings according to punctuate to text, obtain more
Individual subordinate sentence, punctuate is free of in subordinate sentence；If no, go to the 7th step；
4th step：To the comment containing more words, scan sentence by sentence, find adjective, i.e., suffix for/a or/an word,
Here it is candidate's emotion word.
5th step：For a complete sentence in language material, three variables are set.Current polarity plor, is initially 1；
Deposit two lists s and a of emotion word, deposit the emotion word (but its unknown specific emotion) of two polarity respectively, in s storage with
Initial polarity identical word, the word opposite with initial emotion is deposited in a.Search and position an adjective, set window value big
Small, desirable different value, generally 3, judge whether there is negative word in the range of left window, if so, then according to pole as needed
Property transition rule be added in respective list, otherwise stop find negative word；There is turnover further according to what is pointed out in Chinese dictionary
The word of meaning, judges whether the subordinate sentence is started with adversative, if then changing current polarity according to polarity transition rule, i.e.,
Plor takes negative, and otherwise polarity is constant, then respectively by polarity transition rule by the adjective in subordinate sentence be added to two list s and
In a.It is as follows that emotion word is put into list (ACL) regulations：
A. there is adversative there is no negative word, if plor=1, illustrate that polarity does not overturn or overturn by even-times
It is identical with original polarity, then adjective is put into list a, Plor takes negative；Otherwise, if plor=-1, it is strange to illustrate that polarity occurs
Overturn, be then put into s for several times, Plor takes negative.
B. there is adversative to have negative word, if plor=1, adjective is put into s, plor takes negative；Otherwise it is put into a,
Plor takes negative.
C. no adversative has negative word, if plor=1, adjective is put into list a, plor takes negative；Otherwise put
Enter in s, plor takes negative.
D. no adversative does not have negative word, if plor=1, adjective is put into list s, plor takes negative；Otherwise
It is put into a, plor takes negative.
For example：" totality/n is pretty good/a./ wp is exactly/d a little/d is expensive/a, logistics/n not /d is /v very/d is fast/a.No
Cross/d still/d very/d satisfactions/a /u once/q net purchases/n ,/wp praise/v！The initial plor=1 of/wp ".Find and describe after punctuate
Word, find first " good ", plor=1, look for negative word according to window size, do not find, beginning of the sentence is not adversative, " good "
It is put into s lists；Find " expensive " again, before do not negate to have " being exactly " adversative, so " expensive " and adjective polarity before are anti-
Turn, because plor=1, be put into a lists, while plor is changed into -1；3rd adjective " fast ", has negative word, does not have
Adversative, because plor=-1, according to above-mentioned rule, it is put into s lists；Last adjective " satisfaction ", do not negate,
There is turnover, now because plor=-1, be put into s lists, while plor is changed into 1. end products：It is in s " good ", " fast ", it is " full
Meaning "；It is in a " expensive ".
6th step：All adjectives in one comment are divided into two lists by rule, are gone to judge this with seed words
The polarity of word in two lists.If the seed words number containing positive emotion is more than the seed words of Negative Affect in a list
Number, then adjective all in the list is all put into the seed word list of positive emotion, and another is then put into Negative Affect
In seed word list.
7th step：Finally obtain the word frequency of two sentiment dictionaries and emotion word in language material.Because language material is lack of standardization
Property, may occur simultaneously in two dictionaries in the presence of some word, this is not allowed to.So if the word belongs to positive
Word frequency is more than the passive word frequency after weighting, then the emotion of the word is positive to be otherwise considered as passiveness.
The inventive method makes full use of the emotion word obtained in algorithmic procedure, constantly expands seed words.Finally by data
Compare, it is of a relatively high according to majority principle, differentiation emotion, energy exclusive segment interference data, accuracy rate.
Claims (1)
1. a kind of sentiment dictionary construction method based on language material, it is characterised in that comprise the following steps：
The first step, using Chinese word segmentation instrument, language material is pre-processed, continuous Chinese sentence in language material is divided into one
Individual word or word, are separated with space, and the part of speech of tagged words or word；
Second step, count in language material all adjectival word frequency and by being ranked up from high to low, 5%-10% has determination before taking
The adjective of feeling polarities forms emotion dictionary as seed words, and analyzes the feeling polarities of seed words, by the word of front evaluation
Polarity be referred to as positive, it is passive that the polarity of the word of unfavorable ratings is referred to as, and respectively constitutes two seed word lists, the two
Initial list of the seed word list as emotion dictionary, initial word frequency are 1；
3rd step, learnt from else's experience pretreatment language material in text, the language material analyzed if necessary, text is broken according to punctuate
Sentence, obtains multiple subordinate sentences, is free of punctuate in subordinate sentence, continues executing with the 4th step；If not needing the language material analyzed, the 6th is gone to
Step；
4th step, the adjective searched in obtained each subordinate sentence, set a threshold k, the preceding K in adjective position
Traveled through in the range of individual word or word, according to the word with Negation pointed out in Chinese dictionary, determine whether negative word, if
Have, be then added to according to polarity transition rule in respective list, otherwise stop finding negative word；Further according to being pointed out in Chinese dictionary
Have turnover meaning word, judge the subordinate sentence whether started with adversative, if so, then according to polarity transition rule change work as
Preceding polarity, otherwise polarity is constant；Then the adjective in subordinate sentence is added to two lists s and a by polarity transition rule respectively
In；
5th step, two lists s and a that the 4th step of analysis obtains polarity, i.e., examine list s with the seed words in emotion dictionary
With a polarity, if the number containing positive seed words is no less than passive seed words in one of list, institute in the list
Some words be classified as it is positive, the word in another list be then classified as passiveness；If respectively contain identical quantity in two lists
Passive seed words and positive seed words, then return to the 3rd step；Otherwise, judging that the adjective of polarity adds in two lists s and a
It is added in the initial list of emotion dictionary and is used as seed words, if adjective in initial list, its word frequency is added 1, it is no
It is 1 then to set the adjectival word frequency, returns to the 3rd step；
6th step, obtained final emotion dictionary is traveled through, pair simultaneously be judged as positive and passive word, take it
Word frequency, if belonging to positive word frequency height, the word is positive, otherwise to be passive；
Polarity transition rule in 4th step is specific as follows：
Plor variables are set, and whether the polarity for representing between subordinate sentence shifts, and is initially 1,1 expression and even-times turn occurs
Folding so that the subordinate sentence of punctuate connection is identical with initial polarity, and -1 represents odd-times turnover occur so that the subordinate sentence of punctuate connection
It is opposite with initial polarity；Adjective acquiescence is put into in initial polarity identical list s, being put in list a opposite with initial polarity
Word, be divided into four kinds of situations：
Subordinate sentence, which starts, adversative, does not have negative word in K word or word before adjective, if plor=1, adjective is put into
In list a, otherwise it is put into list s, plor becomes -1；
Subordinate sentence, which starts, adversative, has negative word in K word or word before adjective, if plor=1, adjective is put into s
In, otherwise it is put into list a, plor becomes -1；
Subordinate sentence starts no adversative, has negative word in K word or word before adjective, if plor=1, adjective is put into
In list a, otherwise it is put into list s；
Subordinate sentence starts no adversative, does not have negative word in K word or word before adjective, if plor=1, adjective is put
Into list s, otherwise it is put into list a.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410649358.7A CN104317965B (en) | 2014-11-14 | 2014-11-14 | Sentiment dictionary construction method based on language material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410649358.7A CN104317965B (en) | 2014-11-14 | 2014-11-14 | Sentiment dictionary construction method based on language material |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104317965A CN104317965A (en) | 2015-01-28 |
| CN104317965B true CN104317965B (en) | 2018-04-03 |
Family
ID=52373197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410649358.7A Expired - Fee Related CN104317965B (en) | 2014-11-14 | 2014-11-14 | Sentiment dictionary construction method based on language material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104317965B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095190B (en) * | 2015-08-25 | 2018-01-12 | 众联数据技术（南京）有限公司 | A kind of sentiment analysis method combined based on Chinese semantic structure and subdivision dictionary |
| CN105760502A (en) * | 2016-02-23 | 2016-07-13 | 常州普适信息科技有限公司 | Commercial quality emotional dictionary construction system based on big data text mining |
| CN106610955A (en) * | 2016-12-13 | 2017-05-03 | 成都数联铭品科技有限公司 | Dictionary-based multi-dimensional emotion analysis method |
| CN108694165B (en) * | 2017-04-10 | 2021-11-09 | 南京理工大学 | Cross-domain dual emotion analysis method for product comments |
| CN107608953B (en) * | 2017-07-25 | 2020-08-14 | 同济大学 | Word vector generation method based on indefinite-length context |
| CN108563635A (en) * | 2018-04-04 | 2018-09-21 | 北京理工大学 | A kind of sentiment dictionary fast construction method based on emotion wheel model |
| CN108647191B (en) * | 2018-05-17 | 2021-06-25 | 南京大学 | Sentiment dictionary construction method based on supervised sentiment text and word vector |
| CN109800418B (en) * | 2018-12-17 | 2023-05-05 | 北京百度网讯科技有限公司 | Text processing method, device and storage medium |
| CN110287319B (en) * | 2019-06-13 | 2021-06-15 | 南京航空航天大学 | Student evaluation text analysis method based on emotion analysis technology |
| CN112905736B (en) * | 2021-01-27 | 2023-09-19 | 郑州轻工业大学 | Quantum theory-based unsupervised text emotion analysis method |
| CN115796158A (en) * | 2023-02-07 | 2023-03-14 | 中国传媒大学 | Emotion dictionary construction method and device, electronic equipment and computer readable medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102323944A (en) * | 2011-09-02 | 2012-01-18 | 苏州大学 | Sentiment classification method based on polarity transfer rules |
| CN103020249A (en) * | 2012-12-19 | 2013-04-03 | 苏州大学 | Classifier construction method and device as well as Chinese text sentiment classification method and system |
-
2014
- 2014-11-14 CN CN201410649358.7A patent/CN104317965B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102323944A (en) * | 2011-09-02 | 2012-01-18 | 苏州大学 | Sentiment classification method based on polarity transfer rules |
| CN103020249A (en) * | 2012-12-19 | 2013-04-03 | 苏州大学 | Classifier construction method and device as well as Chinese text sentiment classification method and system |
Non-Patent Citations (1)
| Title |
|---|
| Predicting the Semantic Orientation of Adjectives;Hatzivassiloglou V, McKeown K R;《Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics》;19970712;174-181 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104317965A (en) | 2015-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104317965B (en) | Sentiment dictionary construction method based on language material | |
| CN110852087B (en) | Chinese error correction method and device, storage medium and electronic device | |
| CN107092596B (en) | Text emotion analysis method based on attention CNNs and CCR | |
| CN106649603B (en) | Designated information pushing method based on emotion classification of webpage text data | |
| Amin et al. | Bengali vader: A sentiment analysis approach using modified vader | |
| CN105005553B (en) | Short text Sentiment orientation analysis method based on sentiment dictionary | |
| CN106407236B (en) | A kind of emotion tendency detection method towards comment data | |
| CN107239439A (en) | Public sentiment sentiment classification method based on word2vec | |
| CN104331506A (en) | Multiclass emotion analyzing method and system facing bilingual microblog text | |
| CN108388554B (en) | Text emotion recognition system based on collaborative filtering attention mechanism | |
| CN101127042A (en) | Sensibility classification method based on language model | |
| CN104881402A (en) | Method and device for analyzing semantic orientation of Chinese network topic comment text | |
| CN106096664A (en) | A kind of sentiment analysis method based on social network data | |
| CN102096680A (en) | Method and device for analyzing information validity | |
| CN105022805A (en) | Emotional analysis method based on SO-PMI (Semantic Orientation-Pointwise Mutual Information) commodity evaluation information | |
| CN106202584A (en) | A kind of microblog emotional based on standard dictionary and semantic rule analyzes method | |
| CN106021288A (en) | Method for rapid and automatic classification of classroom testing answers based on natural language analysis | |
| CN106126502A (en) | A kind of emotional semantic classification system and method based on support vector machine | |
| CN106445990A (en) | Event ontology construction method | |
| CN106446147A (en) | Emotion analysis method based on structuring features | |
| CN104346326A (en) | Method and device for determining emotional characteristics of emotional texts | |
| CN110147552B (en) | Education resource quality evaluation mining method and system based on natural language processing | |
| CN110851601A (en) | Cross-domain emotion classification system and method based on layered attention mechanism | |
| CN105912522A (en) | Automatic extraction method and extractor of English corpora based on constituent analyses | |
| CN104778240A (en) | Micro blog text data classification method on basis of multi-feature fusion |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180403 Termination date: 20201114 |