CN106682136A - Traditional-Chinese-medicine medical literature classification and storage method based on data mining - Google Patents
Traditional-Chinese-medicine medical literature classification and storage method based on data mining Download PDFInfo
- Publication number
- CN106682136A CN106682136A CN201611174644.8A CN201611174644A CN106682136A CN 106682136 A CN106682136 A CN 106682136A CN 201611174644 A CN201611174644 A CN 201611174644A CN 106682136 A CN106682136 A CN 106682136A
- Authority
- CN
- China
- Prior art keywords
- data
- key word
- traditional
- traditional chinese
- chinese
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000007418 data mining Methods 0.000 title claims abstract description 10
- 239000003814 drug Substances 0.000 title abstract description 20
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 238000004321 preservation Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 238000013075 data extraction Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
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
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a traditional-Chinese-medicine medical literature classification and storage method based on data mining. The classification and storage method include the following steps: acquiring a traditional-Chinese-medicine medical literature basic database; according to a sequential order of loading, saving the literature by a specific coding form; extracting key information from the loaded unstructured text data, and establishing a coding schedule of the key information of the traditional-Chinese-medicine medical literature; dividing all the keywords corresponding to core data into a number of core data groups; at the same time, dividing all the keywords corresponding to non-core data into a number of non-core data groups; acquiring keyword combinations of traditional-Chinese-medicine literature, and according to the keyword combinations which are used as searching keywords, acquiring corresponding traditional-Chinese-medicine literature which is used as the traditional-Chinese-medicine medical literature, saving the traditional-Chinese-medicine medical literature, and using the keyword combinations of the traditional-Chinese-medicine literature as storage identifiers of the traditional-Chinese-medicine medical literature. The method achieves high-efficiency and accurate acquirement of traditional-Chinese-medicine medical literature data, and finishes accurate classification and storage of the traditional-Chinese-medicine medical literature.
Description
Technical field
The present invention relates to data in literature processing technology field, particularly a kind of traditional Chinese medical science medical literature based on data mining
Classification and storage method.
Background technology
Chinese medicine is the important component part shown unique characteristics with advantage in China Today medical and health cause, for abundant generation
Boundary's medical treasure-house, protection human health, produce positive effect.Under the new situation, the correlational study in China's Chinese medicine field exists
While emphasis inherits classical, the mixing together in the field such as same emphasis and western medicine, pharmacy, informaticss, biology is formed
New subject growth point, in academic research field research theme sending out across double subjects or multi-disciplinary scientific paper is then shown as
Table.In medical research field, domain experts, scholar are typically based on qualitatively research method, on a large amount of bases for reading document
On, the study hotspot of certain field or subject is recognized according to its research experience and accumulation subjectivity, form summary class document or report
Accuse, for using for reference.
Prior art is all based at present manual analyses and arranges Chinese medicine document, is also based on without a kind of the scientific of science
The document classification mode of big data analysis.
The content of the invention
To solve above-mentioned technical problem, the invention provides a kind of traditional Chinese medical science medical literature based on data mining is classified and is deposited
Method for storing, it is comprised the following steps：
Line retrieval is entered by traditional Chinese medical science search key in specific knowledge data base, some retrievals with the traditional Chinese medical science are got
The TCM Document of Keywords matching is used as traditional Chinese medical science medical literature basic database；
Respectively according to the sequencing downloaded, a flat file the inside is incorporated into, with the preservation of specific coded format；
Then the non-structured text data to downloading carries out key message extraction, preserves into specific data form,
The coding schedule of the key message of traditional Chinese medical science medical literature is set up, the key message corresponds to respectively a binary coding；
The key message includes core data and noncore data two types, the data for extracting, and is stored in first
Associated databases, used as the basic data of next step data processing, then leading carries out the mining analysis of next step in people SQL；Institute
It is the key word for exceeding given threshold frequency in the text data downloaded to state core data, and the noncore data is the text downloaded
Occurred in notebook data at least one times and less than the key word of given threshold；The data pattern of the corresponding key word i of core data
A relation table Hi (B1, B2 ..., Bmi) can be expressed as, wherein B is the property value of the key word, the attribute of each key word
Value is preset according to the specific field of the key word place traditional Chinese medical science；Key word corresponding data base D1, D2 ..., Dni }
Data pattern can correspond on Hi；The data pattern of the wherein corresponding key word j of noncore data can be expressed as one
Individual relation table Hj (B1, B2 ..., Bmj), wherein B are the attribute of the key word, key word corresponding data base D1, D2 ...,
Dnj } data pattern can correspond on Hj；
The degree of association quantized value of concrete each key word is K (Bmi, Dni)=ρdist(Bmi,Dni)- 1, K (Bmj, Dnj)=
ρdist(Bmj,Dnj)- 1, dist (Bmi, Dni) are the Euclidean distance between Bmi, Dni, and dist (Bmj, Dnj) is between Bmj, Dnj
Euclidean distance, ρ ＞ 1 be contraction-expansion factor；The corresponding key word i of wherein K (Bmi, Dni), K (Bmj, Dnj) expression core data,
The degree of association quantized value of the corresponding key word j of noncore data, the institute by degree of association quantized value in the range of given threshold value is relevant
Keyword is divided into the corresponding all key words of core data in some core data groups as a keyword data group；Together
When the corresponding all key words of noncore data are divided in some noncore data groups；
Corresponding key word in the core data group and corresponding key word in the noncore data group are carried out with
Machine combination of two, gets the combination of TCM Document key word, and crucial for retrieval according to TCM Document crucial phrase cooperation
Word gets corresponding TCM Document as traditional Chinese medical science medical literature, and the traditional Chinese medical science medical literature is stored, and will be described in
The combination of doctor's document keyword is identified as traditional Chinese medical science medical literature storage.
The invention has the advantages that：
The traditional Chinese medical science medical literature classification based on data mining and storage method that the present invention is provided is based on Chinese medicine data base
Keyword retrieval, and data extraction is carried out by the document to retrieving, the key message to getting carries out data mining point
Analysis, obtains keyword data group, and the key word in keyword data group is combined into line retrieval and obtains the related traditional Chinese medical science
Medical literature, and be traditional Chinese medical science medical literature storage mark by TCM Document crucial phrase cooperation.Present invention achieves
Efficiently with accurately acquisition Chinese medicine data in literature, the precise classification storage of traditional Chinese medical science medical literature is completed.
Certainly, the arbitrary product for implementing the present invention it is not absolutely required to while reaching all the above advantage.
Specific embodiment
The technical scheme in the present invention is clearly and completely described below in conjunction with the embodiment of the present invention, it is clear that institute
The embodiment of description is only a part of embodiment of the invention, rather than the embodiment of whole.Based on the embodiment in the present invention,
All other embodiment that those of ordinary skill in the art are obtained under the premise of creative work is not made, belongs to this
The scope of bright protection.
A kind of traditional Chinese medical science medical literature classification based on data mining and storage method are embodiments provided, it includes
Following steps：
Line retrieval is entered by traditional Chinese medical science search key in specific knowledge data base, some retrievals with the traditional Chinese medical science are got
The TCM Document of Keywords matching is used as traditional Chinese medical science medical literature basic database；
Respectively according to the sequencing downloaded, a flat file the inside is incorporated into, with the preservation of specific coded format；
Then the non-structured text data to downloading carries out key message extraction, preserves into specific data form,
The coding schedule of the key message of traditional Chinese medical science medical literature is set up, the key message corresponds to respectively a binary coding；
The key message includes core data and noncore data two types, the data for extracting, and is stored in first
Associated databases, used as the basic data of next step data processing, then leading carries out the mining analysis of next step in people SQL；Institute
It is the key word for exceeding given threshold frequency in the text data downloaded to state core data, and the noncore data is the text downloaded
Occurred in notebook data at least one times and less than the key word of given threshold；The data pattern of the corresponding key word i of core data
A relation table Hi (B1, B2 ..., Bmi) can be expressed as, wherein B is the property value of the key word, the attribute of each key word
Value is preset according to the specific field of the key word place traditional Chinese medical science；Key word corresponding data base D1, D2 ..., Dni }
Data pattern can correspond on Hi；The data pattern of the wherein corresponding key word j of noncore data can be expressed as one
Individual relation table Hj (B1, B2 ..., Bmj), wherein B are the attribute of the key word, key word corresponding data base D1, D2 ...,
Dnj } data pattern can correspond on Hj；
The degree of association quantized value of concrete each key word is K (Bmi, Dni)=ρdist(Bmi,Dni)- 1, K (Bmj, Dnj)=
ρdist(Bmj,Dnj)- 1, dist (Bmi, Dni) are the Euclidean distance between Bmi, Dni, and dist (Bmj, Dnj) is between Bmj, Dnj
Euclidean distance, ρ ＞ 1 be contraction-expansion factor；The corresponding key word i of wherein K (Bmi, Dni), K (Bmj, Dnj) expression core data,
The degree of association quantized value of the corresponding key word j of noncore data, the institute by degree of association quantized value in the range of given threshold value is relevant
Keyword is divided into the corresponding all key words of core data in some core data groups as a keyword data group；Together
When the corresponding all key words of noncore data are divided in some noncore data groups；
Corresponding key word in the core data group and corresponding key word in the noncore data group are carried out with
Machine combination of two, gets the combination of TCM Document key word, and crucial for retrieval according to TCM Document crucial phrase cooperation
Word gets corresponding TCM Document as traditional Chinese medical science medical literature, and the traditional Chinese medical science medical literature is stored, and will be described in
The combination of doctor's document keyword is identified as traditional Chinese medical science medical literature storage.
The traditional Chinese medical science medical literature acquisition methods that the present invention is provided are based on Chinese medicine keyword search over database, and by inspection
Rope to document carry out data extraction, the key message to getting carries out data mining analysis, obtains keyword data group, and
Key word in keyword data group is combined into line retrieval and obtains related traditional Chinese medical science medical literature, and the traditional Chinese medical science is literary
Crucial phrase cooperation is offered for traditional Chinese medical science medical literature storage mark.Present invention achieves efficiently literary with accurately acquisition Chinese medicine
Data are offered, the precise classification storage of traditional Chinese medical science medical literature is completed.
Present invention disclosed above preferred embodiment is only intended to help and illustrates the present invention.Preferred embodiment is not detailed
All of details is described, it is only described specific embodiment also not limit the invention.Obviously, according to the content of this specification,
Can make many modifications and variations.These embodiments are chosen and specifically described to this specification, is to preferably explain the present invention
Principle and practical application so that skilled artisan can be best understood by and utilize the present invention.The present invention is only
Limited by claims and its four corner and equivalent.
Claims (1)
1. a kind of classification of traditional Chinese medical science medical literature and storage method based on data mining, it is characterised in that comprise the following steps：
Line retrieval is entered by traditional Chinese medical science search key in specific knowledge data base, is got some crucial with traditional Chinese medical science retrieval
The TCM Document of word matching is used as traditional Chinese medical science medical literature basic database；
Respectively according to the sequencing downloaded, a flat file the inside is incorporated into, with the preservation of specific coded format；
Then the non-structured text data to downloading carries out key message extraction, preserves into specific data form, sets up
The coding schedule of the key message of traditional Chinese medical science medical literature, the key message corresponds to respectively a binary coding；
The key message includes core data and noncore data two types, the data for extracting, and is stored in first corresponding
Data base, used as the basic data of next step data processing, then leading carries out the mining analysis of next step in people SQL；The core
According to the key word for exceeding given threshold frequency in the text data for download, the noncore data is the textual data downloaded to calculation
Occurred at least one times and less than the key word of given threshold according to middle；The data pattern of the corresponding key word i of core data can be with
It is expressed as a relation table Hi (B1, B2 ..., Bmi), wherein B is the property value of the key word, the property value root of each key word
Preset according to the specific field of the key word place traditional Chinese medical science；The number of the corresponding data base of key word { D1, D2 ..., Dni }
Can correspond on Hi according to pattern；The data pattern of the wherein corresponding key word j of noncore data can be expressed as a pass
It is table Hj (B1, B2 ..., Bmj), wherein B is the attribute of the key word, key word corresponding data base D1, D2 ..., Dnj }
Data pattern can correspond on Hj；
The degree of association quantized value of concrete each key word is K (Bmi, Dni)=ρdist(Bmi,Dni)- 1, K (Bmj, Dnj)=
ρdist(Bmj,Dnj)- 1, dist (Bmi, Dni) are the Euclidean distance between Bmi, Dni, and dist (Bmj, Dnj) is between Bmj, Dnj
Euclidean distance, ρ ＞ 1 be contraction-expansion factor；The corresponding key word i of wherein K (Bmi, Dni), K (Bmj, Dnj) expression core data,
The degree of association quantized value of the corresponding key word j of noncore data, the institute by degree of association quantized value in the range of given threshold value is relevant
Keyword is divided into the corresponding all key words of core data in some core data groups as a keyword data group；Together
When the corresponding all key words of noncore data are divided in some noncore data groups；
Random two are carried out with corresponding key word in the noncore data group to corresponding key word in the core data group
Two combinations, get the combination of TCM Document key word, and are obtained for search key according to the TCM Document crucial phrase cooperation
Corresponding TCM Document is got as traditional Chinese medical science medical literature, the traditional Chinese medical science medical literature is stored, and the traditional Chinese medical science is literary
Crucial phrase cooperation is offered for traditional Chinese medical science medical literature storage mark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611174644.8A CN106682136B (en) | 2016-12-19 | 2016-12-19 | A kind of classification of traditional Chinese medical science medical literature and storage method based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611174644.8A CN106682136B (en) | 2016-12-19 | 2016-12-19 | A kind of classification of traditional Chinese medical science medical literature and storage method based on data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106682136A true CN106682136A (en) | 2017-05-17 |
| CN106682136B CN106682136B (en) | 2018-03-16 |
Family
ID=58869635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611174644.8A Expired - Fee Related CN106682136B (en) | 2016-12-19 | 2016-12-19 | A kind of classification of traditional Chinese medical science medical literature and storage method based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106682136B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111314030A (en) * | 2020-03-11 | 2020-06-19 | 重庆邮电大学 | SCMA (sparse code multiple access) multi-user detection method based on spherical decoding optimization |
| WO2022160539A1 (en) * | 2021-01-26 | 2022-08-04 | 浪达网络科技(浙江)有限公司 | Data processing system and data mining method |
| CN116431838A (en) * | 2023-06-15 | 2023-07-14 | 北京墨丘科技有限公司 | Document retrieval method, device, system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030236785A1 (en) * | 2002-06-21 | 2003-12-25 | Takahiko Shintani | Method of extracting item patterns across a plurality of databases, a network system and a processing apparatus |
| US20080063264A1 (en) * | 2006-09-08 | 2008-03-13 | Porikli Fatih M | Method for classifying data using an analytic manifold |
| CN101149751A (en) * | 2007-10-29 | 2008-03-26 | 浙江大学 | Generalized relating rule digging method for analyzing traditional Chinese medicine recipe drug matching rule |
| CN101599088A (en) * | 2008-11-18 | 2009-12-09 | 北京美智医疗科技有限公司 | The mining multi-dimensional data system and method for medical information system |
| CN104978347A (en) * | 2014-04-11 | 2015-10-14 | 中国中医科学院中医临床基础医学研究所 | Data mining method and data mining system for sensitive keywords in Chinese biomedical literature database |
-
2016
- 2016-12-19 CN CN201611174644.8A patent/CN106682136B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030236785A1 (en) * | 2002-06-21 | 2003-12-25 | Takahiko Shintani | Method of extracting item patterns across a plurality of databases, a network system and a processing apparatus |
| US20080063264A1 (en) * | 2006-09-08 | 2008-03-13 | Porikli Fatih M | Method for classifying data using an analytic manifold |
| CN101149751A (en) * | 2007-10-29 | 2008-03-26 | 浙江大学 | Generalized relating rule digging method for analyzing traditional Chinese medicine recipe drug matching rule |
| CN101599088A (en) * | 2008-11-18 | 2009-12-09 | 北京美智医疗科技有限公司 | The mining multi-dimensional data system and method for medical information system |
| CN104978347A (en) * | 2014-04-11 | 2015-10-14 | 中国中医科学院中医临床基础医学研究所 | Data mining method and data mining system for sensitive keywords in Chinese biomedical literature database |
Non-Patent Citations (2)
| Title |
|---|
| 古求知 等: "中医医案类文献的分析挖掘研究", 《辽宁中医杂志》 * |
| 金力 等: "数据挖掘在中医诊疗规则提取中的应用研究", 《时珍国医国药》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111314030A (en) * | 2020-03-11 | 2020-06-19 | 重庆邮电大学 | SCMA (sparse code multiple access) multi-user detection method based on spherical decoding optimization |
| WO2022160539A1 (en) * | 2021-01-26 | 2022-08-04 | 浪达网络科技(浙江)有限公司 | Data processing system and data mining method |
| CN116431838A (en) * | 2023-06-15 | 2023-07-14 | 北京墨丘科技有限公司 | Document retrieval method, device, system and storage medium |
| CN116431838B (en) * | 2023-06-15 | 2024-01-30 | 北京墨丘科技有限公司 | Document retrieval method, device, system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106682136B (en) | 2018-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105095195B (en) | Nan-machine interrogation's method and system of knowledge based collection of illustrative plates | |
| CN103123618B (en) | Text similarity acquisition methods and device | |
| CN107784102A (en) | A kind of data difference comparative approach based on oracle database | |
| CN102789464B (en) | Natural language processing methods, devices and systems based on semantics identity | |
| CN104008106A (en) | Method and apparatus for obtaining hot topic | |
| RU2010107150A (en) | IDENTIFICATION OF SEMANTIC RELATIONS IN INDIRECT SPEECH | |
| CN106682209A (en) | Cross-language scientific and technical literature retrieval method and cross-language scientific and technical literature retrieval system | |
| CN106682136A (en) | Traditional-Chinese-medicine medical literature classification and storage method based on data mining | |
| WO2020155749A1 (en) | Method and apparatus for constructing personal knowledge graph, computer device, and storage medium | |
| CN106227788A (en) | Database query method based on Lucene | |
| CN107291858A (en) | Data indexing method based on character string suffix | |
| WO2019228015A1 (en) | Index creating method and apparatus based on nosql database of mobile terminal | |
| CN104252542A (en) | Dynamic-planning Chinese words segmentation method based on lexicons | |
| CN103838876A (en) | Method for retrieving document through pinyin and document retrieval system | |
| CN111061828A (en) | Digital library knowledge retrieval method and device | |
| CN106802937A (en) | The conversion method and system of Word document | |
| CN103150409B (en) | Method and system for recommending user search word | |
| CN106777137B (en) | A kind of traditional Chinese medicine document analysis method | |
| CN105630822A (en) | Method for marking similar contents in patent retrieval in red color | |
| CN103927339A (en) | System and method for reorganizing knowledge | |
| CN104850559A (en) | Slide independent storage, retrieval and recombination method and equipment based on presentation document | |
| CN106295252A (en) | Search method for gene prod | |
| CN107870935A (en) | A kind of searching method and device | |
| Yuan et al. | A mathematical information retrieval system based on RankBoost | |
| CN103853832B (en) | Customizable data grasping means in a kind of text retrieval system |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Liu Kai Inventor after: Wu Zhili Inventor before: Tan Hongchun Inventor before: Meng Qingquan Inventor before: Gu Zongyun Inventor before: Geng Yingbao |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20180208 Address after: 518000 Nanshan District, Guangdong Tsinghua Science and technology information research building,, Shenzhen Applicant after: Liu Kai Address before: 230000 Mei Shan Road, Shushan District, Hefei, Anhui Province, No. 70 Applicant before: Tan Hongchun |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180913 Address after: 518000 Beek, science and technology building, room 9, No. 9, research road, high tech Zone, Nanshan District, Shenzhen, Guangdong. Patentee after: Shenzhen Yiyuan Intelligent Technology Co., Ltd. Address before: 518000 scientific research building, Tsinghua information port, Nanshan District, Shenzhen, Guangdong 107 Patentee before: Liu Kai |
|
| 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: 20180316 Termination date: 20181219 |