zh:notes:electric_power
差别
这里会显示出您选择的修订版和当前版本之间的差别。
| 两侧同时换到之前的修订记录 前一修订版 后一修订版 | 前一修订版 | ||
|
zh:notes:electric_power [2024/04/03 21:18] pzczxs [Update Cited Patents with Target Ones] |
zh:notes:electric_power [2024/05/19 22:08] (当前版本) pzczxs [Attributes Extraction] |
||
|---|---|---|---|
| 行 1: | 行 1: | ||
| ====== Data Construction for Electric Power Domain ====== | ====== Data Construction for Electric Power Domain ====== | ||
| ===== Requirements ===== | ===== Requirements ===== | ||
| - | *[[https://opennlp.apache.org/|OpenNLP 1.9.0]] | + | *[[https://opennlp.apache.org/|OpenNLP 1.9.2]] |
| *[[http://bioc.sourceforge.net/|BioC]] | *[[http://bioc.sourceforge.net/|BioC]] | ||
| ===== Data Sources ===== | ===== Data Sources ===== | ||
| 行 68: | 行 68: | ||
| The fundings can be merged by running <color red>FundingMerger.java</color> in the package <color red>cn.edu.bjut.ui</color> according to grant number. | The fundings can be merged by running <color red>FundingMerger.java</color> in the package <color red>cn.edu.bjut.ui</color> according to grant number. | ||
| + | |||
| + | <code bash> | ||
| + | > nohup ./merge-funding.sh > merge-funding.log 2>&1 | ||
| + | </code> | ||
| ==== Update Keyword ==== | ==== Update Keyword ==== | ||
| <color red>KeywordUpdater.java</color> | <color red>KeywordUpdater.java</color> | ||
| + | |||
| + | <code bash> | ||
| + | > nohup ./import-wos-keyword.sh 0 ../dataset/WoS/papers > import-wos-keyword.log 2>&1 | ||
| + | </code> | ||
| ==== Merge Cited Articles ==== | ==== Merge Cited Articles ==== | ||
| <code sql> | <code sql> | ||
| 行 153: | 行 161: | ||
| <code bash> | <code bash> | ||
| - | > nohup ./update-article-technology.sh -l 0 > update-article-technology.log 2>&1 | + | > nohup ./update-article-technology.sh 0 > update-article-technology.log 2>&1 |
| </code> | </code> | ||
| ===== Derwent Innovation Index ===== | ===== Derwent Innovation Index ===== | ||
| 行 175: | 行 183: | ||
| <code bash> | <code bash> | ||
| > nohup ./update-patent-cited-patent.sh > patent-cited-patent.log 2>&1 | > nohup ./update-patent-cited-patent.sh > patent-cited-patent.log 2>&1 | ||
| - | > nohup ./run-update-by-log.sh > patent-cited-patent-log.log 2>&1 | + | > nohup ./update-patent-cited-patent-by-log.sh > update-patent-cited-patent-by-log.log 2>&1 |
| </code> | </code> | ||
| ==== Download Cited Patents ==== | ==== Download Cited Patents ==== | ||
| 行 210: | 行 218: | ||
| <code bash> | <code bash> | ||
| > nohup ./update-pct-flag.sh > update-pct-flag.log 2>&1 | > nohup ./update-pct-flag.sh > update-pct-flag.log 2>&1 | ||
| + | </code> | ||
| + | |||
| + | ==== Update Technologies ==== | ||
| + | One can run <color red>PatentTechnologyUpdater.java</color> in the package <color red>cn.edu.bjut.ui</color> to update the technologies. | ||
| + | |||
| + | <code bash> | ||
| + | > nohup ./update-patent-technology.sh 2 ../dataset/Derwent/technologies > update-patent-technology.log 2>&1 | ||
| </code> | </code> | ||
| ===== Converter ===== | ===== Converter ===== | ||
| 行 221: | 行 236: | ||
| The target articles and patents can be exported by running <color red>ToTextConvertor.java</color> in the package <color red>cn.edu.bjut.converter</color>. Then, one can extract the abbreviations from the titles and abstracts with the approach in [[https://doi.org/10.1142/9789812776303_0042|Schwartz and Hearst (2003)]] by running <color red>AbbreviationExtractor.java</color> in the package <color red>cn.edu.bjut.ui</color>. | The target articles and patents can be exported by running <color red>ToTextConvertor.java</color> in the package <color red>cn.edu.bjut.converter</color>. Then, one can extract the abbreviations from the titles and abstracts with the approach in [[https://doi.org/10.1142/9789812776303_0042|Schwartz and Hearst (2003)]] by running <color red>AbbreviationExtractor.java</color> in the package <color red>cn.edu.bjut.ui</color>. | ||
| + | |||
| + | <code bash> | ||
| + | > nohup ./convert-wos-text.sh > convert-wos-text.log 2>&1 | ||
| + | > nohup ./convert-derwent-text.sh > convert-derwent-text.log 2>&1 | ||
| + | </code> | ||
| ==== Export for TNG model ==== | ==== Export for TNG model ==== | ||
| 行 232: | 行 252: | ||
| The target articles/patents can be exported for [[https://doi.org/10.1109/ICDM.2007.86|TNG (Topic N-Gram) model]] by running <color red>ToTNGConvertor.java</color> in the package <color red>cn.edu.bjut.converter</color>. | The target articles/patents can be exported for [[https://doi.org/10.1109/ICDM.2007.86|TNG (Topic N-Gram) model]] by running <color red>ToTNGConvertor.java</color> in the package <color red>cn.edu.bjut.converter</color>. | ||
| - | ==== Export for Novelty Indicator ==== | + | <code bash> |
| + | > nohup ./convert-wos-bioc.sh > convert-wos-bioc.log 2>&1 | ||
| + | > nohup ./convert-derwent-bioc.sh > convert-derwent-bioc.log 2>&1 | ||
| + | > nohup ./convert-tng.sh > convert-tng.log 2>&1 | ||
| + | </code> | ||
| + | |||
| + | ==== Calculate Novelty Indicator ==== | ||
| The resulting journal of each cited article can be exported by running <color red>NoveltyConvertor.java</color> in the package <color red>cn.edu.bjut.runner</color>. In the meanwhile, the resulting IPC codes of each cited patent can also be exported by running <color red>NoveltyConvertor.java</color> in the package <color red>cn.edu.bjut.runner</color>. Then, the novelty indicator of each document can be calculated by following [[https://doi.org/10.1126/science.1240474 | Uzzi et al. (2013)]]. | The resulting journal of each cited article can be exported by running <color red>NoveltyConvertor.java</color> in the package <color red>cn.edu.bjut.runner</color>. In the meanwhile, the resulting IPC codes of each cited patent can also be exported by running <color red>NoveltyConvertor.java</color> in the package <color red>cn.edu.bjut.runner</color>. Then, the novelty indicator of each document can be calculated by following [[https://doi.org/10.1126/science.1240474 | Uzzi et al. (2013)]]. | ||
| + | <code bash> | ||
| + | > nohup ./convert-wos-novelty.sh ../dataset/WoS/novelty/20240421/paper-citations.txt > convert-wos-novelty.log 2>&1 | ||
| + | > nohup ./convert-derwent-novelty.sh ../dataset/Derwent/novelty/20240421/patent-citations.txt > convert-derwent-novelty.log 2>&1 | ||
| + | </code> | ||
| + | |||
| + | <code sql> | ||
| + | > TRUNCATE article_novelty; | ||
| + | > TRUNCATE patent_novelty; | ||
| + | </code> | ||
| + | |||
| + | <code bash> | ||
| + | > nohup ./import-article-novelty.sh ../dataset/WoS/novelty/20240421/paper_novelty.txt > import-article-novelty.log 2>&1 | ||
| + | > nohup ./import-patent-novelty.sh ../dataset/Derwent/novelty/20240421/patent_novelty.txt > import-patent-novelty.log 2>&1 | ||
| + | </code> | ||
| ==== Extract Citation Network ==== | ==== Extract Citation Network ==== | ||
| The citation network for articles can be extracted by running <color red>WoSCitationNetworkExtractor.java</color> in the package <color red>cn.edu.bjut.converter</color>. | The citation network for articles can be extracted by running <color red>WoSCitationNetworkExtractor.java</color> in the package <color red>cn.edu.bjut.converter</color>. | ||
| 行 251: | 行 291: | ||
| One can run <color red>IndicatorCalculator.java</color> in the package <color red>cn.edu.bjut.ui</color> to calculate all indicators ([[https://doi.org/10.1016/j.techfore.2020.120366|Xu et al., 2021]]). | One can run <color red>IndicatorCalculator.java</color> in the package <color red>cn.edu.bjut.ui</color> to calculate all indicators ([[https://doi.org/10.1016/j.techfore.2020.120366|Xu et al., 2021]]). | ||
| + | |||
| + | ===== Attributes Extraction ===== | ||
| + | <code bash> | ||
| + | > .\opennlp TokenNameFinderTrainer.brat -nameTypes ATTRIBUTE,VALUE -lang en -model en-ElectronicPower-WoS-attributes.bin -annotationConfig annotation.conf -br | ||
| + | atDataDir ElectronicPower-WoS-Train -ruleBasedTokenizer simple -sentenceDetectorMode en-sent.bin | ||
| + | </code> | ||
| ~~DISCUSSION:closed~~ | ~~DISCUSSION:closed~~ | ||
zh/notes/electric_power.1712150309.txt.gz · 最后更改: 2024/04/03 21:18 由 pzczxs