JP2009217528A5 - - Google Patents
Download PDFInfo
- Publication number
- JP2009217528A5 JP2009217528A5 JP2008060406A JP2008060406A JP2009217528A5 JP 2009217528 A5 JP2009217528 A5 JP 2009217528A5 JP 2008060406 A JP2008060406 A JP 2008060406A JP 2008060406 A JP2008060406 A JP 2008060406A JP 2009217528 A5 JP2009217528 A5 JP 2009217528A5
- Authority
- JP
- Japan
- Prior art keywords
- classification
- assignment
- documents
- document
- assigned
- 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
Claims (5)
前記処理部により、
前記第１の文書の各々を前記分類付与対象文書とし、該分類付与対象文書の各々に対して、前記分類体系定義テーブルに格納された前記分類のうちの少なくとも一つを付与し、
前記分類体系定義テーブルに格納された分類毎に、前記分類付与結果と前記人手付与分類テーブルを参照して、第１の分類が人手により付与された文書の件数に占める、前記第１の分類が自動付与された文書の件数の割合を、前記第１の分類に対する第１の分類自動付与精度として算出し、また、前記第１の分類以外の分類の各々について、該分類が人手により付与された文書の件数に占める、前記第１の分類が誤って付与された文書の件数の割合を算出し、その中の最大値を前記第１の分類に対する第２の分類自動付与精度として算出し、
前記第１の分類付与精度が第１の閾値より高く、かつ、前記第２の分類付与精度が第２の閾値より低い場合に、当該分類を自動付与可能な分類として認定して前記分類付与対象文書情報と対応付けて自動分類付与テーブルに格納し、
前記認定結果を前記出力部に出力することを特徴とする分類付与方法。 A classification system definition table for storing data relating to a document classification system, a human-assignment classification table for storing a class previously assigned to each of a plurality of first documents selected in advance for automatic classification, Classification assignment in a classification assignment system comprising: a processing unit for assigning at least one of the classifications stored in the classification system definition table to the classification assignment target document with reference to the manual classification assignment classification table; and an output unit A method,
By the processing unit,
Wherein each of the first document and the classification applied target document, for each of the classification grantees document, applying at least one of the stored the classification in the classification system definition table,
For each classification stored in the classification system definition table, referring to the classification assignment result and the manual assignment classification table , the first classification occupies the number of documents given manually. The ratio of the number of automatically assigned documents is calculated as the first automatic classification accuracy for the first classification, and the classification is manually assigned to each of the classifications other than the first classification. Calculating the ratio of the number of documents in which the first classification is erroneously assigned to the number of documents, and calculating the maximum value among them as the second automatic classification accuracy for the first classification;
When the first classification providing accuracy is higher than the first threshold and the second classification providing accuracy is lower than the second threshold, the classification is recognized as an automatically assignable category and the classification grant target Store it in the automatic classification assignment table in association with the document information,
The classification providing method, wherein the authorization result is output to the output unit .
前記処理部により、
前記第１の文書の各々を分類付与対象文書とし、該分類付与対象文書の各々に対して、前記分類体系定義テーブルに格納された前記分類のうちの一つを付与し、
前記分類体系定義テーブルに格納された分類毎に、前記分類付与結果と前記人手付与分類テーブルを参照して、第１の分類が人手により付与された文書の件数に占める、前記第１の分類が自動付与された文書の件数の割合を、前記第１の分類に対する第１の分類自動付与精度として算出し、また、前記第１の分類以外の分類の各々について、該分類が人手により付与された文書の件数に占める、前記第１の分類が誤って付与された文書の件数の割合を算出し、その中の最大値を前記第１の分類に対する第２の分類自動付与精度として算出し、
前記第１の分類付与精度が第１の閾値より高く、かつ、前記第２の分類付与精度が第２の閾値より低い場合に、当該分類を自動付与可能な分類として認定して前記分類付与対象文書情報と対応付けて自動分類付与テーブルに格納し、
前記人手によって分類が付与されていない前記分類付与対象文書に対して自動付与された分類のうち、前記認定された自動付与可能な分類を分類自動付与結果として確定することを特徴とする分類付与方法。 A classification system definition table for storing data relating to a document classification system, a human-assignment classification table for storing a class previously assigned to each of a plurality of first documents selected in advance for automatic classification, Classification assignment in a class assignment system comprising: a processing unit for giving at least one of the classifications stored in the classification system definition table to the classification grant target document with reference to the manual classification assignment classification table; and an output unit A method,
By the processing unit,
Wherein each of the first document and classified impart target document, for each of the classification grantees document, grant one of the stored the classification in the classification system definition table,
For each classification stored in the classification system definition table, referring to the classification assignment result and the manual assignment classification table , the first classification occupies the number of documents given manually. The ratio of the number of automatically assigned documents is calculated as the first automatic classification accuracy for the first classification, and the classification is manually assigned to each of the classifications other than the first classification. Calculating the ratio of the number of documents in which the first classification is erroneously assigned to the number of documents, and calculating the maximum value among them as the second automatic classification accuracy for the first classification;
When the first classification providing accuracy is higher than the first threshold and the second classification providing accuracy is lower than the second threshold, the classification is recognized as an automatically assignable category and the classification grant target Store it in the automatic classification assignment table in association with the document information,
Of the classifications automatically given to the classification grant target document to which no classification is given manually, the classified automatically assignable classification is determined as a classification automatic grant result. .
前記処理部は、
前記第１の文書の各々を分類付与対象文書とし、該分類付与対象文書の各々に対して、前記分類体系定義テーブルに格納された前記分類のうちの一つを付与し、
前記分類体系定義テーブルに格納された分類毎に、前記分類付与結果と前記人手付与分類テーブルを参照して、第１の分類が人手により付与された文書の件数に占める、前記第１の分類が自動付与された文書の件数の割合を、前記第１の分類に対する第１の分類自動付与精度として算出し、また、前記第１の分類以外の分類の各々について、該分類が人手により付与された文書の件数に占める、前記第１の分類が誤って付与された文書の件数の割合を算出し、その中の最大値を前記第１の分類に対する第２の分類自動付与精度として算出し、
前記第１の分類付与精度が第１の閾値より高く、かつ、前記第２の分類付与精度が第２の閾値より低い場合に、当該分類を自動付与可能な分類として認定して前記分類付与対象文書情報と対応付けて自動分類付与テーブルに格納し、
前記認定結果を前記出力部に出力することを特徴とする分類付与システム。 A classification system definition table for storing data relating to a document classification system, a human-assignment classification table for storing a class previously assigned to each of a plurality of first documents selected in advance for automatic classification, In a classification grant system comprising: a processing unit for assigning at least one of the classifications stored in the classification system definition table to the classification grant target document with reference to the manual classification assignment classification table; and an output unit .
The processor is
Each of the first documents is a classification grant target document, and one of the classifications stored in the classification scheme definition table is assigned to each of the classification grant target documents ;
For each classification stored in the classification system definition table, referring to the classification assignment result and the manual assignment classification table , the first classification occupies the number of documents given manually. The ratio of the number of automatically assigned documents is calculated as the first automatic classification accuracy for the first classification, and the classification is manually assigned to each of the classifications other than the first classification. Calculating the ratio of the number of documents in which the first classification is erroneously assigned to the number of documents, and calculating the maximum value among them as the second automatic classification accuracy for the first classification;
When the first classification providing accuracy is higher than the first threshold and the second classification providing accuracy is lower than the second threshold, the classification is recognized as an automatically assignable category and the classification grant target Store it in the automatic classification assignment table in association with the document information,
The classification grant system, wherein the authorization result is output to the output unit .
前記処理部は、
前記第１の文書の各々を分類付与対象文書とし、該分類付与対象文書の各々に対して、前記分類体系定義テーブルに格納された前記分類のうちの一つを付与し、
前記分類体系定義テーブルに格納された分類毎に、前記分類付与結果と前記人手付与分類テーブルを参照して、第１の分類が人手により付与された文書の件数に占める、前記第１の分類が自動付与された文書の件数の割合を、前記第１の分類に対する第１の分類自動付与精度として算出し、また、前記第１の分類以外の分類の各々について、該分類が人手により付与された文書の件数に占める、前記第１の分類が誤って付与された文書の件数の割合を算出し、その中の最大値を前記第１の分類に対する第２の分類自動付与精度として算出し、
前記第１の分類付与精度が第１の閾値より高く、かつ、前記第２の分類付与精度が第２の閾値より低い場合に、当該分類を自動付与可能な分類として認定して前記分類付与対象文書情報と対応付けて自動分類付与テーブルに格納し、
前記人手によって分類が付与されていない前記分類付与対象文書に対して自動付与された分類のうち、前記認定された自動付与可能な分類を分類自動付与結果として確定することを特徴とする分類付与システム。 A classification scheme definition table for storing data relating to a document classification system and manually applying classification table for storing in advance manually assigned classification for each of the preselected plurality of first document for classification automatically assigned, A classification grant system comprising: a processing unit that gives at least one of the classifications stored in the classification system definition table to the classification grant target document with reference to the manual classification assignment classification table; and an output unit In
The processor is
Each of the first documents is a classification grant target document, and one of the classifications stored in the classification scheme definition table is assigned to each of the classification grant target documents ,
For each classification stored in the classification system definition table, referring to the classification assignment result and the manual assignment classification table , the first classification occupies the number of documents given manually. The ratio of the number of automatically assigned documents is calculated as the first automatic classification accuracy for the first classification, and the classification is manually assigned to each of the classifications other than the first classification. Calculating the ratio of the number of documents in which the first classification is erroneously assigned to the number of documents, and calculating the maximum value among them as the second automatic classification accuracy for the first classification;
When the first classification providing accuracy is higher than the first threshold and the second classification providing accuracy is lower than the second threshold, the classification is recognized as an automatically assignable category and the classification grant target Store it in the automatic classification assignment table in association with the document information,
Of the classifications automatically given to the classification grant target document that has not been given a classification by the human hand, the classified automatically assignable classification is determined as an automatic classification grant result. .
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2008060406A JP4604097B2 (en) | 2008-03-11 | 2008-03-11 | Document classification assigning method, system or computer program |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2008060406A JP4604097B2 (en) | 2008-03-11 | 2008-03-11 | Document classification assigning method, system or computer program |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| JP2009217528A JP2009217528A (en) | 2009-09-24 |
| JP2009217528A5 true JP2009217528A5 (en) | 2010-07-29 |
| JP4604097B2 JP4604097B2 (en) | 2010-12-22 |
Family
ID=41189307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2008060406A Expired - Fee Related JP4604097B2 (en) | 2008-03-11 | 2008-03-11 | Document classification assigning method, system or computer program |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP4604097B2 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5572255B1 (en) * | 2013-10-11 | 2014-08-13 | 株式会社Ｕｂｉｃ | Digital information analysis system, digital information analysis method, and digital information analysis program |
| JP2017027495A (en) * | 2015-07-27 | 2017-02-02 | Kddi株式会社 | Verification device, classification system, verification method, classification method, and computer program |
| JP6974751B2 (en) * | 2017-03-28 | 2021-12-01 | 日本電信電話株式会社 | Visualizers, visualization methods, and programs |
| JP6814091B2 (en) * | 2017-05-12 | 2021-01-13 | 株式会社日立製作所 | Document classification system and document classification method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4931111B2 (en) * | 2006-06-02 | 2012-05-16 | 独立行政法人情報通信研究機構 | Document classification apparatus and program |
-
2008
- 2008-03-11 JP JP2008060406A patent/JP4604097B2/en not_active Expired - Fee Related
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105830166B (en) | A kind of controller, flash memory device and the method for writing data into flash memory device | |
| JP2020533254A5 (en) | ||
| JP2016535344A5 (en) | ||
| JP2017520068A5 (en) | ||
| CN105745628B (en) | A kind of method for writing data into flash memory device, flash memory device and storage system | |
| JP2009217528A5 (en) | ||
| JP2011081549A5 (en) | Information processing apparatus and information processing method | |
| WO2015191731A8 (en) | Systems and methods for software analytics | |
| JP2017538194A5 (en) | ||
| JP2007072665A5 (en) | ||
| JP2013045278A5 (en) | Access control method and access control device | |
| JP2009135824A5 (en) | ||
| JP2011180765A5 (en) | ||
| JP2007334610A5 (en) | ||
| JP2008140067A5 (en) | ||
| CN108090082B (en) | Information processing method and information processing apparatus | |
| JP2007279831A5 (en) | ||
| JP2014239302A5 (en) | ||
| JP2014130450A5 (en) | ||
| US20140278268A1 (en) | Method for mapping elements of a construction project | |
| EP3035196A3 (en) | Data processing method, information processing device, and data processing program | |
| JP2016516235A5 (en) | ||
| JP2007079854A5 (en) | ||
| JP2013097467A5 (en) | ||
| JP2018030371A5 (en) |