DOCUMENT CLASSIFICATION SYSTEM, DOCUMENT CLASSIFICATION METHOD, AND DOCUMENT CLASSIFICATION PROGRAM

• US 20150149372A1
• Filed: 02/28/2013
• Published: 05/28/2015
• Est. Priority Date: 02/29/2012
• Status: Active Grant

• Current Assignee: Fronteo, Inc.
• Original Assignee: Ubic, Inc.
• Inventors: Morimoto, Masahiro, Shirai, Yoshikatsu, Takeda, Hideki, Hasuko, Kazumi
• Granted Patent: US 9,552,570 B2
• Time in Patent Office: Days
• US Class Current: 705/311
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/18 Legal services

Abstract

A document classification system is provided. The document classification system analyzes digital document information which is collected to be submitted as evidence in a lawsuit and classifies the digital document information. The document classification system includes an extraction unit that extracts documents from the collected document information, a document display unit that displays an extracted document group, a classification code receiving unit that receives a classification code assigned to the displayed document group, a selection unit that classifies the extracted document group for each classification code, analyzes a keyword commonly appearing in the classified document group, and selects the keyword, a database that records the selected keyword, a search unit that searches for the keyword from the document information, a score calculation unit that calculates a score indicating connection between the classification code and the document, and an automatic classification unit that automatically assigns the classification code.

Claims

1. A document classification system that acquires digital information recorded in a plurality of computers or servers, analyzes document information included in the acquired digital information, and classifies the document information so as to be readily used in a lawsuit, comprising:

an extraction unit that extracts a document group, which is a data set including a predetermined number of documents, from the document information;

a classification code receiving unit that receives a classification code;

a selection unit that classifies the extracted document group for each classification code on the basis of the classification code, analyzes a keyword which commonly appears in the classified document group, and selects the keyword;

a search unit that searches for the keyword;

a score calculation unit that calculates a score indicating connection between the classification code and the document, using the search result of the search unit and the analysis result of the selection unit; and

an automatic classification unit that automatically assigns the classification code on the basis of the result of the score.

2. The document classification system according to claim 1,

wherein the score calculation unit calculates the score using the keyword which appears in the document group and a weight of each keyword.

3. The document classification system according to claim 2,

wherein the weight is of the keyword and is determined on the basis of the amount of transmitted information for each classification code.

4. The document classification system according to claim 1,

wherein the extraction unit has a function which randomly samples the document group from the document information and extracts the document group.

5. The document classification system according to claim 1,

wherein the search unit has a function which searches for the keyword from document information including a document to which the classification code is not assigned,

the score calculation unit has a function which calculates the score indicating the connection between the classification code and the document using the search result of the search unit and the analysis result of the selection unit, and

the automatic classification unit has a function which extracts a document with the classification code which is not received by the classification code receiving unit and automatically assigns the classification code to the document information.

6. The document classification system according to claim 12,

wherein the database further includes a function which extracts a related term related to the classification code and records the related term,

the search unit further includes a function which searches for the related term from the document information,

the score calculation unit further includes a function which calculates the score on the basis of the search result of the related term by the search unit, and

the automatic classification unit further includes a function which automatically assigns the classification code on the basis of the score which is calculated using the related term.

7. The document classification system according to claim 6,

wherein the database further includes a function which records a keyword correlated with the classification code in advance, and

the automatic classification unit further includes a function which, when a document including the keyword correlated with the classification code is searched from the document group, decides the classification code.

8. The document classification system according to claim 6, further comprising:

a document exclusion unit that selects a document which does not include the keyword selected by the selection unit, the related term, and the keyword correlated with the classification code among the documents included in the document group and excludes the selected document from a classification target of the automatic classification unit.

9. The document classification system according to claim 6, further comprising:

a learning unit that increases or decreases the number of keywords selected by the selection unit, the number of keywords correlated with the classification codes recorded in the database, and the number of related terms, on the basis of the analysis result of the selection unit and the score calculated by the score calculation unit.

12. The document classification system, according to claim 1, further including a database which records the keyword selected by the selection unit, and wherein the search unit is configured to search the keyword recorded in the database based on the document information.

13. The document classification system, according to claim 1, further including a document display unit which displays the document group extracted from the extraction unit and wherein the classification code receiving unit is configured to receive the classification code assigned by the user to the document group displayed by the document display unit on the basis of connection to the lawsuit.

10. A document classification method that is performed in a document classification system which acquires digital information recorded in a plurality of computers or servers, analyzes document information included in the acquired digital information, and classifies the document information so as to be readily used in a lawsuit, the document classification method comprising:

extracting a document group, which is a data set including a predetermined number of documents, from the document information;

displaying the extracted document group on a screen;

receiving a classification code which is assigned to the displayed document group by a user on the basis of connection to the lawsuit;

classifying the extracted document group for each classification code on the basis of the classification code, analyzing a keyword which commonly appears in the classified document group, and selecting the keyword;

recording the selected keyword;

searching for the recorded keyword from the document information;

calculating a score indicating connection between the classification code and the document, using the search result and the analysis result; and

automatically assigning the classification code on the basis of the result of the score.

11. A non-transitory recording medium recording therein a document classification program, which when executed by at least one processor, causes the processor to perform a plurality functions to acquire digital information recorded in a plurality of computers or servers, analyze document information included in the acquired digital information, and classify the document information so as to be readily used in a lawsuit, the plurality of functions comprising:

a function of extracting a document group, which is a data set including a predetermined number of documents, from the document information;

a function of displaying the extracted document group on a screen;

a function of receiving a classification code which is assigned to the displayed document group by a user on the basis of connection to the lawsuit;

a function of classifying the extracted document group for each classification code on the basis of the classification code, analyzing a keyword which commonly appears in the classified document group, and selecting the keyword;

a function of recording the selected keyword;

a function of searching for the recorded keyword from the document information;

a function of calculating a score indicating connection between the classification code and the document, using the search result and the analysis result; and

a function of automatically assigning the classification code on the basis of the result of the score.