Forensic system, forensic method, and forensic program

• US 9,542,474 B2
• Filed: 10/09/2013
• Issued: 01/10/2017
• Est. Priority Date: 10/09/2012
• Status: Active Grant

• Current Assignee: Fronteo, Inc.
• Original Assignee: Ubic, Inc.
• Inventors: Morimoto, Masahiro, Shirai, Yoshikatsu, Takeda, Hideki, Hasuko, Kazumi
• Primary Examiner(s): GORTAYO, DANGELINO N
• Application Number:
  US14/434,589
• Publication Number:
  US 20150286706A1
• Time in Patent Office: 1,189 Days
• Field of Search: 707/736, 707/737, 707/741, 707/749, 707/758, 707/730, 707/726, 707/767, 707/942
• US Class Current: 1/1
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/33 Querying
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/36 Creation of semantic tools, e.g. ontology or thesauri
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/9577 Optimising the visualization of content, e.g. distillation of HTML documents
• CPC Class Codes: G06F 7/36 Combined merging and sorting
• CPC Class Codes: G06Q 50/18 Legal services

Abstract

Disclosed is a forensic system capable of enhancing the accuracy and efficiency of classification work of whether to submit document information as evidence in a lawsuit by highlighting a portion including a specific keyword in a unit of a sentence. The forensic system includes: a database that registers a keyword for determining by a user whether a plurality of pieces of document information included in the digital information is related to a lawsuit; a retrieving unit that retrieves the keyword registered in the database from the document information; a sentence extracting unit that extracts a sentence including the retrieved keyword from the document information; a score calculating unit that calculates a score indicating a degree of relevance to the lawsuit using a feature value extracted from the sentence extracted by the sentence extracting unit; and a highlighting unit that changes a degree of highlighting of the sentence according to the score.

Claims

1. A forensic system that acquires digital information recorded in a plurality of computers or a server and analyzes the acquired digital information, comprising:

a processor, and

a memory, wherein the memory has stored thereon instructions that, when executed by the processor, causes the processor to;

cause a database to register a keyword for determining by a user whether a plurality of pieces of document information included in the digital information is related to a lawsuit;

retrieve the keyword registered in the database from the document information;

extract a sentence including the retrieved keyword from the document information;

classify the extracted document information based on the determination result for each determination result, and analyze and select the keyword that appears commonly in the classified document information;

calculate a score indicating a degree of relevance to the lawsuit based on a feature value extracted from the extracted sentence; and

change a degree of highlighting of the sentence according to the score,

wherein the degree of relevance is assigned to the keyword using a document information group for which it is determined by the user that the document information group is related to a lawsuit in the past;

wherein the database registers the keyword when the degree of relevance exceeds a predetermined threshold value; and

wherein the feature value is extracted based on an appearance frequency or an amount of transmission information related to the keyword.

2. The forensic system according to claim 1,

wherein the feature value is calculated based on the keyword included in the sentence.

3. The forensic system according to claim 1,

wherein the score is calculated from specific semantic information related to the sentence.

4. The forensic system according to claim 1,

wherein the highlighting unit changes a highlighting color according to the feature value.

5. The forensic system according to claim 1,

wherein the sentence extracting unit determines an amount of the sentences that are to be extracted based on a degree of adjacency of the retrieved keywords.

6. The forensic system according claim 1,

wherein the database analyzes the keyword for which it is determined by the user that the document information was related to a lawsuit in the past, and automatically registers the keyword based on an analysis result relating to the analyzed keyword.

7. The forensic system according to claim 1, further comprising:

a result receiving unit that receives a result of relevance determination performed by the user with respect to the document information in which the sentence is highlighted;

a keyword recording unit that records the selected keyword;

a searching unit that searches for the keyword recorded in the keyword recording unit from the document information;

a document score calculating unit that calculates a document score indicating relevance between the determination result and the document information using a search result in the searching unit and an analysis result in the selecting unit; and

an automatic determining unit that automatically determines the relevance based on the document score.

8. A forensic method for acquiring digital information recorded in a plurality of computers or a server and analyzing the acquired digital information, comprising:

a step of registering a keyword for determining by a user whether a plurality of pieces of document information included in the digital information is related to a lawsuit, through a computer;

a step of retrieving the keyword registered from the document information, through the computer;

a step of extracting a sentence including the retrieved keyword from the document information, through the computer;

a step of classifying the extracted document information based on the determination result for each determination result, and analyzing and selecting the keyword that appears commonly in the classified document information;

a step of calculating a score indicating a degree of relevance to the lawsuit based on a feature value extracted from the sentence extracted, through the computer; and

a step of changing a degree of highlighting of the sentence according to the score, through the computer,

wherein the degree of relevance is assigned to the keyword using a document information group for which it is determined by the user that the document information group is related to a lawsuit in the past;

wherein the database registers the keyword when the degree of relevance exceeds a predetermined threshold value; and

wherein the feature value is extracted based on an appearance frequency or an amount of transmission information related to the keyword.

9. A non-transitory computer-readable storage medium that stores forensic program instructions executable by at least one processor for acquiring digital information recorded in a plurality of computers or a server and analyzing the acquired digital information, the program allowing the at least one processor to execute functions comprising:

registering a keyword for determining by a user whether a plurality of pieces of document information included in the digital information is related to a lawsuit;

retrieving the keyword registered from the document information;

extracting a sentence including the retrieved keyword from the document information;

classifying the extracted document information based on the determination result for each determination result, and analyzing and selecting the keyword that appears commonly in the classified document information;

calculating a score indicating a degree of relevance to the lawsuit based on a feature value extracted from the sentence extracted; and

changing a degree of highlighting of the sentence according to the score,

wherein the degree of relevance is assigned to the keyword using a document information group for which it is determined by the user that the document information group is related to a lawsuit in the past;

wherein the database registers the keyword when the degree of relevance exceeds a predetermined threshold value; and

wherein the feature value is extracted based on an appearance frequency or an amount of transmission information related to the keyword.