JP5876144B2 - Digital information analysis system, digital information analysis method, and digital information analysis program - Google Patents

Description

  The present invention relates to a digital information analysis system, a digital information analysis method, and a digital information analysis program. In particular, the present invention relates to a digital information analysis system, a digital information analysis method, and a digital information analysis program for automatically scoring digital information.

  Conventionally, a user is related to a lawsuit with respect to a document group displayed with an extraction unit that extracts a predetermined number of documents from the collected document information and a document display unit that displays the extracted document group on the screen. A classification code receiving unit that receives a classification code assigned based on the classification code, and classifies the extracted document group for each classification code based on the classification code, and analyzes keywords that appear in common in the classified document group A selection part to be selected, a database for recording the selected keyword, a search part for searching the keyword recorded in the database from document information, a search result of the search part and an analysis result of the selection part, There is known a document classification system including a score calculation unit that calculates a score indicating relevance with a document, and an automatic classification unit that automatically assigns a classification code based on the result of the score ( In example, see Patent Document 1.). According to the document separation system described in Patent Document 1, it is possible to analyze digitized document information collected for submission as evidence in a lawsuit and separate it so that it can be easily used in a lawsuit.

JP 2013-182338 A

  In a document classification system described in Patent Document 1, a document may be randomly sampled from document information to be classified, and a reviewer may manually extract a document group to which a classification code is assigned. . When such digital information is sorted, it is desired to improve the sorting speed and sorting accuracy of the digital information by automating the sorting process.

  Therefore, an object of the present invention is to provide a digital information analysis system, a digital information analysis method, and a digital information analysis program that automatically and accurately score digital information.

  In order to achieve the above object, the present invention provides a keyword database that stores a plurality of keywords having relevance to predetermined specific items, weighting information associated with each of the plurality of keywords, and each of the plurality of keywords. , Based on weighting information associated with each of a plurality of keywords, based on the score associated with each of a plurality of digital information including text data, and the score associated with the scoring unit, A sample digital information extraction unit that extracts sample digital information as a sample from a plurality of digital information, and an information update unit that updates weighting information stored in the keyword database by analyzing the extracted sample digital information A digital information analysis system is provided.

  In the digital information analysis system, the sample digital information extraction unit can extract digital information satisfying a predetermined condition as sample digital information.

  In the digital information analysis system, the plurality of keywords may include a plurality of morphemes or a plurality of co-occurrence expressions.

  In the digital information analysis system, the sample digital information extraction unit extracts new sample digital information from a plurality of pieces of digital information associated with the weighting information updated by the information update unit, and the information update unit includes: The weighting can also be updated again using new sample digital information extracted by the sample digital information extraction unit.

  Further, in the digital information analysis system, the information update unit can end the update under a predetermined end condition.

  The digital information analysis system may be information indicating that a predetermined specific item relates to a lawsuit or a cartel.

  In order to achieve the above object, the present invention provides a digital information analysis comprising a keyword database that stores a plurality of keywords having relevance to predetermined specific items and weighting information associated with each of the plurality of keywords. A digital information analysis method in a system, in which a score is associated with each of a plurality of digital information including text data based on each of a plurality of keywords and weighting information associated with each of the plurality of keywords. Based on the stage and the score associated in the scoring stage, the sample digital information extraction stage that extracts sample digital information that is a sample from a plurality of digital information, and the extracted sample digital information Weights stored in the database Digital information analyzing method and an information updating step of updating the information is provided.

  In order to achieve the above object, the present invention provides a digital information analysis comprising a keyword database that stores a plurality of keywords having relevance to predetermined specific items and weighting information associated with each of the plurality of keywords. A digital information analysis program for a system, wherein a score is obtained for each of a plurality of digital information including text data based on each of a plurality of keywords and weighting information associated with each of the plurality of keywords. Corresponding scoring function, sample digital information extraction function that extracts sample digital information as a sample from a plurality of digital information based on the score correlated in the scoring function, and analyzing the extracted sample digital information In the keyword database Digital information analysis program for realizing the information and update function of updating the weighting information being are provided.

  According to the digital information analysis system, the digital information analysis method, and the digital information analysis program according to the present invention, the digital information analysis system, the digital information analysis method, and the digital information analysis that automatically and accurately score the digital information. Can provide a program.

It is a functional block diagram of the digital information analysis system concerning this embodiment. It is a functional block diagram of an information processor. It is a flowchart of a process of the digital information analysis system which concerns on this Embodiment. It is a hardware block diagram of the digital information analysis system which concerns on this Embodiment.

[Embodiment]
(Outline of digital information analysis system 1)
The digital information analysis system 1 according to the present embodiment is configured to process digital information related to a predetermined specific item among a plurality of digital information stored in an information processing apparatus 2 such as a user terminal or a server. It is a system that automatically scores and automatically extracts digital information related to specific items with high accuracy. Here, the predetermined specific item is information indicating that it is related to, for example, a lawsuit or a cartel. The digital information analysis system 1 according to the present embodiment, for example, is an electronic device required for investigating and investigating the cause of a crime or dispute when a crime or legal dispute related to a computer such as unauthorized access or leakage of confidential information occurs. It can be applied to forensics, a technology that collects and analyzes digital information, which is a historical record, and reveals its legal evidence. Note that the digital information is, for example, a document file including text information, a text file, or an e-mail.

  Specifically, the digital information analysis system 1 first scores each of a plurality of digital information using a keyword having a relationship with a specific item. For example, the digital information analysis system 1 associates a higher score with digital information as the relevance to a specific item is higher. Here, the digital information analysis system 1 includes in advance a keyword database that stores a plurality of keywords related to a specific item and weighting information associated with each of the plurality of keywords. The weighting information is information that becomes more weighted as the relevance to the specific matter of the associated keyword is higher. The digital information analysis system 1 scores each of a plurality of digital information using this weighting information.

  Then, the digital information analysis system 1 extracts sample digital information as temporary digital information that clears a predetermined condition from a plurality of scored digital information. The digital information analysis system 1 analyzes the extracted sample digital information, and updates the weighting information associated with each of the plurality of keywords to new weighting information. Then, the digital information analysis system 1 repeats the above process using new weighting information. That is, the digital information analysis system 1 makes digital information scoring, extraction of sample digital information, and update of weighting information as one cycle, and by repeating this cycle, Improve the extraction accuracy from multiple digital information.

  In the present embodiment, the server is one or more servers, and may be configured to include a plurality of servers. For example, the server includes a server capable of storing digital information such as a mail server, a file server, or a document management server. Further, the user terminal is one or more user terminals, and can be configured to include a plurality of user terminals. For example, the user terminal includes a personal computer, a notebook computer, a tablet PC, or a mobile communication terminal such as a mobile phone.

(Details of digital information analysis system 1)
FIG. 1 shows an example of functional configuration blocks of the digital information analysis system according to the present embodiment.

  The digital information analysis system 1 includes an extraction unit 110 that extracts digital information stored in the information processing apparatus 2, a plurality of keywords that are related to predetermined specific items, and a keyword that stores weighting information of each keyword Database 100, scoring unit 120 that associates a score with extracted digital information, sample digital information extraction unit 130 that extracts sample digital information, information update unit 140 that updates weighting information, and extracted digital information A sample digital information and / or an output unit 150 for outputting information related thereto.

(Keyword database 100)
The keyword database 100 stores a plurality of keywords having relevance to predetermined specific items and weighting information associated with each of the plurality of keywords. In the present embodiment, the keyword includes one or more of a word, a plurality of morphemes, a plurality of co-occurrence expressions, and the like. In other words, the keyword database 100 corresponds to each of a plurality of keywords related to a predetermined specific item and / or a combination of a plurality of keywords with weighting information indicating the level of relevance to the predetermined specific item. And store. The keyword database 100 supplies the stored information to the scoring unit 120 in response to the action from the scoring unit 120. Further, the keyword database 100 is controlled by the information updating unit 140 and replaces the stored weighting information with new weighting information.

  Note that a word is a minimum language unit having a specific meaning and function in terms of grammar. The plurality of keywords are configured to include two or more keywords. Note that the score of digital information is a numerical value indicating the level of relevance, for example, in the relevance of a specific item in which a combination of a plurality of keywords is determined in advance. The larger the value, the higher the relevance.

  For example, when the keyword is a co-occurrence expression, the keyword database 100 stores weighting information in association with the combination of the first word and the second word. As an example, an example in which a predetermined specific item is information related to “infringement” will be described. In this case, it is assumed that weighting information “X” is stored in the keyword database 100 in association with a combination of “digital camera” as the first word and “infringement” as the second word. Further, it is assumed that weighting information “Y” is stored in the keyword database 100 in association with the combination of “steep pitch” as the first word and “plan” as the second word (provided that X > Y, where X and Y are numerical values). In this case, the combination of the words “digital camera” and “infringement” is more relevant to the infringement than the combination of the words “rapid pitch” and “plan”.

(Extractor 110)
The extraction unit 110 extracts digital information stored in the information processing apparatus 2 from the information processing apparatus 2. The extraction unit 110 supplies the extracted digital information to the scoring unit 120 and the sample digital information extraction unit 130.

(Scoring unit 120)
The scoring unit 120 scores each of a plurality of digital information including text data based on each of the plurality of keywords stored in the keyword database 100 and weighting information associated with each of the plurality of keywords. Associate. Specifically, when digital information stored in the information processing device 2 is extracted, the scoring unit 120 analyzes text data in the digital information by morphological analysis and stores the text data in the keyword database 100. It is determined whether or not a combination of a plurality of keywords is included in the extracted file.

  As an example, when the scoring unit 120 determines that a keyword is a co-occurrence expression and a combination of keywords stored in the keyword database 100 is included in the extracted digital information, Predetermined specific matters based on the distance between each keyword, the order of multiple keywords, the frequency and frequency of appearance of multiple keywords, and / or whether multiple keywords are included in the same sentence, etc. Judge the level of relevance of the digital information. Then, the scoring unit 120 associates a score with the extracted digital information based on information indicating the determination result (that is, information indicating the level of relevance with respect to a predetermined specific item).

  When the keyword is a co-occurrence expression, the scoring unit 120 includes a plurality of keywords stored in the keyword database 100 or a combination of a plurality of keywords in the digital information extracted by the extraction unit 110. When at least one of a search unit for searching whether or not a plurality of keywords stored in the keyword database 100 or a combination of a plurality of keywords is included in the digital information, the result of the morphological analysis It is also possible to have a relevance determination unit that determines relevance between a predetermined specific item based on digital information and a determination result setting unit that associates the determination result of the relevance determination unit with the digital information.

(Sample Digital Information Extraction Unit 130)
The sample digital information extraction unit 130 extracts sample digital information as a sample from a plurality of digital information based on the score associated with the scoring unit 120. Specifically, the sample digital information extraction unit 130 works on the extraction unit 110 to extract digital information that satisfies a predetermined condition and that the extraction unit 110 extracts from the information processing apparatus 2 as sample digital information. To do. The sample digital information extraction unit 130 can extract one or more pieces of digital information as sample digital information. For example, the sample digital information extraction unit 130 extracts, as sample digital information, digital information associated with a score equal to or higher than a predetermined score or a predetermined number of pieces of digital information from the top of the score. The sample digital information extraction unit 130 supplies the extracted sample digital information to the information update unit 140 and / or the output unit 150.

(Information update unit 140)
The information update unit 140 updates the weighting information stored in the keyword database 100 by analyzing the sample digital information extracted by the sample digital information extraction unit 130. For example, the information updating unit 140 performs morphological analysis on the content (that is, text data) of the extracted sample digital information. Then, the information update unit 140 extracts morpheme or co-occurrence expression information having a relationship with a predetermined specific item based on the result of the morpheme analysis. Next, the information update unit 140 is extracted based on the number of times the extracted morpheme or co-occurrence expression is used, the frequency of use, etc. Recalculate morpheme or co-occurrence expression weighting information. Then, the information updating unit 140 updates the weighting information stored in the keyword database 100 using the weighting information calculated by recalculation. The information update unit 140 stores the updated weighting information in the keyword database 100 as new weighting information.

  Then, the scoring unit 120 associates a new score with each of the plurality of digital information using the new weighting information updated by the information updating unit 140. Then, the sample digital information extraction unit 130 extracts new sample digital information based on the new score. Furthermore, the information update unit 140 can further update the weighting information stored in the keyword database 100 using the new sample digital information extracted by the sample digital information extraction unit 130. Then, the information update unit 140 can end the update under a predetermined end condition. Predetermined end conditions include, for example, a condition in which the difference between the updated weighting information and the pre-update weighting information falls within a predetermined range, a condition in which the weights before and after the update are not substantially changed, etc. Can be mentioned.

(Output unit 150)
The output unit 150 outputs information related to the extraction result of the extraction unit 110, the extraction result of the sample digital information extraction unit 130, and / or the update result of the information update unit 140. For example, the output unit 150 outputs such information in a perceptible manner to the user in response to an instruction from the outside. The output unit 150 is a display device such as a display that can display information such as digital information and / or an output device such as a printer that outputs information such as digital information to a predetermined medium. Further, the output unit 150 can output the information to be output by recording the information on a recording medium such as a magnetic recording medium or an optical recording medium.

(Information processing apparatus 2)
FIG. 2 shows an example of a functional configuration block of the information processing apparatus.

  The information processing apparatus 2 includes a digital information storage unit 200 that stores a plurality of digital information, and an information output unit 210 that outputs the digital information to the outside. The digital information storage unit 200 stores a plurality of digital information such as a document file including text information, a text file, or an e-mail. The digital information storage unit 200 supplies predetermined digital information to the information output unit 210 in response to an action from the extraction unit 110 or the sample digital information extraction unit 130. The information output unit 210 supplies the digital information stored in the digital information storage unit 200 to the extraction unit 110 or the sample digital information extraction unit 130. The digital information analysis system 1 and the information processing apparatus 2 are connected to be communicable with each other via a communication network such as the Internet or a wired or wireless network such as a LAN. The digital information analysis system 1 can also include some or all of the functions and configurations of the information processing apparatus 2.

(Outline of digital information analysis method)
FIG. 3 shows an example of the processing flow of the digital information analysis system according to the embodiment of the present invention.

  First, it is assumed that the digital information analysis system 1 includes the keyword database 100. Then, the extraction unit 110 of the digital information analysis system 1 extracts digital information from the information processing apparatus 2 (Step 10; hereinafter, “Step” is expressed as “S”). The extraction unit 110 supplies the extracted digital information to the scoring unit 120. Next, the scoring unit 120 scores the extracted digital information using information stored in the keyword database 100 (S15).

  The sample digital information extraction unit 130 then extracts a predetermined condition (for example, a condition where the score is equal to or higher than the predetermined score, or a condition for extracting the top X scores (where X is an integer equal to or greater than 1)) Etc.), sample digital information is extracted from a plurality of digital information (S20). The sample digital information extraction unit 130 supplies the extracted sample digital information to the information update unit 140. The information update unit 140 analyzes the content of the sample digital information and updates the weighting information associated with each of the plurality of keywords stored in the keyword database 100 (S25).

  Subsequently, the digital information analysis system 1 repeats scoring of digital information in the scoring unit 120, extraction of sample digital information in the sample digital information extraction unit 130, and update of weighting information in the information update unit 140. (S30) Improve the extraction accuracy of digital information related to specific items predetermined from a plurality of digital information. The digital information analysis system 1 repeats scoring of digital information, extraction of sample digital information, and updating of weighting information, thereby improving the reproducibility of extraction of digital documents having relevance to predetermined specific items. Can be made.

  FIG. 4 shows an example of the hardware configuration of the digital information analysis system according to the embodiment of the present invention.

  The digital information analysis system 1 according to the present embodiment includes a CPU 1500, a graphic controller 1520, a memory 1530 such as a random access memory (RAM), a read-only memory (ROM), and / or a flash ROM, and a storage device 1540 for storing data. A read / write device 1545 that reads data from and / or writes data to a recording medium, an input device 1560 that inputs data, a communication interface 1550 that transmits / receives data to / from an external communication device, a CPU 1500, and a graphic Chipset 1 for connecting a controller 1520, a memory 1530, a storage device 1540, a read / write device 1545, an input device 1560, and a communication interface 1550 so that they can communicate with each other And a 10.

  The chip set 1510 includes a memory 1530, a CPU 1500 that accesses the memory 1530 and executes predetermined processing, and a graphic controller 1520 that controls display on an external display device. Perform data passing. The CPU 1500 operates based on a program stored in the memory 1530 and controls each component. The graphic controller 1520 displays an image on a predetermined display device based on the image data temporarily stored on the buffer provided in the memory 1530.

  The chip set 1510 connects a storage device 1540, a read / write device 1545, and a communication interface 1550. The storage device 1540 stores programs and data used by the CPU 1500 of the digital information analysis system 1. The storage device 1540 is, for example, a flash memory. The read / write device 1545 reads the program and / or data from the storage medium storing the program and / or data, and stores the read program and / or data in the storage device 1540. For example, the read / write device 1545 acquires a predetermined program from a server on the Internet via the communication interface 1550 and stores the acquired program in the storage device 1540.

  The communication interface 1550 executes data transmission / reception with an external device via a communication network. Further, when the communication network is disconnected, the communication interface 1550 can execute data transmission / reception with an external device without going through the communication network. An input device 1560 such as a keyboard, a tablet, or a mouse is connected to the chip set 1510 via a predetermined interface.

  The digital information analysis program for the digital information analysis system 1 stored in the storage device 1540 is provided to the storage device 1540 via a communication network such as the Internet or a recording medium such as a magnetic recording medium or an optical recording medium. The program for the digital information analysis system 1 stored in the storage device 1540 is executed by the CPU 1500.

  The digital information analysis program executed by the digital information analysis system 1 according to the present embodiment works on the CPU 1500 to describe the digital information analysis system 1 using the keyword database 100, the extraction unit 110, the score described with reference to FIGS. It functions as the attaching unit 120, the sample digital information extracting unit 130, the information updating unit 140, and the output unit 150.

(Effect of embodiment)
The digital information analysis system 1 according to the present embodiment can store in advance in the keyword database 100 various keywords having relevance to predetermined specific items and weighting information of the various keywords. The digital information analysis system 1 extracts digital information using information stored in the keyword database 100, extracts sample digital information from the extracted digital information, and weights using the extracted sample digital information Information can be updated. As a result, the digital information analysis system 1 can fully automatically extract and specify digital information having a predetermined relationship with a predetermined specific item without requiring an external instruction.

  And since the digital information analysis system 1 can repeat the scoring to the digital information, the extraction of the sample digital information, and the update of the weighting information, the digital information having relevance to the specific matter from the plurality of digital information It is possible to extract appropriate digital information having a relationship with a predetermined specific item while improving the extraction accuracy.

  While the embodiments of the present invention have been described above, the embodiments described above do not limit the invention according to the claims. In addition, it should be noted that not all combinations of features described in the embodiments are necessarily essential to the means for solving the problems of the invention. Furthermore, the technical elements of the above-described embodiments may be applied independently, or may be applied by being divided into a plurality of parts such as program parts and hardware parts.

DESCRIPTION OF SYMBOLS 1 Digital information analysis system 2 Information processing apparatus 100 Keyword database 110 Extraction part 120 Scoring part 130 Sample digital information extraction part 140 Information update part 150 Output part 200 Digital information storage part 210 Information output part 1500 CPU
1510 chip set 1520 graphic controller 1530 memory 1540 storage device 1545 read / write device 1550 communication interface 1560 input device

Claims (5)

Be one having a relevant to the predetermined specific matters, words, multi-morpheme, or a plurality of keywords including either or more of the plurality of co-occurrence representation, in correspondence to the plurality of keywords A keyword database that stores weighting information that becomes more weighted as the relevance of a particular item related to a keyword is higher ,
Based on each of the plurality of keywords and the weighting information associated with each of the plurality of keywords, the combination of the plurality of keywords is determined in advance for each of the plurality of digital information including text data. A scoring unit that associates scores that are numerical values indicating the level of relevance with the matter ,
A sample including a morpheme or a co-occurrence expression as temporary digital information that clears a predetermined condition from a plurality of digital information scored so that the relevance increases as the numerical value increases by the scoring unit; A sample digital information extraction unit for extracting the sample digital information
The extracted content of the sample digital information by morphological analysis, and an information updating unit for updating the magnitude of the weight for the weighting information stored in the keyword database,
The scoring unit associates a new score with each of a plurality of digital information using new weighting information updated by the information update unit,
The specimen digital information extracting unit, based on the updated new score by the information updating unit, extracts a new specimen digital information,
The information updating unit, there is again to update the size of the weight for the weighting information stored in the keyword database using the new sample digital information the specimen digital information extracting unit has extracted, further The digital information analysis system that terminates the update with a condition that a difference between the updated weighting information and the pre-updated weighting information falls within a predetermined range as a predetermined end condition.   The digital information analysis system according to claim 1, wherein the sample digital information extraction unit extracts digital information satisfying a predetermined condition as the sample digital information. The digital information analysis system according to claim 1 or 2, wherein the predetermined specific matter is information indicating that the matter is related to a lawsuit or a cartel. Be one having a relevant to the predetermined specific matters, words, multi-morpheme, or a plurality of keywords including either or more of the plurality of co-occurrence representation, in correspondence to the plurality of keywords A digital information analysis method in a digital information analysis system including a keyword database that stores weighting information that becomes more weighted as the relevance to a specific item related to a keyword is higher .
Based on each of the plurality of keywords and the weighting information associated with each of the plurality of keywords, the combination of the plurality of keywords is determined in advance for each of the plurality of digital information including text data. A scoring stage that associates scores, which are numerical values indicating the level of relevance with the matter ,
A sample including morpheme or co-occurrence expression as temporary digital information that clears a predetermined condition from a plurality of digital information scored so that the relevance is higher as the numerical value is larger in the scoring step; A sample digital information extraction stage for extracting the sample digital information
The extracted content of the sample digital information by morphological analysis, has an information update step of updating the magnitude of the weight for the weighting information stored in the keyword database,
The scoring step associates a new score with each of a plurality of digital information using the new weighting information updated by the information update step,
The specimen digital information extracting step, based on the updated new score by the information updating unit, extracts a new specimen digital information,
The information updating step, the specimen digital information extracting step by using the extracted the new specimen digital information was updated again the size of the weight for the weighting information stored in the keyword database, further, predetermined A digital information analysis method for ending the update with a condition that a difference between the weight information after the update and the weight information before the update falls within a predetermined range as the end condition. Be one having a relevant to the predetermined specific matters, words, multi-morpheme, or a plurality of keywords including either or more of the plurality of co-occurrence representation, in correspondence to the plurality of keywords A digital information analysis program for a digital information analysis system comprising a keyword database that stores weighting information that is weighted more as the relevance of a specific item related to a keyword is higher .
On the computer,
Based on each of the plurality of keywords and the weighting information associated with each of the plurality of keywords, the combination of the plurality of keywords is determined in advance for each of the plurality of digital information including text data. A scoring function for associating scores, which are numerical values indicating the level of relevance to items ,
A sample including a morpheme or co-occurrence expression as temporary digital information that clears a predetermined condition from a plurality of digital information scored so that the relevance increases as the numerical value increases by the scoring function; Sample digital information extraction function to extract the sample digital information
The was extracted extracted contents of the sample digital information by morphological analysis, is realized, and an information updating function for updating the magnitude of the weight for the weighting information stored in the keyword database,
The scoring function associates a new score with each of a plurality of digital information using the new weighting information updated by the information update function,
The specimen digital information extracting function, based on the updated new score by the information updating unit, extracts a new specimen digital information,
The information update function, there is again to update the size of the weight for the weighting information stored in the keyword database by using the sample the new specimen digital information digital information extracting function is extracted, further A digital information analysis program for ending the update with a condition that a difference between the updated weighting information and the pre-update weighting information falls within a predetermined range as a predetermined end condition.