Document identification and inspection system, document identification and inspection method, and document identification and inspection program

1. A document classification and inspection system that obtains digital information including document information configured by a plurality of documents recorded in a plurality of computers or servers and assigns to one or more of the documents a classification code indicating the degree of relevance of the documents to an inspection matter, the system comprising;

at least one processor;

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

extract a document from the document information;

calculate, with respect to the extracted document, a score indicating the strength of

connection of the document and the classification code in a time series manner;

detect a time-series score change from the calculated score; and

inspect and determine the degree of relevance between the inspection matter and the extracted document from the detected time-series score change.

2. The document classification and inspection system according to claim 1 ,

wherein the the memory has stored thereon further instructions that, when executed by the processor, causes the processor to:

calculate a moving average of the scores; and

calculate a difference moving average of the scores from a short period moving average of the scores and a long period moving average of the scores.

3. The document classification and inspection system according to claim 2 ,

wherein the the memory has stored thereon further instructions that, when executed by the processor, causes the processor to:

inspect and determine the degree of relevance between the inspection matter and the extracted document by a point where a sign of a difference between different moving averages changes or an area where the difference between the different moving averages is positive.

4. A document classification and inspection method for obtaining digital information recorded in a plurality of computers or servers, analyzing document information configured by a plurality of documents, included in the obtained digital information, and assigning a classification code indicating the degree of relevance with an inspection matter to a document to make easy use of the inspection matter to inspect the degree of relevance between the inspection matter and the document, the method causing a computer to execute a process comprising:

extracting a document from a document information, and calculating, with respect to the extracted document, a score indicating the strength of connection of the document and a classification code in a time-series manner;

detecting a time-series score change from the calculated score; and inspecting the degree of relevance between the inspection matter and the extracted document from the detected time-series score change.

5. The document classification and inspection method according to claim 4 , further comprising:

calculating a moving average of the scores to calculate a short period moving average and a long period moving average of the scores; and

calculating a difference moving average of the scores from the short period moving average and the long period moving average of the scores to detect the time-series score change.

6. The document classification and inspection method according to claim 5 ,

wherein the degree of relevance between the inspection matter and the extracted document is inspected and determined by a point where a sign of a difference between different moving averages changes or an area where the difference between the different moving averages is positive.

7. A non-transitory computer readable medium comprising instructions executable by at least one processor and causing the at least one processor to perform a document classification and inspection method for obtaining digital information recorded in a plurality of computers or servers, analyzing document information configured by a plurality of documents, included in the obtained digital information, and assigning a classification code indicating the degree of relevance with an inspection matter to a document to make easy use of the inspection matter to inspect the degree of relevance between the inspection matter and the document, the method comprising:

extracting a document from the document information and calculating, with respect to the extracted document, a score indicating the strength of connection of the document and the classification code in a time-series manner;

detecting a time-series score change from the calculated score; and

inspecting the degree of relevance between the inspection matter and the extracted document from the detected time-series score change.