Document classification apparatus

Claim 2

A document classification apparatus comprising: a 5W1H keyword extraction means for extracting keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; a classification key setting means for setting a 5W1H attribute entered through the input apparatus as a classification key; a classification item selection means for selecting keywords as classification items, each of which has the 5W1H attribute set by the classification key setting means as a classification key, out of keywords extracted by the 5W1H keyword extraction means; and a document distribution means for distributing a document including one of the keywords which are selected as classification items by the classification item selection means and have the 5W1H attribute set as classification keys by the classification key setting means, into a cell corresponding to one of the classification items.

Claim 3

The document classification apparatus as claimed in claim 1 , wherein: the classification item selection means selects keywords by the order of their decreasing occurrence frequencies in the document.

Claim 4

The document classification apparatus as claimed in claim 1 , wherein: the classification item selection means selects keywords as classification items in the order of their decreasing occurrence frequencies in a document including no keywords selected as classification items.

Claim 5

A document classification apparatus comprising: a 5W1H keyword extraction means for extracting keywords with 5W1H attributes from a document entered through an input apparatus; a classification key setting means for setting two 5W1H attributes entered through the input apparatus as a vertical line classification key and a horizontally axial classification key, respectively; a vertical line classification item selection means for selecting keywords with 5W1H attributes as vertical line classification items, extracted by the 5W1H keyword extraction means and then set by the classification key setting means as vertical line classification keys; a horizontally axial classification item selection means for selecting keywords with 5W1H attributes as horizontally axial classification items, extracted by the 5W1H keyword extraction means and then set by the classification key setting means as horizontally axial keys; and a document distribution means for distributing a document that includes the keyword selected as vertical line classification item by the vertical line classification item selection means with the 5W1H attribute set as the vertical line classification key by the classification key setting means and further includes the keyword selected as horizontally axial classification item by the horizontally axial classification item selection means with the 5W1H attribute set as the horizontally axial classification key by the classification key setting means, into a cell located on the intersection of both the row corresponding to the vertical line classification items and the column corresponding to the horizontally axial classification items in a 2-dimensional matrix.

Claim 6

A document classification apparatus comprising: a 5W1H keyword extraction means for extracting keywords with 5W1H attributes from a document entered through an input apparatus; a classification key setting means for setting two 5W1H attributes entered through the input apparatus as a vertical line classification key and a horizontally axial classification key, respectively; a vertical line classification item selection means for selecting keywords with 5W1H attributes as vertical line classification items, extracted by the 5W1H keyword extraction means and then set by the classification key setting means as vertical line classification keys; a horizontally axial classification item selection means for selecting keywords with 5W1H attributes as horizontally axial classification items, extracted by the 5W1H keyword extraction means and then set by the classification key setting means as horizontally axial keys; and a document distribution means for distributing a document that includes the keyword selected as vertical line classification item by the vertical line classification item selection means with the 5W1H attribute set as the vertical line classification key by the classification key setting means and further includes the keyword selected as horizontally axial classification item by the horizontally axial classification item selection means with the 5W1H attribute set as the horizontally axial classification key by the classification key setting means, into a cell located on the intersection of both the row corresponding to the vertical line classification items and the column corresponding to the horizontally axial classification items in a 2-dimensional matrix.

Claim 7

The document classification apparatus as claimed in claim 4 , wherein: the vertical line classification item selection means selects keywords as vertical line classification items in the order of their decreasing occurrence frequencies in the document, and the horizontally axial classification item selection means selects keywords as horizontally axial classification items in the order of their decreasing occurrence frequencies in the document.

Claim 8

The document classification apparatus as claimed in claim 4 , wherein: the vertical line classification item selection means selects keywords as vertical line classification items in the order of their deceasing occurrence frequencies in a document including no keyword selected as the vertical line classification item, and the horizontally axial classification item selection means selects keywords as horizontally axial classification items in the order of their decreasing occurrence frequencies in a document including no keyword selected as horizontally axial classification item.

Claim 9

The document classification apparatus as claimed in claim 4 , wherein: the horizontally axial classification item selection means selects keywords as horizontally axial classification items in a document including the keyword selected as the vertical line classification item by the vertical line classification item selection means with the 5W1H attribute set as the vertical line classification item by the classification key setting means.

Claim 10

The document classification apparatus as claimed in claim 7 , wherein: the vertical line classification item selection means selects keywords as vertical line classification items in the order of their occurrence frequencies; and the horizontally axial classification item selection means selects keywords as horizontally axial classification items in the order of their occurrence frequencies.

Claim 11

The document classification apparatus as claimed in claim 7 , wherein: the vertical line classification item selection means selects keywords as vertical line classification items in the order of their decreasing occurrence frequencies in a document including no keyword selected as the vertical line classification item; and the horizontally axial classification item selection means selects keywords as horizontally axial classification items in the order of their decreasing occurrence frequencies in a document including no keyword selected as the horizontally axial classification item.

Claim 12

A document classification apparatus comprising: a 5W1H keyword extraction means for extracting keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; a classification key setting means for setting a 5W1H attribute entered through the input apparatus as a classification key; a classification level setting means for setting a level entered through the input apparatus as a classification level; a concept data base means for classifying words which may appear in a document as keywords into hierarchic layers in accordance with an upper or lower notion level to each word, assigning a different level to each hierarchic layer, and storing them; a classification item selection means for selecting broader concept words of the keywords extracted by the 5W1H keyword extraction means as classification items, each of which has the 5W1H attribute set by the classification key setting means as a classification key, from words in the classification level set by the classification level setting means in the concept data base means; and a document distribution means for distributing a document including one of the keywords, whose broader concepts contain one of the words selected as classification items by the classification item selection means in the level set by the classification level setting means in the concept data base means and which has the 5W1H attribute set as the classification key by the classification key setting means, into a cell corresponding to one of the classification items.

Claim 13

A document classification apparatus comprising: a 5W1H keyword extraction means for extracting keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; a classification key setting means for setting a 5W1H attribute entered through the input apparatus as a classification key; a classification level setting means for setting a level entered through the input apparatus as a classification level; a concept data base means for classifying words which may appear in a document as keywords into hierarchic layers in accordance with an upper or lower notion level to each word, assigning a different level to each hierarchic layer, and storing them; a classification item selection means for selecting broader concept words of the keywords extracted by the 5W1H keyword extraction means as classification items, each of which has the 5W1H attribute set by the classification key setting means as a classification key, from words in the classification level set by the classification level setting means in the concept data base means; and a document distribution means for distributing a document including one of the keywords, whose broader concepts contain one of the words selected as classification items by the classification item selection means in the level set by the classification level setting means in the concept data base means and which has the 5W1H attribute set as the classification key by the classification key setting means, into a cell corresponding to one of the classification items.

Claim 14

The document classification apparatus as claimed in claim 10 , wherein: the classification item selection means selects words as classification items in the order of decreasing occurrence frequencies of keywords in the document; the keywords corresponding to words in the classification level set by the classification level setting means under the upper notion category in terms of the concept data base means.

Claim 15

The document classification apparatus as claimed in claim 10 , wherein: the classification item selection means selects words as classification items in the order of their decreasing occurrence frequencies in a document in which a first keyword corresponds to a word in the classification level set by the classification level setting means, under the upper notion category words in terms of the concept data base means, does not include a second keyword which corresponds to a word selected as the classification item in the classification level set by the classification level setting means, under the upper notion category.

Claim 16

A document classification apparatus comprising: a 5W1H keyword extraction means for extracting keywords with 5W1H attributes from a document entered through an input apparatus; a classification key setting means for setting two 5W1H attributes entered through the input apparatus as a vertical line classification key and a horizontally axial classification key, respectively; a classification level setting means for setting two levels entered through the input apparatus as a vertical line classification level and a horizontally axial classification level, respectively; a concept data base means for classifying words which may appear as keywords in a document into hierarchic layers in accordance with the upper or lower notion level to each word, assigning a different level to each hierarchic layer, and storing them; a vertical line classification item selection means for selecting as vertical line classification item a broader concept of the keyword extracted by the 5W1H keyword extraction means and being with the 5W1H attributes set as vertical line classification keys by the classification key setting means, from words in a vertical line classification level set by the classification level setting means in the concept data base means; a horizontally axial classification item selection means for selecting as horizontally axial classification item a broader concept of the keyword extracted by the 5W1H keyword extraction means and being with the 5W1H attributes set as horizontally axial classification keys by the classification key setting means, from words in a horizontally axial classification level set by the classification level setting means in the concept data base means; and a document distribution means for distributing a document including a first keyword word with the 5W1H attribute set as the vertical line classification key by the classification key setting means and a second keyword with the 5W1H attribute set as the horizontally axial classification key by the classification key setting means, into a cell located on the intersection of both the row corresponding to the vertical line classification items and the column corresponding to the horizontally axial classification items in a 2-dimensional matrix; broader concepts of the first keyword containing the word selected as the vertical line classification item by the vertical line classification item selection means in the vertical line level set by the classification level setting means in the concept data base means, and broader concepts of the second keyword containing the word selected as the horizontally axial classification item by the horizontally axial classification item selection means in the horizontally axial level set by the classification level setting means in the concept data base means.

Claim 17

A document classification apparatus comprising: a 5W1H keyword extraction means for extracting keywords with 5W1H attributes from a document entered through an input apparatus; a classification key setting means for setting two 5W1H attributes entered through the input apparatus as a vertical line classification key and a horizontally axial classification key, respectively; a classification level setting means for setting two levels entered through the input apparatus as a vertical line classification level and a horizontally axial classification level, respectively; a concept data base means for classifying words which may appear as keywords in a document into hierarchic layers in accordance with the upper or lower notion level to each word, assigning a different level to each hierarchic layer, and storing them; a vertical line classification item selection means for selecting as vertical line classification item a broader concept of the keyword extracted by the 5W1H keyword extraction means and being with the 5W1H attributes set as vertical line classification keys by the classification key setting means, from words in a vertical line classification level set by the classification level setting means in the concept data base means; a horizontally axial classification item selection means for selecting as horizontally axial classification item a broader concept of the keyword extracted by the 5W1H keyword extraction means and being with the 5W1H attributes set as horizontally axial classification keys by the classification key setting means, from words in a horizontally axial classification level set by the classification level setting means in the concept data base means; and a document distribution means for distributing a document including a first keyword word with the 5W1H attribute set as the vertical line classification key by the classification key setting means and a second keyword with the 5W1H attribute set as the horizontally axial classification key by the classification key setting means, into a cell located on the intersection of both the row corresponding to the vertical line classification items and the column corresponding to the horizontally axial classification items in a 2-dimensional matrix; broader concepts of the first keyword containing the word selected as the vertical line classification item by the vertical line classification item selection means in the vertical line level set by the classification level setting means in the concept data base means, and broader concepts of the second keyword containing the word selected as the horizontally axial classification item by the horizontally axial classification item selection means in the horizontally axial level set by the classification level setting means in the concept data base means.

Claim 18

The document classification apparatus as claimed in claim 13 , wherein: the vertical line classification item selection means selects words as vertical line classification items in the order of decreasing occurrence frequencies of keywords in the document; the keywords corresponding to the words in the vertical line classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means, while the horizontally axial classification item selection means selects words as horizontally axial classification items in the order of decreasing occurrence frequencies of keywords in the document; the keywords corresponding to the words in the horizontally axial classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means.

Claim 19

The document classification apparatus as claimed in claim 13 , wherein: the vertical line classification item selection means selects the words as vertical line classification items in the order of their decreasing occurrence frequencies in a document in which a first keyword corresponding to the word in the vertical line classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means, does not include a second keyword which corresponds to a word selected as the vertical line classification item in the vertical line classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means; and the horizontally axial classification item selection means selects words as horizontally axial classification items in the order of their decreasing occurrence frequencies in a document in which a third keyword corresponding to a word selected as the horizontally axial classification item in the horizontally axial classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means, does not include a fourth keyword which corresponds to a word selected as the horizontally axial classification item in the horizontally axial classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means.

Claim 20

The document classification apparatus as claimed in claim 13 , wherein: the horizontally axial classification item selection means selects the words as horizontally axial classification items from upper notion category words to keywords in a document including a keyword with the 5W1H attribute set as vertical line classification key by the classification key setting means; the keyword corresponding to a word selected by the vertical line classification item selection means in the vertical line classification level set by the classification level setting means, under the upper notion category in terms of the concept data base.

Claim 21

The document classification apparatus as claimed in claim 16 , wherein: the vertical line classification item selection means selects words as vertical line classification items in the order of decreasing occurrence frequencies of keywords in the document; the keywords corresponding to the words in the vertical line classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means, and the horizontally axial classification item selection means selects words as horizontally axial classification items in the order of decreasing occurrence frequencies of keywords in the document; the keywords corresponding to the words in the horizontally axial classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means.

Claim 22

The document classification apparatus as claimed in claim 16 , wherein: the vertical line classification item selection means selects the words as vertical line classification items in the order of their decreasing occurrence frequencies in a document in which a first keyword corresponds to the word in the vertical line classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means, does not include a second keyword which corresponds to the word selected as the vertical line classification item in the vertical line classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means; and the horizontally axial classification item selection means selects the words as horizontally axial classification items in the order of their decreasing occurrence frequencies in a document in which a third keyword corresponding to the word in the horizontally axial classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means, does not include a fourth keyword which corresponds to a word selected as horizontally axial classification items in the horizontally axial classification level set by the classification level setting means, under the upper notion category in terms of the concept data base means.

Claim 23

A document classification method comprising the steps of: extracting keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; setting a 5W1H attribute entered through the input apparatus as a classification key; selecting keywords as classification items, each of which has the 5W1H attribute set in the setting step as a classification key, out of keywords extracted in the extracting keyword step; and distributing a document including one of the keywords which are selected as the classification items and have the 5W1H attribute set as the classification key, into a cell corresponding to one of the classification items.

Claim 24

A document classification method comprising the steps of: extracting keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; setting a 5W1H attribute entered through the input apparatus as a classification key; selecting keywords as classification items, each of which has the 5W1H attribute set in the setting step as a classification key, out of keywords extracted in the extracting keyword step; and distributing a document including one of the keywords which are selected as the classification items and have the 5W1H attribute set as the classification key, into a cell corresponding to one of the classification items.

Claim 25

A document classification method comprising the steps of: extracting keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; setting a 5W1H attribute entered through the input apparatus as a classification key; setting a level entered through the input apparatus as a classification level; classifying words which may appear as keywords in a document, into the upper or lower notion hierarchic layer to the words, assigning a specific level to each hierarchic layer, and storing them as a concept data base; selecting upper notion category words as classification items, each of which has the 5W1H attribute set in the setting a 5W1H attribute step as a classification key, out of the keywords extracted from words in the classification level; and distributing a document including one of the keywords with the 5W1H attribute set as the classification key into a cell corresponding to one of the classification items; the one of the keywords corresponding to a word selected as the classification item in the level under the upper notion category in the concept data base.

Claim 26

A document classification method comprising the steps of: extracting keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; setting a 5W1H attribute entered through the input apparatus as a classification key; setting a level entered through the input apparatus as a classification level; classifying words which may appear as keywords in a document, into the upper or lower notion hierarchic layer to the words, assigning a specific level to each hierarchic layer, and storing them as a concept data base; selecting upper notion category words as classification items, each of which has the 5W1H attribute set in the setting a 5W1H attribute step as a classification key, out of the keywords extracted from words in the classification level; and distributing a document including one of the keywords with the 5W1H attribute set as the classification key into a cell corresponding to one of the classification items; the one of the keywords corresponding to a word selected as the classification item in the level under the upper notion category in the concept data base.

Claim 27

A computer-readable medium, comprising: a computer-readable data storage device; a program stored on said device, said program causing a computer: to extract keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; to set a 5W1H attribute entered through the input apparatus as a classification key; to select keywords as classification items, each of which has the 5W1H attribute set in the to set step as a classification key, out of keywords extracted in the to extract keywords step; and to distribute a document including one of the keywords which are selected as the classification items and have the 5W1H attribute set as the classification key into a cell corresponding to one of the classification items.

Claim 28

A computer-readable medium, comprising: a computer-readable data storage device; a program stored on said device, said program causing a computer: to extract keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; to set a 5W1H attribute entered through the input apparatus as a classification key; to select keywords as classification items, each of which has the 5W1H attribute set in the to set step as a classification key, out of keywords extracted in the to extract keywords step; and to distribute a document including one of the keywords which are selected as the classification items and have the 5W1H attribute set as the classification key into a cell corresponding to one of the classification items.

Claim 29

A computer-readable medium, comprising: a computer-readable data storage device; a program stored on said device, said program causing a computer: to extract keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; to set a 5W1H attribute entered through the input apparatus as a classification key; to set a level entered through the input apparatus as a classification level; to classify words, which may appear in a document as a keyword, into hierarchic notion layers in accordance with the upper or lower notion to each word, to assign a different level to each hierarchic notion layer, and to store them as a concept data base; to select broader concept words as classification items to the extracted keywords, each classification item has the 5W1H attribute set in the to set a 5W1H attribute step as a classification key, from words in the classification level in terms of the concept data base; and to distribute a document including one of the keywords with the 5W1H attribute set as the classification key, into a cell corresponding to one of the classification items; the one of the keywords corresponding to a word selected as the classification item in the level under the broader concept in terms of the concept data base.

Claim 30

A computer-readable medium, comprising: a computer-readable data storage device; a program stored on said device, said program causing a computer: to extract keywords, each of which has a 5W1H attribute, from a document entered through an input apparatus; to set a 5W1H attribute entered through the input apparatus as a classification key; to set a level entered through the input apparatus as a classification level; to classify words, which may appear in a document as a keyword, into hierarchic notion layers in accordance with the upper or lower notion to each word, to assign a different level to each hierarchic notion layer, and to store them as a concept data base; to select broader concept words as classification items to the extracted keywords, each classification item has the 5W1H attribute set in the to set a 5W1H attribute step as a classification key, from words in the classification level in terms of the concept data base; and to distribute a document including one of the keywords with the 5W1H attribute set as the classification key, into a cell corresponding to one of the classification items; the one of the keywords corresponding to a word selected as the classification item in the level under the broader concept in terms of the concept data base.