JP2806867B2 - Document database construction method, display method, and display device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a document database for extracting specific words from newspaper articles, technical documents, literary works, etc., and relating the words in a network format.

[0002]

2. Description of the Related Art In recent years, newspaper articles, technical documents, literary works, and the like have been digitized.
Many of these digitized documents do not have keywords or summaries created by the authors, and various attempts have been made to extract subjects and automatically create summaries on electronic computers.

As a method of extracting a word or a sentence indicating a subject from a specific document, first, a method of utilizing the frequency of appearance of a keyword, and second, a method of performing linguistic analysis.

[0004] The former, "in general, what you want to emphasize in the document are those mentioned repeatedly, frequently there is a high possibility that indicate the subject matter of the document words that appear" is based on the theory that. However, in the independent words, "and"
"That", "this", "early", "(that)",
There are words (such as connectives, adnominals, adverbs, formal nouns, prefixes, suffixes, part of demonstrative pronouns, etc.) that appear as linguistic functions, such as "ka (Yoi)" and "(tsuya) pi". . For this reason, it is not possible to determine an important word simply based on the appearance frequency. After excluding such language function words, it is necessary to extract words that have a meaning alone and represent the features of the document. For that purpose, first, an important word list having a large vocabulary is prepared in advance, and then the appearance frequency of a single word in the document is calculated to determine a keyword. In determining this keyword, a result of a linguistic analysis described later may be used. Then, an abstract is generated based on words having a high appearance frequency in the keyword group.

[0005] However, this method cannot cope with a document in which words are paraphrased by synonyms or the like, so that it is difficult to accurately extract means only by simply using the appearance frequency of keywords.

Further, a large-scale thesaurus (synonym dictionary) must be prepared in order to cope with synonyms, which causes a problem that the load on the system increases.
On the other hand, the latter language analysis is a method of determining important words by setting unique parameters related to the conjunctions and the structure of the sentence by focusing on the structure of the conjunction and the sentence, and analyzing the relation between the sentences and the logical structure of the document.

According to this method, a noun phrase with "ha" and "ga" as adjuncts, or a word at the end of a sentence ending with "da" or "da-na" is used as an important word. And For example, in the sentence "Tomorrow's weather will be fine", the noun phrase "weather" accompanied by "ha" is an important word.

In this method, it is effective if the contents of the target document are limited in terms of the field (for example, only technical documents). However, as in a literary work document, it is effective to use "one day", "soon", etc. When judging the development of the story from the conjunction or the description of the hero's action, different unique parameters are required.

[0009]

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and (1) limits the field of document contents without building knowledge on word dictionaries and grammar. (3) It is an object of the present invention to automatically perform subject extraction and expression generation capable of accurately grasping the contents of a document without human intervention such as document preprocessing.

[0010]

According to the present invention, first, an independent word extraction step for extracting an independent word from a given document is executed. In this step, an operation of extracting an independent word from a sentence is performed. The “independent word” in the present invention refers to a word that has a meaning alone. For example, in the case of the sentence “I want to be a cooking teacher”, “cooking”, “teacher”, and “become” are independent words.

Next, a co-occurrence table creation step of creating a co-occurrence table for recording the co-occurrence words and the number of times of co-occurrence for each of the extracted independent words is executed. The term “co-occurrence” in the present invention refers to a relationship between two independent words that exist simultaneously in the same sentence. That is, when a plurality of independent words exist in the same sentence at the same time, these independent words are said to co-occur with each other or to have a co-occurrence relationship. When two independent words having a co-occurrence relation exist, one independent word is referred to as a co-occurring word with respect to the other independent word.

Here, specific examples of the co-occurrence table are shown in FIG. 1 and FIG. FIG. 1 shows an example of creating a co-occurrence table based on two sentences, sentence 1 “I want to be a cooking teacher” and sentence 2 “I am a cooking school teacher”. In the figure, “cooking”, “teacher”, and “nar” are extracted as independent words of sentence 1, and “cooking”,
"School" and "teacher" are extracted. The co-occurrence words on the right side of the figure that are co-occurring with these independent words are extracted and the number of co-occurrence is calculated. For example, the independent word “cooking” exists in both sentence 1 and sentence 2, and for the independent word “cooking”, the co-occurrence word “teacher” occurs once in sentence 1 and 1 in sentence 2 Appeared twice and co-occurred twice. Therefore, the co-occurrence frequency of the co-occurrence word “teacher” with respect to the independent word “cooking” is 2.

FIG. 2 shows an example in which a co-occurrence table is created based on the sentence "I attend a cooking school to become a cooking teacher." Next, a co-occurrence probability calculation step of calculating a co-occurrence probability indicating the strength of the co-occurrence relationship based on the co-occurrence table is executed. Here, the co-occurrence probability is
When there is independent word wi appeared, it is the probability co-occurrence word cj for w i is co-occur with wi P (cj / wi), can be calculated by the following equation (1).

[0014] _{P (c j / w i)} = M (c j / wi) / N wi ····· (1) However, _{w i:} independent words _{(1 ≦ i ≦ N B,} N B: one document the total word amount number) _{c j} in: co-occurrence word for independent words _{w i} (1 ≦ J ≦ N
_{b (wi), N b (} wi: the number of co-occurrence word for the _wi)
M _(c j _{/ w} i): co-occurrence frequency of the independent words _{w i} and the co-occurrence word _{c j} thereto N _wi: the co-occurrence probability calculated by the number of occurrences of (1) of independent words _{w i} is independent word _{w i}
It is the conditional probability of the occurrence of, because shows the semantic links from w _i to the co-occurrence word c _j for it, one-way links, such as the information "independent word w _i → co-occurrence word c _j" Can be expressed by

Subsequently, the present invention executes a co-occurrence number expected value calculating step of calculating an expected value of the co-occurrence number. The expected value E (c _j / w _i ) of the co-occurrence count can be calculated by the following equation (2).

[0016] _{E (c j / w i)} = N s · {1- (1-P cj) m - (1-P wi) m + (1-P cj) m · (1-P wi) m} ... (2) However, _{N s:} one Sobun number in the document N _i: total independence number of words m: average independence number of words in a sentence _{P cj = N cj / N I} P cj: the co-occurrence word _{c j} the occurrence probability _{P wi = N wi / N I} P wi: independent words _{w i} occurrence probability _m-N I / N _s then, the expected value _{E (c} j / _{w i)} and the actual co-occurrence number of times M (c
A subject suggestion independent word group selection step of extracting a combination of an independent word satisfying a certain condition and a co-occurring word corresponding thereto is executed by comparing _j / wi ₎ . As the constant condition, the following equation (3) can be exemplified.

M (c _j / w _i )> E (c _j / w _i ) (3) Then, if the above equation (3) is satisfied, the expected value E (c _j / w)
_i) the actual co-occurrence number will be _{M (c} j / _{w i)} is greater than, it can be said that there is a semantic connection between independent words _{w i} and the co-occurrence word _{c j.} However, the case is extremely small word equivalent number N _B with respect to the total independence number of words N _I in the document, for example, when repeated often with a small word amount, such as the story of a child-friendly, semantic connection is (3) above even if it is very weak
Many combinations of independent words and co-occurring words that satisfy the condition of the expression will appear.

Therefore, considering the average number of appearances of one word, it may be determined that the co-occurrence relation is strong only when the following expression (4) is satisfied. _{M (c j / w i)} > E (c j / w it) + α · N I / N B ····· (4) α , for example, can be determined experimentally.

FIG. 3 shows a total of 5984 words and 11 words.
FIG. 9 is a graph showing the relationship between the number of co-occurrences M (c _j / w _i ) set to α = 1.5 using 98 words of co-occurrence data and its expected value E (c _j / w _i ). . FIG. 4 shows α under similar conditions.
FIG. 5 shows a case where α = 0.5 under the same conditions. Points in the plots in FIGS. 3 to 5 indicate combinations of co-occurring independent words, and points above the solid line in each of the figures satisfy the above equation (4). That is, if α is increased, only information having a stronger co-occurrence relationship can be extracted, and if α is decreased, information having a weaker co-occurrence relationship can be extracted. The setting of α may be 1.5 as an initial value, for example, and may be arbitrarily changed by the user.

Next, the present invention executes a co-occurrence network generation step to set a link from an independent word to a co-occurrence word corresponding thereto and to generate a co-occurrence network. That is, strong semantic connection to the co-occurrence relation is to have the independent word group represented by a link from the independent word w _i to the co-occurrence word c _j thereto, the aforementioned co-occurrence probability P (c j _/ w _i)
Is reflected in the link display form to indicate the strength of the co-occurrence relationship, thereby generating and displaying a co-occurrence network that visually represents the subject of the document. This co-occurrence network, for example, visually recognizes a character string representing each independent word of the independent word group selected in the subject suggestion independent word group selection step and a character string representing each of these independent words having a co-occurrence relationship. A co-occurrence line that is supposed to be connected can be formed on a screen such as a CRT.

The co-occurrence line is, for example, a line type according to the magnitude of the co-occurrence probability of a certain independent word and the co-occurrence word corresponding thereto.
A line or an arrow whose color, shade, direction, length, or thickness is determined can be exemplified. Further, the magnitude of the co-occurrence probability may be visually distinguishable by a three-dimensional expression.

FIG. 6 shows an example of the generated co-occurrence network. Such a co-occurrence network is called CR
It can be displayed and visualized by an output device such as a T screen or a printer, and the subject of the document can be easily visually recognized.

Here, an arrow and a line are used as the display form of the link, and the thickness of the arrow and the line is determined by the co-occurrence probability P (c _j
/ W _i ) is divided into three stages as shown below, depending on the strength of / wi.

[0024]

[Table 1] Such a table may be stored in a storage device of the computer as a table format (for example, a level table).

The numbers with circles in FIG. 6 correspond to the levels in Table 1 above. In the figure, it can be seen that the link from the independent word "Mama" to the co-occurring word "I" is the strongest.

As described above, according to the present invention, the subject of a document can be extracted without constructing a large-scale grammar dictionary. Further, since the semantic connection of the independent words that can suggest the subject can be visually expressed in a network format, a manual search and an automatic search by a computer can be performed extremely efficiently.

In addition, a human can supplement the grammar knowledge necessary for summarization by referring to the network output, so that the subject can be further extracted and the summarization can be generated from the network output. Detailed text comprehension becomes possible.

Furthermore, in the present invention, since the constant (α in equation (4)) is made variable when extracting the subject suggestion words, the number of links to be extracted (displayed) can be freely increased or decreased according to the user's request. . For this reason, it is possible to create a database and generate a co-occurrence network regardless of the contents of a document, from a story such as an old story composed of a small amount of words to a technical document having a large number of words.

Also, the present invention provides a method of displaying a CRT or the like in order to allow a user to determine a required original text by referring to a co-occurrence network and to easily perform an operation for acquiring the original text. The following method using an apparatus is provided.

That is, the present invention searches one or more co-occurrence networks generated in the co-occurrence network generation step, and searches for one or more co-occurrence networks including an arbitrary keyword as an independent word. A document retrieval step for extracting and displaying the screen, and reading out the original text of a document corresponding to an arbitrary co-occurrence network among one or more co-occurrence networks displayed on the screen in the document retrieval step And performing a text reference step to be displayed.

In the document search step, a search formula input section for inputting a search formula for specifying a keyword and a search execution command input section for inputting a search execution command are displayed on the screen of the display device. It may be. At this time, the user inputs a search expression using an input device such as a keyboard, and inputs a search execution command to the search execution command input unit. When a search expression and a search execution command are input, in the document search step, one or two or more co-occurrence networks generated in the co-occurrence network generation step are searched, and a keyword specified by the search expression is searched. The included co-occurrence network is extracted. The extracted co-occurrence network is displayed on a screen by a CRT or the like.

When displaying the co-occurrence network on the screen,
For example, an independent word that matches a keyword may be displayed emphasized or distinguished from others. The method emphasize or discriminate can illustrate how to display a different color, font, or size, etc. The keywords and match independent words and other independent word.

When the original text is displayed on the screen in the original text reference step, there are a method of displaying the entire original text on the screen and a method of displaying a part of the original text on the screen. When displaying a part of the original sentence on the screen, display the sentence or character string containing the keyword entered in the document search step, or the sentence or character string containing the keyword and the sentence or character string before and after it. You may. At this time, it may be displayed by highlighting the sentence containing only keywords, or keyword. Examples of the emphasizing method include, for example, a method of displaying only a keyword or a sentence including the keyword in a shaded manner, a method of reversely displaying the same, and a method of making the color, font, and size of characters different from those of other characters. .

When a new keyword (second keyword) is input in the original text reference step, separately from the keyword (first keyword) input in the document search step, the second keyword is input. To display the sentence containing As a method of specifying the second keyword,
A method of designating the display coordinates of the second keyword by the position designation means can be exemplified.

When requesting reference to the original text,
A method of designating the display coordinates of the co-occurrence network corresponding to the original text by the position designation means can be exemplified. Further, since there may be a plurality of sentences including the keyword in the original sentence, one sentence of the plurality of sentences is displayed on the screen, and the keyword (search formula) and the sentence including the keyword are included in the original sentence. and a number indicating how many, and the numerical value indicating whether the statements that are currently displayed out of the sentence, including the keyword is what the second sentence, the sentence before the sentence that is currently displayed in one of the statements, including the keyword A pre-sentence display instruction input unit for inputting a display instruction and a next sentence display instruction input unit for inputting a display instruction for a sentence after the currently displayed sentence among sentences including a keyword may be displayed on the screen. .

At this time, the user inputs a numerical value indicating the number of sentences including the keyword in the original sentence, and a numerical value indicating the number of the sentence currently displayed among the sentences including the keyword. , It can be recognized that a sentence including a keyword exists before or after the currently displayed sentence. Then, when the user inputs a preamble display command to the preamble display command input unit, the sentence before the currently displayed sentence among the sentences including the keyword is displayed on the screen, and the currently displayed sentence including the keyword is displayed. The number indicating the number of the sentence is 1
Is decremented by one. Further, if the user inputs the next sentence display command to the next sentence display command input unit, with the following statement statement currently displayed among the sentences containing the keywords is displayed on the screen, of the sentence containing the keywords The number indicating the number of the sentence currently displayed is incremented by one.

Further, when displaying the generated co-occurrence network on the screen in the co-occurrence network generation step, a constant change instruction input unit for inputting an instruction to change a predetermined constant added to the expected value is provided. You may make it display on a screen. At this time, if a constant change instruction is input to the constant change instruction input section, the subject suggestion independent word selection step is restarted, and the number of co-occurrences is compared with the expected value and the numerical value obtained by adding the changed constant to the document. Re-select independent words that suggest the subject of Then, the co-occurrence network is re-created based on the re-selected independent words and displayed on the screen.

Next, the document database display device of the present invention will be described. The document database display device includes a co-occurrence table, a co-occurrence probability calculation unit, a co-occurrence count expected value calculation unit, a subject suggestion independent word group selection unit, a co-occurrence network generation unit, a keyword input unit, a document search unit, and a co-occurrence network designation. Means and an original text reference means.

The co-occurrence table records, for each independent word extracted from a given document, a co-occurring word for each independent word and the number of co-occurrences. The co-occurrence probability calculating means calculates a co-occurrence probability indicating the strength of the co-occurrence relationship based on the co-occurrence table.

The co-occurrence count expected value calculating means calculates an expected value of the co-occurrence count based on the co-occurrence table. The subject suggestion independent word group selecting means selects an independent word group suggesting the subject of the document by comparing the expected value and the number of times of co-occurrence.

The co-occurrence network generation means includes a character string representing each independent word of the independent word group selected by the subject suggestion independent word group selection means, and a character string having a co-occurrence relation among the character strings. The co-occurrence network is generated by connecting the columns by a co-occurrence line having a display form corresponding to the magnitude of the co-occurrence probability.

The keyword input means is, for example, a keyboard, and is a device for the user to input a search formula for specifying a keyword. The document search means searches one or more co-occurrence networks generated by the co-occurrence network generation means, and extracts one or more co-occurrence networks including a keyword specified by the search expression. Screen display.

The co-occurrence network designating means designates any one of two or more co-occurrence networks displayed on the screen by the document search means. The original text reference means reads the original text of the document corresponding to the co-occurrence network specified by the co-occurrence network specifying means, and displays a part or all of the original text on a screen.

The co-occurrence line of the co- occurrence network
A line or arrow whose line type, direction, color, shading, length, or thickness is determined by the size of the co-occurrence probability between certain independent words , and these line types, directions, colors, shading, and lengths The thickness or thickness may be arbitrarily changed by the user.

[0045]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 7 shows a conceptual diagram of the processing of the present invention. FIG. 11 is a flowchart showing the procedure of the process of the present invention.

The processing of this embodiment is roughly divided into a co-occurrence database creation processing (100) and a subject suggestion independent word network display processing (200). In order to realize these processes, a CPU having 16-bit processing, preferably 32-bit processing or more, a large-capacity external storage device such as a main memory and a hard disk device, and an external display / output device such as a CRT or a printer are provided. An electronic computer system is used. The co-occurrence database creation processing (100) and the subject suggestion independent word network display processing (2)
00) means that the execution program is read into the CPU from the large-capacity external storage device and executed. The input of the original text is input in advance by application software such as an editor or a word processor, and is stored in a large-capacity external storage device in, for example, a text file format.

The above co-occurrence database creation processing (10
0) and subject suggestion independent word network display processing (200)
May be realized by a single computer, or may realize a co-occurrence database creation device for realizing a co-occurrence database creation process (100) and a subject suggestion independent word network display process (200). It may be divided into a subject suggestion independent word network display device, and these devices may be connected by a communication line so that digitized document data, a co-occurrence database, and the like can be transmitted and received by communication. Further, it is natural that the data transfer between the co-occurrence database creation device and the subject suggestion independent word network display device is not limited to communication. For example, the data transfer is performed by recording on a recording medium such as an FD or a CD-ROM. Methods and the like can be exemplified.

The co-occurrence database creation processing (10
0) and subject suggestion independent word network display processing (20
0) will be described. <Co-occurrence database creation process (100)> The co-occurrence database creation process (100) is based on digitized document data, and includes a co-occurrence table (TBLn), a co-occurrence probability table (TBMn), and an expected value table (TBNn). ) Is created, and this co-occurrence database (KDB) is recorded in a large-capacity external storage device (or main memory). The co-occurrence database creation process (100) includes an independent word extraction process (110) and a co-occurrence table creation process (12) as shown in FIG.
0), a co-occurrence probability calculation process (130), and a co-occurrence count expected value calculation process (140).

The independent word extraction process (110) extracts independent words from the digitized document data and calculates the total number of independent words and the number of vocabulary words in the document. Co-occurrence table creation processing (1
20) creates a co-occurrence table (TBLn) for registering, for each independent word extracted by the independent word extraction process (110) , a co-occurring word for each independent word and its co-occurrence count.

The co-occurrence probability calculation process (130) calculates the co-occurrence probability of each independent word co-occurring with the corresponding co-occurrence word for all independent words recorded in the co-occurrence table (TBLn). When a plurality of co-occurring words exist for one independent word, a co-occurrence probability is calculated for each co-occurring word. Further, in the co-occurrence probability calculation process (130), for each independent word,
A co-occurrence probability table (TBMn) for registering co-occurrence words and co-occurrence probabilities co-occurring with the co-occurrence word is created.

The co-occurrence frequency expected value calculation process (140) is performed on all independent words recorded in the co-occurrence table (TBLn).
An expected value of the number of co-occurrences of each independent word co-occurring with the co-occurring word is calculated. When a plurality of co-occurring words exist for one independent word, an expected value of the number of co-occurring times is calculated for each co-occurring word. Then, for each independent word, an expected value table (TBNn) for registering a co-occurring word and an expected value of the number of co-occurrences co-occurring with the co-occurring word is created.

(Subject suggestion independent word network display processing (200)) The subject suggestion independent word network display processing (200) creates a co-occurrence network based on a co-occurrence database (KDB) , and creates the co-occurrence network. This is a process of outputting to an output device such as a CRT or a printer, as well as searching for the original text of the co-occurrence network and outputting it to the output device.
In this embodiment, a CRT is used as an output device.

Theme suggestion independent word network display processing (2)
00), as shown in FIG. 7, a subject suggestion independent word group selection process (210), a co-occurrence network generation process (220),
Document search processing (230) and original text reference processing (240)
Can be divided into

The subject suggestion independent word group selection processing (210)
From a large-capacity external storage device, a co-occurrence database (KDB) corresponding to document data specified by a user, that is, a co-occurrence table (TBLn) and a co-occurrence probability table (T
BMn) and the expected value table (TBNn) are read. Then, for all the independent words, the relationship between the independent word and the co-occurring word corresponding to the independent word (ie, the relationship between the expected co-occurrence count and the actual co-occurrence count) satisfies the above expression (4). Are determined, and a table for registering these combinations is created. Normal,
An initial value (1.5) is set for the constant α in the equation (4).

The co-occurrence network generation process (220)
The co-occurrence network corresponding to each document is created with reference to the table created by the subject suggestion independent word group selection process (210). The created co-occurrence network is displayed on the CRT screen. This co-occurrence network is based on FIG.
As shown in FIG. 2, the character string is a word indicating an independent word and a co-occurrence line connecting the character strings indicating the independent words in a co-occurrence relationship. Co-occurrence lines have different line types, colors,
Different shades, lengths, or thicknesses. When determining the line type, color, shading, length, or thickness of a link, refer to the co-occurrence probability in the co-occurrence probability table, and select the line type, color, and length of the link according to the magnitude of the co-occurrence probability. Or determine the thickness. As a method for differentiating the strength of co-occurrence,
A method in which two independent words having a co-occurrence relationship and a co-occurrence line connecting these independent words are displayed in a three-dimensional expression, and the expression form of the three-dimensional expression is changed depending on the magnitude of the co-occurrence probability can also be exemplified. Further, when the co-occurrence line is represented by shading according to the strength of the co-occurrence relation, it is possible to make only those whose co-occurrence relation is stronger than a certain degree by the user's selection substantially visible to the user. Alternatively, even weaker co-occurrence relationships can be made substantially visible to the user.

In the co-occurrence network generation process (220), when a plurality of documents are specified by the user,
A co-occurrence network is generated for each document. When the co-occurrence networks are displayed on the screen, the user can select between displaying all documents arranged side by side on one screen and displaying each document superimposed on one screen. Has become. It is also possible to change the expression level (co-occurrence level) of the co-occurrence network by changing the value of the constant α in equation (4) and re-selecting the subject suggestion independent word group.

The document search process (230) searches for one or more co-occurrence networks generated in the co-occurrence network generation process (220) when the user inputs a keyword from a keyboard or the like, for example. , A co-occurrence network including the keyword input by the user is extracted. Here, when there are a plurality of co-occurrence networks including a keyword, these co-occurrence networks are displayed as a whole document or one document at a time depending on the selection of the user.

The original text reference process (240) reads out the original text of the document specified by the user from the document data in the mass storage device and displays it on the screen. As a procedure for designating the original text, the display coordinates of the co-occurrence network of the document desired by the user among one or two or more co-occurrence networks displayed on the screen by the document search process (230) by the position designation means. You can specify it. The position designation means
For example, it is a pointing device such as a mouse.
If the user specifies the display position of one or more arbitrary independent words on the co-occurrence network using a pointing device before designating the original sentence, the independent words are used as the second keyword of the present invention. Will be recognized as And
When displaying the original sentence, a sentence including the second keyword and sentences before and after the sentence are picked up and displayed from the original sentence. At this time, the second keyword or a sentence including the second keyword is emphasized or distinguished by a method such as hatching or reverse display. Further, when there are a plurality of sentences including the keyword in the original sentence, scroll or jump to a portion or a sentence before the currently displayed sentence among the sentences including the keyword, and You can scroll or jump to a part or sentence.

Hereinafter, the operation of the present embodiment will be described. First, the flow of the co-occurrence database creation processing (100) will be described using the example of the Andersen fairy tale “Mermaid Princess”.

The “Mermaid Princess” document is input as text by an editor or a word processor, and is stored as document data in a large-capacity external storage device. This "Mermaid Princess"
Is 687, and these sentences are input sentences 1, 2,
3 ... 687.

In the co-occurrence database creation process (100), an independent word extraction process (110) is executed to sequentially read sentences 1 to Ns (here, Ns = 687), and for each sentence, create an independent word wi An extraction is performed. This independent word extraction processing (110) is specifically performed by the CPU while referring to an independent word / attached word dictionary (DIC) set on a large-capacity external storage device. This independent word / adjunct dictionary (DIC)
Stores the stem and use of the independent word, connection information of an auxiliary word that may accompany the independent word, and the like. Furthermore, the independent word / adjunct dictionary (DIC) includes independent words that are excluded from the subject of the independent words of the present invention, for example, independent words composed of parts of speech such as conjunctions, adverbs, adverbs, formal nouns, and prefixes. Independent words that are unlikely to be the subject of the document, such as

As a result of the independent word extraction processing, the document “Mermaid” is converted to “Mermaid”, “Princess”,
"The Prince", "kiss", the words such as "" and "young" has been extracted as independent words w _i.

Subsequently, a co-occurrence table creation process (120)
There is performed, for each independent word _{w i} extracted by the independent word extraction processing (110), the co-occurrence word _{c j} and their co-occurrence count _{M (c} j / _{w i)} is calculated. Then, for each independent word w _i , the co-occurrence word c _j and its co-occurrence number M (c _j
/ W _i ) is generated. Here, a specific example of the co-occurrence table (TBL1) is shown in FIG.

As shown in the figure, for example, the independent word “mermaid” and its co-occurrence word “hime” co-occur in the document 47 times, while the independent word “hime” and its co-occurrence word “hime” co-occur. The number of times that the word “mermaid” co-occurs in the document is 50 times. The co-occurrence table (TBL) thus created
1) is stored in a large-capacity external storage device.

Next, a co-occurrence probability calculation process (130) is executed, and based on the number of co-occurrences M (c _j / w _i ) registered in the co-occurrence table (TBL1), the co-occurrence probability P (c _j / wi) is calculated. w _i )
Is calculated. The calculation of the co-occurrence probability P (c _j / w _i ) is calculated based on the above equation (1). For example, the number of occurrences N _wi of the independent word “mermaid” in a document is 74 times. Accordingly, the co-occurrence probability P (c _j / w _i ) at which the independent word “mermaid” co-occurs with the co-occurrence word “princess” is as follows.

P (c _j / w _i ) = M (c _j / w _i ) / N
_wi = 47/74 = 0.635135 calculated co-occurrence probability _{P (c} j / _{w i),} together with the independent words _{w i} and the co-occurrence word _{c j} thereto, is registered in the co-occurrence probability table (TBMn) .

In FIG. 9, the co-occurrence probability P (c _j / w _i ) is registered in the co-occurrence probability table (TBMn) of the same format as the co-occurrence table (TBL1). (C _j / w _i ) may be stored in a large-capacity external storage device or the like so as to have a certain relation with the co-occurrence table (TBL1). Further, a single table may be stored together with the co-occurrence count expected value E (c _j / w _i ) described later. Furthermore, the co-occurrence frequency M (c _j /
w _i ), the co-occurrence probability P (c _j / w _i ), and the co-occurrence count expected value E (c _j / w _i ) described below may be stored in association with each other.

Next, the co-occurrence count expected value calculation processing (140)
Is performed, and the co-occurrence count expected value E (c _j / w _i ) is calculated based on the above-described equation (2). As a result, the co-occurrence frequency expected value E (c _j / w _i ) at which the independent word “mermaid” co-occurs with the co-occurrence word “princess” is 16.575816.
The co-occurrence count expected value E (c _j /
w _i ) is registered in the expected value table (TBNn) together with the independent word w _j and the co-occurring word c _{j corresponding} thereto, and the expected value table (TBNn) is stored in the co-occurrence database KDB of the large-capacity external device.

Through the above processing, the co-occurrence database (K
DB) is completed. In FIG. 7, the co-occurrence table (TBL1, 2,... N) and the co-occurrence probability P (c _j / w)
_i ) is registered in the co-occurrence probability table (TBM1, 2,...)
.. N) and an expected value table (TBN1, 2,... N) for registering the co-occurrence count expected value E (c _j / w _i ) constitute a co-occurrence database (KDB).

Next, the flow of the subject suggestion independent word network display processing (200) will be described. In the subject suggestion independent word network display processing (200), a subject suggestion independent word group selection processing (210) is first executed. In the subject suggestion independent word group selection process (210), a co-occurrence database corresponding to a document specified by the user (for example, a fairy tale "Mermaid Princess") is read from the co-occurrence database group of the large-capacity external storage device. It is. Then, as shown in FIG. 11, the above-mentioned equation (4) for each of all the independent words w _i and the total co-occurrence word c _j is examined. Here, 1.5 is set as the initial value for the constant α.

[0071] Then, to create a table for registering a combination of co-occurrence word c _j for it and the independent word w _i that satisfies the above equation (4). Next, a co-occurrence network generation process (220) is performed. In the co-occurrence network generation processing (220), the subject suggestion independent word group selection processing (2)
Reading combinations of the tables created with independent words w _i and the co-occurrence word c _j for it at 10), stores the link towards the co-occurring word c _j in the large capacity external storage device thereto from the independent word w _i Hand over to the display module that is being used. Display module, a string that represents the independent word w _i,
A character string representing a co-occurrence word c _j and an independent word w
A co-occurrence network consisting of co-occurrence lines connecting _i and the co-occurrence word c _j is formed on the screen. At this time,
The thickness of the co-occurrence line is determined based on the level table (stored on the large-capacity external storage device) shown in Table 1 described above. still,
Strength of the co-occurrence relation is not the thickness of independent words w _i and a line connecting the co-occurrence word c _j thereto, linetype, color, shading, as distinguished by length, or three-dimensional representation Is also good.

Further, the user who refers to the co-occurrence network output from the CRT or the printer can change the co-occurrence level. In this case, the value of the constant α in the above equation (4) is changed, so that the subject suggestion independent word group selection processing (210) and the co-occurrence network generation processing (220) are executed again. In Subject suggesting independent word group selection process (210), the combination of the co-occurrence word c _j thereto and independent word w _i not satisfy the equation (4) for changing the value of the constant α is selected, registering a combination thereof Table is recreated. Then, in the co-occurrence network generation process (220), a new co-occurrence network is created based on the re-created table and output to the CRT.

The subject suggestion independent word group selection processing (21)
0) and the co-occurrence network generation process (220) are executed for all the selected documents when the user selects a plurality of documents. A plurality of co-occurrence networks created in this way may be displayed simultaneously on one screen, or only one co-occurrence network may be displayed on one screen and each screen may be switched by screen switching or page switching. A co-occurrence network may be displayed.

In the document search process (230), when the user inputs an arbitrary keyword (independent word) from an input device such as a keyboard, the input keyword and the independent word included in the co-occurrence network of each document are determined. A co-occurrence network that includes a self-sufficient word that matches the input keyword is extracted. The extracted co-occurrence network is a CRT
Is displayed on the screen. At this time, on the co-occurrence network, an independent word that matches the keyword input by the user is displayed so as to be emphasized or distinguished from other independent words. For example, the display color, size,
The typeface and the like are made different from other independent words, or the independent words are shaded, inverted, or squared.

Since a plurality of keywords can be input, a co-occurrence network including all keywords is determined when a plurality of keywords are input.

With the above processing, the user can enter the CR
By referring to the co-occurrence network output to T or a printer, the subject of each document can be visually grasped.
Then, the user selects a document to refer to the original text. To select a document, the user double-clicks on the screen the display coordinates of the co-occurrence network of the desired document by using a mouse as a position specifying means. As a result, the original text reference processing (240) is executed, the co-occurrence network of the display coordinates specified by the mouse is determined, and the original text of the document corresponding to this co-occurrence network is read from the large-capacity external storage device. And from among the read original sentences,
The sentence including the keyword input by the user and the sentences before and after the keyword are picked up and displayed on the CRT screen.

Next, an operation procedure when the subject suggestion independent word network display processing (200) is realized by a computer having a CRT and a hard disk device as a large-capacity external storage device will be described with reference to FIGS. explain.

FIG. 13 is an initial screen displayed on the CRT when the subject suggestion independent word network display processing (200) is activated. This initial screen is provided with a menu bar “File”, “Display”, and “Help”. The user selects "File" from these menu bars. When the menu bar “File” is selected, a “File” pull-down menu is displayed as shown in FIG. This pull-down menu includes
"New", "Open" and "Exit"
Is set. “New creation” is selected when a new document is read, that is, when a co-occurrence network for a new document is created. “Open” is selected when displaying a document that has already been read or a co-occurrence network of the document. "Termination of the application" indicates the subject suggestion independent word network display processing (20
Select this to end 0).

When the user selects “new creation” from the pull-down menu, a “new creation” dialog box as shown in FIG. 15 is displayed. This dialog box displays the location “bunsyo” (default value) where the document file is stored in the hard disk device and the number “4” of documents stored in the document file. Further, a “display all documents” button, a “display one document at a time” button, and a “cancel” button are set in the dialog box. The "Display All Documents" button is used to display multiple co-occurrence networks side by side on one screen. The "Display One Document at a Time" button displays multiple co-occurrence networks on one screen. a button to be selected if you <br/>. The “cancel” button is a button that is selected when ending the new creation processing.

When the display coordinates of the "display all documents" button are designated by the pointing device, the subject suggestion independent word group selection process (210) of the subject suggestion independent word network display process (200) and the co-occurrence network generation process (22)
0) is executed to create a co-occurrence network for each document in the document file. The created co-occurrence networks are displayed side by side on one screen as shown in FIG. On this screen, “edit” and “window” are added in addition to the menu bar “file”, “display”, and “help”.

Here, when the user selects the menu bar "edit", a pull-down menu "search" is displayed as shown in FIG. Subsequently, when the user selects the “search” pull-down menu, a “search” dialog box is displayed as shown in FIG. This dialog box is provided with an area for inputting a search character string (independent word) (up to three words can be input in the drawing), a “search execution” button, and a “cancel” button. The search character string is input from an input device such as a keyboard (see FIG. 19). When the input of the search character string is completed, the user selects the “search execution” button.

When the “execute search” button is selected, in the subject suggestion independent word network display processing (200), the co-occurrence network including all the search character strings input by executing the document search processing (230) is displayed. Is extracted. And
Independent word w _i that matches the search string on the extracted co-occurrence network, displays different colors, sizes and other independent word, font, etc., (FIG. 19 is displayed in a different format, a square enclosed ). Thus, the user can visually grasp the subject of each document, and can easily select a document whose original text is to be referred to.

When the user refers to the original text, the user double-clicks the display coordinates of the co-occurrence network corresponding to the original text or the display coordinates of the display window of the co-occurrence network with the mouse. By this operation, a dialog box of the original sentence is displayed on the screen as shown in FIG. In this dialog box, a part of the original text of the document corresponding to the selected co-occurrence network is displayed. A part of the original sentence displays the earliest sentence and the sentences before and after the sentence including the search character string in the original sentence, and the sentence including the search character string is shaded. .

Further, in the dialog box, a search character string as a keyword input at the time of document search processing,
A numerical value indicating how many sentences including the search character string are included in the original sentence and a numerical value indicating the number of the sentence currently displayed sentence among the sentences including the search character string (FIG. 2)
0, number of cases), “Previous” button, “Next” button,
An “OK” button is displayed.

The "previous" button is a button selected when referring to a sentence preceding the currently displayed sentence among sentences including the search character string. When the display coordinates of the "previous" button are designated by the pointing device, the display screen scrolls or jumps to the sentence preceding the currently displayed sentence among the sentences including the search character string.

The "next" button is a button selected when referring to a sentence next to the currently displayed sentence among sentences including the search character string. When the display coordinates of the “next” button are designated by pointing, the display screen scrolls or jumps to the sentence next to the currently displayed sentence among the sentences including the search character string.

Note that, even when the display screen is scrolled by the “previous” button or the “next” button, the sentence including the search character string is displayed in a shaded manner. The “OK” button is a button selected when closing the dialog box.

By performing such a procedure for each document,
You can refer to the original text of all documents. As a result, the user can determine a necessary document and an unnecessary document.

FIG. 21 shows a screen after the document 4 has been saved or discarded. In the present embodiment, when the document 4 is saved or discarded, the display window of the co-occurrence network corresponding to the document 4 is deleted from the screen.

When the user selects the "display one document at a time" button on the screen shown in FIG. 15, the display windows of the co-occurrence networks overlap as shown in FIG. Only the originating network will be displayed. On this screen, in addition to the menu bar "File", "View", "Help",
"Edit" and "Window" are added.

Here, in order to execute the document search process (230), the menu bar "edit" is selected and the pull-down menu is read out in the same manner as in the case of the above-mentioned "all document display", and the pull-down menu is read out. Select "Search" from. When "search" is selected, a "search" dialog box is displayed as shown in FIG. The configuration of this dialog box is the same as in the case of “display all documents”.

After the search character string as a keyword is input by the keyboard, when the display coordinates of the “execute search” button are designated by the pointing device,
The co-occurrence network including all the input search character strings is extracted, and the display window of the co-occurrence network is moved to the front. At this point, the search process is temporarily interrupted (see FIG. 24).

In the co-occurrence network moved to the foreground, the independent word that matches the search character string is displayed in a different form, such as a different color or font, from the other independent words in the co-occurrence network (FIG. 24). Medium, square box).

When the display coordinates of the “execute search” button are designated by the pointing device again, the search process is restarted. When a corresponding co-occurrence network is found, the display window of the co-occurrence network is moved to the foreground instead of the previously displayed co-occurrence network display window (see FIGS. 25 and 26).

When referring to the original text of the document corresponding to the foreground co-occurrence network, the document search process (2
30) A procedure for inputting a keyword (second keyword) different from the keyword (first keyword) input and referring to the original text, and referring to the original text without inputting the second keyword. There is a procedure.

First, the procedure for referring to the original text without selecting the second keyword is as follows. For example, when referring to the original text corresponding to the co-occurrence network shown in FIG. Double-click.
As a result, a dialog box of the original text is displayed on the screen. The displayed original sentence is a sentence including the first keyword and sentences before and after the sentence.

In the procedure for selecting the second keyword and then referring to the original text, for example, the display coordinates of the desired independent word are clicked on the co-occurrence network shown in FIG. 27 with the mouse. At this time, although not shown, the selected independent word is displayed in a format different from other independent words. Next, when the display coordinates of the co-occurrence network (the display coordinates of the display window of the co-occurrence network) are double-clicked with the mouse, a dialog box of the original text is displayed as shown in FIG. In this dialog box, among the original sentences, a sentence including the second keyword and sentences before and after the second keyword are displayed. The sentence including the second keyword is shaded.

Further, the dialog box displays a character string of the independent word selected as the second keyword, a numerical value indicating how many sentences including the second keyword are included in the original document, and a currently displayed text. A number indicating which sentence is the sentence containing the search string in the original sentence,
A “Previous” button, a “Next” button, and an “OK” button are displayed. The functions of the “previous” button, “next” button, and “OK” button are the same as in the case of “display all documents”.

When the document corresponding to the foreground co-occurrence network is discarded, the display window of the co-occurrence network is deleted, and the display window of the next co-occurrence network is moved to the foreground. .

Next, a procedure for changing the expression level (co-occurrence level) of the co-occurrence network will be described. In both cases of “display all documents” and “display one document at a time,” the “+” button and “−”
Buttons are provided, and when the display coordinates of one of the buttons is designated by the pointing device, the expression level is changed. For example, in the case where the co-occurrence networks are displayed in a superimposed manner as shown in FIG. 29, in order to increase the expression level (decrease the co-occurrence level), the user needs:
The display coordinates of the "+" button are designated by a pointing device. When the display coordinates of the "+" button are designated, the subject suggestion independent word group selection process (210) and the co-occurrence network generation process (220) of the subject suggestion independent word network display process (200) are executed again. In Subject suggesting independent word group selection process (210), (4) the smaller the value of the constant alpha, the value of the constant alpha is decreased (4) independent words satisfy the equation w _i and the co-occurrence word c to it Select a combination of _j . Then, the co-occurrence network generation processing (22
0), recreate the co-occurrence network based at in combination with the newly selected the independent words w _i and the co-occurrence word c _j thereto. The recreated co-occurrence network is C
It is displayed on the RT (see FIG. 30).

On the other hand, to lower the expression level (increase the co-occurrence level), the user specifies the display coordinates of the "-" button using a pointing device. When the display coordinates of the "-" button are designated, the subject suggestion independent word group selection processing (2) of the subject suggestion independent word network display processing (200)
10) and the co-occurrence network generation process (220) are executed again. In the subject suggestion independent word group selection process (210),
(4) increasing the value of the constant α in Equation selects a combination of independent words w _i and the co-occurrence word c _j thereto satisfying the value of the constant α is increased (4). Then, the co-occurrence network generation processing (220), reshaping the co-occurrence network based on a combination of the co-occurrence word c _j newly selected and independent word w _i with respect thereto. The recreated co-occurrence network is displayed on the CRT (see FIG. 31).

As described above, according to the present embodiment, the user
The subject of each document can be visually grasped without reading the original text. Also, the operation performed to grasp the subject of each document is simple.

As a method of expressing the co-occurrence network, as shown in FIG. 32, the strength of the co-occurrence relationship between independent words may be differentiated by the type of a straight line connecting the independent words. . In the drawing, the co-occurrence lines are classified into three types: a thick solid line, a thin solid line, and a dotted line. As a method of determining a line type, three constants A, B, and C (A>B> C) are set in advance.
Is determined, and a thick solid line connects the independent words having the co-occurrence relationship with the expression (4) that satisfies the expression (4) and the difference (left side and right side) is larger than the constant A, and satisfies the expression (4) and the difference is The independent words having a co-occurrence relationship equal to or greater than the constant B and equal to or less than the constant A are connected by a thin solid line, and the independent words having the co-occurrence relationship satisfying the expression (4) and having a difference less than the constant C are indicated by a dotted line. A method of tying can be exemplified. The line type of the co-occurrence line connecting the independent words is
When the expression level (co-occurrence level) is changed by the "+" button and the "-" button, the expression level (co-occurrence level) is changed in accordance with the change.

Further, as a method of expressing the co-occurrence network, as shown in FIGS. 33 to 36, a method of differentiating the strength of the co-occurrence relation between independent words by gradation (shading) of the independent words and the co-occurrence lines. Can be exemplified. in this case,
In the co-occurrence network generation processing, a co-occurrence network having a high expression level (co-occurrence level is low) in advance (see FIG. 33)
Is generated. At the time of generation, the co-occurrence level between independent words having a co-occurrence relationship is also classified into several stages according to the size. For example, when the co-occurrence levels are classified into three levels, three constants A, B, and C (A>B> C) are determined in advance, and (condition 1) the above equation (4) is satisfied and the difference (Condition 2) A self-sustained word that satisfies the above expression (4) and has a co-occurrence relation that is equal to or greater than the constant B and equal to or less than the constant A (condition 2). Inter-words, (Condition 3) Classify into three inter-independent words that satisfy the above expression (4) and have co-occurrence with a difference less than the constant C.
Then, when the co-occurrence network is displayed on the screen, for example, as shown in FIG. 34, only the independent word and the co-occurrence line satisfying the above (condition 1) are displayed. In the screen of FIG. 34, the portions with a dark gradation (“hair” and “hair”, “transparent”
And "passed") have reached the user's visibility level.

When the user selects the "+" button or the "-" button on the screen, the gradation is changed. For example, if the "+" button on the screen is selected,
As shown in FIG. 3, the colors of the independent word and the co-occurrence line satisfying the above (condition 2) gradually become darker, and finally, as shown in FIG. It has the same depth as words and co-occurrences. At this time, (Condition 1)
In addition to the independent words and the co-occurrence lines satisfying (2), the independent words and the co-occurrence lines satisfying (Condition 2) can be seen.

When the independent word and the co-occurrence line satisfying the above (condition 1) and the independent word and the co-occurrence line satisfying the (condition 2) are displayed on the screen, the "-" button on the screen is displayed. When selected, the colors of the self-contained word and the co-occurrence line satisfying (Condition 2) gradually decrease, and eventually decrease to a level that cannot be captured by human vision. At this time, the user sees only the independent word and the co-occurrence line satisfying (condition 1).

In addition to the co-occurrence line type and gradation,
A method of differentiating by the color of a co-occurrence line or an independent word, or a three-dimensional expression may be used. <Other Embodiments> When the present invention is realized by a co-occurrence database creation device and a subject suggestion independent word network display device, the co-occurrence database creation device is arranged on the server side, and the subject suggestion independent word network display device is provided. Can be conceived on the client side and these devices are connected by a communication line. When this method is adopted, it is preferable that the subject-suggested independent word group selection process and the co-occurrence network generation process are performed by the co-occurrence database creation device to generate a co-occurrence network in advance. Then, a request for transmitting a co-occurrence network including an arbitrary keyword is transmitted from the subject suggestion independent word network display device to the co-occurrence database creation device. The co-occurrence database creation apparatus searches for a co-occurrence network group created in advance and extracts a co-occurrence network including an arbitrary keyword,
Send to the subject suggestion independent word network display device.

The subject suggestion independent word network display device:
When the co-occurrence database is received from the co-occurrence database creation device, the co-occurrence database is displayed on a screen by a display device such as a CRT.

When a user who has referred to the co-occurrence network on the screen inputs a reference request for the original text (specifies the display coordinates of the co-occurrence network by the position specifying means), the subject suggestion independent word network display device specifies The identification information of the co-occurrence network is transmitted to the co-occurrence database creation device.

When the co-occurrence database creation device receives the identification information from the subject suggestion independent word network display device, it reads the original text of the document corresponding to the co-occurrence network specified by the identification information, and displays the subject suggestion independent word network display. Send to device.

In the subject suggestion independent word network display device which has received the original text, the original text is displayed on the screen in the same procedure as in the above-described embodiment. When this method is adopted, when the user who refers to the co-occurrence network desires to change the expression level, the co-occurrence network is recreated by the co-occurrence database creation device, and the re-created co-occurrence network is re-subjected to the subject. Although it may be sent back to the suggestion independent word network display device, a co-occurrence database creation device creates a co-occurrence network with a high expression level in advance, and adds a level An identifier may be set. Here, the level identifier is information for identifying the strength of the co-occurrence relationship between the independent words.

For example, when classifying the co-occurrence strength into three levels, three constants A, B, and C (A>
B> C), and (Condition 1) between independent words having a co-occurrence relationship that satisfies the above-mentioned expression (3) (or expression (4)) and whose difference (left side−right side) is larger than the constant A, Condition 2) between independent words that satisfy the above-mentioned expression (3) (or expression (4)) and have a co-occurrence relationship in which the difference is equal to or greater than the constant B and equal to or less than the constant A, (condition 3) the expression (3) (Or (4)
) Are satisfied, and the difference is classified into three of the independent words having a co-occurrence relationship smaller than the constant C.

A level identifier "1" is set between independent words satisfying the above condition 1, a level identifier "2" is set between independent words satisfying the above condition 2, and a level identifier "2" is set between independent words satisfying the above condition 3. An identifier “3” is added.

The co-occurrence network creation device stores the co-occurrence network to which the level identifier has been added in the mass storage device. Then, when a transmission request for a co-occurrence network including an arbitrary keyword is transmitted from the subject suggestion independent word network display device to the co-occurrence network creation device, the co-occurrence network creation device is stored in the mass storage device. Then, the co-occurrence network including the arbitrary keyword and its level identifier are extracted. Then, the co-occurrence network creating device transmits the level identifier together with the co-occurrence network to the subject suggestion independent word network display device.

The subject suggestion independent word network display device is:
First, a screen is displayed on the screen between the independent words to which the level identifier “1” is added and the independent words to which the level identifier “2” is added. Then, when the user specifies to increase the expression level (reduce the co-occurrence level), the subject-suggested independent word network display device displays between the independent words to which the level identifier “1” is added and the level identifier “2”. Are displayed on the screen between the independent words to which "" is added and the independent words to which the level identifier "3" is added.

On the other hand, when the user specifies to lower the expression level (increase the co-occurrence level), the subject suggestion independent word network display device displays the screen only between the independent words to which the level identifier “1” is added. indicate.

[0117]

According to the present invention, by showing the semantic connection between words using the co-occurrence relation, it becomes possible to grasp the document subject visible to the operator.

Further, by providing a constant capable of increasing or decreasing the number of links, a general-purpose database can be created and a co-occurrence network can be extracted regardless of the type of document.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram showing a specific example of a co-occurrence table.

FIG. 2 is an explanatory diagram showing a specific example of a co-occurrence table;

FIG. 3 shows the number of co-occurrences M (c _j / w _i ) and its expected value E
Graph showing the _(c j / _{w i)} relationship alpha = 1.5 and

FIG. 4 shows the number of co-occurrences M (c _j / w _i ) and its expected value E
Graph showing the relationship between the alpha = 2.5 and _(c j / _{w i)}

FIG. 5 shows the number of co-occurrences M (c _j / w _i ) and its expected value E
Graph showing the _(c j / _{w i)} the relationship between alpha = 0.5

FIG. 6 is an explanatory diagram showing an example of an expression form of a co-occurrence network.

FIG. 7 is a block diagram showing the concept of the processing of the present invention.

FIG. 8 is an explanatory diagram showing a co-occurrence table according to the embodiment;

FIG. 9 is an explanatory diagram illustrating a calculation result of a co-occurrence probability according to the embodiment;

FIG. 10 is an explanatory diagram showing a calculation result of a co-occurrence count expected value according to the embodiment;

FIG. 11 is a flowchart showing co-occurrence database creation processing and subject suggestion independent word network display processing according to the embodiment;

FIG. 12 is an explanatory diagram illustrating a display example of a co-occurrence network according to the embodiment;

FIG. 13 is an initial screen when the subject suggestion independent word network display processing is executed.

FIG. 14 is an operation screen (1) when the subject suggestion independent word network display processing is executed.

FIG. 15 is an operation screen (2) when subject display independent word network display processing is executed.

FIG. 16 is a display screen of a co-occurrence network.

FIG. 17 is an operation screen (1) of a document search process.

FIG. 18 is an operation screen (2) of a document search process.

FIG. 19 is an operation screen (3) of a document search process.

[Figure 20] Original text display screen

[FIG. 21] Co-occurrence network display screen after original text is stored or discarded

FIG. 22: Co-occurrence network display screen

FIG. 23 is an operation screen (4) of a document search process.

FIG. 24 is an operation screen (5) of a document search process.

FIG. 25 is an operation screen (6) for a document search process.

FIG. 26 is an operation screen (7) of a document search process.

FIG. 27: Operation screen for original sentence reference processing

[FIG. 28] Original text display screen

FIG. 29 is an operation screen when changing the expression level of a co-occurrence network

FIG. 30 is a display screen (1) after the expression level of the co-occurrence network is changed.

FIG. 31 is a display screen (2) after changing the expression level of the co-occurrence network

FIG. 32 shows another display format of the co-occurrence network (1).

FIG. 33 shows another display format of the co-occurrence network (2).

FIG. 34 shows another display format of the co-occurrence network (3).

FIG. 35 shows another display format of the co-occurrence network (4).

FIG. 36 shows another display format of the co-occurrence network (5).

[Explanation of symbols]

 DIC, independent word, attached word dictionary TBL1-n, co-occurrence table TBM1-n, co-occurrence probability table TBN1-n, expected value table KDB, co-occurrence database 100, co-occurrence database creation process 110・ Independent word extraction processing 120 ・ ・ Co-occurrence table creation 130 ・ ・ Co-occurrence probability calculation processing 140 ・ ・ Co-occurrence count expected value calculation processing 200 ・ ・ Subject suggestive independent word network display processing 210 ・ ・ Subject suggestive independent word group selection processing 220: Co-occurrence network generation processing 230: Document search processing 240: Original text reference processing

Continuation of the front page (56) References JP-A-7-56948 (JP, A) JP-A-6-332939 (JP, A) JP-A-5-197712 (JP, A) JP-A-5-282367 (JP) JP-A-7-200608 (JP, A) JP-A-5-28199 (JP, A) JP-A-63-292268 (JP, A) JP-A-9-134360 (JP, A) 8-329118 (JP, A) JP-A-6-103311 (JP, A) JP-A-6-176058 (JP, A) JP-A-59-38846 (JP, A) JP-A-2-98778 (JP, A) A) JP-A-5-346938 (JP, A) JP-A-3-252767 (JP, A) JP-A-3-15981 (JP, A) JP-A-1-140332 (JP, A) JP-A-2 -188881 (JP, A) JP-A-4-1854 (JP, A) Eiichi Arita, Ryuichi Oka, "Extraction of fragmentary knowledge chain from newspaper article text data", IEICE Technical Report Vol. . 93, no. 528 (NLC93-63-68), PP. 23-30 (March 22, 1994) Shunsaku Tamura, Kimio Hosono, et al., "Expansion of search formula using semantic maps", Proceedings of the 24th Information Science and Technology Research Conference PP. 161-167, Japan Science and Technology Information Center (March 18, 1988) Yasuhiro Suzuki, Koji Tochiuchi, "Improvement of Automatic Abstraction Method with Keyword Density Method", Transactions of the Information Processing Society of Japan, Vol. 29, No. 3 PP. 325-328 (March 15, 1988) (58) Field surveyed (Int. Cl. ⁶ , DB name) G06F 17/30

Claims (16)

(57) [Claims] An independent word extraction step of extracting an independent word from a given document; and a co-occurrence table for creating a co-occurrence table for recording the co-occurring words and the number of co-occurrences for each of the extracted independent words. A creating step, a co-occurrence probability calculating step of calculating a co-occurrence probability indicating the strength of the co-occurrence relationship based on the co-occurrence table, and a co-occurrence calculating an expected value of the number of co-occurrence times based on the co-occurrence table An expected number of times calculation step; a subject suggestion independent word group selecting step of comparing the expected value and the co-occurrence number to select a group of independent words having a co-occurrence relationship capable of suggesting the subject of the document; Co-occurrence network generating step of setting a link between independent words having a co-occurrence relationship suggesting the subject and displaying the expression form of the link as a co-occurrence network determined based on the co-occurrence probability How to build a document database that contains the. 2. The method according to claim 1, wherein the subject suggestion independent word group selection step comprises:
2. The independent word group having a co-occurrence relation that can suggest a subject of a document by comparing the number of times of co-occurrence with a numerical value obtained by adding a predetermined constant to the expected value. How to build a document database. 3. The co-occurrence network generation step includes: a character string representing each independent word of the co-occurrence independent word group selected in the subject suggestion independent word group selection step; 2. The method according to claim 1, further comprising the step of displaying on a screen a co-occurrence network formed from co-occurrence lines visually connecting the character strings representing the respective characters. 4. The co-occurrence line is a line or an arrow whose line type, color, shading, direction, length, or thickness is determined by the magnitude of co-occurrence probabilities between co-occurring independent words. 4. The method for constructing a document database according to claim 3, wherein 5. Searching one or more co-occurrence networks generated in the co-occurrence network generation step to extract one or more co-occurrence networks including an arbitrary keyword, A document search step of displaying a co-occurrence network on a screen, and one or two displayed on the screen in the document search step
2. The construction of a document database according to claim 1, further comprising the steps of: extracting an original sentence corresponding to an arbitrary co-occurrence network among the one or more co-occurrence networks and displaying all or a part of the original sentence on a screen. Method. 6. Searching for one or more co-occurrence networks generated in the co-occurrence network generation step, and including one or more first keywords
A document search step of extracting one or more co-occurrence networks and displaying the co-occurrence network on a screen; and one or two screens displayed on the screen in the document search step
Extracting a source sentence corresponding to an arbitrary co-occurrence network of the one or more co-occurrence networks, and a sentence or character string including one or more second keywords of the original text;
2. The document database construction method according to claim 1, further comprising: an original sentence reference step of displaying a sentence or character string including the second keyword and sentences or character strings before and after the second keyword on a screen. 7. The original sentence reference step includes: when displaying a sentence or character string including the one or more second keywords and a sentence or character string before and after the sentence or character string on the screen, the second keyword or 7. The method according to claim 6, wherein the sentence including the second keyword is displayed in a distinguished manner. 8. The document search step includes: displaying a search formula input unit for inputting a search formula for specifying a keyword and a search execution command input unit for inputting a search execution command; When a search formula is input to the input unit and a search execution command is input to the search execution command input unit, one or two or more co-occurrence networks generated in the co-occurrence network generation step are searched, Extracting one or more co-occurrence networks including the keyword specified by the search expression; displaying the one or more co-occurrence networks extracted above on a screen; The method according to claim 5, further comprising the step of: distinguishing and displaying a keyword specified by the search expression among the independent words included in the network. How to build a document database. 9. In the original sentence reference step, when displaying a sentence including the keyword on a screen, the keyword, a numerical value indicating how many sentences including the keyword are included in the original sentence, and the keyword A numerical value indicating the number of the sentence currently displayed in the sentence including the sentence, and a pre-sentence display for inputting a display instruction of a sentence prior to the currently displayed sentence among the sentences including the keyword Displaying a command input unit and a next sentence display command input unit for inputting a display command of a sentence after the currently displayed sentence among the sentences including the keyword, and displaying a preamble sentence on the preamble display command input unit When a command is input, a sentence before the currently displayed sentence among the sentences including the keyword is displayed on the screen, and when a next sentence display command is input to the next sentence display command input unit, the keyword is displayed. Containing sentence 6. The method according to claim 5, wherein a sentence next to the currently displayed sentence is displayed on the screen. 10. The co-occurrence network generation step includes: displaying a constant change instruction input unit for inputting an instruction to change a predetermined constant added to the expected value together with the generated co-occurrence network on a screen; When a constant change instruction is input to the constant change instruction input unit, the subject suggestion independent word selection step is restarted,
A step of comparing the number of times of co-occurrence and the numerical value obtained by adding the constant after the change to the expected value to re-select an independent word group having a co-occurrence relationship that can suggest the subject of the document; and 3. The method according to claim 2, further comprising the steps of: re-creating the co-occurrence network based on the independent word; and displaying the re-created co-occurrence network on a screen. 11. A character string representing each independent word of a group of independent words in a co-occurrence relationship that can suggest the subject of a document, and a co-occurrence line visually connecting the character strings of the independent words in a co-occurrence relationship. When the display coordinates of an arbitrary character string are specified by the position specifying means and the display coordinates of the co-occurrence network are specified by the position specifying means, the co-occurrence network corresponding to the co-occurrence network is displayed. The original sentence of the document to be extracted is extracted, and a sentence or a character string including the character string specified by the position designation unit, or a sentence or a character string including the character string and sentences or character strings before and after the original sentence are extracted from the original sentence. How to display the document database to be displayed on the screen. 12. The co-occurrence line is a line or an arrow whose line type, direction, color, length, or thickness is determined by the magnitude of the co-occurrence probability between co-occurring independent words. The method for displaying a document database according to claim 11. 13. A co-occurrence table for recording, for each independent word extracted from a given document, a co-occurrence word for each independent word and the number of times of co-occurrence, and a co-occurrence relationship based on the co-occurrence table. A co-occurrence probability calculating means for calculating a co-occurrence probability representing strength; a co-occurrence number expected value calculating means for calculating an expected value of the number of co-occurrence based on the co-occurrence table; A subject suggestion independent word group selecting means for selecting independent word groups having a co-occurrence relationship that can suggest the subject of the document by comparing A co-occurrence network consisting of a character string representing a word and a co-occurrence line connecting the character strings representing the independent words in co-occurrence among the character strings in a form corresponding to the magnitude of the co-occurrence probability Co-occurrence network generation means and keywords Keyword input means for inputting, and one or two or more co-occurrence networks generated by the co-occurrence network generation means are searched, and one or two or more keywords including the keyword input to the input means are searched. Document search means for extracting a co-occurrence network and displaying the screen, and co-occurrence network designating means for designating an arbitrary co-occurrence network among one or more co-occurrence networks displayed on the screen by the document search means A document database display device comprising: an original text reference unit that reads an original text of a document corresponding to the co-occurrence network specified by the co-occurrence network specification unit and displays a part or all of the original text on a screen. 14. A co-occurrence line composed of a character string representing each independent word of a group of independent words that can suggest a subject of a document, and a co-occurrence line connecting character strings representing respective independent words having a co-occurrence relationship. When the display coordinates of the co-occurrence network are specified by the position specifying means after the display coordinates of an arbitrary character string are specified by the position specification means, a document corresponding to the co-occurrence network is displayed. Of the original sentence, and a sentence or character string including the specified character string in the original sentence, or a sentence or character string including the character string, and a sentence or character string before and after the character string are displayed on a screen. A document database display device that displays only a sentence including the character string or only the character string. 15. The co-occurrence line is a line or an arrow whose line type, direction, color, shading, length, or thickness is determined according to the magnitude of the co-occurrence probability between co-occurring independent words. The display device for a document database according to claim 14, wherein: 16. The co-occurrence line type, color, shading, length,
Or the thickness is arbitrarily changed by a user.
4. The display device of the document database according to 4.