JP2006092193A - Document processor and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To specify, in detail, a category of a quantity expressed by numerical value expression described in a document to be digitized. <P>SOLUTION: This document processor associating one or more nouns and category data expressing the category of the quantity that is a numerical value imparted with a unit and stores them analyzes inputted document data, and extracts sentence data expressing a sentence including the numerical value expression that is a character string expressing the numerical value imparted with the unit. The document processor analyzes the sentence data, generates a set of the nouns included in the sentence data, and specifies the category expressed by the category data stored in association with the one or more nouns each having a highest degree of similarity with the set as the category of the quantity expressed by the numerical value expression included in the sentence expressed by the sentence data extracted by an extraction means. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  More particularly, the present invention relates to a technique for extracting a specific type of information from information described in a paper document.

  Paper documents (hereinafter simply referred to as “documents”) are excellent media for transmitting and recording information, but the problem is that a space such as a library is required to store them. There is. In addition, when information is recorded on a paper document and saved, if the information recorded on the paper document is needed later, the target information can be selected from many paper documents stored in the archive. I have to find a paper document in which I was recorded. That is, the form of recording and storing information on a paper document is not preferable from the viewpoint of improving the efficiency of business.

  Under such circumstances, paper documents are digitized and stored. Specifically, an image corresponding to each page of a paper document is read by a scanner device or the like, and image data corresponding to the image (hereinafter referred to as “document image data”) is filed for each paper document and stored on a hard disk or the like. Storage in a storage device has been performed.

By the way, when a paper document is digitized and stored, the document image data corresponding to the paper document is not simply stored as a file, but the information (hereinafter referred to as “category”) described in the paper document is stored. It is convenient to search for information and perform various statistical processes by classifying them into databases. As an example of a technique that enables this, there is a technique for extracting proper nouns such as a person name, a place name, and an organization name from a paper document to be digitized (Patent Document 1).
Japanese Patent Application Laid-Open No. 07-021169

  By the way, in a paper document, in addition to the proper nouns described above, a character string (hereinafter referred to as “numerical expression”) representing a numerical value (hereinafter referred to as “quantity”) to which a unit such as an amount of money, length, or temperature is given. ”), And business documents such as payment documents and sales slips are examples. When digitizing such a business document, it is indispensable to extract these numerical expressions in addition to the proper nouns described above and classify the quantities represented by the numerical expressions into categories. When a paper document to be digitized is written in Japanese, it is generally easy to extract a numerical expression from document image data corresponding to the paper document. This is because such a numerical expression has a numerical part in which symbols representing scales such as numbers, Chinese numerals, and “,” and “.” Are consecutive, and a prefix indicating the unit in the numerical part (for example, , “$”, “$”, Etc.) and suffixes (for example, “Yen”, “m”, “° C.”, etc.) are added. Furthermore, it is easy to specify a general category (for example, “amount”, “length”, etc.) of the numerical value represented by the numerical expression based on the prefix or the suffix. .

  However, when creating a database by digitizing a business document as described above, it is not possible to extract a numerical expression described in the business document or specify a rough category of the quantity represented by the numerical expression. It is enough. Because, for example, for a numerical expression that represents money amount, even if it is databased without specifying whether the numerical expression represents the amount of "travel expenses" or the amount of "sales money" This is because such a database cannot be used for accounting, etc., and is useless at all.

  The present invention has been made in view of the above problems, and an object of the present invention is to provide a technique that makes it possible to specify in detail a category of a quantity represented by a numerical expression described in a document to be digitized. It is said.

  In order to solve the above problems, the present invention relates to a storage unit that stores one or more nouns and category data that represents a category of a quantity that is a numerical value to which a unit is assigned in association with each other, and an electronic document. An input means for inputting converted document data, and extracting the sentence data representing a sentence including a numerical expression which is a character string representing a numerical value to which a unit is assigned by analyzing the document data inputted to the input means Means for analyzing the sentence data extracted by the extracting means, extracting nouns included in the sentence represented by the sentence data, and generating the set; and the set generated by the generating means; The category represented by the category data stored in the storage unit in association with the one or more nouns having the highest degree of similarity is included in the sentence represented by the sentence data extracted by the extraction unit. To provide a document processing apparatus having a specifying means for specifying a category of the quantity represented by the numeric representation being. According to such a document processing device, category data stored in the storage means in association with one or more nouns having the highest degree of similarity to a set of nouns included in a sentence including numerical expressions. Is identified as the category of the quantity represented by the numerical expression.

  In a more preferred aspect, the one or more nouns stored in the storage means in association with the category data are nouns that define a category of a quantity represented by the numerical expression when a sentence is formed together with the numerical expression. It is characterized by being.

  In a more preferred aspect, the set generated by the generating means includes a noun other than the one or more nouns stored in the storage means in association with the category data specified by the specifying means. In this case, the information processing apparatus includes a writing unit that writes the noun in the storage unit in association with the category data. In such an aspect, the set of nouns used together with the numerical expression representing the quantity for which the category is specified by the specifying means is stored in the storage means in association with the category data or 1 When a noun other than a plurality of nouns is included, the noun is written to the storage means in association with the category data.

  In a more preferred aspect, the storage means represents a hierarchical structure for a quantity category, which is a numerical value to which a unit is assigned, and hierarchical structure data representing one or more categories included in each hierarchy is written. And the specifying means determines the category of the quantity represented by the numerical expression included in the sentence represented by the sentence data extracted by the extracting means according to the hierarchical structure represented by the hierarchical structure data. Specify the category in order from the highest hierarchy, and refer to one or more nouns stored in the storage means in association with the category data representing each of all categories belonging to the hierarchy specifying the category, The category of the hierarchy is specified. In such an aspect, when specifying a category belonging to a lower hierarchy, only the noun stored in the storage means in association with each category belonging to the hierarchy is referred to, and unnecessary data is referred to. Therefore, there is an effect that the identification accuracy is improved.

  Further, in order to solve the above-described problem, the present invention is a computer device that analyzes document data when document data obtained by digitizing a document is input, and uses a character string representing a numerical value to which a unit is assigned. Extraction means for extracting sentence data representing a sentence including a numerical expression, and analyzing the sentence data extracted by the extraction means, extracting nouns contained in the sentence represented by the sentence data and generating a set thereof The degree of similarity between the generating means to be generated and the set generated by the generating means among a set of nouns stored in the computer device for each category data representing a category of a quantity that is a numerical value assigned with a unit. The number included in the sentence represented by the sentence data extracted by the extracting means, the category represented by the category data stored in the computer device in association with the highest set Providing a program to function as a specifying means for specifying a category of the quantity represented by the expression. According to such a program, the numerical expression included in the sentence belongs based on the noun stored in the computer device for each category to which the numerical expression belongs and the noun included in the sentence including the numerical expression. A category is identified. In another aspect of the present invention, the program may be written and provided in a computer-readable recording medium.

  According to the present invention, not only the numerical expression described in the document to be digitized is extracted and the rough category according to the unit of the numerical expression is specified, but the quantity category represented by the numerical expression is detailed. It becomes possible to specify.

The best mode for carrying out the present invention will be described below with reference to the drawings.
(A: Configuration)
FIG. 1 is a block diagram showing a configuration example of a document digitizing system 10 having a document processing apparatus 110 according to an embodiment of the present invention. An image reading device 120 in FIG. 1 is a scanner device having an automatic paper feeding mechanism such as an ADF (Auto Document Feeder), for example, reads a paper document set in the ADF page by page, and a document corresponding to the read image. The image data is delivered to the document processing apparatus 110 via a communication line 130 such as a LAN (Local Area Network). In the present embodiment, the case where the communication line 130 is a LAN will be described, but it is needless to say that a WAN (Wide Area Network), the Internet, or the like may be included. In the present embodiment, the document processing apparatus 110 and the image reading apparatus 120 are described as separate hardware, but it is needless to say that both may be configured as integral hardware. In such an aspect, the communication line 130 is an internal bus that connects the document processing apparatus 110 and the image reading apparatus 120 within the hardware.

  The document processing apparatus 110 in FIG. 1 stores and accumulates document image data delivered from the image reading apparatus 120 as a file, and has the configuration shown in FIG. As shown in FIG. 2, the document processing apparatus 110 includes a control unit 200, a communication interface (hereinafter referred to as IF) unit 210, a storage unit 220, and a bus 230 that mediates data exchange between these components. And.

  The control unit 200 is a CPU (Central Processing Unit), for example, and controls each unit of the document processing apparatus 110 by executing various kinds of software stored in a storage unit 220 described later. The communication IF unit 210 is connected to the image reading device 120 via the communication line 130, receives the document image data sent from the image reading device 120 via the communication line 130, and delivers it to the control unit 200. It is. That is, the communication IF unit 210 functions as an input unit to which document image data sent from the image reading device 120 is input.

  As shown in FIG. 2, the storage unit 220 includes a volatile storage unit 220a and a nonvolatile storage unit 220b. The volatile storage unit 220a is, for example, a RAM (Random Access Memory), and is used as a work area by the control unit 200 operating according to various software described below. On the other hand, the non-volatile storage unit 220b is, for example, a hard disk, and stores data and various software for causing the control unit 200 to realize functions unique to the document processing apparatus according to the present invention. The document image data is filed and written in the nonvolatile storage unit 220b.

  Examples of data stored in the non-volatile storage unit 220b include hierarchical structure data representing the hierarchical structure of the quantity category represented by the numerical expression, and a sentence including the quantity category represented by the numerical expression and the numerical expression thereof. And correspondence data representing the correspondence with one or more nouns. These hierarchical structure data and correspondence data are categories of quantities represented by numerical expressions described in a document (that is, a paper document to be digitized) corresponding to document image data input via the communication IF unit 210. Plays a role as a classification dictionary that is used when specifying a word based on a noun included in a sentence including the numerical expression. Hereinafter, a set of the hierarchical structure data and the correspondence data is also referred to as a classification dictionary.

  For example, an example of a hierarchical structure for a quantity category represented by a numerical expression for money (hereinafter also referred to as “money expression”) is the hierarchical structure shown in FIG. In the hierarchical structure illustrated in FIG. 3, the quantity represented by the monetary expression (that is, the monetary amount) is “travel expenses”, “purchasing expenses”, “loyalty”, “utility expenses”, “conference expenses”, and “recruitment activity expenses”. "Travel expenses" is further subdivided into "accommodation expenses" and "transportation expenses", "purchasing expenses" are further divided into "commercial software purchase expenses" and "magazine / material purchases" It is subdivided into “cost”.

  On the other hand, examples of the correspondence data include data shown in FIGS. 4A, 4B, and 4C. Each of the correspondence relationship data shown in FIG. 4 includes category data representing a quantity category represented by monetary expression (for example, character string data representing a category) and one or more nouns (also referred to as features). . For example, in the correspondence data shown in FIG. 4A, the category of the quantity represented by the monetary expression included in the sentence including “Tokyo, Nagoya, Shinkansen, limited express, fee, billing” is “transportation expense”. Each noun contained in the correspondence data is extracted from the sentence “I will charge 7890 yen as an express fare for the Shinkansen from Tokyo to Nagoya”. In the present embodiment, the correspondence data is generated by associating one or more nouns included in the sentence including the monetary expression with the category data representing the quantity category represented by the monetary expression. Explained. However, it is needless to say that one or more nouns included in the correspondence data do not necessarily constitute a sentence together with a monetary expression. In short, a noun that suffices to compose a sentence with a monetary expression that represents the quantity of a certain category is sufficient, and when composing a sentence with a monetary expression, the category of the quantity represented by that monetary expression (ie, monetary amount) Any noun that defines

  Also, the correspondence relationship data shown in FIG. 4B indicates that the category of the quantity represented by the monetary expression included in the sentence including “hotel, 3 nights, expense” is “accommodation expense”. Each noun included in the correspondence data shown in FIG. 4 (b) is extracted from the sentence “The hotel cost for 3 nights at a hotel is 45,000 yen”. .

  Further, the correspondence data shown in FIG. 4C indicates that the category of the quantity represented by the monetary expression included in the sentence including “magazine, purchase, expense” is “book-material purchase expense”. Yes. Each noun included in the correspondence data shown in FIG. 4C is extracted from the sentence “The purchase cost of the magazine was 6,000 yen”.

  As is clear from the above, each noun included in the correspondence data has a feature that, when a sentence is constructed with a monetary expression, the category of the quantity (that is, monetary) represented by the monetary expression is determined. ing. Therefore, according to the document processing apparatus 110 according to the present embodiment, the hierarchical structure data representing the hierarchical structure shown in FIG. 3 and the correspondence relationships shown in FIGS. 4 (a), 4 (b), and 4 (C). The document image data corresponding to the document in which the sentence “5000 yen is charged as an express charge for the Shinkansen from Tokyo to Nagoya” is input under the condition that the data is stored in the nonvolatile storage unit 220b. Then, since the noun included in the sentence matches the noun included in the correspondence data shown in FIG. 4A, the monetary expression included in the sentence (ie, “5000 yen”). The category of quantity represented by) is specified as “transportation expenses”.

  On the other hand, examples of software stored in the non-volatile storage unit 220b include OS software for causing the control unit 200 to implement an operating system (hereinafter referred to as “OS”) and paper document digitization software. . Here, the paper document digitization software extracts the numerical expression described in the document corresponding to the document image data sent from the image reading device 120, and the category of the quantity represented by the numerical expression is stored in the classification dictionary. This is software for causing the control unit 200 to execute processing specified based on the above. Hereinafter, functions provided to the control unit 200 by executing these software will be described.

  When the power (not shown) of the document processing apparatus 110 is turned on, the control unit 200 first reads the OS software from the nonvolatile storage unit 220b and executes it. The control unit 200 operating according to the OS software and realizing the OS is provided with a function for controlling each unit of the document processing apparatus 110 and a function for reading out and executing other software from the nonvolatile storage unit 220b. Is done. In the present embodiment, the control unit 200 that completes the execution of the OS software and realizes the OS immediately reads the paper document digitizing software from the nonvolatile storage unit 220b and executes it. FIG. 5 is a flowchart showing the flow of the category specifying process performed by the control unit 200 operating according to the paper document digitizing software. As shown in FIG. 5, the control unit 200 operating according to the paper document digitizing software is given the following three functions.

  First, when document image data is input via the communication IF unit 210, the document image data is analyzed by OCR (Optical Character Recognition) or the like, and is described in a paper document corresponding to the document image data. This is an extraction function that extracts sentence data representing a sentence. In the present embodiment, only the sentence data for a sentence including a monetary expression among the sentences described in the paper document is extracted by the extraction function. In order to selectively extract only sentence data representing a sentence including a monetary expression in this way, a numerical expression including a character (for example, yen) or a symbol (for example, \) representing a monetary unit is included. Only for the sentence, sentence data representing the sentence may be extracted.

  Second, a generation function that performs morphological analysis on the sentence data extracted by the extraction function, extracts all nouns included in the sentence represented by the sentence data, and generates a set thereof. Third, the sentence data is represented based on the set generated by the generation function and the classification dictionary (that is, the hierarchical structure data and the correspondence data stored in the nonvolatile storage unit 220b). This is a specific function that specifies the category of the quantity represented by the monetary expression included in the sentence. More specifically, in the present embodiment, it is included in the correspondence data including one or more nouns (that is, a set of nouns) having the highest degree of similarity to the set generated by the generation function. The category represented by the category data is identified by the identifying function as the category of the quantity represented by the monetary expression. In addition, as a method for determining the similarity between sets, for example, a known technique such as a vector space method may be used.

  As described above, the hardware configuration of the document processing apparatus 110 according to the present embodiment is the same as that of a general computer apparatus, and the control unit 200 operates according to various software stored in the nonvolatile storage unit 220b. By doing so, functions specific to the document processing apparatus according to the present invention are realized. As described above, in the present embodiment, the case where the functions specific to the document processing apparatus according to the present invention are realized by the software module has been described. However, the document processing apparatus according to the present invention is realized by the hardware module having these functions. Of course, it may be configured. Specifically, the input means for inputting document image data from the image reading device 120, the storage means for storing the classification dictionary, the extraction means for performing the extraction function, and the generation function. The document processing apparatus according to the present invention is realized by combining the generating means and the specifying means having the specific function with hardware modules, and combining these hardware modules to operate in accordance with the flowchart shown in FIG. May be configured.

(B: Operation)
Next, of the operations performed by the document processing apparatus 110, operations that significantly show the features will be described with reference to the drawings.

  First, when a user sets a paper document in the ADF of the image reading apparatus 120 and performs a predetermined operation (for example, pressing a start button provided in the operation unit of the image reading apparatus 120), each of the paper documents An image corresponding to the page is read by the image reading device 120, and document image data corresponding to the image of each page is sent from the image reading device 120 to the document processing device 110 via the communication line 130.

  On the other hand, when the document image data is input via the communication IF unit 210, the control unit 200 of the document processing apparatus 110 writes and stores the document image data in the volatile storage unit 220a. Then, the control unit 200 applies the category specifying process according to the flowchart shown in FIG. 5 to the document image data stored in the volatile storage unit 220a, and is described in the paper document corresponding to the document image data. The category of the quantity represented by the monetary expression included in the sentence is specified, and the paper document is digitized. Hereinafter, the operation performed by the control unit 200 will be described with reference to FIG.

  FIG. 5 is a flowchart showing the flow of the category specifying process performed by the control unit 200. As shown in FIG. 5, the control unit 200 first analyzes document image data input via the communication IF unit 210 and accumulated in the volatile storage unit 220a, and a document corresponding to the document image data. Among the sentences described in (that is, the document to be classified), sentence data representing a sentence including a monetary expression is extracted (step SA1).

  Next, the control unit 200 performs morphological analysis on the sentence data extracted in step SA1, extracts all nouns included in the sentence represented by the sentence data, and generates a set (step SA2). Then, based on the noun set generated in step SA2 and the classification dictionary described above, the control unit 200 identifies the quantity category represented by the monetary expression included in the sentence (step SA3). Specifically, the control unit 200 identifies correspondence data including a set of nouns having the highest degree of similarity to the noun set generated in step SA2, and the category included in the correspondence data. The category represented by the data is specified as the category of the quantity represented by the monetary expression.

  More specifically, the control unit 200 first identifies the category of the quantity represented by the monetary expression in order from the highest layer according to the hierarchical structure data stored in the non-volatile storage unit 220b. When the hierarchical structure data represents the hierarchical structure shown in FIG. 3, the control unit 200 first uses all the correspondence data stored in the non-volatile storage unit 220b to express the monetary expression. It is specified whether the category of the quantity to be represented is “travel expense”, “purchasing expense”, “loyalty”, “utility expense”, “conference fee”, or “recruitment activity expense”. Note that, as described in the present embodiment, when specifying categories in order from the highest layer, for example, the correspondence data shown in FIG. 4A is lower than the target layer. For the correspondence data for the category of the hierarchy, the control unit 200 replaces the category data included in the correspondence data with the category data of the higher hierarchy according to the hierarchical structure data, and then specifies the category. Use it. For example, since the category data included in the correspondence relationship data shown in FIG. 4A is “transportation expenses”, the category data is replaced with “travel expenses” which is a higher category.

  When the category of the quantity represented by the monetary expression is specified as “travel expenses”, the control unit 200 selects the correspondence data regarding “accommodation expenses” and the “transportation expenses” among the correspondence data. Is used to specify whether the category of the quantity represented by the monetary expression is “accommodation expenses” or “transportation expenses”. In this way, by identifying the quantity category represented by the monetary expression in order from the highest hierarchy, and only referring to the correspondence data for the category belonging to the specified hierarchy, unnecessary correspondence data is obtained. The reference accuracy is eliminated, and the specific accuracy is improved.

  Thereafter, the control unit 200 writes the category data representing the category specified by the category specifying operation and the document image data in association with each other and writes them in the nonvolatile storage unit 220b, and digitizes the paper document corresponding to the document image data Exit. The category data associated with the document image data in this way is used as a search tag when searching for the document image data. If there are multiple sentences including monetary expressions in the paper document to be digitized, specify the category represented by the monetary expression for each monetary expression included in each sentence, and specify all the identification results. Of course, it may be written in the nonvolatile storage unit 220b in association with the document image data.

  As described above, according to the document processing apparatus 110 according to the present embodiment, it is possible to specify in detail the category of the quantity represented by the monetary expression described in the paper document to be digitized. In the present embodiment, the case has been described in which the category of the quantity represented by the monetary expression is specified in order from the highest hierarchy, but the correspondence data stored in the nonvolatile storage unit 220b is used to Of course, only the lowest category may be specified.

(C. deformation)
Although the best mode for carrying out the present invention has been described above, it goes without saying that the following modifications may be made.
(C-1: Modification 1)
In the above-described embodiment, the case where the classification is performed based on the document image data corresponding to the image of the paper document has been described. However, data created by a word processor or the like (data in which character codes and line feed codes of characters described in a document are arranged in the order of description, and control codes representing frame lines, ruled lines, and figures are arranged. Of course, the document to be digitized may be classified based on the code data). In short, any document data corresponding to a paper document may be image data or code data.

(C-2: Modification 2)
In the embodiment described above, the case has been described in which the quantity category represented by the monetary expression described in the document to be digitized is specified in detail. However, for numerical expressions such as length and temperature, it goes without saying that if a classification dictionary corresponding to the numerical expressions is prepared, the category of the quantity represented by the numerical expressions can be specified in detail.

(C-3: Modification 3)
In the embodiment described above, the case has been described in which the quantity category represented by the monetary expression described in the document to be digitized is uniquely specified. However, it is not always possible to uniquely specify the quantity category represented by the numerical expression for all numerical expressions. For example, there may occur a case where a plurality of categories are specified as candidates for the quantity category represented by the numerical expression. In such a case, the plurality of candidates may be presented to the user, and the category selected by the user may be specified as the quantity category represented by the numerical expression.

(C-4: Modification 4)
In the above-described embodiment, the case where the category of the quantity represented by the monetary expression described in the document to be digitized is specified based on the classification dictionary prepared in advance has been described. However, each time a quantity category represented by a numerical expression is specified, a new correspondence data is generated by associating a set of nouns generated by the above generation function for the sentence including the numerical expression with the specified result. The classification dictionary may be updated by updating existing correspondence data based on the set of nouns and the specific result.

  Specifically, when a noun other than the noun included in the correspondence data including the category data specified by the specific function is included in the set of nouns generated by the generation function. The noun may be updated by writing the noun into the correspondence data. In this way, each time a quantity category represented by a numerical expression is newly specified, the contents of the classification dictionary are expanded, and the category specifying accuracy based on the classification dictionary is improved.

(C-5: Modification 5)
In the above-described embodiment, a case has been described in which software for causing the control unit 200 to realize functions unique to the document processing apparatus according to the present invention is stored in advance in the nonvolatile storage unit 220b. However, for example, the software is recorded on a computer-readable recording medium such as a CD-ROM (Compact Disk-Read Only Memory) or a DVD (Digital Versatile Disk), and is generally used with such a recording medium. Of course, the software may be installed in a simple computer device. This produces an effect that a general computer device can function as the document processing device according to the present invention.

1 is a diagram illustrating an example of an overall configuration of a document digitization system having a document processing apparatus 110 according to an embodiment of the present invention. 2 is a diagram illustrating an example of a hardware configuration of the document processing apparatus 110. FIG. It is a figure which shows an example of the hierarchical structure about the category of the quantity which money amount expression represents. It is a figure which shows an example of the correspondence data about money amount expression. It is a flowchart which shows the flow of the category specification process which the control part 200 of the document processing apparatus 110 performs according to paper document digitization software.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 10 ... Document digitization system, 110 ... Document processing apparatus, 120 ... Image reading apparatus, 130 ... Communication line, 200 ... Control part, 210 ... Communication IF part, 220 ... Memory | storage part, 220a ... Volatile memory part, 220b ... Nonvolatile Sex memory part.

Claims (5)

Storage means for storing one or a plurality of nouns and category data representing a category of a quantity, which is a numerical value to which a unit is assigned, in association with each other;
An input means for inputting document data obtained by digitizing a document;
Extracting means for analyzing document data input to the input means and extracting sentence data representing a sentence including a numerical expression that is a character string representing a numerical value assigned with a unit;
Generating means for analyzing the sentence data extracted by the extracting means, extracting nouns included in the sentence represented by the sentence data, and generating a set thereof;
Sentence data extracted by the extraction means for the category represented by the category data stored in the storage means in association with the one or more nouns having the highest degree of similarity with the set generated by the generation means A means for identifying the quantity category represented by the numerical expression included in the sentence represented by
A document processing apparatus. The one or more nouns stored in the storage means in association with the category data are nouns that determine a category of a quantity represented by the numerical expression when a sentence is formed together with the numerical expression. The document processing apparatus according to claim 1. If the set generated by the generating unit includes a noun other than the one or more nouns stored in the storage unit in association with the category data specified by the specifying unit, the noun The document processing apparatus according to claim 1, further comprising a writing unit that writes the information to the storage unit in association with the category data. The storage means represents a hierarchical structure for a quantity category that is a numerical value to which a unit is assigned, and also has written hierarchical structure data that represents one or more categories included in each hierarchy,
The specifying means is:
When specifying the category of the quantity represented by the numerical expression included in the sentence represented by the sentence data extracted by the extraction means, the order is specified in order from the highest hierarchy according to the hierarchy structure represented by the hierarchy structure data. The category of the hierarchy is specified by referring to one or more nouns stored in the storage means in association with the category data representing each of the categories belonging to the hierarchy specifying the category. The document processing apparatus according to claim 1. Computer equipment,
When document data obtained by digitizing a document is input, an extraction unit that analyzes the document data and extracts sentence data representing a sentence including a numerical expression that is a character string representing a numerical value to which a unit is assigned;
Generating means for analyzing the sentence data extracted by the extracting means, extracting nouns included in the sentence represented by the sentence data, and generating a set thereof;
Corresponds to the set having the highest degree of similarity to the set generated by the generating means among the set of nouns stored in the computer device for each category data representing the quantity category that is a numerical value to which the unit is assigned. A program for functioning as a specifying means for specifying the category represented by the category data stored in the computer device as the category of the quantity represented by the numerical expression included in the sentence represented by the sentence data extracted by the extracting means .

Images