JP2023096460A - Text information extracting system, text information extracting method, and program - Google Patents

Abstract

To provide a text information extracting system, a text information extracting method, and a program capable of improving workability by extracting information.SOLUTION: A server 1 executes the processing to extract item information meeting items from text data of a text file. The server executes the processing to create data after extraction of the contents including the item information after the item information is extracted. Afterward, the server executes the processing to transmit the data after extraction to a terminal 3. The terminal 3 receives the data after extraction transmitted from the server 1 and then creates display information to cause a display unit 36 to display the same, and afterward, executes the processing to cause the display unit 36 to display the created display information. A document in which an extraction position can be recognized is displayed in a display area DA2, and an automatic extraction result is displayed in a display area DA3.SELECTED DRAWING: Figure 1

Description

The present invention relates to a text information extraction system, a text information extraction method, and a program.

Patent Literature 1 below describes that contracts signed between companies or between individuals are stored in a warehouse of a management company to which they are entrusted. The management company creates a management ledger, and manages dates such as the expiration date and the amount of money described in the contract, for example.

Japanese Unexamined Patent Application Publication No. 2021-71860

In the management company described above, it is necessary to input various items such as the date and amount described in the contract into the management ledger, and this work requires a great deal of labor.

SUMMARY OF THE INVENTION The present invention has been made in view of such circumstances, and an object of the present invention is to provide a text information extraction system, a text information extraction method, and a program capable of improving workability by extracting information. do.

To achieve the above object, a text information extraction system according to one aspect of the present invention comprises:
A text information extraction system comprising an information processing device capable of extracting information from text data and one or more terminals connected to the information processing device,
The information processing device includes file receiving means for receiving a transmission file transmitted from the terminal;
Text file determination means for determining whether the transmission file is a text file;
a text file converting means for converting the transmission file into a text file when the text file determining means determines that the transmission file is negative;
An item for extracting item information that matches at least one item from the text data of the text file determined by the text file determination means or converted into the text file by the text file conversion means. information extraction means;
post-extraction data generation means for generating post-extraction data including the item information extracted by the item information extraction means;
post-extraction data transmission means for transmitting the post-extraction data generated by the post-extraction data generation means to the terminal that transmitted the transmission file.

A text information extraction method of one aspect of the present invention is a method corresponding to the text information extraction system of one aspect of the present invention described above.

A program of one aspect of the present invention is a program corresponding to the text information extraction system of one aspect of the present invention described above.

According to the present invention, workability can be improved by extracting information. That is, the present invention is a system comprising an information processing device capable of extracting information from text data and one or more terminals. Extraction can be performed, and thus workability can be improved.

It is a figure showing an example of an outline of this service provided by a text information extraction system concerning one embodiment of the present invention. It is a block diagram which shows an example of the system configuration|structure regarding a text information extraction system. 3 is a block diagram showing an example of the hardware configuration of a server and a terminal in the text information extraction system of FIG. 2; FIG. 3 is a functional block diagram showing an example of a functional configuration of a server in the text information extraction system of FIG. 2; FIG. 3 is a functional block diagram showing an example of a functional configuration of a terminal in the text information extraction system of FIG. 2; FIG. 3 is a flow chart showing an example of a processing operation of a server in the text information extraction system of FIG. 2; 3 is a flowchart showing an example of processing operations of a terminal in the text information extraction system of FIG. 2; It is a figure which shows an example of text data. It is a figure which shows the 1st example of item information. It is a figure which shows the 2nd example of item information. It is a figure which shows the 3rd example of item information. It is a figure which shows the 4th example of item information. It is a figure which shows an example of a file import part. FIG. 10 is a diagram showing an example of displaying a successfully imported document on the display unit; FIG. 10 is a diagram showing an example of displaying display information based on post-extraction data on the display unit (the head portion of the document and the head portion of the extraction result as well). FIG. 10 is a diagram showing an example of display information based on post-extraction data displayed on the display unit (the tail part of the document, the extraction result is the head part); FIG. 10 is a diagram showing an example of displaying display information based on post-extraction data on the display unit (the tail part of the document, the extraction result is the middle part); FIG. 10 is a diagram showing an example of display information based on post-extraction data displayed on the display unit (document trailing portion, extraction result also leading portion).

<Overview of this service>
FIG. 1 is a diagram showing an overview of this service provided by a text information extraction system according to one embodiment of the present invention.

In FIG. 1, this service is provided by a server 1 (information processing device) managed by a service provider (not shown). In this embodiment, for example, a company manages the server 1 . The server 1 is connected to a predetermined network N (see FIG. 2) such as the Internet. A terminal 3 operated by a user 2 is also connected to this network N. FIG.
Note that the number of terminals 3 is not limited to one as shown in the drawing, and a plurality of terminals may be provided. The user 2 may be an individual, an employee of a company, or the like. Alternatively, the user 2 may be an employee of a company that manages the server 1, or the like.

In this service, a document (reference numerals omitted) displayed in the display area DA1 of the display unit 36 on the upper left side of FIG. When the terminal 3 receives the results, the automatic extraction results (reference numerals omitted) can be displayed in the display area DA3 of the display unit 36 as shown in the lower left side of FIG. Documents (reference numerals omitted) on which automatic extraction results are reflected can also be displayed in the display area DA2.

In this service, the document in the display area DA2 (the document reflecting the result of automatic extraction) and the result of automatic extraction in the display area DA3 can be displayed side by side. In this service, the document and the automatic extraction result can be displayed so that the user 2 can easily check them.

This service eliminates the need for the user 2 to manually extract information on various items one by one from the document shown in the upper left of FIG. 1, for example. Therefore, this service can significantly improve the workability compared to the conventional one.

The flow from the document (reference numerals omitted) in the display area DA1 to the document in the display area DA2 and the automatic extraction result in the display area DA3 will be briefly described below.

A part of the document, for example, is displayed in the display area DA1 of the display unit 36 of the terminal 3 operated by the user 2 (the entire document can be viewed by scrolling the screen). A document is here assumed to be a text relating to a contract. Note that the contract is only an example, and other examples will be described later.

If the document displayed in the display area DA1 is divided into blocks and explained in terms of blocks BL1 to BL3, the range (position) of block BL1 shows the contents of the "research and development consignment agreement". . In addition, within the scope of block BL2, "YYYY Co., Ltd. (hereinafter referred to as "Party A") and ZZZZ Co., Ltd. ”). ” is displayed. In addition, in the range of block BL3, there is a display of the content of "(Purpose) Article 1 Party A to Party B...".

The terminal 3 executes a process of generating a file (transmission file) to be transmitted to the server 1 based on the document having the contents as described above. Then, the terminal 3 executes processing for transmitting the generated transmission file to the server 1 .

When there is a transmission file from the terminal 3, the server 1 executes processing for receiving it. It is assumed here that the received file (transmission file) is a text file (if it is not a text file, the server 1 executes processing to convert it into a text file). The server 1 executes a process of extracting item information that matches the items stored in advance in the storage unit from the text data of the text file that is the received file. After the item information is extracted, the server 1 executes processing for generating post-extraction data containing the item information. After that, the server 1 executes a process of transmitting the post-extraction data to the terminal 3 .
The post-extraction data described above is not limited to "data" but may be in various formats such as "file". For example, when generating in the "file" format, "post-extraction data" may be read as "post-extraction file".

When the server 1 transmits the post-extraction data, the terminal 3 executes a process of receiving the data. After receiving the post-extraction data, the terminal 3 executes processing for generating display information to be displayed on the display unit 36 . After that, the terminal 3 executes processing for displaying the display information on the display unit 36 .

When the terminal 3 causes the display unit 36 to display the display information, a document as shown in the lower left side of FIG. 1 is displayed in the display area DA2. Further, the automatic extraction result is displayed in the display area DA3.

As for the portion of the document displayed in the display area DA2, if block BL1 to block BL3 are explained as described above, the range (position) of block BL1 shows the content of the "research and development consignment agreement". This "research and development consignment agreement" is indicated here by a square frame. It should be noted that a square frame encloses the highlight HL1. The "research and development consignment agreement" displayed with the highlight HL1 corresponds to the part automatically extracted. The highlight HL1 is only an example, and another method may be used to identify the extraction point. The highlight HL1 is displayed by drawing a line based on at least the information on the extraction position contained in the post-extraction data and the information on the character length from the extraction position.

In the range of block BL2 in display area DA2, "YYYY Co., Ltd. (hereinafter referred to as "Party A") and ZZZZ Co., Ltd. (hereinafter referred to as "Party B") enter into a research and development contract (hereinafter referred to as (hereinafter referred to as “this Agreement”). ” is displayed. Similarly, in the range of block BL3, there is a display of the contents of "(Purpose) Article 1. Party A is to Party B....". Among these displays, the former "YYYY Co., Ltd." and "ZZZZ Co., Ltd." are displayed with a highlight HL2 and a highlight HL3. Highlights HL2 and HL3 are indicated by square frames like the above-described highlight HL1, and correspond to portions automatically extracted.

Note that the following example may be adopted for the highlights HL1 to HL3. That is, when display information related to "item" or display information related to "item information", which will be described later, is clicked with a mouse, for example, highlights HL1 to HL3 may appear.

As a result of the automatic extraction, in the display area DA3, "・contract title", "research and development consignment contract", "・contractor company name", "YYYY Co., Ltd.", "・contractor company name", "ZZZZ Ltd.” is displayed. Among these, the characters ".contract title", "contractor company name", and "contractor company name" are display information related to "items". In addition, the characters “R&D consignment agreement”, “YYYY Co., Ltd.”, and “ZZZZ Co., Ltd.” are display information related to “item information”.
The characters “R&D consignment agreement”, “YYYY Co., Ltd.”, and “ZZZZ Co., Ltd.” are results of item information automatically extracted from the text data described above by the server 1 . The result of this item information is displayed in the display area DA3 as display information.

It should be noted that, although not shown, the "item" pre-stored in the storage unit of the server 1 includes, for example, "contract date", and the above-mentioned text data also includes characters of "contract date". Then, in the display area DA3, characters of "contract date" are displayed as display information related to "item". Further, in the display area DA3, characters of "contract date" extracted to match the "item" are also displayed as display information related to the "item information".

As for the above-mentioned "contract date", as an example of this service, not only the characters of "contract date" but also numbers representing the date can be displayed. Numerical dates can be extracted if they are included in text data.
If the text data contains, for example, "one year" as the effective period of the contract date, the last date of the effective period is obtained from the above-mentioned date numbers, and this is added to the item It can also be information (even if the text data does not have a valid period of the contract date, it can be obtained from "one year" and provided to the user 2).

As described above with reference to Figure 1, by receiving the provision of this service, it is possible to automatically extract information from items that match the content of the contract in the example of Figure 1. can. According to this service, the user 2 does not have to manually extract information on various items one by one.

In FIG. 1, an example of a contract is given as the type of document (data type), but it is not limited to this. In other words, in addition to the contract, it can include terms and conditions, regulations, rules, and the like. Also included are manuals, technical documents, purchase orders, invoices, receipts, and the like. The type of document (data type) is not particularly limited as long as information matching the "item" described later can be extracted. For example, it is possible to extract information from moving images and sounds by transcribing the sound of moving images or, for example, transcribing the sounds recorded in an IC recorder.

<System Configuration of Text Information Extraction System 100>
FIG. 2 is a block diagram showing an example of a system configuration regarding the text information extraction system 100. As shown in FIG.

The text information extraction system 100 includes a server 1 (information processing device), a network N to which the server 1 is connected, and a plurality of terminals 3 connected to the server 1 via the network N. FIG.
The server 1 is a device that cooperates with the operation of the terminal 3 to execute various processes. A plurality of terminals 3 are devices operated by the user 2 . A plurality of terminals 3 are provided from terminal 3-1 to terminal 3-n (n is an integer equal to or greater than 1).

<Hardware Configuration of Server 1>
FIG. 3 is a block diagram showing the hardware configuration of the server 1 and terminal 3 in the text information extraction system 100 of FIG.

The server 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input/output interface 15, a display section 16 (output section), It comprises an input unit 17 , a storage unit 18 , a communication unit 19 and a drive 20 .

The CPU 11 executes various processes according to programs recorded in the ROM 12 or programs loaded from the storage unit 18 to the RAM 13 .
The RAM 13 also stores data necessary for the CPU 11 to execute various processes.

The CPU 11 , ROM 12 and RAM 13 are interconnected via a bus 14 . An input/output interface 15 is connected to the bus 14 .
A display unit 16 (output unit), an input unit 17 , a storage unit 18 , a communication unit 19 and a drive 20 are connected to the input/output interface 15 .

The display unit 16 (output unit) is configured by a display (screen) and displays various images. The input unit 17 is composed of various hardware and the like, and inputs various information.
The storage unit 18 is configured by a hard disk, a DRAM (Dynamic Random Access Memory), or the like, and stores various data.
The communication unit 19 controls communication with another device (the terminal 3 in the case of FIG. 2) via a predetermined network N. FIG.

A drive 20 is provided as required. A removable medium 21 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory is mounted in the drive 20 as appropriate.
A program read from the removable medium 21 by the drive 20 is installed in the storage section 18 as necessary. In addition, the removable medium 21 can also store various data stored in the storage section 18 in the same manner as the storage section 18 .

With respect to the server 1 and the terminal 3 as described above, it is assumed that various types of processing, which will be described later, are realized through the cooperation of these various types of hardware and various types of software.

<About terminal 3>
In FIG. 3, terminal 3 is an information processing terminal operated by user 2 . The terminal 3 is assumed to be, for example, a personal computer (PC) or a mobile terminal such as a smart phone or a tablet. In the case of a personal computer (PC), it may be either a so-called desktop personal computer or a notebook personal computer.
The hardware configuration of the terminal 3 is basically the same as the hardware configuration of the server 1 described above. That is, it has a CPU 31, a ROM 32, a RAM 33, a bus 34, an input/output interface 35, a display section 36, an input section 37, a storage section 38, a communication section 39, a drive 40, and a removable medium 41. consists of

<Functional Configuration of Server 1>
FIG. 4 is a functional block diagram showing an example of the functional configuration of the server 1 in the text information extraction system 100 of FIG. 2. As shown in FIG.

4, the server 1 includes the CPU 11, the storage unit 18, the communication unit 19, and other functions (not shown in FIG. 4), as described above with reference to FIG. .

The CPU 11 includes an item registration processing unit 111, a file reception processing unit 112 (file reception means), a text file judgment processing unit 113 (text file judgment means), a text file conversion processing unit 114 (text file conversion means), Data type identification processing unit 115 (data type identification means), item selection processing unit 116 (item selection unit), item information extraction processing unit 117 (item information extraction unit), post-extraction data generation processing unit 118 (post-extraction data generation means) and a post-extraction data transmission processing unit 119 (post-extraction data transmission means).

In other words, when the CPU 11 of the server 1 operates, the item registration processing unit 111, the file reception processing unit 112, the text file determination processing unit 113, the text file conversion processing unit 114, and the data A type identification processing unit 115, an item selection processing unit 116, an item information extraction processing unit 117, a post-extraction data generation processing unit 118, and a post-extraction data transmission processing unit 119 function.

The storage unit 18 includes an item storage unit 181, a received file storage unit 182, a text file storage unit 183, an item information storage unit 184, a position/length information storage unit 185, and an extracted data storage unit 186. have.

The item registration processing unit 111 of the CPU 11 executes processing for pre-storing “items” to be extracted when information is extracted in the item storage unit 181 of the storage unit 18 .

The "items" described above are collected so as to correspond to the data type of the file transmitted from the terminal 3 (transmission file). In addition, although not explained here with all examples, they are collected so as to correspond to the data types of files that can be transmitted from the terminal 3 (transmission files).
Specifically, when the data type of the transmission file is contract data, for example, items generally described in the contract are collected in advance as "items" and stored.
Here, for example, "title", "contracting company", "contractor", "contract date", "automatic renewal", "notice of automatic renewal" etc. It shall be. For example, taking "contract date" as an example, if the meaning of "contract date" is the same and the characters are similar, this "contract date" is also stored in advance as an "item".

As will be described later, the CPU 11 (item information extraction processing unit 117) operates so as to extract item information (described later) matching the "item". At that time, for example, when extracting item information that matches "contract date" or "contract date", not only the characters of "contract date" or "contract date" but also the date (for example, "20 XX year XX month XX day”, “20XX/XX/XX”, “20XX.XX.XX”, etc.) can also be extracted.
Regarding notation of dates, for example, there are various notation methods for dates. Specifically, there are various possibilities such as the Japanese calendar, the Western calendar, the end of XX in XX. Here, it is assumed that the values can be normalized. For example, it is assumed that the date can be standardized to "yyyy/mm/dd".

The file reception processing unit 112 executes processing for receiving a transmission file transmitted from the terminal 3 . The file reception processing unit 112 also executes processing for storing the received transmission file in the reception file storage unit 182 .

The text file determination processing unit 113 executes processing for determining whether or not the file (transmission file) received by the file reception processing unit 112 is a text file. If the text file determination processing unit 113 determines that the file is a text file, a process of storing this in the text file storage unit 183 is executed. On the other hand, when it is determined that the file is not a text file (no), the text file processing unit 114 operates.

The text file conversion processing unit 114 converts the received file (transmission file) into a text file (text file conversion) when the text file determination processing unit 113 determines No (determines that the file is not a text file). Execute. The text file conversion processing unit 114 also executes processing for storing the file converted into a text file (text file) in the text file storage unit 183 .

The data type identification processing unit 115 executes processing for identifying the data type of the text data based on the content of part or all of the text data in the text file stored in the text file storage unit 183. do. To explain in a little more detail, the text data is, for example, contract data, clause data, regulation data, regulation data, manual data, technical document data The data type identification processing unit 115 executes processing for identifying data, order form data, invoice data, receipt data, and the like.
By specifying which data type the text data belongs to, items can be automatically switched according to the data type (document type).

The item selection processing unit 116 selects an “item” corresponding to the data type (for example, contract data) specified by the data type specifying processing unit 115 from among items stored in the item storage unit 181 . . Since there are various “items”, the item selection processing unit 116 operates to select from among the “item group” of the item storage unit 181 .

The item information extraction processing unit 117 extracts item information matching at least one item from the text data of the text file stored in the text file storage unit 183 (extracts information). To explain in a little more detail, taking the example of the above contract, from the text data of the contract, "title", "contracting company", "contractor", "contract date", "automatic renewal", The item information extraction processing unit 117 executes a process of extracting item information that matches the "item" such as "notice of automatic update". For example, by extracting information matching the "title", the item information extraction processing unit 117 operates so as to extract item information such as "research and development consignment contract" or "business consignment contract". For extraction, regular expressions and named entity extraction in natural language processing are employed (not particularly limited).
The method of extracting "contracting company" and "contractor" is not particularly limited, but for example, the company (company) first extracted from the text data of the contract is "contracting company", and then The extracted companies should be referred to as "contractors".

The item information extraction processing unit 117 also executes processing for storing the extracted item information in the item information storage unit 184 . In addition, the item information extraction processing unit 117 associates the extracted item information with the information on the extraction position in the text data and the information on the character length from this extraction position with the item information, and then extracts the position/length information. A process of storing in the storage unit 185 is also executed.

The extraction position in the text data described above can be obtained, for example, by setting the first character of the text data to "0" and finding the order in which the item information appears from this first character (an example is (For example, the number of lines in the text data may be determined.). In addition, the character length from the extraction position is obtained by obtaining the number of characters if the item information is, for example, "outsourcing agreement" (this is an example). In this case, the character length from the extraction position is "7".

The post-extraction data generation processing unit 118 executes processing for generating post-extraction data including the above-described item information extracted (information extracted) by the item information extraction processing unit 117 . The post-extraction data generation processing unit 118 also executes processing for storing the generated post-extraction data in the post-extraction data storage unit 186 . It should be noted that the post-extraction data is generated in a text file format or in a format requested by the user 2 (for example, if it is generated in a "file" format, "extraction data" is replaced with "extraction file"). may be read as ).
The post-extraction data generation processing unit 118 determines whether or not the item information extracted (information extracted) by the item information extraction processing unit 117 is consistent information, and determines whether the item information is consistent. When it is determined that the information (described later) is unqualified, a process of generating post-extraction data is executed so that a warning is issued at the terminal 3 (the terminal 3 that has transmitted the transmission file).
Examples of the inconsistent information mentioned above include the following. (1) When the "contract start date" is earlier than the "contract date", a warning is issued at this time. (2) When the date does not exist (for example, "February 29, 2021"), a warning is issued at this time. (3) When the same item information is acquired at a plurality of locations and the acquisition contents are different, a warning is issued at this time. (4) When the "contracting company" can be extracted from, for example, the opening part and the signature field, the company name is different, and a warning is issued at this time.
In the post-extraction data generation processing unit 118, if the information is inconsistent, for example, processing is executed so as to associate predetermined warning information with the item information.

The post-extraction data transmission processing unit 119 executes processing for transmitting the post-extraction data generated by the post-extraction data generation processing unit 118 to the terminal 3 that has transmitted the transmission file.

The item storage unit 181 of the storage unit 18 is a storage area for pre-storing “items” to be extracted when extracting information. The item storage unit 181 stores various “items”. Various "items" are, for example, divided into the above data types and stored as "item groups".

The received file storage unit 182 is a storage area for storing files transmitted and received from the terminal 3 (transmission files).

The text file storage unit 183 is a storage area for storing the above-described received file (transmission file) which is a text file, or for storing the above-described text file (text file).

The item information storage unit 184 is a storage area for storing item information extracted by the item information extraction processing unit 117 . The item information storage unit 184 stores, for example, "research and development consignment contract" and "business consignment contract" as item information in the case of information extraction matching the "item" of "title". Examples of item information will be described later with reference to FIGS. 9 to 12. FIG.

The position/length information storage unit 185 stores, in the extracted item information, information relating to the extraction position in the text data and information relating to the character length from this extraction position in association with the item information. area.

The post-extraction data storage unit 186 is a storage area for storing post-extraction data generated by the post-extraction data generation processing unit 118 .

<Functional Configuration of Terminal 3>
FIG. 5 is a functional block diagram showing an example of the functional configuration of the terminal 3 in the text information extraction system 100 of FIG.

5, the terminal 3 includes a CPU 31, a display unit 36, a storage unit 38, a communication unit 39, and other functions (not shown in FIG. 5), as described above with reference to FIG. configured with.

The CPU 31 includes a transmission file generation processing unit 311, a file transmission processing unit 312, a post-extraction data reception processing unit 313 (post-extraction data reception means), a display information generation processing unit 314 (display information generation means), and an information display. and a processing unit 315 (information display means).

In other words, in the CPU 31 of the terminal 3, when operating, a transmission file generation processing unit 311, a file transmission processing unit 312, a post-extraction data reception processing unit 313, and a display information generation processing unit 314 , and the information display processing unit 315 function.

The storage unit 38 has a transmission file storage unit 381 , an extracted data storage unit 382 , and a display information storage unit 383 .

A transmission file generation processing unit 311 of the CPU 31 executes processing for generating a transmission file to be transmitted to the server 1 . The transmission file generation processing unit 311 also executes processing for storing the generated transmission file in the transmission file storage unit 381 .

The file transmission processing unit 312 executes processing for transmitting the transmission file generated by the transmission file generation processing unit 311 to the server 1 .

The post-extraction data reception processing unit 313 executes processing for receiving the post-extraction data transmitted from the server 1 . The post-extraction data reception processing unit 313 also executes processing for storing the received post-extraction data in the post-extraction data storage unit 382 .

The display information generation processing unit 314 executes processing for generating display information to be displayed on the display unit 36 of the terminal 3 from the received post-extraction data. Further, the display information generation processing unit 314 executes processing for storing the generated display information in the display information storage unit 383 .

Here, the first display information using the information about the extraction position and the information about the character length contained in the post-extraction data and the second display information including the item information are generated, and It is assumed that the display information generation processing unit 314 executes processing for storing the first display information and the second display information in the display information storage unit 383 .
Here, it is assumed that the display information generation processing unit 314 executes a process of issuing a predetermined warning when warning information is associated with item information in the post-extraction data.

The information display processing unit 315 executes processing for displaying the display information generated by the display information generation processing unit 314 on the display unit 36 . Here, it is assumed that the information display processing unit 315 executes the process of displaying the first display information and the second display information on the left and right screens of the display unit 36, for example.

A transmission file storage unit 381 of the storage unit 38 is a storage area for storing transmission files to be transmitted to the server 1 .
The post-extraction data storage unit 382 is a storage area for storing post-extraction data transmitted from the server 1 .
The display information storage unit 383 is a storage area for storing display information (first display information and second display information) generated by the display information generation processing unit 314 .

<Example of processing operation of server 1>
Next, an example of processing operation of the server 1 will be described.
FIG. 6 is a flow chart showing an example of the processing operation of the server 1 in the text information extraction system 100 of FIG.

As an operation of the CPU 11 in the server 1, the file reception processing section 112 (file reception means) receives the transmission file transmitted from the terminal 3 in step S1. When the transmission file reception and the like are completed, the process proceeds to step S2.

In step S2, the text file determination processor 113 (text file determination means) determines whether the received file (the file transmitted from the terminal 3) is a text file or not. If it is determined that the file is not a text file (No in step S2), the process proceeds to step S3. On the other hand, if it is determined that the file is a text file (Yes in step S2), the process proceeds to step S4.

In step S3, since the received file (transmission file from the terminal 3) was determined not to be a text file (no) in step S2, the text file conversion processing unit 114 (text file conversion means) converts it into a text file ( text file). After conversion into the text file, the process proceeds to step S4.

In step S4, the data type identification processor 115 (data type identification means) identifies the data type of the text file. That is, by looking at some or all of the text data in the text file, it is specified that this is contract data, for example. After specifying the data type, the process proceeds to step S5.

In step S5, the item selection processing section 116 (item selection means) selects which "item" corresponds to the specified data type (for example, contract data) in the "item group" of the item storage section 181. to choose from. After completing the selection of the "item", the process proceeds to step S6. It should be noted that the "item" is an extraction target when information is extracted.

In step S6, the item information extraction processing unit 117 (item information extraction means) extracts item information matching the item selected in step S5 from the text data of the text file. To explain in a little more detail, taking the example of the above contract, from the text data of the contract, "title", "contracting company", "contractor", "contract date", "automatic renewal", The item information extraction processing unit 117 extracts item information that matches the "item" such as "notification of automatic update". The extracted item information is associated with information about the extraction position in the text data and information about the character length from this extraction position. After the item information is extracted, the process proceeds to step S7.

In step S7, the post-extraction data generation processing unit 118 (post-extraction data generation means) generates post-extraction data including the extracted (extracted) item information. After generating the post-extraction data, the process proceeds to step S8.
In step S7, it is determined whether or not the extracted item information is consistent information, and in the case of inconsistency, warning information is associated with the item information.

In step S<b>8 , the post-extraction data transmission processing section 119 (post-extraction data transmission means) transmits the generated post-extraction data to the terminal 3 . When the extracted data is transmitted and received by the terminal 3, the terminal 3 operates as described below.

<Example of processing operation of terminal 3>
Next, an example of processing operation of the terminal 3 will be described.
FIG. 7 is a flow chart showing an example of the processing operation of the terminal 3 in the text information extraction system 100 of FIG.

As an operation of the CPU 31 in the terminal 3, the transmission file generation processing unit 311 generates a file (transmission file) to be transmitted to the server 1 in step S21. After generating the transmission file, the process proceeds to step S22.

In step S22, the file transmission processing unit 312 transmits the generated transmission file to the server 1. FIG. After transmitting the transmission file, the process moves to step S23.

In step S23, the post-extraction data reception processing section 313 (post-extraction data receiving means) determines whether or not the post-extraction data transmitted from the server 1 has been received. If it is determined that the post-extraction data has not yet been received (No in step S23), step S23 is repeated again. On the other hand, if it is determined that the post-extraction data has been received (Yes in step S23), the process proceeds to step S24.

In step S24, the display information generation processing unit 314 (display information generation means) generates display information (first display information and second display information) to be displayed on the display unit 36 of the terminal 3 from the received post-extraction data. After generating the display information, the process proceeds to step S25.

In step S25, the information display processing unit 315 (information display means) displays the generated display information on the screen of the display unit 36, for example, on the left and right. The screen display will be described later with reference to FIGS. 15 to 18. FIG.

<Examples of text data TD and item information EX1 to EX10>
FIG. 8 is a diagram showing an example of text data TD.
FIG. 9 is a diagram showing a first example of item information (item information EX1 to EX3). FIG. 10 is a diagram showing a second example of item information (item information EX4 to EX5). FIG. 11 is a diagram showing a third example of item information (item information EX6 to EX8). FIG. 12 is a diagram showing a fourth example of item information (item information EX8 to EX10).

In FIG. 8, the text data TD is displayed on the display unit 16 of the server 1, for example, as follows (the figure shows an example in which the tail part is included). If disclosure is requested by a court or administrative agency based on laws and regulations, rules, court decisions/orders, administrative agency orders/guidance, etc., the party shall disclose the other party's confidential information to the court or administrative agency. However, if any of these events occur, each party shall promptly notify the other party.¥n5.Each party shall not disclose confidential information disclosed by the other party. Confidential Information shall not be used for purposes other than the Contracted Work, and Confidential Information shall not be reproduced or modified for any purpose other than the Contracted Work.\n6. \n7.If either party becomes aware of the occurrence or possible occurrence of a situation such as leakage, loss, theft or misappropriation of confidential information, it shall immediately notify the other party to that effect in writing. ¥n8.Each party shall return to the other party, erase or dispose of confidential information received from the other party in the event of any of the following events.\n8. n (1) When this contract ends¥n (2) When the other party requests a refund¥n¥nArticle 12 (Handling of Personal Information)¥nParty A and Party B shall handle Party B’s personal information It shall be handled in accordance with the information protection regulations.\n\nArticle 13 (Cancellation)\n1. This Agreement may be canceled in whole or in part.\n(1) If any provision of this Agreement is violated and is not corrected despite notice to set a reasonable period of time\n(2) ) Subject to seizure, provisional seizure, provisional disposition, public auction disposition, or other disposition of public authority, bankruptcy, commencement of civil rehabilitation proceedings, commencement of corporate reorganization proceedings, commencement of special liquidation, petition for special mediation, or petition for preservative procedures for these, or ¥n (3) When a self-drawn bill or check is dishonored ¥n (4) When receiving disposition for delinquency of taxes and public dues ¥n (5) If it is judged that serious anxiety has arisen in the state, or if it is judged that it will occur in the future ¥n (6) ◎◎ group, ◎◎ member, ◎◎ Person who has not been a member for less than 5 years, ◎◎Associate members, ◎◎Organization affiliated companies, corporate racketeers, etc., social activist trolls or special intelligence ◎◎Groups, etc., or other similar persons, or included in major shareholders or investors ¥n (7) By yourself or by using a third party, you make a request, an unreasonable request that exceeds legal responsibility, make a threatening statement or conduct a transaction, or disseminate rumors. Or when you commit an act of defamation or obstruction of business by fraudulent means or force, or other illegal act¥n (8) When you damage the reputation, honor, or credibility of the other party, or when you significantly destroy the relationship of trust with the other party ¥n (9) When Party A deems that other serious reasons that make it difficult to continue this Agreement have occurred ¥n2. Notwithstanding the preceding paragraph, Party A may terminate this Agreement at any time by notifying Party B in writing with five business days' notice. \n3. In accordance with the provisions of the preceding two paragraphs, even if Party A or Party B cancels or cancels all or part of this Agreement, it does not prevent the other party from claiming damages. \n4. In the event that this Agreement is terminated pursuant to paragraph 1, the party subject to the termination of the Agreement will of course lose the benefit of time and shall immediately perform all obligations to the other party. \n\nArticle 14 (Compensation for damages)\n1. Party A and Party B may claim damages from the other party in the event of damage due to reasons attributable to the other party in relation to the performance of this Agreement. \n2. The cumulative total of damages related to the performance of this contract shall be limited to the total amount of commission fees actually paid by Party A to Party B under this contract, regardless of default, unjust enrichment, tort or any other cause of claim. and \n3. The preceding paragraph shall not apply if the damage is caused intentionally or by gross negligence of the person obligated to compensate for damages. \n\n\nArticle 15 (Amendment of Agreement)\nWhen Party A and Party B change or amend this Agreement, they shall exchange documents signed and sealed by both Party A and Party B. ¥n¥nArticle 16 (Consultation)¥nIf any doubt arises between Party A and Party B regarding this Agreement, it shall be resolved through discussion between Party A and Party B. \n\nArticle 17 (Exclusive Court of Jurisdiction)\nIn the event of a dispute between Party A and Party B regarding this Agreement, the Tokyo District Court shall be the exclusive jurisdictional court of first instance. \n\nArticle 18 (Governing Law)\nThis Agreement shall be interpreted in accordance with the laws of Japan. \n\nAs a proof of the above contract, two copies of this document will be prepared, and each party will retain one copy after affixing their names and seals. ¥n¥nMay 6, 2021¥n¥nFirst Party:¥n◎◎Tokyo◎Ku◎◎◎1-chome 2-3 3¥n Co., Ltd. YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY… n◎◎City◎◎Ward◎◎◎4-5-6¥nZZZZ Co., Ltd.¥n CEO BB BB¥n¥n” is displayed on the display unit 16 (this is an example).

When the item information (item information EX1 to EX10) matching the "item" is extracted (extracted) from the text data TD as described above, the display section 16 of the server 1 displays, for example, as follows. That is, as shown in FIG. 9, for the item information EX1, "label": "title", "value": "outsourcing contract", "index": 0, "length":7" (which is extracted from the beginning of the text data TD and is not shown here).
These indications can be read as follows. That is, the "item" is "title", and the "service consignment contract" is extracted to match this. , it can be read that it is positioned at the leading "0" and the character length from this extraction position is "7" (the following can also be read in the same way, so the explanation is omitted).

Regarding the item information EX2, "label": "contract origin company", "value": "YYYYYYYYYYY", "index": 10, and "length": 15 are displayed. be.

Regarding the item information EX3, "label": "contractor company", "value": "ZZZZ Corporation", "index": 38, and "length": 8 are displayed. .

Further, as shown in FIG. 10, regarding the item information EX4, ““label”: “auto renew””, ““value”:”, and the fact that A and B will not renew by one month before the period expires. There is no written declaration of intention””, ““index”: 262”, and ““length”: 40” are displayed.

Further, regarding the item information EX5, ““label”: “auto renewal announcement””, ““value”: “one month before expiration”, ““index”: 263”, ““length”: 9”. is displayed.

Further, as shown in FIG. 11, regarding the item information EX6, ““label”: “contract date””, ““value”: “May 6, 2021”, ““index”: 3905”, “ “length”: 9” is displayed.

Regarding the item information EX7, "label": "contract origin company", "value": "YYYYYYYYYYY", "index": 3936, and "length": 15 are displayed. be.

Regarding the item information EX8, "label": "contract origin person", "value": "AA A", "index": 3960, and "length": 4 are displayed. (See also Figure 12).

Further, as shown in FIG. 12, regarding the item information EX9, ““label”: “contractor company”, ““value”: “ZZZZ Corporation”, ““index”: 3988”, ““length” :8” is displayed.

As for the item information EX10, ““label”: “contractor person”, ““value”: “BB BB””, ““index”: 4004”, and ““length”: 5” are displayed.

Post-extraction data is generated including the above item information (for example, item information EX1 to EX10), and is transmitted to the terminal 3. FIG.

<Regarding file import etc. on terminal 3>
FIG. 13 is a diagram showing an example of the file import section 4. As shown in FIG.
An application program necessary for using this service is installed in the terminal 3 in advance, and the file import section 4 is displayed on the display section 36 by the application program.

The file import section 4 is provided with a new creation section 4a for new creation. A template creating unit 4b for creating from a template is also provided. An import unit 4c for importing and taking in files is also provided.

For example, when a document file is dragged and dropped at the position of the import section 4c, characters and numbers are displayed in the display area DA1a of the display section 36 in five blocks (blocks BL1 to BL5) as shown in FIG. is displayed. In FIG. 14, among blocks BL1 to BLn, characters and numbers are displayed in blocks BL1 to BL5. Note that the display area DA1b does not have any display that will be particularly described here (in FIG. 14).

The display in block BL1 is "research and development consignment contract".
In addition, the display in block BL2 is as follows: "YYYYYYYYYYY Co., Ltd. (hereinafter referred to as "Party A") and ZZZZZZZZZ Co., Ltd. (hereinafter referred to as "Party B".) ”). (In FIG. 1, the number of letters "Y" and "Z" is reduced for convenience of drawing space).

In addition, the indications in block BL3 are "(Purpose)" and "Article 1 Party A shall commercialize the manufacture of the product (hereinafter referred to as the "Product") described in Exhibit 1 (omitted) for Party B. For the purpose of this, we entrust Party B with research and development related to the manufacture of this product (hereinafter referred to as "this research and development"), and Party B will be entrusted with this. ”.

In addition, the indications in block BL4 are: "(Commissioned work)", "Article 2. The content of this research and development entrusted to Party B by Party A based on the preceding article shall be as follows.", "(1) Research Title: Research and development of XXX method for the purpose of streamlining sentence creation”, “(2) Research purpose: Developing and commercializing XXX suitable for XXX”, “(3) Research content: XXXXXXXXXXXX”, “(4) Research Person in charge CC CC”, “(5) Expenses required for research 5,000,000 yen”, “(6) Research period May 1, 2021 to April 30, 2022”, “(7) Research Location: Inside Party B's office.

In addition, the indications in block BL5 are "(Payment of consignment fee)", "Article 3 Party A shall pay Party B 5,000,000 yen as a consignment fee for this research and development." ``2. The commission fee specified in the preceding paragraph shall be paid by transferring the following amount to the account designated by Party B at the following time.''

A file (transmission file) to be transmitted to the server 1 is generated from the document file as described above. Thereafter, when the display information (the first display information and the second display information) to be displayed on the display unit 36 of the terminal 3 is generated and displayed, as shown in FIG. become.

<Display information based on extracted data>
FIG. 15 is a diagram showing an example of display information displayed on the display unit 36 based on the data after extraction (the head portion of the document and the head portion of the extraction result as well).

In FIG. 15, in block BL1 shown in display area DA2, "R&D consignment contract" is highlighted (hereafter, highlighting is represented by a square frame, and reference numerals are omitted). That is, it can be seen that the "R&D consignment contract" is automatically extracted.

Also, in block BL2, "YYYYYYYYYYY Co., Ltd." and "ZZZZZZZZ Co., Ltd." are highlighted. That is, it can be seen that "YYYYYYYYYYY Co., Ltd." and "ZZZZZZZZ Co., Ltd." are automatically extracted.

In addition, in block BL3, "to commercialize the manufacture of the product (hereinafter referred to as 'this product') described in Attachment 1 (omitted)" is highlighted. That is, it can be seen that "to commercialize the manufacture of the product described in Attachment 1 (omitted) (hereinafter referred to as "this product")" was automatically extracted.

It can be seen that blocks BL4 and BL5 are not extracted because they are not highlighted.

In a display area DA3 to the right of the display area DA2, the results of automatic extraction are displayed in a predetermined order in the vertical direction of the drawing. Specifically, "contract title" is displayed as an item, and "research and development consignment contract" is displayed as item information.
In addition, "contract purpose" is displayed as an item, and "to commercialize the manufacture of the product (hereinafter referred to as "the product") described in Attachment 1 (omitted)" is displayed as item information.

In addition, "contractor company name" is displayed as an item, and "YYYYYYYYYYY Co., Ltd." is displayed as item information.
In addition, "contract source address" is displayed as an item, and "◎◎ capital ◎ ward ◎◎◎ 1-2-3" is displayed as item information.
In addition, "contract source contractor title name" is displayed as an item, and "representative director" is displayed as item information.
In addition, "contract source contractor name" is displayed as an item, and "AAA" is displayed as item information.

Also, "contracted company name" is displayed as an item, and "ZZZZZZZZ Co., Ltd." is displayed as item information.
Also, "Contractor Address" is displayed as an item, and "◎◎City◎◎Ward◎◎◎4-5-6" is displayed as item information.
In addition, "contractor/contractor position name" is displayed as an item, and "representative director" is displayed as item information.

FIG. 16 is a diagram showing an example of display information based on post-extraction data displayed on the display unit 36 (the tail part of the document, the extraction result is the head part).
When the screen of the display area DA2 is scrolled, a display state as shown in FIG. 16 is obtained.

In block BLn-3 shown in display area DA2, "(contract period)", "Article 31 The effective period of this contract shall be one year from the date of conclusion of this contract. However, two months before the expiration of the contract period , If there is no other manifestation of intention in writing from one party, and if the transaction between Party A and Party B continues, the new period shall be automatically renewed for one year, and the same shall apply thereafter. ", "2. Even if the effective period of this Agreement has expired, the provisions of Articles 7, 14 through 25, this paragraph, and Articles 27 through 33 shall remain applicable even after the termination of this Agreement. shall continue." is displayed, and if there is no separate written declaration of intent from either party at the "date of conclusion of this contract", "one year", or "two months prior to the expiration of the contract period" and the transaction continues between A and B" and "one year" are highlighted. In other words, "the date of conclusion of this contract", "one year", "up to two months before the expiration of the contract period, if there is no separate written declaration of intent from either party, and if the transaction between Party A and Party B continues. It can be seen that "if there is" and "one year" were automatically extracted.

In block BLn-2 shown in display area DA2, "(Governing Law/Agreed Jurisdiction)", "Article 32 This Agreement shall be interpreted in accordance with the laws of Japan", "2. In the event of any dispute regarding the contract, we agree to the exclusive jurisdiction of the Tokyo District Court for the first instance." is displayed, and "Tokyo District Court" is highlighted. That is, it can be seen that "Tokyo District Court" was automatically extracted.

In the block BLn-1 shown in the display area DA2, "(Consultation)", "Article 33 If any doubt arises regarding matters not stipulated in this Agreement or the interpretation of the provisions of this Agreement, we will We will try to resolve it." is displayed. Since there is no highlight display, it can be seen that extraction has not been performed.

In the block BLn shown in the display area DA2, "Two copies of this document have been prepared as a proof of the conclusion of this contract, and both parties A and B will affix their names and seals, and each party will hold one copy.", "May 1, 2021", "Party: ◎◎ Tokyo ◎ Ward ◎◎◎ 1-2-3", "YYYYYYYYYYY Co., Ltd.", "Representative Director AA A", "B: ◎ ◎ Tokyo ◎ Ward ◎◎◎ 4-5-6", "ZZZZZZZZ Co., Ltd.", "Representative Director BB BB" are displayed, and "May 1, 2021", "◎◎ Tokyo ◎ Ward ◎◎◎ 1-2-3", "YYYYYYYYYYY Co., Ltd.", " "Representative Director", "AA A", "◎◎City◎◎Ward◎◎◎4-5-6", and "Representative Director" and "BB BB" are highlighted. That is, "May 1, 2021", "◎◎ Tokyo ◎ Ward ◎◎◎ 1-2-3", "YYYYYYYYYYY Co., Ltd.", "Representative Director" "AAA", "◎◎ Tokyo ◎ Ward ◎ ◎◎4-5-6", "Representative Director" and "BB BB" were automatically extracted.

Note that the display area DA3 to the right of the display area DA2 is in the same state as in FIG. 15 because it is not scrolled. By scrolling, the display state shown in FIG. 17 is obtained.
FIG. 17 is a diagram showing an example of display information based on post-extraction data displayed on the display unit (the tail part of the document, the extraction result being the middle part).

In FIG. 17, by scrolling from the state of FIG. 16, in the display area DA3, "Contractor Contractor Job Title" is displayed as an item, and "Representative Director" is displayed as item information.
Also, "Contractor Contractor Name" is displayed as an item, and "BB BB" is displayed as item information.
Also, "contract date" is displayed as an item, and "April 21, 2021" is displayed as item information.
In addition, "contract period start date" is displayed as an item, and "contract conclusion date" is displayed as item information. In addition, since the "conclusion date of this contract" is "April 21, 2021" which is the "contract date" here, "April 21, 2021" may be displayed as the item information. shall be
Also, "contract term end date" is displayed as an item, and "April 30, 2022" is displayed as item information.
Also, "contract period" is displayed as an item, and "one year" is displayed as item information.
In addition, "Conditions for contract renewal" is displayed as an item, and "Conditions for renewal of contract" is displayed as item information, "If there is no separate written declaration of intent from one party at least two months before the expiration of the contract period, and there is no transaction between Party A and Party B If continuing" is displayed.

By further scrolling from the state of FIG. 17, items and item information as shown in FIG. 18 are displayed in the display area DA3.
FIG. 18 is a diagram showing an example of display information based on post-extraction data displayed on the display unit (the tail part of the document and the head part of the extraction result).

"Renewal contract period" is displayed as an item, and "1 year" is displayed as item information.
In addition, "notification time of automatic update" is displayed as an item, and "-" is displayed as item information. Note that "-" means that there was no corresponding item information, but for example, sample examples may appear by clicking here.
In addition, "contract termination notification time" is displayed as an item, and "two months before expiration of contract period" is displayed as item information. For example, by clicking here, the date may appear. Also, by moving the cursor, the content of the block containing "two months before expiration of the contract period" may be displayed as a pop-up.
Then, "jurisdictional court" is displayed as the last item, and "Tokyo District Court" is displayed as item information.
Although not shown, if item information is associated with warning information, the item information to be warned is displayed in a highlighted state, for example (this is an example, and a warning is issued). shall not be limited if it is known that the Then, when the highlighted item information is clicked, for example, the specific content of the warning is further displayed.

<About effect>
As described above with reference to FIGS. 2 to 18, according to this service, item information is extracted (or information extraction) can be performed automatically. According to this service, it is not necessary for the user 2 to manually extract item information of various items one by one.

<Summary>
An embodiment of the text information extraction system 100 of the present invention has been described above, but the present invention is not limited to this embodiment described above. Moreover, the effects described in the present embodiment are merely a list of the most suitable effects produced by the present invention, and the effects of the present invention are not limited to those described in the present embodiment.

In this embodiment, for example, item information has been extracted for items that match the content of the contract as described above. (Specific examples shall be omitted).

The hardware configuration shown in FIG. 3 is merely an example for achieving the object of the present invention, and is not particularly limited. Also, the functional configurations shown in FIGS. 4 and 5 are merely examples, and are not particularly limited. That is, it is sufficient if the text information extraction system 100 (server 1 or terminal 3) has a function capable of executing the above-described series of processes as a whole. In particular, it shall not be limited to the examples of FIGS.

Also, the locations of the functional blocks are not particularly limited to those shown in FIGS. 4 and 5, and may be arbitrary. For example, the functional blocks of the server 1 may be transferred to the terminal 3 or the like as appropriate. Also, one functional block may be composed of hardware alone, software alone, or a combination thereof.

Also, for example, when a series of processes is executed by software, a program that constitutes the software is installed in a computer or the like from a network or a recording medium. Also, the computer may be a computer built into dedicated hardware.
The computer may be a computer capable of executing various functions by installing various programs, such as the server 1, or may be a general-purpose smart phone or personal computer.

Further, for example, a recording medium containing such a program is not only constituted by a removable medium (not shown) that is distributed separately from the main body of the device in order to provide the program to the user, but also is preinstalled in the main body of the device. It may be composed of a recording medium or the like that is provided to the user in a state in which it is stored.

In this specification, the steps of writing a program recorded on a recording medium are not necessarily processed chronologically according to the order, but may be executed in parallel or individually. It shall also include the processing performed. Further, in this specification, the term "system" means an overall device composed of a plurality of devices, a plurality of means, or the like.

A recording medium containing such a program is not only configured by the removable medium 21 of FIG. It consists of a recording medium, etc. provided to a person.
The removable medium 21 is composed of, for example, a magnetic disk (including a floppy disk), an optical disk, or a magneto-optical disk. Optical discs are composed of, for example, CD-ROMs (Compact Disk-Read Only Memory), DVDs (Digital Versatile Disks), and the like. The magneto-optical disk is composed of an MD (Mini-Disk) or the like.
The recording medium provided to the user 2 in a state of being pre-installed in the apparatus main body includes, for example, the ROM 32 in FIG. 3 in which the program is recorded, the hard disk included in the storage unit 38 in FIG. 3, and the like.

To summarize the above, the text information extraction system to which the present invention is applied is sufficient if it has the following configuration, and can take various embodiments.
That is, a text information extraction system to which the present invention is applied (for example, the text information extraction system 100 in FIG. 2) is
An information processing device (eg, server 1 in FIG. 2) capable of extracting information from text data (eg, text data TD in FIG. 8), and one or more terminals (eg, FIG. 2) connected to the information processing device A text information extraction system comprising a terminal 3) of
The information processing apparatus includes file receiving means (for example, the file reception processing unit 112 in FIG. 4) for receiving a transmission file transmitted from the terminal;
Text file determination means (for example, text file determination processing unit 113 in FIG. 4) for determining whether the transmission file is a text file;
Text file conversion means (for example, the text file conversion processing unit 114 in FIG. 4) that converts the transmission file into a text file when the text file decision means determines the negative;
At least one item (for example, “label” in FIG. 9 : item information extraction means (for example, the item information extraction processing unit 117 in FIG. 4) for extracting the item information (for example, "value": "outsourcing contract" in FIG. 9) that matches the "title");
post-extraction data generation means for generating post-extraction data including the item information extracted by the item information extraction means (for example, post-extraction data generation processing unit 118 in FIG. 4);
post-extraction data transmission means (for example, post-extraction data transmission processing unit 119 in FIG. 4) for transmitting the post-extraction data generated by the post-extraction data generation means to the terminal that transmitted the transmission file; .

According to the present invention, information can be extracted, and workability can be improved. That is, the present invention is a system comprising an information processing device capable of extracting information from text data and one or more terminals. can be extracted. Therefore, workability can be improved.
For example, from the text data TD of FIG. 8, it is possible to extract item information that matches the "title" of FIG. 9, ie, "outsourcing agreement" of FIG. Therefore, it is possible to improve workability compared with the conventional one.

Also, the text information extraction system to which the present invention is applied is
The information processing apparatus includes data type identification means (for example, the data type identification processing unit 115 in FIG. 4) that identifies the data type of the text data based on the content of part or all of the text data. )and,
Item selection means (for example, item in FIG. 4) for selecting the item corresponding to the data type specified by the data type specification means from items stored in an item storage section (for example, item storage section 181 in FIG. 4) A selection processing unit 116) is further provided.

According to the present invention, it is possible to specify which data type the text data belongs to, and by specifying the data type, a suitable item can be selected from among various items. Therefore, it can contribute to the improvement of workability.

Also, the text information extraction system to which the present invention is applied is
Regarding the item information, the post-extraction data generation means includes information on an extraction position in the text data (for example, "index": 0 in FIG. 9) and information on a character length from the extraction position (for example, The post-extraction data is generated after associating with the "length" of 7).

According to the present invention, regarding the item information, since the post-extraction data is generated by linking the information on the extraction position in the text data and the information on the character length from the extraction position, the terminal on the side that receives the post-extraction data can utilize information about the extraction position and information about the character length from the extraction position.

Also, the text information extraction system to which the present invention is applied is
The terminal includes post-extraction data receiving means (for example, post-extraction data reception processing unit 313 in FIG. 5) for receiving the post-extraction data;
display information generating means for generating display information to be displayed on a display unit of the terminal from the extracted data received by the extracted data receiving means (for example, a display information generation processing unit 314 in FIG. 5);
and an information display unit (for example, the information display processing unit 315 in FIG. 5) that causes the display unit to display the display information generated by the display information generation unit.

According to the present invention, the terminal side can generate display information to be displayed on the display section of the terminal from the received post-extraction data, and display this display information on the display section. The user can confirm the extracted items and item information from the display information displayed on the display unit.

Also, the text information extraction system to which the present invention is applied is
The terminal includes post-extraction data receiving means (for example, post-extraction data reception processing unit 313 in FIG. 5) for receiving the post-extraction data;
display information generating means for generating display information to be displayed on a display unit of the terminal from the extracted data received by the extracted data receiving means (for example, a display information generation processing unit 314 in FIG. 5);
Information display means for displaying the display information generated by the display information generation means on the display unit (for example, the information display processing unit 315 in FIG. 5);
The display information generating means generates first display information (for example, information displayed in the display area DA2 in FIG. 15) using the information about the extraction position and the information about the character length, and at least the item information to generate second display information (for example, the information displayed in the display area DA3 in FIG. 15),
The information display means divides and displays the first display information and the second display information generated by the display information generation means on the display section.

According to the present invention, the first display information using the information on the extraction position and the information on the character length and the second display information including the item information can be displayed separately on the display section. Therefore, it is possible to contribute to improvement in ease of confirmation by the user.

Also, the text information extraction system to which the present invention is applied is
The post-extraction data generation means determines whether or not the item information extracted by the item information extraction means is consistent information, and determines whether the item information is not consistent. The post-extraction data is generated so that a warning is issued at the terminal when it is determined to be information.

According to the present invention, the post-extraction data generation means can generate post-extraction data so that a destination terminal can issue a warning if the item information is inconsistent after judging the consistency of the item information. According to the present invention, inconsistency of item information can be checked.

The text information extraction method to which the present invention is applied is
A text information extraction method executed by a text information extraction system comprising an information processing device capable of extracting information from text data and one or more terminals connected to the information processing device,
The information processing device includes a file reception step of receiving a transmission file transmitted from the terminal;
a text file determination step of determining whether the transmission file is a text file;
a text file converting step of converting the transmission file into a text file when the text file determining step determines that the transmission file is negative;
Items for extracting item information that matches at least one item from the text data of the text file determined by the text file determination step or converted into the text file by the text file conversion step. an information extraction step;
a post-extraction data generating step of generating post-extraction data including the item information extracted by the item information extraction step;
and a post-extraction data transmission step of transmitting the post-extraction data generated by the post-extraction data generation step to the terminal that transmitted the transmission file.

According to the present invention, since the text information extraction method is executed by the text information extraction system, workability can be improved.

A program to which the present invention is applied is
A computer that controls a text information extraction system comprising an information processing device capable of extracting information from text data and one or more terminals connected to the information processing device,
The information processing device includes a file reception step of receiving a transmission file transmitted from the terminal;
a text file determination step of determining whether the transmission file is a text file;
a text file converting step of converting the transmission file into a text file when the text file determining step determines that the transmission file is negative;
Items for extracting item information that matches at least one item from the text data of the text file determined by the text file determination step or converted into the text file by the text file conversion step. an information extraction step;
a post-extraction data generating step of generating post-extraction data including the item information extracted by the item information extraction step;
and a post-extraction data transmission step of transmitting the post-extraction data generated in the post-extraction data generation step to the terminal that transmitted the transmission file.

According to the present invention, the computer that controls the text information extraction system is caused to execute the above-described control processing, so that information can be extracted, and workability can be improved.

1... Server 2... User 3... Terminal 4... File import unit 11... CPU
112 File reception processing unit (file reception means)
113 Text file determination processing unit (text file determination means)
114 Text file conversion processing unit (text file conversion means)
115 Data type identification processing unit (data type identification means)
116 Item selection processing unit (item selection means)
117 Item information extraction processing unit (item information extraction means)
118 ... Post-extraction data generation processing unit (post-extraction data generation means)
119 ... post-extraction data transmission processing unit (post-extraction data transmission means)
31 CPU
313 ... Post-extraction data reception processing unit (post-extraction data reception means)
314 Display information generation processing unit (display information generation means)
315... Information display processing unit (information display means)
N: network

Claims (8)

A text information extraction system comprising an information processing device capable of extracting information from text data and one or more terminals connected to the information processing device,
The information processing device includes file receiving means for receiving a transmission file transmitted from the terminal;
Text file determination means for determining whether the transmission file is a text file;
a text file converting means for converting the transmission file into a text file when the text file determining means determines that the transmission file is negative;
An item for extracting item information that matches at least one item from the text data of the text file determined by the text file determination means or converted into the text file by the text file conversion means. information extraction means;
post-extraction data generation means for generating post-extraction data including the item information extracted by the item information extraction means;
and post-extraction data transmission means for transmitting the post-extraction data generated by the post-extraction data generation means to the terminal that transmitted the transmission file. The information processing apparatus includes data type identification means for identifying the data type of the text data based on the contents of part or all of the text data;
an item selection means for selecting the item corresponding to the data type specified by the data type specifying means from among items stored in an item storage unit;
The text information extraction system according to claim 1. The post-extraction data generation means generates the post-extraction data after associating information regarding an extraction position in the text data and information regarding a character length from the extraction position with respect to the item information.
3. A text information extraction system according to claim 1 or 2. The terminal includes post-extraction data receiving means for receiving the post-extraction data;
display information generation means for generating display information to be displayed on a display unit of the terminal from the post-extraction data received by the post-extraction data reception means;
an information display means for displaying the display information generated by the display information generation means on the display unit;
A text information extraction system according to any one of claims 1 to 3. The terminal includes post-extraction data receiving means for receiving the post-extraction data;
display information generation means for generating display information to be displayed on a display unit of the terminal from the post-extraction data received by the post-extraction data reception means;
information display means for displaying the display information generated by the display information generation means on the display unit;
The display information generating means generates first display information using the information about the extraction position and the information about the character length, and generates second display information including at least the item information,
The information display means divides and displays the first display information and the second display information generated by the display information generation means on the display section.
4. The text information extraction system according to claim 3. The post-extraction data generation means determines whether or not the item information extracted by the item information extraction means is consistent information, and determines whether the item information is not consistent. generating the post-extraction data so that a warning is issued on the terminal when it is determined to be information;
A text information extraction system according to any one of claims 1 to 5. A text information extraction method executed by a text information extraction system comprising an information processing device capable of extracting information from text data and one or more terminals connected to the information processing device,
The information processing device includes a file reception step of receiving a transmission file transmitted from the terminal;
a text file determination step of determining whether the transmission file is a text file;
a text file converting step of converting the transmission file into a text file when the text file determining step determines that the transmission file is negative;
Items for extracting item information that matches at least one item from the text data of the text file determined by the text file determination step or converted into the text file by the text file conversion step. an information extraction step;
a post-extraction data generating step of generating post-extraction data including the item information extracted by the item information extraction step;
and a post-extraction data transmission step of transmitting the post-extraction data generated in the post-extraction data generation step to the terminal that transmitted the transmission file. A computer that controls a text information extraction system comprising an information processing device capable of extracting information from text data and one or more terminals connected to the information processing device,
The information processing device includes a file reception step of receiving a transmission file transmitted from the terminal;
a text file determination step of determining whether the transmission file is a text file;
a text file converting step of converting the transmission file into a text file when the text file determining step determines that the transmission file is negative;
Items for extracting item information that matches at least one item from the text data of the text file determined by the text file determination step or converted into the text file by the text file conversion step. an information extraction step;
a post-extraction data generating step of generating post-extraction data including the item information extracted by the item information extraction step;
a post-extraction data transmission step of transmitting the post-extraction data generated in the post-extraction data generation step to the terminal that transmitted the transmission file.

Images