JP5962449B2 - Determination program, determination method, and determination apparatus - Google Patents

Description

  The present invention relates to a determination program, a determination method, and a determination apparatus.

  The digitization of paper documents is progressing. For example, in the medical field, the introduction of an electronic medical chart system is progressing. When an electronic medical record system is newly introduced, as an example, the paper document that has been generated in the business before the introduction is scanned, and the paper document is digitized into image data. Electronic documents in which paper documents are digitized in this way may be classified according to indexes such as patient names, document names, and departments so that hospital staff can easily view them on the electronic medical record system. .

  As an example of a technique for supporting the classification of electronic documents, by scanning together with paper documents, index information of paper documents to be scanned, for example, paper on which a barcode representing patient name, document name, and department is printed. Techniques for automating the classification of electronic documents are known.

JP 2009-11874 A JP 2007-87021 A

  However, with the above-described technology, each time a paper document is scanned, a barcode is generated and an extra paper is generated, so that there is a limit to effectively supporting the classification of electronic documents.

  An object of one aspect is to provide a determination program, a determination method, and a determination apparatus that can effectively support classification of electronic documents.

  The determination program according to one aspect reads a display content displayed on each of a plurality of display media, and causes a computer to execute a process of performing a character recognition process on each read display content. Further, the computer performs character recognition processing corresponding to a predetermined position common to each of the first display medium and the second display medium that are not continuously read from among the plurality of display media. When the result is equal to or higher than the first matching rate, a process of determining that the character recognition result corresponding to the predetermined position indicates the same identification information is executed. Further, the computer recognizes a result of character recognition processing corresponding to a predetermined position common to each of the third display medium and the fourth display medium that are sequentially read from the plurality of display media. Is equal to or higher than the second matching rate lower than the first matching rate, a process of determining that the character recognition result corresponding to the predetermined position indicates the same identification information is executed.

  According to an embodiment, classification of electronic documents can be effectively supported.

FIG. 1 is a diagram illustrating the configuration of the electronic medical record system according to the first embodiment. FIG. 2 is a block diagram illustrating a functional configuration of the client terminal according to the first embodiment. FIG. 3 is a diagram illustrating an example of keyword data. FIG. 4 is a diagram illustrating an example of a document management master. FIG. 5 is a diagram illustrating an example of extraction of identification information. FIG. 6 is a flowchart illustrating the procedure of the reading process according to the first embodiment. FIG. 7 is a flowchart illustrating the procedure of the determination process according to the first embodiment. FIG. 8 is a schematic diagram illustrating an example of a computer that executes a determination program according to the first and second embodiments.

  Hereinafter, a determination program, a determination method, and a determination apparatus according to the present application will be described with reference to the accompanying drawings. Note that this embodiment does not limit the disclosed technology. Each embodiment can be appropriately combined within a range in which processing contents are not contradictory.

[System configuration]
FIG. 1 is a diagram illustrating the configuration of the electronic medical record system according to the first embodiment. In the electronic medical chart system 1 shown in FIG. 1, an electronic medical chart service that allows creation, editing, and browsing of an electronic medical chart on the client terminals 30 </ b> A to 30 </ b> C is provided by the server device 10. As described above, in the electronic medical record system 1, the electronic medical record created after the introduction is managed by the server device 10, and the hospital document that has been managing the document, letter, book, etc. on the display medium before the introduction is digitized. The server device 10 is also made to manage the electronic document that has been processed.

  As shown in FIG. 1, the electronic medical chart system 1 accommodates a server device 10 and client terminals 30A, 30B, and 30C. Hereinafter, the terminals of the client terminals 30A to 30C may be collectively referred to as “client terminal 30”. In the example of FIG. 1, three client terminals are illustrated. However, the number of client terminals that can be accommodated in the electronic medical record system 1 is not limited to the illustrated number, and an arbitrary number of client terminals can be accommodated.

  The server device 10 and the client terminal 30 are connected via the network 5 so that they can communicate with each other. As an example of the network 5, any communication network such as the Internet (Internet), LAN (Local Area Network), and VPN (Virtual Private Network) can be adopted regardless of wired or wireless.

  The client terminal 30 is a computer that uses the electronic medical record service. For example, the client terminal 30 is used by hospital personnel who have an account for the electronic medical record system 1, such as doctors and nurses, and lecturers, associate professors, and professors in a university hospital. As an example of the client terminal 30, a mobile terminal such as a smartphone, a mobile phone, a PHS (Personal Handyphone System), or a PDA (Personal Digital Assistants) can be adopted in addition to a fixed terminal such as a personal computer.

  The server device 10 is a computer that provides the electronic medical record service. As an aspect of the server device 10, the server device 10 can be implemented by installing an electronic medical record program that provides an electronic medical record service as package software or online software on a desired computer. For example, the server device 10 may be implemented as a Web server that provides the above electronic medical record service, or may be implemented as a cloud that provides the above electronic medical record service by outsourcing.

  Here, the paper document of the hospital is stored in, for example, a hospital storage or the like (not shown). For example, when the electronic medical record system 1 is not yet introduced, various paper documents such as a letter of introduction received from a patient by a doctor, a medical record in which the contents of examination are filled in, a written consent for examination or surgery, etc. It is put together in a bag and stored in a patient unit. Of these, paper documents such as letters of introduction and consent forms are signed in writing by doctors outside the hospital and patient signatures, so they are once stored in the vault even after the introduction of the electronic medical record system 1. The For this reason, even after the electronic medical record system 1 is introduced, a paper document is generated and a scene for classifying the electronic document occurs. Like the above paper documents, paper documents generated at the time of outpatient examination in the examination room, as well as paper documents generated at the time of hospitalization and examination, are collectively managed in a patient bag.

  The paper document of the hospital stored in the storage is digitized by the client terminal 30, for example. For example, the client terminal 30 sequentially acquires image data of each paper document by causing a scanner to read a plurality of papers. At this time, the scanner generates image data for each display medium by reading the display contents displayed on the respective display media included in the plurality of display media in the order in which the display media are set. After that, the client terminal 30 executes a character recognition process for recognizing a character included in the image data of the paper document as a display medium and converting it into a character code, a so-called OCR (Optical Character Reader) process. By executing the OCR process in this way, text data of characters included in the paper document is obtained. After that, the client terminal 30 extracts an index for classifying the electronic document including the image data and the text data using the character recognition result included in the paper document as a display medium, and then images the image together with the index of each electronic document. Data and text data are uploaded to the server device 10.

  In the present embodiment, the following description will be given on the assumption that electronic documents are classified by patient unit. In this embodiment, the case where the client terminal 30 is caused to generate text data is illustrated, but the server device 10 may be allowed to generate text data. In this embodiment, the case where the image data of the paper document is read by the scanner included in the client terminal 30 is illustrated. However, the server device 10 can generate image data by connecting the scanner to the server device 10. .

[Configuration of Client Terminal 30]
Subsequently, a functional configuration of the client terminal 30 according to the present embodiment will be described. FIG. 2 is a block diagram illustrating a functional configuration of the client terminal 30 according to the first embodiment. As illustrated in FIG. 2, the client terminal 30 includes a scanner 31, a communication I / F (interface) unit 32, a storage unit 33, and a control unit 35. Note that the client terminal 30 may include various functional units included in a known computer, for example, various input / output devices, in addition to the functional units illustrated in FIG.

  The scanner 31 is a reading device that reads the display content displayed on the display medium from the display medium and converts it into image data. As one aspect, the scanner 31 reads reflected light obtained by irradiating light onto a display medium such as paper to be read with a CCD (Charge Coupled Devices) or the like, and converts it into image data of a digital signal. In addition, as an example of the scanner 31, a type that fixes a display medium that is a manuscript and moves the reading device may be adopted, or a type that manually moves the display medium that is a manuscript and moves it. Can also be adopted.

  The communication I / F unit 32 is an interface that performs communication control with other devices, for example, the server device 10 and other client terminals 30. As an aspect of the communication I / F unit 32, a network interface card such as a LAN card can be employed. For example, the communication I / F unit 32 transmits an electronic document including image data and text data to the server device 10 or receives an electronic medical record or electronic document to be viewed from the server device 10.

  The storage unit 33 is a storage device that stores various programs such as an OS (Operating System) executed by the control unit 35 and a determination program described later. As one mode of the storage unit 33, a storage device such as a semiconductor memory element such as a flash memory, a hard disk, and an optical disk can be cited. The storage unit 33 is not limited to the above-mentioned types of storage devices, and may be a RAM (Random Access Memory) or a ROM (Read Only Memory).

  The storage unit 33 stores image data 33a, text data 33b, keyword data 33c, a document management master 33d, and the like as examples of data used for various programs executed by the control unit 35. In addition to the data shown in FIG. 2, other electronic data, for example, the setting of the resolution of the read image in the scanner 31 and the setting of the algorithm for character recognition used for OCR processing can also be stored.

  The image data 33a is image data obtained by digitizing a paper document. As one aspect of the image data 33a, when a plurality of papers are read by the scanner 31, images of each paper document are registered in a predetermined file format. For example, any file format such as TIFF (Tagged Image File Format), JPEG (Joint Photographic Experts Group), GIF (Graphic Interchange Format), or PDF (Portable Document Format) can be adopted as the file format of the image data 33a.

  The text data 33b is data obtained by converting the image data of a paper document into text. The text data 33b is registered for each display medium, that is, for each page unit, after characters included in the image data generated for each paper document by the scanner 31 are converted into text data by OCR processing.

  The keyword data 33c is data in which a keyword for extracting an index for classifying an electronic document is defined. As such a keyword, attribute information positioned in the vicinity of identification information used as an index when browsing an electronic document is defined. As an aspect of the keyword data 33c, data in which items such as a keyword ID (identifier) and a keyword are associated can be employed. FIG. 3 is a diagram illustrating an example of the keyword data 33c. FIG. 3 shows, as an example, various keywords related to attribute information that prompts the patient name to be entered in order to obtain a character string representing the patient name as identification information (attribute value). As shown in FIG. 3, when extracting a character string representing a patient name as identification information, various notations of “patient name”, “patient name”, “ This means that a keyword such as “name” is searched. Here, the case where a character string representing a patient's name is extracted as identification information is illustrated, but when a character string representing a document name or medical department is extracted, similarly, the document name or medical department is entered. Various notations of attribute information for prompting are used as keywords.

  The document management master 33d is master data used for managing an electronic document obtained by digitizing a paper document. As an aspect of the document management master 33d, data in which items such as a record number, an image ID, a text ID, and attribute information are associated can be employed. The “record number” referred to here is an aspect of identification information for identifying a record held by the document management master 33d, and is represented here by, for example, a sequential serial number. “Image ID” indicates identification information for identifying image data, and “Text ID” indicates identification information for identifying text data. “Attribute information” refers to attribute information located in the vicinity of identification information used as an index when browsing an electronic document.

  FIG. 4 is a diagram illustrating an example of the document management master 33d. FIG. 4 illustrates the document management master 33d when five sheets are read by the scanner 31. As shown in FIG. 4, the image ID of the first read paper document is “G001”, the text ID is “T001”, and a predetermined position relative to the keyword shown in FIG. This means that the patient name attribute value “Taro Yoshida” has been extracted from the position on the right. Further, as shown in FIG. 4, the image ID of the second paper document read is “G002”, the text ID is “T002”, and the patient name is displayed from the right side of the keyword shown in FIG. This means that the attribute value “Yoshi x Taro” is extracted. Furthermore, as shown in FIG. 4, the image ID of the third read paper document is “G003”, the text ID is “T003”, and the attribute value “Yoshida” of the patient name from the position on the right side of the keyword. It means that “thick x” is extracted.

  The control unit 35 has an internal memory for storing programs defining various processing procedures and control data, and executes various processes using these. As shown in FIG. 2, the control unit 35 includes a character recognition unit 35a, a determination unit 35b, and an output unit 35c.

  The character recognition unit 35a is a processing unit that executes OCR software. As one aspect, each time the paper document is read by the scanner 31 and image data is generated by the scanner 31, the character recognition unit 35a recognizes the characters included in the image data with respect to the image data of the paper document. Execute OCR processing to convert to code. By executing the OCR process in this way, text data of characters included in a paper document as a display medium can be obtained. Thereafter, the character recognition unit 35a assigns an image ID to the image data and assigns a text ID to the text data. In addition, the character recognition unit 35 a registers image data and text data in the storage unit 33. Although the case where characters included in the image data are converted into a text file has been illustrated here, it may be converted into an HTML file, an XML file, or an RTF (Rich Text Format) file.

  The determination unit 35b is a processing unit that determines whether or not the character recognition result indicates the same identification information by using the character recognition result corresponding to a predetermined position common among the paper documents. As one aspect, every time text data is generated by the character recognition unit 35a, the determination unit 35b searches the text data for a character string that matches the keyword defined in the keyword data 33c. At this time, when a character string that matches the keyword is found, the determination unit 35b determines a character recognition result of the patient name corresponding to a predetermined position, for example, a position to the right of the keyword, from the character string that matches the keyword. To extract. Then, the determination unit 35b registers the character recognition result of the patient name as the attribute value of the attribute information in association with the record number, the image ID, and the text ID of the document management master 33d and registers them in the document management master 33d. Thereafter, the determination unit 35b repeatedly executes the process of extracting the character recognition result of the patient name and registering it in the document management master 33d until all the paper documents are read by the scanner 31.

  FIG. 5 is a diagram illustrating an example of extraction of identification information. FIG. 5 shows a case where the identification information of record number 1 and record number 2 shown in FIG. 4 is extracted. As shown in FIG. 5, when the OCR process is performed on the image data 51A of the paper document, text data 52A is obtained. Thereafter, the keywords “patient name”, “patient name”, “inpatient name” and the like shown in FIG. 3 are searched from the text data 52A. As a result, “patient name” is searched from the text data 52A. In this case, the character recognition result “Taro Yoshida” located on the right side of the keyword “patient name” is extracted. In addition, when the OCR process is performed on the paper document 51B, text data 52B is obtained. Thereafter, the keyword “patient name”, “patient name”, “inpatient name”, etc. shown in FIG. 3 are searched from the text data 52B. As a result, “patient name” is searched from the text data 52B. In this case, the character recognition result “Yoshi × Taro” located on the right side of the keyword “patient name” is extracted. As described above, when the paper document is a horizontally written document, the patient name is often written side by side on the right side or the lower side as viewed from the attribute information that prompts the patient name to be entered. For this reason, there is a high possibility that the character string of the identification information will appear after the right side of the character string corresponding to the keyword after the text is made. Therefore, when the paper document is a horizontally written document, the character recognition result on the right side of the character string corresponding to the keyword is extracted.

  After extracting the character recognition result of the patient name for all the paper documents and registering it in the document management master 33d, the determination unit 35b is included in the text data between the paper documents in a continuously read relationship. It is determined whether the character recognition result on the right side of the keyword indicates the same identification information. At this time, the determination unit 35b calculates the matching rate of the character recognition results between the paper documents that are in a continuously read relationship. For example, the determination unit 35b calculates, as the matching rate, the rate at which the characters constituting the character string match among the character strings constituting the patient's name. In the example of FIG. 5, between the character recognition result “Taro Yoshida” extracted from the text data 52A and the character recognition result “Kichi × Taro” extracted from the text data 52B, “K” "And" Buro "match the three characters. For this reason, the matching rate is calculated as “3 ÷ 4 × 100 = 75%”.

  In addition, the determination unit 35b has the same character recognition result on the right side of the keyword included in the text data between the first display medium and the second display medium that are not continuously read. The second matching rate, which is lower than the first matching rate used to determine that it indicates that is shown, is compared with the previously calculated matching rate. For example, the character recognition result is obtained when the character recognition result on the right side of the keyword cannot be extracted from the text data of the display medium read later among the display media that are continuously read. In some cases, display media to be compared are skipped. In this case, whether or not the character recognition result on the right side of the keyword included in the text data indicates the same identification information between the first display medium and the second display medium that are not continuously read. Is determined. In such a case, the first matching rate is used as a threshold value.

  As described above, the value of the second matching rate is made lower than the first matching rate because the name of the patient between the third display medium and the fourth display medium that are in the continuously read relationship. Are similar, the two display media are related to the same patient than when the patient names are similar between the first display medium and the second display medium that are not continuously read. This is because the possibility of being a paper document is high. This is because a display medium such as a paper document managed in a hospital storage etc. is stored in a patient unit by a wrapping bag, and each display medium may be set in the scanner 31 in a state where each display medium is stacked in a patient unit. Because it is expensive. In the present embodiment, the following description will be given on the assumption that the first matching rate is 90% and the second matching rate is 70%.

  In the example of FIG. 5, the matching rate “75%” between the character recognition result “Taro Yoshida” extracted from the text data 52A and the character recognition result “Kichi × Taro” extracted from the text data 52B is the second. It is more than the matching rate. For this reason, the character recognition result “Taro Yoshida” extracted from the text data 52A and the character recognition result “Kichi × Taro” extracted from the text data 52B are identified as indicating the same identification information. After that, the determination unit 35b recognizes the character recognition result “Taro Yoshida” extracted from the text data 52A of the paper document previously read, and the character recognition extracted from the text data 52B of the paper document read later. Overwrite the result. As a result, the attribute value of the attribute information of record number 2 shown in FIG. 4 is updated to “Taro Yoshida”. Then, even when the matching rate of the character recognition result is calculated between the record number 2 and the record number 3, the recognition result of the three characters “yoshi”, “da”, and “thick” matches, The matching rate “3 ÷ 4 × 100 = 75%” equal to or higher than the matching rate “70%” is calculated. For this reason, the character recognition result “Taro Yoshida” of record number 2 that was read first is overwritten on the character recognition result of record number 3 that was read later. As described above, even when erroneous recognition or the like occurs in character recognition at the position corresponding to the keyword in one display medium among the display media that are continuously read, interpolation is performed based on the character recognition result of the other display medium. Since it can be determined that the same identification information is shown, the electronic document can be effectively classified on a patient basis.

  The output unit 35 c is a processing unit that executes data output control for the server device 10. As one aspect, the output unit 35c includes an electronic document including the image data 33a and the text data 33b stored in the storage unit 33 after the determination process by the determination unit 35b is completed, and a document management stored in the storage unit 33. The master 33d is uploaded to the server device 10. As a result, the server apparatus 10 can classify the electronic documents using the identification information “patient name”, which is the attribute value of the attribute information included in the document management master 33d, as an index.

  The control unit 35 can employ various integrated circuits and electronic circuits. Further, a part of the functional unit included in the control unit 35 may be another integrated circuit or an electronic circuit. For example, an ASIC (Application Specific Integrated Circuit) is an example of the integrated circuit. Examples of the electronic circuit include a central processing unit (CPU) and a micro processing unit (MPU).

[Process flow]
Next, the process flow of the client terminal 30 according to the present embodiment will be described. Here, after (1) reading processing executed by the client terminal 30 is described, (2) determination processing is described.

(1) Reading Process FIG. 6 is a flowchart illustrating the procedure of the reading process according to the first embodiment. This reading process is started when a reading instruction is received via an input device or the like (not shown) with a plurality of sheets set in the scanner 31.

  As shown in FIG. 6, when a paper document as a display medium is read (step S101), the scan 31 generates image data of the paper document (step S102). Subsequently, the character recognition unit 35a generates text data of the paper document by executing an OCR process for recognizing a character included in the image data of the paper document and converting it to a character code (step S103).

  Then, the character recognition unit 35a assigns an image ID to the image data and assigns a text ID to the text data (step S104). Then, the character recognition unit 35a registers image data and text data in the storage unit 33 (step S105).

  Subsequently, the determination unit 35b searches the text data generated in step S103 for a character string that matches the keyword defined in the keyword data 33c (step S106). If no character string matching the keyword is found (No in step S107), the process proceeds to step S110.

  At this time, when a character string that matches the keyword is searched (step S107 Yes), the determination unit 35b executes the following process. That is, the determination unit 35b extracts a character recognition result of a patient name corresponding to a predetermined position, for example, a position on the right side of the keyword, from a character string that matches the keyword (step S108).

  Then, the determination unit 35b associates the character recognition result of the patient name extracted in step S108 with the record number of the document management master 33d, the image ID and text ID numbered in step S104, and associates them with the document management master 33d. It is registered in 33d (step S109).

  After that, until all the paper documents are read by the scanner 31 (No at Step S110), the processes from Step S101 to Step S109 are repeatedly executed. Then, when all the paper documents have been read by the scanner 31 (step S110 Yes), the process ends.

(2) Determination Processing FIG. 7 is a flowchart illustrating a determination processing procedure according to the first embodiment. For example, the determination process is started when the reading process illustrated in FIG. 6 is completed. Note that the above-described determination processing is performed on the record from which the character recognition result is extracted when each character recognition result is extracted from two records in the document management master 33d that are at least continuously read. It is also possible to start and execute the process.

  As shown in FIG. 7, the determination unit 35b initializes a counter N that counts the record number of the document management master 33d to an initial value, for example, zero (step S301). Subsequently, the determination unit 35b increments the record number counter N by one (step S302).

  Then, the determination unit 35b compares the character recognition result of the patient name in the record number N with the character recognition result of the patient name in the record number N + 1, and between the two paper documents that are continuously read. The matching rate of the character recognition result to the right of the keyword included in each text data is calculated (step S303).

  Here, when the matching rate calculated in step S303 is a predetermined threshold, for example, the second matching rate is 70% or more (Yes in step S304), the determination unit 35b executes the following process. . That is, the determination unit 35b sets the character recognition result of the record number N to the character recognition result of the record number N + 1 (Step S305). When the matching rate calculated in step S303 is less than the second matching rate (No in step S304), the process proceeds to step S306 without executing the process in step S305.

  Thereafter, as long as there is a record next to the record number N + 1, that is, a record with the record number N + 2 (Yes in step S306), the processes from step S302 to step S305 are repeated. Then, when there is no record next to the record number N + 1, that is, the record with the record number N + 2 (step S306 No), the process is terminated.

[Effect of Example 1]
As described above, the client terminal 30 according to the present embodiment reads the display content displayed on each of the plurality of display media, and performs character recognition processing on each read display content. The client terminal 30 according to the present embodiment corresponds to a predetermined position common to each of the first display medium and the second display medium that are not continuously read from among the plurality of display media. When the result of the character recognition processing to be performed is equal to or higher than the first matching rate, it is determined that the character recognition result corresponding to the predetermined position indicates the same identification information, and is continuously read from the plurality of display media. When the result of character recognition processing corresponding to a predetermined position common to the third display medium and the fourth display medium having the above relationship is equal to or higher than the second matching rate lower than the first matching rate In addition, it is determined that the character recognition result corresponding to the predetermined position indicates the same identification information.

  For this reason, in the client terminal 30 according to the present embodiment, even when the recognition rate of the character at a predetermined position is reduced in one display medium among the display media that are continuously read, the other display medium It can be determined that the same identification information is shown by interpolation with the character recognition result. Therefore, in the client terminal 30 according to the present embodiment, the character recognition result that is the identification information is visually input to the person concerned at the hospital, or the paper recognition is performed again by reading the paper document again. The trouble of letting it go can be suppressed. Therefore, the client terminal 30 according to the present embodiment can effectively support the classification of electronic documents. For example, when the patient's name is written on a paper document by handwriting, the recognition rate of characters tends to decrease, but the classification of electronic documents is effective even when characters are written on paper documents by handwriting. Can help.

  Although the embodiments related to the disclosed apparatus have been described above, the present invention may be implemented in various different forms other than the above-described embodiments. Therefore, another embodiment included in the present invention will be described below.

[Application example]
In the first embodiment, the case where identification information is identified between two display media in a continuously read relationship is exemplified. However, the number of display media in a continuously read relationship is three. Even in this case, it can be identified that the identification information indicates the same identification information. For example, the client terminal 30 can identify identification information among three display media, that is, a third display medium, a fourth display medium, and a fifth display medium.

  Explaining this, the client terminal 30 is respectively connected between the fourth display medium located in the center of the three display media and the third display medium located in front of the fourth display medium. The matching rate of the result of the character recognition process corresponding to the common predetermined position is calculated. Further, the client terminal 30 matches the rate of the result of character recognition processing corresponding to a predetermined position common to each of the fourth display medium and the fifth display medium located after the fourth display medium. Is calculated. Here, the client terminal 30 determines the matching rate of the result of the character recognition process calculated between the third display medium and the fourth display medium, and between the fourth display medium and the fifth display medium. Even if both of the calculated matching rates of the character recognition processing result are lower than the second matching rate, the third display is performed if the third matching rate is lower than the second matching rate, for example, 50% or more. It can also be determined that the character recognition result corresponding to a predetermined position among the medium, the fourth display medium, and the fifth display medium indicates the same identification information. As a result, even when the recognition rate of the character corresponding to a predetermined position included in the display medium read by being sandwiched between the display media related to the same patient is reduced, the character recognition result of the display medium positioned before and after is interpolated. It can be determined that the same identification information is indicated.

[Scope of application]
In the first embodiment, the case where the electronic document obtained by digitizing the paper document such as the medical chart in the hospital is exemplified. However, when the electronic document read by collecting a plurality of papers is classified, for example, it is accepted at a bank window. The processing executed by the functional units 35a to 35c in the control unit 35 can be similarly applied to the case where electronic documents obtained by digitizing various types of paper slips are classified by customer. In this case, for example, keywords such as “name”, “customer name”, “name”, and “name” can be defined in the keyword data 33c.

[Distribution and integration]
In addition, each component of each illustrated apparatus does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the character recognition unit 35a, the determination unit 35b, or the output unit 35c may be connected as an external device of the client terminal 30 via a network. Further, the functions of the client terminal 30 may be realized by having different devices each having the character recognition unit 35a, the determination unit 35b, or the output unit 35c and connected to each other through a network.

[Judgment program]
The various processes described in the above embodiments can be realized by executing a prepared program on a computer such as a personal computer or a workstation. In the following, an example of a computer that executes a determination program having the same function as that of the above-described embodiment will be described with reference to FIG.

  FIG. 8 is a schematic diagram illustrating an example of a computer that executes a determination program according to the first and second embodiments. As illustrated in FIG. 8, the computer 100 includes an operation unit 110a, a speaker 110b, a camera 110c, a display 120, and a communication unit 130. Further, the computer 100 includes a CPU 150, a ROM 160, an HDD 170, and a RAM 180. These units 110 to 180 are connected via a bus 140.

  As shown in FIG. 8, the HDD 170 stores in advance a determination program 170a that exhibits the same functions as those of the character recognition unit 35a, the determination unit 35b, and the output unit 35c described in the first embodiment. The determination program 170a may be integrated or separated as appropriate, like the respective components of the character recognition unit 35a, determination unit 35b, and output unit 35c shown in FIG. In other words, all data stored in the HDD 170 need not always be stored in the HDD 170, and only data necessary for processing may be stored in the HDD 170.

  Then, the CPU 150 reads the determination program 170 a from the HDD 170 and expands it in the RAM 180. Thereby, as shown in FIG. 8, the determination program 170a functions as a determination process 180a. The determination process 180a expands various data read from the HDD 170 in an area allocated to itself on the RAM 180 as appropriate, and executes various processes based on the expanded data. The determination process 180a includes processes executed by the character recognition unit 35a, the determination unit 35b, and the output unit 35c illustrated in FIG. 2, for example, the processes illustrated in FIGS. In addition, each processing unit virtually realized on the CPU 150 does not always require that all processing units operate on the CPU 150, and only a processing unit necessary for the processing needs to be virtually realized.

  Note that the determination program 170a is not necessarily stored in the HDD 170 or the ROM 160 from the beginning. For example, each program is stored in a “portable physical medium” such as a flexible disk inserted into the computer 100, so-called FD, CD-ROM, DVD disk, magneto-optical disk, or IC card. Then, the computer 100 may acquire and execute each program from these portable physical media. Each program is stored in another computer or server device connected to the computer 100 via a public line, the Internet, a LAN, a WAN, etc., and the computer 100 acquires and executes each program from these. It may be.

DESCRIPTION OF SYMBOLS 1 Electronic medical record system 5 Network 10 Server apparatus 30 Client terminal 31 Scanner 32 Communication I / F part 33 Memory | storage part 33a Image data 33b Text data 33c Keyword data 33d Document management master 35 Control part 35a Character recognition part 35b Judgment part 35c Output part

Claims (4)

Read the display content displayed on each of the multiple display media, perform character recognition processing on each read display content,
Of the plurality of display media, the result of character recognition processing corresponding to a predetermined position common to each of the first display medium and the second display medium that are not continuously read is the first display medium. When the matching rate is equal to or higher than the matching rate, it is determined that the character recognition result corresponding to the predetermined position indicates the same identification information;
Among the plurality of display media, the result of character recognition processing corresponding to a predetermined position common to each of the third display medium and the fourth display medium that are sequentially read is the first match. A character recognition result corresponding to the predetermined position is determined to indicate the same identification information when the second matching ratio is lower than the second matching ratio.
A determination program that causes a computer to execute processing. The fourth display medium is in a relationship that is continuously read with the third display medium and is in a relationship that is continuously read with the fifth display medium,
As a process for determining the identification information of the character recognition result,
The result of character recognition processing corresponding to a predetermined position common to each of the third display medium and the fourth display medium is equal to or higher than a third matching rate lower than the second matching rate, and When the result of character recognition processing corresponding to a predetermined position common to each of the fourth display medium and the fifth display medium is equal to or higher than the third matching rate, the character recognition result corresponding to the predetermined position The determination program according to claim 1, wherein the determination programs indicate that they indicate the same identification information. Computer
Read the display content displayed on each of the multiple display media, perform character recognition processing on each read display content,
Of the plurality of display media, the result of character recognition processing corresponding to a predetermined position common to each of the first display medium and the second display medium that are not continuously read is the first display medium. When the matching rate is equal to or higher than the matching rate, it is determined that the character recognition result corresponding to the predetermined position indicates the same identification information;
Among the plurality of display media, the result of character recognition processing corresponding to a predetermined position common to each of the third display medium and the fourth display medium that are sequentially read is the first match. A character recognition result corresponding to the predetermined position is determined to indicate the same identification information when the second matching ratio is lower than the second matching ratio.
A determination method characterized by executing processing. A character recognition unit that reads display contents displayed on each of a plurality of display media and performs character recognition processing on each of the read display contents;
Of the plurality of display media, the result of character recognition processing corresponding to a predetermined position common to each of the first display medium and the second display medium that are not continuously read is the first display medium. A third display medium that determines that the character recognition result corresponding to the predetermined position indicates the same identification information when the matching rate is equal to or higher than the matching rate, and is in a continuously read relationship among the plurality of display media And the character corresponding to the predetermined position when the result of the character recognition processing corresponding to the predetermined position common to each of the fourth display media is equal to or higher than the second matching rate lower than the first matching rate. And a determination unit that determines that the recognition results indicate the same identification information.

Images