JP6529254B2 - INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, PROGRAM, AND STORAGE MEDIUM - Google Patents

Description

  The disclosed technology relates to an information processing apparatus, an information processing method, a program, and a storage medium.

  IT is rapidly advancing in the medical field centering on electronic medical records. On the other hand, medical information of various paper media still exists in the hospital. Paper medical care information includes, for example, medical care information provision documents, explanatory consent documents, documents necessary for medical treatment such as required documents at admission and discharge, diagnostic documents, and documents for administrative procedures such as order slips, reservation slips, and application forms. is there.

  In an environment where medical information (paper documents) on paper media and electronic information such as electronic medical records are mixed, it is desirable that not only electronic information but also paper documents can be quickly retrieved and used.

  Therefore, in order to ensure readability of the paper document, the paper document is digitized by a scanner, and basic information such as type information indicating the type of paper document, medical department information, patient number is manually registered, and the electronic system A linking workflow is generally implemented. However, since the types of paper documents used in hospitals may be several thousand types or more, and each hospital has its own format, it takes an enormous amount of time to register the above basic information from paper documents. It takes time and effort.

  In Patent Document 1, in order to save labor of registering basic information included in a paper document, a bar code is added to the paper document, and the bar code is read by a bar code reader to read basic information included in the paper document. A method of extracting and registering is disclosed.

  Further, in Patent Document 2, it is disclosed that a character string (name of the issuer of the form) to be extracted from the form is stored, and this character string is collated with the recognition result of the form to recognize the form. There is.

Patent No. 5356905 JP 2001-312694 A

  However, in the method of Patent Document 1, since it is necessary to attach a bar code to a paper document in advance to digitize each sheet of a large number of medical records and medical questionnaires, the operation with human hands is complicated and the load is large. Further, in the method of Patent Document 2, since the entire character string to be extracted and the recognition result of the form are collated, if the collation can not be performed, the entire new character string and the recognition result different from the characters which could not be matched. Since it is necessary to collate as in the past, it takes time to recognize the form.

  The technology disclosed herein has been made in view of such circumstances, and has an object to automatically extract information from paper documents more easily and quickly.

  It is to be noted that the operation and effect are not limited to the above object but are derived from the respective configurations shown in the embodiments for carrying out the invention described later, and it is another object of the present invention to exert the operation and effect not obtained by the prior art. It can be positioned as one.

The information processing apparatus according to the disclosed technology includes a first extracting means for extracting a plurality of regions from the imaged medical document data, a second extraction means for extracting a region including a first character from said plurality of areas And third extraction means for extracting medical department information of the medical document data from the area extracted by the second extraction means, and the first character includes "family" .

  According to the disclosed technology, information can be extracted easily and quickly from an imaged paper document.

It is a figure showing an example of the composition of the information processing system concerning a 1st embodiment. It is a block diagram showing an example of functional composition of an information processor concerning a 1st embodiment. It is a flowchart which shows an example of operation | movement of the information processing apparatus which concerns on 1st Embodiment. It is a flowchart which shows an example of a procedure of the setting process of the candidate area | region in FIG.3 S120 which concerns on 1st Embodiment. It is a flowchart which shows an example of a procedure of an identification process of extraction object in FIG.3 S140 which concerns on 1st Embodiment. It is a schematic diagram which shows an example of the setting process of the candidate area | region in FIG.4 S120 which concerns on 1st Embodiment, and the identification process of extraction object in FIG.6 S140. It is a schematic diagram which shows an example of a knowledge structure which concerns on 1st Embodiment. It is a flowchart which shows an example of the process sequence of the information processing method by the information processing system which concerns on 2nd Embodiment. It is a flowchart which shows an example of a procedure of a correction process of the candidate area | region in FIG.8 S'230 which concerns on 2nd Embodiment. It is a schematic diagram which shows an example of a correction process of the candidate area | region in FIG.8 S'230 which concerns on 2nd Embodiment. It is a flowchart which shows an example of the process sequence of the information processing method by the information processing system which concerns on 3rd Embodiment. It is a flowchart which shows an example of a procedure of narrowing-down processing of the candidate area | region in FIG.11 S240 which concerns on 3rd Embodiment. It is a schematic diagram which shows an example of the narrowing-down process of the candidate area | region in FIG.11 S240 which concerns on 3rd Embodiment. It is a flowchart which shows an example of the process sequence of the information processing method by the information processing system which concerns on 4th Embodiment. It is a flowchart which shows an example of a procedure of extraction processing of the medical department in FIG.3 S140 based on 5th Embodiment. It is a flowchart which shows an example of the process sequence of the information processing method by the information processing system which concerns on 6th Embodiment. It is a schematic diagram which shows an example of the structural presence or absence in extraction object in connection with FIG. 16 concerning 6th Embodiment, and knowledge management of extraction object. It is a flowchart which shows an example of the process sequence of the information processing method by the information processing system which concerns on 7th Embodiment. It is a schematic diagram which shows an example of the information processing of FIG. 17 which concerns on 7th Embodiment. It is a flowchart which shows an example of the procedure of confirmation operation support which identifies the extraction object based on the knowledge in FIG.3 S140 which concerns on 8th Embodiment, and is a transaction control object. It is a schematic diagram which shows an example of the information processing of FIG. 19 which concerns on 8th Embodiment.

  Hereinafter, the information processing apparatus according to the present embodiment will be described in detail with reference to the drawings. However, the components described in this embodiment are merely examples, and the scope of the technology of the present invention is determined by the claims and is limited by the following individual embodiments. Do not mean.

First Embodiment
First, the first embodiment will be described.

  FIG. 1 shows an example of the configuration of the information processing system according to the first embodiment.

  As shown in FIG. 1, the information processing system includes a registration unit 1 (information processing apparatus) and a storage unit 2. The registration unit 1 and the storage unit 2 are communicably connected to each other via a wired or wireless network 6. The registration unit 1 and the storage unit 2 are communicably connected to various systems (electronic medical record system 3, ordering system 4 and other systems 5) in the hospital via the network 6. A plurality of registration units 1 and storage units 2 may be provided.

  The registration unit 1 will be described in detail. The registration unit 1 is an information processing apparatus such as a PC. The registration unit 1 includes a UI device 101, a CPU 102, a RAM 103, a communication IF 104, a UI display unit 105, a program storage area 106, and a data storage area 107.

  The UI device 101 includes at least one of a mouse, a digitizer, and a keyboard, and is used for confirmation, correction, and transmission of registration information by the user.

  The CPU 102 interprets and executes the program read from the program storage area 106 to the RAM 103, thereby enabling various controls, calculations, and UI display in the apparatus. For example, the CPU 102 executes a program to function as a document image analysis unit 110, a candidate area setting unit 120, a candidate area recognition unit 130, an extraction information identification unit 140, and a registration unit 150 as shown in FIG. The CPU 102 and the RAM 103 provided in the registration unit 1 may be one or plural. That is, when at least one or more processing units (CPU) and at least one storage unit (RAM) are connected, and at least one or more processing units execute a program stored in at least one or more storage units. The registration unit 1 functions as each unit described above.

  The document image analysis unit 110 acquires a document image obtained by digitizing a paper document obtained by a scanner (not shown) and analyzes it. Here, digitization by a scanner can be reworded as imaging. That is, the document image corresponds to an example of imaged document data. In addition, the medical document which was imaged is called medical document data. The document image analysis unit 110 may obtain the digitized document image obtained by the scanner directly from the scanner, or the document image analysis when the document image obtained by the scanner is stored in the storage unit 2 The unit 110 may acquire a document image from the storage unit 2.

  The document image analysis unit 110 analyzes the layout of the digitized document image of the paper document, and divides it into a plurality of regions such as a character region and a photo region (region division) to extract a region. That is, the document image analysis unit 110 corresponds to an example of a first extraction unit that extracts a plurality of areas from the document data that has been imaged.

  Note that the document image analysis unit 110 acquires, for each area, the coordinates of each area divided and the attribute information indicating whether each area is a character area or a picture area by area division. Attribute information indicating whether it is a text area or a photo area can be obtained by various known methods. The means for digitizing the paper document is not limited to the scanner, and may be another means.

  The candidate area setting unit 120 sets a candidate area for which information is to be extracted from the area divided by the document analysis unit 110. Specifically, the candidate area setting unit 120 sets a character area as a candidate area. In other words, the candidate area setting unit 120 does not set the photo area as a candidate area among the areas divided by the document analysis unit 110. The process of the candidate area setting unit 120 may be omitted, and the type of document etc. may be identified by using the dictionary described later by the extraction information identification unit 140 without setting the candidate area. Although the time taken to identify the document type and the like is shortened by the process of the candidate area setting unit 120, the above effect can be obtained even if the process of the candidate area setting unit 120 is omitted.

  The candidate area recognition unit 130 acquires character recognition information by performing processing for recognizing the contents of the candidate area set by the candidate area setting unit 120. The character recognition information is the recognition result of the contents of the candidate area.

  The extraction information identification unit 140 identifies an extraction target region from the candidate region based on the recognition result of the candidate region recognition unit 130, and identifies basic information from the description of the identified region. Specifically, the extraction information identification unit 140 identifies an extraction target region from the candidate region using knowledge such as a dictionary created in advance. Then, the extraction information identification unit 140 identifies, for example, the type of the document, using knowledge such as a dictionary created in advance from the identified area. Details of the knowledge such as the dictionary will be described later. The knowledge of the dictionary or the like may be stored in the RAM 103 or may be stored in the data storage area 107. Further, knowledge such as a dictionary may be stored in a ROM (not shown) included in the registration unit 1.

  The registration unit 150 registers (records) the document image in a predetermined storage unit using the information identified by the extraction information identification unit 140. For example, the registration unit 150 associates the type of the paper document identified by the extraction information identification unit 140 with the document image and registers it as the registration information 10 in the data storage area 107 or the like. The registration unit 150 may store the registration information 10 in the storage unit 2.

  Although the CPU 102 functions as each unit illustrated in FIG. 2 in the above example, the present invention is not limited to this, and the FPGA may have at least a part of the above functions. Further, the above functions may be distributed to a plurality of CPUs. Furthermore, the program storage area 106 may be provided inside the registration unit 1 or outside the registration unit 1. The program storage area 106 may be configured by at least one storage device such as a memory, or may be configured by a plurality of storage devices.

  The communication IF 104 is connected to the network 6 and is a communication interface between the registration unit 1, the storage unit 2, and various servers 3 to 5 in the hospital.

  The UI display unit 105 is an LED, a liquid crystal panel, or the like that displays the state of the apparatus, image information, and registration contents.

  Specifically, the program storage area 106 and the data storage area 107 are a hard disk and a flash memory. However, it is not limited to a specific storage medium. In the registration unit 1, the registration information 10 is stored in the data storage area 107. The registration information 10 may be stored in the storage unit 2. The registration information 10 of the registration unit 1 may be directly associated with a system in the hospital (for example, the electronic medical record system 3) and stored.

  Assuming that registration information is stored in the storage unit 2, the storage unit 2 will be described in detail. The storage unit 2 is a storage medium such as at least one or more HDD or SSD, and the storage unit 2 stores a binder pool 20. The binder pool 20 contains binders 201 and 202. Each binder contains a medical document. That is, the storage unit 2 manages the medical document in units of binders. The binder pool 20 may be stored in association with a system in the hospital (for example, the electronic medical record system 3). In the binder pool 20, registration data is stored for each binder according to a predetermined rule so that information can be easily used. As a method of putting together a binder, for example, various materials may be stored for each patient, or each material may be stored for each type. For example, based on the type of paper document identified by the extraction information identification unit 140, the registration unit 150 can store registration information including a document image in the binder for each type.

  With the above-described configuration, it is possible to refer to the registration information in the entire information processing system.

  The network 6 may be an intranet operated in a hospital or an organization, or may be the Internet.

  Since the electronic medical record system / order system is a widely spread and well-known device, the description of the hardware configuration and the operation flow will be omitted.

  Next, an example of the processing procedure of the information processing method by the information processing system according to the present embodiment will be described.

  FIG. 3 is a flowchart illustrating an example of the processing procedure of the information processing method by the information processing apparatus according to the first embodiment.

  First, in step S110, the document image analysis unit 110 obtains a document image obtained by digitizing a paper document obtained by a scanner (not shown). Then, the document image analysis unit 110 analyzes the layout of the digitized document image of the paper document, and divides the region into character regions and photograph regions (region division). As a method of dividing a document image, for example, a known method disclosed in Japanese Patent Application Laid-Open No. 2002-314806 can be used.

  Subsequently, in step S120, the candidate area setting unit 120 sets an area to be an extraction target candidate from the analysis result of the document image. Details of this process will be described later.

  Subsequently, in step S130, the candidate area recognition unit 130 recognizes a character string in the candidate area and records recognition information. The recognition information includes the recognition result of the character string and the number of characters, and the number of lines in the case of a paragraph. In addition, the recognition process can use a well-known character recognition technique.

  Subsequently, in step S140, the extraction information identification unit 140 of the information processing apparatus identifies an extraction target region based on the recognition result of the candidate region and the knowledge information, and identifies basic information from the extraction target region. Then, the registration unit 150 of the information processing apparatus registers the document image based on the identification information. Details of this process will be described later.

  Next, the setting process of the candidate area in step S120 will be described.

  FIG. 4 is a flowchart showing an example of a procedure of setting processing of candidate areas in step S120 of FIG. 3 according to the first embodiment.

  First, in step S 1201, area information acquired by document image analysis by the document image analysis unit 110, that is, coordinate information indicating the position of each area, and attribute information indicating that each area is a character area or a photograph area The analysis unit 110 inputs the candidate area setting unit 120.

  Subsequently, in step S1202, the candidate area setting unit 120 determines whether the area acquired by the document image analysis unit 110 is a character area based on the attribute information. If it is a character area, the candidate area setting unit 120 sets the character area as a candidate area in step S1203.

  Subsequently, in step S1204, the candidate area setting unit 120 determines whether there is an unprocessed area. If there is still an unprocessed area, the process proceeds to step S1202, and the processing from step S1202 to step S1204 is repeated and executed. However, if there is no unprocessed area, the candidate area setting process is ended.

  Next, the process of identifying the extraction target in step S140 will be described.

  FIG. 5 is a flowchart showing an example of the procedure of identification processing of the extraction target in step S140 of FIG. 3 according to the first embodiment.

  First, in step S1401, the candidate area setting unit 120 and the candidate area recognition unit 130 input candidate area information to the extraction information identification unit 140. The candidate area information includes the coordinate information of the candidate area obtained by the candidate area setting unit 120 and the character recognition information obtained by the candidate area recognition unit 130.

  Subsequently, in steps S1402 to S1407, the extraction information identification unit 140 identifies the extraction target region based on the character recognition information and the knowledge information of the candidate region, and identifies the contents of the extraction target region. This part will be described in detail.

  First, in step S1402, the extraction information identification unit 140 determines whether the candidate area to be processed has a word tail in the word dictionary (see reference numeral 604 in FIG. 6).

  If the ending is in the candidate area, the extraction information identification unit 140 identifies the candidate area as an extraction area in step S1403. That is, the extraction information identification unit 140 corresponds to an example of a second extraction unit that extracts a region including the first character from a plurality of regions. Further, the ending included in the ending dictionary corresponds to an example of the first character or word. More specifically, the first character is a word ending of a plurality of characters. Further, although the word ending included in the word ending dictionary is one character, it is not limited to this and may be a plurality of characters.

  Then, in step S1404, the extraction information identification unit 140 extracts a term in the term dictionary (see reference numeral 605 in FIG. 6) from the extraction area. Here, the term included in the term dictionary corresponds to an example of information different from the first character. That is, the extraction information identification unit 140 corresponds to an example of a third extraction unit that extracts information different from the region extracted by the second extraction unit or the first character.

  Then, in step S1405, based on the relationship between the term dictionary and the classification dictionary (see reference numeral 606 in FIG. 6), the type of the document is identified by the extracted term, and the extraction target identification process is ended. That is, the extraction information identification unit 140 corresponds to an example of a classification unit that classifies document data using the information extracted by the third extraction unit.

  If the word tail included in the word-end dictionary is not in the candidate area, in step S1406, the extraction information identification unit 140 determines whether there is an unprocessed candidate area. If there is an unprocessed candidate area, the processing from step S1402 to step S1405 is repeatedly performed. If there is no unprocessed candidate area, the extraction information identification unit 140 determines that there is no area corresponding to the type in the candidate area, and determines that there is no type.

  Next, an example of the identification process of the extraction target in the present embodiment will be described in more detail while showing the contents of the dictionary.

  FIG. 6 is a schematic view showing an example of setting processing of candidate areas in step S120 according to the first embodiment, and identification processing of extraction targets in step S140 of FIG.

  Reference numeral 601 denotes an example of the result of analysis of a document image by the document image analysis unit 110. The document image is divided into areas surrounded by a frame, and a text area, a photo area, or other attributes are assigned to each area.

  Reference numeral 602 denotes an example of the setting result of the candidate area obtained by the candidate area setting unit 120 from the analysis result of the document image. Each candidate area is recorded with area numbers and coordinate information in order.

  603 is the result of the identification process of the extraction object from the candidate area.

  In the present embodiment, the inflection dictionary 604, the term dictionary 605, and the classification dictionary 606 used for the identification process of the extraction target are stored in a ROM (not shown). The ending dictionary 604 records common endings included in the type. The term dictionary 605 records terms included in the type. For example, the term dictionary 605 includes the terms "interview" and "question". That is, the term dictionary 605 includes first reference characters and second reference characters which are different from each other, and the ROM (not shown) holding the term dictionary 605 corresponds to an example of the holding means. The classification dictionary 606 records classifications related to types. The above dictionary may be stored in storage means (program storage area 106, data storage area 107, storage unit 2 or the like) other than the ROM. In this case, the storage means corresponds to an example of the holding means.

  Process in the order of candidate areas. Since the character recognition information of the candidate area 01 obtained by the candidate area recognition unit 130 includes the word end of “book” in the 6-end dictionary 04, the extraction information identification unit 140 identifies the candidate area as the extraction target area. .

  Further, the extraction information identification unit 140 determines that the term “explanation” in the term dictionary 605 is included in the extraction target area. Specifically, the extraction information identification unit 140 compares the terms included in the term dictionary 605 with the characters included in the extraction target area, and if the comparison results match, the terms included in the term dictionary 605 are extracted target areas Judged that it was extracted from In the present embodiment, the extraction information identification unit 140 compares the term “inquiry” with the characters included in the extraction target area, and if there is no match, the next term in the term dictionary 605 is compared with the characters included in the extraction target area. I do. That is, the extraction information identification unit 140, which is an example of the third extraction unit, compares the character included in the area extracted by the second extraction unit with the first reference character, and the comparison result matches. Extracts the character matching the first reference character as information, and if the comparison result does not match, the character contained in the area extracted by the second extraction unit is compared with the second reference character Do.

  The extraction information identification unit 140 determines from the term dictionary 605 that the term “description” is associated with the “type number” “02”. Therefore, the extraction information identification unit 140 determines that the type “description / consent form” corresponding to “02” in the classification dictionary 606 is the document type of the extraction target (paper document). Then, the registration unit 150 associates the type “description / consent form” with the document image and records the type in the data storage area 107 or the storage unit 2.

  As described above, the present embodiment sets candidate areas to be extracted based on attribute information of each area in the document image, identifies extraction target areas from the candidate areas based on character recognition information and knowledge information of the candidate areas, and To obtain the type of However, the present invention is not limited to the above embodiment. For example, in the case of extracting medical department information or patient information (patient identification information such as patient ID) from a medical document (paper document), the extraction target The knowledge information should be replaced according to The patient ID is, for example, a number.

  For example, in the case of medical department information extraction, a term dictionary for type extraction may be a medical department dictionary including "family" and the like. Furthermore, the term dictionary may be changed to a dictionary including words such as "child" and "skin". Although the classification dictionary is not an essential component, the classification dictionary may be changed to "Pediatrics", "Dermatology", etc. so that classification can be performed in the medical department similarly. Further, in the present embodiment, knowledge is described in the word of dictionary, but it may be called other than dictionary. When patient information (patient ID and the like) is extracted, a term extraction dictionary for type extraction may be a dictionary including “ID”, “number”, and the like. In this case, characters such as “ID” are often present at the beginning of the region rather than at the end, but in the present embodiment, the term “endword dictionary” is used to simplify the description. In addition, when extracting patient information (patient ID etc.) etc., since it is not necessary to classify, a term dictionary etc. is unnecessary. The details of the medical department information and the method of extracting patient information (patient ID and the like) will be described in a fifth embodiment described later.

  Further, in the present embodiment, the classification is classified into the classification shown in FIG. 6 in order to easily manage the document image in extracting the medical document type, but the invention is not limited to this and may be classified more finely. And may be classified more roughly. The words and the number of words included in each dictionary are not limited to the contents described in FIG. 6 and can be arbitrarily changed.

  Further, in the present embodiment, an end dictionary for type extraction, a term dictionary, and a classification dictionary have been taken as an example, but the names of the dictionaries may be other than the names described in FIG. It may be configured differently. For example, as shown in FIG. 7, the term dictionary may have not only the association of terms and terms with types, but also the association with endings. In this case, if an end is found, it is only necessary to check whether or not a term that can be combined with it is included and extract the term. For example, in step S1402, when the ending of the "101" number "book" is found, in step S1404, instead of extracting all terms included in the term dictionary from the area, the ending "book" of the "101" number Extract only terms that can be combined with. That is, it is only necessary to extract “inquiry”, “explanation” and the like (there is no need to extract “question”), and it is possible to speed up the process. Also, 601, 602, and 603 shown in the example of FIG. 6 may be collected as a dictionary. That is, the form of the dictionary is not limited to the above example, and may be another form.

  Further, in the present embodiment, the dictionary is provided inside the registration unit 1 as an example, but the dictionary may be provided outside the registration unit 1. It may be defined and referenced externally. Further, in the present embodiment, in the document image in which the information corresponding to the type is not found, it is output as no type, but other outputs, for example, the type may be unknown.

  As described above, according to the first embodiment, it is possible to easily and automatically extract information from a paper document. In the above embodiment, since it is not necessary to add additional information such as a barcode to the paper document, it is possible to extract the information such as the document type without taking much time as compared with the prior art. Further, since it is not necessary to add additional information such as a bar code to the paper document, it is possible to easily extract information such as the document type even from a document of unknown format. That is, information such as the document type can be extracted automatically, even if the medical document is not manually attached with information or the format of the medical document is not known in advance.

  Further, in the above embodiment, since the extraction area is identified using the word end dictionary, it is not necessary to check all the areas with the term dictionary, and information such as the document type can be extracted at high speed. . In addition, in the case of extracting from the document image a word that indicates the type itself, such as the “interview sheet,” there is a risk that it takes a lot of time to extract the word that indicates the type. However, according to the present embodiment, since the combination of the ending and the term is used, it is possible to shorten the time for extracting the term indicating the type such as “interview sheet”. Here, in the medical field, the medical department and the type of the document have various names for each hospital, and therefore, it is possible to obtain a remarkable effect by using the present embodiment in the medical field.

  In the above example, the type of the document image is identified in step S1405, but this step is not essential, and the process may be ended in step S1404. In this case, the operator can perform classification with reference to the terms extracted in step S1404.

Second Embodiment
Next, a second embodiment of the present invention will be described.

  In the first embodiment described above, the character area is set as a candidate area to be extracted from the analysis result of the document image. In the second embodiment, the region is merged with the region if the region extraction of the correct chunk can not be performed by the analysis processing of the document image.

  Here, the hardware configuration of the information processing system according to the second embodiment and the functional configuration of the information processing apparatus are the same as those in FIGS.

  Next, an example of the processing procedure of the information processing method according to the present embodiment will be described.

  FIG. 8 is a flowchart illustrating an example of the processing procedure of the information processing method by the information processing system according to the second embodiment.

  First, in step S ′ 210, the document image analysis unit 110 obtains a document image obtained by digitizing a paper document obtained by a scanner (not shown). Then, the document image analysis unit 110 analyzes the digitized document image of the paper document and divides it into a text region and a photo region. This step is similar to step S110.

  Subsequently, in step S'220, the candidate area setting unit 120 sets an area as a candidate for extraction of a character area from the analysis result of the document image. The specific process is the same as step S120.

  Subsequently, in step S ′ 230, the candidate area setting unit 120 corrects the candidate area. Details of this process will be described later.

  Subsequently, in step S ′ 240, the candidate area recognition unit 130 recognizes the character string in the corrected candidate area, and records the recognition information. This step is similar to step S130.

  Subsequently, in step S ′ 250, the extraction information identification unit 140 identifies the extraction target region based on the recognition result of the candidate region after the correction and the knowledge information, and identifies the extraction target content. This step is similar to step S140.

  Next, the correction process of the candidate area in step S ′ 230 will be described.

  FIG. 9 is a flowchart showing an example of the procedure of the correction process of the candidate area in step S ′ 230 of FIG. 8 according to the second embodiment.

  First, in step S ′ 2301, the candidate area set in step S ′ 220 is input.

  Subsequently, in steps S ′ 2302 to S ′ 2306, an area to be merged is selected from the above candidate areas and merged.

  In step S ′ 2302, the candidate area setting unit 120 determines whether an interval between two candidate areas to be processed is equal to or less than a predetermined threshold T 1. That is, the candidate area setting unit 120 compares the interval between two adjacent candidate areas with the threshold T1. Here, the threshold T1 corresponds to an example of a first threshold.

  If the interval between candidate areas is less than or equal to a predetermined threshold value T1, in step S ′ 2303, is the difference between the character sizes in the two candidate areas targeted for further processing by the candidate area setting unit 120 less than or equal to a predetermined threshold value T2? Determine if. Here, the threshold T2 corresponds to an example of a second threshold.

  If the difference in character size in the candidate area is equal to or less than a predetermined threshold T2, the process proceeds to step S'2304. In step S'2304, when a plurality of characters are included in one candidate area to be processed further by the candidate area setting unit 120, it is determined whether the difference between the character spacings thereof is equal to or less than a predetermined threshold T3. To judge. That is, step S'2304 may not be executed when a plurality of characters are not included in one candidate area. Here, the threshold T3 corresponds to an example of a third threshold.

  If the difference between the character spaces in the candidate area is equal to or less than the predetermined threshold value T3, in step S'2305, the two candidate areas are determined to be areas to be merged, and in step S'2306, the candidate area setting unit 120 Merges the two candidate areas and updates the information of the candidate areas. That is, the candidate area setting unit 120 corresponds to an example of area merging means for merging the areas extracted by the first extraction means based on the information on the areas extracted by the first extraction means. In addition, in the present embodiment, the extraction information identification unit 140 corresponding to an example of the second extraction unit extracts an area including the first character or word from the merged area.

  Subsequently, in step S'2307, the candidate area setting unit 120 determines whether there is an uncompared area. If there is still an uncompared region, step S '2302 is entered, and the processing from step S' 2302 to step S '2306 is repeated and executed. If there is no uncompared region, correction processing of the candidate region is ended. Do.

  Next, an example of the correction process of the candidate area in step S ′ 230 will be described.

  FIG. 10 shows a second embodiment of the present invention, and is a schematic view showing an example of correction processing of a candidate area in step S ′ 230 of FIG.

  Reference numeral 10001 denotes an example of setting results of candidate areas in a document image. Since "same", "mean" and "book" are separated, they are extracted as independent areas.

  In the case of type extraction, reference numeral 10002 is an example of the result of correction processing of candidate areas from 10001. The space between character areas from within the candidate area of 10001 is within a certain range T1, and the difference in character size in each area is within a certain range T2, and the difference in space between character strings when there are multiple characters in each area Merge the candidate areas within a certain range T3 as divided areas.

  In this embodiment, the candidate area is corrected based on the characteristics of the extraction target to make it a meaningful area. In the present embodiment, the interval between candidate areas, the difference in character size in candidate areas, and the difference in interval of character strings in candidate areas are used as merging conditions of candidate areas, but other conditions may be set. Good. Also, division processing in the case of over-integration of candidate areas may be taken as an example. In the above embodiment, the interval between candidate areas (that is, the position of the candidate area), the difference in character size in the candidate area, and the difference in the interval between character strings in the candidate area are all used as merging conditions for candidate areas. However, at least one may be used. That is, the information on the area used to merge the areas is information indicating at least one of the position of the area extracted by the first extraction means and the characters included in the area extracted by the first extraction means.

  According to the second embodiment, a meaningful area can be extracted, and the accuracy of the information extraction process can be improved.

Third Embodiment
Next, a third embodiment of the present invention will be described.

  In the second embodiment described above, the area is corrected to a meaningful area according to the analysis result of the document image. In the third embodiment, candidate regions are narrowed based on the characteristics of the extraction target.

  Here, the hardware configuration of the information processing system according to the third embodiment is the same as the hardware configuration of the information processing system according to the first embodiment shown in FIG. The functional configuration of the information processing system according to the third embodiment is the same as the functional configuration of the information processing system according to the first embodiment shown in FIG.

  Next, the processing procedure of the information processing method according to the present embodiment will be described.

  FIG. 11 is a flowchart showing an example of the processing procedure of the information processing method by the information processing system according to the third embodiment of the present invention.

  First, in step S210, the document image analysis unit 110 analyzes the digitized document image of the paper document, and divides it into a text region and a photograph region. The specific process is the same as step S110.

  Subsequently, in step S220, the candidate area setting unit 120 sets an area as a candidate for extraction of a character area from the analysis result of the document image. The specific process is the same as step S120.

  Subsequently, in step S230, the candidate area recognition unit 130 recognizes a character string in the candidate area and records recognition information. The specific process is the same as step S130.

  Subsequently, in step S240, the extraction information identification unit 140 narrows down the candidate region based on the characteristics of the extraction target. Details of this process will be described later.

  Subsequently, in step S250, the extraction information identification unit 140 identifies the extraction target region based on the recognition result of the candidate region and the knowledge information, and identifies the extraction target content. The specific process is the same as step S140.

  Next, the narrowing-down process of the candidate area in step S240 will be described. The narrowing-down process of the candidate area is hereinafter also referred to as filtering process of the candidate area.

  FIG. 12 is a flowchart showing the third embodiment of the present invention, and showing an example of the procedure of narrowing-down processing of candidate areas in step S240 of FIG.

  First, in step S2401, the candidate area setting unit 120 inputs the candidate area set in step S220 to the extraction information identification unit 140.

  Subsequently, in steps S2402 to S2404, the extraction information identification unit 140 narrows down the candidate area. In the case of type extraction, the narrowing-down conditions of candidate areas are utilized by utilizing the characteristics that the type area is likely to be within a certain range from the top of the document image and the type area is unlikely to exist in the document of multiple paragraphs. Set as. Here, the plurality of paragraphs may be two or more paragraphs or three or more paragraphs. Further, "within a certain range" is, for example, within the range of the upper 1/3 of the entire document image. The fixed range may be within the range of the upper half of the entire document image or may be other range. Further, in the case of medical department extraction or patient information extraction, the range of narrowing may be different from that in the case of type extraction. That is, the narrowing-down condition of the candidate area may be changed according to the extraction target. Note that in order to narrow down the candidate area, the above two conditions may be used, or either one may be used. In addition, other conditions such as the position in the horizontal direction of the document image may be added to the above two conditions.

  In step S2402, the extraction information identification unit 140 determines whether the candidate area to be processed is within a predetermined range. If it is within the predetermined range, in step 2403, the extraction information identification unit 140 further determines whether the number of rows of the candidate area is equal to or less than a predetermined threshold T. If it is equal to or less than the predetermined threshold T, in step 2404, the candidate area is left as a candidate area. Here, the threshold T corresponds to an example of a fourth threshold.

  In step 2405, candidate areas outside the predetermined range or candidate areas with the number of lines of characters in the candidate area above the predetermined threshold T are excluded from the candidate areas. This is based on the fact that information indicating the type of document image is normally unlikely to exist in a document of a plurality of lines. As described above, the extraction information identification unit 140 corresponds to an example of a region selection unit that selects a region to be processed by the second extraction unit.

  Subsequently, in step S2406, the extraction information identification unit 140 determines whether there is an unprocessed area. If there is still an unprocessed area, the process proceeds to step S2402, and the processing from step S2402 to step S2405 is repeatedly executed, but if there is no unprocessed area, the filtering process of the candidate area is ended.

  Next, an example of the narrowing-down process of the candidate area in step S240 will be described.

  FIG. 13 is a schematic view showing an example of the narrowing-down process of the candidate area in step S240 of FIG. 11 according to the third embodiment of the present invention.

  Reference numeral 1001 denotes an example of setting results of candidate areas in a certain document image. The area enclosed by the frame is set as a candidate area.

  In the case of type extraction, 1002 is an example of the result of filtering of the candidate area from 1001 on. Only the area surrounded by a frame which has a position within a certain range from the candidate area 1001 and is not a plurality of lines remains. These candidate regions are the target regions of the identification process.

  In the present embodiment, the candidate area is narrowed based on the characteristics of the extraction target, and the extraction target is identified from the remaining candidate areas. In the present embodiment, the condition of filtering of the candidate area is set based on the characteristics of the type information by taking the type extraction as an example, but other conditions may be set. Moreover, when extracting other information, you may set the conditions of filtering according to the characteristic of the said extraction information. In this embodiment, the position of the candidate area (step S2402) and the number of lines of characters in the candidate area (step S2403) are used to narrow down the candidate area, but at least one piece of information may be used. According to the third embodiment, in addition to the effects of the first embodiment, the efficiency of the information extraction process can be improved.

Fourth Embodiment
Next, a fourth embodiment of the present invention will be described.

  In the third embodiment described above, candidate areas are set from analysis results of a document image, candidate areas are filtered according to the characteristics of extraction targets, and extraction targets are identified from the candidate areas to be targets. In the fourth embodiment, in the candidate area to be an object, the order of the extraction object likeness is added, and the extraction object is identified in the order of the extraction object likeness.

  Here, the hardware configuration of the information processing system according to the fourth embodiment is the same as the hardware configuration of the information processing system according to the first embodiment shown in FIG. The functional configuration of the information processing system according to the fourth embodiment is the same as the functional configuration of the information processing system according to the first embodiment shown in FIG.

  Next, the processing procedure of the information processing method according to the present embodiment will be described.

  FIG. 14 is a flowchart showing an example of the processing procedure of the information processing method by the information processing system according to the fourth embodiment of the present invention.

  First, in step S310, the document image analysis unit 110 analyzes the digitized document image of the paper document, and divides the document image into a character area and a photograph area. The specific process is the same as step S110.

  Subsequently, in step S320, the candidate area setting unit 120 sets an area as a candidate for extraction of a character area from the analysis result of the document image. The specific process is the same as step S120.

  Subsequently, in step S330, the candidate area recognition unit 130 recognizes a character string in the candidate area and records recognition information. The specific process is the same as step S130.

  Subsequently, in step S340, the extraction information identification unit 140 narrows down the candidate region based on the characteristics of the extraction target. The specific process is the same as step S240.

  Subsequently, in step S350, the extraction information identification unit 140 calculates the likeness of the extraction target in the candidate region to be processed, and attaches the order of the likeness of the extraction target. That is, priority of processing is given to the candidate area. That is, the extraction information identification unit 140 corresponds to an example of an assigning unit that assigns a priority to the area extracted by the first extraction unit. Details of the process for giving the order of the extraction object likeness will be described later.

  Subsequently, in step S360, the extraction information identification unit 140 identifies the extraction target area in the order of the extraction target likeliness determined in step S350 based on the recognition result of the candidate area and the knowledge information, and identifies the extraction target contents. . The specific process is the same as step S140.

  Next, the calculation processing method of the candidate area extraction target likelihood in step S350 will be described.

The document type area basically corresponds to the area that seems to be the title of the document image. The title is basically located above the document, large in character size, and centered on the center line. However, due to the wide variety of medical document formats, the type area does not necessarily have the above-mentioned characteristics. Here, these characteristics are used to comprehensively obtain the likeness of the candidate area according to the following equation.
Type likeness = w1 * {character size} + w2 * {reciprocal of proximity to center line} + w3 * {reciprocal of the number of areas at the top}
Here, W1, W2, and W3 are weightings of the respective elements. We give high numerical weight to the important elements. Here, “upper part” indicates, for example, the range of the upper one-third of the entire document image, but is not limited thereto. In addition, it is good also as using the value which shows the kind-likeness shown to Formula 1 as at least 1 item among three terms. Also, the position of the candidate area is used to obtain the number of areas at the top. That is, the extraction information identification unit 140, which is an example of the giving unit, gives priority based on at least one of the position of the area extracted by the first extracting unit and the size of the characters included in the area.

  In addition, although the value which shows the classification likeness shown to Formula 1 is calculated | required by three terms, it is good also as calculating classification likeness using four or more items. Also, for example, a region having a large value indicating the type likeness is set as a processing target of the extraction information identification unit 140.

  In the present embodiment, the extraction target likelihood (priority) of the candidate area is calculated, and the extraction target is identified in the extraction target likelihood order. In the present embodiment, the type extraction is taken as an example, and the character size, the position of the area, and the number of areas are used as elements related to the likeness to be extracted, but other characteristics may be used.

  According to the fourth embodiment, in addition to the effects of the first and third embodiments, processing can be performed from candidate areas with high probability of extraction target areas, and the efficiency of extraction processing is further improved. Will be able to

Fifth Embodiment
Next, a fifth embodiment will be described.

  In the first, second, third and fourth embodiments described above, examples of extracting type information from a medical document have been mainly described. In the fifth embodiment, medical department information or patient information is extracted from a medical document.

  Here, the hardware configuration of the information processing system according to the fifth embodiment is the same as the hardware configuration of the information processing system according to the first embodiment shown in FIG. The functional configuration of the information processing system according to the fifth embodiment is the same as the functional configuration of the information processing system according to the first embodiment shown in FIG. Furthermore, since the processing procedure of the information processing method according to the fifth embodiment is the same as step S140 of the information processing method according to the first embodiment shown in FIG. 3, the description of steps S110 to 130 is omitted. Do.

  The classification extraction process basically requires classification of classification according to the contents of the classification area after identification of the classification area, so identification of the classification area according to the ending information, extraction of classification terms in the classification area, and classification identification are performed in three steps. Be done. Since the medical department extraction is basically for extracting the medical department name, it is processed in two steps of identification of the medical department area and extraction of the medical department name in the medical department area. Extraction of patient information is similar to that of medical department extraction.

  Here, the identification processing of the medical department extraction in step S140 of this embodiment will be described.

  FIG. 15 is a flowchart showing the fifth embodiment of the present invention, and showing an example of the procedure of the medical department extraction process in step S140 of FIG.

  First, in step S4401, the candidate area setting unit 120 inputs candidate area information to the extraction information identification unit 140.

  Subsequently, in step S4402, the extraction information identification unit 140 determines whether the candidate area to be processed has a word end in the medical department word end dictionary.

  If there is an end, in step S4403, the extraction information identification unit 140 identifies the candidate area as a medical department area. Then, in step S4404, the extraction information identification unit 140 extracts the term in the medical treatment department term dictionary in the relevant area as a medical department name.

  If there is no ending, it is determined in step S4405 whether there is an unprocessed candidate area. If there is an unprocessed candidate area, the processing from step S4402 to step S4404 is repeatedly executed. If there is no unprocessed candidate area, it is determined that there is no area corresponding to the medical department from the candidate areas, and it is determined that there is no medical department information.

  In the present embodiment, in addition to type extraction, medical department information or patient information is extracted from a document image. The knowledge information may be replaced according to the extraction target.

  According to the fifth embodiment, in addition to the effects of the first, second, and fourth embodiments, extraction of information other than type information is also possible.

Sixth Embodiment
Next, a sixth embodiment will be described.

  In the first, second, third, fourth and fifth embodiments described above, an example in which only one type of information is extracted among the type, medical department, and patient information has been mainly described. In the sixth embodiment, the case of extracting a plurality of pieces of information from a document image will be described.

  Here, the hardware configuration of the information processing system according to the sixth embodiment is the same as the hardware configuration of the information processing system according to the first embodiment shown in FIG. The functional configuration of the information processing system according to the sixth embodiment is the same as the functional configuration of the information processing system according to the first embodiment shown in FIG.

  Next, the processing procedure of the information processing method by the information processing system according to the present embodiment will be described.

  FIG. 16 is a flowchart showing an example of the processing procedure of the information processing method by the information processing system according to the sixth embodiment of the present invention.

  First, in step S510, the document image analysis unit 110 divides the digitized document image of the paper document. The specific process is the same as step S110.

  Subsequently, in step S520, the candidate area setting unit 120 sets a candidate area to be extracted from the result of the area division. The specific process is the same as step S120.

  Subsequently, in step S530, the candidate area recognition unit 130 recognizes the character string in the candidate area and records the recognition information. The specific process is the same as step S130.

  Subsequently, in step S540, the extraction information identification unit 140 determines whether the extraction target has a structural characteristic by referring to the information shown in FIG.

  If it is determined that there is a characteristic, in step S550, the extraction information identification unit 140 narrows the candidate area based on the characteristic of the extraction target. For example, when extracting type information having structural characteristics, the extraction information identification unit 140 narrows down the candidate areas to candidate areas present at the top of the document image. The specific process is the same as step S340. Here, “upper part” indicates, for example, the range of the upper one-third of the entire document image, but is not limited thereto.

  Subsequently, in step S560, the extraction information identification unit 140 switches the knowledge information according to the extraction target based on the information shown in FIG.

  Subsequently, in step S570, the extraction information identification unit 140 identifies an extraction target based on the recognition result of the candidate area and the knowledge information. The specific process is the same as step S140. The operator may input information indicating the extraction target to the registration unit 1 so that the registration unit 1 can grasp the extraction target, or the registration unit 1 automatically switches the extraction target in a predetermined order. Thus, the registration unit 1 may grasp the extraction target.

  Next, an example of presence / absence of structural characteristics of the extraction target and knowledge management of the extraction target will be described.

  FIG. 17 shows a sixth embodiment of the present invention, and is a schematic view showing an example of presence or absence of structural characteristics of an extraction target and knowledge management of the extraction target concerning FIG.

  Reference numeral 1401 denotes a management table for the presence or absence of structural characteristics of the extraction target. The extraction target records whether or not there is a structural characteristic. Since the type information is basically at the top of the document image, it is assumed that there is a structural characteristic. Since medical department information and patient information may be described anywhere in the document image, there is no structural feature.

  Reference numeral 1402 denotes a knowledge management table to be extracted, which manages knowledge necessary for extracting the extraction target. For classification extraction, an end dictionary 1 for classification extraction, a term dictionary 1, and a classification dictionary 1 necessary for classification are used. The term dictionary 2 and term dictionary 2 for medical department extraction are used for medical department extraction. The ending dictionary 3 for patient information extraction is used for patient information extraction.

  In the present embodiment, when extracting a plurality of pieces of information, the knowledge information used for the setting process of the candidate area by the structure information and the identification process of the extraction target is switched according to the extraction target information. Further, in the present embodiment, when the extraction target has a characteristic on the structure, the narrowing-down processing of the candidate area is performed based on the structural characteristic of the extraction target, but the extraction target likeness is further It may be calculated and ranked. Further, in the present embodiment, knowledge of a plurality of pieces of extraction information is separately managed, but knowledge may be collectively managed.

  According to the sixth embodiment, in addition to the effects of the first, second, third and fifth embodiments, in the case of extracting a plurality of pieces of information, it is possible to realize the efficiency of the information extraction considering the characteristics of the information become.

  In the first, second, third, fourth, fifth and sixth embodiments described above, the character area is set as a candidate area to be extracted from the analysis result of the document image. However, not only the character area but also other attribute areas may be widely set as candidate areas to be extracted within a predetermined range. In the first, second, third, fourth and sixth embodiments described above, the extraction target area is identified based on the character recognition and knowledge of the candidate area, and the extraction information is identified. The character recognition result of the candidate area may be corrected, and the extraction target may be identified based on the correction information and the knowledge.

Seventh Embodiment
Next, a seventh embodiment will be described.

  In the first, second, third, fourth, fifth and sixth embodiments described above, the information to be extracted is extracted by analyzing the document image. In the seventh embodiment, both medical information and document images stored in a hospital system (for example, an electronic medical record system) are analyzed to extract information.

  Here, the hardware configuration of the information processing system according to the seventh embodiment is the same as the hardware configuration of the information processing system according to the first embodiment shown in FIG. The functional configuration of the information processing system according to the seventh embodiment is the same as the functional configuration of the information processing system according to the first embodiment shown in FIG.

  Next, the processing procedure of the information processing method by the information processing system according to the present embodiment will be described.

  FIG. 18 is a flowchart showing an example of the processing procedure of the information processing method by the information processing system according to the seventh embodiment of the present invention.

  First, in step S610, the extraction information identification unit 140 extracts a patient number from the document image. The patient number extraction process can use the fifth embodiment.

  Subsequently, in step S620, the extraction information identification unit 140 extracts the relevant information of the patient from the electronic medical record system. Relevant information shall be relevant to classification. Details of the related information will be described later.

  Subsequently, in step S630, the extraction information identification unit 140 confirms whether there is related information of type classification. If there is related information, in step S640, the type classification is narrowed down using the related information. If there is no relevant information, step S650 is entered.

  Subsequently, in step S650, the type is identified from the type classification. The type extraction process can use any one of the first, second and fourth embodiments.

  Next, an example of information processing by the information processing system according to the present embodiment will be described.

  FIG. 19 is a schematic view showing the seventh embodiment of the present invention and showing an example of the information processing of FIG.

  Reference numeral 1601 is an example of description of structure information of medical care information in the electronic medical record system. Basic information includes patient information, examination date, and first visit or reexamination. Moreover, S (main complaint) O (finding) A (examination) P (plan) is included as medical treatment information.

  Reference numeral 1602 denotes an example of related information related to type classification included in medical care information of an electronic medical record. The basic information includes, for example, terms such as a first visit or a revisit. Further, among the medical care information, for example, terms such as scheduled surgery or hospitalization treatment may be mentioned.

  Reference numeral 1603 denotes a classification dictionary originally used for the type extraction process.

  In the processing example of extracting terms relating to type classification from basic information and narrowing down type classification candidates, first, related information of “first visit” is extracted from 1601. In the case of "first visit", the document image has no possibility of the type such as a written consent or a record / report, so it is excluded from the type candidates. Then, the type is determined from the type numbers “01” and “10” that can be associated with the “first visit” and classified.

  Further, when extracting a term relating to type classification from medical care information, the type of document image is identified from the type classification of the range corresponding to the extracted related term in the same manner as described above.

  In the present embodiment, contents related to the extracted information are taken out from the electronic medical record system, and the extracted information candidates are narrowed down. In the present embodiment, the use of the electronic medical record system is taken as an example, but it may be linked with other related systems. Further, in the present embodiment, the information related to type extraction has been described as an example, but other related information may be set. Further, in the present embodiment, the type extraction has been described as an example, but medical department extraction or other information extraction may be performed. Furthermore, in the present embodiment, classification classification candidates are narrowed down based on the related information, and the classification is identified from the possible classifications. However, as in the first, second, third, fourth, and fifth embodiments, the classification method may be identified first, and the extraction result may be confirmed by the classification classified from related information. Good.

  According to the seventh embodiment, in addition to the effects of the first, second, third, fourth and sixth embodiments, it is possible to realize an information extraction mechanism in cooperation with a related system.

Eighth Embodiment
Next, an eighth embodiment will be described.

  In the first, second, third, fourth, fifth, sixth and seventh embodiments described above, type information etc. is automatically extracted for medical non-fixed form documents. . The eighth embodiment relates to information extraction in an atypical document in the general field.

  For example, in the case of a bank, capturing of documents and data related to operations such as opening an account, lending, and mortgage is basically performed manually. For example, in the case of US dollar denominated foreign remittances, it is very time-consuming to check whether the related parties of the transaction include prohibited trading countries or problematic corporations / individuals, etc. according to the US OFAC regulations. Support for business efficiency.

  Here, in order to improve the work efficiency, necessary information is automatically extracted from documents having various formats, and the documents are classified as an eighth embodiment. The hardware configuration of the information processing system according to the eighth embodiment is the same as the hardware configuration of the information processing system according to the first embodiment shown in FIG. The functional configuration of the information processing system according to the eighth embodiment is the same as the functional configuration of the information processing system according to the first embodiment shown in FIG. Also, the hardware configuration of the information processing system according to the third embodiment is the same as the hardware configuration of the information processing system according to the first embodiment shown in FIG. In addition, since the processing procedure of the information processing method according to the eighth embodiment is the same as step S140 of the information processing method according to the first embodiment shown in FIG. 3, the description of steps S110 to 130 is omitted. Do.

  Next, identification processing of an extraction target based on knowledge in step S140 will be described.

  FIG. 20 is a flow chart showing an eighth embodiment of the present invention, identifying an extraction target based on the knowledge in step S140 of FIG. .

  First, in step S7401, the candidate area setting unit 120 inputs candidate area information to the extraction information identification unit 140.

  Subsequently, in steps S7402 to S7406, the extraction information identification unit 140 checks whether or not the contents of the basic extraction item are applicable, and determines the transaction regulation target. The details will be described below.

  In step S7402, the extraction information identification unit 140 takes out the basic extraction item n. Then, in step S7403, the content m corresponding to the basic extraction item n is extracted.

  Then, in step S7404, it is checked whether there is any candidate information that corresponds to the content m of the basic extraction item n. If there is any that corresponds to the content m of the basic extraction item n, it is determined that the document needs to be further examined, and the processing of step S7407 is entered. If there is nothing corresponding to the content m of the basic extraction item n, the process proceeds to step S7405, where it is checked whether all the content of the basic item n have been checked. If there is still unchecked content, step S7403 is entered, and the processing from step S7403 to step S7404 is repeated and executed. If all contents of the basic extraction item n are checked, it is checked in step S7406 whether all basic extraction items have been checked. If there are still unchecked basic extraction items, step S7402 is entered, and the processing from step S7402 to step S7406 is repeated and executed. In all the basic extraction items, if there is nothing corresponding to the contents of all the basic items, step S7412 follows and it is determined that the document image is not subject to restriction.

  Steps S7407 to S7413 are scrutinizing processes in the case where there is an item corresponding to the contents of the basic extraction item in step S7404. The details will be described below.

  In step S7407, the extraction item is extracted. Then, in step S7408, the content m 'corresponding to the extraction item n' is extracted.

  Then, in step S7409, it is checked whether or not there is any candidate information that corresponds to the content m 'of the extraction item n'. If there is anything corresponding to the content m 'of the extraction item n', step S7413 is entered and it is determined that the document is to be restricted. If there is nothing corresponding to the content m 'of the extraction item n', step S74010 is entered to check whether all the content of the extraction item n 'has been checked. If there is still unchecked content, the processing proceeds to step S7408, and the processing from step S7408 to step S7409 is repeated and executed. If all contents of the extracted item n are checked, it is checked in step S7411 whether all the extracted items have been checked. If there is an extraction item that has not been checked yet, step S7407 is entered, and the processes from step S7407 to step S7411 are repeated and executed. If the contents of all the extracted items do not correspond to the contents of all the extracted items, the process proceeds to step S7412 and it is determined that the document image is not subject to restriction.

  Next, an example of information processing by the information processing system according to the present embodiment will be described.

  FIG. 21 is a schematic view showing an eighth embodiment of the present invention and showing an example of the information processing of FIG.

  1801 is an example of a form for overseas remittance business. Items to be checked for transaction control include the remittance currency, country name, and trader surrounded by an ellipse.

  Reference numeral 1802 is an example of knowledge used to check the subject of transaction regulation. The knowledge information includes a content list of each item included in the 18030 basic extraction item, the 18040 extraction item, the 18031 basic extraction item, and a content list of each item included in the 18041 and 18042 extraction items. For example, the content number of the 18030 basic extraction item 01 "remittance currency" is set as "0101", and the content is set as "USD". Further, for example, there are a plurality of contents lists corresponding to the 18040 extraction item 11 "country name", and are listed up in order. In addition to Japanese, descriptions in other languages are also recorded in association.

  In the above-mentioned information processing, if there is one that corresponds to “remittance currency” and “USD” set as basic extraction items, it is considered as a scrutiny target. Then, it is checked whether or not it corresponds to the list of trade prohibited country names set as extraction items, or the list of problematic companies / individuals set as extraction items.

  In the present embodiment, information is automatically extracted from a financial form using knowledge of financial business. In the present embodiment, the overseas remittance business is taken as an example of the financial business, but the present invention may be applied to other business related to document images. Moreover, although the example which divides and checks the item to check into a basic extraction item and an extraction item was given in the example of automation of overseas remittance business, you may manage collectively and you may make it the structure of other than that.

  According to the eighth embodiment, if the proposed architecture is applied by replacing the necessary knowledge in the information extraction of the field to be set as a target, the application to non-medical work becomes possible.

  In the first, second, third, fourth, fifth, sixth, seventh and eighth embodiments described above, information is extracted from a scanned document image. It may be a target. At that time, an image correction process for a camera input image may be added.

(Other embodiments)
It goes without saying that the object of the present invention can also be achieved by supplying a computer readable storage medium storing a program code of software that implements the functions of the above-described embodiments to a system or apparatus. Needless to say, this can also be achieved by the computer (or CPU or MPU) of the system or apparatus reading out and executing the program code stored in the storage medium.

  In this case, the program code itself read out from the storage medium implements the functions of the above-described embodiments, and the storage medium storing the program code constitutes the present invention.

  As a storage medium for supplying the program code, for example, a flexible disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a non-volatile memory card, a ROM or the like can be used.

  Also, the functions of the above-described embodiment are realized by executing the program code read by the computer. In addition, a case where the OS (Operating System) or the like operating on the computer performs a part or all of the actual processing based on the instructions of the program code, and the above-described embodiment is realized by the processing is also included. Needless to say.

  The above plurality of embodiments may be combined.

110 document image analysis unit 120 candidate region setting unit 130 candidate region recognition unit 140 extraction information identification unit 150 registration unit

Claims (11)

First extraction means for extracting a plurality of regions from imaged medical document data;
A second extraction means for extracting a region including a first character from said plurality of regions,
Third extraction means for extracting medical department information of the medical document data from the area extracted by the second extraction means;
Equipped with
An information processing apparatus characterized in that the first character includes "family" . The information processing equipment according to claim 1, further comprising a classifying means for classifying the document data by using the information extracted by the third extraction unit. The apparatus further comprises area selecting means for selecting an area to be processed by the second extracting means based on the information on the areas extracted by the first extracting means.
It said second extraction means, the information processing apparatus according to claim 1 or claim 2, characterized in that extracting a region including the first character from the selected region. The information on the area is information indicating at least one of the position of the area extracted by the first extraction unit and the characters included in the area extracted by the first extraction unit.
The area selecting means selects an area extracted by the first extracting means which is within a predetermined range in the document data and in which the number of lines of contained characters is equal to or less than a fourth threshold. The information processing apparatus according to Item 3. The apparatus further comprises an assigning unit that assigns a priority to the area extracted by the first extracting unit.
Said second extraction means, information processing apparatus according to any one of claims 1 to 4, characterized in that extracting a region including the first character in the order based on the priority.   6. The information according to claim 5, wherein the giving unit gives a priority based on at least one of the position of the area extracted by the first extracting unit and the size of characters included in the area. Processing unit. It said classification means, according to claim 2 Symbol, characterized in that classifying the medical document data by using the information extracted by the information obtained and the third extracting means from the medical document data and the electronic medical record of the same patient Information processor. 8. The information processing apparatus according to claim 7, wherein the information obtained from the electronic medical record is information indicating whether or not a first visit. A first extraction step of extracting a plurality of regions from imaged medical document data;
A second extraction step of extracting a region including a first character from said plurality of regions,
A third extraction step of extracting medical department information of the medical document data from the area extracted in the second extraction step;
Equipped with
An information processing method characterized in that the first character includes "family" ;   A program causing a computer to execute each process according to claim 9.   A storage medium storing the program according to claim 10.

Images