JP2014115857A - Business form definition data creation system and business form definition data creation method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technology capable of determining an order of creation of business form definition data in accordance with the use situation of a business form.SOLUTION: A business form definition data creation system includes: an acquisition part for acquiring feature information indicating information related to the feature point of a business form; and a feature information storage part for storing identification information for identifying a business form and the feature information of the identified business form in association. The business form definition data creation system is configured to compare the feature information of the business forms stored in the feature information storage part, and to classify the business forms in groups. The business definition data creation system is configured to determine a business form as the object of the creation of business form definition data in accordance with the number of the business forms belonging to each group, and creates the business form definition data on the basis of the feature information of the business form.

Description

  The present invention relates to a form definition data creation system and a form definition data creation method.

  As a technique for registering format information of a form that is not held in a financial institution, there is a technique described in Japanese Patent Application Laid-Open No. 2008-299748 (Patent Document 1). This gazette states that “the sales office terminal sends image data of a form for which format information is not registered, and the form registration terminal creates format information based on the acquired form image data. When it is confirmed that the format information stored in the form image registration file is not affected, the created format information is sent to the server and stored in the all form image registration file. The format information created by the form registration terminal is acquired ”(see summary).

JP 2008-299748 A

  In the technique of Patent Document 1, the form registration terminal creates form definition data as format information based on image data of a form for which format information is not registered. However, in the technique of Patent Document 1, when there are a plurality of image data of forms for which form definition data is not registered, form definition data is uniformly generated for all forms. Therefore, for example, it is not possible to preferentially create form definition data for forms that are frequently used.

  Therefore, the present invention provides a technique capable of determining the creation order of the form definition data according to the use state of the form.

  In order to solve the above-mentioned problem, the present invention is a form definition data creation system for creating form definition data used for reading a form, and an acquisition unit for acquiring feature information representing information on feature points of the form; A feature information storage unit that associates and accumulates the form and the feature information; a classification unit that classifies the forms into groups by comparing the feature information stored in the feature information storage unit; A creation unit that creates the form definition data based on feature information, and the creation unit determines a form for which the form definition data is to be created according to the number of forms belonging to each group. It has a form definition data creation system.

  According to the present invention, since feature information representing information on feature points of a form is compared and the forms are classified into groups, the number of forms that can be regarded as the same form can be grasped. For this reason, the creation order of the form definition data can be determined according to the use state of the form. Problems, configurations, and effects other than those described above will be clarified by the following description of embodiments.

It is a figure which shows the structure of the form definition data creation system of one Example of this invention. It is a flowchart of the form process performed by the form definition data creation system. It is a figure which shows the identification number, image data, and characteristic information which are stored in undefined form DB. It is a flowchart of the classification process performed by an undefined form server. It is a figure for demonstrating the score table used for the addition of a score. It is a figure which shows the example in which the undefined form newly stored in undefined form DB is classified into the same group as another undefined form. It is a figure which shows another example which classify | categorizes the newly stored undefined form into the same group as the already stored undefined form. It is a figure which shows the result as which the some undefined form was classified by the classification | category part. It is a flowchart of a form definition data creation process executed by the form definition data creation system. It is a figure which shows the example of the image data and form definition data which are displayed on a display device in order to create form definition data. It is a figure for demonstrating another example of a classification process. It is a figure which shows the form definition data creation apparatus as one Example of a form definition data creation system.

  Hereinafter, examples will be described with reference to the drawings.

A1. System configuration:
In the present embodiment, an example of a system capable of determining the creation order of the form definition data according to the use state of the form will be described.

  FIG. 1 is a diagram showing a configuration of a form definition data creation system 1000 according to an embodiment of the present invention. The form definition data creation system 1000 is a system for creating form definition data necessary for reading a form. The form definition data includes, for example, data relating to the position of characters written in the form and the attributes of the written characters. The form definition data creation system 1000 has a configuration in which a form reading terminal 400, an undefined form server 200, a form definition terminal 300, and a center server 500 are connected to each other via a network NT. In FIG. 1, illustration of other components that are not necessary for the description is omitted. This also applies to the drawings described later.

  The form reading terminal 400 is installed in a financial institution or the like and is a terminal for acquiring the feature information from the read form. The feature information includes, for example, a form ID assigned to each form type, form title, form paper size, ruled line layout information described in the form, various item names, At least one of the item name position information is included. The form from which the form reading terminal 400 obtains characteristic information includes, for example, a form for depositing, a form for applying for various reports such as name change, a form for purchasing an investment trust, and a resident At least one of the forms for paying tax is included. The form reading terminal 400 includes a reading terminal control unit 410, a display 440, a scanner 450, an input device 460, a reading terminal communication unit 470, and a form definition data storage unit 430.

  The form definition data storage unit 430 stores form definition data for each type of form.

  The scanner 450 acquires form image data. The form for which image data has been acquired by the scanner 450 is hereinafter also referred to as a “form to be processed”.

  The reading terminal control unit 410 includes a CPU (not shown) and an internal storage device (not shown) such as a ROM and a RAM. The reading terminal control unit 410 functions as the determination unit 412 and controls the entire form reading terminal 400 by developing and executing a program stored in the ROM on the RAM. Based on the image data acquired by the scanner 450, the reading terminal control unit 410 acquires a form ID, a form title, ruled line layout information, and an item name as characteristic information. Also, the reading terminal control unit 410 performs OCR (Optical Character Reader) processing on the form for which form definition data has already been created, using the form definition data, and values and characters (hereinafter referred to as “characters”) written in each item. "Item value").

  The determination unit 412 determines whether or not the form definition data of the processing target form is stored in the form definition data storage unit 430 based on the acquired form ID. The form determined by the determination unit 412 that the form definition data is not stored in the form definition data storage unit 430 is hereinafter also referred to as “undefined form”.

  The display 440 displays at least one of the image data acquired by the scanner 450, the feature information acquired by the reading terminal control unit 410, and the item value. The input device 460 is configured by, for example, a keyboard and a mouse. The input device 460 is used for inputting or correcting feature information by an operator of a financial institution when feature information is not described in a form or when feature information is described outside a predetermined frame. Used for. The input device 460 is used by an operator to input item values when the item values of the processing target form are not acquired from the image data.

  The reading terminal communication unit 470 performs data communication between the form reading terminal 400 and another device. The other device is at least one of the undefined form server 200, the form definition terminal 300, and the center server 500. The reading terminal communication unit 470 transmits the image data and feature information of the undefined form to the undefined form server 200. Further, the reading terminal communication unit 470 transmits image data, feature information, and item values of the processing target form to the center server 500.

  Next, the undefined form server 200 will be described. The undefined form server 200 includes a server control unit 210, a server communication unit 220, an undefined form database (undefined form DB) 230, and a score table 235.

  The server communication unit 270 performs data communication between the undefined form server 200 and other devices. The other apparatus is at least one of the form reading terminal 400, the form definition terminal 300, and the center server 500. The server communication unit 270 receives image data and feature information of an undefined form from the reading terminal communication unit 470 of the form reading terminal 400. In the undefined form DB 230, image data and feature information of the undefined form received by the server communication unit 270 are stored in association with identification information for distinguishing from image data and feature information of other undefined forms. Is done.

  The server control unit 210 includes a CPU (not shown) and an internal storage device (not shown) such as a ROM or a RAM. The server control unit 210 develops and executes a program stored in the ROM on the RAM, thereby functioning as the classification unit 212 and controls the entire undefined form server 200. Further, the server control unit 210 adds identification information to the image data and feature information of the undefined form received by the server communication unit 270.

  The classification unit 212 compares feature information of a plurality of undefined forms stored in the undefined form DB 230, and classifies undefined forms that are regarded as the same form into the same group. Details of the classification performed by the classification unit 212 will be described later.

  The score table 235 is a table in which feature information and scores are related. The score table 235 is used when comparing feature information of undefined forms.

  Next, the form definition terminal 300 will be described. The form definition terminal 300 includes a definition terminal control unit 310, a display 340, an input device 360, a definition terminal communication unit 370, and a form definition database (form definition DB) 330.

  The form definition DB 330 stores form definition data for each form type. The form definition DB 330 stores the created form definition data each time new form definition data is created by a definition data creation unit 314 described later.

  The definition terminal control unit 310 includes a CPU (not shown) and an internal storage device (not shown) such as a ROM or a RAM. The definition terminal control unit 310 functions as the definition data creation unit 314 and controls the entire form definition terminal 300 by developing and executing a program stored in the ROM on the RAM. The definition data creation unit 314 creates form definition data based on the feature information of the undefined form. Details of the creation of the form definition data performed by the definition data creation unit 314 will be described later.

  The input device 360 is configured by a keyboard, a mouse, or the like, for example. The input device 360 is used when creating form definition data. The display 340 displays at least one of the image data, the feature information, and the created form definition data.

  The definition terminal communication unit 370 mainly performs data communication between the undefined form server 200 and the form reading terminal 400 and the form definition terminal 300. The definition terminal communication unit 370 transmits the form definition data to the form reading terminal 400 when the form definition DB 330 is updated.

  The center server 500 includes a center server control unit 510 and a center server communication unit 570. The center server communication unit 570 mainly performs data communication between the center server 500 and the form reading terminal 400, and acquires image data, feature information, and item values of the processing target form from the form reading terminal 400. .

  The center server control unit 510 includes a CPU (not shown) and an internal storage device (not shown) such as a ROM or a RAM. The center server control unit 510 functions as a form processing unit 512 and controls the entire center server 500 by developing and executing a program stored in the ROM on the RAM. The form processing unit 512 performs various processes based on the feature information and item values. The various types of processing include deposit procedures, name change procedures, and resident tax payment procedures.

A2. Form processing:
FIG. 2 is a flowchart of the form process executed by the form definition data creation system 1000. The form process is a process performed by the form reading terminal 400, the undefined form server 200, and the center server 500. The form processing is started when the reading terminal control unit 410 instructs the scanner 450 included in the form reading terminal 400 to acquire image data of the form.

  When the reading terminal control unit 410 instructs acquisition of the form image data, the scanner 450 acquires the form image data set in the scanner 450 (step S100). The form set in the scanner 450 is, for example, a form brought into the financial institution where the form reading terminal 400 is installed by a customer.

  When the image data of the form to be processed is acquired by the scanner 450 (step S100), the reading terminal control unit 410 acquires feature information based on the image data (step S102). The feature information can be acquired using a known method described in, for example, Japanese Patent Application Laid-Open No. 2011-248609, regardless of the presence or absence of form definition data. When the feature information cannot be acquired based on the image data, the operator inputs the feature information using the input device 460. The reading terminal control unit 410 acquires the input feature information.

  When the feature information is acquired, the determination unit 412 searches the form definition data storage unit 430 for form definition data corresponding to the processing target form based on the feature information (step S104). Specifically, the determination unit 412 searches the form definition data storage unit 430 for form definition data associated with the form ID among the feature information acquired in step S102. The determination unit 412 compares the form ID, the form title, the form paper size, the ruled line layout information, the item name and the position information thereof with the form definition data, and determines a predetermined match. The form definition data satisfying the degree may be searched.

  If the form definition data associated with the form ID is not stored in the form definition data storage unit 430, the determination unit 412 determines that the processing target form is an undefined form (step S106: YES). If the form definition data associated with the form ID is stored in the form definition data storage unit 430, the determination unit 412 determines that the processing target form is not an undefined form (step S106: NO).

  If it is determined that the form to be processed is an undefined form (step S106: YES), the reading terminal communication unit 470 obtains the image data acquired in step S100 and the feature information acquired in step S102. Then, it is transmitted to the undefined form server 200 (step S108).

  Next, in the undefined form server 200, when the server communication unit 270 receives the image data and feature information of the undefined form from the form reading terminal 400 (step S120), the server control unit 210 displays the image of the undefined form. An identification number is assigned to the data and feature information and stored in the undefined form DB 230 (step S122). In this embodiment, the server control unit 210 assigns a number such as “001” as an identification number to image data and feature information.

  FIG. 3 is a diagram showing identification numbers, image data, and feature information stored in the undefined form DB 230. In the undefined form DB 230, as shown in FIG. 4, the identification number “001”, the feature information 812, and the image data of the undefined form 810 are linked.

  Returning to FIG. 2, when the image data and the feature information are stored in the undefined form DB 230, the classification unit 212 of the undefined form server 200 performs a classification process described later (step S124).

  When the reading terminal communication unit 470 transmits the image data and the feature information to the undefined form server 200 (step S108), the reading terminal control unit 410 determines that the processing target form is an undefined form, step S102. Among the feature information acquired in step 1, the item name is displayed on the display 440 to prompt the input of the item value corresponding to the item name (step S110). The operator inputs the item value corresponding to the displayed item name with reference to the image data or the form to be processed.

  On the other hand, when the determination unit 412 determines in step S106 that the processing target form is not an undefined form (step S106: NO), the reading terminal control unit 410 displays the image data and the form acquired by the scanner 450. Based on the definition data, the item value is acquired by character recognition (step S112).

  When the item value is input by the operator (step S110) or the item value is acquired by character recognition (step S112), the reading terminal communication unit 470 converts the image data, the feature information, and the item value into the center. It transmits to the server 500 (step S114). Note that the reading terminal communication unit 470 may transmit only the feature information and the item value to the center server 500.

  When the center server communication unit 570 of the center server 500 receives the image data, the feature information, and the item value (step S130), the form processing unit 512 of the center server 500, for example, according to a form type, for example, a predetermined process such as a deposit process The process is executed (step S132). Thus, a series of form processing ends.

A3. Classification process:
FIG. 4 is a flowchart of the classification process performed by the undefined form server 200. The undefined form classification process is a process performed by the classification unit 212 of the undefined form server 200 when image data and feature information of an undefined form are stored in the undefined form DB 230 (FIG. 2, step S122). It is.

  When the classification process is started, the classification unit 212 searches the undefined form DB 230 to check whether or not characteristic information of other undefined forms has already been stored (step S200). The case where the feature information of another undefined form is stored is a case where feature information having an identification number different from the newly stored feature information exists in the undefined form DB 230 in this embodiment. .

  When the feature information of other undefined forms has already been stored (step S200: YES), the classification unit 212 includes the feature information of each other undefined form and the newly registered undefined form. Each feature information is compared, and a score is added to the undefined form (step S202).

  FIG. 5 is a diagram for explaining the score table 235 used for adding points. The score table 235 determines the points to be added to newly registered undefined forms when the same feature information exists in other undefined forms and newly stored undefined forms. It is a table. The number of points to be added is determined for each feature information and is weighted according to the feature information. For example, when the form ID of a newly stored undefined form is the same as the form ID of an already stored undefined form, 50 points are added to the undefined form. In the score table 235, the number of points to be a predetermined border is described. The number of points that become borders refers to the undefined forms that have already been stored and the newly stored items that have been added when the total number of points added to the newly stored undefined forms reaches the number of points that become borders. This is the number of points that can be regarded as an undefined form as the same form. In the score table 235 of this embodiment, 100 points are described as the number of points serving as a border.

  Returning to FIG. 4, the classification unit 212 uses the score table 235 to add a score to the newly stored undefined form (step S202), and the total score added to the new undefined form Is greater than or equal to the number of borders (step S204). When the total number of points added to the newly stored undefined form is equal to or greater than the number of points serving as a border (step S204: YES), the classification unit 212 converts the newly stored undefined form to It is classified into the same group as the undefined form that has already been stored (step S206).

  On the other hand, when no other undefined form is stored in step S200 (step S200: NO), the total number of points added to the new undefined form in step S204 is not more than the number of points serving as a border. In this case (step S204: NO), the classification unit 212 stores the new undefined form as it is in the undefined form DB 230 without classifying it into a group. A series of classification processes is completed as described above.

  FIG. 6 is a diagram illustrating an example in which undefined forms newly stored in the undefined form DB 230 are classified into the same group as other undefined forms. FIG. 6 shows an undefined form 810 already stored in the undefined form DB 230 and an undefined form 820 newly stored in the undefined form DB 230. An identification number “001”, image data, and feature information 812 are associated with the undefined form 810. An identification number “002”, image data, and feature information 822 are associated with the undefined form 820. FIG. 6 also shows a score table 235.

  As shown in FIG. 6, both the form ID of the newly stored undefined form 820 and the form ID of the already stored undefined form 810 are “1001”. Therefore, the classification unit 212 adds 50 points to the newly stored undefined form 820 according to the score table 235. Similarly, the form title of each form is “payment slip”. Therefore, the classification unit 212 adds 30 points to the undefined form 820 newly stored according to the score table 235. Further, the paper size of each form is “A5”. Therefore, the classification unit 212 adds 20 points to the newly stored undefined form 820 according to the score table 235. The total number of these points (100 points) is equal to or greater than the number of points serving as the border of the score table 235. Therefore, the classification unit 212 classifies the newly stored undefined form 820 into the same group g1 as other stored undefined forms 810. The classified group g1 is a group created based on the undefined form 810 stored in the undefined form DB 230 before the undefined form 820. The group g1 is a group to which an undefined form that is regarded as the same as the undefined form 810 having the characteristic information 812 belongs.

  FIG. 7 is a diagram illustrating another example in which newly stored undefined forms are classified into the same group as previously stored undefined forms. FIG. 7 shows an undefined form 810, an undefined form 820, and an undefined form 830 that are already stored in the undefined form DB 230. Among these, the undefined form 810 and the undefined form 820 are already classified into the same group g1. The undefined form 840 having the identification number “004” is an undefined form newly stored in the undefined form DB 230.

  The classification unit 212 compares the newly stored feature information of the undefined form 840 with the feature information of the undefined form 810 belonging to the group g1. Here, when the total number of points added to the undefined form 840 is less than 100, the classification unit 212 next displays the feature information of the undefined form 840 and the undefined that does not belong to the group g1. The feature information of the form 830 is compared. As a result, when the total number of points added to the undefined form 840 is 100 points or more, the classification unit 212 classifies the undefined form 840 into the same group g2 as the undefined form 830. The classified group g2 is a group created based on the undefined form 830. Further, the group g2 is a group to which an undefined form that is regarded as the same as the undefined form 830 belongs. When a new undefined form is stored, if the group has already been created in this way, the classification unit 212 adds the feature information of the undefined form that is used as a reference when the group is created and the new information. Comparison with feature information of undefined forms.

  FIG. 8 is a diagram illustrating a result of classification of a plurality of undefined forms by the classification unit 212. A group g1 illustrated in FIG. 8 is a group to which an undefined form 810 having the characteristic information 812 associated with the identification number “001” belongs. Four undefined forms 810, 820, 850, and 860 belong to the group g1. The group g2 is a group to which an undefined form having the characteristic information 832 associated with the identification number “003” belongs. Two undefined forms 830 and 840 belong to the group g2. The undefined form 870 having the identification number “007” is a form that does not belong to any group. When the classification process is executed, the undefined form in the undefined form DB 230 is classified as shown in FIG.

A4. Form definition data creation process:
FIG. 9 is a flowchart of a form definition data creation process executed by the form definition data creation system 1000. When the form definition data creation process is started, the form definition terminal 300 inquires of the undefined form server 200 whether or not an undefined form is stored in the undefined form DB 230 (step S300).

  When the server communication unit 270 receives an inquiry from the form definition terminal 300 (step S302), the server control unit 210 searches the undefined form DB 230 to determine whether there is an undefined form and the number of undefined forms. It transmits to the definition terminal 300 (step S304). When the contents of the undefined form DB 230 are classified as shown in FIG. 8, the undefined form server 200 determines that there are undefined forms and that four undefined forms are classified into the group g1. That the two undefined forms are classified in the group g2 and that there is one undefined form that does not belong to the group is transmitted to the form definition terminal 300. The definition terminal communication unit 370 of the form definition terminal 300 receives the presence / absence and number of undefined forms from the undefined form server 200 (step S306).

  If undefined forms exist in the undefined form DB 230 (step S308: YES) and a plurality of undefined forms exist in the undefined form DB 230 (step S310: YES), the definition data The creation unit 314 requests the undefined form server 200 to transmit image data and feature information of the group having the largest number of undefined forms (step S312). For example, when the undefined form DB 230 is classified as shown in FIG. 8, the definition data creation unit 314 has the image data and feature information of the group g1 in which the number of undefined forms is larger than the group g2. Is requested (step S312). When there are not a plurality of undefined forms, that is, when only one undefined form is stored in the undefined form DB (step S310: NO), the definition data creation unit 314 stores the undefined forms stored. A request is made to transmit the image data and feature information of the form (step S314).

  When the image data and feature information transmission request is received from the form definition terminal 300 (step S316), the undefined form server 200 searches the undefined form DB 230 for the requested image data and feature information, and forms the form definition terminal. It transmits to 300 (step S318).

  When image data and feature information are received from the undefined form server 200 (step S320), the definition data creation unit 314 of the form definition terminal 300 creates form definition data based on the received image data and feature information (step S320). S322).

  FIG. 10 is a diagram showing an example of the image data 001i and the form definition data d1 displayed on the display device 340 for creating the form definition data. The definition data creation unit 314 displays the feature information received in step S320 of FIG. 9 on the display device 340 together with the image data 001i as form definition data d1 using the format shown in FIG. When the characteristic data is acquired in the form processing described with reference to FIG. 2, the definition data creation unit 314 determines the number of characters as shown in FIG. And the character type and coordinates are displayed in association with the item number (item number) and item name. The operator collates the image data 001i displayed on the display 340 with the form definition data d1, and if there is an item described in the image data 001i but not in the form definition data d1. The item is added to the form definition data d1. If an unnecessary item is described in the form definition data d1, the item is deleted from the form definition data d1.

  Returning to FIG. 9, when the form definition data is created, the definition terminal control unit 310 stores the created form definition data in the form definition DB 330 and transmits it to the form reading terminal 400 (step S324).

  Upon receiving the created form definition data from the form definition terminal 300 (step S326), the form reading terminal 400 adds the form definition data to the form definition data storage unit 430 and stores it (step S328). This completes the form definition data creation process.

  According to the form definition data creation system 1000 as described above, the determination unit 412 stores the form definition data corresponding to the process target form in the form definition data storage unit 430 based on the acquired feature information. Judge whether there is no undefined form. In the case of an undefined form, the acquired image data and feature information are stored in the undefined form DB 230. Each time feature information of an undefined form is acquired in the undefined form DB 230, the feature information is stored and accumulated. Therefore, the operator of the financial institution can count the number of undefined forms read by the form reading terminal 400. Can be grasped.

  The classification unit 212 of the undefined form server 200 compares the feature information of the undefined forms in the undefined form DB 230, and selects the same form from the undefined forms stored in the undefined form DB 230. A plurality of undefined forms that can be regarded are classified into the same group. As a result, since a group is created for each type of undefined form, the operator can grasp the number of types of undefined form read by the form reading terminal 400. In addition, since it is possible to grasp the number of undefined forms belonging to the group, it is possible to grasp undefined forms that are frequently read by the form reading terminal 400. Therefore, the operator can grasp undefined forms that are frequently used by customers. Further, the definition data creation unit 314 obtains image data and feature information of a group having a large number of undefined forms, and creates form definition data. Therefore, form definition data can be created preferentially from undefined forms that are frequently used. When form definition data is newly created, the created form definition data is transmitted to the form reading terminal 400 and stored in the form definition data storage unit 430. As a result, the form reading terminal 400 can automatically perform processing of undefined forms that had previously required input of item values or the like using the form definition data. As a result, the convenience of the customer can be improved and the burden on the operator can be reduced.

  Furthermore, in the form definition data creation system 1000 according to the present embodiment, the classification unit 212 uses the same for other undefined forms that have already been stored in the undefined form DB 230 and the newly stored undefined forms. If feature information exists, a predetermined score is added to the newly stored undefined form for each identical feature information. If the score added to the newly stored undefined form is equal to or greater than the predetermined score, the newly stored undefined form is the same as the other undefined form that has already been stored. Classify into groups. As a score to be added, for example, a high score can be set for feature information having high importance as information representing a feature of the form, such as a form ID and a form title. Therefore, even if an undefined form whose feature information does not completely match, a form whose feature information with high importance matches can be regarded as the same form as an undefined form that has already been stored. . Therefore, according to the form definition data creation system of the present embodiment, it is possible to grasp the form that is effective for newly creating the form definition data and create the form definition data.

B1. Classification process:
In the first embodiment described above, the classification unit 212 adds a score for each feature information to the undefined form newly stored in the undefined form DB 230, and the added score is a predetermined score or more. In this case, even if the undefined form does not completely match the feature information, the newly stored undefined form is classified into the same group as the already stored undefined form. On the other hand, in the present embodiment, an example will be described in which a plurality of undefined forms whose feature information is completely matched are classified into the same group.

  FIG. 11 is a diagram for explaining another example of the classification process. When the classification process is started, the classification unit 212 stores image data and feature information of other undefined forms in the undefined form DB 230 as in the first embodiment (FIG. 4, step S200). It is searched whether or not (FIG. 11, step S400).

  When image data and feature information of other undefined forms are already stored (step S400: YES), the classification unit 212 has the same item name as the item name of the newly stored undefined form. Another undefined form is searched from the undefined form DB (step S402). The classification unit 212 counts “+1” for other undefined forms having the same item name (step S404).

  The classification unit 212 repeatedly executes step S402 to step S404 when the search has not been completed for all item names of the newly stored undefined form (step S406: NO).

  When the search is completed for all item names of the newly stored undefined form (step S406: YES), the classification unit 212 searches for an undefined form in which the number of counts matches the number of item names. (Step S408). Other undefined forms in which the number of counts matches the number of item names are undefined forms that have all the item names of newly stored undefined forms.

  If there is another undefined form in which the number of counts matches the number of item names (step S408: YES), the classification unit 212 determines the newly stored undefined form, the number of counts, and the item name. Are classified into the same group (step S410). On the other hand, if no other undefined form is stored in step S400 (step S400: NO), or if there is no other undefined form in which the count matches the number of item names in step S408 ( In step S408: NO), the classification unit 212 stores the new undefined form in the undefined form DB 230 as it is without classifying it into a group. A series of classification processes is completed as described above. After the classification process is completed, a form definition data creation process is performed as in the first embodiment (A4).

  When the above classification process is performed, the classification unit 212 of the undefined form server 200 compares the feature information of the undefined form in the undefined form DB 230, and stores the undefined form stored in the undefined form DB 230. Forms that can be regarded as the same form from the definition forms are classified into groups. Furthermore, the definition data creation unit 314 creates form definition data in preference to the group with the largest number of undefined forms. Therefore, also in Example 2, there exists an effect similar to Example 1.

  In this embodiment, the classification unit 212 classifies the newly stored undefined form and undefined forms having all the item names of the undefined form into the same group. For this reason, it is possible to exclude similar forms and reliably classify only the same form into the same group. Therefore, the form definition data can be effectively created even for a form that is preferred to create form definition data by excluding similar forms.

C. Variations:
In addition, this invention is not limited to an above-described Example, Various modifications are included. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described. Also, a part of the configuration of one embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to a part of the configuration of one embodiment. . It is also possible to add, delete, and replace the configuration of each embodiment.

  Each of the above-described configurations, functions, processing units, processing means, and the like may be realized by hardware by designing a part or all of them with, for example, an integrated circuit. Each of the above-described configurations, functions, and the like may be realized by software by interpreting and executing a program that realizes each function by the processor. Information such as programs, tables, and files that realize each function can be stored in a recording device such as a memory, a hard disk, or an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

  In addition, the control lines and information lines in the figure are those that are considered necessary for the explanation, and not all the control lines and information lines on the product are necessarily shown. Actually, it may be considered that almost all the components are connected to each other.

C1. Modification 1:
FIG. 12 is a diagram showing a form definition data creation device 100 as an example of the form definition data creation system. In the various embodiments described above, the form definition data creation system 1000 including the undefined form server 200, the form definition terminal 300, the form reading terminal 400, and the center server 500 creates the form definition data. Yes. On the other hand, the creation of the form definition data may be performed by one apparatus as shown in FIG.

C2. Modification 2:
In the various embodiments described above, the form definition data creation system 1000 includes one form reading terminal 400 (FIG. 1). On the other hand, the form definition data creation system 1000 may include a plurality of form reading terminals 400.

C3. Modification 3:
In the first embodiment described above, when a plurality of undefined forms are already classified into a group and the undefined form is newly stored in the undefined form DB 230, the classification unit 212 causes the undefined form belonging to the group. Among them, the feature information of the undefined form that is used as a reference when creating the group is compared with the feature information of the newly stored undefined form. On the other hand, the classification unit 212 may compare the feature information of all undefined forms belonging to the group with the feature information of the newly stored undefined forms.

C4. Modification 4:
In the various embodiments described above, the classification unit 212 performs classification every time an undefined form is stored in the undefined form DB 230. On the other hand, the classification unit 212 may perform classification at a predetermined timing, for example, when an inquiry about the presence / absence of an undefined form is received from the form definition terminal 300.

C5. Modification 5:
In the various embodiments described above, as feature information, the form ID assigned to each form type, form title, form paper size, ruled line layout information described in the form, The item name and its position information are used. On the other hand, the feature information may be the size of characters of the item names described in the form, the font, the color of the form, or the like.

C6. Modification 6:
In the various embodiments described above, the form definition data creation system 1000 creates form definition data for undefined forms stored in the undefined form DB 230. On the other hand, the form definition data creation system 1000 may classify all forms for which feature information has been acquired, and create form definition data.

C7. Modification 7:
In the various embodiments described above, the form definition data creation system 1000 creates form definition data for undefined forms with the largest number of forms belonging to a group. On the other hand, the form definition data creation system 1000 may create form definition data for a form belonging to a group when the number of forms belonging to the group is equal to or greater than a predetermined number.

001i: Image data 001, 002, 003, 004, 005, 006, 007 ... Identification number 100 ... Form definition data creation device 200 ... Undefined form server 210 ... Server control part 212 ... Classification part 220 ... Server communication part 230 ... Not yet Definition form DB
235 ... Score table 270 ... Server communication part 300 ... Form definition terminal 310 ... Definition terminal control part 314 ... Definition data creation part 330 ... Form definition DB
340 ... Display device 360 ... Input device 370 ... Definition terminal communication unit 400 ... Form reading terminal 410 ... Reading terminal control unit 412 ... Determination unit 430 ... Form definition data storage unit 432 ... Form definition data 440 ... Display device 450 ... Scanner 460 ... Input device 470 ... Reading terminal communication unit 500 ... Center server 510 ... Center server control unit 512 ... Form processing unit 570 ... Center server communication unit 810, 820, 830, 840, 850, 860, 870 ... Undefined forms 812, 822, 832 ... Feature information 1000 ... Form definition data creation system g1, g2 ... Group d1 ... Form definition data NT ... Network

Claims (6)

A form definition data creation system for creating form definition data used to read a form,
An acquisition unit for acquiring feature information representing information on feature points of the form;
A feature information storage unit that associates and accumulates the form and the feature information;
Comparing the feature information of each form accumulated in the feature information storage unit, classifying each form into a group,
A creation unit that creates the form definition data based on the feature information;
The form creation data creation system, wherein the creation unit determines a form for which the form definition data is to be created according to the number of forms belonging to each group. The form definition data creation system according to claim 1,
The form creation data creation system in which the creation unit determines a form in a group having the largest number of forms belonging to the group as a target for creating the form data. The form definition data creation system according to claim 1 or claim 2,
The acquisition unit acquires the feature information for each of a plurality of feature points from each form,
The classification unit adds a score corresponding to the matched feature information when the feature information matches another document for the comparison target document, and the added score is equal to or more than a predetermined score A form definition data creation system for classifying the forms to be compared into the same group as the other forms. The form definition data creation system according to claim 3,
A form definition data creation system in which each feature information score is weighted. The form definition data creation system according to claim 1 or claim 2,
The classification unit creates a form definition data for classifying the form to be compared into the same group as the other form when the characteristic information of the form to be compared matches the characteristic information of another form. system. A method for creating form definition data by a form definition data creation system,
Acquiring feature information representing information on feature points of the form;
Linking and storing the form and the feature information;
Comparing the feature information of each of the accumulated forms, and classifying each form into a group;
Creating the form definition data based on the feature information,
The method of creating the form definition data includes a step of determining a form for which the form definition data is to be created according to the number of forms belonging to each group.

Images