JP2020035235A - Business center operation supporting system and business center operation supporting method - Google Patents

Abstract

To provide a business center operation supporting system and a business center operation supporting method that can efficiently handle a large amount of closing work in a business center.SOLUTION: A business center operation supporting system 10 includes: a storage unit 101 that holds form information 125, form image data 126, and transaction identification information 127; and an arithmetic logical unit 104 that acquires identification information acquired for forms of target transaction to closing processing from the storage unit, extracts attribute information of each form in a form group corresponding to the identification information from the form information 125, executes recognition processing on image data of the form of the target transaction by a second recognition engine different from a first recognition engine used in the recognition processing at time of the target transaction, specifies the attribute information of the form, collates attribute information of each form in the form group with attribute information of the form of the target transaction, and performs predetermined completion processing on the closing processing for a target transaction whose attribute information matches one of the forms in the form group.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an office center operation support system and an office center operation support method.

  A so-called high-performance ATM that can process various payment slips such as tax and public money has appeared. According to the high-performance ATM, the user can process various kinds of payment processing conventionally limited to the window. For this reason, it is expected that the congestion of counters at business offices will be reduced and the convenience of users will be improved.

  Note that a form recognition technique exists as a characteristic function of the above-described high-performance ATM. This technology extracts and recognizes necessary information from the entire image of a form read by a scanner, and makes it possible to issue a receipt printed with a form image and a receipt stamp when a receipt is issued.

  As a conventional technology related to such a recognition technology, for example, a character recognition device that recognizes characters in an image, cuts out a local image while scanning an input image, extracts features, and registers the features in the dictionary with the features. A first-stage character recognition unit that determines a character candidate based on the degree of similarity with the extracted character feature; and extracts a feature different from the feature already used for feature extraction for the determined character candidate. And a character recognition device (see Patent Document 1) characterized by having one or more different characteristic character recognizing means for narrowing down the character candidates based on the similarity between the character and the character registered in the dictionary. Have been.

  In addition, a customer contact terminal device of a financial institution that performs provisional receipt processing of a form in which a customer has filled in necessary information including a transaction amount by hand, and receives information on the provisional receipt processing and responds to a reception serial number and the transaction amount. A host computer for issuing an authentication amount to be returned to the counter terminal device, and returning the handwritten transaction amount based on the OCR-formatted form read data obtained by printing the reception serial number and the authentication amount at the counter terminal device. A form data processing system (see Patent Literature 2) is also proposed, which includes a collation unit provided at a central processing center for collating with the authentication amount.

  In addition, a form type file in which keyword words for form type discrimination are registered in advance, a form image data is read, a character string is extracted from the read image data, and character recognition is performed on the extracted character string. Unit, a form type determining keyword word extracting unit that extracts a character string recognized by the character recognizing unit as a keyword word, and the extracted keyword word and the form type determining keyword word registered in the form type file. There has also been proposed a form type discriminating device (see Patent Document 3), which comprises a discriminating means for discriminating a form type by collating.

JP 2006-251920A JP 2006-4121 A JP-A-200-JP

By the way, in financial institutions that have introduced the above-mentioned high-performance ATM, as a closing work for transactions at the high-performance ATM, collation and confirmation of the actual form and the transaction result by the employees are performed for each branch. We are implementing.

On the other hand, there is also a need to consolidate the tightening work in an office center instead of performing it for each branch. Therefore, if the closing work of each branch is performed in an office center, a large number of man-hours of about 10 man days are required depending on the financial institution, which is unrealistic in terms of business costs. On the other hand, even if a recognition technique such as a conventional technique is applied, automation of the above-described tightening operation is difficult, and cannot be an effective option.
Therefore, an object of the present invention is to provide a technique for efficiently performing a huge amount of tightening work in an office center.

  The office center operation support system of the present invention for solving the above-mentioned problems includes a form information describing attribute information of each form used in a financial institution, image data of a form used in a predetermined transaction in the financial institution, A storage unit that holds the identification information of the transaction identified by the predetermined recognition processing on the image data of the form, and the identification information obtained from the storage unit regarding the form of the transaction to be closed, and the identification information A process of extracting attribute information of each form in the form group corresponding to the form information from the form information, and a second recognition engine different from the first recognition engine used in the recognition processing at the time of the target transaction, thereby processing the target transaction. Executing a recognition process on the image data of the form to specify attribute information of the form; An operation unit that compares attribute information of the form of the target transaction with attribute information of any of the forms in the group of forms and executes a predetermined completion process related to the closing process for the target transaction. Features.

  In addition, the office center operation support method of the present invention includes a form information describing attribute information of each form used in a financial institution, image data of a form used in a predetermined transaction in the financial institution, and an image of the form. An information processing system including a storage unit that holds the identification information of the transaction identified by the predetermined recognition process for the data and the storage unit that holds the identification information obtained for the form of the transaction targeted for the closing process from the storage unit, A process of extracting attribute information of each form in the form group corresponding to the identification information from the form information, and a second recognition engine different from the first recognition engine used in the recognition process at the time of the target transaction, A process for recognizing the image data of the form of the target transaction to specify attribute information of the form, and an attribute of each form in the form group And comparing the attribute information of the form of the target transaction with the attribute information of the form of the target transaction, and executing a predetermined completion process related to a closing process for the target transaction in which the attribute information matches any one of the forms in the form group. And

  ADVANTAGE OF THE INVENTION According to this invention, the enormous fastening work in an office center can be made efficient.

FIG. 1 is a network configuration diagram including an office center operation support system according to an embodiment. It is a figure showing the example of hardware constitutions of the tax public money server in this embodiment. FIG. 2 is a diagram illustrating a hardware configuration example of a high-performance ATM according to the embodiment. It is a figure showing the example of data composition of the report specific knowledge of this embodiment. FIG. 3 is a diagram illustrating a data configuration example of form image data according to the embodiment. It is a figure showing the example of data composition of transaction identification information of this embodiment. It is a figure showing the example of data composition of acceptance possibility knowledge of this embodiment. It is a figure showing the example of the flow of the office center operation support method in this embodiment. It is a figure showing the example of a screen in this embodiment.

--- Network configuration ---

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. FIG. 1 is a network configuration diagram including an office center operation support system 10 of the present embodiment. The office center operation support system 10 shown in FIG. 1 is a computer system for efficiently performing a huge amount of closing work in the office center.

  The office center operation support system 10 according to the present embodiment is a system operated by a financial institution. As shown in FIG. 1, a tax and public money server 100 operated by the headquarters of the financial institution and the like are installed in each business office. And a high-performance ATM 200. The tax and public money server 100 and the high-performance ATM 200 are communicably connected to each other via a network 1 inside a secure financial institution.

  Of course, such a configuration is merely an example, and one of the tax and public money server 100 and the high-performance ATM 200 may have the configuration and functions of the office center operation support system 10.

  In the above-described configuration, the tax and public money server 100 cooperates with each of the high-performance ATMs 200 provided in each business office to provide the customer with a service of a tax and public money payment transaction using a form at each business office.

  More specifically, the server device determines the subsequent operation content corresponding to the type of the form received from the customer at the high-performance ATM 200 and instructs the high-performance ATM 200 to the operation content. In addition, as the above-mentioned operation content, it is assumed that a transaction can be accepted.

  The tax and public money server 100 of the present embodiment has a function of recognizing various forms. This recognition function extracts and recognizes necessary information from a form image obtained from the high-performance ATM 200.

The high-performance ATM 200 is an ATM that can handle various payment slips (hereinafter, forms) such as tens of thousands of types of tax and public money, which were conventionally limited to handling at a counter.
The customer who is a user of the high-performance ATM 200 does not need to enter a payment request form, and can perform various payment processing by himself / herself. As a result, it is easy to improve customer convenience and customer satisfaction.

The high-performance ATM 200 of the present embodiment has a function of recognizing various forms, although the feature extraction algorithm is different from that of the tax and public money server 100. This recognition function extracts and recognizes necessary information from a form image read by the scanner unit, and notifies the tax public money server 100 of the result. Unlike conventional devices and the like, it is possible to recognize a form without registering a format, such as determining an area to be read in advance. When issuing a receipt upon completion of the transaction, a receipt with a receipt printed on the form image is issued, and it is not necessary to stamp the original payment slip at the counter.
−−− Hardware configuration −−−

  Next, a hardware configuration of the tax and public money server 100 that configures the office center operation support system 10 of the present embodiment will be described. FIG. 2 is a diagram illustrating a hardware configuration example of the tax and public money server 100 of the present embodiment.

  In this case, the tax and public money server 100 includes a storage unit 101 including an appropriate nonvolatile storage element such as an SSD (Solid State Drive) and a hard disk drive, a memory 103 including a volatile storage element such as a RAM, and a storage unit 101. The stored program 102 is read into a memory 103 and executed to execute overall control of the apparatus itself, and also to perform various determinations, calculations and control processing, such as a CPU 104, and to a network 1 for connection to a network 1 A communication unit 105 for performing communication processing with each of the functional ATMs 200;

  The program 102 held in the storage unit 101 is a general information processing function and a function required as a device constituting the office center operation support system 10 of the present embodiment, that is, a function for recognizing various forms. 2 is a program that implements the second recognition engine 111.

  In addition, the storage unit 101 stores at least form identification knowledge 125, form image data 126, transaction identification information 127, and reception availability knowledge 128. Details of the information 125 to 128 will be described later.

  FIG. 3 shows a hardware configuration example of the high-performance ATM 200 of the present embodiment. The high-performance ATM 200 according to the present embodiment includes a storage unit 201 including an appropriate nonvolatile storage element such as an SSD (Solid State Drive) and a hard disk drive, a memory 203 including a volatile storage element such as a RAM, and a storage unit 201. An arithmetic unit 204 such as a CPU for executing the stored program 202 by reading it out to the memory 203 and performing overall control of the apparatus itself and performing various determinations, calculations and control processing, and an input for receiving a key input or a voice input from a user Unit 205, an output unit 206 such as a display for displaying processing data, a communication unit 207 connected to the network 1 to perform communication processing with the tax and public money server 100, a scanner unit 208 to perform an image acquisition operation for a form, and Print unit responsible for the above-mentioned receipt issuing operation 209.

  In addition, as a matter of course, the ATM naturally has a configuration and functions such as a cash storage and discharge / acceptance mechanism, and a cash transport mechanism from the storage to the discharge / acceptance mechanism. (Not shown because of the existing technology).

  The program 202 provided in the storage unit 201 is a general information processing function and a function required as a device constituting the office center operation support system 10 of the present embodiment, that is, a twelfth function as a function of recognizing various forms. Is a program for implementing the recognition engine 110 of FIG.

  The above-described first recognition engine 110 performs a character recognition process on image data of a form obtained by the scanner unit 208, and acquires a keyword (attribute information) described in the form. However, the first recognition engine 110 and the second recognition engine 111 use different feature extraction algorithms.

For example, when the feature extraction algorithm employed in the first recognition engine 110 is a so-called superposition method, the feature extraction algorithm employed in the second recognition engine 111 is a so-called directional matching method. Assume the situation.
Of course, the feature extraction algorithm in the recognition engine is not limited to these specific examples, and may be appropriately adopted.

Note that the storage unit 201 of the high-performance ATM 200 may also hold the form identification knowledge 125, the form image data 126, the transaction identification information 127, and the acceptability knowledge 128, similarly to the tax and public money server 100. .
−−− Data structure example −−−

Next, tables used by the office center operation support system 100 of the present embodiment will be described. FIG. 4 shows an example of the form identification knowledge 125 in the present embodiment.
The form identification knowledge 125 of the present embodiment is a table storing attribute information of each form used in the financial institution.
The data structure is a collection of records in which a keyword as attribute information is associated with a handling type as a key.

  Of these, the handling type is a value used also in the reception availability knowledge 128 described later, and is a value uniquely determined for each combination of keywords described in the form. It should be noted that each handling type is linked to a predetermined value in the acceptability knowledge 128 as to whether or not the handling type is specified as a handling target in the above-described branch of the financial institution.

  The keyword is a keyword described (including printing) in a form, and specifically, a name of a place such as a prefecture or a municipal government, or a name of a tax and public money such as a municipal tax or a property tax is assumed.

FIG. 5 shows an example of the form image data 126 in the present embodiment. The form image data 126 according to the present embodiment is a table storing form image data obtained by the high-performance ATM 100 by the scanner unit 108.
The data structure is a collection of records including data such as a storage location of form image data and an image shooting date and time, using the transaction ID as a key.

FIG. 6 shows an example of the transaction identification information 127 in the present embodiment. The transaction identification information 127 of the present embodiment is a table that stores information on the handling type specified by the tax and public money server 100 in the form identification knowledge 125 with respect to the form image data of each transaction in the form image data 126 described above.
The data structure is a collection of records in which transaction ID values are associated with transaction type values specified for the transaction form using the transaction ID as a key.

FIG. 7 shows an example of the acceptability knowledge 128 according to the present embodiment. The acceptability knowledge 128 according to the present embodiment is a table that defines conditions of a form to be handled in a branch of a financial institution.
The data structure is a collection of records in which values such as a payment term, a arrears fee, and acceptability are associated with a handling type as a key.
The payment deadline defines the necessity that the payment deadline described in the form indicated by the handling type is before the elapse.
In addition, the arrearages specify the necessity of no arrearages described in the form indicated by the handling type.
The acceptability is a value that defines whether or not the above-mentioned business office accepts the form.
--- Flow example ---

  Hereinafter, the actual procedure of the office center operation support method in the present embodiment will be described with reference to the drawings. Various operations corresponding to the office center operation support method described below are realized by programs that the tax and public money server 100 and the high-performance ATM 200, which constitute the office center operation support system 10, read into a memory or the like and execute. . This program is composed of codes for performing various operations described below.

FIG. 8 is a diagram illustrating an example of a flow of the office center operation support method according to the present embodiment. Here, it is assumed that a customer operates a high-performance ATM 200 and performs a predetermined transaction procedure using a form in a normal business hours (eg, until 15:00) at a branch of a financial institution. .
In this case, the high-performance ATM 200 captures the form brought by the customer with the scanner unit 208 and acquires the form image data (s10).

  The high-performance ATM 200 inputs the form image data obtained in s10 to the first recognition engine 110, and specifies the content of the form by character recognition (s11). What is specified here is a keyword.

  Subsequently, the high-performance ATM 200 links the form image data and the keyword obtained in s10 and s11 with the transaction ID assigned to the transaction, and transmits the data to the tax and public money server 100 via the network 1 (s12).

  On the other hand, the tax and public money server 100 receives the form image data and the keyword associated with the transaction ID transmitted from the above-described high-performance ATM 200 (s13).

  Also, the tax and public money server 100 generates a record using the transaction ID as a key for the form image data obtained in s13, and stores the record in the form image data 126 (s14).

  Subsequently, the tax and public money server 100 checks the keyword obtained in s13 with each record of the form identification knowledge 125, and handles the corresponding form (in s10, the high-performance ATM 200 was set as the object of photographing the form image data). (Form identification information) is specified (s15).

  For example, if the keywords obtained in s13 are “Hokkaido”, “Sapporo”, and “Municipal tax”, the combination of these keywords is checked against each record of the form-specific knowledge 125 illustrated in FIG. The handling type “1111111111” can be specified.

  Further, the tax and public money server 100 generates a record in which the handling type specified in s15 is linked to the transaction ID obtained in s13, and stores the record in the handling type information 127 (s16).

  Subsequently, the tax and public money server 100 compares the handling type specified in s15 with each record of the reception possibility knowledge 128, identifies a record having a matching value in the “handling type” column, That is, it is determined whether or not the payment form and the delinquent money match in the form (s17).

For example, based on the handling type “1111111111” of the target form, the tax and public money server 100 determines whether the payment term is “OK” and the delinquent money is “none”, or the description of the form (keyword obtained in s13) Is determined based on
The tax and public money server 100 specifies whether or not the form can be accepted according to the result of the above determination, and notifies the high-performance ATM 200 of the specific result (s18).

  For example, as a result of the above-described determination, when the form is matched with respect to the payment deadline and the late payment, the tax and public money server 100 notifies the high-performance ATM 200 that the form can be accepted. On the other hand, as a result of the above-described determination, if the form is not matched with respect to the payment deadline and the arrears, the tax and public money server 100 notifies the high-performance ATM 200 that the form cannot be accepted.

On the other hand, the high-performance ATM 200 receives the above-described specification result of the acceptability from the tax and public money server 100, and executes a business operation corresponding to the specification result with respect to the corresponding form currently being processed (s19). When the specific result indicates “reception not possible”, the high-performance ATM 200 displays a message such as “this form cannot be handled” on the output unit 206 and ends the processing. When the specific result indicates “acceptable”, the high-performance ATM 200 executes a predetermined procedure according to the transaction.

  The tax and public money server 100 and the high-performance ATM 200 repeatedly execute each of the above-described processes of s10 to s19 for each transaction involving a form until the business hours of the business office of the financial institution end.

  Here, after the business hours of the above-mentioned financial institution (for example, after 15:00), as a closing process at the office center, the tax and public money server 100 uses, for example, the high-performance ATM 200 of each business office for one day on that day. The transaction that involves the form processing described above is set as the transaction to be closed, and the subsequent processing is performed.

  In this case, the tax and public money server 100 determines, as the transaction information to be subjected to the above-described closing processing, the transaction type obtained for the form processed in the target transaction (specified by the transaction ID, for example, “t00000001”) as the transaction identification. A record group (attribute information of each form in the form group) acquired from the information 127 and corresponding to the handling type is extracted from the form specifying knowledge 125 (s20).

  For example, if the handling type obtained for the form processed in the target transaction is “11111111111” as the information of the target transaction “t00000001” of the closing process, three records are shown as a record group corresponding to this handling type. 4 is extracted from the form identification knowledge 125 illustrated in FIG.

These three records are a record in which keyword 1 is "Hokkaido", a keyword 2 is "Sapporo", a keyword 3 is "Municipal tax", a keyword 1 is "Hokkaido", a keyword 2 is "Sapporo", and a keyword 3 is The record of “property tax”, the keyword 1 is “Hokkaido”, the keyword 2 is “Otaru City”, and the keyword 3 is a record of “municipal tax”.
Here, the record group extracted by the tax and public money server 100 is a population of characters to be recognized by the second recognition engine 111 used in the closing process.

  Subsequently, the tax and public money server 100 acquires the form image data of the transaction “t00000001” to be closed based on the information of “form image data storage destination” indicated by the form image data 126 using the transaction ID “t00000001” as a key. Then, character recognition processing is performed on the form image data by the second recognition engine 111 (s21).

  The second recognition engine 111 is a recognition engine having a different feature extraction algorithm from the first recognition engine 110 used by the high-performance ATM 200 during business hours.

  In addition, the tax and public money server 100 specifies a keyword (attribute information), which is a description content of the form, from the form image data by the character recognition processing of s21 described above (s22).

  At s22, the tax and public money server 100 obtains, for example, each keyword of "Hokkaido", "Sapporo City", and "Municipal Tax" from the form image data of the transaction ID "t00000001".

  Next, the tax and public money server 100 collates the keyword specified by each record in the record group extracted in s20 with the keyword specified in s22 (s23).

The records extracted in s20 described above include a record in which keyword 1 is “Hokkaido”, a keyword 2 is “Sapporo”, a keyword 3 is “citizen tax”, a keyword 1 is “Hokkaido”, a keyword 2 is “Sapporo”, Since the keyword 3 was a record of “property tax”, the keyword 1 was a record of “Hokkaido”, the keyword 2 was a record of “Otaru”, and the keyword 3 was a record of “municipal tax”, as a result of the comparison in s23, One record including the keywords “Hokkaido”, “Sapporo”, and “Municipal tax” obtained from the form image data of the transaction with the transaction ID “t00000001” can be specified.

As a result of the above-described comparison, if the keyword specified by each record in the record group extracted in s20 does not match the keyword specified in s22 (s24: n), the tax and public money server 100 sets the transaction to be closed. Is notified to the terminal such as the person in charge of the closing process at the office center (s25), and the process is terminated.

  On the other hand, if the keyword specified by any of the records in the record group extracted in s20 matches the keyword specified in s22 as a result of the above matching (s24: y), the tax and public money server 100 determines For the transaction to be closed, a predetermined completion process related to the closing process (for example, a status value of closing completed is given to the target transaction in a transaction management DB or the like) (s26), and the process is performed. To end.

Although the best mode for carrying out the present invention has been specifically described above, the present invention is not limited to this, and can be variously modified without departing from the gist thereof.
According to this embodiment, a huge amount of tightening work in the office center can be made efficient.

  In the office center operation support technology according to the present embodiment, the form presented by the customer is processed by the high-performance ATM during the normal business hours of the financial institution (for example, until 15:00), so that the desired transaction of the customer can be performed. Assume a situation in which procedures are being carried out. In the business hours, regarding the transaction via the form, each operation of acquiring the image data for the form by the high-performance ATM and recognizing the character from the image data (by the first recognition engine) is executed. Is described. The high-performance ATM or the tax and public money server specifies the handling type of the form (identification information of the form) by collating the keyword included in the description content recognized as described above with the form identification knowledge described above. In addition, the tax and public money server or the high-performance ATM determines and executes the business operation of the form by collating the specified handling type with the reception availability knowledge. The handling type and image data of each form obtained according to the above-described series of procedures are held at least in the above-mentioned tax and public money server.

  On the other hand, after the business hours of the above-mentioned financial institution (for example, after 15:00), as a closing process at the office center, the tax and public money server performs, for example, a transaction involving a form processing at a high-performance ATM for one day on that day. , Are set as transactions to be closed, and the handling type obtained for the corresponding form is obtained from the storage unit, and a record group (attribute information of each form in the form group) corresponding to this handling type is extracted from the form specifying knowledge. . The record group extracted here is a population of characters to be recognized by the second recognition engine used in the closing process.

  Therefore, the tax and public money server executes a recognition process on the image data of the form of the transaction to be closed by a second recognition engine different from the first recognition engine used during the above-mentioned business hours, and The keyword (attribute information) included in the description content of is specified. In addition, the tax and public money server checks the keyword specified by each record in the record group described above against the keyword specified for the form of the transaction to be closed, and determines whether the keyword matches any one of the records in the record group. With respect to the transaction (i), predetermined completion processing related to the closing processing (for example, a status value of closing completion is given to the target transaction in a DB or the like for transaction management) is executed.

At least the following will be made clear by the description in this specification. That is, in the office center operation support system of the present embodiment, the calculation unit specifies, as a result of the collation, a target transaction whose attribute information does not match any of the forms in the form group as a confirmation target by a person, A process of outputting information on the target transaction to the predetermined device may be further executed.

  According to this, unlike transactions in which the closing process has been completed by the series of processes up to the above-described collation, transactions requiring confirmation work by personnel (for example, the content of the form was erroneously recognized by the recognition engine. As a result, it is possible to efficiently identify transactions (transactions performed with incorrect contents), and to perform only such transactions as personnel confirmation work (at the office center). As a result, the enormous tightening work in the office center can be made more efficient.

  Further, in the office center operation support system according to the present embodiment, the arithmetic unit performs a recognition process on the image data of the form of the target transaction by a second recognition engine having a different feature extraction algorithm from the first recognition engine. May be executed.

  According to this, for example, even if different character recognition software is adopted as the first and second recognition engines, the difference between the two feature extraction algorithms is not large. By performing recognition, the accuracy of the tightening operation can be further improved. As a result, the enormous tightening work in the office center can be made more efficient.

  Further, in the office center operation support method of the present embodiment, the information processing system specifies, as a result of the collation, a target transaction in which the attribute information does not match any of the forms in the form group as an object to be confirmed by personnel, A process of outputting information on the target transaction to a predetermined device may be further executed.

  Further, in the office center operation support method according to the present embodiment, the information processing system recognizes the form of the target transaction with respect to the image data by a second recognition engine having a different feature extraction algorithm from the first recognition engine. The processing may be executed.

1 network 10 office center operation support system 100 tax and public money server 101 storage unit 102 program 103 memory 104 arithmetic unit 105 communication unit 125 form identification knowledge (form information)
126 Form image data 127 Transaction identification information 128 Acceptability knowledge 200 High-performance ATM
201 Storage unit 202 Program 203 Memory 204 Operation unit 205 Input unit 206 Output unit 207 Communication unit 208 Scanner unit 209 Print unit 225 Form identification knowledge (form information)
226 Form image data 227 Transaction identification information 228 Acceptance knowledge

Claims (6)

Form information describing attribute information of each form used by the financial institution, image data of the form used in the predetermined transaction at the financial institution, and the transaction identified by a predetermined recognition process for the image data of the form A storage unit for storing identification information;
Acquiring identification information obtained from the storage unit with respect to the form of the transaction to be closed, and extracting attribute information of each form in the form group corresponding to the identification information from the form information; and A second recognition engine that is different from the first recognition engine used in the recognition process, performs a recognition process on the image data of the form of the target transaction, and specifies attribute information of the form; The attribute information of each form in the group is compared with the attribute information of the form of the target transaction, and a predetermined completion process related to the closing process is executed for the target transaction in which the attribute information matches any of the forms in the form group. An operation unit that performs
An office operation support system characterized by including: The arithmetic unit includes:
As a result of the collation, a target transaction whose attribute information does not match any of the forms in the group of forms is specified as a target to be checked by personnel, and a process of outputting information on the target transaction to a predetermined device is further executed. ,
2. The office center operation support system according to claim 1, wherein: The arithmetic unit includes:
A second recognition engine having a different feature extraction algorithm from the first recognition engine executes a recognition process on the image data of the form of the target transaction.
2. The office center operation support system according to claim 1, wherein: Form information describing attribute information of each form used by the financial institution, image data of the form used in the predetermined transaction at the financial institution, and the transaction identified by a predetermined recognition process for the image data of the form An information processing system including a storage unit for holding the identification information and
A process of acquiring identification information obtained with respect to the form of the transaction to be subjected to the closing process from the storage unit, and extracting attribute information of each form in the form group corresponding to the identification information from the form information;
At the time of the target transaction, a second recognition engine different from the first recognition engine used in the recognition process executes a recognition process on the image data of the form of the target transaction to specify attribute information of the form. Processing,
The attribute information of each form in the form group is compared with the attribute information of the form of the target transaction, and for the target transaction in which the attribute information matches any of the forms in the form group, a predetermined completion process related to a closing process When,
An operation center operation support method characterized by performing the following. The information processing system,
As a result of the comparison, a target transaction in which the attribute information does not match any of the forms in the group of forms is specified as a target to be checked by personnel, and a process of outputting information on the target transaction to a predetermined device is further performed.
The operation center operation support method according to claim 4, wherein: The information processing system,
A second recognition engine having a different feature extraction algorithm from the first recognition engine executes a recognition process on the image data of the form of the target transaction,
The operation center operation support method according to claim 4, wherein:

Images