Information processing system, information processing method, and program
The system automates the verification of OCR-processed destination information by determining reliability and allowing user selection, reducing manual input and errors in address correction.
Patent Information
- Application Number
- JP2023220703
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-12-27
- Publication Date
- 2025-07-09
AI Technical Summary
Existing OCR processing systems require manual visual correction of second character strings, such as house number and building name, leading to potential errors due to operator input.
A mechanism that includes specifying transmission destination candidates through OCR processing, determining reliability, and displaying a screen for user selection to confirm and approve the destination, reducing manual input and errors.
Efficiently checks OCR processing results with reduced labor, minimizing manual corrections and errors in destination identification.
Smart Images

Figure 2025103356000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to an information processing system, an information processing method, and a program.
Background Art
[0002] In conventional slip processing operations, most of the work was manual, where the slips were transcribed visually. However, in this work, transcription errors and mistakes in misidentifying addresses were likely to occur. Therefore, in recent years, in order to improve the efficiency of slip processing operations, OCR (Optical Character Recognition) processing is often used to digitize the characters printed on the forms.
[0003] Patent Document 1 discloses a mechanism for cutting out the area of the address field of a form from the acquired image data of the form, performing OCR processing to recognize the character string in the address field, and simplifying the correction work of the character string.
Prior Art Documents
Patent Documents
[0004]
Patent Document 1
Disclosure of the Invention
Problems to be Solved by the Invention
[0005] In Patent Document 1, a postal code address that can be corrected based on an address dictionary is corrected to a correct address and output as data of the first character string, and the address following the postal code address is separated and output as data of the uncorrected second character string. However, in Patent Document 1, it only reduces the operator's work, and the second character string still requires the operator to visually check and correct it as before. Specifically, the first character string includes "prefecture", "city", "town area", etc. These character strings are likely to be correctly input from the comparison with the address dictionary. However, the second character string is the character string read by the OCR process as it is, and the operator visually checks and manually corrects whether there are errors in fine details such as "house number" and "building name" (for example, re-entering the number "24" instead of the number "29" misread by the OCR process). There is a problem that errors may occur by the operator due to the above-mentioned visual and manual corrections.
[0006] Therefore, it is desirable to reduce the manual input work by the operator and digitize the OCR-processed content without errors.
[0007] Therefore, an object of the present invention is to provide a mechanism for efficiently checking the result of OCR processing of a document with less labor.
Means for Solving the Problems
[0008] The present invention includes a specifying means for specifying a transmission destination candidate of the document by reading characters from an image of the document, a determining means for determining the reliability as the transmission destination of the document for the transmission destination candidate specified by the specifying means, and a screen generated using the reliability determined by the determining means, and a display control means for controlling to display a screen for receiving a selection of the transmission destination of the document from the transmission destination candidate.
Effects of the Invention
[0009] According to the present invention, it is possible to efficiently check the result of OCR processing of a document with less labor.
Brief Description of the Drawings
[0010]
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Embodiments for Carrying Out the Invention
[0011] FIG. 1 is a diagram showing an example of the system configuration of an information processing apparatus in the present embodiment. As shown in FIG. 1, in the present invention, a client terminal 110, a server device 120, and a printing device 130 are connected to be mutually data communicable via a network 140. The network 140 includes a LAN (Local Area Network), a WAN (Wide Area Network), or the like. The client terminal 110, the server device 120, and the printing device 130 do not necessarily need to be constantly communicable, and it is sufficient if they can communicate as needed.
[0012] FIG. 2 is a block diagram showing an example of the hardware configuration of an information processing apparatus applicable as the server device 120, the client terminal 110, and the printing device 130 of the present invention.
[0013] As shown in FIG. 2, an information processing apparatus has a CPU (Central Processing Unit) 201, a ROM (Read Only Memory) 202, a RAM (Random Access Memory) 203, a storage device 204, an input controller 205, an audio controller 206, a video controller 207, a memory controller 208, and a communication I / F controller 209 connected via a system bus 200.
[0014] The CPU 201 comprehensively controls each device and controller connected to the system bus 200.
[0015] The ROM 202 or the external memory 213 holds a BIOS (Basic Input / Output System), an OS (Operating System), which are control programs executed by the CPU 201, a computer-readable executable program for implementing this information processing method, and various necessary data (including data tables).
[0016] The RAM 203 functions as the main memory, work area, etc. of the CPU 201. When executing a process, the CPU 201 loads a program etc. necessary for the execution from the ROM 202 or the external memory 213 into the RAM 203, and realizes various operations by executing the loaded program.
[0017] The input controller 205 controls inputs from input devices such as a keyboard 210 and a pointing device such as a mouse (not shown). When the input device is a touch panel, it is assumed that the user can give various instructions by pressing (touching with a finger etc.) in accordance with icons, cursors, buttons, etc. displayed on the touch panel.
[0018] Also, the touch panel may be a touch panel capable of detecting positions touched with multiple fingers, such as a multi-touch screen.
[0019] The video controller 207 controls the display to an external output device such as the display 212. The display shall include the display of a notebook personal computer integrated with the main body. Note that the external output device is not limited to a display, and may be, for example, a projector. In addition, for the device capable of receiving the above-described touch operation, an input device is also provided.
[0020] Note that the video controller 207 can control the video memory (VRAM) for display control, and can use a part of the RAM 203 as the video memory area, or can separately provide a dedicated video memory.
[0021] The memory controller 208 controls access to the external memory 213. As the external memory, an external storage device (hard disk) that stores a boot program, various applications, font data, user files, edited files, and various data, etc., a flexible disk (FD), or a compact flash (registered trademark) memory connected via an adapter to the PCMCIA card slot can be used.
[0022] The communication I / F controller 209 is connected to and communicates with an external device via a network, and executes communication control processing on the network. For example, communication using TCP / IP, a telephone line such as ISDN, and communication using a 4G line or 5G line of a mobile phone are possible.
[0023] Still, the CPU 201 enables display on the display 212 by executing an outline font expansion (rasterization) process on, for example, the display information area in the RAM 203. In addition, the CPU 201 enables user instructions with a mouse cursor (not shown) on the display 212.
[0024] Figure 3 is a flowchart showing an example of the transmission destination information display process in the embodiment of the present invention.
[0025] In step S301, the server device 120 acquires an image of a document (such as an invoice or a purchase order) from the client terminal 110 or the printing device 130. The image may be one scanned by the printing device 130, one acquired by the client terminal via email or the like, or one captured by a camera-equipped mobile terminal, among others.
[0026] In step S302, the server device 120 performs OCR processing on the image acquired in step S301 and obtains a character string.
[0027] In step S303, the client terminal 110 acquires the character string obtained by the OCR processing from the server device 120.
[0028] In step S304, candidates for the destination are identified. From the character string acquired in step S303, candidates for the destination of the document are identified. For this, known techniques may be used. For example, by using a named entity extraction technique, which is a mechanism for extracting proper nouns and named expressions from natural text, character strings indicating the destination such as company names, names, and addresses including prefecture names can be identified.
[0029] In step S305, the client terminal 110 determines whether candidates for the destination could be identified by the OCR processing. If not, it proceeds to step S310. If so, it proceeds to step S306.
[0030] In step S306, it is determined whether there is one candidate for the destination identified in step S305. If there is one, it proceeds to step S308. If not, it proceeds to step S307.
[0031] In step S307, the likelihood (reliability) as a destination is evaluated based on the amount of information of a plurality of destination candidates. For example, it is possible to evaluate the likelihood as a destination using the amount of information, such as whether only the company name is described or whether information such as an address, a telephone number, or an email address is also described. Also, the location where it is described in the document (description location) may be used. For example, if it is described in the upper left corner of the first page of the document, it can be evaluated that the possibility is high, and if it is described in the middle or at the end of the text, it can be evaluated that the possibility is low. Also, evaluation may be performed by quantifying the amount of information and the description location. Not limited to the amount of information and the description location, other information may be used for evaluation.
[0032] In step S308, the client terminal 110 refers to the destination information master (described later in FIG. 6) in the server device 120, and determines whether or not the plurality of destination candidates evaluated in step S307 are registered in the destination information master. At this time, the character matching rate between the destination information in the master and the destination candidate may be calculated.
[0033] In step S309, the ranking of the candidates is determined from the evaluation of the destination candidates in step S307. Based on the evaluation of the likelihood as a destination of the destination candidates, candidates with a higher likelihood of being the destination have a higher ranking as candidates. At this time, a process of reflecting the master collation result in step S308 in the ranking as a candidate may be performed. For example, the character matching rate between the destination information in the master and the destination candidate may be reflected in the ranking. Alternatively, for the evaluation result quantified in step S307, when the destination candidate is registered in the destination information master, a process of multiplying by an arbitrary value or adding points may be performed.
[0034] In step S310, when the destination candidate cannot be specified, a message indicating that "the destination candidate could not be specified by OCR processing" is displayed. When even one destination candidate can be specified, a message indicating that "〇 destination candidates have been specified by OCR processing" is displayed, and the process ends.
[0035] Figure 4 is a flowchart showing an example of the destination selection and approval process in an embodiment of the present invention.
[0036] In step S401, destination candidates are displayed on the destination information confirmation screen (described later with reference to FIG. 5). At this time, the display is based on the ranking of the destination information in step S309 of FIG. 3.
[0037] In step S402, the user is accepted to select a candidate that the user wants to determine as the destination from among the destination candidates in step S401.
[0038] In step S403, the destination candidate selected by the user in step S402 is set as the destination.
[0039] In step S404, the data with the destination set is sent to the approver arbitrarily set by the user, and an approval request from the approver is accepted.
[0040] In step S405, it is determined whether the approver arbitrarily set by the user has approved the data with the destination set. If approved, the process proceeds to step S406; if not approved, the process proceeds to step S407.
[0041] In step S406, a process of sending the data approved in step S405 to the destination is performed. Specifically, the data is sent by sending it to the email address associated with the destination set in S403 or by sending it to the storage folder associated with the destination.
[0042] In step S407, the data of the document not approved in step S405 is returned to the user who is the sender, and the process ends.
[0043] Figure 5 is a diagram showing an example of a destination information confirmation screen in an embodiment of the present invention.
[0044] The confirmation screen 501 is a screen for confirming the preview of the document and the OCR processing result for each document.
[0045] The preview screen 502 displays the image of the document acquired in step S301. With this preview screen, the user can check the destination information while confirming the content described in the actual document. This can prevent misplacement of forms.
[0046] The form information display screen 503 is a screen where the user can select correct information for each item of the form.
[0047] The destination candidate selection reception field 504 is an item that displays the destination candidates identified by the process of the present invention in a selectable manner and receives the selection of the destination from the user. It shall be displayed in the order of the evaluation results in step S309 (the order of the likelihood as a destination). Also, it shall be displayed in a form that can distinguish between the destination candidates registered in the master information and those not registered. Specifically, it can be displayed in a distinguishable manner by changing the background color or, as shown in FIG. 5, by stating that the candidate is not registered in the master information. Also, the shade of the color may be changed according to the matching rate with the master information. Also, candidates with no matching information in the master may be controlled not to be displayed. By having such a function, the user can clearly judge which candidate is reliable as information at a glance.
[0048] FIG. 6 is a diagram showing an example of a destination information master in an embodiment of the present invention.
[0049] The destination master data 601 holds information such as the company name, address, and phone number of the destination. In step S309, the information in this master data is searched to check if there is a match. If item names, etc. that are frequently handled in addition to the destination information are registered in the master data, the registered information can also be made to be confirmed and selected after OCR processing.
[0050] As described above, by changing the display form based on the reliability of information, it becomes possible to efficiently check the items of the form without manual input work after the OCR processing of the form data. By devising the order and color display of the selection candidates, the user can immediately determine which candidate is correct as the destination information. Furthermore, there is no need for the user to manually correct the misdetected characters, and confirmation and selection can be performed at once with the candidate pull-down, enabling efficient form confirmation work.
[0051] As described above, the embodiments have been shown. However, the present invention can take an embodiment as, for example, a system, an apparatus, a method, a program, or a recording medium. Specifically, it may be applied to a system composed of a plurality of devices, or may be applied to an apparatus consisting of a single device.
[0052] Also, the program in the present invention is a program that can be executed by a computer according to the processing methods of the flowcharts shown in FIGS. 3 and 4, and the storage medium of the present invention stores a program that can be executed by a computer according to the processing methods of FIGS. 3 and 4. Note that the program in the present invention may be a program for each processing method of each device in FIGS. 3 and 4.
[0053] Needless to say, the object of the present invention is also achieved by supplying a recording medium recording a program that realizes the functions of the above-described embodiments to a system or an apparatus, and causing a computer (or a CPU or MPU) of the system or apparatus to read and execute the program stored in the recording medium.
[0054] In this case, the program itself read from the recording medium realizes the novel functions of the present invention, and the recording medium recording the program constitutes the present invention.
[0055] As a recording medium for supplying a program, for example, a flexible disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a DVD-ROM, a magnetic tape, a non-volatile memory card, a ROM, an EEPROM, a silicon disk, etc. can be used.
[0056] In addition, by executing the program read by the computer, not only the functions of the above-described embodiments are realized, but also based on the instructions of the program, an OS (operating system) or the like operating on the computer performs part or all of the actual processing, and it goes without saying that the case where the functions of the above-described embodiments are realized by that processing is also included.
[0057] Furthermore, after the program read from the recording medium is written into the memory provided in the function expansion board inserted into the computer or the function expansion unit connected to the computer, based on the instructions of the program code, the CPU or the like provided in the function expansion board or the function expansion unit performs part or all of the actual processing, and it goes without saying that the case where the functions of the above-described embodiments are realized by that processing is also included.
[0058] In addition, the present invention may be applied to a system composed of a plurality of devices or to an apparatus composed of a single device. Needless to say, the present invention is also applicable when it is achieved by supplying a program to a system or an apparatus. In this case, by reading the recording medium storing the program for achieving the present invention into the system or the apparatus, the system or the apparatus can enjoy the effects of the present invention.
[0059] Furthermore, by downloading and reading the program for achieving the present invention from a server, a database, etc. on the network by a communication program, the system or the apparatus can enjoy the effects of the present invention. Note that all configurations combining the above-described embodiments and their modifications are also included in the present invention.
Explanation of Reference Numerals
[0060] 110 Client terminal 120 Server device 130 Printing device 140 Network
Claims
1. Specific means for identifying candidate destinations for the document by reading characters from an image of the document; Determining means for determining the reliability as the destination of the document for the candidate destinations identified by the specific means; Display control means for controlling to display a screen generated using the reliability determined by the determining means, the screen being for receiving a selection of the destination of the document from the candidate destinations; An information processing apparatus characterized by comprising the above.
2. The information processing apparatus according to claim 1, wherein the display control means controls to arrange the candidate destinations in descending order of the reliability on the condition that the specific means identifies a plurality of candidate destinations.
3. The information processing apparatus according to claim 2, wherein the determining means determines the reliability using at least one of the type of the candidate destination or the position of the candidate destination described in the document.
4. The information processing apparatus according to claim 1, wherein the display control means further controls the display based on the coincidence rate between the candidate destinations identified by the specific means and pre-registered candidate destinations.
5. The information processing apparatus according to claim 4, wherein the display control means controls to display the screen such that the candidate destinations that match between the candidate destinations identified by the specific means and pre-registered candidate destinations can be identified.
6. The information processing apparatus according to claim 5, wherein the display control means controls to display the screen not including the candidate destinations on the condition that the candidate destinations identified by the specific means do not match the pre-registered candidate destinations.
7. The information processing apparatus according to claim 1, wherein the display control means controls to display the screen including the image of the document.
8. The information processing apparatus according to claim 1, wherein the display control means further generates a screen for receiving a selection as to whether to permit transmission of the document to the destination of the document determined by receiving a selection via the screen.
9. A specific step in which the specific means identifies candidate destinations for the document by reading characters from an image of the document; A determining step in which the determining means determines the reliability as the destination of the document for the candidate destinations identified by the specific means; A display control step in which a control means controls to display a screen generated using the reliability determined by the determination means, the screen being for receiving a selection of a transmission destination of the document from the transmission destination candidates. An information processing apparatus characterized by having the above.
10. A program for causing a computer to function as each of the means according to any one of Claims 1 to 8.
Citation Information
Patent Citations
Form recognition program and form recognition device
JP2022122643A