Information processing device and program
The information processing device facilitates error tracing and correction in OCR processes by allowing users to review and validate each stage post-completion, improving error identification and correction efficiency.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- FUJIFILM BUSINESS INNOVATION CORP
- Filing Date
- 2022-03-23
- Publication Date
- 2026-04-21
AI Technical Summary
Existing OCR systems struggle to identify the specific process causing errors in the series of operations from character information reading to digitization, making it difficult to trace and correct errors effectively.
An information processing device that allows users to trace back and review the appropriateness of each stage of the OCR process after completion, displaying individual process progress and enabling user input to correct or modify intermediate data, with criteria-based validation of correction and conversion candidates.
Enables retrospective review of OCR processes to identify and correct errors efficiently, providing detailed process understanding and validation of correction candidates based on similarity and regularity criteria, enhancing error identification and correction.
Smart Images

Figure 0007848537000001 
Figure 0007848537000002 
Figure 0007848537000003
Abstract
Description
Technical Field
[0001] The present invention relates to an information processing apparatus and a program.
Background Art
[0002] Techniques for reading and digitizing character information recorded on a medium such as paper are known (for example, Patent Documents 1 and 2).
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Patent Document 2
Summary of the Invention
Problems to be Solved by the Invention
[0004] In such a technique, a series of multiple processes are executed from the reading of character information by OCR (Optical Character Recognition / Reader) until the final data is obtained, and at some stages of the multiple processes, it is determined whether the process is appropriate and corrected as necessary. However, in a series of multiple processes from character information to digitization, after the data of the processing result is obtained, if there is an error in the obtained processing result, it is difficult to identify the process that caused the error among the series of multiple processes.
[0005] An object of the present invention is to be able to confirm the appropriateness of the processing at each stage by tracing back a series of multiple processes after the entire processing is completed, as compared with a configuration that individually determines the appropriateness of the processing at each stage of a series of multiple processes in OCR.
Means for Solving the Problems
[0006] The invention described in claim 1 comprises a processor, the processor sequentially executes two or more processes as a process of reading character information and converting it into data, outputs the processing result, accepts user input on the output processing result, and, in response to the input, processes the progress of each of the two or more processes that led to the processing result. 、 Display device For each of those processes individually display The system then accepts further user input and transitions from a screen displaying the progress of each individual process shown on the display device to a screen displaying the progress of the process immediately preceding or immediately following the said process. This is an information processing device characterized by the following: Claim 2 The invention described herein is an information processing apparatus according to claim 1, characterized in that, in displaying the progress of the process, the processor displays the progress of the process which is presumed to be problematic based on predetermined criteria in a manner that can be distinguished from the progress of other processes. Claim 3 The invention described is Equipped with a processor, The aforementioned processor, As a process for reading character information and converting it into data, two or more processes are sequentially executed, including at least one of a correction process for correcting the intermediate data obtained in the preceding process, and a conversion process for converting the intermediate data obtained in the preceding process, and the processing result is output. User operations on the output processing result are accepted, and in response to the operations, the progress of each process in the two or more processes leading to the processing result is displayed on a display device, one or more correction candidates are displayed in the display of the progress of the correction process, one or more conversion candidates are displayed in the display of the progress of the conversion process, and the validity of the correction candidates and conversion candidates, which is judged based on predetermined criteria, is displayed in the display of the progress of the correction process and the conversion candidates. The information processing device is characterized in that, as the correction process, it performs a correction performed by the processor in accordance with predetermined rules, and a correction that accepts user input and replaces the intermediate data string with the input string, and identifies the validity of the correction candidate based on the similarity between the intermediate data obtained in the preceding process and the correction candidate in the correction, and the similarity between the correction candidate and the input string in the correction. Claim 4 The invention described herein is characterized in that the processor identifies the validity of the proposed modification based at least on the similarity between the proposed modification and the intermediate data obtained in the preceding processing, 3 This is the information processing device described above. Claim 5 The invention described is Equipped with a processor, The aforementioned processor, As a process for reading character information and converting it into data, two or more processes are sequentially executed, including at least one of a correction process for correcting the intermediate data obtained in the preceding process, and a conversion process for converting the intermediate data obtained in the preceding process, and the processing result is output. User operations on the output processing result are accepted, and in response to the operations, the progress of each process in the two or more processes leading to the processing result is displayed on a display device, one or more correction candidates are displayed in the display of the progress of the correction process, one or more conversion candidates are displayed in the display of the progress of the conversion process, and the validity of the correction candidates and conversion candidates, which is judged based on predetermined criteria, is displayed in the display of the progress of the correction process and the conversion candidates. The information processing device is characterized by selecting the conversion candidates from a data set based on a predetermined classification, and determining the validity of the conversion candidates based on the degree of conformity to the regularity extracted from the data set included in the classification of the conversion candidates. Claim 6The invention described herein is characterized in that the processor displays the progress of the processing in the amendment and the progress of the processing in the correction in a way that allows for identification, claim 3 This is the information processing device described above. Claim 7 The invention described above provides a computer with a function to sequentially execute two or more processes as a process of reading character information and converting it into data, and output the processing result; a function to accept user input on the outputted processing result; and a function to process the progress of each of the two or more processes leading to the processing result in response to the operation. 、 Display device For each of those processes individually Display function, A function that further accepts user input and transitions from a screen displaying the progress of each individual process shown on the display device to a screen displaying the progress of the process immediately preceding or immediately following the said process, of Control processing including This program is characterized by its ability to achieve certain goals. The invention described in claim 8 provides a computer with a function to sequentially execute two or more processes, including at least one of a correction process for correcting intermediate data obtained in a preceding process and a conversion process for converting intermediate data obtained in a preceding process, as a process for reading character information and converting it into data, and outputting a processing result; a function to accept user input on the outputted processing result; a function to display the progress of each of the two or more processes leading to the processing result on a display device in response to the input; a function to display one or more correction candidates in the display of the progress of the correction process, and a function to display one or more conversion candidates in the display of the progress of the conversion process. The program is characterized by implementing a control process that includes: a function to display the validity of the correction candidates and conversion candidates, which is determined based on predetermined criteria, in the display of the progress of the correction process and the conversion process; a function to perform corrections performed by the processor according to predetermined rules, and corrections that accept user input and replace the intermediate data string with the input string; and a function to identify the validity of the correction candidates based on the similarity between the intermediate data obtained in the preceding process and the correction candidates in the correction, and the similarity between the correction candidates and the input string in the correction. The invention described in claim 9 is a program that enables a computer to implement a control process that includes: a function to sequentially execute two or more processes, including at least one of a correction process for correcting intermediate data obtained in a preceding process and a conversion process for converting the intermediate data obtained in a preceding process, as a process for reading character information and converting it into data, and outputting a processing result; a function to accept user operations on the outputted processing result; a function to display the progress of each of the two or more processes leading to the processing result on a display device in response to the operation; a function to display one or more correction candidates in the display of the progress of the correction process and one or more conversion candidates in the display of the progress of the conversion process; a function to display the validity of the correction candidates and conversion candidates, which is judged based on predetermined criteria, in the display of the progress of the correction process and the conversion process; a function to select the conversion candidates from a data group based on a predetermined classification; and a function to specify the validity of the conversion candidates based on the degree of conformity to the regularity extracted from the data group included in the classification of the conversion candidates. [Effects of the Invention]
[0007] According to the present invention of claim 1, compared to a configuration in which the appropriateness of a process is determined individually at each stage of a series of processes, it is possible to provide an information processing device that, after the entire process is completed, allows for retrospectively reviewing the series of processes and confirming the appropriateness of each stage of the process. Furthermore, compared to a configuration that displays the entirety of two or more processes in a list, it is possible to present more information about the progress of each individual process. Also, compared to a configuration that transitions to the screen of a process selected from a list of processes, it becomes easier to understand the chronological relationship between the source and destination processes. Claim 2 According to the present invention, compared to a configuration that displays the progress of each process in the same manner, it becomes easier to visually recognize the parts in a series of processes where problems are presumed to exist. Claim 3 According to the present invention, Compared to a configuration where the appropriateness of each stage of a series of processes is judged individually, this provides an information processing device that allows the appropriateness of each stage of the series of processes to be checked retrospectively after the entire process is completed. Compared to configurations that only display the results of corrections and conversions, this configuration allows users to understand the processing steps in more detail. Furthermore, compared to configurations that do not indicate validity in the display of candidates, it becomes easier to visually identify problematic candidates. Also, compared to configurations that determine validity without using the similarity relationship with the previous processing result and the corrected string, it becomes possible to determine whether the correction process is appropriate or not. Claim 4 According to the present invention, the appropriateness of the modification process can be determined compared to a configuration that determines appropriateness without using the similarity relationship with the processing result of the preceding step. Claim 5 According to the present invention, Compared to a configuration that individually judges the appropriateness of each stage of a series of processes, this information processing device allows users to review the entire process after completion and verify the appropriateness of each stage. Furthermore, compared to a configuration that only displays the results of correction and conversion, it allows users to understand the processing process in more detail. Additionally, compared to a configuration that does not indicate validity in the display of candidates, it becomes easier to visually identify problematic candidates.Compared with a configuration that determines validity without using the regularity extracted from the data group included in the conversion candidate classification, it is possible to determine the suitability of the conversion candidate based on the relationship between each data in the data group. Claim 6 According to the present invention of claim, compared with a configuration that displays the correction by the processor and the correction by the user in the same manner, it is possible to distinguish and grasp the processing by the processor and the processing by the user. Claim 7 According to the present invention of claim, compared with a configuration that determines the suitability of processing individually at each stage of a series of processing, it is possible to provide a program that allows the suitability of processing at each stage to be confirmed by tracing back a series of processing after the entire processing is completed. Furthermore, compared to a configuration that displays the entirety of two or more processes in a list, it is possible to present more information about the progress of each individual process. Also, compared to a configuration that transitions to the screen of a process selected from a list of processes, it becomes easier to understand the chronological relationship between the source and destination processes. According to the present invention of claim 8, compared to a configuration in which the appropriateness of processing is judged individually at each stage of a series of processes, a program is provided that allows the user to review the entire process after it has been completed and check the appropriateness of processing at each stage. Furthermore, compared to a configuration in which only the results of correction and conversion are displayed, the user can understand the process of processing in more detail. Furthermore, compared to a configuration in which the validity of candidates is not indicated, it becomes easier to visually identify problematic candidates. Furthermore, compared to a configuration in which the appropriateness of processing is judged without using the similarity relationship with the results of the previous processing stage and the corrected string, it is possible to determine the appropriateness of the correction process. According to the present invention of claim 9, compared to a configuration in which the appropriateness of processing is judged individually at each stage of a series of processes, a program can be provided that allows the user to review the entire process after it has been completed and check the appropriateness of processing at each stage. Furthermore, compared to a configuration in which only the results of correction and conversion are displayed, the user can understand the process of processing in more detail. Furthermore, compared to a configuration in which the appropriateness of candidates is not indicated, it becomes easier to visually identify problematic candidates. Furthermore, compared to a configuration in which the appropriateness of conversion candidates is judged without using regularities extracted from the data set included in the classification of conversion candidates, the appropriateness of conversion candidates can be judged based on the relationships between each data in the data set.
Brief Description of Drawings
[0008] [Figure 1] It is a diagram showing an example of the overall configuration of an information processing system including a user terminal as an information processing device to which the present embodiment is applied. [Figure 2] It is a diagram showing an example of the hardware configuration of a user terminal as an information processing device to which the present embodiment is applied. [Figure 3] It is a diagram showing an example of the hardware configuration of a management server as an information processing device to which the present embodiment is applied. [Figure 4] It is a diagram showing an example of the functional configuration of the control unit of the user terminal. [Figure 5] It is a diagram showing an example of the functional configuration of the control unit of the management server when the management server performs part of the processing of the user terminal. [Figure 6] It is an example of a flowchart showing the processing flow of the user terminal. [Figure 7] It is an example of a flowchart showing the processing flow of the management server when the management server performs part of the processing of the user terminal. [Figure 8] It is a diagram showing a specific example of a service to which the present invention is applied. [Figure 9] This figure shows a specific example of a user interface that is displayed as a display device on the user terminal's display unit. [Figure 10] This figure shows a specific example of a user interface that is displayed as a display device on the user terminal's display unit. [Figure 11] This figure shows a specific example of a user interface that is displayed as a display device on the user terminal's display unit. [Figure 12] This figure shows a specific example of a user interface that is displayed as a display device on the user terminal's display unit. [Figure 13] This figure shows a specific example of a user interface that is displayed as a display device on the user terminal's display unit. [Figure 14] This figure shows a specific example of a user interface that is displayed as a display device on the user terminal's display unit. [Modes for carrying out the invention]
[0009] Embodiments of the present invention will be described in detail below with reference to the attached drawings. (Configuration of the information processing system) Figure 1 shows an example of the overall configuration of an information processing system 1, which includes user terminals 10-1 to 10-n (where n is an integer value of 2 or more) as an information processing device to which this embodiment is applied. The information processing system 1 is configured by connecting user terminals 10-1 to 10-n and a management server 30 via a network 90. The network 90 is, for example, a LAN (Local Area Network), the Internet, etc. When it is not necessary to explain each of the user terminals 10-1 to 10-n individually, they are collectively referred to as user terminal 10.
[0010] The user terminal 10 is an information processing device such as a personal computer, smartphone, or tablet that is operated by the user. The user terminal 10 performs a series of processes from reading character information to converting that character information into data (hereinafter referred to as "OCR processing"). OCR processing consists of two or more processes. Each process that makes up OCR processing has a defined definition, and each process is executed based on that definition.
[0011] The user terminal 10 outputs the individual processing results of each process that constitutes the executed OCR process, and displays the outputted information as "processing result information" on the user interface. When the user performs an input operation on the processing result information, the user interface displays the progress of each individual process in each process leading to the processing result as "progress information" according to the input information. In other words, the processing result information is information that outputs the processing results of each of the two or more processes that constitute the OCR process individually, regardless of the preceding and succeeding processing results, whereas the progress information is information that outputs the processing results of each of the two or more processes that constitute the OCR process as an overall flow in which the preceding and succeeding processing results are related.
[0012] Examples of two or more processes included in OCR processing include processes performed by multiple users, processes performed by multiple CPUs (Central Processing Units) (see explanation of control unit 11 in Figure 2), and processes performed by a user and a CPU. Examples of two or more processes performed by multiple users include so-called double-checking where two or more processes are performed sequentially by different users, where two or more users each perform verification or correction processes, and where two or more users each perform verification or correction processes simultaneously and then perform a comparison.
[0013] Furthermore, among the processes included in OCR processing, two or more processes performed by multiple CPUs include, for example, cases where OCR processing based on a first dictionary and OCR processing based on a second dictionary are performed separately. Also, among the processes included in OCR processing, two or more processes performed by the user and the CPU include, for example, a combination of processing by the CPU and processing by the user. In this sense of "combination," an example would be a combination of correction control processing by the CPU and confirmation and correction processing by the user.
[0014] The management server 30 is an information processing device that acts as a server for managing the entire information processing system 1. The management server 30 can perform some of the above-mentioned processes performed by the user terminal 10. For example, when the management server 30 performs some of the OCR processing, it performs processes such as converting the information read by the user terminal 10 (hereinafter referred to as "read information") into data, and sending the individual processing results of two or more processes performed as processing result information to the user terminal 10.
[0015] Furthermore, when the management server 30 performs a portion of the OCR processing, it generates progress information according to the input information received from the user terminal 10 for processing result information. In this way, when the management server 30 performs a portion of the above-mentioned processing by the user terminal 10, information entered into the user terminal 10 by the user's input operation, information output as a result of processing by the user terminal 10 and the management server 30, and information acquired from external sources (not shown) are transmitted and received between the management server 30 and the user terminal 10. Details of these processes performed by the management server 30 will be described later.
[0016] The configuration of the information processing system 1 described above is merely an example; the information processing system 1 as a whole only needs to have the functionality to implement the processing described above. For this reason, some or all of the functions that implement the processing described above may be shared or collaborated within the information processing system 1. That is, some or all of the functions of the user terminal 10 may be functions of the management server 30, or some or all of the functions of the management server 30 may be functions of the user terminal 10. Furthermore, some or all of the functions of the user terminal 10 and the management server 30 that constitute the information processing system 1 may be transferred to other servers, etc., not shown in the diagram. This will facilitate processing for the information processing system 1 as a whole, and also allow for mutual complementarity of processing.
[0017] (User terminal hardware configuration) Figure 2 shows an example of the hardware configuration of a user terminal 10, which is an information processing device to which this embodiment is applied. The user terminal 10 includes a control unit 11, a memory 12, a storage unit 13, a communication unit 14, an operation unit 15, a display unit 16, and a reading unit 17. These units are connected by a data bus, an address bus, a PCI (Peripheral Component Interconnect) bus, etc.
[0018] The control unit 11 is a processor that controls the functions of the user terminal 10 through the execution of various software such as the OS (operating system) and application software. The control unit 11 is composed of, for example, a CPU. The memory 12 is a storage area that stores various software and data used for its execution, and is used as a work area during calculations. The memory 12 is composed of, for example, RAM (Random Access Memory).
[0019] The storage unit 13 is a storage area that stores input data for various software and output data from various software. The storage unit 13 is composed of, for example, an HDD (Hard Disk Drive), an SSD (Solid State Drive), or semiconductor memory used to store programs and various setting data. The storage unit 13 stores various information as databases, such as a string DB 131 which stores various strings and conversion tables, and a processing result DB 132 which stores processing result information.
[0020] The communication unit 14 transmits and receives data between the management server 30 and the outside world via the network 90. The operation unit 15 consists of, for example, a keyboard, mouse, mechanical buttons, and switches, and accepts input operations. The operation unit 15 also has operation images displayed on the display unit 16. The operation unit 15 also includes a touch sensor that forms a touch panel integrally with the display unit 16. The display unit 16 consists of, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display used for displaying information, and displays image and text data. The display unit 16 displays a user interface as a display device.
[0021] The reading unit 17 reads images recorded on a medium such as paper (for example, a form). The reading unit 17 is composed of, for example, a CCD scanner that reduces the reflected light from light irradiated onto the document from a light source using a lens and receives it with a CCD (Charge Coupled Devices), or a CIS scanner that receives the reflected light from light sequentially irradiated onto the document from an LED light source with a CIS (Contact Image Sensor).
[0022] (Management server hardware configuration) Figure 3 shows an example of the hardware configuration of a management server 30, which is an information processing device to which this embodiment is applied. The management server 30 has hardware configurations corresponding to the control unit 11, memory 12, storage unit 13, communication unit 14, operation unit 15, and display unit 16 of the user terminal 10 hardware configuration shown in Figure 2. These units are connected by a data bus, address bus, PCI bus, etc.
[0023] In other words, the management server 30 has a control unit 31 composed of a processor such as a CPU, a memory 32 composed of a storage area such as RAM, and a storage unit 33 composed of a storage area such as an HDD, SSD, or semiconductor memory. The storage unit 33 stores various information as a database, such as a string DB 331 which stores various strings and conversion tables, and a processing result DB 332 which stores processing result information. It also has a communication unit 34 which sends and receives data to and from user terminals 10 and external parties via the network 90. Furthermore, the management server 30 has an operation unit 35 composed of a keyboard, mouse, touch panel, etc., and a display unit 36 composed of a liquid crystal display or organic EL display, etc.
[0024] (Functional configuration of the user terminal's control unit) Figure 4 shows an example of the functional configuration of the control unit 11 of the user terminal 10. The control unit 11 of the user terminal 10 functions as follows: OCR control unit 101, processing result acquisition unit 102, input operation reception unit 103, progress information generation unit 104, candidate extraction unit 105, validity determination unit 106, display control unit 107, and transmission / reception control unit 108.
[0025] The OCR control unit 101 controls the execution of the OCR process. As described above, the OCR process consists of two or more processes. Examples of processes that constitute the OCR process include processes performed by multiple users, processes performed by multiple CPUs, and processes performed by users and CPUs. For example, the process of correcting intermediate data obtained as a result of the preceding process (hereinafter referred to as the "correction process") and the process of converting the intermediate data obtained as a result of the preceding process into other data using a database (hereinafter referred to as the "conversion process") are both examples of processes that constitute the OCR process.
[0026] The OCR control unit 101 controls the correction process by performing corrections that the CPU performs according to predetermined rules, and by performing corrections that replace the string of intermediate data obtained as a result of the preceding process with the string entered by the user's input operation. The OCR control unit 101 also controls the modification of the definitions and processing results used in the OCR process based on the user's input operation. In this case, the OCR control unit 101 can control the process to re-execute the OCR process from the processing related to the modification after the definitions and processing results used in the OCR process have been modified in response to the user's input operation.
[0027] The processing result acquisition unit 102 acquires the individual processing results of two or more processes that constitute the OCR process, which are executed under the control of the OCR control unit 101. The processing results include information consisting of multiple items. The processing results acquired by the processing result acquisition unit 102 are stored and managed in a database as processing result information. Specifically, the acquired processing result information is stored and managed in the processing result DB 132 of the storage unit 13 (see Figure 2).
[0028] The input operation reception unit 103 receives user input operations. User input operations include, for example, touch operations with a finger or mouse operations. The input operation reception unit 103 also receives input operations to launch application software and display the user interface on the display unit 16 (see Figure 2).
[0029] Furthermore, the input operation reception unit 103 receives user input operations regarding the processing result information displayed on the user interface. For example, the input operation reception unit 103 receives user input operations to select information on one or more items from among the multiple items included in the processing result information that are to be used to generate progress information. The input operation reception unit 103 also receives user input operations regarding the progress information of the processes that constitute the OCR process, which are displayed on the user interface. In addition, the input operation reception unit 103 receives input operations to modify the definitions used in each process that constitutes the OCR process and the results of the processes.
[0030] The progress information generation unit 104 generates progress information for two or more processes leading to the processing result, according to the input information received by the input operation reception unit 103. The candidate extraction unit 105 extracts one or more correction candidates from the information stored in the database to be displayed on the user interface as progress information of the correction process. The candidate extraction unit 105 also extracts one or more conversion candidates from the information stored in the database to be displayed on the user interface as progress information of the conversion process. For example, the candidate extraction unit 105 extracts one or more correction candidates or conversion candidates from the information stored in the string DB 131 of the storage unit 13.
[0031] The validity determination unit 106 determines the validity of correction candidates or conversion candidates when the candidate extraction unit 105 extracts them. The validity of correction candidates or conversion candidates is determined based on predetermined criteria. Criteria for determining the validity of correction candidates include, for example, a similarity score indicating the degree of similarity between the correction candidate and the intermediate data obtained in the preceding process, or a similarity score indicating the degree of similarity with the string entered by the user for correction. Criteria for determining the degree of validity of conversion candidates include, for example, a value indicating the degree of conformity to the regularity extracted from the data group included in the classification of the conversion candidates.
[0032] The display control unit 107 controls the display of various information on the display unit 16 (see Figure 2). For example, the display control unit 107 controls the display of the user interface of the display unit 16. The user interface displayed on the display unit 16 can be displayed by launching dedicated application software for the user that is pre-installed on the user terminal 10. The user interface can also be displayed by accessing a dedicated website for the user.
[0033] The display control unit 107 controls the display of processing result information acquired by the processing result acquisition unit 102 and stored in the database on the user interface. Specifically, the display control unit 107 controls the display of individual processing result information for the processes constituting the OCR process, which is stored in the processing result DB 132 of the storage unit 13, on the user interface. The processing result information displayed on the user interface includes information consisting of multiple items. A specific example of the user interface in which the processing result information is displayed will be described later with reference to Figure 9.
[0034] Furthermore, the display control unit 107 controls the display of the progress information generated by the progress information generation unit 104 on the user interface. Specifically, the display control unit 107 controls the display of a list of progress information for some or all of the two or more processes that constitute the OCR process. The display control unit 107 also controls the display of progress information for processes related to the item selected by the user's input operation on the user interface. In this case, the display control unit 107 can control the display of progress information for processes not related to the selected item on the user interface. Specific examples of the user interface in which progress information for individual processes is displayed in a list will be described later with reference to Figures 10 and 11.
[0035] Furthermore, the display control unit 107 can control the display of progress information for each of the two or more processes leading to the processing result, individually for each process. In this case, the display control unit 107 can further accept user input and control the transition from a screen displaying the progress of each individual process shown on the user interface to a screen displaying the progress of the process immediately preceding or immediately following each individual process.
[0036] Furthermore, the display control unit 107 controls the display of the progress of processes that are presumed to have problems based on predetermined criteria, in a manner that is distinguishable from the progress of other processes, as progress information. The "predetermined criteria" are not particularly limited and may be, for example, thresholds set by user input operations. The display control unit 107 also controls the display of one or more candidate strings for correction (hereinafter referred to as "correction candidates") on the user interface as progress information for correction processes. Furthermore, for example, the display control unit 107 controls the display of one or more candidate strings for conversion (hereinafter referred to as "conversion candidates") on the user interface as progress information for conversion processes. The correction candidates and conversion candidates are extracted by the candidate extraction unit 105, which will be described later, based on predetermined criteria.
[0037] The display control unit 107 controls the display on the user interface to show an indication of the validity of the correction candidate or conversion candidate identified by the validity identification unit 106. The form of the "indication of validity" is not particularly limited and can be any form of display that allows the user to recognize the validity of the conversion candidate at a glance. For example, a form of display such as color or numerical value can be used. In addition, the display control unit 107 controls the display on the user interface in a manner that allows identification of the progress of the correction process, including the progress of the correction control process by the CPU and the progress of the correction process that replaces the input string with the input string entered by the user.
[0038] The transmission / reception control unit 108 controls the transmission and reception of various information via the communication unit 14 (see Figure 2). The transmission / reception control unit 108 functions when the management server 30 or another external server (not shown) performs part of the processing of the user terminal 10. For example, suppose the user terminal 10 performs the process of reading character information formed on a medium such as paper, and the management server 30 performs the process of converting the character information read by the user terminal 10 into data. In this case, the transmission / reception control unit 108 controls the transmission of the character information read by the OCR control unit 101 as reading information to the management server 30, and controls the reception of processing result information, progress information, etc., sent from the management server 30.
[0039] (Functional configuration of the control unit of the management server) Figure 5 shows an example of the functional configuration of the control unit of the management server 30 when the management server 30 performs some of the processing for the user terminal 10. When the management server 30 performs part of the processing of the user terminal 10, the control unit of the management server 30 functions as follows: read information acquisition unit 301, OCR control unit 302, processing result acquisition unit 303, input information acquisition unit 304, progress information generation unit 305, candidate extraction unit 306, validity determination unit 307, and transmission / reception control unit 308. Of these, the functions of the OCR control unit 302, processing result acquisition unit 303, progress information generation unit 305, candidate extraction unit 306, and validity determination unit 307 are the same as the functions of the OCR control unit 101, processing result acquisition unit 102, progress information generation unit 104, candidate extraction unit 105, and validity determination unit 106 in Figure 3, and therefore their explanation is omitted.
[0040] The read information acquisition unit 301 acquires the read information transmitted from the user terminal 10 and received under the control of the transmission / reception control unit 308. The input information acquisition unit 304 acquires input information for processing result information that has been transmitted from the user terminal 10 and received under the control of the transmission / reception control unit 308. The transmission / reception control unit 308 controls the transmission and reception of various information via the communication unit 34 (see Figure 3). For example, suppose the user terminal 10 reads character information formed on a medium such as paper (e.g., a form), and the management server 30 converts the character information read by the user terminal 10 into data. In this case, the transmission / reception control unit 308 controls the reception of the reading information transmitted from the user terminal 10 and controls the transmission of processing result information to the user terminal 10. The transmission / reception control unit 308 also controls the reception of input information for the processing result information transmitted from the user terminal 10 and controls the transmission of generated progress information to the user terminal 10.
[0041] (Processing flow at the user terminal) Figure 6 is an example of a flowchart showing the processing flow of the user terminal 10. The user terminal 10 performs OCR processing (step 601) and outputs processing result information (step 602). When an input operation to launch the application software is performed (YES in step 603), the user terminal 10 accepts the input operation (step 604) and displays the user interface on the display unit 16 (see Figure 2) (step 605). Conversely, if no input operation to launch the application software is performed (NO in step 603), the user terminal 10 repeats step 603 until an input operation to launch the application software is performed.
[0042] The user terminal 10 displays processing result information on the user interface (step 606). When an input operation is performed to select information for one or more items from among the information of multiple items included in the processing result information displayed on the user interface that will be used to generate progress information (YES in step 607), the user terminal 10 accepts the input operation (step 608) and generates progress information according to the input information (step 609). On the other hand, if no input operation has been performed to select information for one or more items that will be used to generate progress information (NO in step 607), the user terminal 10 repeats step 607 until that input operation is performed.
[0043] If the user terminal 10 finds in the progress information generated in step 609 that there is a process that is presumed to have a problem based on predetermined criteria (YES in step 610), it changes the display mode of the progress information so that the process that is presumed to have a problem can be identified from the progress of other processes (step 611), and displays that progress information on the user interface (step 612). On the other hand, if there is no process in the progress information that is presumed to have a problem based on predetermined criteria (NO in step 610), it proceeds to step 612.
[0044] When an input operation is performed to correct the definitions and processing results used in each process that constitutes the OCR process (YES in step 613), the user terminal 10 accepts the input operation (step 614) and performs the correction (step 615). Then, in response to the user's input operation, the OCR process is re-executed starting from the process related to the correction (step 616). On the other hand, if no input operation has been performed to correct the definitions and processing results used in each process that constitutes the OCR process (NO in step 613), the user terminal 10 repeats step 613 until such an input operation is performed.
[0045] (Processing flow of the management server) Figure 7 is an example of a flowchart showing the processing flow of the management server 30 when the management server 30 performs some of the processing for the user terminal 10.
[0046] When the management server 30 receives read information from the user terminal 10 (YES in step 701), it acquires the read information (step 702) and performs OCR processing, including converting the read string into data (step 703). The management server 30 then outputs the processing result information (step 704). Conversely, if no read information has been sent (NO in step 701), the management server 30 repeats step 701 until read information is received.
[0047] The management server 30 sends the processing result information output in step 704 to the user terminal 10 (step 705). When input information for the processing result information is sent from the user terminal 10 (YES in step 706), the management server 30 acquires that input information (step 707) and generates progress information according to the input information (step 708). On the other hand, if no input information for the processing result information has been sent (NO in step 706), the management server 30 repeats step 706 until input information for the processing result information is sent.
[0048] The management server 30 sends the progress information output in step 708 to the user terminal 10 (step 709). When the management server 30 receives input information from the user terminal 10 to correct the definitions used in each process that constitutes the OCR process and the results of the processes (YES in step 710), it acquires the input information (step 711) and makes the corrections (step 712). Then, according to the input information entered by the user, it re-executes the OCR process starting from the process related to the correction (step 713). On the other hand, if input information to correct the definitions used in each process that constitutes the OCR process and the results of the processes has not been sent (NO in step 710), the user terminal 10 repeats step 710 until that input information is sent.
[0049] (Specific example) Figure 8 shows a specific example of a service to which the present invention is applied. In Figure 8, the area above the dashed line represents the cloud, and the area below the dashed line represents on-premises. As shown in Figure 8, the service to which the present invention applies (hereinafter referred to as "this service") is implemented by the processes shown in (1) to (10). Of these, in (1) "Business design and operation verification", processes such as setting the reading definition of a string formed on a medium such as paper (for example, a form, etc.), output settings, and business check settings are performed.
[0050] (1) "Business design and operational verification" is realized through coordination with (4) "Document recognition, confirmation, and correction", (5) "OCR confirmation and correction", and (6) "Business check" described later (for example, feedback from operational verification). (2) "Data entry" is performed, which involves inputting data to be processed by OCR. Data to be processed by OCR may be entered from cloud storage services, multifunction printers (MFPs), scanners, web browsers, etc., or from external systems via APIs (Application Programming Interfaces).
[0051] In (3) "Sorting OCR," the OCR engine sorts the input data based on the design data set in (1) "Business Design and Operation Verification," determining which form and which page it corresponds to, and performs processes such as reading and extracting text information. In (4) "Form Identification, Confirmation, and Correction," processes such as splitting the forms based on the sorting results from (3) "Sorting OCR," presenting the split results to the user, and correcting them to the correct state are performed.
[0052] In (5) "OCR Verification and Correction," the character information extracted in (3) "Sorting OCR" is presented to the user, and processing such as correction to the correct state or rollback is performed. In addition, in (5) "OCR Verification and Correction," the results of extraction, verification, and correction are compared with data stored in a predetermined database, the corrected data resulting from the comparison is displayed on the user interface, the effort and errors in verification and correction are detected, and the replacement results are displayed in advance.
[0053] In (6) "Business Check," the processing results of (5) "OCR Confirmation and Correction" are checked based on the business check settings defined in (1) "Business Design and Operational Verification," errors are detected, errors are notified to the user, and the user is required to make corrections and return the changes. In (7) "Data Output," based on the processing results of (1) through (6) above, the data that will be ultimately output is generated and output according to the output settings defined in (1) "Business Design and Operational Verification." The data output in (7) "Data Output" includes data output to business systems operating in a cloud environment, data output to cloud storage services, data output to external systems via APIs, and data output to business systems operating in an on-premises environment via a web user interface.
[0054] In (8) "Return," processing such as returning to the previous stage during the check in the processes of (5) and (6) is performed. "Return" in (8) may be performed as an escalation when the user cannot make a decision, or when an error is detected in the process of (4) and it is re-executed. In "Business Management" in (9), the present invention is applied to perform processing such as the management and execution of websites (tenants), workspaces, and jobs. In "DB" (database) in (10), defined data and saved data such as processing results are stored and managed.
[0055] Figures 9 to 14 illustrate specific examples of user interfaces displayed as display devices on the display unit 16 of the user terminal 10. Figure 9 shows an example of a user interface displaying processing result information. Processing result information is acquired on a job-by-job basis in OCR processing. A "job" is a unit of processing execution. The processes that constitute OCR processing are managed on a job-by-job basis. The processing result information for each job records the target of reading or data conversion for each record. A "record" is a unit obtained by dividing one or more forms submitted in a job into individual forms. For example, if one job contains data for three forms, three records will be generated.
[0056] The processing result information for the job (job 026) shown in Figure 9 contains 5 records (records 001 to 005) per report. The targets for reading or data conversion in each record are "Name", "Product", "Price", "Code-1" (product code 1), and "Code-2" (product code 2). Of these, "Code-1" (product code 1) is "XP00102" for record 001, "XP11099" for record 002, "a02" for record 003, "XP2534" for record 004, and "XP12334" for record 005, with record 003 having an unnatural value. In this case, the user performs an operation (for example, a touch operation or a click operation) to select the cell displaying the unnatural value (a02). In the example in Figure 9, it is assumed that the operation of selecting the shaded cell was performed. Then, the progress information for record 003 corresponding to the selected cell is displayed in the user interface. Figure 10 shows an example.
[0057] Figure 10 shows a specific example of a user interface displaying progress information. The user interface shown in Figure 10 displays the progress information for record 003, which was selected as having an unnatural value from the processing result information of job 026 in Figure 9. The progress information shown in Figure 10 is displayed with the job and record selected, but the user can switch to another job by pressing dropdown button B1, and to another record by pressing dropdown button B2. In addition, in the example in Figure 10, only the white-outlined cell C can be modified by the user. The user performs the operation of selecting the cell C they want to check or modify from among the white-outlined cells C.
[0058] In the example shown in Figure 10, the OCR process consists of processes P1 to P7. Each of the dashed areas representing processes P1 to P7 contains one or more cells displaying information indicating the individual processing results or the content of the processing. For example, the "Document Image" (process P1) is shown in the font shown in Figure 10 as "〇〇jiro", "D-Centre", "C5150", and "XY44". The "Recognition Result" (process P2) is also shown in the font shown in Figure 10 as "〇〇jiro", "D-Cento", "C515o", and "XY44".
[0059] Furthermore, the "Data Correction" (Processing P3) shows that data correction (Correction 001) was performed on "D-Cento" and data correction (Correction 002) was performed on "C515o". The "Data Correction Result" (Processing P4) shows that for "D-Cento", two candidates (Candidate 01 "D-Centre", Candidate 02 "D-Works") were extracted, and of these, Candidate 01 "D-Centre" was selected. The selected candidate (Candidate 01) and the unselected candidate (Candidate 02) are displayed in a way that makes them distinguishable. In the example in Figure 10, the unselected candidate (Candidate 02) is obscured in order to make it distinguishable. Furthermore, it is shown that "C515o" was corrected to "C5150".
[0060] Next, the "Confirmation and Correction Result" (processing P5) is shown in the font shown in Figure 10 as "〇〇jiro", "D-Centre", "C5150", and "XY44". Furthermore, the "Data Conversion" (processing P6) indicates that data conversions (conversion 001 and conversion 002) for "D-Centre" and "C5150" (conversion 001 and conversion 002) have been performed. Finally, the "Output Result" (processing P7) is shown in the font shown in Figure 10 as "〇〇jiro", "D-Centre", "324,000", "a02", and "XY44". The content displayed in cell C in the "Output Result" (processing P7) corresponds to the content of record 003 in the processing result information shown in Figure 9 above. Here, "a02", which was selected as an unnatural value, may be displayed in an identifiable manner. For example, it may be identifiable by the color of the text, the weight of the text, the color of cell C, the thickness of the border of cell C, etc.
[0061] Furthermore, as progress information, at least one of the possibilities of a processing problem occurring or not occurring may be represented in a manner that can be visually identified. In this embodiment, the possibility of a problem occurring and the possibility of not occurring are distinguished by a value indicating the degree of similarity of the strings that were read or converted (hereinafter referred to as "similarity").
[0062] Of the processing result information in Figure 9 above, the cells C related to the derivation of "a02" in the "Output Result" (Processing P7), which was selected as an unnatural value, are "Correction 001" and "Correction 002" in "Data Correction" (Processing P3), "D-Centre" and "C5150" in "Confirmation and Correction Result" (Processing P5), and "Conversion 002" in "Data Conversion" (Processing P6). Of these, for the four cells C other than "Conversion 002" which is directly related to "a02" in the "Output Result" (Processing P7) ("Correction 001", "Correction 002", "D-Centre", and "C5150"), for example, the similarity can be calculated using the Levenshtein distance between the "Recognition Result" (Processing P2), the "Data Correction Result" (Processing P4), and the "Confirmation and Correction Result" (Processing P5). If the difference in similarity is within a certain range, it can be judged that "the possibility of a problem is low," and this fact may be displayed in cell C in an identifiable manner. Although not shown in the diagram, for example, cell C may be color-coded.
[0063] Furthermore, in "data conversion" (processing P6), when calculating similarity, differences in regularity between adjacent values in the conversion table are taken into consideration. If the calculated similarity is low, a message indicating a high probability of a problem may be displayed in cell C in an identifiable manner. For example, although not shown in the illustration, cell C may be color-coded. In addition, the similarity may be displayed alongside the other values in cell C. Figure 11 shows an example of this.
[0064] When the calculated similarity score is listed in cell C, it may be represented as a numerical value between 0 and 1, as shown in Figure 11. In this case, for example, a similarity score closer to "0" can indicate "abnormality," while a similarity score closer to "1" can indicate "normality." In the example in Figure 11, the similarity score listed in "Correction 001" under "Data Correction" (Processing P3) is "0.75," the similarity score listed in "Correction 002" is "0.8," the similarity score listed in "D-Centre" under "Confirmation Correction Result" (Processing P5) is "1.0," and the similarity score listed in "C5150" is "1.0." The similarity score listed in "Conversion 002" under "Data Conversion" (Processing P6) is "0.0."
[0065] In the example above, candidate 01 "D-Centre" is selected from the two candidates in the "Data Correction Result" (processing P4), and the display of candidate 02 "D-Works," which was not selected, is obscured. However, there are cases where neither candidate is selected due to deficiencies or other reasons. In this case, although not shown in the diagram, the display of both candidates is obscured, but by looking at the "Confirmation Correction Result" (processing P5), it can be seen that corrections have been made by the user's input. This makes it possible to detect that the "Data Correction" (processing P3) is not functioning with the intended accuracy.
[0066] In this embodiment, the above-mentioned similarity is used as the logic for determining validity. For example, suppose the formula for calculating similarity using the Levenshtein distance is predetermined as "Similarity = 1 - Levenshtein distance ÷ Number of characters in the longer string". Furthermore, suppose a threshold is predetermined such that if the similarity is greater than 0 and less than 0.4, cell C is displayed in red to indicate low similarity, and if the similarity is between 0.4 and 0.7, cell C is displayed in green to indicate high similarity.
[0067] In this case, the validity of "Correction 001" in "Data Correction" (Processing P3) is determined as follows: The similarity between "D-Cento" in "Recognition Result" (Processing P2) and candidate 01 "D-Centre" in "Data Correction Result" (Processing P4) is "0.75" (1-2÷8=0.75), and the similarity between candidate 01 "D-Centre" in "Data Correction Result" (Processing P4) and "D-Centre" in "Confirmation Correction Result" (Processing P5) is "1.0" (1-0÷8=1.0). Therefore, the similarity in both cases is 0.7 or higher, and the cell color turns green, indicating high similarity. As a result, the validity is determined to be "high".
[0068] Furthermore, the validity of "Correction 002" in "Data Correction" (Processing P3) is determined as follows: The similarity between "C515o" in "Recognition Result" (Processing P2) and "C5150" in "Data Correction Result" (Processing P4) is "0.8" (1-1÷5=0.8), and the similarity between "C5150" in "Data Correction Result" (Processing P4) and "C5150" in "Confirmation Correction Result" (Processing P5) is "1.0" (1-0÷5=1.0). As a result, the similarity in both cases is 0.7 or higher, and the cell color turns green, indicating a high degree of similarity. Consequently, the validity is determined to be "high".
[0069] The logic used to determine validity described above may be predefined for each table, or it may be determined according to the type of string, etc. Alternatively, multiple checks may be performed, and the check result deemed to extract the most regularity may be adopted. Furthermore, if the number of data points is small, the threshold may be made variable according to the number of data points. For example, if the number of data points is very small, such as "3," even if two of the three data points match, the similarity score would be "0.67," which is not valid.
[0070] In the examples shown in Figures 10 and 11 above, all cell C entries for all processes are displayed in the user interface as progress information for record 003, which was selected as an unnatural value from the processing result information in Figure 9. However, it is also possible to display only the cell C entries for processes related to "a02" in the "output result" (processing P7) selected by the user's input operation in the user interface. Figure 12 shows a specific example of such a user interface. To display only the cell C entries related to "a02" in the selected "output result" (processing P7) in the user interface, press the check button B3 labeled "Show only processes related to the selected output result," as shown in Figure 12.
[0071] When you select cell C labeled "Conversion 002" in "Data Conversion" (Process P6) from the user interface shown in Figure 12 (for example, by touching or clicking), a user interface for modifying the definitions used in the process and the results of the process will be displayed. Figure 13 shows a specific example of such a user interface.
[0072] In the user interface display area A1 shown in Figure 13, a dropdown button B11 is located. The dropdown button B11 is used to select the processing result to be modified from the data conversion processing results displayed in the dropdown list. In the example in Figure 13, the operation to select the cell "Conversion 002" in Figure 12 has been performed, so "Conversion 002" is automatically selected as the initial value for the dropdown button B11.
[0073] Furthermore, display area A2 displays some of the progress information from Figure 12 mentioned above, as well as the derived path, as information to support the user. Display area A3 displays the conversion tables T1 and T2 used in "data conversion" (processing P6). Conversion table T1 is a table that associates "product name" with "code table", and its table name is "table01". Conversion table T2 is a table that associates "model number" with "product code", and its table name is "List02". Note that conversion tables T1 and T2 are stored and managed in the string DB131 of the storage unit 13.
[0074] The buttons B12 and B13, labeled "Modify," displayed to the right of each of the conversion tables T1 and T2, are buttons that appear next to the relevant strings in record 003, which was selected as having an unnatural value. This allows the user to smoothly perform only the operations necessary for correction without performing unnecessary operations. In this case, the user looks at the displayed conversion table T2, confirms that the product code associated with the model number "C5150" is incorrect, and presses button B13 to correct the product code. Then, although not shown in the diagram, an input field for individually editing the product code stored in conversion table T2 appears. For example, if the correct string "XP2459" is entered, "a02" will be corrected to "XP2459".
[0075] Figure 14 shows the user interface with the modifications reflected. The modifications are displayed in a manner that makes them identifiable as having been modified. In the example in Figure 14, the modifications are displayed in bold to make them identifiable as having been modified. Note that "a manner that makes the modifications identifiable" is not limited to the example in Figure 14 where the changes are shown in bold; for example, the color of the modifications could be changed, or the cells could be highlighted. The user presses button B14, labeled "Save and return to XXX," if they want to save the modifications but not rerun the process. The user presses button B15, labeled "Save and rerun," if they want to save the modifications and rerun the process. In this case, although not shown in the illustration, there may be a button that allows the user to choose whether to roll back and rerun the existing OCR process or to start a separate OCR process and run it anew. The user presses button B16, labeled "Back," if they want to return to the user interface shown in Figure 10 or Figure 11 without saving the modifications.
[0076] The validity of "Conversion 002" in "Data Conversion" (Process P6) is determined as follows. In this case, "table01" is not considered as it is an intermediate table in the two-stage matching process. First, each value representing the "product code" in conversion table T2 (table name "List02") is checked using an algorithm related to the regularity (degree of commonality) of strings. For example, if the Longest Common Subsequence (LCS) algorithm is used, "XP" is extracted as the string common to the product code values "XP0040", "XP0037", "XP4144", and "XP3237". Then, since the value representing the product code "a02" does not contain the common string "XP", "a02" is detected as an outlier.
[0077] Although this embodiment has been described above, the present invention is not limited to the embodiment described above. Furthermore, the effects of the present invention are not limited to those described in this embodiment. For example, the configuration of the information processing system 1 shown in Figure 1, the hardware configuration of the user terminal 10 shown in Figure 2, and the hardware configuration of the management server 30 shown in Figure 3 are merely examples for achieving the objectives of the present invention and are not particularly limited. Similarly, the functional configuration of the user terminal 10 shown in Figure 4 and the functional configuration of the management server 30 shown in Figure 5 are also merely examples and are not particularly limited. It is sufficient that the information processing system 1 in Figure 1 is equipped with a function that can execute the above-described process as a whole, and the functional configuration used to realize this function is not limited to the examples in Figures 4 and 5.
[0078] Furthermore, the order of the processing steps for the user terminal 10 shown in Figure 6 and the processing steps for the management server 30 shown in Figure 7 are merely illustrative and not particularly limiting. Processing is not limited to being performed chronologically according to the illustrated steps; it may also be performed in parallel or individually. Similarly, the specific examples shown in Figures 8 to 14 are merely examples and not particularly limiting.
[0079] For example, in the above-described embodiment, character information is read as part of the OCR process, but graphic information may also be read in addition to character information.
[0080] Furthermore, for example, Figures 10 to 12 show the overall flow, including the sequential relationships between the results of each of the processes P1 to P7, as progress information, but are not limited to this. For example, each of the results of processes P1 to P7 could be displayed individually in the user interface. In this case, the display could be switched to the result of the previous process by performing a predetermined operation. An example of a "predetermined operation" would be pressing a button labeled "Previous" (not shown in the diagram). This would allow the user to review the results of each process retrospectively.
[0081] Furthermore, while the color coding of cells C according to similarity in the user interface shown in Figures 10 to 12 was explained using "red" (low similarity) and "green" (high similarity) as examples, it is not limited to these. For example, multiple similarity thresholds may be set, and three or more colors may be used to color-code the cells according to their values. Alternatively, a color may be displayed to indicate that a determination is not possible. In addition, it may be possible to distinguish at a glance between processing P1 to P7 that is performed by the program and processing that is performed by user input. For example, the dashed areas of "data correction" (processing P3) and "data conversion" (processing P6), which are processed by the program, may be distinguished from the dashed area of "confirmation and correction result" (processing P5) by color coding. [Explanation of Symbols]
[0082] 1...Information processing system, 10...User terminal, 11...Control unit, 30...Management server, 31...Control unit, 90...Network, 101...OCR control unit, 102...Processing result acquisition unit, 103...Input operation reception unit, 104...Progress information generation unit, 105...Candidate extraction unit, 106...Validity determination unit, 107...Display control unit, 108...Transmission / reception control unit, 109...Display control unit, 301...Reading information acquisition unit, 302...OCR control unit, 303...Processing result acquisition unit, 304...Input information acquisition unit, 305...Progress information generation unit, 306...Candidate extraction unit, 307...Validity determination unit, 308...Transmission / reception control unit
Claims
1. Equipped with a processor, The aforementioned processor, The process involves reading text information and converting it into data by sequentially executing two or more processes and outputting the results. The system accepts user input on the outputted processing results. In accordance with the above operation, the progress of each of the two or more processes leading to the processing result is displayed individually on the display device for each of those processes. An information processing device characterized by further accepting user operations and transitioning from a screen displaying the progress of each of the individual processes shown on the display device to a screen displaying the progress of the process immediately preceding or immediately following the said process.
2. The information processing apparatus according to claim 1, characterized in that, in displaying the progress of the process, the processor displays the progress of the process that is presumed to have a problem based on predetermined criteria in a way that is distinguishable from the progress of other processes.
3. comprising a processor, The aforementioned processor, As a process for reading character information and converting it into data, two or more processes are executed sequentially, including at least one of a correction process that corrects the intermediate data obtained in the previous process, and a conversion process that converts the intermediate data obtained in the previous process, and the processing result is output. The system accepts user input on the outputted processing results. In accordance with the above operation, the progress of each of the two or more processes leading to the processing result is displayed on the display device. In displaying the progress of the correction process, one or more correction candidates are displayed; and in displaying the progress of the conversion process, one or more conversion candidates are displayed. In displaying the progress of the correction process and the conversion process, the validity of the correction candidate and the conversion candidate, as determined based on predetermined criteria, is displayed. The aforementioned correction process includes a correction performed by the processor in accordance with predetermined rules, and a correction that accepts user input and replaces the intermediate data string with the input string. An information processing device characterized by determining the validity of the correction candidate based on the similarity between the intermediate data obtained in the preceding processing and the correction candidate in the correction, and the similarity between the correction candidate and the string entered in the correction.
4. The information processing apparatus according to claim 3, characterized in that the processor determines the validity of the correction candidate based at least on the similarity between the intermediate data obtained in the preceding processing and the correction candidate.
5. comprising a processor, The aforementioned processor, As a process for reading character information and converting it into data, two or more processes are executed sequentially, including at least one of a correction process that corrects the intermediate data obtained in the previous process, and a conversion process that converts the intermediate data obtained in the previous process, and the processing result is output. The system accepts user input on the outputted processing results. In accordance with the above operation, the progress of each of the two or more processes leading to the processing result is displayed on the display device. In displaying the progress of the correction process, one or more correction candidates are displayed; and in displaying the progress of the conversion process, one or more conversion candidates are displayed. In displaying the progress of the correction process and the conversion process, the validity of the correction candidate and the conversion candidate, as determined based on predetermined criteria, is displayed. The aforementioned conversion candidates are selected from a set of data based on a predetermined classification. An information processing device characterized by determining the validity of the conversion candidates based on the degree of conformity to the regularity extracted from the data set included in the classification of the conversion candidates.
6. The aforementioned processor, The information processing apparatus according to claim 3, characterized in that it displays the progress of the processing in the correction and the progress of the processing in the correction in a way that allows for identification.
7. On the computer, The function reads text information and converts it into data by sequentially executing two or more processes and outputting the processing results. A function to accept user input on the outputted processing result, In response to the aforementioned operation, the function includes displaying the progress of each of the two or more processes leading to the aforementioned processing result on a display device, for each individual process, A function that further accepts user input and transitions from a screen displaying the progress of each individual process shown on the display device to a screen displaying the progress of the process immediately preceding or immediately following the said process, A program characterized by enabling control processing that includes such processing.
8. A computer, The process of reading character information and converting it into data includes a function that sequentially executes two or more processes, including at least one of a correction process that corrects the intermediate data obtained in the previous process, and a conversion process that converts the intermediate data obtained in the previous process, and outputs the processing result. A function to accept user input on the outputted processing result, In accordance with the above operation, the function displays on a display device the progress of each of the two or more processes leading to the above processing result, The function includes displaying one or more correction candidates in the progress of the correction process, and displaying one or more conversion candidates in the progress of the conversion process, In displaying the progress of the correction process and the conversion process, the function includes displaying the validity of the correction candidate and the conversion candidate, which is determined based on predetermined criteria. The aforementioned correction process includes a function that performs corrections according to predetermined rules by the processor, and a function that accepts user input and replaces the intermediate data string with the input string. The validity of the aforementioned correction candidate is determined based on the similarity between the intermediate data obtained in the preceding processing and the correction candidate in the correction, and the similarity between the correction candidate and the string entered in the correction. A program characterized by enabling control processing that includes such processing.
9. A computer, The process of reading character information and converting it into data includes a function that sequentially executes two or more processes, including at least one of a correction process that corrects the intermediate data obtained in the previous process, and a conversion process that converts the intermediate data obtained in the previous process, and outputs the processing result. A function to accept user input on the outputted processing result, In accordance with the above operation, the function displays on a display device the progress of each of the two or more processes leading to the above processing result, The function includes displaying one or more correction candidates in the progress of the correction process, and displaying one or more conversion candidates in the progress of the conversion process, In displaying the progress of the correction process and the conversion process, the function includes displaying the validity of the correction candidate and the conversion candidate, which is determined based on predetermined criteria. The function includes selecting the aforementioned conversion candidates from a set of data based on a predetermined classification, The validity of the conversion candidate is determined based on the degree of fit to the regularity extracted from the data set included in the classification of the conversion candidate, A program characterized by enabling control processing that includes such processing.
Citation Information
Patent Citations
Erroneously read character correcting method
JP1993314303A
Character reader
JP1994036067A
Mistaken character corrector
JP1995013991A
Information processing apparatus, information processing system, information processing method, and program
JP2016015007A
Image processing system, image processing method, program, image processing device, information processing device
JP2020102166A