Data input automation device and data input automation method

Abstract

According to some embodiments of the present invention, a data input automation device comprises: a processor; and a memory configured to store instructions which, when executed by the processor, cause the processor to perform the operations of: generating an automation model on the basis of a manual input process in which a user inputs sample input data displayed in a sample input image to a legacy management program; generating a tuning model by tuning a detailed operation of the automation model on the basis of the user's feedback on a driving state of the automation model; executing the tuning model to automatically input new input data displayed in a new input image to the legacy management program; and verifying the automatically input new input data on the basis of a recording format of existing input data previously input to the legacy management program.

Description

Data entry automation device and data entry automation method

[0001] The present invention relates to a data input automation device and a data input automation method for automating the process of inputting data into various types of legacy management programs, thereby reducing the time and cost required for manual input and preventing a decrease in data accuracy caused by input errors.

[0002] Prescription data entry programs and accounting management software utilized in pharmacies are managed through a method where users manually input prescription or sales / cost-related data. In the case of prescription entry, manually inputting vast amounts of patient, hospital, doctor, medication, and insurance information can consume significant time and cost, and errors can compromise the reliability of the database. Consequently, there is a continuous demand to streamline the data entry methods of these existing manual programs.

[0003] (Patent Document 1) Korean Published Patent No. 10-2023-0151192

[0004] One of the objectives of the present invention is to provide a data input automation device and method capable of resolving inefficiency and reduced accuracy caused by manual work by automating the process of inputting data into legacy management programs currently used in various fields, such as prescription entry. The technical objectives of the present invention are not limited to the problems mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below.

[0005] According to some embodiments of the present invention, a data input automation device comprises: a processor; and a memory configured to store instructions that, when executed by the processor, cause the processor to perform: an operation of generating an automation model based on a manual input process in which a user inputs sample input data displayed in a sample input image into a legacy management program; an operation of generating a tuning model by tuning the detailed operation of the automation model based on the user's feedback regarding the operating state of the automation model; an operation of automatically inputting new input data displayed in a new input image into the legacy management program by executing the tuning model; and an operation of verifying the automatically inputted new input data based on the recording format of existing input data previously entered into the legacy management program.

[0006] According to some embodiments of the present invention, the manual input process is provided in the form of a video recording the procedure in which the user checks the sample input image and inputs the sample input data into the legacy management program.

[0007] According to some embodiments of the present invention, the manual input process repeats the process of the user identifying target data in the sample input image, the process of performing a window switching from the sample input image to the legacy management program, the process of writing and saving the target data in the input window of the legacy management program, and the process of performing a window switching from the legacy management program to the sample input image.

[0008] According to some embodiments of the present invention, the sample input image includes an image file that scans or captures an input data document, and the target data is identified based on the result of optical character recognition (OCR) for the image file.

[0009] According to some embodiments of the present invention, the user feedback for generating the tuning model includes correction feedback for misrecognition between similar characters caused by the optical character recognition (OCR).

[0010] According to some embodiments of the present invention, the user feedback for generating the tuning model includes update request feedback regarding a version update of the legacy management program, and the tuning model is configured to identify changes in the user interface (UI) before and after the update of the legacy management program in response to the update request feedback, and to automatically tune based on the UI changes.

[0011] According to some embodiments of the present invention, when the tuning model is executed to automatically input the new input data into the legacy management program, the tuning model is configured to repeat the operation of identifying target data based on optical character recognition (OCR) from the new input image, identifying an input window within the legacy management program corresponding to the target data, and inputting and saving the target data into the input window.

[0012] According to some embodiments of the present invention, the operation of verifying the new input data includes determining whether there is an unstored item among the automatically input new input data, and if there is an unstored item, displaying the unstored item to the user for model tuning.

[0013] According to some embodiments of the present invention, the operation of verifying the new input data includes, when the unstored item does not exist, determining whether the new input data is identical to the existing input data, and when the new input data is not identical to the existing input data, determining whether the data format of the new input data and the data format of the existing input data are identical.

[0014] According to some embodiments of the present invention, when the new input data is not identical to the existing input data and the data format of the new input data and the data format of the existing input data are not identical, the new input data is displayed to the user for model tuning.

[0015] According to some embodiments of the present invention, a data input automation method comprises: a step of generating an automation model based on a manual input process in which a user inputs sample input data displayed on a sample input image into a legacy management program; a step of generating a tuning model by tuning the detailed operation of the automation model based on the user's feedback regarding the operating state of the automation model; a step of automatically inputting new input data displayed on a new input image into the legacy management program by executing the tuning model; and a step of verifying the automatically inputted new input data based on the recording format of existing input data previously entered into the legacy management program.

[0016] According to embodiments of the present invention, a data input automation device and method can be provided to resolve inefficiency and reduced accuracy caused by manual work by automating the process of inputting data into legacy management programs currently used in various fields, such as prescription entry. The technical effects according to embodiments of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art in accordance with the disclosure of this document.

[0017] FIG. 1 illustrates a method of operation for a data input automation device according to some embodiments.

[0018] FIG. 2 illustrates elements constituting a data input automation device according to some embodiments.

[0019] FIG. 3 illustrates a prescription image containing prescription data entered into a prescription input program according to some embodiments.

[0020] FIG. 4 illustrates a prescription input program for recording prescription data identified from a prescription image according to some embodiments.

[0021] FIGS. 5 to 14 illustrate a user interface of a prescription input program according to some embodiments.

[0022] FIG. 15 illustrates steps constituting a data input automation method according to some embodiments.

[0023] Embodiments of the present invention will be described in detail below with reference to the drawings. The description below is intended only to illustrate the embodiments and is not intended to limit or restrict the scope of the rights according to the present invention. Anything that can be easily inferred by a person skilled in the art from the detailed description and embodiments of the invention should be interpreted as falling within the scope of the rights according to the present invention. Detailed descriptions of matters widely known to those skilled in the art regarding the present invention are omitted.

[0024] The terms used in this invention are described as general terms widely used in the technical field relating to this invention; however, the meaning of the terms used in this invention may vary depending on the intent of those skilled in the field, the emergence of new technologies, examination standards, or case law. Some terms may be selected at the discretion of the applicant, and in such cases, the meaning of the arbitrarily selected terms will be explained in detail. The terms used in this invention should be interpreted not merely in their dictionary meanings, but in a sense that reflects the overall context of the specification.

[0025] FIG. 1 illustrates a method of operation for a data input automation device according to some embodiments.

[0026] Referring to FIG. 1, the data input automation device (100) can automatically input an input image (10) into a legacy management program (30) based on an automation model (20).

[0027] The data input automation device (100) may be a desktop PC, laptop PC, smartphone, tablet PC, or other electronic device used by the user for data management. The user can perform new data input, data modification, data deletion, data retrieval, etc. by running a legacy management program (30) through the data input automation device (100).

[0028] The legacy management program (30) may refer to a management program that is operated through the user's manual data input. For example, the legacy management program (30) may include a prescription management program used in pharmacies, an accounting management program used by individual business owners or accounting-related companies, etc. The legacy management program (30) may be used mainly in the form of a PC application, but may also be implemented in the form of a mobile app that runs on a mobile device such as a smartphone as needed.

[0029] The input image (10) may represent a document displaying data to be input into the legacy management program (30). For example, the input image (10) may be an image file obtained by scanning or photographing a document displaying data. If the legacy management program (30) is a prescription management program, the input image (10) may be a prescription image file obtained by scanning or photographing a physical prescription form issued by a medical institution. Alternatively, if the legacy management program (30) is an accounting management program, the input image (10) may be an image related to expenses, such as a receipt or a credit card payment slip.

[0030] FIG. 2 illustrates elements constituting a data input automation device according to some embodiments.

[0031] Referring to FIG. 2, the data input automation device (100) may include a memory (110) and a processor (120). However, it is not limited thereto, and some components may be omitted from the data input automation device (100), or other components may be further included in the data input automation device (100).

[0032] The memory (110) may be configured to store various data, instructions, computer programs, software, and mobile applications processed by the data input automation device (100). For example, the memory (110) may be implemented as a non-volatile memory such as ROM, PROM, EPROM, EEPROM, flash memory, PRAM, MRAM, RRAM, FRAM, etc., or as a volatile memory such as DRAM, SRAM, SDRAM, PRAM, RRAM, FeRAM, etc., and may be implemented in the form of an HDD, SSD, SD, Micro-SD, etc., or a combination thereof.

[0033] The processor (120) may be configured to execute instructions, programs, applications, etc., stored in memory (110). The processor (120) may be implemented as an array of logic gates or a general-purpose microprocessor for processing various operations, and may be composed of a single processor or multiple processors. For example, the processor (120) may be implemented in at least one form of a microprocessor, CPU, GPU, and AP.

[0034] The data input automation device (100) may be configured to generate an automation model (20) based on a manual input process in which a user inputs sample input data displayed on a sample input image into a legacy management program (30). For example, the user may generate a manual input process by recording a procedure consisting of keyboard input, mouse input, etc., for inputting sample input data into the legacy management program (30), and an automation model (20) may be generated based on this. For example, the automation model (20) may be implemented in the form of an artificial intelligence (AI) model that trains the data input process using the manual input process as training data. The process of the automation model (20) learning the manual input process may be performed through various machine learning techniques.

[0035] The data input automation device (100) may be configured to generate a tuning model by tuning the detailed operation of the automation model (20) based on user feedback regarding the operating status of the automation model (20). For example, if the automation model (20) fails to smoothly perform automatic input of specific data among the data of the input image (10), the user may clearly record the process again and provide it to the automation model (20), and the automation model (20) may be tuned based on the user's demonstration of the process.

[0036] The data input automation device (100) can be configured to execute a tuning model to automatically input new input data displayed in a new input image into a legacy management program (30). When a tuning model is generated through model tuning, it may be possible to execute it to automatically input new input data that is not involved in learning. This is possible because both the existing training data and the new data are configured in the same format. For example, the tuning model can perform optical character recognition (OCR) on a new input image to generate text data, identify text for the current input stage among multiple input stages in the new input image, input the identified text into a corresponding location among the input locations of the legacy management program (30), save the input state, and proceed to the next input stage after completing the current input stage.

[0037] The data input automation device (100) may be configured to perform an operation of verifying automatically entered new input data based on the record format of existing input data that was previously entered into the legacy management program (30). Through the verification process, it may be verified whether all data for multiple input steps has been entered, and whether the form of the entered data (e.g., numbers, English alphabet codes, Korean names, etc.) is identical to the form of previously entered data. If, as a result of the verification, some data is missing or the format of the entered data differs from the existing format, a procedure for model tuning may be performed.

[0038] According to an embodiment, the manual input process may be provided in the form of a video recording the procedure in which a user checks a sample input image and inputs sample input data into a legacy management program (30). The user may record the manual input process in the form of a video and provide it as material for model training. For example, the user may record the process of identifying target text in a sample input image and copying it, and the process of pasting the copied target text into the input window of the legacy management program (30).

[0039] According to an embodiment, the manual input process may repeat the process of a user identifying target data from a sample input image, performing a window transition from the sample input image to a legacy management program (30), writing and saving the target data in the input window of the legacy management program (30), and performing a window transition from the legacy management program (30) to the sample input image. For example, the prescription data input process may consist of multiple input steps, such as a patient information input process, a hospital information input process, a doctor information input process, a drug information input process, and an insurance information input process. The data identification and input process for each input step may be recorded in the form of a video.

[0040] According to an embodiment, the sample input image may include an image file obtained by scanning or capturing an input data document, and the target data may be identified based on the results of Optical Character Recognition (OCR) on the image file. For example, in the case of automatic prescription entry, the sample input image may be a sample image file obtained by scanning or capturing a prescription document. Optical Character Recognition (OCR) may be performed to select text from the scanned / captured sample image file. Once text recognition is enabled by OCR, the target text in the sample input image may be identified by methods such as block selection.

[0041] According to the embodiment, user feedback for generating a tuning model may include correction feedback regarding misrecognition between similar characters caused by Optical Character Recognition (OCR). Optical Character Recognition (OCR) can recognize numbers, Korean characters, English alphabets, etc., that are most similar to the input image; however, depending on the printing state of prescriptions, etc., or the scanning / photography state, some distortion may occur in the image, and as a result, misrecognition of characters may occur. For example, “1,” “I,” and “l” correspond to similar characters that may be misrecognized by one another, and “i” and “j,” and “m” and “rn” may also correspond to similar characters. According to the embodiment, the detection of misrecognized characters may be based on the data format. For example, if “l” is entered in a place where the existing input data consists entirely of uppercase English letters, it may be presumed that this is a misrecognition of “I”. User feedback may be generated regarding character misrecognition, and through this, the automation model (20) and / or the tuning model may be further tuned.

[0042] According to an embodiment, user feedback for creating a tuning model may include update request feedback regarding version updates of the legacy management program (30), and the tuning model may be configured to identify changes in the user interface (UI) before and after the update of the legacy management program (30) in response to the update request feedback, and to automatically tune based on the UI changes. For example, if the version of the prescription entry program is updated and the location of the input window for entering patient information changes, update request feedback may be provided to reflect this. Based on this, the tuning model may be further tuned by considering UI changes such as the change in the input window location. Alternatively, the tuning model may periodically look up update information of the legacy management program (30), and if update information is found, perform additional tuning to automatically reflect UI changes without user intervention.

[0043] According to an embodiment, when a tuning model is executed to automatically input new input data into a legacy management program (30), the tuning model may be configured to identify target data based on optical character recognition (OCR) from a new input image, identify an input window within the legacy management program (30) corresponding to the target data, and repeat the operation of inputting and saving the target data into the input window. For example, in the case of a prescription input process, for items such as patient, hospital, doctor, medicine, and insurance, the tuning model may repeatedly perform OCR-based text identification and automatic entry into the corresponding input location.

[0044] According to an embodiment, the operation of verifying new input data may include determining whether there are any unstored items among the automatically entered new input data, and if unstored items exist, displaying the unstored items to the user for model tuning. The existence of unstored items may imply that the input / saving process of the item was not smooth, and to generate user feedback regarding this, information regarding the unstored items may be displayed to the user through program messages, sending notifications to registered mobile phones, etc. Alternatively, if it is confirmed that unstored items exist, the tuning model may be configured to independently check the input / saving process of the unstored items without user intervention and perform tuning to supplement them.

[0045] According to an embodiment, the operation of verifying new input data may include an operation of determining whether the new input data is identical to existing input data when no unstored items exist, and an operation of determining whether the data format of the new input data and the data format of the existing input data are identical when the new input data is not identical to existing input data. After checking for missing data through the verification of unstored items, a process of checking the suitability of the data format may follow. For example, if data that has previously been recorded is newly recorded, additional verification regarding the format of the data may not be necessary. Alternatively, as described above, if lowercase text is newly entered into an input window where all existing data consists of uppercase text, user feedback may be provided regarding the input.

[0046] According to an embodiment, if new input data is not identical to existing input data and the data format of the new input data is not identical to the data format of the existing input data, the new input data may be displayed to the user for model tuning. If there is no identical existing record and the data format differs from the existing record, there is a high probability that the input is unsuitable; in this case, relevant information may be provided to the user so that the user can re-record the process and proceed with model tuning.

[0047] FIG. 3 illustrates a prescription image containing prescription data entered into a prescription input program according to some embodiments.

[0048] Referring to FIG. 3, if the legacy management program (30) is a prescription input program, a prescription image (10) containing prescription data input therein may be shown.

[0049] Prescription data included in the prescription image (10) may include patient information (11), disease information (12), medical institution information (13), prescribing doctor information (14), prescription drug information (15), and other information (16). The information in the prescription data may be entered into each input location of the prescription input program. The user may record the process of entering the information in the prescription data into each input location as a video and provide it for model training.

[0050] The prescription image (10) may be an image file obtained by scanning or capturing a prescription sheet. Information regarding the prescription data may be accessible through optical character recognition (OCR) on the image file of the prescription image (10). For example, a user may drag and block-select text representing each piece of information from the OCR-recognized prescription image (10) file, copy it, and paste it into a corresponding location in the prescription input program, and the automation model (20) may learn this process.

[0051] FIG. 4 illustrates a prescription input program for recording prescription data identified from a prescription image according to some embodiments.

[0052] Referring to FIG. 4, a prescription input program (30) for recording prescription data identified from a prescription image (10) may be illustrated. The prescription input program of FIG. 4 may be an example of a legacy management program (30).

[0053] The prescription input program (30) may include function menus such as prescription input, prescription inquiry, environment settings, help, and exit. The prescription input menu may display an insurance information input window, a patient information input window, a hospital / doctor information input window, a drug information input window, etc.

[0054] Information regarding the patient's health insurance or other private insurance can be entered through the insurance information input window. Patient information such as patient name, age, gender, prescription issuance number, dispensing date, insured person, customer memos / special notes, and past prescription history can be entered through the patient information input window. Medical license, issuing institution, disease code, and period of use can be entered through the hospital / doctor information input window. Drug classification, drug name, ingredient name, method of administration, dosage, frequency of administration, duration of administration, total dosage, covered / non-covered status, and usage method can be entered through the drug information input window.

[0055] FIGS. 5 to 14 illustrate a user interface of a prescription input program according to some embodiments.

[0056] Referring to FIG. 5, a prescription dispensing (510) menu may be selected on the screen of an exemplary prescription input program (30), and within the prescription dispensing (510) menu, a patient information input window (520), a doctor / hospital information input window (530), and a drug information input window (540) may be displayed.

[0057] Referring to FIG. 6, the prescription manufacturing status (610) menu can be selected on the screen of an exemplary prescription input program (30), and when the prescription manufacturing status (610) menu is selected, a dispensing record screen (620) showing the history of medicines dispensed according to the prescription can be displayed.

[0058] Referring to FIG. 7, the dispensing and sales status by drug (710) menu can be selected on the screen of an exemplary prescription input program (30), and when the dispensing and sales status by drug (710) menu is selected, an inquiry / search screen (720) showing the dispensing and sales status by type of drug can be displayed.

[0059] Referring to FIG. 8, a settings menu (810) may be selected on the screen of an exemplary prescription input program (30). When the settings menu (810) is selected, the overall settings (820), individual settings (830), output settings (840), label-related settings (850), and data path settings (860) items may be displayed. For example, when the overall settings (820) item is selected, a detailed content screen (870) showing the detailed settings of the overall settings (820) item may be displayed.

[0060] Referring to FIG. 9, a dispensing / sales (900) tab may be selected on the screen of an exemplary prescription entry program (30), and when the dispensing / sales (900) tab is selected, detailed menus related thereto may be displayed. The detailed menus may include customer management (receipt printing), score management / SMS sending, PharmChart, PharmChart PLUS, PharmChart (dispensing room), prescription dispensing, reception status, prescription dispensing status, monthly dispensing status, quick drug price calculation, dispensing / sales drug management, electronic prescription, drug sales, drug sales status, dispensing exception to separation of duties, dispensing exception to separation of duties status, cash / card approval management, pharmacist memo pad, sending PharmFax, application for hypertension / diabetes expenses, request for supply of small pharmaceutical packages, Pharm Storage Service, diabetes support system, and smoking cessation aid linkage system.

[0061] Referring to FIG. 10, a purchase inventory (1000) tab may be selected on the screen of an exemplary prescription entry program (30), and when the purchase inventory (1000) tab is selected, detailed menus related thereto may be displayed. The detailed menus may include order creation / status, receiving order creation / status, consumable registration / status, Pharm order / automatic ordering, inventory status / expiration date, inventory correction / correction status, appropriate inventory calculation, inventory management, psychotropic drug management, narcotic drug management, misuse drug management, status by customer, transaction status by drug, drug receipt and disbursement status, voucher registration, voucher inquiry, closing work, recall notification for recalled drugs, recall drug inventory transmission, narcotic drug handling management, automatic receipt of transaction statement, and inter-pharmacy transaction registration / status.

[0062] Referring to FIG. 11, a management (1100) tab may be selected on the screen of an exemplary prescription entry program (30), and when the management (1100) tab is selected, detailed menus related thereto may be displayed. The detailed menus may include drug inflow / outflow status, deposit classification status, drug dispensing / sales status, daily sales status, profit / loss by drug sold, period-based management analysis, period-based management analysis, time-based management analysis, tax reporting data analysis, dispensing data analysis, dispensing status by period, visiting customer analysis, long-term dispensing patients, drug aggregation by client, drug classification management, purchase / sales by drug classification, drug sales status, billing details by reimbursement institution, fund management, Pharm Bank, and Pharm Tax.

[0063] Referring to FIG. 12, a billing management (1200) tab may be selected on the screen of an exemplary prescription input program (30), and when the billing management (1200) tab is selected, detailed menus related thereto may be displayed. The detailed menus may include investigation of prescription dispensing errors, investigation of division of labor exception errors, recalculation of dispensing records, aggregation of billing data, management of EDI billing history, management of EDI reception history, selection of supplementary billing data, selection of omitted billing data, selection of additional billing data, selection of objection data, selection of industrial accident re-billing data, billing for omitted division of labor exceptions, additional billing for division of labor exceptions, and billing for industrial accident veterans' benefits forms.

[0064] Referring to FIG. 13, a basic management (1300) tab may be selected on the screen of an exemplary prescription input program (30), and when the basic management (1300) tab is selected, detailed menus related thereto may be displayed. The detailed menus may include prescribing physician / issuing institution, health insurance / industrial accident workplace management, business partner management / pharmaceutical company, dispensing fee setting, drug location / unit, regional prescription drug management, packaged drug management, ingredient / low-cost substitute drug management, medication guidance / usage method setting, appointment prescription management (dispensing exception), substitution / combination / age contraindication inquiry, account management code, payment bank registration, opening time management, bundled prescription management, and narcotic drug code linkage management.

[0065] Referring to FIG. 14, a settings tab (1400) can be selected on the screen of an exemplary prescription input program (30), and when the settings tab (1400) is selected, detailed menus related thereto can be displayed. The detailed menus may include settings, user registration settings, billing portal settings, data backup (all), backup data restoration, data splitting, data merging, index organization, database reduction, automatic update, remote 1:1 after-sales service, application for compensation for insurance limit difference, and personal information destruction.

[0066] FIG. 15 illustrates steps constituting a data input automation method according to some embodiments.

[0067] Referring to FIG. 15, the data input automation method (1500) may include steps (1510) through (1540). However, it is not limited thereto, some steps may be omitted or other general steps may be added, and the steps of the data input automation method (1500) may be executed in a different order than the illustrated order.

[0068] The data input automation method (1500) may consist of steps processed sequentially in the data input automation device (100). Therefore, even if the details are omitted below, the description of the data input automation device (100) above may be equally applicable to the data input automation method (1500).

[0069] Steps (1510) to (1540) of the data input automation method (1500) can be performed by the memory (110) and processor (120) of the data input automation device (100).

[0070] In step (1510), the data input automation device (100) can perform the step of creating an automation model based on a manual input process in which a user inputs sample input data displayed on a sample input image into a legacy management program.

[0071] In step (1520), the data input automation device (100) can perform the step of creating a tuning model by tuning the detailed operation of the automation model based on user feedback regarding the operating status of the automation model.

[0072] In step (1530), the data input automation device (100) can perform the step of automatically inputting new input data displayed in the new input image into the legacy management program by running a tuning model.

[0073] In step (1540), the data input automation device (100) can perform a step of verifying automatically entered new input data based on the record format of existing input data that was previously entered into a legacy management program.

[0074] According to an embodiment, the data input automation method (1500) may be implemented in the form of a computer program stored on a computer-readable storage medium. That is, the computer program may include instructions for implementing the data input automation method (1500), and the instructions of the program may be stored on a computer-readable storage medium. The computer program may include a mobile application.

[0075] According to an embodiment, a computer-readable storage medium may include magnetic media such as a hard disk, a floppy disk, and a magnetic tape, optical media such as a CD-ROM and a DVD, magneto-optical media such as a floptical disk, and a hardware device specifically configured to store and execute computer program instructions such as ROM, RAM, and flash memory. Computer program instructions may include machine code generated by a compiler and high-level language code that can be executed by a computer using an interpreter, etc.

[0076] Although embodiments of the present invention have been described in detail above, the scope of the rights according to the present invention is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present invention as described in the following claims are also included within the scope of the rights according to the present invention.

Claims

1. In a data input automation device, processor; and When executed by the above processor, the above processor: The action of creating an automated model based on the manual input process in which a user inputs sample input data displayed in a sample input image into a legacy management program, The operation of generating a tuning model by tuning the detailed operation of the automation model based on the user's feedback regarding the operating status of the automation model, The operation of executing the above tuning model to automatically input new input data displayed in the new input image into the above legacy management program, A data recording automation device comprising: a memory configured to store commands that perform an operation to verify the newly input data automatically entered based on the recording format of the existing input data previously entered into the legacy management program.

2. In Paragraph 1, A data recording automation device in which the above manual input process is provided in the form of a video recording the procedure in which the user checks the sample input image and inputs the sample input data into the legacy management program.

3. In Paragraph 2, A data recording automation device that repeats the above manual input process, the process of the user identifying target data in the sample input image, the process of performing a window switching from the sample input image to the legacy management program, the process of writing and saving the target data in the input window of the legacy management program, and the process of performing a window switching from the legacy management program to the sample input image.

4. In Paragraph 3, A data recording automation device comprising a sample input image including an image file that scans or captures an input data document, and a target data identified based on the result of optical character recognition (OCR) for the image file.

5. In Paragraph 4, A data recording automation device in which the user feedback for generating the above tuning model includes correction feedback for misrecognition between similar characters caused by the above optical character recognition (OCR).

6. In Paragraph 1, The user feedback for generating the above tuning model includes update request feedback regarding version updates of the legacy management program, and The above tuning model is a data recording automation device configured to identify changes in the user interface (UI) of the legacy management program before and after an update in response to the update request feedback, and to automatically tune based on the UI changes.

7. In Paragraph 1, A data recording automation device configured such that when the tuning model is executed to automatically input the new input data into the legacy management program, the tuning model identifies target data based on optical character recognition (OCR) from the new input image, identifies an input window within the legacy management program corresponding to the target data, and repeats the operation of inputting and saving the target data into the input window.

8. In Paragraph 1, A data recording automation device, wherein the operation of verifying the new input data includes the operation of determining whether there is an unstored item among the automatically entered new input data, and the operation of displaying the unstored item to the user for model tuning if the unstored item exists.

9. In Paragraph 8, The operation of verifying the new input data mentioned above is, An operation to determine whether the new input data is identical to the existing input data when the above unsaved item does not exist, A data recording automation device comprising an operation to determine whether the data format of the new input data and the data format of the existing input data are the same when the new input data is not the same as the existing input data.

10. In Paragraph 9, A data recording automation device in which, when the new input data is not identical to the existing input data and the data format of the new input data and the data format of the existing input data are not identical, the new input data is displayed to the user for model tuning.

11. Regarding data entry automation methods, A step of creating an automated model based on a manual input process in which a user inputs sample input data displayed on a sample input image into a legacy management program; A step of generating a tuning model by tuning the detailed operation of the automation model based on user feedback regarding the operating status of the automation model; A step of executing the above tuning model to automatically input new input data displayed in the new input image into the above legacy management program; and A data recording automation method comprising: a step of verifying the newly input data automatically entered based on the recording format of the existing input data previously entered into the legacy management program.

Images