After-class trusteeship manual attendance data entry method, system and device and storage medium

Abstract

The invention discloses an after-class trusteeship manual attendance data entry method, system and device and a storage medium, and the method comprises the steps: obtaining to-be-entered attendance record image data, carrying out the OCR character recognition of the attendance record image data, and obtaining an initial attendance record table; generating a prompt statement according to the prompt template and the initial attendance record table, and inputting the prompt statement into a large language model for standardization processing to obtain a standard attendance record table; performing character extraction on the standard attendance record table to obtain attendance characters, and converting the attendance characters into corresponding attendance states to obtain a target attendance record table; matching and determining corresponding attendance teams according to the student names, splitting the target attendance record table into sub-class examination record tables corresponding to the attendance teams, and inputting the sub-class examination record tables into an attendance system of the hosting education platform according to the attendance time periods. The method improves the efficiency and accuracy of after-class trusteeship manual attendance data entry, and can be applied to the technical field of data processing.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method, system, device and storage medium for entering manual attendance data for after-school care. Background Art

[0002] With the development of after-school services and the in-depth advancement of educational informatization, digital management has become an important means to improve management efficiency and enhance the quality of after-school teaching. However, during this digital transformation, after-school services are often implemented simultaneously, and all student attendance is manually recorded by teachers using paper. After integrating into the management platform, many schools are faced with the real-world scenario of having to enter all manual attendance records into the informatization system.

[0003] Manually entering attendance data into the system often leads to inefficiencies, errors, and high labor costs. This is especially true for schools with a large amount of manual attendance data. The extensive data entry process not only slows down the digitization of after-school services but also disrupts the normal teaching work of schools and teachers. Summary of the Invention

[0004] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0005] To this end, an object of an embodiment of the present invention is to provide a method for entering manual attendance data for after-school care, which improves the efficiency and accuracy of entering manual attendance data for after-school care.

[0006] Another object of an embodiment of the present invention is to provide an after-school care manual attendance data entry system.

[0007] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0008] In a first aspect, an embodiment of the present invention provides a method for entering manual attendance data for after-school tutoring, comprising the following steps:

[0009] Obtaining the attendance record image data to be entered, performing OCR text recognition on the attendance record image data, and obtaining an initial attendance record form;

[0010] Generate a prompt statement based on the prompt template and the initial attendance record form, input the prompt statement into the large language model for standardization processing, and obtain a standard attendance record form;

[0011] Extracting characters from the standard attendance record form to obtain attendance characters, converting the attendance characters into corresponding attendance statuses to obtain a target attendance record form;

[0012] The corresponding attendance group is determined based on the student name matching, and the target attendance record form is split into class attendance record forms corresponding to each attendance group, and then the class attendance record forms are entered into the attendance system of the hosting education platform according to the attendance period.

[0013] Furthermore, in one embodiment of the present invention, the step of obtaining the attendance record image data to be entered, performing OCR text recognition on the attendance record image data, and obtaining the initial attendance record form specifically includes:

[0014] Scanning / photographing the manually entered attendance record by a scanner / camera device to obtain the attendance record image data;

[0015] Performing cell segmentation on the attendance record image data using an image segmentation model to obtain a plurality of cell images, and determining the coordinate position of each of the cell images;

[0016] Performing OCR text recognition on each of the cell images to obtain character information corresponding to each of the cell images;

[0017] The character information is arranged according to the coordinate positions to generate the initial attendance record form.

[0018] Furthermore, in one embodiment of the present invention, the step of generating a prompt statement based on the prompt template and the initial attendance record form, inputting the prompt statement into a large language model for standardization processing, and obtaining a standard attendance record form specifically includes:

[0019] Determine a number of table conversion elements according to the attendance business rules, and construct the prompt template according to the table conversion elements;

[0020] Performing format conversion on the initial attendance record form to obtain formatted text that can be recognized by a large language model;

[0021] splicing the prompt template and the formatted text to obtain the prompt sentence, and inputting the prompt sentence into a large language model to obtain a model output text;

[0022] Performing structured data extraction on the model output text to obtain header fields and content fields;

[0023] The standard attendance record form is obtained by mapping the table rows and columns according to the table header field and the content field.

[0024] Furthermore, in one embodiment of the present invention, the step of extracting characters from the standard attendance record form to obtain attendance characters, converting the attendance characters into corresponding attendance statuses, and obtaining a target attendance record form specifically includes:

[0025] Determine a target character area of the attendance character in the standard attendance record form, perform character extraction on each cell of the target character area, and obtain the attendance character;

[0026] Converting the attendance character into the corresponding attendance status according to a preset mapping rule;

[0027] The attendance characters in the target character area are replaced according to the attendance status to obtain the target attendance record form.

[0028] Furthermore, in one embodiment of the present invention, the step of determining the corresponding attendance team according to the student name matching and splitting the target attendance record form into the class attendance record forms corresponding to each attendance team specifically includes:

[0029] Obtain the student names in the target attendance record form, match the student names according to a preset class division database, and obtain the attendance class group corresponding to each student name;

[0030] Add the attendance team corresponding to each student's name to the target attendance record form to obtain a team attendance record form;

[0031] The team attendance record form is screened according to each attendance team, and the screened team attendance record form is saved to obtain the class attendance record form corresponding to each attendance team.

[0032] Furthermore, in one embodiment of the present invention, the step of entering the class attendance record form into the attendance system of the hosting education platform according to the attendance period specifically includes:

[0033] Determine the attendance period corresponding to the class attendance record form;

[0034] Obtaining course schedule information corresponding to the attendance group, and determining the target course corresponding to the class attendance record form according to the course schedule information and the attendance period;

[0035] The class attendance record form is entered into the attendance system of the hosting education platform as the attendance data of the target course.

[0036] Furthermore, in one embodiment of the present invention, before entering the class attendance record form into the attendance system of the hosting education platform according to the attendance period, the following steps are also included:

[0037] The class attendance record form is displayed through a human-computer interaction interface, and relevant personnel are reminded to make adjustments or confirmations.

[0038] In a second aspect, an embodiment of the present invention provides an after-school care manual attendance data entry system, comprising:

[0039] An image recognition module is used to obtain the attendance record image data to be entered, perform OCR text recognition on the attendance record image data, and obtain an initial attendance record form;

[0040] A model processing module is used to generate a prompt statement based on the prompt template and the initial attendance record form, and input the prompt statement into the large language model for standardization processing to obtain a standard attendance record form;

[0041] A character conversion module is used to extract characters from the standard attendance record form to obtain attendance characters, convert the attendance characters into corresponding attendance statuses, and obtain a target attendance record form;

[0042] The form entry module is used to determine the corresponding attendance group based on student name matching, and split the target attendance record form into class attendance record forms corresponding to each attendance group, and then enter the class attendance record forms into the attendance system of the hosting education platform according to the attendance period.

[0043] In a third aspect, an embodiment of the present invention provides an after-school care manual attendance data entry device, comprising:

[0044] at least one processor;

[0045] at least one memory for storing at least one program;

[0046] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for entering manual attendance data for after-school tutoring.

[0047] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor, wherein the program executable by the processor is used to execute the above-mentioned method for entering manual attendance data for after-school tutoring when executed by the processor.

[0048] The advantages and benefits of the present invention will be described in part in the following description and will become apparent from the following description or learned through practice of the present invention:

[0049] The embodiment of the present invention obtains attendance record image data to be entered, performs optical character recognition (OCR) on the attendance record image data to obtain an initial attendance record form, generates a prompt statement based on a prompt template and the initial attendance record form, inputs the prompt statement into a large language model for standardization processing to obtain a standard attendance record form, performs character extraction on the standard attendance record form to obtain attendance characters, converts the attendance characters into corresponding attendance statuses to obtain a target attendance record form, determines the corresponding attendance group based on student name matching, and splits the target attendance record form into sub-class attendance record forms corresponding to each attendance group. The sub-class attendance record forms are then entered into the attendance system of the after-school education platform according to the attendance period. Manual attendance data typically exists in the form of paper records or unstructured electronic documents. The data is scattered and formatted in a non-uniform manner, making it difficult to directly use for system entry. The embodiment of the present invention processes the image data of manual attendance records through OCR technology, a large language model, and table character recognition extraction to output a standardized attendance record form that is convenient for entry into the attendance system of the after-school education platform, thereby improving the efficiency and accuracy of manual attendance data entry for after-school after-school care. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0051] Figure 1 A flowchart of a method for entering manual attendance data for after-school tutoring provided by an embodiment of the present invention;

[0052] Figure 2 A structural block diagram of an after-school care manual attendance data entry system provided by an embodiment of the present invention;

[0053] Figure 3 This is a structural block diagram of a device for entering manual attendance data for after-school tutoring provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided for ease of explanation only and do not limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0055] In the description of the present invention, "a plurality" means two or more. The terms "first" and "second" are used solely to distinguish technical features and are not to be construed as indicating or implying relative importance, or as implicitly indicating the number of the indicated technical features, or as implicitly indicating the order of the indicated technical features. Furthermore, unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art.

[0056] Reference Figure 1 The embodiment of the present invention provides a method for entering manual attendance data for after-school tutoring, which specifically includes the following steps:

[0057] S101, obtaining the attendance record image data to be entered, performing OCR text recognition on the attendance record image data, and obtaining an initial attendance record form;

[0058] S102, generating a prompt statement based on the prompt template and the initial attendance record form, inputting the prompt statement into the large language model for standardization processing, and obtaining a standard attendance record form;

[0059] S103, extracting characters from the standard attendance record form to obtain attendance characters, converting the attendance characters into corresponding attendance statuses, and obtaining a target attendance record form;

[0060] S104: Determine the corresponding attendance team based on the student name matching, split the target attendance record form into class attendance record forms corresponding to each attendance team, and then enter the class attendance record forms into the attendance system of the hosting education platform according to the attendance period.

[0061] Specifically, manual attendance data usually exists in the form of paper records or unstructured electronic documents. The data is scattered and the format is not uniform, making it difficult to use it directly for system entry. The embodiment of the present invention processes the image data of manual attendance records through OCR technology, large language models and table character recognition extraction, and outputs a standardized attendance record form, which is convenient for entering into the attendance system of the managed education platform, thereby improving the efficiency and accuracy of manual attendance data entry for after-school management.

[0062] As an optional implementation method, the step of obtaining the attendance record image data to be entered, performing OCR text recognition on the attendance record image data, and obtaining the initial attendance record form specifically includes:

[0063] Scan / photograph the manually entered attendance record through a scanner / camera device to obtain attendance record image data;

[0064] Perform cell segmentation on the attendance record image data through the image segmentation model to obtain multiple cell images and determine the coordinate position of each cell image;

[0065] Perform OCR text recognition on each cell image to obtain the character information corresponding to each cell image;

[0066] Arrange the character information according to the coordinate position to generate the initial attendance record form.

[0067] Specifically, users can upload photos or files of manual attendance records to be entered on the human-computer interaction interface. The system supports uploading pictures or PDF files, batch uploading, and pre-describing the attendance status represented by symbols in pictures or files to improve the accuracy of subsequent intelligent processing. Through OCR recognition capabilities, large quantities of pictures and files can be recognized, summarized by picture content, upload order and number of pages, and quickly converted into a table format. The specific process is as follows:

[0068] 1) Device parameter settings

[0069] Scanner: Set the resolution to ≥300dpi to ensure that the lines and text in the table are clearly visible; use grayscale or color mode to scan to avoid shadow interference caused by uneven lighting.

[0070] Camera device: Adjust the camera focal length to ensure that the form is fully captured in the frame, turn on the automatic fill light to avoid reflections; use a fixed bracket to prevent shaking, and use perspective correction algorithms (such as Homography transformation) to eliminate tilt or deformation.

[0071] 2) Image optimization

[0072] Denoising: Use Gaussian filtering or median filtering to eliminate image noise.

[0073] Binarization: Use adaptive thresholding methods (such as the Otsu algorithm) to convert the image to black and white to enhance the contrast between table lines and text.

[0074] 3) Table structure detection

[0075] Based on edge detection: Use the Canny algorithm to extract the edges of table lines, combine it with Hough transform to detect straight lines, and locate horizontal and vertical intersections to divide cells.

[0076] Based on projection analysis: perform horizontal and vertical projection on the binary image, and determine the row and column boundaries through peaks and troughs. It is suitable for tables without borders or broken lines.

[0077] 4) Coordinate marking

[0078] For each segmented cell, record the coordinates of its upper left corner and lower right corner (with the upper left corner of the image as the origin) and generate a coordinate mapping table, for example: {"cell_1":(x1,y1,x2,y2),...}.

[0079] 5) Text area processing

[0080] Perform local contrast enhancement on each cell image and use Tesseract OCR or deep learning models (such as CRNN) to recognize text.

[0081] For handwriting: Use an attention-based OCR model combined with adversarial training to improve recognition rate.

[0082] 6) Data cleaning

[0083] Rule verification: For example, checking the validity of the date format (YYYY-MM-DD) and time format (HH:MM).

[0084] Semantic error correction: Correct typos through NLP models (such as BERT).

[0085] 7) Data Arrangement: Sort the recognition results by rows and columns according to the coordinate mapping table, and merge cells that span rows or columns (based on coordinate overlap).

[0086] 8) Format export: Generate structured data (such as CSV, Excel), retaining the original table style (font, alignment).

[0087] As an optional implementation, a prompt statement is generated based on the prompt template and the initial attendance record form, and the prompt statement is input into the large language model for standardization processing to obtain a standard attendance record form. This step specifically includes:

[0088] Determine several form conversion elements according to attendance business rules, and build prompt templates based on the form conversion elements;

[0089] Convert the format of the initial attendance record form to obtain formatted text that can be recognized by the large language model;

[0090] The prompt template and formatted text are concatenated to obtain a prompt sentence, and the prompt sentence is input into the large language model to obtain the model output text;

[0091] Extract structured data from the model output text to obtain header fields and content fields;

[0092] Map the table rows and columns according to the header fields and content fields to obtain a standard attendance record table.

[0093] Specifically, the output table is converted into markdown language that is easy for the large language model to understand, and then input into the large language model. Combined with standardized prompts and user-defined prompts, the large language model converts some characters in the cells and outputs a standardized structured document that can be processed by the platform. The specific process is as follows:

[0094] 1) Business rule analysis: Based on the attendance business rules, clarify the statistical dimensions (such as the number of lateness / early departure, leave type, etc.) and define key conversion factors (such as date range, student ID, exception type, etc.).

[0095] 2) Prompt template design

[0096] Structural directives: Define the output schema (such as JSON Schema) to ensure that the model return fields match the target table headers.

[0097] Sample template: The above is the school's attendance record form. Please re-output an attendance record form based on the above content. The table headers are name, class, and date (horizontally). If the student signs in, mark 1; if the student takes leave, mark "0".

[0098] 3) Data cleaning and standardization: Delete merged cells and unify time formats (e.g., convert "08:30AM" to a standardized timestamp).

[0099] Outlier annotation: Mark invalid data such as duplicate punch-ins and missing cards.

[0100] 4) Generate formatted text: Convert the table into a text structure that can be parsed by the large model, such as markdown language.

[0101] 5) Prompt statement splicing: Combine the prompt template with the formatted text to generate a complete instruction.

[0102] 6) Large language model call: Use a local LLM (such as Llama3) or cloud API to input the concatenated prompt sentence and obtain the original output text containing structured fields.

[0103] 7) Data extraction and verification

[0104] Regular matching: Extract key-value pairs through patterns (such as "student ID":"(.*?)").

[0105] Anomaly detection: Compare the original data with the number of model output entries to prevent missed processing.

[0106] 8) Header field generation

[0107] Extract unique key names from the model output as table headers, for example: ["Student ID","Date","Attendance Status","Class Hour Deviation"].

[0108] 9) Row and column mapping logic

[0109] Vertical alignment: Match content fields to corresponding columns based on JSON key names.

[0110] Horizontal expansion: Dynamically add derived fields (such as "monthly attendance rate" = actual attendance days / expected attendance days).

[0111] 10) Generate standard table: Use Python's pandas or Excel formulas to generate the final table according to the mapping relationship to achieve standard attendance record table output.

[0112] As an optional implementation method, the step of extracting characters from the standard attendance record form to obtain attendance characters, converting the attendance characters into corresponding attendance statuses, and obtaining the target attendance record form specifically includes:

[0113] Determine the target character area of the attendance characters in the standard attendance record form, extract characters from each cell in the target character area, and obtain the attendance characters;

[0114] Convert attendance characters into corresponding attendance status according to preset mapping rules;

[0115] The attendance characters in the target character area are replaced according to the attendance status to obtain a target attendance record form.

[0116] Specifically, the system converts the standard characters in the standard attendance form into standard attendance status for after-school services such as signing in, asking for leave, attending quality classes, and not attending classes. The specific process is as follows:

[0117] 1) Determine the target character area

[0118] Locate the attendance symbol area: In a standard attendance record form, the target character area is typically the range of cells that record students' daily attendance status, such as the cell where the date column intersects the student name row. For example, a student's attendance on "2024-09-01" is indicated by a "√" symbol in the cell.

[0119] Note the table structure: the header usually contains a date column (from the beginning of the month to the end of the month), a student name column on the left, and the core data area is a "date × name" matrix.

[0120] Data validation and boundary processing: Check whether the cell format is uniform (such as text, numbers or symbols) to avoid extraction failures caused by merged cells or format errors.

[0121] Handle blank or abnormal values: If a cell is empty, mark it as "absent" or fill it with a default value according to the rules.

[0122] 2) Character extraction and conversion

[0123] Manual extraction: directly read the symbols in the cell (such as "√", "B", "+", etc.), which is suitable for small-scale data.

[0124] Automated Extraction: Use scripts (such as Excel formulas, VBA, or Python) to batch read the cell contents in the target area. Example formula: =INDIRECT(ADDRESS(row number, column number)) or iterate over cells and assign values to an array.

[0125] Mapping rule settings: Preset the correspondence between symbols and attendance status, for example: √ → normal attendance; B → leave; - → late; * → early departure. The mapping relationship is stored in a dictionary table for easy maintenance and expansion.

[0126] 3) Character replacement and target table generation

[0127] Cell-by-cell replacement: Replace symbols with text descriptions based on extracted characters and mapping rules. For example, replace "B" with "Request for Leave."

[0128] Batch Replacement Tool:

[0129] Excel: Use the SUBSTITUTE function or the Find and Replace function (Ctrl+H).

[0130] Script: Loop through cells and replace via VBA macro or Python pandas library.

[0131] Generate the final table: In the target area after replacement, the original table structure is retained and only the symbols are modified to status texts.

[0132] Add auxiliary columns: for example, count the number of lateness and attendance rate, and use formulas (such as COUNTIF) to automatically calculate.

[0133] As an optional implementation method, the step of determining the corresponding attendance team according to the student name matching and splitting the target attendance record form into the class attendance record forms corresponding to each attendance team specifically includes:

[0134] Obtain the student names in the target attendance record form, match the student names according to the preset class database, and obtain the attendance class group corresponding to each student name;

[0135] Add the attendance team corresponding to each student's name to the target attendance record form to obtain the team attendance record form;

[0136] The team attendance record forms are screened according to each attendance team, and the screened team attendance record forms are saved to obtain the class attendance record forms corresponding to each attendance team.

[0137] Specifically, the attendance group is automatically matched according to the student's name, so that the target attendance record form is split into the class attendance record forms corresponding to each attendance group. The specific process is as follows:

[0138] 1) Establish a class database

[0139] Structure example: student name (unique identifier), student ID, class name; add the student ID field to avoid confusion among students with the same name.

[0140] Storage format: Excel worksheet (such as "class database") or database table (such as Access / SQLite).

[0141] 2) Attendance team matching: Obtain student names one by one from the student name row of the target attendance record table, search and match them in the class database to obtain the corresponding attendance team.

[0142] 3) Add a new team column: Insert a "team" column on the far right of the attendance sheet and fill in the student's name corresponding to the attendance team.

[0143] 4) Filter and save: Filter the table data corresponding to the same attendance team and save it to a new worksheet to obtain the class attendance record table corresponding to each attendance team.

[0144] As an optional implementation method, the step of entering the class attendance record form into the attendance system of the hosting education platform according to the attendance period specifically includes:

[0145] Determine the attendance period corresponding to the class attendance record form;

[0146] Obtain the course schedule information corresponding to the attendance group, and determine the target course corresponding to the class attendance record form based on the course schedule information and attendance period;

[0147] Enter the class attendance record form as the attendance data of the target course into the attendance system of the managed education platform.

[0148] Specifically, all attendance times in the class attendance record form are counted to obtain the corresponding attendance period, and then the target course corresponding to the class attendance record form is determined according to the course schedule information of the attendance group, so that the class attendance record form is entered into the attendance system of the hosting education platform as the attendance data of the target course.

[0149] As an optional implementation method, before entering the class attendance record form into the attendance system of the hosting education platform according to the attendance period, the following steps are also included:

[0150] The class attendance record form is displayed through the human-computer interaction interface, and relevant personnel are reminded to make adjustments or confirmations.

[0151] Specifically, before entering the class attendance record form, the form must be displayed through the human-computer interaction interface, and manual adjustments and confirmation must be made. Attendance data that cannot be matched to the class can be manually linked. Unrecognizable students can be manually linked to students of the same school. Special symbols that cannot be processed can be batch-set to corresponding attendance status. Manual adjustments and confirmations will further improve the accuracy of attendance data entry.

[0152] The above describes the method steps of the embodiment of the present invention. It is understandable that manual attendance data usually exists in the form of paper records or unstructured electronic documents, the data is scattered and the format is not uniform, and it is difficult to use directly for system entry. The embodiment of the present invention processes the image data of manual attendance records through OCR technology, large language model and table character recognition extraction, and outputs a standardized attendance record form, which is convenient for entering the attendance system of the hosting education platform, and improves the efficiency and accuracy of after-school hosting manual attendance data entry; through the implementation of the present invention, school users only need to upload pictures or scans of manual attendance data tables taken by mobile phones to quickly complete the recognition processing and enter attendance data, effectively improving the efficiency of manual attendance entry, greatly reducing school labor costs, and speeding up the speed of digital management of school after-school services.

[0153] Reference Figure 2 The embodiment of the present invention provides an after-school care manual attendance data entry system, comprising:

[0154] The image recognition module is used to obtain the attendance record image data to be entered, perform OCR text recognition on the attendance record image data, and obtain the initial attendance record form;

[0155] The model processing module is used to generate prompt sentences based on the prompt template and the initial attendance record form, input the prompt sentences into the large language model for standardization processing, and obtain a standard attendance record form;

[0156] The character conversion module is used to extract characters from the standard attendance record form to obtain attendance characters, convert the attendance characters into corresponding attendance status, and obtain the target attendance record form;

[0157] The form entry module is used to determine the corresponding attendance group based on student name matching, and split the target attendance record form into class attendance record forms corresponding to each attendance group, and then enter the class attendance record forms into the attendance system of the managed education platform according to the attendance period.

[0158] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0159] Reference Figure 3 The embodiment of the present invention provides a device for entering manual attendance data for after-school tutoring, comprising:

[0160] at least one processor;

[0161] at least one memory for storing at least one program;

[0162] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for entering manual attendance data for after-school tutoring.

[0163] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0164] An embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor. When the program is executed by the processor, it is used to execute the above-mentioned method for entering manual attendance data for after-school tutoring.

[0165] A computer-readable storage medium according to an embodiment of the present invention can execute a method for entering manual attendance data for after-school care provided by an embodiment of the method according to the present invention, can execute any combination of implementation steps of the embodiment of the method, and has the corresponding functions and beneficial effects of the method.

[0166] The embodiment of the present invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs Figure 1 The method shown.

[0167] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0168] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art can implement the present invention set forth in the claims using ordinary skills without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0169] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0170] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0171] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable media on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0172] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0173] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0174] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0175] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for entering manual attendance data for after-school tutoring, characterized in that: The following steps are involved: Obtaining the attendance record image data to be entered, performing OCR text recognition on the attendance record image data, and obtaining an initial attendance record form; Generate a prompt statement based on the prompt template and the initial attendance record form, input the prompt statement into the large language model for standardization processing, and obtain a standard attendance record form; Extracting characters from the standard attendance record form to obtain attendance characters, converting the attendance characters into corresponding attendance statuses to obtain a target attendance record form; The corresponding attendance group is determined based on the student name matching, and the target attendance record form is split into class attendance record forms corresponding to each attendance group, and then the class attendance record forms are entered into the attendance system of the hosting education platform according to the attendance period.

2. A method for entering manual attendance data for after-school tutoring according to claim 1, characterized in that: The step of obtaining the attendance record image data to be entered, performing OCR text recognition on the attendance record image data, and obtaining an initial attendance record form specifically includes: Scanning / photographing the manually entered attendance record by a scanner / camera device to obtain the attendance record image data; Performing cell segmentation on the attendance record image data using an image segmentation model to obtain a plurality of cell images, and determining the coordinate position of each of the cell images; Performing OCR text recognition on each of the cell images to obtain character information corresponding to each of the cell images; The character information is arranged according to the coordinate positions to generate the initial attendance record form.

3. A method for entering manual attendance data for after-school tutoring according to claim 1, characterized in that: The step of generating a prompt statement based on the prompt template and the initial attendance record form, inputting the prompt statement into a large language model for standardization processing, and obtaining a standard attendance record form specifically includes: Determine a number of table conversion elements according to the attendance business rules, and construct the prompt template according to the table conversion elements; Performing format conversion on the initial attendance record form to obtain formatted text that can be recognized by a large language model; splicing the prompt template and the formatted text to obtain the prompt sentence, and inputting the prompt sentence into a large language model to obtain a model output text; Performing structured data extraction on the model output text to obtain header fields and content fields; The standard attendance record form is obtained by mapping the table rows and columns according to the table header field and the content field.

4. A method for entering manual attendance data for after-school care according to claim 1, characterized in that: The step of extracting characters from the standard attendance record form to obtain attendance characters, converting the attendance characters into corresponding attendance states, and obtaining a target attendance record form specifically includes: Determine a target character area of the attendance character in the standard attendance record form, perform character extraction on each cell of the target character area, and obtain the attendance character; Converting the attendance character into the corresponding attendance status according to a preset mapping rule; The attendance characters in the target character area are replaced according to the attendance status to obtain the target attendance record form.

5. A method for entering manual attendance data for after-school tutoring according to claim 1, characterized in that: The step of determining the corresponding attendance team according to the student name matching and splitting the target attendance record form into the class attendance record forms corresponding to each attendance team specifically includes: Obtain the student names in the target attendance record form, match the student names according to a preset class division database, and obtain the attendance class group corresponding to each student name; Add the attendance team corresponding to each student's name to the target attendance record form to obtain a team attendance record form; The team attendance record form is screened according to each attendance team, and the screened team attendance record form is saved to obtain the class attendance record form corresponding to each attendance team.

6. A method for entering manual attendance data for after-school care according to claim 1, characterized in that: The step of entering the class attendance record form into the attendance system of the hosting education platform according to the attendance period specifically includes: Determine the attendance period corresponding to the class attendance record form; Obtaining course schedule information corresponding to the attendance group, and determining the target course corresponding to the class attendance record form according to the course schedule information and the attendance period; The class attendance record form is entered into the attendance system of the hosting education platform as the attendance data of the target course.

7. A method for entering manual attendance data for after-school care according to any one of claims 1 to 6, characterized in that: Before entering the class attendance record form into the attendance system of the hosting education platform according to the attendance period, the following steps are also included: The class attendance record form is displayed through a human-computer interaction interface, and relevant personnel are reminded to make adjustments or confirmations.

8. A manual attendance data entry system for after-school care, characterized in that: include: An image recognition module is used to obtain the attendance record image data to be entered, perform OCR text recognition on the attendance record image data, and obtain an initial attendance record form; A model processing module is used to generate a prompt statement based on the prompt template and the initial attendance record form, and input the prompt statement into the large language model for standardization processing to obtain a standard attendance record form; A character conversion module is used to extract characters from the standard attendance record form to obtain attendance characters, convert the attendance characters into corresponding attendance statuses, and obtain a target attendance record form; The form entry module is used to determine the corresponding attendance group based on student name matching, and split the target attendance record form into class attendance record forms corresponding to each attendance group, and then enter the class attendance record forms into the attendance system of the hosting education platform according to the attendance period.

9. A manual attendance data entry device for after-school care, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the after-school care manual attendance data entry method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to execute the after-school care manual attendance data entry method according to any one of claims 1 to 7 when executed by the processor.

Images