Question recording method and system based on intelligent adaptation progressive intelligent learning

Abstract

The invention relates to a question recording method and system based on intelligent adaptive progressive intelligent learning, and provides a comprehensive test question recording method which can perform test question intelligent recording on a single question or a whole test question page. Before test questions are input, a test question data packet corresponding to the progress (gradient / difficulty) is called according to the current learning progress of a student, distinctive input is performed according to the type of the test questions, single questions are directly input into a test question bank, and single question automatic input is performed on a test question page by combining single question segmentation and an OCR and LLM large language model recognition technology. Therefore, auxiliary question recording can be carried out in combination with an intelligent technology, the question recording efficiency is improved, question recording of the corresponding stage can be carried out according to the current learning progress of the user, progressive question recording learning can be carried out by matching with the learning progress of students, the question doing speed of the students adapts to the learning progress, and the learning efficiency and level are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a question recording method and system and electronic device based on intelligent adaptive progressive intelligent learning. Background Art

[0002] Learning by recording questions is an effective learning method that can help users understand and master knowledge more deeply. By learning by recording questions, you can improve your learning efficiency and cultivate logical thinking and expression skills. At the same time, this method can also help students and other users find problems in the learning process and adjust their learning strategies in time.

[0003] The traditional recording methods mainly include the following: 1. Word document input; 2. Manually input into the online question bank system; 3. Scan the paper questions and use OCR recognition; 4. Use voice recognition technology for input.

[0004] Although the test questions can be input, there are different technical application defects: first, the efficiency of Word document input is low and prone to errors; second, manual input into the online question bank system takes a long time; third, OCR recognition may have recognition errors and requires manual verification; finally, voice recognition is greatly affected by environmental noise and has limited accuracy. Therefore, most traditional input methods are still manual operations, which are mainly inefficient.

[0005] In addition, in the process of entering a whole page (not a single question) of test questions, in the traditional recording methods, except for OCR technology, the other methods all require entering the single questions on the page one by one, so the efficiency is relatively low and it is easy to make mistakes. In the recording process, there are also mixed materials of whole page test questions and single questions. The traditional recording method cannot quickly and efficiently enter the test questions according to the type of test questions to be entered.

[0006] Finally, the traditional question entry method mainly involves entering assessment questions, so it rarely involves the entry of reinforcement learning questions, and it is impossible to automatically and progressively enter questions based on students' learning situation. Summary of the invention

[0007] In order to solve the above problems, the present application proposes a question recording method, system and electronic device based on adaptive progressive intelligent learning.

[0008] On the one hand, the present application proposes a method for recording questions based on intelligent adaptive progressive intelligent learning, comprising the following steps: S1. Get the user's current learning progress; S2, reading and filtering from the background database to obtain the test questions to be entered that match the user's current learning progress; S3. Determine the type of the test question to be entered: (1) If the test question to be entered is a single question, the LLM large language model is used to identify the test content of the single question and automatically enter it into the test question database; (2) If the test question to be entered is a test question page, then using an image contour recognition algorithm to identify the contour of the area where each question in the test question page is located; According to the area outline, the test question page is divided into single question pages to obtain a plurality of single question pages; Using an OCR text recognition algorithm, traverse and recognize text information in each of the single question pages, including: text, symbols, numbers and / or English characters related to the question and answer; Using the LLM large language model to identify the questions and answers in the text information, obtain the corresponding test content and automatically enter it into the test database; S4, the user logs in to the question bank, reads and studies each question of the current learning progress; S5. After learning, refer to the above steps to enter and study the test questions for the next stage of learning progress.

[0009] As an optional implementation scheme of the present application, optionally, the following steps are also included: When the user has finished studying all the questions in the current learning progress, the system will automatically record and generate the corresponding learning log; At the same time, a notification for entering the next stage of test questions is sent to the user.

[0010] As an optional implementation scheme of the present application, optionally, the following steps are also included: Preparing and preprocessing the test questions to be entered corresponding to different learning progress in advance, wherein the preprocessing includes: color marking the area where each test question to be entered in the test question page is located, and if there are multiple test questions to be entered, there is no overlap between the color marked areas; Binding the test questions to be entered with the corresponding learning progress to generate a test question data package for the corresponding learning stage; Each of the test question data packets is stored in the background database.

[0011] As an optional implementation scheme of the present application, optionally, S2, reading and screening from the background database to obtain test questions to be entered that match the user's current learning progress, including: Read the user's current learning progress from the log module and send it to the backend database; Generate an SQL retrieval instruction of the current learning progress and send it to the backend database; The backend database executes the SQL search instruction to retrieve and feed back the test question data package that matches the user's current learning progress; The test question data packet is parsed to obtain a number of test questions to be entered that match the user's current learning progress.

[0012] As an optional implementation scheme of the present application, optionally, in step S3, after traversing and identifying the text information in each of the single-title pages using an OCR text recognition algorithm, the method further includes: According to the text information, assembling matching questions and answers to generate a number of single questions; Use the LLM large language model to identify keywords in each question and determine whether there are questions with the same title: If it exists, deduplication is performed; Otherwise give up.

[0013] As an optional implementation scheme of the present application, optionally, in step S3, after traversing and identifying the text information in each of the single-title pages using an OCR text recognition algorithm, the method further includes: Attribute annotation is performed on each question, and the subject, chapter and knowledge point information to which the question belongs are marked; Send each marked question to the management end for confirmation.

[0014] On the other hand, the present application proposes a system for implementing the method for recording questions based on intelligent adaptive progressive intelligent learning, comprising: The user end is used to log in to the backend server, participate in the test question entry and the test question study corresponding to the learning progress; On the management side, log in to the backend server and participate in the review of test questions and corresponding learning progress; Backend server, including: User management module, used to manage students and administrators; The learning progress recording module is used to automatically record the learning log of each stage of the students, and send a notification to the user to enter the next stage of test questions after the user has finished learning each test question of the current learning progress; The test question screening module is used to read and screen the test questions to be entered that match the user's current learning progress from the background database; The test question input module is used to determine the type of the test question to be input: (1) If the test question to be entered is a single question, the LLM large language model is used to identify the test content of the single question and automatically enter it into the test question database; (2) If the test question to be entered is a test question page, then using an image contour recognition algorithm to identify the contour of the area where each question in the test question page is located; According to the area outline, the test question page is divided into single question pages to obtain a plurality of single question pages; Using an OCR text recognition algorithm, traverse and recognize text information in each of the single question pages, including: text, symbols, numbers and / or English characters related to the question and answer; Using the LLM large language model to identify the questions and answers in the text information, obtain the corresponding test content and automatically enter it into the test database; Backend database, used to store test question data packets; LLM large language model port, used to call the LLM large language model; The user management module, learning progress recording module, test question screening module, test question entry module, LLM large language model port and backend database are all deployed on the backend server; The user end and the management end are respectively connected to the background server for communication.

[0015] In another aspect, the present application further provides an electronic device, comprising: processor; a memory for storing processor-executable instructions; Among them, the processor is configured to implement the method of recording questions based on adaptive progressive intelligent learning when executing the executable instructions.

[0016] Technical effects of the present invention: The present invention proposes a comprehensive test question entry method, which can intelligently enter test questions for a single question or a whole page of test questions. Before entering the test questions, first retrieve the test question data package of the corresponding progress (gradient / difficulty) according to the student's current learning progress, and perform differential entry according to the test question type. The single question is directly entered into the test question library, and the test question page combines single question segmentation, OCR and LLM large language model recognition technology to automatically enter the single question. Therefore, the present invention can combine intelligent technology to assist in question recording, improve the efficiency of test question entry, and can enter the test questions of the corresponding stage according to the user's current learning progress, and can match the student's learning progress to perform progressive question recording and learning, so that the student's speed of answering questions is adapted to the learning progress, and improve the learning efficiency and level.

[0017] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0019] Figure 1It is shown as a schematic diagram of the implementation process of the present invention; Figure 2 Shown is a schematic diagram of the process of recording a question of the present invention; Figure 3 A schematic diagram showing the outline marking of a test question page of the present invention is shown; Figure 4 Shown is a schematic diagram of the system composition structure of the present invention; Figure 5 It is a schematic diagram showing the application of the electronic device of the present invention. DETAILED DESCRIPTION

[0020] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0021] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0022] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure. Example 1

[0023] like Figure 1 As shown, on the one hand, the present application proposes a method for recording questions based on intelligent adaptive progressive intelligent learning, comprising the following steps: S1. Get the user's current learning progress; S2, reading and filtering from the background database to obtain the test questions to be entered that match the user's current learning progress; S3. Determine the type of the test question to be entered: (1) If the test question to be entered is a single question, the LLM large language model is used to identify the test content of the single question and automatically enter it into the test question database; (2) If the test question to be entered is a test question page, then using an image contour recognition algorithm to identify the contour of the area where each question in the test question page is located; According to the area outline, the test question page is divided into single question pages to obtain a plurality of single question pages; Using an OCR text recognition algorithm, traverse and recognize text information in each of the single question pages, including: text, symbols, numbers and / or English characters related to the question and answer; Using the LLM large language model to identify the questions and answers in the text information, obtain the corresponding test content and automatically enter it into the test database; S4, the user logs in to the question bank, reads and studies each question of the current learning progress; S5. After learning, refer to the above steps to enter and study the test questions for the next stage of learning progress.

[0024] The following will be combined with the attached Figure 2 The implementation process of the present invention is described in detail with reference to the recording process shown in FIG.

[0025] The present invention will combine the students' learning progress to enter and study the test questions of the corresponding stage (level / difficulty).

[0026] Specific test questions for different stages can be prepared by the user himself or by the administrator.

[0027] The management of students (users) and teachers (administrators) can be done through the teacher-student management system on the backend server. The learning progress of students can be recorded by the system or reviewed and assessed by administrators. The system can also automatically generate corresponding learning logs and identify the user's learning progress based on the learning logs.

[0028] As an optional implementation scheme of the present application, optionally, the following steps are also included: When the user has finished studying all the questions in the current learning progress, the system will automatically record and generate the corresponding learning log; At the same time, a notification for entering the next stage of test questions is sent to the user.

[0029] The background system will automatically record the students' learning progress. Once the current stage of test questions is completed, the system will automatically record and issue a learning notification for the next stage, thereby advancing learning adaptively.

[0030] As an optional implementation scheme of the present application, optionally, the following steps are also included: Preparing and preprocessing the test questions to be entered corresponding to different learning progress in advance, wherein the preprocessing includes: color marking the area where each test question to be entered in the test question page is located, and if there are multiple test questions to be entered, there is no overlap between the color marked areas; Binding the test questions to be entered with the corresponding learning progress to generate a test question data package for the corresponding learning stage; Each of the test question data packets is stored in the background database.

[0031] As for the test questions for students at different stages, the administrator or students can prepare the test questions to be entered corresponding to the learning progress.

[0032] In order to facilitate the subsequent contour recognition in step S3, the area where each of the test questions to be entered in the test question page is located is marked with a color, so that when performing contour recognition, the contour of the area where each test question is located can be identified according to the marked area ( Figure 3 The test page shown is not marked with area color). The color mark should be a light color to avoid too dark color affecting OCR recognition. The administrator can operate the light color mark.

[0033] Students' learning progress can be automatically read from the system.

[0034] As an optional implementation scheme of the present application, optionally, S2, reading and screening from the background database to obtain test questions to be entered that match the user's current learning progress, including: Read the user's current learning progress from the log module and send it to the backend database; Generate an SQL retrieval instruction of the current learning progress and send it to the backend database; The backend database executes the SQL search instruction to retrieve and feed back the test question data package that matches the user's current learning progress; The test question data packet is parsed to obtain a number of test questions to be entered that match the user's current learning progress.

[0035] In the initial stage, that is, the first learning stage, the user can import the entity data package of the corresponding stage by himself. The system starts to record the learning progress of the first stage. In the process of entering test questions in the subsequent stage, the system can read the learning progress of the current user from the log module, and if the current learning progress is, for example, the second stage, the test question data package of the corresponding stage can be retrieved in the background. The present invention adopts SQL retrieval instructions: first, an SQL retrieval instruction of the current learning progress is generated, and the retrieval instruction contains the association description of the current test question and the corresponding learning progress. The background database will execute the SQL instruction and retrieve and feedback the corresponding test question data package. The data package is parsed in the test question screening module to obtain a corresponding number of test questions to be entered.

[0036] The SQL search steps are: parsing SQL instructions, extracting key information such as query conditions, table names, and field names; locating the corresponding database table based on the extracted information; filtering out records that meet the query conditions in the database table; extracting the required data fields from the filtered records based on the field names. Organizing the extracted data fields into a result set and returning it to the user.

[0037] Next, intelligent assisted entry will be carried out based on the type of test questions.

[0038] S3. Determine the type of the test question to be entered: (1) If the test question to be entered is a single question, the LLM agent is used to identify the test content of the single question and automatically enter it into the test question database; A single question means there is only one question. This type of question can be directly entered into the question bank.

[0039] The present invention adopts the LLM large language model to automatically enter the corresponding single-question test content, which may specifically include the following steps: Through the LLM large language model port on the background, a model call request is sent to a third party, or a corresponding test question automatic entry request is generated and sent to a third party; Read the test document content through the LLM large language model; Use the LLM model to preprocess the document, including word segmentation and stop word removal; Identify the topic part of the text, which is usually located at the beginning of a paragraph or marked with a specific format; Identify the answer section in the text, which may be located below the question or marked in a specific format; Structuring the identified questions and answers to form a standard format; The structured question and answer data are stored in the question bank, including question content, answer content, question type and other information; at the same time, the question bank can also be indexed for subsequent retrieval and use.

[0040] (2) If the test question to be entered is a test question page, then using an image contour recognition algorithm to identify the contour of the area where each question in the test question page is located; According to the area outline, the test question page is divided into single question pages to obtain a plurality of single question pages; Using an OCR text recognition algorithm, traverse and recognize text information in each of the single question pages, including: text, symbols, numbers and / or English characters related to the question and answer; Using the LLM large language model to identify the questions and answers in the text information, obtain the corresponding test content and automatically enter it into the test database; If it is a test question page, it is necessary to combine contour recognition, OCR text recognition and LLM large language model for intelligent assisted input.

[0041] Because each test page contains several test questions, they need to be identified separately. Therefore, contour recognition, OCR text recognition, and intelligent recognition and extraction of test questions using the LLM large language model, as well as corresponding automated operations, are required.

[0042] The steps of using the image contour recognition algorithm to identify and mark the question areas on the test paper may be: 1. Image preprocessing: Grayscale the test paper image and convert the color image into a grayscale image to simplify subsequent processing.

[0043] Apply filtering techniques, such as Gaussian filtering, to remove noise and unnecessary details from the image.

[0044] 2. Edge Detection: Use edge detection algorithms, such as Canny edge detection, to identify edges and contours on the test paper.

[0045] This step aims to highlight the boundaries of the test area for subsequent contour extraction.

[0046] 3. Contour extraction: Based on edge detection, contour extraction algorithms (such as the findContours function in OpenCV) are used to identify the contours on the test paper.

[0047] These contours correspond to the outer boundaries of the test area.

[0048] 4. Contour analysis and marking: Analyze the extracted contour and determine whether it belongs to the test area based on its shape, size and other features.

[0049] Contours that meet the characteristics of the test area are marked for subsequent processing.

[0050] 5. Region cropping and storage: According to the marked outline, cut out the corresponding Figure 3 Image of the test area shown.

[0051] These cropped images are stored in a database for subsequent OCR recognition or manual marking.

[0052] By marking the outline of the test page, it is easy to realize the subsequent OCR and LLM automatic processing of single questions on each page: the whole process is automated and no manual intervention is required, which greatly improves the efficiency of test paper processing. High accuracy: Through precise outline recognition and marking, each test question area on the test paper can be accurately identified. Scalability: This method is suitable for test papers of different types and formats, and has strong versatility and scalability.

[0053] For using the LLM large language model to identify the test content and automatically enter the test question database, the steps can be: 1. Test question recognition: Use the LLM large language model to parse the text and identify the test question content. LLM can learn language rules from a large amount of text data and accurately identify test questions.

[0054] 2. Question classification: Classify the identified questions according to the question type (such as multiple-choice questions, fill-in-the-blank questions, etc.).

[0055] 3. Automatic entry: The classified test questions are automatically entered into the test question bank for easy subsequent management and use.

[0056] The specific understanding can be combined with the LLM identification in the previous single question identification.

[0057] Advantages of using LLM for test content recognition: ‌Efficient and accurate‌: The LLM large language model can efficiently and accurately identify the content of test questions, reducing manual entry errors; ‌Automated processing‌: The entire process is automated, saving manpower and time costs; ‌Scalability‌: Suitable for test question recognition and entry in different disciplines and fields; Using the LLM large language model to identify test question content and automatically enter it into the test question database can significantly improve the efficiency and accuracy of test question processing, bringing convenience to the fields of education and examinations. ‌ The OCR text recognition algorithm and the image contour recognition algorithm are not limited in this embodiment, and the user can select the corresponding algorithm to perform corresponding operations.

[0058] S4, the user logs in to the question bank, reads and studies each question of the current learning progress; S5. After learning, refer to the above steps to enter and study the test questions for the next stage of learning progress.

[0059] Automatically inputting the test questions of the corresponding stage can effectively improve the efficiency of recording questions, reduce the time of recording questions, and speed up the user's learning process of test questions. After the test question library is formed, students can log in to the backend server through the user end such as APP, enter the test question input module, and select the test questions of this stage from the test question library to answer questions and study. The system will record the progress of this study. After the study is completed, the system will send the corresponding next stage of learning task notification to the user end or the management end. In this way, learning can be promoted.

[0060] As an optional implementation scheme of the present application, optionally, in step S3, after traversing and identifying the text information in each of the single-title pages using an OCR text recognition algorithm, the method further includes: According to the text information, assembling matching questions and answers to generate a number of single questions; Use the LLM large language model to identify keywords in each question and determine whether there are questions with the same title: If it exists, deduplication is performed; Otherwise give up.

[0061] For the test page, in order to avoid the duplication of multiple test questions, noise reduction and deduplication are performed. Here, the LLM large language model is used to identify the keywords in each single question and determine whether there are single questions with the same title (multiple single questions obtained after the test page is processed). If so, deduplication is performed.

[0062] Read the text data to be processed through the LLM large language model (that is, each single topic after segmentation and recognition); Split text data into sentences or paragraphs; Use the LLM large language model to encode each sentence or paragraph; Compare the encoded vectors to find repeated or similar sentences or paragraphs; Mark or delete repeated sentences or paragraphs; Recombine the remaining sentences or paragraphs to generate the deduplicated text; Output the processed text data.

[0063] The thresholds or parameters for deduplication and noise reduction can be configured in the LLM model in advance.

[0064] As an optional implementation scheme of the present application, optionally, in step S3, after traversing and identifying the text information in each of the single-title pages using an OCR text recognition algorithm, the method further includes: Attribute annotation is performed on each question, and the subject, chapter and knowledge point information to which the question belongs are marked; Send each marked question to the management end for confirmation.

[0065] After the test questions are entered, the questions are deduplicated and noise-reduced to avoid repeated test questions. The administrator can also confirm the annotation information to facilitate learning the accurate test question content.

[0066] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory. Example 2

[0067] As shown in the figure, based on the implementation principle of Example 1, on the other hand, the present application proposes a system for implementing the method for recording questions based on intelligent adaptive progressive intelligent learning, including: The user end is used to log in to the backend server, participate in the test question entry and the test question study corresponding to the learning progress; On the management side, log in to the backend server and participate in the review of test questions and corresponding learning progress; Backend server, including: User management module, used to manage students and administrators; The learning progress recording module is used to automatically record the learning log of each stage of the students, and send a notification to the user to enter the next stage of test questions after the user has finished learning each test question of the current learning progress; The test question screening module is used to read and screen the test questions to be entered that match the user's current learning progress from the background database; The test question input module is used to determine the type of the test question to be input: (1) If the test question to be entered is a single question, the LLM large language model is used to identify the test content of the single question and automatically enter it into the test question database; (2) If the test question to be entered is a test question page, then using an image contour recognition algorithm to identify the contour of the area where each question in the test question page is located; According to the area outline, the test question page is divided into single question pages to obtain a plurality of single question pages; Using an OCR text recognition algorithm, traverse and recognize text information in each of the single question pages, including: text, symbols, numbers and / or English characters related to the question and answer; Using the LLM large language model to identify the questions and answers in the text information, obtain the corresponding test content and automatically enter it into the test database; Backend database, used to store test question data packets; LLM large language model port, used to call the LLM large language model; The user management module, learning progress recording module, test question screening module, test question entry module, LLM large language model port and backend database are all deployed on the backend server; The user end and the management end are respectively connected to the background server for communication.

[0068] The above interactions between the user terminal, the management terminal and the backend server may be understood and implemented in conjunction with the corresponding steps in Example 1, and will not be elaborated in this example.

[0069] The user end and management end can be a mobile terminal or a smart APP, etc.

[0070] The modules or steps of the present invention described above can be implemented by a general-purpose computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software. Example 3

[0071] like Figure 5 As shown, further, in another aspect, the present application also proposes an electronic device, including: processor; a memory for storing processor-executable instructions; Among them, the processor is configured to implement a question recording method based on adaptive progressive intelligent learning as described in Example 1 when executing the executable instructions.

[0072] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor. The processor is configured to implement a method for recording questions based on intelligent adaptive progressive intelligent learning as described in the above embodiment 1 when executing the executable instructions.

[0073] Here, it should be noted that the number of processors can be one or more. At the same time, the electronic device of the embodiment of the present disclosure may also include an input system and an output system. Among them, the processor, memory, input system and output system may be connected through a bus or in other ways, which are not specifically limited here.

[0074] As a computer-readable storage medium, the memory can be used to store software programs, computer executable programs and various modules, such as the program or module corresponding to the method for recording questions based on adaptive progressive intelligent learning in the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0075] The input system can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output system can include display devices such as display screens.

[0076] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for recording questions based on intelligent adaptive progressive intelligent learning, characterized in that: The steps include: S1. Get the user's current learning progress; S2, reading and filtering from the background database to obtain the test questions to be entered that match the user's current learning progress; S3. Determine the type of the test question to be entered: (1) If the test question to be entered is a single question, the LLM large language model is used to identify the test content of the single question and automatically enter it into the test question database; (2) If the test question to be entered is a test question page, then using an image contour recognition algorithm to identify the contour of the area where each question in the test question page is located; According to the area outline, the test question page is divided into single question pages to obtain a plurality of single question pages; Using an OCR text recognition algorithm, traverse and recognize text information in each of the single question pages, including: text, symbols, numbers and / or English characters related to the question and answer; Using the LLM large language model to identify the questions and answers in the text information, obtain the corresponding test content and automatically enter it into the test database; S4, the user logs in to the question bank, reads and studies each question of the current learning progress; S5. After learning, refer to the above steps to enter and study the test questions for the next stage of learning progress.

2. A method for recording questions based on adaptive progressive intelligent learning according to claim 1, characterized in that: The following steps are also included: When the user has finished studying all the questions in the current learning progress, the system will automatically record and generate the corresponding learning log; At the same time, a notification for entering the next stage of test questions is sent to the user.

3. A method for recording questions based on adaptive progressive intelligent learning according to claim 1, characterized in that: The following steps are also included: Preparing and preprocessing the test questions to be entered corresponding to different learning progress in advance, wherein the preprocessing includes: color marking the area where each test question to be entered in the test question page is located, and if there are multiple test questions to be entered, there is no overlap between the color marked areas; Binding the test questions to be entered with the corresponding learning progress to generate a test question data package for the corresponding learning stage; Each of the test question data packets is stored in the background database.

4. A method for recording questions based on adaptive progressive intelligent learning according to claim 3, characterized in that: S2. Read and filter the test questions to be entered that match the user's current learning progress from the background database, including: Read the user's current learning progress from the log module and send it to the backend database; Generate an SQL retrieval instruction of the current learning progress and send it to the backend database; The backend database executes the SQL search instruction to retrieve and feed back the test question data package that matches the user's current learning progress; The test question data packet is parsed to obtain a number of test questions to be entered that match the user's current learning progress.

5. The method for recording questions based on adaptive progressive intelligent learning according to claim 1, characterized in that: In step S3, after traversing and identifying the text information in each of the single-title pages using an OCR text recognition algorithm, the following steps are further included: According to the text information, assembling matching questions and answers to generate a number of single questions; Use the LLM large language model to identify keywords in each question and determine whether there are questions with the same title: If it exists, deduplication is performed; Otherwise give up.

6. A method for recording questions based on adaptive progressive intelligent learning according to claim 5, characterized in that: In step S3, after traversing and identifying the text information in each of the single-title pages using an OCR text recognition algorithm, the following steps are further included: Attribute annotation is performed on each question, and the subject, chapter and knowledge point information to which the question belongs are marked; Send each marked question to the management end for confirmation.

7. A system for implementing the method for recording questions based on intelligent adaptive progressive intelligent learning as described in any one of claims 1 to 6, characterized in that: include: The user end is used to log in to the backend server, participate in the test question entry and the test question study corresponding to the learning progress; On the management side, log in to the backend server and participate in the review of test questions and corresponding learning progress; Backend server, including: User management module, used to manage students and administrators; The learning progress recording module is used to automatically record the learning log of each stage of the students, and send a notification to the user to enter the next stage of test questions after the user has finished learning each test question of the current learning progress; The test question screening module is used to read and screen the test questions to be entered that match the user's current learning progress from the background database; The test question input module is used to determine the type of the test question to be input: (1) If the test question to be entered is a single question, the LLM large language model is used to identify the test content of the single question and automatically enter it into the test question database; (2) If the test question to be entered is a test question page, then using an image contour recognition algorithm to identify the contour of the area where each question in the test question page is located; According to the area outline, the test question page is divided into single question pages to obtain a plurality of single question pages; Using an OCR text recognition algorithm, traverse and recognize text information in each of the single question pages, including: text, symbols, numbers and / or English characters related to the question and answer; Using the LLM large language model to identify the questions and answers in the text information, obtain the corresponding test content and automatically enter it into the test database; Backend database, used to store test question data packets; LLM large language model port, used to call the LLM large language model; The user management module, learning progress recording module, test question screening module, test question entry module, LLM large language model port and backend database are all deployed on the backend server; The user end and the management end are respectively connected to the background server for communication.

8. An electronic device, characterized in that include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement a question recording method based on adaptive progressive intelligent learning as described in any one of claims 1 to 6 when executing the executable instructions.

Images