Method for realizing automatic input of question type structure through self-adaptive identification

Abstract

The invention relates to a method for realizing automatic entry of a question type structure through self-adaptive identification. The method sequentially comprises the following steps: step 1, extracting test question contents from an external document; step 2, pasting the test question content extracted from the step 1 to a test question input area; and step 3, identifying key information of the test question content through an AI algorithm and automatically storing the key information to a question bank system. Compared with the technical scheme, the technical scheme provided by the invention has the advantages that the question recording efficiency is improved, and errors such as missed recording and wrong recording which are artificially generated by question recording personnel in the question recording process are greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of computer-related technologies, and in particular to a method for automatically entering a question type structure through adaptive recognition. Background Art

[0002] When entering test questions, the question bank system needs to perform targeted structural entry based on different question types (single-choice questions, multiple-choice questions, fill-in-the-blank questions, subjective questions, material analysis questions, etc.) to meet the diversity of test questions in different subjects.

[0003] After massive searches, it was found that the prior art publication number is CN116758554A, which discloses a method, device, electronic device and storage medium for extracting test question information, the method comprising: determining the initial test question type, initial illustration type and illustration image of the test question with illustrations; based on the initial test question type, the initial illustration type and the illustration image, obtaining test question feature information, the test question feature information at least including illustration feature information; obtaining test question information based on the illustration feature information. When the test question information of the illustrated test question to be searched is determined based on the exemplary embodiment method of the present disclosure; and recommended test questions are obtained from the test question library based on the test question information to be searched, test questions can be efficiently screened, and the accuracy of test question search can be improved, thereby accurately recommending test questions to users.

[0004] In summary, the existing method is to manually judge the question type and select the input mode corresponding to the question type to input one by one. A relatively advanced method is to first select the question type to be input and then input the test questions of this type uniformly when inputting.

[0005] Although the above two methods can achieve the purpose of recording questions, they have the problem of low efficiency.

[0006] In view of the above-mentioned defects, the designers have actively carried out research and innovation in order to create a method for automatically entering question structure through adaptive recognition, making it more valuable for industrial use. Summary of the invention

[0007] In order to solve the above technical problems, the purpose of the present invention is to provide a method for automatically entering question type structure through adaptive recognition.

[0008] To achieve the above object, the present invention adopts the following technical solution:

[0009] A method for automatically entering a question type structure through adaptive recognition, characterized in that it comprises the following steps in sequence:

[0010] Step 1: Extract test content from external documents;

[0011] Step 2: Paste the test content extracted from step 1 into the test entry area;

[0012] Step 3: Identify key information of the test content through AI algorithms and automatically store it in the question bank system; the key information includes but is not limited to the question type, question stem and options.

[0013] As a further improvement of the present invention, in step 1, the test content in the PDF scan or Word document is copied.

[0014] As a further improvement of the present invention, step 2 comprises the following steps in sequence:

[0015] Step 21, paste the test content extracted from step 1 into the rich text input box;

[0016] Step 22, the rich text box extracts text content in two formats, 'text / html' and 'text / rtf', from the pasted test content;

[0017] Step 23: Use regular expressions to match and extract the values ​​of the attribute src of all image tags img from the text in the 'text / html' format. These values ​​will form a set A.

[0018] Step 24: Use regular expressions to match and extract all image data from the text in the 'text / rtf' format. These data will constitute set B.

[0019] Step 25: For the image data in set B, convert it from hex format to base64 encoding, then convert the base64-encoded image data into a file stream and upload it to the cloud to obtain the network access address of the image;

[0020] Step 26. After obtaining the network access addresses of the images in set A, we can find all corresponding image tags img in the text in the 'text / html' format and replace their attributes src with the generated network access addresses;

[0021] Step 27. Finally, insert the processed text in 'text / html' format into the rich text editor.

[0022] As a further improvement of the present invention, the pasting step in step 21 is implemented through the clipboard of the operating system and the paste function of the rich text box.

[0023] As a further improvement of the present invention, step 3 comprises the following steps in sequence:

[0024] Step 31: Each line in the rich text represents a node, which describes the content and style of the text in the line. The node description content is parsed according to a specific dimension identifier to identify the dimension information of the question. The dimension information includes but is not limited to the type of question, the stem, the options, and the answer.

[0025] Step 32: Based on the above step 31, the feature information of multiple dimensions is input into the pre-trained test question recognition model, and the test question recognition model is used to output a recognition result of whether the target file belongs to a test question.

[0026] By means of the above scheme, the present invention has at least the following advantages:

[0027] Compared with the technical solution of the present invention, the technical solution of the present invention improves the efficiency of recording questions and greatly reduces the errors such as omissions and wrong recordings made by the recorders during the recording process.

[0028] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 It is a flow chart of a method for realizing automatic entry of question type structure through adaptive recognition according to the present invention.

[0031] Figure 2 It is an implementation example of the present invention. DETAILED DESCRIPTION

[0032] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, rather than all the embodiments. The components of the embodiment of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiment of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but merely represents the selected embodiment of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0034] Example

[0035] like Figure 1-2 As shown,

[0036] A method for automatically entering a question type structure through adaptive recognition, characterized in that it comprises the following steps in sequence:

[0037] Step 1: Extract test content from external documents;

[0038] Step 2: Paste the test content extracted from step 1 into the test entry area;

[0039] Step 3: Identify key information of the test content through AI algorithms and automatically store it in the question bank system; the key information includes but is not limited to the question type, question stem and options.

[0040] Preferably, in step 1, copy the test content in the PDF scan or Word document.

[0041] Preferably, step 2 includes the following steps in sequence:

[0042] Step 21, paste the test content extracted from step 1 into the rich text input box;

[0043] Step 22, the rich text box extracts text content in two formats, 'text / html' and 'text / rtf', from the pasted test content;

[0044] Step 23: Use regular expressions to match and extract the values ​​of the attribute src of all image tags img from the text in the 'text / html' format. These values ​​will form a set A.

[0045] Step 24: Use regular expressions to match and extract all image data from the text in the 'text / rtf' format. These data will constitute set B.

[0046] Step 25: For the image data in set B, convert it from hex format to base64 encoding, then convert the base64-encoded image data into a file stream and upload it to the cloud to obtain the network access address of the image;

[0047] Step 26. After obtaining the network access addresses of the images in set A, we can find all corresponding image tags img in the text in the 'text / html' format and replace their attributes src with the generated network access addresses;

[0048] Step 27. Finally, insert the processed text in 'text / html' format into the rich text editor.

[0049] Preferably, the pasting step in step 21 is implemented through the clipboard of the operating system and the paste function of the rich text box.

[0050] Preferably, step 3 includes the following steps in sequence:

[0051] Step 31: Each line in the rich text represents a node, which describes the content and style of the text in the line. The node description content is parsed according to a specific dimension identifier to identify the dimension information of the question. The dimension information includes but is not limited to the type of question, the stem, the options, and the answer.

[0052] Step 32: Based on the above step 31, the feature information of multiple dimensions is input into the pre-trained test question recognition model, and the test question recognition model is used to output a recognition result of whether the target file belongs to a test question.

[0053] The first embodiment of the present invention:

[0054] 1. Extract the test content from the external document and paste it into the rich text input box. This step can be achieved through the operating system's clipboard and the paste function of the rich text box.

[0055] 2. The rich text box can extract text content in two formats, 'text / html' and 'text / rtf', from the pasted content. This is due to the inherent function of the rich text box, which can parse and process text content in different formats.

[0056] 3. Next, we need to use regular expressions to match and extract the values ​​of the src attribute of all image tags img from the text in the 'text / html' format. These values ​​will form set A.

[0057] 4. Similarly, we also need to use regular expressions to match and extract all image data from the text in the 'text / rtf' format. These data will form set B.

[0058] 5. For the image data in set B, we need to convert it from hex format to base64 encoding. Then, we can convert these base64-encoded image data into a file stream and upload it to the cloud to obtain the network access address of the image.

[0059] 6. After obtaining the network access addresses of the images in set A, we can find all the corresponding image tags img in the text in the 'text / html' format and replace their attribute src with the generated network access addresses.

[0060] 7. Finally, we insert the processed text in 'text / html' format into the rich text editor, thus completing the entire paste-copy process.

[0061] 8. Each line in the rich text represents a node. The node describes the content and style of the text in that line. The node description content is parsed according to the specific dimension identifier to identify the type of question, stem, options, answers and other dimensional information.

[0062] 9. Based on the above step 8, the feature information of the multiple dimensions is input into a pre-trained test question recognition model, and the test question recognition model is used to output a recognition result of whether the target file belongs to a test question.

[0063] The present invention provides a method for automatically entering question type structure through adaptive recognition, which can greatly improve the entry efficiency during the question entry process.

[0064] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly referring to the number of technical features indicated. Thus, features defined as "first", "second", and the like may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0065] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0066] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the technical principles of the present invention, and these improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for automatically entering question structure through adaptive recognition, characterized in that: The following steps are included in sequence: Step 1: Extract test content from external documents; Step 2: Paste the test content extracted from step 1 into the test entry area; Step 3: Identify key information of the test content through AI algorithm and automatically store it in the question bank system; wherein the key information includes but is not limited to the type of question, question stem and options of the test.

2. A method for automatically entering question type structure through adaptive recognition as claimed in claim 1, characterized in that: Copy the test content from the PDF scan or Word document in step 1.

3. A method for automatically entering question type structure through adaptive recognition as claimed in claim 1, characterized in that: Step 2 includes the following steps in sequence: Step 21, paste the test content extracted from step 1 into the rich text input box; Step 22, the rich text box extracts text content in two formats, 'text / html' and 'text / rtf', from the pasted test content; Step 23: Use regular expressions to match and extract the values ​​of the attribute src of all image tags img from the text in the 'text / html' format. These values ​​will form a set A. Step 24: Use regular expressions to match and extract all image data from the text in the 'text / rtf' format. These data will constitute set B. Step 25: For the image data in set B, convert it from hex format to base64 encoding, then convert the base64-encoded image data into a file stream and upload it to the cloud to obtain the network access address of the image; Step 26. After obtaining the network access addresses of the images in set A, we can find all corresponding image tags img in the text in the 'text / html' format and replace their attributes src with the generated network access addresses; Step 27. Finally, insert the processed text in 'text / html' format into the rich text editor.

4. A method for automatically entering question structure through adaptive recognition as claimed in claim 3, characterized in that: The pasting step in step 21 is implemented through the clipboard of the operating system and the paste function of the rich text box.

5. A method for automatically entering question type structure through adaptive recognition as claimed in claim 1, characterized in that: Step 3 includes the following steps in sequence: Step 31: Each line in the rich text represents a node, which describes the content and style of the text in the line. The node description content is parsed according to a specific dimension identifier to identify the dimension information of the question. The dimension information includes but is not limited to the type of question, the stem, the options, and the answer. Step 32: Based on the above step 31, the feature information of multiple dimensions is input into the pre-trained test question recognition model, and the test question recognition model is used to output a recognition result of whether the target file belongs to a test question.

Images