Question bank resource matching video recording system and method

Abstract

The invention relates to the technical field of computers, in particular to a question bank resource matching video input system and method.The question bank resource matching video input system comprises a question unit used for storing and managing questions and a library module of a video unit used for storing a plurality of question explanation videos; the test question extraction module is used for extracting test questions of to-be-recorded videos from the test question bank; the sample storage unit is used for recording the extracted test questions; the test question sample conversion unit is used for acquiring to-be-processed test question explanation videos associated with the test questions; the video association module is used for determining association degrees between a plurality of video clips of a test question explanation video to be processed and the test questions, and the video segmentation module is used for determining video clips associated with the test questions based on the association degrees and segmenting the test question explanation video to be processed. And the association module is used for associating the video clips and the corresponding test questions and storing the video clips and the corresponding test questions into the library module, so that the search efficiency of the user is improved, and the input efficiency of the test question explanation video is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a system and method for recording matching videos of question bank resources. Background Art

[0002] At present, educational informatization is constantly developing, the technology of question searching and recommending is very mature, and the accuracy of question searching can reach the product level. However, for most users, explanation video resources will be the focus of more parent users. The demand for explanation videos when explaining questions is increasing. It is particularly important to obtain explanation videos simultaneously when searching for questions.

[0003] Chinese patent application publication number: CN113507613A, discloses a video recording scheduling system based on CDN, including a search module, a receiving and identifying module, a node assembly module, a filtering and screening module, a list sending module, a video definition module, a video cache module and a classification storage module. The output end of the search module is connected to the input end of the receiving and identifying module, the output end of the receiving and identifying module is connected to the input end of the node assembly module, and the output end of the node assembly module is connected to the input end of the filtering and screening module. The video is pre-cached and stored in categories. Synonym search reduces the system workload, thereby improving the work efficiency of search queries, reducing the difficulty of video scheduling, and improving user experience.

[0004] In the prior art, when searching for test question explanation videos, videos containing multiple test question explanation videos are often found, resulting in low user search efficiency. Moreover, when uploading test question explanation videos, most websites will enter multiple test question explanation videos, resulting in low test question explanation video entry efficiency and low matching rate with test questions. Summary of the invention

[0005] To this end, the present invention provides a video recording system for question bank resources, which is used to solve the problem that when searching for test question explanation videos, videos containing multiple test question explanation videos are often found, resulting in low user search efficiency, and when uploading test question explanation videos, most websites will record multiple test question explanation videos, resulting in low test question explanation video recording efficiency and low matching rate with test questions.

[0006] To achieve the above-mentioned purpose, the present invention provides a system for recording video of a question bank resource on the one hand, and a method for recording video of a question bank resource on the other hand, which comprises:

[0007] The library module includes a test question unit for storing and managing test questions and a video unit for storing test question explanation videos;

[0008] A test question extraction module, which is connected to the library module and is used to extract the test questions to be recorded in the video from the test question unit;

[0009] A test sample module, which is connected to the test extraction module, and includes a sample storage unit for recording the extracted test questions and a video sample storage unit for recording the explanation video of the test question to be processed associated with each of the test questions;

[0010] A video association module, which is connected to the test question sample module and is used to determine the degree of association between a number of video clips of the test question explanation video to be processed and each of the test questions;

[0011] A video segmentation module, connected to the video association module, for determining a video segment associated with each test question based on the degree of association between a plurality of video segments and each test question, and segmenting a target video segment from the video segments;

[0012] An association module is connected to the video segmentation module and the library module, and is used to associate the target video segment with the corresponding test question and store them in the library module.

[0013] Furthermore, the test question unit at least stores a test question ID, a test question stem, and a test question associated video ur l. If the test question has no associated video, the test question associated video ur l is an empty field.

[0014] Furthermore, the test question extraction module is used to extract the test questions to be recorded in the video from the test question unit, including:

[0015] To determine the video URL associated with the test question;

[0016] If the question-associated video ur l is an empty field, the question will be extracted.

[0017] Furthermore, the test sample module is used to configure an identification code for a single test question, wherein:

[0018] The identification code includes a QR code and / or a barcode;

[0019] The identification code corresponds to the test question ID one by one.

[0020] Furthermore, the video association module determines the video clip associated with each test question based on the degree of association between the plurality of video clips and each test question, wherein:

[0021] Determine the relevance between each video clip and the test question, if the relevance is greater than a predetermined relevance threshold;

[0022] It is determined that the video clip is associated with the test question.

[0023] Furthermore, the video association module determines the association between the test question and the video clip, including:

[0024] The video association module determines the association between the test questions and the test question segments by:

[0025] Used to determine the question stem area information corresponding to the test question;

[0026] Used to extract video title area information from video frames based on video clips;

[0027] The method is used to calculate the average value of the overlap between the question stem area information and the video question stem area information corresponding to each video frame, and the average value of the overlap is determined as the correlation between the test question and the video clip;

[0028] Among them, the question stem area is divided according to a preset question stem recognition model.

[0029] Furthermore, the video segmentation module segments the target video segment from the video segment, including:

[0030] Determine the video clips associated with the test questions;

[0031] determining a duration of a target video segment in the video segment;

[0032] Cutting each of the target video segments from the explanation video of the test question to be processed;

[0033] The duration of each of the target video segments is determined based on the duration of similar frames in the video segment.

[0034] Furthermore, the video segmentation module is also used to determine the URL of the target video segment.

[0035] Furthermore, the video segmentation module is also used to construct a corresponding relationship between the test question ID of the test question and the URL.

[0036] Furthermore, a method for applying to a video recording system for question bank resources is provided, which comprises:

[0037] Step S1, extracting the test questions to be recorded in the video;

[0038] Step S2, obtaining the explanation video of the test question to be processed associated with each of the test questions, and determining the relevance between several video clips of the explanation video of the test question to be processed and each of the test questions;

[0039] Step S3, determining the video segments associated with each test question based on the correlation between the plurality of video segments and each test question, and segmenting the target video segments from the video segments;

[0040] Step S4, associating the target video clip with the corresponding test question and storing them in the library module.

[0041] Compared with the prior art, the present invention is provided with a library module including a test question unit for storing and managing test questions and a video unit for storing a plurality of test question explanation videos, a test question extraction module for extracting test questions to be recorded videos from the test question library, a test question sample module including a sample storage unit for recording the extracted test questions and a test question sample conversion unit for obtaining the test question explanation videos to be processed associated with each of the test questions, a video association module for determining the association between a plurality of video clips of the test question explanation videos to be processed and each of the test questions, a video segmentation module for determining the video clip associated with each test question based on the association, and segmenting the test question explanation videos to be processed, and an association module for associating the video clips with the corresponding test questions and storing them in the library module, thereby improving the user search efficiency and the test question explanation video entry efficiency.

[0042] In particular, the present invention determines the test question explanation video to be processed based on the correlation between several video clips of the test question explanation video and each of the test questions. In a real situation, when selecting video clips, there are likely to be several test question explanation videos to be processed that contain video clips associated with the test questions. Based on this, the present invention determines the correlation between the video clip and each of the test questions, and then determines the video clip, thereby improving the accuracy of entering the test question explanation video.

[0043] In particular, the present invention segments the video clips associated with the test questions, obtains the target video clips, takes into account the changes of the test question pages in the explanation video, and completely matches the test questions with the test question explanation videos, thereby improving the accuracy and efficiency of the test question explanation video recording. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of the structure of a video recording system for matching question bank resources according to an embodiment of the invention;

[0045] Figure 2 It is a logic block diagram of correlation comparison of an embodiment of the invention;

[0046] Figure 3 A schematic diagram of the method steps of a method for recording video matching with question bank resources according to an embodiment of the invention. DETAILED DESCRIPTION

[0047] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0049] It should be noted that in the description of the present invention, 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 an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] See also Figures 1 to 3 As shown, Figure 1 This is a structural diagram of a video recording system for matching question bank resources according to an embodiment of the invention. Figure 2 This is a schematic diagram of correlation comparison of an embodiment of the invention. Figure 3 The schematic diagram of the correspondence between the test questions and the test question explanation videos of the embodiment of the invention is a video recording system for the question bank resources of the present invention, which includes:

[0051] The library module includes a test question unit for storing and managing test questions and a video unit for storing test question explanation videos;

[0052] A test question extraction module, which is connected to the library module and is used to extract the test questions to be recorded in the video from the test question unit;

[0053] A test sample module, which is connected to the test extraction module, and includes a sample storage unit for recording the extracted test questions and a video sample storage unit for recording the explanation video of the test question to be processed associated with each of the test questions;

[0054] A video association module, which is connected to the test question sample module and is used to determine the degree of association between a number of video clips of the test question explanation video to be processed and each of the test questions;

[0055] A video segmentation module, connected to the video association module, for determining a video segment associated with each test question based on the degree of association between a plurality of video segments and each test question, and segmenting a target video segment from the video segments;

[0056] An association module is connected to the video segmentation module and the library module, and is used to associate the target video segment with the corresponding test question and store them in the library module.

[0057] Specifically, there is no limitation on the content sources of the test question unit and the video unit. For example, it can be content uploaded and stored by the user, or it can be content available on the Internet. This will not be elaborated here.

[0058] Specifically, there is no limitation on the storage method of the test question unit and the video unit. It can be a local database or a cloud database. Those skilled in the art can choose according to the number of test questions and videos, which will not be elaborated here.

[0059] Specifically, there is no limitation on the storage method of the sample storage unit, which can be a MySQL database or a cloud database. It is understandable that in order to enable multiple people to use it, storage and subsequent operations can be performed in a cloud database. Technical personnel in this field can make a choice based on actual conditions, which will not be elaborated here.

[0060] Specifically, the test question unit at least stores the test question ID, the test question stem, and the test question associated video ur l. If the test question does not have an associated video, the test question associated video ur l is an empty field.

[0061] It can be understood that the present invention can search for test questions based on each field and display them according to whether there is a video URL associated with the test question.

[0062] Specifically, the test question extraction module is used to extract the test questions to be recorded in the video from the test question unit, including:

[0063] To determine the video URL associated with the test question;

[0064] If the question-associated video ur l is an empty field, the question will be extracted.

[0065] It can be understood that test questions with associated video URLs are searchable online and do not require the entry of test question explanation videos.

[0066] Specifically, the test sample module is used to configure an identification code for a single test question, wherein:

[0067] The identification code includes a QR code and / or a barcode;

[0068] The identification code corresponds to the test question ID one by one.

[0069] Specifically, the video association module determines the video segment associated with each test question based on the degree of association between the plurality of video segments and each test question, wherein:

[0070] Determine the relevance between each video clip and the test question, if the relevance is greater than a predetermined relevance threshold;

[0071] It is determined that the video clip is associated with the test question.

[0072] Specifically, the predetermined correlation threshold is selected within the interval [0.95, 1].

[0073] It is understandable that if there are multiple test question explanation videos with a correlation greater than a predetermined correlation threshold, the test question explanation video with the highest correlation is selected.

[0074] It is understandable that selecting test question explanation videos according to a predetermined relevance threshold can screen out test question explanation videos that are significantly different from the test questions, thereby ensuring the accuracy of the test question explanation videos.

[0075] Specifically, the video association module determines the association between the test questions and the test question segments by:

[0076] Used to determine the question stem area information corresponding to the test question;

[0077] Used to extract video title area information from video frames based on video clips;

[0078] The method is used to calculate the average value of the overlap between the question stem area information and the video question stem area information corresponding to each video frame, and the average value of the overlap is determined as the correlation between the test question and the video clip;

[0079] Among them, the question stem area is divided according to a preset question stem recognition model.

[0080] Specifically, the preset question stem recognition model can identify the question stem area and the problem-solving area in the picture frame. There is no limitation on the specific training process of the question stem recognition model, as long as it can realize the corresponding function. The neural network visual model can be used for training to realize the corresponding function, which will not be elaborated here.

[0081] Specifically, there is no limitation on the method of calculating the overlap between text information and video text information. For example, it can be a similarity algorithm and overlap calculation. Those skilled in the art can choose the method according to the actual situation. This is the prior art and will not be elaborated.

[0082] It can be understood that the process of calculating the overlap between the text information and the video text information is performed in the logic component to ensure the accuracy of the overlap calculation.

[0083] Specifically, the present invention determines the test question explanation video to be processed based on the correlation between several video clips of the test question explanation video and each of the test questions. In a real situation, when selecting video clips, there are likely to be several test question explanation videos to be processed that contain video clips associated with the test questions. Based on this, the present invention determines the correlation between the video clip and each of the test questions, and then determines the video clip, thereby improving the accuracy of entering the test question explanation video.

[0084] Specifically, the video segmentation module segments the target video segment from the video segment, including:

[0085] Determine the video clips associated with the test questions;

[0086] determining a duration of a target video segment in the video segment;

[0087] Cutting each of the target video segments from the explanation video of the test question to be processed;

[0088] The duration of each of the target video segments is determined based on the duration of similar frames in the video segment.

[0089] Specifically, similar frames are determined, including:

[0090] Determine the initial frame of each video clip and the picture stem area of ​​each initial frame;

[0091] Determine the picture frame where the new question stem area appears;

[0092] All picture frames before the picture frame are determined to be similar frames.

[0093] It is understandable that when explaining the test questions, one page may not be enough. In this case, the newly added page does not have the test question stem. Based on this, the stem area in the picture frame is continuously compared until a new stem area appears. The picture frames before the new stem area appears are determined as similar frames, and the video clips are cut to ensure the integrity of the video clip cutting.

[0094] Specifically, the video segmentation module is also used to determine the URL of the target video segment.

[0095] Specifically, the video segmentation module is also used to construct a corresponding relationship between the test question ID of the test question and the ur l.

[0096] It is understandable that a correspondence between the test question stem and the URL can also be constructed, and the user can search for the test question explanation video based on the test question ID and the test question stem.

[0097] Specifically, the present invention segments the video clips associated with the test questions, obtains the target video clips, takes into account the changes of the test question pages in the explanation video, and completely matches the test questions with the test question explanation videos, thereby improving the accuracy and efficiency of the test question explanation video recording.

[0098] Specifically, it also includes a method applied to a video recording system for a question bank resource.

[0099] Step S1, extracting the test questions to be recorded in the video;

[0100] Step S2, obtaining the explanation video of the test question to be processed associated with each of the test questions, and determining the relevance between several video clips of the explanation video of the test question to be processed and each of the test questions;

[0101] Step S3, determining the video segments associated with each test question based on the correlation between the plurality of video segments and each test question, and segmenting the target video segments from the video segments;

[0102] Step S4, associating the target video clip with the corresponding test question and storing them in the library module.

[0103] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A video recording system for question bank resources, characterized in that: include: The library module includes a test question unit for storing and managing test questions and a video unit for storing test question explanation videos; A test question extraction module, which is connected to the library module and is used to extract the test questions to be recorded in the video from the test question unit; A test sample module, which is connected to the test extraction module, and includes a sample storage unit for recording the extracted test questions and a video sample storage unit for recording the explanation video of the test question to be processed associated with each of the test questions; A video association module, which is connected to the test question sample module and is used to determine the degree of association between a number of video clips of the test question explanation video to be processed and each of the test questions; A video segmentation module, connected to the video association module, for determining a video segment associated with each test question based on the degree of association between a plurality of video segments and each test question, and segmenting a target video segment from the video segments; An association module is connected to the video segmentation module and the library module, and is used to associate the target video segment with the corresponding test question and store them in the library module.

2. The question bank resource matching video recording system according to claim 1, characterized in that: The test question unit at least stores the test question ID, the test question stem, and the test question associated video URL. If the test question does not have an associated video, the test question associated video URL is an empty field.

3. The question bank resource matching video recording system according to claim 1, characterized in that: The test question extraction module is used to extract the test questions to be recorded in the video from the test question unit, including: Used to determine the video URL associated with the test question; If the test question-associated video url is an empty field, the test question will be extracted.

4. The question bank resource matching video recording system according to claim 1, characterized in that: The test sample module is used to configure an identification code for a single test question, wherein: The identification code includes a QR code and / or a barcode; The identification code corresponds to the test question ID one by one.

5. The question bank resource matching video recording system according to claim 1, characterized in that: The video association module determines the video segment associated with each test question based on the degree of association between the plurality of video segments and each test question, wherein: Determine the relevance between each video clip and the test question, if the relevance is greater than a predetermined relevance threshold; It is determined that the video clip is associated with the test question.

6. The question bank resource matching video recording system according to claim 5, characterized in that: The video association module determines the association between the test questions and the test question segments, including: Used to determine the question stem area information corresponding to the test question; Used to extract video title area information from video frames based on video clips; The method is used to calculate the average value of the overlap between the question stem area information and the video question stem area information corresponding to each video frame, and the average value of the overlap is determined as the correlation between the test question and the video clip; Among them, the question stem area is divided according to a preset question stem recognition model.

7. The question bank resource matching video recording system according to claim 1, characterized in that: The video segmentation module segments the target video segment from the video segment, including: Determine the video clips associated with the test questions; determining a duration of a target video segment in the video segment; Cutting each of the target video segments from the explanation video of the test question to be processed; The duration of each of the target video segments is determined based on the duration of similar frames in the video segment.

8. The question bank resource matching video recording system according to claim 7, characterized in that: The video segmentation module is also used to determine the URL of the target video segment.

9. The question bank resource matching video recording system according to claim 8, characterized in that: The video segmentation module is also used to construct a corresponding relationship between the test question ID of the test question and the URL.

10. A method for applying the video recording system for question bank resources according to any one of claims 1 to 9, characterized in that: include: Step S1, extracting the test questions to be recorded in the video; Step S2, obtaining the explanation video of the test question to be processed associated with each of the test questions, and determining the relevance between several video clips of the explanation video of the test question to be processed and each of the test questions; Step S3, determining the video segments associated with each test question based on the correlation between the plurality of video segments and each test question, and segmenting the target video segments from the video segments; Step S4, associating the target video clip with the corresponding test question and storing them in the library module.

Images