Teaching resource generation method and device, equipment, storage medium and computer program product

Abstract

The invention discloses a teaching resource generation method and device, equipment, a storage medium and a computer program product. The teaching resource generation method comprises the following steps: acquiring teaching data input by a first terminal; the teaching data is related to a teaching theme; analyzing the teaching data to extract teaching content from the teaching data; the teaching content represents teaching knowledge point information provided by the first terminal; based on the teaching content, determining videos and audios related to a micro class; and generating teaching resources related to the micro-class based on the videos and the audios related to the micro-class.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a teaching resource generation method, device, equipment, storage medium and computer program product. Background Art

[0002] At present, micro-courses, as a new type of teaching resource, are increasingly favored by educators and students because of their conciseness and easy dissemination.

[0003] However, in the related art, the creation of micro-class teaching resources mostly depends on the personal ability and time of educators such as teachers, and lacks systematic and automated support. It can be seen that the generation process of micro-class teaching resources is dependent on the performance of teachers' skills or teaching equipment, resulting in low efficiency in the generation of micro-class teaching resources. In addition, the micro-class teaching resource generation scheme of the related art also has the problem of difficulty in ensuring the timeliness and accuracy of the micro-class content. Summary of the invention

[0004] In order to solve the technical problems existing in the related technologies, the embodiments of the present application provide a teaching resource generation method, device, equipment, storage medium and computer program product.

[0005] To achieve the above purpose, the technical solution of the embodiment of the present application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for generating teaching resources, the method comprising:

[0007] Acquiring teaching data input by the first terminal; the teaching data is related to the teaching subject;

[0008] Analyzing the teaching data to extract teaching content from the teaching data; the teaching content represents the teaching knowledge point information provided by the first terminal;

[0009] Based on the teaching content, determine the video and audio related to the micro-course;

[0010] Based on the video and audio related to the micro-course, teaching resources related to the micro-course are generated.

[0011] In a second aspect, an embodiment of the present application further provides a teaching resource generating device, the device comprising:

[0012] An acquisition unit, configured to acquire teaching data input by the first terminal; the teaching data is related to the teaching subject;

[0013] An extraction unit, configured to analyze the teaching data to extract teaching content from the teaching data; the teaching content represents the teaching knowledge point information provided by the first terminal;

[0014] A first determining unit, configured to determine the video and audio related to the micro-course based on the teaching content;

[0015] A generating unit is used to generate teaching resources related to the micro-course based on the video and audio related to the micro-course.

[0016] In a third aspect, an embodiment of the present application further provides a teaching resource generating device, comprising: a processor and a memory for storing a computer program that can be run on the processor;

[0017] Wherein, when the processor is used to run the computer program, it executes the steps of the teaching resource generation method described in the embodiment of the present application.

[0018] In a fourth aspect, an embodiment of the present application further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the teaching resource generation method described in the embodiment of the present application are implemented.

[0019] In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the teaching resource generation method described in the embodiment of the present application.

[0020] The teaching resource generation method, device, equipment, storage medium and computer program product provided in the embodiment of the present application obtain the teaching data input by the first terminal; the teaching data is related to the teaching subject; the teaching data is analyzed to extract the teaching content from the teaching data; the teaching content represents the teaching knowledge point information provided by the first terminal; based on the teaching content, the video and audio related to the micro-class are determined; based on the video and audio related to the micro-class, the teaching resources related to the micro-class are generated. The technical scheme of the embodiment of the present application is adopted, for the teaching data input by the first terminal, the teaching content in the teaching data is automatically analyzed and refined, and the video and audio related to the micro-class are determined based on the teaching content, and then the teaching resources related to the micro-class are generated based on the video and audio related to the micro-class. In this way, the teaching resources related to the micro-class can be created without relying on the teacher's technology or teaching equipment, which reduces manual operation and improves the generation efficiency of the teaching resources related to the micro-class; the artificial intelligence big model technology is used to timely conduct in-depth analysis of the teaching data, identify all the teaching knowledge point information, so as to ensure the accuracy and timeliness of the micro-class content. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The process diagram of the teaching resource generation method of the present application embodiment is as follows Figure 1 ;

[0022] Figure 2 The process diagram of the teaching resource generation method of the present application embodiment is as follows Figure 2 ;

[0023] Figure 3 A schematic diagram of the functional architecture of a micro-course teaching resource generation system according to an embodiment of the present application;

[0024] Figure 4 A schematic diagram of the processing flow of the teaching content analysis and refinement module of the embodiment of the present application;

[0025] Figure 5 The following is a schematic diagram of the process of extracting key summary information from video teaching materials in an embodiment of the present application. Figure 1 ;

[0026] Figure 6 The following is a schematic diagram of the process of extracting key summary information from video teaching materials in an embodiment of the present application. Figure 2 ;

[0027] Figure 7 The following is a schematic diagram of the process of extracting key summary information from text teaching materials in the embodiment of the present application. Figure 1 ;

[0028] Figure 8 The following is a schematic diagram of the process of extracting key summary information from text teaching materials in the embodiment of the present application. Figure 2 ;

[0029] Fig. 9 A schematic diagram of the interaction process between a user and a micro-course teaching resource generation system according to an embodiment of the present application;

[0030] Fig.10 A schematic diagram of the structure of a teaching resource generating device according to an embodiment of the present application;

[0031] Fig.11 This is a schematic diagram of the hardware composition structure of the teaching resource generation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] The present application will be further described in detail below with reference to the accompanying drawings and embodiments.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0034] At present, micro-courses, as a new type of teaching resource, are increasingly favored by educators and students due to their conciseness and ease of dissemination. However, the existing micro-course production methods mostly rely on the personal ability and time of educators such as teachers, and lack systematic and automated support.

[0035] In the related technologies, there are already many technical solutions for creating micro-course teaching resources, and each technical solution has its own unique advantages. The following is an explanation of some of the main technical solutions:

[0036] 1. Create micro lessons by recording the screen: Create micro lessons by recording the display process of the computer screen and the sound obtained by the microphone. You can use presentation software (PowerPoint) to record the courseware, or use Camtasia Studio, ALLCapture, VideoStudio, Educreations, Explain Everything and other software to record and form micro lesson videos.

[0037] 2. Shoot and create micro-courses: Use shooting tools such as mobile phones, digital cameras, tablets, cameras, etc. to make micro-courses. Generally speaking, the formal shooting environment is a recording classroom. However, in actual applications, portable shooting equipment is also often used to make filmed micro-courses.

[0038] 3. Software-synthesized micro-courses: Using image, animation or video production software (such as Flash, PowerPoint, VideoStudio, Movie Maker, GIF Animator, etc.), through micro-course script design and technical synthesis, output micro-course videos for teaching. This production method is often used for micro-courses such as astronomy that require animation presentation.

[0039] 4. Mix multiple methods to create micro-courses: integrate shooting, screen recording, software synthesis, etc., and finally edit and synthesize the micro-course video. It can be seen that this production method requires high technical support and video editing level, and it takes more time, but the quality of the generated micro-course video will be higher.

[0040] It can be seen that the creation method of micro-course teaching resources in related technologies is dependent on the teacher's technology or the performance of teaching equipment, resulting in a very low efficiency in generating micro-course teaching resources. In addition, the micro-course teaching resource generation scheme in related technologies also has the problem of difficulty in ensuring the timeliness and accuracy of micro-course content.

[0041] Based on this, an embodiment of the present application proposes a method for generating teaching resources. In various embodiments of the present application, the teaching data input by the first terminal is automatically analyzed and refined in the teaching data, and the video and audio related to the micro-class are determined based on the teaching content, and then based on the video and audio related to the micro-class, the teaching resources related to the micro-class are generated. In this way, the teaching resources related to the micro-class can be created without relying on the teacher's technology or teaching equipment, which reduces manual operations and improves the generation efficiency of teaching resources related to the micro-class; the artificial intelligence big model technology is used to conduct in-depth analysis of the teaching data in a timely manner to identify all teaching knowledge point information, thereby ensuring the accuracy and timeliness of the micro-class content.

[0042] The present application embodiment provides a teaching resource generation method, which is applied to a teaching resource generation device. Figure 1 The process diagram of the teaching resource generation method of the present application embodiment is as follows Figure 1 ;like Figure 1 As shown, the teaching resource generation method includes:

[0043] Step 101: Acquire teaching data input by a first terminal.

[0044] In the embodiment of the present application, the teaching data is related to the teaching subject, and the first terminal is a terminal corresponding to an educator such as a teacher, that is, the user of the first terminal inputs or uploads the teaching subject and teaching data through the user interface displayed by the teaching resource generating device. The teaching data can also be called teaching materials.

[0045] It should be noted that, in the embodiment of the present application, the teaching data input by the first terminal may be multimodal teaching data, wherein the multimodal teaching data includes teaching data of the following types: audio, picture, video, text, etc.

[0046] Here, the teaching resource generation device has a built-in big model system, specifically an artificial intelligence big model system. That is to say, the teaching resource generation method of the embodiment of the present application is to use artificial intelligence big model technology to create teaching resources related to micro-courses for the multimodal teaching data input by the first terminal.

[0047] Step 102: Analyze the teaching data to extract teaching content from the teaching data.

[0048] In the embodiment of the present application, the teaching content represents the teaching knowledge point information provided by the first terminal, wherein the teaching knowledge point information provided by the first terminal can be understood as key teaching information used for teaching.

[0049] In actual application, the teaching resource generating device can adaptively adjust the depth and breadth of the teaching content, ie, the teaching knowledge point information, according to the difficulty of the teaching data and the characteristics of the learner (corresponding to the second terminal).

[0050] In actual application, since the artificial intelligence big model technology is used to automatically analyze the teaching data provided by the first terminal to identify all the teaching knowledge point information, the teaching data input into the artificial intelligence big model needs to be data in a format suitable for processing by the artificial intelligence big model. In other words, the teaching data provided by the first terminal needs to be preprocessed in advance, that is, the teaching data needs to be formatted, so that the format-converted teaching data is suitable for processing by the artificial intelligence big model.

[0051] Based on this, in one embodiment, the teaching data is analyzed to extract teaching content from the teaching data, including: preprocessing the teaching data to obtain teaching data in a target format; inputting the teaching data in the target format into a first target model, and analyzing the teaching data in the target format through the first target model to extract teaching content from the teaching data in the target format.

[0052] Here, the first target model is an artificial intelligence large model, and the teaching data in the target format is data in a format suitable for processing by the first target model. In practical applications, for preprocessing the teaching data to obtain teaching data in a target format, the teaching data can be format-converted to obtain data in a format suitable for processing by the first target model, that is, teaching data in a target format. Specifically, multimodal teaching data (including audio, picture, video, text and other types of teaching data) can be converted into teaching data in a target format by a specific method (such as video frame extraction, audio noise reduction, image standardization and other processing methods). Exemplarily, assuming that the teaching data is text-type teaching data, the text-type teaching data is segmented into sentences and words, and part-of-speech tagging and entity recognition are performed.

[0053] In actual application, in one embodiment, before inputting the teaching data in the target format into the first target model, the method also includes: determining the first target model; the first target model represents an artificial intelligence large model suitable for analyzing the teaching data in the target format.

[0054] In actual application, after determining the artificial intelligence big model suitable for analyzing the teaching data in the target format, that is, the first target model, the big model technology is used to conduct in-depth analysis of the teaching data in a timely manner to identify all teaching knowledge point information, thereby ensuring the accuracy and timeliness of the micro-course content. Among them, the first target model can be determined based on the data task type.

[0055] Based on this, in one embodiment, determining the first target model includes: determining the type of data task to be processed; and selecting the first target model from a plurality of artificial intelligence large models based on the type of data task to be processed.

[0056] For example, for image recognition tasks, a model based on a convolutional neural network (CNN) can be selected; for text generation tasks, a Transformer-based model can be selected, such as a pre-trained language generation model (GPT, Generative Pretrained Transformer) or a bidirectional Transformer-based autoencoding language model (BERT, Bidirectional Encoder Representation from Transformers).

[0057] In actual application, the big model technology is used to conduct in-depth analysis of the teaching data in the target format to extract key information from the teaching data in the target format and then generate teaching content.

[0058] Based on this, in one embodiment, analyzing the teaching data in the target format through the first target model to extract teaching content from the teaching data in the target format includes: analyzing the teaching data in the target format through the first target model to extract key information from the teaching data in the target format; generating the teaching content based on the key information.

[0059] Here, when the target format of the teaching data is image (picture) data, the image (picture) data is analyzed to extract features such as color, texture, and shape from the image (picture) data as key information of the image (picture) data; when the target format of the teaching data is audio data, the audio data is analyzed to extract spectral features from the audio data as key information of the audio data; when the target format of the teaching data is video data, the video data is analyzed to extract dynamic features of the video from the video data as key information of the video data; when the target format of the teaching data is text data, the text data is analyzed to extract keywords and key phrases of the text from the text data as key information of the text data.

[0060] It should be noted that in actual application, in order to grasp the teaching points of text data more accurately, it is necessary not only to extract the keywords and key phrases of the text, but also to understand the context and semantic relationships of the text. That is to say, for text-type teaching data, the extracted key information includes the keywords and key phrases of the text, as well as the context and semantic relationships of the text.

[0061] The following takes video-type teaching data as an example to explain the key information extraction process in detail.

[0062] In practical applications, since the target format of video teaching data includes two parts, image and voice (ie, audio), when extracting key information from the target format of video teaching data, it is necessary to comprehensively consider the key information of both image and voice.

[0063] Based on this, in one embodiment, the teaching data in the target format includes video teaching data in a target format; extracting key information from the teaching data in the target format includes: extracting image key frames from the video teaching data in the target format; extracting voice features from the video teaching data in the target format; based on the image key frames and the voice features, generating key summary information of the video teaching data in the target format, and determining the key summary information of the video teaching data in the target format as the key information.

[0064] Here, the teaching resource generating device can use an open source computer program such as the ffmpeg tool, or use a video processing library (such as OpenCV) to extract image key frames from the video teaching data in the target format; use a speech recognition model to perform speech recognition on the video teaching data in the target format, that is, use the speech recognition model to extract speech features from the video teaching data in the target format, so that after obtaining the image key frames and speech features, the image key frames and speech features are combined to comprehensively analyze and extract the key summary information of the video teaching data in the target format, and the key summary information of the video teaching data in the target format is determined as the key information of the teaching data in the target format.

[0065] In one embodiment, the key summary information of the video teaching data in the target format is generated based on the image key frames and the voice features, including: performing object recognition on the image key frames to obtain a first analysis result; converting the voice features into text information, and analyzing the text information to obtain a second analysis result; based on the first analysis result and the second analysis result, the key summary information of the video teaching data in the target format is generated.

[0066] Here, the teaching resource generation device can first select a visual model suitable for understanding video content, such as a pre-trained CNN model or a Transformer-based model, and then use the pre-trained CNN model or Transformer-based model to perform object recognition on the image key frames. After using the speech recognition model to extract speech features from the video teaching data in the target format, the speech features are converted into corresponding text information, and the selected natural language processing (NLP, Natural Language Processing) model suitable for text summarization, such as the BERT model, can be used to analyze the converted text information. Specifically, the converted text information can be subjected to text sentiment analysis and keyword extraction to obtain corresponding analysis results. Finally, based on the fusion of the object recognition results of the image key frames and the analysis results of the text information, the key summary information of the video teaching data in the target format is generated.

[0067] Here, the teaching resource generation device fuses the visual features and the speech features. Specifically, a simple splicing method or a more complex fusion strategy can be used to fuse the visual features and the speech features to obtain the fused features. Then, the fused features are input into the pre-trained NLP model, and the pre-trained NLP model outputs the key summary information of the video teaching data in the target format. At this point, the generation of the key summary of the video teaching data in the target format is completed.

[0068] It should be noted that in the embodiments of the present application, the key summary information of the video teaching data in the target format generally relates to the main content and emotional color of the video teaching data in the target format. Specifically, it may include key objects, scene descriptions, emotional tendencies, etc. in the video teaching data in the target format.

[0069] The following takes the teaching data of text type as an example to explain the key information extraction process in detail.

[0070] In practical applications, key information can be extracted from text-type teaching data by selecting a large model suitable for the text summarization task, namely the second target model.

[0071] Based on this, in one embodiment, the teaching data in the target format includes text teaching data in the target format; extracting key information from the teaching data in the target format includes: performing feature extraction on the text teaching data in the target format to obtain corresponding text features, and converting the text features into text feature vectors; inputting the text feature vectors into a second target model to obtain key information of the text teaching data in the target format output by the second target model.

[0072] Here, for converting the text features into text feature vectors, word embedding technology such as Word2Vec, BERT, etc. can be used to convert the text features into numerical vectors, i.e., text feature vectors. Among them, the second target model represents an artificial intelligence large model suitable for the text summary task. Exemplarily, the second target model can be a BERT model, GPT, T5 model, etc. In this way, by inputting the text feature vector into the trained second target model, and then the second target model outputs the key information of the text teaching data in the target format, the generation of the key summary of the text teaching data in the target format is completed.

[0073] In actual application, before feature extraction, the teaching resource generation device may also perform text preprocessing on the text teaching data in the target format, that is, clean the text teaching data in the target format to remove irrelevant characters and punctuation marks.

[0074] Based on this, in one embodiment, the teaching data in the target format includes text teaching data in the target format; the extracting key information from the teaching data in the target format includes: preprocessing the text teaching data in the target format to obtain preprocessed text teaching data in the target format; performing feature extraction on the preprocessed text teaching data in the target format to obtain corresponding text features, and converting the text features into text feature vectors; inputting the text feature vectors into the second target model to obtain the key information of the preprocessed text teaching data in the target format output by the second target model.

[0075] Here, when the text teaching data in the target format only includes Chinese text teaching data, preprocessing the text teaching data in the target format not only includes cleaning the text teaching data in the target format to remove irrelevant characters and punctuation marks, but also includes word segmentation of the text teaching data in the target format to divide the text teaching data in the target format into processable units.

[0076] It should be noted that, in the embodiment of the present application, the key information of the text teaching data in the target format may generally include key sentences, key phrases, etc. in the text teaching data in the target format.

[0077] In actual application, after identifying key information such as key sentences of the preprocessed target format text teaching data, the key sentences can be combined into summaries to generate key summary information of the preprocessed target format text teaching data.

[0078] Based on this, in one embodiment, after inputting the text feature vector into the second target model to obtain the key information of the preprocessed text teaching data in the target format output by the second target model, the method also includes: combining the key information of the preprocessed text teaching data in the target format to obtain the key summary information of the preprocessed text teaching data in the target format.

[0079] Here, in the embodiment of the present application, the key summary information of the pre-processed target format text teaching data may include key sentences, key phrases, etc.

[0080] Step 103: Based on the teaching content, determine the video and audio related to the micro-course.

[0081] In one embodiment, determining the video and audio related to the micro-class based on the teaching content includes: determining a target teaching template and a target teaching media resource based on the teaching content, and synthesizing the target teaching template and the target teaching media resource to obtain a video related to the micro-class; performing voice conversion on the teaching content to obtain audio related to the micro-class.

[0082] Here, the teaching resource generation device can select appropriate teaching templates and media resources according to the extracted teaching knowledge point information, that is, determine the target teaching template and the target teaching media resource. Of course, in practical applications, the relevant teaching templates and media resources can also be automatically recommended according to the extracted teaching knowledge point information, and the embodiment of the present application is not limited here. After obtaining the target teaching template and the target teaching media resource, the target teaching template and the target teaching media resource are synthesized into a micro-class video.

[0083] Here, the teaching resource generation device can use speech synthesis technology to convert the extracted teaching knowledge point information into audio, and use the audio as audio related to the micro-course.

[0084] Step 104: Generate teaching resources related to the micro-course based on the video and audio related to the micro-course.

[0085] In one embodiment, generating teaching resources related to the micro-course based on the video and audio related to the micro-course includes: synchronizing the video and audio related to the micro-course to obtain synchronized video and audio; performing one or more of the following processing methods on the synchronized video and audio to obtain the teaching resources related to the micro-course: editing; adding subtitles; adding special effects.

[0086] Here, after obtaining the video and audio related to the micro-course, the teaching resource generation device needs to ensure the synchronization of the micro-course video and the micro-course audio, and perform post-processing on the synchronized micro-course video and the micro-course audio, such as editing, adding subtitles, etc., to generate publishable micro-course teaching resources.

[0087] In one embodiment, after generating the teaching resources related to the micro-course based on the video and audio related to the micro-course, the method further includes: storing and publishing the teaching resources for the user of the second terminal to use the teaching resources.

[0088] Here, the second terminal is a terminal corresponding to a learner, such as a student. Exemplarily, for the user of the second terminal to use the teaching resources, the user of the second terminal may download or learn online the teaching resources related to the micro-course.

[0089] The present application embodiment also provides another teaching resource generation method, which is applied to a teaching resource generation device. Figure 2 The process diagram of the teaching resource generation method of the present application embodiment is as follows Figure 2 ;like Figure 2 As shown, the teaching resource generation method includes:

[0090] Step 201: Acquire teaching data input by the first terminal.

[0091] In an embodiment of the present application, the teaching data is related to the teaching topic, and the teaching data input by the first terminal may be multimodal teaching data, wherein the multimodal teaching data includes audio, picture, video, text and other types of teaching data.

[0092] Step 202: pre-process the teaching data to obtain teaching data in a target format.

[0093] Step 203: input the teaching data in the target format into the first target model, and analyze the teaching data in the target format through the first target model to extract key information from the teaching data in the target format.

[0094] In one embodiment, before inputting the teaching data in the target format into the first target model, the method further includes: determining the first target model; the first target model represents an artificial intelligence large model suitable for analyzing the teaching data in the target format.

[0095] In a specific embodiment, determining the first target model includes: determining the type of data task to be processed; and selecting the first target model from a plurality of artificial intelligence large models based on the type of data task to be processed.

[0096] In one embodiment, the teaching data in the target format includes video teaching data in a target format; extracting key information from the teaching data in the target format includes: extracting image key frames from the video teaching data in the target format; extracting voice features from the video teaching data in the target format; generating key summary information of the video teaching data in the target format based on the image key frames and the voice features, and determining the key summary information of the video teaching data in the target format as the key information.

[0097] In one embodiment, the key summary information of the video teaching data in the target format is generated based on the image key frames and the voice features, including: performing object recognition on the image key frames to obtain a first analysis result; converting the voice features into text information, and analyzing the text information to obtain a second analysis result; based on the first analysis result and the second analysis result, the key summary information of the video teaching data in the target format is generated.

[0098] In another embodiment, the teaching data in the target format includes text teaching data in the target format; extracting key information from the teaching data in the target format includes: performing feature extraction on the text teaching data in the target format to obtain corresponding text features, and converting the text features into text feature vectors; inputting the text feature vectors into a second target model to obtain key information of the text teaching data in the target format output by the second target model.

[0099] In another embodiment, the teaching data in the target format includes text teaching data in the target format; extracting key information from the teaching data in the target format includes: preprocessing the text teaching data in the target format to obtain preprocessed text teaching data in the target format; performing feature extraction on the preprocessed text teaching data in the target format to obtain corresponding text features, and converting the text features into text feature vectors; inputting the text feature vectors into a second target model to obtain key information of the preprocessed text teaching data in the target format output by the second target model.

[0100] In one embodiment, after inputting the text feature vector into the second target model to obtain the key information of the preprocessed text teaching data in the target format output by the second target model, the method further includes: combining the key information of the preprocessed text teaching data in the target format to obtain the key summary information of the preprocessed text teaching data in the target format.

[0101] Step 204: Generate teaching content based on the key information.

[0102] In the embodiment of the present application, the teaching content represents the teaching knowledge point information provided by the first terminal, and the teaching knowledge point information provided by the first terminal can be understood as key teaching information used for teaching.

[0103] Step 205: Based on the teaching content, determine the video and audio related to the micro-course.

[0104] In one embodiment, determining the video and audio related to the micro-class based on the teaching content includes: determining a target teaching template and a target teaching media resource based on the teaching content, and synthesizing the target teaching template and the target teaching media resource to obtain a video related to the micro-class; performing voice conversion on the teaching content to obtain audio related to the micro-class.

[0105] Step 206: Synchronize the video and audio related to the micro-course to obtain synchronized video and audio.

[0106] Step 207: Perform one or more of the following processing methods on the synchronized video and audio to obtain teaching resources related to the micro-course: editing; adding subtitles; adding special effects.

[0107] In one embodiment, after obtaining the teaching resources related to the micro-course, the method further includes: storing and publishing the teaching resources so that the user of the second terminal can use the teaching resources.

[0108] It should be noted that the specific processing process of the teaching resource generation device to generate teaching resources has been described in detail above and will not be repeated here.

[0109] By adopting the technical solution of the embodiment of the present application, the teaching data input by the first terminal is automatically analyzed and the teaching content in the teaching data is refined, and the video and audio related to the micro-class are determined based on the teaching content, and then the teaching resources related to the micro-class are generated based on the video and audio related to the micro-class. In this way, the teaching resources related to the micro-class can be created without relying on the teacher's technology or teaching equipment, which reduces manual operations and improves the efficiency of generating teaching resources related to the micro-class. The artificial intelligence big model technology is used to conduct in-depth analysis of the teaching data in a timely manner to identify all teaching knowledge point information, thereby ensuring the accuracy and timeliness of the micro-class content.

[0110] The present application is described below in conjunction with application examples.

[0111] In the related technologies, there are many technical solutions for creating micro-course teaching resources, such as creating micro-courses by screen recording, creating micro-courses by shooting, creating micro-courses by software synthesis, creating micro-courses by mixing multiple methods, etc. However, these common technical solutions still have the following technical problems:

[0112] 1. Single content and small capacity: Usually only the key content is highlighted, resulting in single content in micro-courses, which reduces learning interest. 2. The form is relatively monotonous: The current micro-course forms are not diverse enough, and are mostly based on teacher lectures, lacking innovation. 3. The purpose is not clear enough: The development of some micro-course designs originated from competitions, rather than application goals, resulting in generally weak application of micro-courses. 4. Technology or equipment dependence: The production and application of micro-courses require certain technology or equipment support, and have high requirements for teachers' technology or teaching equipment resources. 5. Weak innovation in teaching models: The use of micro-courses to innovate teaching models is generally weak, and more attention needs to be paid to the innovation of application-oriented and resource-sharing mechanisms.

[0113] In order to solve at least one of the above technical problems, the present application proposes a method and system for assisting teachers in creating micro-course teaching resources (corresponding to the aforementioned teaching resources related to micro-courses) with the help of artificial intelligence (AI) big model technology. The basic principles of the micro-course teaching resource generation method and system are as follows: on the provided user interface, allow the user of the first terminal to input or upload teaching topics and related multimodal teaching materials (corresponding to the aforementioned multimodal teaching data); use AI big model technology to automatically analyze the teaching materials provided by the first terminal (corresponding to the aforementioned teaching data) and extract teaching knowledge points (corresponding to the aforementioned teaching content); select appropriate teaching templates (corresponding to the aforementioned target teaching templates) and media resources (corresponding to the aforementioned target teaching media resources) according to the extracted teaching knowledge points, and synthesize the selected teaching templates and media resources into micro-course videos; use speech synthesis technology to convert the teaching content into micro-course audio and synchronize it with the micro-course video; post-process the micro-course video and micro-course audio, such as editing, adding subtitles, etc., to generate micro-course teaching resources; store and publish the generated micro-course teaching resources for users of the second terminal to download or learn the micro-course teaching resources online.

[0114] It can be seen that the micro-course teaching resource generation method proposed in this application supports the creation of micro-course teaching resources for multimodal teaching data (including audio, picture, video, text and other types of teaching data), and uses AI big model technology to automatically analyze multimodal teaching data to refine teaching content, that is, key teaching knowledge point information, to assist teachers in conveniently creating micro-course teaching resources, reduce manual operations, and improve the generation efficiency and personalization level of micro-course teaching resources; with the support of the micro-course teaching resource generation system, this application does not rely on certain technologies or equipment, and the rich micro-course teaching resources innovate the teaching model; use AI big model technology to conduct in-depth analysis of teaching data in a timely manner, identify all teaching knowledge point information, and thus ensure the accuracy and timeliness of micro-course content.

[0115] The functional architecture of the micro-course teaching resource generation system proposed in this application is explained below.

[0116] Figure 3 Schematic diagram of the functional architecture of the micro-course teaching resource generation system of the present application embodiment. Figure 3 As shown, the micro-course teaching resource generation system includes: a user interface, a teaching content analysis and refinement module, a teaching template and media resource selection module, a video editing module, a speech synthesis module, a post-processing module, and a storage and publishing module; wherein,

[0117] User interface: used to receive teaching topics and teaching materials (i.e. teaching data, including audio, picture, video, text and other types of teaching data) input or uploaded by users (corresponding to the users of the aforementioned first terminal), and to display the micro-course teaching resources after they are produced and published;

[0118] Teaching content analysis and refinement module: used to analyze teaching materials and extract teaching knowledge points (i.e. teaching content, also known as teaching content) from the teaching materials. In practical applications, the depth and breadth of teaching knowledge points can be adjusted according to the difficulty of teaching materials and learner characteristics.

[0119] Teaching template and media resource selection module: used to select appropriate teaching templates (corresponding to the aforementioned target teaching templates) and appropriate teaching media resources (corresponding to the aforementioned target teaching media resources) according to teaching knowledge points, and can also automatically recommend relevant teaching templates and teaching media resources according to teaching knowledge points.

[0120] Video editing module: used to combine teaching templates and teaching media resources into micro-class videos;

[0121] Speech synthesis module: used to convert teaching knowledge points into micro-class audio;

[0122] Post-processing module: used to post-process the synchronized micro-course video and micro-course audio to generate publishable micro-course teaching resources;

[0123] Storage and publishing module: used to store and publish generated micro-course teaching resources.

[0124] In this application, the teaching content analysis and refinement module is the core module of the micro-course teaching resource generation system. The teaching content analysis and refinement module mainly uses AI big model technology to replace traditional NLP technology, that is, it is a process of using AI big model technology to analyze and refine multimodal teaching materials.

[0125] Figure 4 Schematic diagram of the processing flow of the teaching content analysis and refinement module of the embodiment of the present application, such as Figure 4As shown in the figure, the course content analysis and refinement module mainly includes core steps such as data preprocessing, model selection, key information extraction, content understanding and generation, model fine-tuning and model integration. The implementation process of these core steps is explained below:

[0126] 1. Data preprocessing: Convert multimodal teaching materials (including audio, image, video, and text) (such as video frame extraction, audio noise reduction, image standardization, etc.) into a format suitable for AI large model processing (corresponding to the teaching data in the target format mentioned above). For example, text teaching materials are divided into sentences and words, and part-of-speech tagging and entity recognition are performed.

[0127] 2. Model selection: Select or train an AI model that is suitable for analyzing teaching materials in the target format (corresponding to the first target model mentioned above). For example, for image recognition tasks, you can choose a CNN-based model; for text generation tasks, you can choose a Transformer-based model, such as GPT or BERT.

[0128] 3. Extraction of key information: Use AI big models to conduct in-depth analysis of multimodal teaching materials after format conversion to extract key information. For example, extract color, texture, shape and other features in images, extract spectral features in audio, extract dynamic features in videos, etc. For text-based teaching materials, it is necessary not only to extract keywords and key phrases, but also to understand the context and semantic relationships, so as to grasp the teaching knowledge points more accurately.

[0129] 4. Content understanding and generation: Utilize the understanding and generation capabilities of AI big models to automatically generate teaching scripts or outlines, or even directly generate drafts of teaching content.

[0130] 5. Model fine-tuning: Fine-tune the parameters of the AI ​​big model based on data from specific teaching fields to improve the accuracy and applicability of the AI ​​big model in specific teaching scenarios.

[0131] 6. Model integration: Integrate the optimized AI large model into the micro-course teaching resource generation system to realize a fully automated process for analyzing and refining teaching materials.

[0132] The core implementation process of the teaching content analysis and refinement module is explained below in conjunction with specific application examples.

[0133] Assuming that the teaching material is a video teaching material, Figure 5 The following is a schematic diagram of the process of extracting key summary information from video teaching materials in an embodiment of the present application. Figure 1 ,like Figure 5 As shown, the processing flow mainly includes the following steps:

[0134] 1. Video preprocessing: Use tools such as ffmpeg to extract image key frames from video teaching materials.

[0135] 2. Image analysis: Use the pre-trained CNN model to perform object recognition on image keyframes.

[0136] 3. Audio processing: Use the speech recognition model to extract speech features from the video teaching materials and convert the extracted speech features into text information.

[0137] 4. Text analysis: Use NLP models such as BERT to perform sentiment analysis and keyword extraction on text information.

[0138] 5. Multimodal fusion: Combine image and text analysis results to extract the main content and emotional color of video teaching materials.

[0139] 6. Result integration: Generate key summary information of video teaching materials, generally including key objects, key scene descriptions and key emotional tendencies.

[0140] Figure 6 The following is a schematic diagram of the process of extracting key summary information from video teaching materials in an embodiment of the present application. Figure 2 ,like Figure 6 As shown in the figure, the processing flow mainly includes steps such as environment preparation, data preprocessing, model selection, feature extraction, feature fusion and summary generation. The specific implementation process is as follows:

[0141] First, prepare the relevant environment and tools, including a high-performance graphics processor (GPU, Graphic Processing Unit) (for model training and inference), Python environment, deep learning framework (such as PyTorch or TensorFlow), video processing library (such as OpenCV), audio processing library (such as librosa), and Hugging Face's Transformers library, etc.; then, use the video processing library to extract video key frames or generate thumbnails from the video teaching materials, and process the audio. The speech recognition model can be used to convert the video teaching materials into text; next, select a visual model suitable for video content understanding, such as a CNN model or a Transformer-based model; a model suitable for audio processing, such as Wav2Vec 2.0; Select a natural language processing model suitable for text summarization, such as BERT or GPT model; Next, start feature extraction, that is, extract visual features from video key frames and extract speech features from audio transcripts; Finally, fuse the visual features and speech features, which can be fused using simple splicing or more complex fusion strategies, and input the fused features into the pre-trained natural language processing model to obtain the key summary information in the video teaching materials, thus completing the generation of the summary.

[0142] Assuming that the teaching materials are text teaching materials, Figure 7 The following is a schematic diagram of the process of extracting key summary information from text teaching materials in the embodiment of the present application. Figure 1 ,like Figure 7 As shown, the processing flow mainly includes the following steps:

[0143] 1. Text preprocessing: clean the text teaching materials, remove irrelevant characters and punctuation marks, or segment the text teaching materials (for languages ​​such as Chinese) and divide the text teaching materials into processable units.

[0144] 2. Feature extraction: Use word embedding technology (such as Word2Vec, BERT, etc.) to convert the preprocessed text into a numerical vector (corresponding to the aforementioned text feature vector).

[0145] 3. Model selection: Select a large model suitable for the text summarization task (corresponding to the second target model mentioned above), such as BERT, GPT, T5 and other models.

[0146] 4. Model training: A classification model needs to be trained to identify key sentences.

[0147] 5. Key information identification: Use the selected large model suitable for the text summarization task to identify the key information in the text and combine it into a summary. For example, the output vector of the BERT model can be used to identify key sentences through thresholds or specific algorithms (such as TextRank), and the key sentences can be combined into a summary.

[0148] 6. Result integration: Generate key summary information of text teaching materials, generally including key sentences, key phrases, etc.

[0149] Figure 8 The following is a schematic diagram of the process of extracting key summary information from text teaching materials in the embodiment of the present application. Figure 2 ,like Figure 8 As shown in the figure, the processing flow includes the following steps: first, the chapter teaching materials in the text teaching materials are divided into sentences, split into multiple sentences, and the word2vec method is used to vectorize and extract features of multiple sentences. A weighted graph model is constructed based on the similarity of the features of each sentence in the text. Then, the importance of each sentence is scored based on the TextRank algorithm, and the sentence importance is sorted according to the scoring results. Finally, important sentences are selected as chapter summaries, that is, key summary information is extracted from the text teaching materials.

[0150] It should be noted that the TextRank algorithm is a graph-based text ranking algorithm used to extract keywords and key sentences from texts. It is simple and efficient, and does not rely on domain-specific corpora. Therefore, it is widely used in natural language processing tasks such as text summarization and keyword extraction. The principle of the TextRank algorithm is similar to Google's PageRank algorithm. It calculates the similarity between words or sentences in the text, builds a graph model, that is, a weighted graph model, and then uses an iterative calculation method to determine the importance score of each node (that is, each sentence).

[0151] Fig. 9 Schematic diagram of the interaction process between the user and the micro-course teaching resource generation system of the embodiment of the present application, where the interacting users include teachers and students, such as Fig. 9 As shown, the interaction process includes the following steps:

[0152] Step 1: The teacher inputs or uploads the teaching topic and related multimodal teaching materials through the user interface provided by the micro-course teaching resource generation system;

[0153] Step 2: The micro-course teaching resource generation system uses AI big model technology to analyze teaching materials and extract teaching knowledge point information (i.e. key teaching content) from the teaching materials;

[0154] Step 3: Teachers select appropriate teaching templates and teaching media resources based on key teaching content;

[0155] Step 4: The teacher uses the video editing function of the micro-class teaching resource generation system to synthesize the selected appropriate teaching template and teaching media resources into a micro-class video;

[0156] Step 5: The teacher uses the speech synthesis function of the micro-class teaching resource generation system to convert the key teaching content into micro-class audio;

[0157] Step 6: The teacher performs post-processing on the generated micro-class video and micro-class audio to generate publishable micro-class teaching resources;

[0158] Step 7: Teachers store and publish the generated micro-class teaching resources.

[0159] Step 8: Students log in and use micro-course teaching resources through the user interface provided by the micro-course teaching resource generation system.

[0160] Compared with the solutions of related technologies, the key points of this application solution are:

[0161] 1. Application of AI big model technology: Existing technologies rely on manual editing or simple software tools to generate micro-course teaching resources, while this application utilizes cutting-edge AI big model technology to provide significant improvements in accuracy, generation efficiency, and personalization.

[0162] 2. Automated process of teaching content analysis and refinement: Compared with the existing technology, the micro-course teaching resource generation system of the present application can automatically complete the teaching content analysis and refinement process for multimodal teaching materials, reduce manual intervention, and improve the generation efficiency of micro-course teaching resources.

[0163] 3. In-depth analysis and refinement of teaching content: The teaching content analysis and refinement module in this application has more advanced content understanding and information extraction capabilities, and can more accurately identify and refine teaching points compared to existing technologies.

[0164] 4. System integration and collaborative working capabilities: The various modules of the micro-course teaching resource generation system of this application work closely and efficiently together, and can provide a smoother and more seamless workflow compared to the existing technology.

[0165] 5. Artificial intelligence-assisted teaching achieves educational equity: Compared with existing technical solutions, this application not only simplifies user operations, but also has great breakthroughs in technical implementation. It is of great significance to improving educational efficiency, creating personalized teaching content, sharing educational resources and innovating teaching plans.

[0166] Compared with the solutions of the related art, the solution of the present application has the following technical effects:

[0167] 1. High degree of automation: This application uses a built-in AI large model system to automatically analyze and refine teaching content, reducing manual operations and improving the efficiency of micro-course creation.

[0168] 2. Possess intelligent analysis capabilities: Use AI big models to conduct in-depth analysis of teaching data, identify key knowledge points and teaching focus, and ensure the accuracy and pertinence of micro-course content.

[0169] 3. Resource co-construction and sharing: Support resource sharing and collaboration among teachers, promote the co-construction and sharing of high-quality micro-class teaching resources, and improve the overall teaching quality.

[0170] 4. Easy to maintain and update: It can conveniently support teachers in creating micro-class teaching resources to ensure the timeliness and accuracy of teaching content.

[0171] 5. Lower the technical threshold: Reduce the requirements for teachers' technical capabilities, allowing more teachers to participate in the production and use of micro-courses, and expanding the scope of application of micro-courses.

[0172] In order to implement the teaching resource generation method of the embodiment of the present application, the embodiment of the present application also provides a teaching resource generation device, Fig.10 Schematic diagram of the composition structure of the teaching resource generation device of the embodiment of the present application. Fig.10 As shown, the teaching resource generating device comprises:

[0173] The acquisition unit 1001 is used to acquire teaching data input by the first terminal; the teaching data is related to the teaching subject;

[0174] An extraction unit 1002 is used to analyze the teaching data to extract teaching content from the teaching data; the teaching content represents the teaching knowledge point information provided by the first terminal;

[0175] A first determining unit 1003 is used to determine the video and audio related to the micro-course based on the teaching content;

[0176] The generating unit 1004 is used to generate teaching resources related to the micro-course based on the video and audio related to the micro-course.

[0177] In one embodiment, the extraction unit 1002 includes: a preprocessing subunit and a first extraction subunit; wherein,

[0178] The preprocessing subunit is used to preprocess the teaching data to obtain teaching data in a target format;

[0179] The first extraction subunit is used to input the teaching data in the target format into the first target model, and analyze the teaching data in the target format through the first target model to extract teaching content from the teaching data in the target format.

[0180] In one embodiment, the device further includes: a second determining unit; wherein,

[0181] The second determination unit is used to determine the first target model before the first extraction subunit inputs the teaching data in the target format into the first target model; the first target model represents an artificial intelligence large model suitable for analyzing the teaching data in the target format.

[0182] In one embodiment, the second determining unit is specifically configured to:

[0183] Determine the type of data task to be processed; and select the first target model from a plurality of artificial intelligence large models based on the type of data task to be processed.

[0184] In one embodiment, the first extraction subunit includes: a second extraction subunit and a generation subunit; wherein,

[0185] The second extraction subunit is used to analyze the teaching data in the target format through the first target model to extract key information from the teaching data in the target format;

[0186] The generating subunit is used to generate the teaching content based on the key information.

[0187] In one embodiment, the teaching data in the target format includes video teaching data in the target format; and the second extraction subunit is specifically configured to:

[0188] Extracting image key frames from the video teaching data in the target format; extracting voice features from the video teaching data in the target format; generating key summary information of the video teaching data in the target format based on the image key frames and the voice features, and determining the key summary information of the video teaching data in the target format as the key information.

[0189] In one embodiment, the second extraction subunit is further specifically configured to:

[0190] Performing object recognition on the image key frame to obtain a first analysis result; converting the voice features into text information, and analyzing the text information to obtain a second analysis result; and generating key summary information of the video teaching data in the target format based on the first analysis result and the second analysis result.

[0191] In another embodiment, the teaching data in the target format includes text teaching data in the target format; and the second extraction subunit is specifically used for:

[0192] Feature extraction is performed on the text teaching data in the target format to obtain corresponding text features, and the text features are converted into text feature vectors; the text feature vectors are input into a second target model to obtain key information of the text teaching data in the target format output by the second target model.

[0193] In another embodiment, the teaching data in the target format includes text teaching data in the target format; and the second extraction subunit is specifically used for:

[0194] Preprocessing the text teaching data in the target format to obtain preprocessed text teaching data in the target format; performing feature extraction on the preprocessed text teaching data in the target format to obtain corresponding text features, and converting the text features into text feature vectors; inputting the text feature vectors into a second target model to obtain key information of the preprocessed text teaching data in the target format output by the second target model.

[0195] In one embodiment, the device further comprises: a combination unit; wherein,

[0196] The combination unit is used to combine the key information of the preprocessed text teaching data in the target format after the second extraction subunit inputs the text feature vector into the second target model to obtain the key summary information of the preprocessed text teaching data in the target format output by the second target model.

[0197] In one embodiment, the first determining unit 1003 is specifically configured to:

[0198] Based on the teaching content, a target teaching template and a target teaching media resource are determined, and the target teaching template and the target teaching media resource are synthesized to obtain a video related to the micro-class; the teaching content is voice-converted to obtain audio related to the micro-class.

[0199] In one embodiment, the generating unit 1004 is specifically configured to:

[0200] The video and audio related to the micro-course are synchronized to obtain synchronized video and audio; the synchronized video and audio are processed in one or more of the following ways to obtain the teaching resources related to the micro-course: editing; adding subtitles; adding special effects.

[0201] In one embodiment, the device further includes: a storage publishing unit, wherein:

[0202] The storage and publishing unit is used to store and publish the teaching resources related to the micro-course after the generation unit 1004 generates the teaching resources related to the micro-course based on the video and audio related to the micro-course, so that the user of the second terminal can use the teaching resources.

[0203] In actual application, the acquisition unit 1001 can be implemented by a communication interface in the teaching resource generation device; the extraction unit 1002, the first determination unit 1003 and the generation unit 1004 can be implemented by a processor in the teaching resource generation device.

[0204] It should be noted that: the teaching resource generation device provided in the above embodiment only uses the division of the above program modules as an example when generating teaching resources. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the teaching resource generation device provided in the above embodiment and the teaching resource generation method embodiment belong to the same concept. The specific implementation process is detailed in the teaching resource generation method embodiment, which will not be repeated here.

[0205] Based on the hardware implementation of the above program modules, and in order to implement the teaching resource generation method of the embodiment of the present application, the embodiment of the present application also provides a teaching resource generation device, Fig.11 Schematic diagram of the hardware structure of the teaching resource generation device of the embodiment of the present application. Fig.11 As shown, the teaching resource generating device 1100 includes:

[0206] Communication interface 1101, capable of exchanging information with other devices;

[0207] The processor 1102 is connected to the communication interface 1101 to implement information interaction with other devices, and is used to execute the teaching resource generation method provided above when running a computer program, and the computer program is stored in the memory 1103.

[0208] Specifically, the communication interface 1101 is used to obtain teaching data input by the first terminal; the teaching data is related to the teaching subject;

[0209] The processor 1102 is used to analyze the teaching data to extract teaching content from the teaching data; the teaching content represents the teaching knowledge point information provided by the first terminal; based on the teaching content, determine the video and audio related to the micro-class; based on the video and audio related to the micro-class, generate teaching resources related to the micro-class.

[0210] It should be noted that the specific processing process of the communication interface 1101 and the processor 1102 can be understood by referring to the above-mentioned teaching resource generation method.

[0211] Of course, in actual application, the various components in the teaching resource generating device 1100 are coupled together through the bus system 1104. It can be understood that the bus system 1104 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 1104 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Fig.11 Various buses are labeled as bus system 1104 .

[0212] The memory 1103 in the embodiment of the present application is used to store various types of data to support the operation of the teaching resource generating device 1100. Examples of such data include: any computer program used to operate on the teaching resource generating device 1100.

[0213] The teaching resource generation method disclosed in the above embodiment of the present application can be applied to the processor 1102, or implemented by the processor 1102. The processor 1102 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above teaching resource generation method can be completed by the hardware integrated logic circuit or software instructions in the processor 1102. The above-mentioned processor 1102 can be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 1102 can implement or execute the various teaching resource generation methods, steps and logic block diagrams disclosed in the embodiment of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the teaching resource generation method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in the memory 1103. The processor 1102 reads the information in the memory 1103 and completes the steps of the aforementioned teaching resource generation method in combination with its hardware.

[0214] In an exemplary embodiment, the teaching resource generating device 1100 can be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), field programmable gate array (FPGA), general processor, controller, microcontroller (MCU), microprocessor, or other electronic components to execute the aforementioned teaching resource generating method.

[0215] It can be understood that the memory 1103 of the embodiment of the present application can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a ferromagnetic random access memory, a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAMbus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 1103 described in the embodiments of the present application is intended to include but is not limited to these and any other suitable types of memories.

[0216] In an exemplary embodiment, the present application embodiment further provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, for example, a memory 1103 storing a computer program, and the above-mentioned computer program can be executed by a processor 1102 in the teaching resource generating device 1100 to complete the steps of the teaching resource generating method described in the above-mentioned embodiment of the present application. Among them, the computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface storage, optical disk, or CD-ROM.

[0217] In an exemplary embodiment, the present application also provides a computer program product, including a computer program, which can be executed by the processor 1102 in the teaching resource generating device 1100 to complete the steps of the teaching resource generating method described in the aforementioned embodiment of the present application.

[0218] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0219] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0220] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for generating teaching resources, characterized in that: The method comprises: Acquiring teaching data input by the first terminal; the teaching data is related to the teaching subject; Analyzing the teaching data to extract teaching content from the teaching data; the teaching content represents the teaching knowledge point information provided by the first terminal; Based on the teaching content, determine the video and audio related to the micro-course; Based on the video and audio related to the micro-course, teaching resources related to the micro-course are generated.

2. The method according to claim 1, characterized in that The analyzing the teaching data to extract teaching content from the teaching data includes: Preprocessing the teaching data to obtain teaching data in a target format; The teaching data in the target format is input into a first target model, and the teaching data in the target format is analyzed by the first target model to extract teaching content from the teaching data in the target format.

3. The method according to claim 2, characterized in that Before inputting the teaching data in the target format into the first target model, the method further includes: Determining the first target model; the first target model represents an artificial intelligence macromodel suitable for analyzing the teaching data in the target format; The determining the first target model comprises: Determine the type of data task to be processed; Based on the type of the data task to be processed, the first target model is selected from a plurality of artificial intelligence large models.

4. The method according to claim 2, characterized in that: The analyzing the teaching data in the target format by using the first target model to extract teaching content from the teaching data in the target format includes: Analyzing the teaching data in the target format by using the first target model to extract key information from the teaching data in the target format; The teaching content is generated based on the key information.

5. The method according to claim 4, characterized in that The teaching data in the target format includes video teaching data in the target format; The extracting key information from the teaching data in the target format comprises: Extracting image key frames from the video teaching data in the target format; Extracting speech features from the video teaching data in the target format; Based on the image key frames and the voice features, key summary information of the video teaching data in the target format is generated, and the key summary information of the video teaching data in the target format is determined as the key information.

6. The method according to claim 5, characterized in that The step of generating key summary information of the video teaching data in the target format based on the image key frame and the speech feature includes: Performing object recognition on the image key frame to obtain a first analysis result; Converting the speech feature into text information, and analyzing the text information to obtain a second analysis result; Based on the first analysis result and the second analysis result, key summary information of the video teaching data in the target format is generated.

7. The method according to claim 4, characterized in that The teaching data in the target format includes text teaching data in the target format; The extracting key information from the teaching data in the target format comprises: Extracting features from the text teaching data in the target format to obtain corresponding text features, and converting the text features into text feature vectors; The text feature vector is input into the second target model to obtain key information of the text teaching data in the target format output by the second target model.

8. The method according to claim 4, characterized in that The teaching data in the target format includes text teaching data in the target format; The extracting key information from the teaching data in the target format comprises: Preprocessing the text teaching data in the target format to obtain the preprocessed text teaching data in the target format; Performing feature extraction on the preprocessed text teaching data in the target format to obtain corresponding text features, and converting the text features into text feature vectors; The text feature vector is input into the second target model to obtain key information of the preprocessed text teaching data in the target format output by the second target model.

9. The method according to claim 8, characterized in that After inputting the text feature vector into the second target model to obtain the key information of the preprocessed text teaching data in the target format output by the second target model, the method further includes: The key information of the preprocessed target format text teaching data is combined to obtain the key summary information of the preprocessed target format text teaching data.

10. The method according to claim 1, characterized in that Determining the video and audio related to the micro-course based on the teaching content includes: Based on the teaching content, determine a target teaching template and a target teaching media resource, and synthesize the target teaching template and the target teaching media resource to obtain a video related to the micro-course; The teaching content is converted into voice to obtain audio related to the micro-course.

11. The method according to claim 1, characterized in that The generating of teaching resources related to the micro-course based on the video and audio related to the micro-course includes: Synchronizing the video and audio related to the micro-course to obtain synchronized video and audio; The synchronized video and audio are processed in one or more of the following ways to obtain the teaching resources related to the micro-course: editing; adding subtitles; adding special effects.

12. The method according to claim 1, characterized in that After generating the teaching resources related to the micro-course based on the video and audio related to the micro-course, the method further includes: The teaching resource is stored and published so that the user of the second terminal can use the teaching resource.

13. A teaching resource generation device, characterized in that: The device comprises: An acquisition unit, configured to acquire teaching data input by the first terminal; the teaching data is related to the teaching subject; An extraction unit, configured to analyze the teaching data to extract teaching content from the teaching data; the teaching content represents the teaching knowledge point information provided by the first terminal; A first determining unit is used to determine the video and audio related to the micro-course based on the teaching content; A generating unit is used to generate teaching resources related to the micro-course based on the video and audio related to the micro-course.

14. A teaching resource generating device, characterized in that: include: a processor and a memory for storing a computer program capable of running on said processor; Wherein, when the processor is used to run the computer program, it executes the steps of the method described in any one of claims 1 to 12.

15. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

16. A computer program product comprising a computer program, characterized in that The computer program implements the steps of the method according to any one of claims 1 to 12 when executed by a processor.

Images