Language learning data recommendation method, device, electronic device and readable storage medium
By obtaining user history learning information and matching language learning data according to levels, the problem of recommendation mismatch in language learning applications is solved, personalized recommendations are achieved, and learning efficiency and effect are improved.
Patent Information
- Application Number
- CN202411140647.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-20
AI Technical Summary
The recommendation mechanism of existing language learning applications is usually based on the topic of interest selected by the user, resulting in the recommended learning videos that do not match the user's current level, affecting the learning experience.
By obtaining user's historical learning information, determining user levels, and matching language preview, practice and review data based on user levels, recommending learning resources suitable for their level to users.
Provide a personalized learning experience, improve learning efficiency and motivation, ensure that users obtain learning resources that are appropriate to their current level, systematically learn language, consolidate knowledge points, and improve learning results.
Smart Images

Figure CN118673221B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of language learning data recommendation, and in particular to a language learning data recommendation method, device, electronic device and readable storage medium. Background Art
[0002] With the rapid development of Internet technology, people are increasingly inclined to learn various languages through language applications installed on terminals. For example, users can use language applications to learn English. Currently, users can learn English at various stages in language applications, including English at the middle school level, English at the university level, and some work-related English content. However, current language applications usually recommend learning video resources based on the topics of interest selected by users, and usually recommend learning video resources to users in a default order. This recommendation method may result in the recommended learning videos not matching the user's current level, thus affecting the user's learning experience. Summary of the invention
[0003] In view of this, the embodiments of the present disclosure provide a language learning data recommendation method, device, electronic device and readable storage medium to solve the recommendation mismatch problem existing in current language learning applications.
[0004] In a first aspect of an embodiment of the present disclosure, a method for recommending language learning data is provided, the method comprising: obtaining historical learning information of a user in a language application; determining a user level of the user in the language application based on the historical learning information of the user in the language application; determining language learning data that matches the user level based on the user level of the language application, the language learning data comprising any one or more of the following: language preview data, language practice data, and language review data; and recommending the language learning data to the language application.
[0005] According to a second aspect of an embodiment of the present disclosure, a language learning data recommendation device is provided, the device comprising: an acquisition module for acquiring historical learning information of a user in a language application; a first determination module for determining a user level of the user in the language application based on the historical learning information of the user in the language application; a second determination module for determining language learning data matching the user level based on the user level of the user in the language application, the language learning data comprising any one or more of the following: language preview data, language practice data, and language review data; and a recommendation module for recommending language learning data to the language application.
[0006] According to a third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned language learning data recommendation method when executing the computer program.
[0007] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned language learning data recommendation method is implemented.
[0008] Compared with the prior art, the disclosed embodiment has the following beneficial effects: the disclosed embodiment can obtain the historical learning information of the user in the language application and determine the user level of the user based on the information, so as to provide each user with a personalized learning experience. The user will obtain language learning data that matches his or her actual level and needs, thereby improving learning efficiency and learning motivation. According to the user's user level in the language application, language learning data that matches the user level is determined, including language preview data, language practice data, and language review data. This precise recommendation mechanism can ensure that the user obtains learning resources that are suitable for his or her current level, and improves the pertinence and effectiveness of learning. By recommending language preview, practice, and review data suitable for the user's level, this helps the user to systematically learn the language, consolidate knowledge points, and improve learning effects. Users will be more likely to maintain learning motivation and achieve better learning results. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0010] Figure 1 is a flow chart of a method for recommending language learning data provided by an embodiment of the present disclosure;
[0011] Figure 2 is a flow chart of a method for acquiring candidate language learning videos provided by an embodiment of the present disclosure;
[0012] Figure 3 It is a flowchart of a method for extracting and marking knowledge points in a candidate language learning video provided by an embodiment of the present disclosure;
[0013] Figure 4 It is a flowchart of a method for generating a learning chart provided by an embodiment of the present disclosure;
[0014] Figure 5 is a schematic diagram of a language learning data recommendation system provided by an embodiment of the present disclosure;
[0015] Figure 6 is a block diagram of a language learning data recommendation device provided by an embodiment of the present disclosure;
[0016] Figure 7 It is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0017] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.
[0018] It should be noted that the user information (including but not limited to terminal device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.
[0019] With the rapid development of Internet technology, people are increasingly inclined to learn various languages through language applications installed on terminals. For example, users can use language applications to learn English. Currently, users can learn English at various stages in language applications, including English at the middle school level, English at the university level, and some work-related English content. However, current language applications usually recommend learning video resources based on the topics of interest selected by users, and usually recommend learning video resources to users in a default order. This recommendation method may result in the recommended learning videos not matching the user's current level, thus affecting the user's learning experience.
[0020] Therefore, it is necessary to propose a new method and system to improve the recommendation mechanism of language learning applications, so that it can better recommend learning resources according to the actual level and needs of users, thereby improving the learning effect and experience of users. The present invention aims to solve the recommendation mismatch problem existing in current language learning applications, and provide users with more personalized and accurate learning resource recommendations, thereby improving the learning efficiency and satisfaction of users.
[0021] The language learning data recommendation method and device according to the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.
[0022] Figure 1The method provided by the embodiment of the present disclosure can be executed by any electronic device with computer processing capability, for example, the electronic device can be a server.
[0023] like Figure 1 As shown, the language learning data recommendation method includes steps S110 to S140.
[0024] In step S110 , the user's historical learning information in the language application is obtained.
[0025] Step S120, determining the user level of the user in the language application according to the historical learning information of the user in the language application.
[0026] In step S130, language learning data matching the user level is determined according to the user level in the language application program, and the language learning data includes any one or more of the following: language preview data, language practice data, and language review data.
[0027] In step S140 , language learning data is recommended to the language application.
[0028] This method can provide a personalized learning experience for each user by obtaining the user's historical learning information in the language application and determining the user's user level based on the information. The user will obtain language learning data that matches his or her actual level and needs, thereby improving learning efficiency and motivation. According to the user's user level in the language application, language learning data that matches the user level is determined, including language preview data, language practice data, and language review data. This precise recommendation mechanism can ensure that users obtain learning resources that are suitable for their current level and improve the pertinence and effectiveness of learning. By recommending language preview, practice, and review data suitable for their level to users, this helps users learn the language systematically, consolidate knowledge points, and improve learning effects. Users will be more likely to maintain learning motivation and achieve better learning results.
[0029] In some embodiments of the present disclosure, the language application program of the user on the terminal device may provide the function of learning various languages, including but not limited to Chinese, English, Korean, etc. These language learning applications generally provide a variety of learning functions and resources to help users effectively learn and improve their listening, speaking, reading and writing skills in the target language. For example, for non-Chinese native users, the Chinese learning application program may provide basic pinyin, Chinese character learning, grammar rule explanation, and daily conversation practice. Advanced learners can learn more in-depth vocabulary, reading materials, listening training and writing exercises through the application program to improve their Chinese proficiency. English learning applications generally include content in English listening, speaking, reading and writing, which is suitable for learners of different levels. The application program may provide functions such as vocabulary testing, grammar practice, oral dialogue simulation, and reading comprehension to help users improve their English skills in an all-round way. Korean learning applications may provide content such as Korean alphabet learning, vocabulary practice, grammar explanation, listening practice and reading materials, which are suitable for beginners and advanced learners. Users can learn Korean culture and customs through the application program, improve their Korean listening, speaking, reading and writing skills, and prepare for daily life and career development. In addition to the above languages, language applications can also support learning various other languages, such as Spanish, French, German, Japanese, etc. These applications usually combine multiple learning methods, such as text teaching materials, video courses, voice exercises, interactive games, etc., to provide a diverse and interesting learning experience, helping users to easily and efficiently master the skills and knowledge of the target language. Through language applications on terminal devices, users can learn languages anytime and anywhere, achieving personalized and flexible learning goals.
[0030] The historical learning information of users in language applications refers to various data and information generated by users in the process of using applications. This information can help applications better understand users' learning needs, levels and preferences, so as to provide personalized learning experience. For example, when users use language applications for the first time, they can usually enter some information on the user interface of the language application, such as language level, learning goals, topics of interest, etc. This information can help applications understand users' starting level and learning needs, so as to provide users with more personalized learning recommendations. Various behaviors and interaction data of users in applications are also important historical learning information. This includes learning notes made by users, questions answered incorrectly, learning materials collected, etc. By analyzing this data, applications can understand users' learning preferences, weaknesses and interests, so as to adjust the recommended learning resources and content. Applications can track users' learning progress and achievements, including courses learned, exercises completed, test scores, etc. This data can help applications evaluate users' learning effects and adjust the recommended learning content and difficulty according to users' performance. The interaction records between users and applications are also important historical learning information. For example, discussions participated in by users, questions raised, video content watched, etc. can reflect users' learning interests and needs, and help applications better personalize the recommendation of learning resources. By comprehensively analyzing the historical learning information generated by users in language applications, the application can more accurately understand the user's learning needs and level, and provide users with more personalized and accurate learning resource recommendations, thereby improving the user's learning effect and satisfaction.
[0031] In some embodiments of the present disclosure, the user level of a user in a language application is an indicator used to characterize the user's learning situation and level on the application. This level can be determined based on the user's learning performance, historical learning information, and other relevant data, so as to provide the user with more personalized and appropriate learning resources for his level. The user level can cover different stages or detailed levels, as follows: Middle school stage: The user level can characterize the language learning level of the user in the middle school stage. This may involve the development of basic grammar, vocabulary, and listening, speaking, reading and writing skills. University stage: The user level can indicate that the user already has a certain language foundation and may need a deeper improvement in vocabulary, grammar, and reading skills. Working stage: The user level can indicate that the user already has a high level of language ability and may need professional language learning content, such as business communication, professional terminology, etc. In this embodiment, the middle school stage, university stage, and working stage can be divided more detailed according to actual needs. Detailed stage division: Primary stage: The user may be at the beginner stage and needs basic language learning resources and exercises. Intermediate stage: The user may have mastered the basics and needs more learning resources and challenges of medium difficulty. Advanced stage: Users may already have a high level of language ability and need more in-depth, specialized learning content and challenges. Sub-stage division: Sub-stages of the primary stage: such as the introductory stage, different stages of the primary stage, etc. Sub-stages of the intermediate stage: such as improvement and consolidation of the intermediate stage, etc. Sub-stages of the advanced stage: such as advancement and specialization of the advanced stage, etc. By dividing users into different levels or stages suitable for their learning levels and needs, language applications can better personalize and recommend learning resources, help users effectively improve their language skills, and achieve more efficient learning results.
[0032] In some embodiments, obtaining the user's historical learning information in the language application is a key function that can help the application better understand the user's learning habits, preferences and progress, thereby providing a more personalized and effective learning experience. This information can usually be obtained through the user database storage method, and the specific steps are as follows: The user database is a key resource for storing user information and learning data. Through the user database, the application can store and manage each user's personal information, learning records, learning progress and other data. Historical learning information may include but is not limited to the following: Learning time: Record the user's learning time on the application, including the start and end time of each learning. Learning content: Record the specific content such as courses, exercises, videos, etc. that the user has learned. Learning progress: Track the user's learning progress in each course or learning module, including the learned part and the unfinished part. Learning results: Record the user's scores in exercises and tests to evaluate the learning effect and level. Learning preferences: Analyze the user's preferences for different types of learning resources, such as video courses, exercises, games, etc., to recommend learning content in a personalized way. Data analysis: By performing data analysis on historical learning information, the application can draw the following conclusions: the user's learning habits and preferences, such as in which time period the learning effect is better, the type of learning content they like, etc. The user's learning progress and level help the application provide users with learning resources and challenges suitable for their level. The user's learning needs in order to personalize the recommendation of learning content and improve the user's learning motivation and effect. Personalized recommendation: Based on historical learning information and data analysis results, the application can implement personalized recommendation functions to recommend courses, exercises, activities, etc. that best suit the user's learning needs and level, thereby improving the user's learning experience and effect. By obtaining and analyzing the user's historical learning information in the language application, the application can better understand the user and provide more personalized and effective learning support, thereby helping users improve their language skills and achieve their learning goals faster.
[0033] In some embodiments, the user level of the user in the language application is determined based on the user's historical learning information in the language application. For example, determining the user level of the language application is to evaluate the user's learning level and ability based on the user's historical learning information and performance in the application, and classify it into different levels. This user level system can help the application to better personalize the recommendation of learning content, provide challenges and support suitable for the user's level, thereby improving the user's learning effect and satisfaction. The length of time a user spends learning on the application is an important indicator. Long-term learning may indicate the user's enthusiasm and degree of involvement in learning. The user's scores in exercises and tests can reflect their learning effect and degree of mastery. The user's learning progress in each course or learning module is also an important basis for evaluation. The user's learning frequency and continuity can also reflect his or her learning attitude and level. Users with shorter learning time, lower grades, and slower learning progress may be classified as primary users. Users with moderate learning time, average grades, and stable learning progress may be classified as intermediate users. Users with longer learning time, higher grades, and faster learning progress may be classified as advanced users. The user's level can be updated regularly based on their learning performance and historical learning information. As the user's learning progresses in the application, his or her level may also change. Level updates can motivate users to continue learning, challenge higher-level learning content, and maintain learning motivation. Based on the user's level, the application can personalize and recommend learning resources suitable for the user's level, such as courses, exercises, challenges, etc., to help users maintain their interest in learning and improve their abilities. By determining the user's level based on the user's historical learning information in the language application, the application can better understand the user's learning level and needs, and provide more personalized and effective learning support, thereby improving the user's learning experience and results.
[0034] In some embodiments, according to the user level of the user in the language application, the language learning data matching the user level is determined, and the language learning data includes any one or more of the following: language preview data, language practice data, and language review data. For example, the language preview data may include language preview text data and language preview video. The language practice data may include language practice text data and language practice video. The language review data may include language review text data and language review video. Specifically, the teaching resources matching the current level of the user can be determined through the current user level to solve the problem of low recommendation accuracy in the related art.
[0035] Language preview text data: includes reading materials suitable for the user's level, such as articles, essays, stories, etc. These texts can be classified and matched according to the difficulty of the user's language level.
[0036] Language preview videos: including teaching videos suitable for the user's level, listening practice videos, etc. The video content can cover vocabulary, grammar, listening training and other aspects to help users improve their language skills.
[0037] Language practice text data: Text materials provided to users for language practice, including fill-in-the-blank exercises, reading comprehension, grammar exercises, etc. These practice contents should be selected and recommended based on the user's language ability level.
[0038] Language practice videos: including oral practice videos and listening practice videos suitable for the user's level. These videos can help users consolidate what they have learned and improve their language proficiency.
[0039] Language review text data: Text materials provided to users to review language knowledge, including grammar summaries, key vocabulary lists, review outlines, etc. These data should be determined based on the user's level and learning progress.
[0040] Language review videos: including review videos suitable for the user's level, such as grammar point explanations, key vocabulary reviews, etc. These videos can help users review what they have learned and deepen their understanding.
[0041] In the above way, the application can match the language learning data suitable for the user through algorithms or rules according to the user's level. The matching principle can be adjusted based on factors such as the user's learning history information, level assessment results, and learning goals to ensure that the user obtains the most suitable learning resources. By determining the language learning data that matches the user level according to the user level, the application can provide users with personalized and targeted learning support to help users improve their language skills and achieve their learning goals more effectively.
[0042] In some embodiments, language preview data, language practice data, and / or language review data are recommended to language applications. For example, based on the user level, text and video materials suitable for preview are recommended. These contents may include new vocabulary, grammar knowledge, listening exercises, etc., to help users prepare before learning new knowledge. Recommendations can be based on user levels, and the user's preferences and learning performance can be analyzed by algorithms to recommend the most relevant and appropriate preview content to users. Based on the user level, text and video materials suitable for practice are recommended. These contents may include grammar exercises, reading comprehension, listening exercises, etc., to help users consolidate what they have learned. Recommendations can recommend practice content suitable for their ability level to users based on the user level. Personalized recommendations can improve the user's learning motivation and effect. Based on the user level, text and video materials suitable for review are recommended. These contents may include key vocabulary review, grammar summary, review outline, etc., to help users consolidate what they have learned. The application can continuously optimize the recommendation algorithm through user feedback, learning history data analysis, etc., to improve the accuracy and personalization of the recommendation. Continuously optimizing the recommendation system can help users find learning resources suitable for them faster and improve learning efficiency and satisfaction. By recommending language preview data, language practice data, and language review data to language applications, we can provide users with personalized and targeted learning support, helping them to improve their language skills and achieve their learning goals more effectively.
[0043] Figure 2 FIG. 1 is a flow chart of a method for obtaining candidate language learning videos provided by an embodiment of the present disclosure. Figure 2 As shown, before determining the user level of the user in the language application, the method further includes steps S210 to S240.
[0044] In step S210, an initial language learning video is obtained from an original language audio-visual resource library.
[0045] In step S220, the interval between two consecutive time axes in the subtitles of the initial language learning video is determined.
[0046] In step S230, the cutting point of the initial language learning video is determined according to the interval between two consecutive time axes in the subtitles of the initial language learning video.
[0047] In step S240, the initial language learning video is cut according to the cutting points of the initial language learning video to obtain a plurality of candidate language learning videos, and the plurality of candidate language learning videos are stored in a teaching video material library.
[0048] The method can cut the initial language learning video according to the cutting points of the initial language learning video to obtain multiple candidate language learning videos, and store the multiple candidate language learning videos in a teaching video material library, so as to provide teaching materials for subsequent recommendation scenarios.
[0049] In some embodiments, the initial language learning video is one of the important learning resources in the language learning application, which can provide users with an audio-visual learning experience and help users improve their listening, speaking and language comprehension skills. These video materials can cover various learning stages and content types to meet the learning needs of users at different stages. Video content type: Teaching videos include videos specially designed for teaching purposes, covering grammar explanations, vocabulary learning, oral practice and other content. These videos are usually produced by professional teachers or language experts to help users learn language knowledge systematically. TV programs and movies provide users with different types of TV programs and movies, allowing users to improve their listening and comprehension skills through language application in real scenes. Speech videos include speech videos on various topics, which can help users improve their understanding of specific topics while exercising their listening and oral expression skills. News videos provide the latest news reports and current affairs discussion videos to help users understand current social hot topics and expand their vocabulary and language application capabilities. The application should continuously update the initial language learning video library to ensure that users can always obtain fresh, interesting and educational video content. The updated video content should cover different topics, difficulty levels and styles to meet the learning needs and interests of different users. Based on the user's learning stage, interests, and learning goals, the application can recommend the most suitable initial language learning video for the user. By analyzing the user's learning history and feedback information, the application can better understand the user's needs and provide more personalized and accurate video recommendations. By watching different types of videos, users can expand their language application ability, increase their vocabulary, and improve their listening comprehension and oral expression. By continuously updating and optimizing the initial language learning video library, language learning applications can provide users with rich and diverse learning resources to help users get a better experience and effect in the language learning process.
[0050] In some embodiments, determining the timeline interval between subtitles in the initial language learning video is to help understand the organizational structure of the video content and cut it when necessary to provide a better learning experience. Traverse the subtitles in each initial language learning video and record the duration of each subtitle. By calculating the timeline interval between two adjacent subtitles, the duration between the subtitles can be determined. If the timeline interval between two consecutive subtitles exceeds 10 seconds, they can be regarded as two independent scenes or paragraphs. The excess of this interval indicates that the video content may have a scene transition or a theme change, so cutting can be considered at these positions. The cutting method should ensure the semantic integrity before and after the cutting point to ensure that learners can understand and absorb the coherence of the content when watching the video. Proper cutting can help users better understand the video content and avoid information overload and learning confusion. Under the premise that cutting does not affect the semantic integrity, it can improve the digestibility and learning effect of the video, making it easier for users to master and absorb knowledge. By calculating the interval between two consecutive timelines in the subtitles and cutting when necessary, the language learning application can optimize the organizational structure of the video content and provide a clearer and more coherent learning experience, thereby helping users learn and master language knowledge more efficiently.
[0051] Based on the above embodiment, according to the interval between two consecutive time axes in the subtitles of the initial language learning video, determining the cutting point of the initial language learning video includes: taking the time axis whose interval between two consecutive time axes in the subtitles of the initial language learning video exceeds the first preset duration as at least one candidate time axis; configuring the preset time parameter at the beginning and end of at least one candidate time axis to determine the cutting point of the initial language learning video. For example, the first preset duration may be 10 seconds, and the preset time parameter may be 2 seconds. According to the interval between two consecutive time axes in the subtitles of the initial language learning video, find the time axis that exceeds the first preset duration (for example, 10 seconds) as at least one candidate time axis. Leave the preset time parameter (for example, 2 seconds) at the beginning and end of at least one candidate time axis to determine the cutting point of the initial language learning video. Doing so can reserve a certain amount of time for the introduction and extraction of the dialogue, and ensure the rationality of the cutting point. Based on the cutting point calculated above, write a Python program to automatically cut the video and its supporting subtitle file. The Python program can parse the subtitle file of the video, calculate the time axis interval, determine the cutting point, and call the open source multimedia processing tool FFmpeg to realize the synchronous cutting of the video and subtitle file. In the Python program, you need to call an open source multimedia processing tool such as FFmpeg to cut the video and subtitle files. FFmpeg can be used to accurately cut video files and keep the synchronization between the video and the subtitles, ensuring that the cut video content and the subtitle content match. Through the above process, you can automatically determine the cutting point of the initial language learning video according to the subtitle timeline interval, and use the Python program to call the FFmpeg tool to achieve synchronous cutting of the video and subtitle files. Such an automated process can improve the organizational structure of video content and the learning experience, and provide users with more personalized and efficient learning resources.
[0052] In some embodiments, after cutting the initial language learning video, the method further includes: determining whether the duration of each candidate language learning video after cutting is greater than a second preset duration, and deleting the candidate language learning video greater than the second preset duration; determining whether the duration of each candidate language learning video after cutting is less than a third preset duration, and deleting the candidate language learning video less than the third preset duration, and the third preset duration is less than the second preset duration. For example, the second preset duration can be 10 minutes, and the third preset duration is 1 minute. In this way, the candidate language learning videos after cutting are screened to ensure that the length of the final generated video is within a suitable range to provide a better learning experience. After cutting the initial language learning video, it is necessary to determine the duration of each candidate language learning video. By calculating the duration of each candidate video, the length of each video can be known. Second preset duration (for example, 10 minutes): For the candidate language learning video, check whether its duration is greater than the second preset duration. If the duration of a candidate video exceeds the second preset duration, delete it. In this way, videos that are too long can be excluded to ensure that the video length is moderate. The third preset duration (for example, 1 minute): Next, check whether the duration of the remaining candidate language learning videos is less than the third preset duration. If the duration of a candidate video is less than the third preset duration, it will also be deleted. The third preset duration should be less than the second preset duration, so that videos that are too short can be excluded to ensure that the video length is not too short. Through this screening method, candidate language learning videos with moderate duration can be retained and provided to users for learning. The length of the screened video will neither be too long to cause excessive learning burden, nor too short to cause incomplete content, thereby providing users with a good learning experience. Through the above steps, the cut candidate language learning videos can be screened to ensure that the final generated video length is within an appropriate range, providing users with more refined and efficient learning resources.
[0053] In some embodiments, the initial language learning video is cut according to the cutting point of the initial language learning video to obtain multiple candidate language learning videos, and the multiple candidate language learning videos are stored in the teaching video material library. For example, according to the cutting point determined above, the initial language learning video is cut to obtain multiple candidate language learning videos. Each candidate video should contain a complete language learning content unit, such as a dialogue segment, a grammar explanation, etc. The multiple candidate language learning videos obtained by cutting are stored in the teaching video material library. This video material library can be used for a database or folder system for storing teaching video resources. Each candidate video should be correctly named and marked for subsequent management and retrieval. It can be classified and labeled according to factors such as video content, theme, difficulty, etc. The manager needs to maintain the teaching video material library to ensure that the video resources therein are the latest, high-quality, and meet user needs. The video material library can be regularly reviewed and updated, outdated or low-quality video resources can be deleted, and new high-quality learning resources can be added. In order to ensure the security of the video material library, it can be considered to back up the video resources regularly and take necessary security measures to prevent data loss or damage. You can consider using cloud storage or other backup solutions to ensure the reliability and durability of the video library. Through the above steps, the multiple candidate language learning videos cut can be effectively stored in the teaching video library, providing rich video resources for subsequent teaching activities and learning. This management method can improve the organization and accessibility of video resources and provide users with a better learning experience.
[0054] Figure 3 FIG. 1 is a flow chart of a method for extracting and annotating knowledge points in a candidate language learning video provided by an embodiment of the present disclosure. Figure 3 As shown, the above method may further include step S310 and step S320.
[0055] In step S310, teaching features are extracted from each candidate language learning video, where the teaching features include vocabulary features, grammar features, and sentence features.
[0056] In step S320, the difficulty coefficients of vocabulary features, grammatical features, and sentence features are marked according to preset strategies, and the marking results are stored in the teaching video material library.
[0057] This method can effectively extract various knowledge points from the text subtitles in the video based on the automatic extraction program, and annotate them in the teaching materials to help teachers and students better understand and apply these knowledge points. Such automated processing can improve teaching efficiency and quality and promote the dissemination and learning of knowledge.
[0058] In some embodiments of the present disclosure, teaching features are extracted from various candidate language learning videos, and the teaching features include lexical features, grammatical features, and sentence pattern features. For example, the automatic extraction program for knowledge points is mainly developed and written based on open-source tools in the field of natural language processing such as Python NLTK, Stanfordnlp, and JMWE. The extraction algorithm for vocabulary includes steps such as word segmentation, sentence segmentation, stop word removal, part-of-speech tagging, lemmatization, named entity recognition, and word frequency analysis. The extraction algorithm for grammar is completed jointly based on dictionary matching and matching based on part-of-speech rule templates. The extraction algorithm for sentence patterns is matched based on the classical grammar dictionary. Each extracted knowledge point will be annotated in the teaching materials.
[0059] Specifically, Python NLTK (Natural Language Toolkit, abbreviated as NLTK) is a Python library for natural language processing that provides rich tools and resources for processing text data. Stanfordnlp is a natural language processing tool developed by Stanford University that provides functions such as word segmentation, part-of-speech tagging, and syntactic analysis. JMWE (Java Maximum Entropy Toolkit for Word Segmentation and Named Entity Recognition) is a tool for word segmentation and named entity recognition. The extraction algorithm for vocabulary includes the following steps: Word segmentation: splitting the text into words or phrases; Sentence segmentation: splitting the text into sentences; Stop word removal: removing common words with no actual meaning, such as "de" (of), "shi" (is), etc.; Part-of-speech tagging: determining the part of speech of each word, such as noun, verb, etc.; Lemmatization: restoring the word to its basic form, such as restoring "running" to "run"; Named entity recognition: identifying named entities in the text, such as person names, place names, etc.; Word frequency analysis: analyzing the frequency of words appearing in the text. The extraction algorithm for grammar is based on dictionary matching and matching based on part-of-speech rule templates. The extraction algorithm for sentence patterns is matched based on the classical grammar dictionary to identify sentence structures and grammar rules. Each extracted knowledge point will be annotated in the teaching materials so that teachers and students can clearly understand the content and importance of each knowledge point. The annotation can include information such as the name, definition, example sentences, and related concepts of the knowledge point, making the knowledge point easier to understand and remember. Through the above steps, the automatic extraction program can effectively extract various knowledge points from the text and annotate them in the teaching materials to help teachers and students better understand and apply these knowledge points. Such automated processing can improve teaching efficiency and quality and promote the dissemination and learning of knowledge.
[0060] In some embodiments, the difficulty coefficients of vocabulary features, grammar features, and sentence features are marked according to preset strategies, and the marking results are stored in the teaching video material library. For example, the preset strategy includes configuring difficulty quantification formulas according to the knowledge points of each stage, which are used to calculate the difficulty characteristics of vocabulary, grammar, sentence patterns, and video speech speed. The difficulty coefficient markings may include the following:
[0061] Vocabulary difficulty: calculated based on factors such as vocabulary frequency, word length, and vocabulary spelling difficulty.
[0062] Grammatical difficulty: Calculated based on factors such as usage frequency and vocabulary difficulty in usage.
[0063] Sentence Difficulty: Calculated based on the frequency of grammar in the sentence and the difficulty of the grammar point.
[0064] After obtaining the difficulty features of vocabulary, usage, sentence structure, etc., the overall difficulty features of the video teaching clips can be calculated and marked. The overall difficulty features can comprehensively consider factors such as vocabulary, grammar, sentence structure difficulty, and video speech speed to provide teachers and students with a comprehensive evaluation indicator. The difficulty coefficient results calculated and marked are stored in the teaching video material library. Such marking can help teachers and students better understand and choose teaching resources suitable for their own level. The marking results can include information such as the difficulty level and difficulty coefficient value of each clip for subsequent teaching activities and learning. Through the above steps, the difficulty features of vocabulary, grammar, sentence structure and the video itself can be calculated and marked according to the preset strategy, and the results can be stored in the teaching video material library. Such difficulty marking can help teachers and students better select and use teaching resources and improve learning efficiency and quality.
[0065] In some embodiments, a mapping relationship is established between the candidate language learning videos in the teaching video material library and their corresponding teaching features, and these mapping relationships are stored in the teaching video material library, so that the corresponding teaching materials can be quickly queried when recommending to users later. For each language learning video, there are corresponding teaching features in the teaching video material library, such as vocabulary difficulty, grammar difficulty, sentence difficulty, etc. A mapping relationship is established to associate the features of each video with its corresponding teaching video, so that the corresponding relationship between the video and its features can be quickly found. The mapping relationship between the video and the teaching features is stored in the teaching video material library, usually in the form of a database. Each video has a unique identifier, and the corresponding teaching features are also associated and stored through this identifier. When the mapping relationship between the video and the teaching features is established and stored in the teaching video material library, the system can quickly query the teaching features of a specific video. When recommending language learning videos to users, the system can quickly query qualified videos according to the user's learning needs and level, and recommend them to users. By establishing a mapping relationship and realizing the quick query and recommendation functions, the user experience can be improved, allowing users to more easily find teaching resources that meet their needs. Users can quickly find suitable language learning videos according to their learning goals, interests and levels, thereby improving learning efficiency and results. Through the above steps, a mapping relationship between videos and teaching features is established and stored in the teaching video material library, thereby realizing fast query and recommendation functions, providing users with a better learning experience and personalized support.
[0066] In some embodiments, the method further includes: establishing a scene theme index based on the video scene subtitles corresponding to each candidate language learning video; establishing a test question label index based on the historical test data with a frequency greater than a preset number of times in the historical test data; and storing the scene theme index and the test question label index in the teaching video material library. For example, the video scene subtitles corresponding to each candidate language learning video are processed by an automated algorithm to establish a scene theme index, realize automatic classification of scene texts, facilitate users to retrieve videos of their own interest, and enhance learning enthusiasm. The automated topic indexing algorithm includes steps such as text preprocessing, feature word extraction, feature word weighting, topic modeling, similarity calculation, and text topic clustering algorithm. Among them, this embodiment implements the topic clustering of text based on the LDA model (Latent Dirichlet Allocation). Sort out the test question scene keywords that appear frequently in various large-scale language proficiency tests, especially extracting them from some tests that emphasize the practical application ability and output ability of the language. For example, IELTS TOEFL listening, speaking, writing tests, CET-4 and CET-6 writing tests, etc. Establish a mapping relationship between exam question keywords and teaching video subject terms, create an exam question tag index for the teaching video, and achieve the connection between system learning and examination needs.
[0067] Based on the above embodiment, the video scene subtitles corresponding to each candidate language learning video are processed by an automated algorithm to perform text preprocessing, including word segmentation, part-of-speech tagging, etc. Key feature words are extracted from the processed text and weighted according to their importance. The text is clustered by themes using topic modeling techniques, such as the LDA model, and the text content is summarized into different topics. Similarity calculation and topic clustering: Calculate the similarity between texts, perform topic clustering, and classify videos of related topics together. Sort out the high-frequency test scene keywords in various large-scale language proficiency tests, such as IELTS, TOEFL, CET-4 and CET-6. According to the keywords that appear more than a preset number of times in the historical test data, establish a test question label index to describe the theme and content of the test question. Establish a mapping relationship between test question keywords and teaching video subject words so as to associate test question labels with video themes. The established scene subject index and test question label index are stored in the teaching video material library for subsequent query and recommendation. Such index storage can help users quickly retrieve the video content they are interested in and improve their learning enthusiasm and efficiency. Through the above steps, a scene theme index is established based on the video scene subtitles, and a test question label index is established based on historical test data, and these indexes are stored in the teaching video material library. Such index establishment and storage can help the system achieve the connection between learning and test needs, and provide users with more personalized and targeted learning recommendations.
[0068] In some embodiments, the candidate language learning videos, teaching features, scene theme indexes, and test question label indexes in the teaching video material library are associated with each other so that when recommending to the user, the teaching language data matching the user can be recommended to the language application program according to the user's actual situation. Each candidate language learning video will have corresponding teaching features, such as vocabulary difficulty, grammar difficulty, etc. These teaching features can be associated with the video through a unique identifier. The scene theme index of each video can describe the theme and content of the video and is associated with the video through a unique identifier. The test question label index describes the test question theme involved in the video and is associated with the video through a unique identifier. Analyze according to the user's actual situation and learning needs, including language learning level, learning goals, interests and hobbies, etc. According to the user's needs and personalized information, the system can retrieve videos matching the user from the teaching video material library. When recommending, the user's learning features, scene theme preferences, and test question label requirements will be comprehensively considered to ensure that the recommended video meets the user's actual situation and learning needs. Through the established association, the system can recommend teaching language data matching the user according to the user's actual situation, including video content, teaching features, scene theme, and test question labels. Personalized recommendations can help users find teaching resources that meet their learning needs more quickly, improving learning outcomes and learning interests. By establishing associations between videos, teaching features, scene theme indexes, and test question label indexes, the system can recommend teaching language data that matches the user based on the user's actual situation, achieve personalized recommendations, and improve the user's learning experience and outcomes. Such a recommendation system can better meet the user's learning needs and help users improve their language skills more quickly.
[0069] Figure 4 FIG. 1 is a flow chart of a method for generating a learning graph provided by an embodiment of the present disclosure. Figure 4 As shown, the above method may further include steps S410 to S430.
[0070] In step S410, in the process of a user learning a language using a language application, behavior data made in response to language learning video data is recorded and stored in a user database.
[0071] In step S420, learning content feedback information made by the teacher regarding the user's historical learning situation in the language application is received, and the learning content feedback information is stored in the user database.
[0072] In step S430, a learning chart is generated based on the behavior data and the learning content feedback information, and the learning chart is stored in the user database.
[0073] The method can record the behavior data made for language learning video data in the process of users learning languages using language applications, and store the behavior data in a user database. The method can receive the learning content feedback information made by the teacher for the user's historical learning situation in the language application, and store the learning content feedback information in the user database. A learning chart is generated based on the behavior data and the learning content feedback information, and the learning chart is stored in the user database. In this way, the user's behavior data in the language learning video can be recorded in real time, the teacher's learning content feedback information can be received, and a learning chart is generated based on these data, providing users with more comprehensive learning feedback and analysis. This personalized learning monitoring and feedback system can help users better understand their own learning situation, adjust learning strategies in a timely manner, and improve learning effects.
[0074] In some embodiments, in the process of a user learning a language using a language application, the behavior data made for the language learning video data is recorded, and these data are stored in the user database. At the same time, it also includes receiving the learning content feedback information made by the teacher for the user's historical learning situation in the language application, and storing this information in the user database. Finally, a learning chart is generated based on the behavior data and the learning content feedback information, and these charts are stored in the user database. When the user watches the language learning video, the system records the user's behavior data, such as viewing time, number of views, number of pauses, repeated viewing segments, etc. These behavior data are stored in the user database so that the system can analyze the user's learning habits and behavior patterns. The teacher can provide feedback information for the user's historical learning situation in the language application, including learning progress, learning effect, suggested aspects for improvement, etc. Feedback information storage: These learning content feedback information are also stored in the user database so that the system can understand the user's learning performance and the teacher's evaluation. Based on the user's behavior data and the teacher's feedback information, a learning chart is generated, such as a learning progress chart, a learning effect evaluation chart, a learning behavior analysis chart, etc. These generated learning charts are also stored in the user database so that users and teachers can view the learning situation and progress.
[0075] Figure 5 Schematic diagram of a language learning data recommendation system provided by an embodiment of the present disclosure.
[0076] like Figure 5 As shown, the language learning data recommendation system may include an audio-visual resource processing module, a teaching feature marking module, and a learning plan adaptive recommendation module. Among them, the teaching feature marking module includes a teaching content extraction module, a difficulty feature marking module, a topic label indexing module, and a test question label indexing module. The language learning data recommendation system is mainly used to execute four parts of the operation process:
[0077] ①. Preparation process of teaching materials: Original audio-visual resource library: Collect various language learning resources, including videos, audios, texts, etc. Store these resources in the original audio-visual resource library as basic data for subsequent processing. Cut and filter the original video through the audio-visual resource processing module to extract the clips suitable for teaching. Annotate the cut video, including adding subtitles, annotations, etc. Extract key teaching content from the video through the teaching content extraction module, such as vocabulary, grammar, sentence patterns, etc. Organize the extracted teaching content into structured data for subsequent use. Difficulty feature labeling: Label the teaching content according to its difficulty through the difficulty feature labeling module, such as elementary, intermediate, advanced, etc. Topic label indexing: Label the teaching content according to the theme through the topic label indexing module, so that users can learn according to the theme. Test label indexing: Generate corresponding test questions according to the teaching content through the test label indexing module, and label them for users to practice. Store the processed teaching videos and related data in the teaching video material library for users to learn and use.
[0078] ②. User information collection and update process: User information collection: When a user uses the application for the first time, basic information about the user is collected, such as age, language level, learning goals, etc. Based on the collected information, a personalized learning plan and recommended content are configured for the user.
[0079] The user database stores the user's basic information and learning data in the user database. The user's learning data is updated in real time, including learning progress, learning results, etc. The user data is preprocessed, including data cleaning, feature extraction, etc. The user's learning behavior and characteristics are analyzed to provide data support for subsequent personalized recommendations.
[0080] ③. Teachers’ feedback process on user learning situation: Teacher management module: Teachers log in to the system through the management module to view students’ learning situation. Teachers can manage their own students, including viewing students’ learning data and providing feedback. Teachers provide specific learning feedback and suggestions based on students’ learning data. The teacher’s feedback information is stored in the user database for students to view and refer to.
[0081] ④. Flexible recommendation process: Optimal learning path planning: According to the user's learning data and characteristics, the optimal learning path is planned, and learning content and resources suitable for the user are recommended. Provide users with personalized learning recommendations, including videos, exercises, review content, etc. Before formal learning, recommend users to preview to understand the content to be learned. During the learning process, recommend users to do relevant exercises to consolidate the learning content. After the study, recommend users to review to strengthen memory and understanding. Through the collaborative work of the above four parts, the language learning application can provide users with a comprehensive and personalized learning experience, helping users learn languages more effectively.
[0082] The disclosure solves the outstanding pain points of second language learners in language learning other than their mother tongue through an in-depth understanding and research of language learning rules. For example, the user's mother tongue is Chinese, and he wants to learn English as a second language. The above method can be used to deeply process audio-visual resources according to teaching purposes. Generally, the complete broadcast time of English TV movies is relatively long. If users watch them completely, they are likely to ignore the purpose of learning. Therefore, the system cuts the video into scene segments of appropriate length in the processing link; the current American drama learning products can only be recommended according to the default video playback order, and the experience is poor. In the implementation process, the disclosure will recommend learning content according to the user's ability and interest, so as to teach students in accordance with their aptitude; in addition, videos of important knowledge points can also be recommended to users for learning first, and this method is particularly suitable for improving short-term learning effects. In addition, the learning function of the system fully considers the methods and advantages of situational teaching. For example, when users are in different learning stages, the required resources and learning strategies are different; it is best to let users understand the background knowledge in the preview stage, and the review stage is to deepen and consolidate cognition by doing vocabulary exercises. Therefore, the disclosure has formulated corresponding implementation methods for the learning and practice programs of each stage. The third is to provide learning plans that meet the different needs of learners to the greatest extent. Based on clear feature markings such as the difficulty of teaching materials and assessment points, as well as long-term and detailed tracking records of individual students' learning conditions, adaptive teaching materials are provided for learners. In addition, the system also establishes test question links, which is beneficial for users to practice knowledge points in the learning process. In general, the present invention solves the pain points mentioned in the above background technology, can put itself in the shoes of users when using learning software, and provide them with personalized learning plans with good interactivity and obvious learning effects.
[0083] Figure 6 It is a block diagram of a language learning data recommendation device provided by an embodiment of the present disclosure.
[0084] like Figure 6 As shown, the language learning data recommendation device 600 includes an acquisition module 610 , a first determination module 620 , a second determination module 630 and a recommendation module 640 .
[0085] Specifically, the acquisition module 610 is used to acquire the user's historical learning information in the language application.
[0086] The first determining module 620 is used to determine the user level of the user in the language application according to the historical learning information of the user in the language application.
[0087] The second determining module 630 is used to determine language learning data matching the user level according to the user level in the language application program, where the language learning data includes any one or more of the following: language preview data, language practice data, and language review data.
[0088] The recommendation module 640 is used to recommend language learning data to the language application.
[0089] The language learning data recommendation device 600 can obtain the historical learning information of the user in the language application program, and determine the user's user level based on the information, so as to provide each user with a personalized learning experience. The user will obtain language learning data that matches his or her actual level and needs, thereby improving learning efficiency and learning motivation. According to the user's user level in the language application program, the language learning data that matches the user level is determined, including language preview data, language practice data, and language review data. This accurate recommendation mechanism can ensure that the user obtains learning resources that are suitable for his or her current level, and improves the pertinence and effect of learning. By recommending language preview, practice and review data suitable for his or her level to the user, it is helpful for the user to systematically learn the language, consolidate knowledge points, and improve learning effects. The user will be more likely to maintain learning motivation and achieve better learning results.
[0090] In some embodiments of the present disclosure, before determining the user level of the user in the language application, the language learning data recommendation device 600 is further used to: obtain an initial language learning video from an original language audio-visual resource library; determine the interval between two consecutive time axes in the subtitles of the initial language learning video; determine the cutting point of the initial language learning video according to the interval between two consecutive time axes in the subtitles of the initial language learning video; cut the initial language learning video according to the cutting point of the initial language learning video to obtain multiple candidate language learning videos, and store the multiple candidate language learning videos in a teaching video material library.
[0091] In some embodiments of the present disclosure, determining the cutting point of the initial language learning video based on the interval between two consecutive time axes in the subtitles of the initial language learning video includes: taking a time axis in the subtitles of the initial language learning video in which the interval between two consecutive time axes exceeds a first preset duration as at least one candidate time axis; and configuring preset time parameters at the beginning and end of at least one candidate time axis to determine the cutting point of the initial language learning video.
[0092] In some embodiments of the present disclosure, after cutting the initial language learning video, the language learning data recommendation device 600 is further used to: determine whether the duration of each candidate language learning video after cutting is greater than a second preset duration, and delete the candidate language learning videos that are greater than the second preset duration; determine whether the duration of each candidate language learning video after cutting is less than a third preset duration, and delete the candidate language learning videos that are less than the third preset duration, and the third preset duration is less than the second preset duration.
[0093] In some embodiments of the present disclosure, the language learning data recommendation device 600 is also used to: extract teaching features from each candidate language learning video, the teaching features including vocabulary features, grammatical features, and sentence features; mark the difficulty coefficients of the vocabulary features, grammatical features, and sentence features according to preset strategies, and store the marked results in the teaching video material library.
[0094] In some embodiments of the present disclosure, the language learning data recommendation device 600 is also used to: establish a scene theme index based on the video scene subtitles corresponding to each candidate language learning video; establish a test question label index based on historical test data with a frequency of occurrence greater than a preset number of times in the historical test data; and store the scene theme index and the test question label index in the teaching video material library.
[0095] In some embodiments of the present disclosure, the language learning data recommendation device 600 is also used to: record behavioral data made in response to language learning video data during the process of a user using a language application to learn a language, and store the behavioral data in a user database; receive learning content feedback information made by a teacher regarding the user's historical learning situation in the language application, and store the learning content feedback information in the user database; generate a learning chart based on the behavioral data and the learning content feedback information, and store the learning chart in the user database.
[0096] Figure 7 is a schematic diagram of an electronic device 700 provided in an embodiment of the present disclosure. Figure 7As shown, the electronic device 700 of this embodiment includes: a processor 710, a memory 720, and a computer program 730 stored in the memory 720 and executable on the processor 710. When the processor 710 executes the computer program 730, the steps in the above-mentioned language learning data recommendation method embodiments are implemented. Alternatively, when the processor 710 executes the computer program 730, the functions of the modules in the above-mentioned device embodiments are implemented.
[0097] The electronic device 700 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 700 may include, but is not limited to, a processor 710 and a memory 720. Those skilled in the art will appreciate that Figure 7 The electronic device 700 is merely an example and does not limit the electronic device 700 . The electronic device 700 may include more or fewer components than those shown in the figure, or different components.
[0098] The processor 710 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
[0099] The memory 720 may be an internal storage unit of the electronic device 700, for example, a hard disk or memory of the electronic device 700. The memory 720 may also be an external storage device of the electronic device 700, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 700. The memory 720 may also include both an internal storage unit of the electronic device 700 and an external storage device. The memory 720 is used to store computer programs and other programs and data required by the electronic device.
[0100] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.
[0101] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present disclosure implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned language learning data recommendation method embodiments can be implemented. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.
[0102] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should all be included in the protection scope of the present disclosure.
Claims
1. A method for recommending language learning data, characterized in that: include: Get the user's historical learning information in the language application; Determining the user level of the user in the language application according to the historical learning information of the user in the language application; Determining language learning data matching the user level according to the user level of the user in the language application, the language learning data comprising any one or more of the following: language preview data, language practice data, and language review data; recommending the language learning data to the language application; Before determining the user level of the user in the language application, the method further comprises: Access initial language learning videos from original language audio-visual resource repositories; Determining the interval between two consecutive time axes in the subtitles of the initial language learning video; determining a cutting point of the initial language learning video according to an interval between two consecutive time axes in the subtitles of the initial language learning video; Cutting the initial language learning video according to the cutting points of the initial language learning video to obtain a plurality of candidate language learning videos, and storing the plurality of candidate language learning videos in a teaching video material library; Determining the cutting point of the initial language learning video according to the interval between two consecutive time axes in the subtitles of the initial language learning video includes: taking two consecutive time axes in the subtitles of the initial language learning video whose interval exceeds a first preset time length as at least one candidate time axis; configuring preset time parameters at the beginning and end of at least one of the candidate timelines to determine a cutting point of the initial language learning video; After cutting the initial language learning video, the method further includes: Determine whether the duration of each candidate language learning video after cutting is greater than a second preset duration, and delete the candidate language learning videos greater than the second preset duration; determining whether the duration of each candidate language learning video after cutting is less than a third preset duration, and deleting the candidate language learning video less than the third preset duration, wherein the third preset duration is less than the second preset duration; The method further comprises: Establishing a scene topic index based on the video scene subtitles corresponding to each of the candidate language learning videos; Establishing a test question label index based on historical test data that has a frequency greater than a preset number of times in the historical test data; The scene theme index and the test question label index are stored in the teaching video material library.
2. The method for recommending language learning data according to claim 1, characterized in that: The method further comprises: Extracting teaching features from each of the candidate language learning videos, wherein the teaching features include vocabulary features, grammar features, and sentence features; The difficulty coefficients of the vocabulary features, the grammatical features, and the sentence features are marked respectively according to a preset strategy, and the marking results are stored in the teaching video material library.
3. The method for recommending language learning data according to claim 1, characterized in that: The method further comprises: In the process of a user learning a language using the language application, recording behavior data performed in response to the language learning video data, and storing the behavior data in a user database; receiving learning content feedback information made by a teacher regarding the user's historical learning situation in the language application, and storing the learning content feedback information in the user database; A learning chart is generated based on the behavior data and the learning content feedback information, and the learning chart is stored in the user database.
4. A language learning data recommendation device, characterized in that: include: The acquisition module is used to obtain the user's historical learning information in the language application; A first determining module, configured to determine the user level of the user in the language application according to the historical learning information of the user in the language application; A second determining module is used to determine language learning data matching the user level according to the user level of the user in the language application, wherein the language learning data includes any one or more of the following: language preview data, language practice data, and language review data; a recommendation module, configured to recommend the language learning data to the language application; Before determining the user level of the user in the language application, the language learning data recommendation device is further used to: Access initial language learning videos from original language audio-visual resource repositories; Determining the interval between two consecutive time axes in the subtitles of the initial language learning video; determining a cutting point of the initial language learning video according to an interval between two consecutive time axes in the subtitles of the initial language learning video; Cutting the initial language learning video according to the cutting points of the initial language learning video to obtain a plurality of candidate language learning videos, and storing the plurality of candidate language learning videos in a teaching video material library; Determining the cutting point of the initial language learning video according to the interval between two consecutive time axes in the subtitles of the initial language learning video includes: taking two consecutive time axes in the subtitles of the initial language learning video whose interval exceeds a first preset time length as at least one candidate time axis; configuring preset time parameters at the beginning and end of at least one of the candidate timelines to determine a cutting point of the initial language learning video; After cutting the initial language learning video, the language learning data recommendation device is further used to: Determine whether the duration of each candidate language learning video after cutting is greater than a second preset duration, and delete the candidate language learning videos greater than the second preset duration; determining whether the duration of each candidate language learning video after cutting is less than a third preset duration, and deleting the candidate language learning video less than the third preset duration, wherein the third preset duration is less than the second preset duration; The language learning data recommendation device is also used for: Establishing a scene topic index based on the video scene subtitles corresponding to each of the candidate language learning videos; Establishing a test question label index based on historical test data that has a frequency greater than a preset number of times in the historical test data; The scene theme index and the test question label index are stored in the teaching video material library.
5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the language learning data recommendation method according to any one of claims 1 to 3 is implemented.
6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the language learning data recommendation method according to any one of claims 1 to 3 is implemented.
Citation Information
Patent Citations
Method, system and medium for splicing and playing multi-language audio-video files according to levels
CN113453072A
Historical score-based curriculum recommendation method and system for online education platform
CN114418807A
Intelligent editing method and system for teaching video, electronic equipment and storage medium
CN114938462A
Education resource recommendation method and system based on artificial intelligence
CN116628339A
Intelligent language education system and method
CN118135851A
