Poem learning system and method
Through the following and recitation module of the poetry learning system, the recognition range is adjusted using time stamp segmented playback and voice boundary information, which solves the problem of lack of fun and immediate feedback in the traditional ancient poetry learning methods, and improves learning efficiency and memory effect.
Patent Information
- Application Number
- CN202510357681.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-25
- Publication Date
- 2025-05-23
AI Technical Summary
The traditional learning methods of ancient poetry lack interest and interactivity, and lack instant feedback mechanisms, resulting in low learning efficiency and low memory efficiency.
Provide a poetry learning system, including a reading module and a memorization module. The following module creates a follow-up time stamp to play poems in segments, and gradually displays text during playback. The recitation module adjusts the recognition range according to the user's voice boundary information and dynamically adjusts the start and end positions of the recognition range to improve the accuracy and efficiency of recitation.
Through dynamic display and segmented playback, users can learn more clearly, enhance oral expression skills, reduce learning fatigue, improve learning efficiency and fun, and solve the problem of insufficient immediate feedback and interactivity in traditional learning methods.
Smart Images
Figure CN120032540A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence, and in particular to a poetry learning system and method. Background Art
[0002] Ancient poetry is a treasure of ancient Chinese literature. It is poetry written in classical Chinese or ancient Chinese, including poems, lyrics, songs and other forms. It is known for its harmonious rhythm, concise language and profound artistic conception, and is an important carrier of Chinese culture. Learning ancient poetry can not only help us inherit and promote the excellent traditional Chinese culture, but also improve our language expression ability and literary literacy.
[0003] The traditional way of learning ancient poetry mainly relies on paper books, classroom lectures, recitation and memorization, and teachers' explanations and guidance. Although this learning method is widely used in educational practice, it also has some obvious shortcomings. First, although the content of paper books is authoritative, the form is single, lacking in fun and interactivity, and it is difficult to stimulate the interest of learners. Secondly, the traditional method lacks an instant feedback mechanism, the learning progress is slow, and the teaching efficiency is low. These shortcomings have limited the depth and breadth of ancient poetry learning to a certain extent.
[0004] Therefore, how to develop a poetry learning system to enhance the user's learning interest and improve the user's learning efficiency is a technical problem that needs to be solved urgently. Summary of the invention
[0005] The present application provides a poetry learning system to enhance the learning interest and efficiency of users. The present application also provides a poetry learning method.
[0006] In a first aspect, the present application provides a poetry learning system, comprising:
[0007] Follow-up reading module and recitation module;
[0008] The follow-up reading module is used to establish a follow-up reading timestamp according to the title, author and content of the poem and play the poem in sections according to the follow-up reading timestamp. During the process of playing the poem or the user following the reading, the text mapped by the timestamp is displayed dynamically and progressively;
[0009] The recitation module is used to display the recitation content and mark the text that needs to be displayed and / or the text that needs to be hidden according to the type of display mode, and render and display the text according to the marking. During the user's recitation, the starting position and the ending position of the recognition range are adjusted according to the boundary information in the user's voice content, and the target word position is searched within the recognition range, and the recognition range is updated according to the target word position.
[0010] Optionally, the follow-up reading module is specifically used for:
[0011] When playing poetry or the user is following along, as the audio plays, the text is gradually displayed in timestamp order and the text is gradually animated based on the start time and end time.
[0012] Optionally, the recitation module is specifically used to: detect boundary information in the user's voice content, wherein the boundary information includes voice pauses, semantic transitions or rhythm changes;
[0013] According to the boundary information, the starting position and the ending position of the recognition range are dynamically adjusted to divide the speech stream into multiple sub-segments with clear boundaries, the position of the target word is determined in each sub-segment, and the recognition range is updated according to the position of the target word.
[0014] Optionally, the system further includes: an original text module;
[0015] The original text module is used to display the original text content of ancient poems and to read and play the original text content using a preset rhythmic change rule.
[0016] Optionally, the system further comprises: an appreciation module;
[0017] The appreciation module is used to extract the original information, translation information, annotation information, creation background information and cultural heritage information of the poem;
[0018] Classify and integrate original information, translation information, annotation information, creative background information and cultural heritage information in a structured form to generate knowledge system information;
[0019] Presenting the knowledge system information.
[0020] Optionally, the system further comprises: a video module;
[0021] The video module is used to extract the artistic conception information and emotional atmosphere information contained in the original text information of the poem;
[0022] A visualization image matching the content of the poem is generated based on the artistic conception information and the emotional atmosphere information, and the visualization image is displayed.
[0023] Optionally, the follow-up reading module is further used for:
[0024] Record the user's voice reading the poem and obtain recorded voice information;
[0025] In response to the user triggering the recording playback function, the pre-recorded poetry reading audio is compared and played with the recorded voice information.
[0026] Optionally, the recitation module is further used for:
[0027] During the user's recitation process, obtain the user's recitation voice of the poem;
[0028] The recited speech is scored.
[0029] In a second aspect, the present application also provides a poetry learning method, the method comprising:
[0030] In the follow-up mode, a follow-up timestamp is established according to the title, author and content of the poem and the poem is played in segments according to the follow-up timestamp. During the poem playback process or the user's follow-up process, the text mapped by the timestamp is displayed progressively and dynamically.
[0031] In the recitation mode, according to the type of display mode, the recitation content is displayed and the text to be displayed and / or the text to be hidden is marked, and the text is rendered and displayed according to the markings. During the user's recitation, the starting position and the ending position of the recognition range are adjusted according to the boundary information in the user's voice content, and the target word position is searched within the recognition range, and the recognition range is updated according to the target word position.
[0032] Optionally, during the playback of poetry or the user's follow-up reading, the text mapped by the timestamp is displayed dynamically and progressively, including:
[0033] When playing poetry or the user is following along, as the audio plays, the text is gradually displayed in timestamp order and the text is gradually animated based on the start time and end time.
[0034] Optionally, the embodiment of the present application may also detect boundary information in the user's voice content, where the boundary information includes voice pauses, semantic transitions, or rhythm changes;
[0035] According to the boundary information, the starting position and the ending position of the recognition range are dynamically adjusted to divide the speech stream into multiple sub-segments with clear boundaries, the position of the target word is determined in each sub-segment, and the recognition range is updated according to the position of the target word.
[0036] The original text of ancient poems is displayed and the original text is read aloud using a preset rhythmic change rule.
[0037] Optionally, the embodiment of the present application can also extract the original information, translation information, annotation information, creation background information and cultural heritage information of the poem;
[0038] Classify and integrate original information, translation information, annotation information, creative background information and cultural heritage information in a structured form to generate knowledge system information;
[0039] Presenting the knowledge system information.
[0040] Optionally, the embodiment of the present application can also extract the artistic conception information and emotional atmosphere information contained in the original text information of the poem;
[0041] A visualization image matching the content of the poem is generated based on the artistic conception information and the emotional atmosphere information, and the visualization image is displayed.
[0042] Optionally, the embodiment of the present application can also record the user's voice reading the poem to obtain recorded voice information; in response to the user triggering the recording playback function, the pre-recorded poetry reading audio is compared and played with the recorded voice information.
[0043] Optionally, the embodiment of the present application can also obtain the user's reciting voice of the poem during the user's reciting process, and score the reciting voice.
[0044] In a third aspect, an embodiment of the present application provides a device, comprising a memory and a processor, wherein the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes the method described in the second aspect above.
[0045] In a fourth aspect, an embodiment of the present application provides a computer storage medium, in which a code is stored. When the code is executed, a device executing the code implements the method described in the second aspect above. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0047] Figure 1 A structural diagram of a specific implementation method of the poetry learning method provided by the present application is a poetry learning system;
[0048] Figure 2 A flowchart of a poetry learning system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0050] It should be noted that the poetry learning system and method provided in this application are used in the field of artificial intelligence applications. It can also be applied to other fields, such as the field of deep learning. The above is only an example and does not limit the application field of the method and method name provided in this application.
[0051] Ancient poetry is a treasure of ancient Chinese literature. It is poetry written in classical Chinese or ancient Chinese, including poems, lyrics, songs and other forms. It is known for its harmonious rhythm, concise language and profound artistic conception, and is an important carrier of Chinese culture. Learning ancient poetry can not only help us inherit and carry forward the excellent traditional Chinese culture, but also improve our language expression ability and literary literacy. The artistic conception and emotions of ancient poetry are rich and diverse, which can cultivate aesthetic ability and artistic appreciation, and at the same time arouse readers' emotional resonance. By learning ancient poetry, we can also gain a deeper understanding of the life, thoughts and culture of ancient society and enhance our understanding of history. In addition, the learning process of ancient poetry requires understanding, analysis and appreciation, which helps to cultivate logical thinking and innovative thinking ability.
[0052] The traditional way of learning ancient poetry mainly relies on paper books, classroom lectures, recitation and memorization, and teachers' explanations and guidance. Although this learning method is widely used in educational practice, it also has some obvious shortcomings. First, although the content of paper books is authoritative, the form is single, lacking in fun and interactivity, and it is difficult to stimulate the interest of learners. Secondly, the traditional method lacks an instant feedback mechanism, the learning progress is slow, and the teaching efficiency is low. These shortcomings have limited the depth and breadth of ancient poetry learning to a certain extent.
[0053] In view of this, the present application proposes a poetry learning system, including a follow - reading module and a reciting module; the follow - reading module is used to establish follow - reading timestamps according to the title, author, and content of the poem and play the poem in segments according to the follow - reading timestamps. During the process of playing the poem or the user's follow - reading, the text mapped by the timestamps is gradually and dynamically displayed. The reciting module is used to display the reciting content according to the type of display mode and mark the text to be displayed and / or the text to be hidden, and render and display according to the marked corresponding text. During the user's reciting process, the starting position and the ending position of the recognition range are adjusted according to the boundary information in the user's speech content, and the target word position is searched within the recognition range, and the recognition range is updated according to the target word position. Through dynamic display and segmented playback, users can more clearly follow the audio to learn, enhance their oral expression ability, and at the same time reduce the fatigue caused by long - term concentration. In addition, the gradual dynamic display can also help users better master the rhythm and rhyme of the poem, improve the interest of learning, and solve the problem of low learning efficiency caused by the lack of instant feedback and interactivity in traditional learning, as well as solve the problem of slow learning progress and low memory efficiency caused by the lack of personalized guidance in traditional reciting methods. By dynamically adjusting the recognition range and providing real - time feedback, the system can help users more efficiently memorize the poem content and reduce the time wasted by repeatedly reciting the mastered part.
[0054] To enable those skilled in the art to better understand the solution of the present application, the following further detailed description of the present application will be given in conjunction with the accompanying drawings and specific embodiments. Specifically, as Figure 1 shown.
[0055] Figure 1 is a structural diagram of a poetry learning system provided by an embodiment of the present application. As Figure 1 shown, the system includes: a follow - reading module 100 and a reciting module 110;
[0056] The follow - reading module 100 is used to establish follow - reading timestamps according to the title, author, and content of the poem and play the poem in segments according to the follow - reading timestamps. During the process of playing the poem or the user's follow - reading, the text mapped by the timestamps is gradually and dynamically displayed.
[0057] Specifically, the follow-up reading module is used to establish and store character-level follow-up reading timestamps (hereinafter referred to as timestamps) according to the title, author and content of the poem, accurately segment the poem according to the timestamp, and realize segmented playback of the poem. Combined with the timestamp of each word (start time and end time), the dual time axis synchronous rendering control logic is used to ensure that the audio playback and text display are accurately synchronized in time. During the playback of poems or the user's follow-up reading, as the audio plays, the text is gradually displayed in the order of the timestamps and the text is gradually animated based on the start time and end time (the Bezier curve smoothing algorithm for transition between words can be used to make the transition of text display more natural and smooth, thereby improving the user experience).
[0058] The follow-up reading module 100 can divide the poetry audio into the smallest word-level unit by establishing a word-level timestamp (the start time and end time of each word). This segmentation method makes the processing of audio data more refined and avoids repeated loading and processing of the entire audio. During the playback or follow-up reading process, the audio segment can be loaded on demand according to the timestamp instead of loading the entire audio file at one time. This on-demand loading mechanism greatly reduces memory usage and reduces system resource consumption. And the dual-time axis synchronous rendering control logic is used to separate audio playback and text display into two independent time axes. The audio playback time axis is responsible for controlling the playback progress of the audio, and the text display time axis controls the display order and animation effect of the text according to the timestamp. This separation mechanism makes the processing of audio and text independent of each other, reducing the coupling between the two. The system does not need to frequently update the text display state during audio playback, thereby reducing the utilization rate of CPU and memory. In addition, each word of this module has an independent timestamp, which can accurately control the synchronization of audio playback and text display. This accuracy avoids the delay or asynchronous problems that may occur in traditional methods. This module uses the Bezier curve algorithm to implement text gradient animation, making the transition of text display more natural and smooth. This algorithm is relatively efficient in calculation and will not impose too much burden on system performance. The key parameters of the gradient animation (such as the control points of the Bezier curve) can be pre-calculated and cached before playback, further reducing the amount of real-time calculations during playback and reducing response delays.
[0059] In short, this module not only reduces the usage of system resources, but also reduces response delays. At the same time, it has strong adaptability and can provide users with a smooth and efficient follow-up reading experience.
[0060] In some possible implementations, the follow-up module can also be used to:
[0061] The user's voice of following the poem is recorded to obtain the recorded voice information, and in response to the user triggering the recording playback function, the pre-recorded poetry reading audio is compared and played with the recorded voice information. That is, the follow-up reading module can also provide a follow-up reading recording playback function, which is convenient for users to compare the original audio with their own follow-up reading recording, and conduct self-evaluation and improvement.
[0062] The recitation module 110 is used to display the recitation content and mark the text that needs to be displayed and / or needs to be hidden according to the type of display mode, and render and display the corresponding text according to the marking. During the user's recitation process, the starting position and the ending position of the recognition range are adjusted according to the boundary information in the user's voice content and the target word position is searched within the recognition range, and the recognition range is updated according to the target word position. The display mode can be, for example, an interlaced display mode, a first word display mode, and a display mode without prompts, etc., so as to meet the learning needs of different users.
[0063] Specifically, the recitation module can be specifically used to re-segment the source data of poetry according to the width of the device screen. To ensure that the recitation content can be presented in an appropriate layout on electronic devices (such as mobile phones, tablets, computers) with different screen sizes, etc., to avoid abnormal text display, and provide users with a comfortable reading and recitation interface, according to the type of display mode, the recitation content is displayed and the text to be displayed and / or the text to be hidden is marked, and the text corresponding to the marking is rendered and displayed. For example, when the type of display mode is an interlaced display mode, it is necessary to clearly mark the line to be hidden, and when the type of display mode is a first word display mode, it is marked that only the position of the first word needs to be displayed, and these marking information will be used for subsequent rendering and display. Then, based on the marking information, the graphics rendering technology can be used to display the recitation content on the display interface. For the interlaced display mode, the displayed and hidden texts are displayed alternately. For the first word display mode, the first word is highlighted to guide the user to start recitation. Through this visual presentation, users can be effectively assisted in reciting.
[0064] When the user starts to recite, the boundary information in the user's voice content is detected, where the boundary information includes voice pauses, semantic transitions or rhythm changes. According to the boundary information, the starting position and the ending position of the recognition range are dynamically adjusted to divide the voice stream into multiple sub-segments with clear boundaries, and the position of the target word is determined in each sub-segment. According to the position of the target word, the recognition range is updated, that is, the recognition range is adjusted in real time and dynamically according to the user's voice content. The target word position is searched within the specified range, and the recognition range is continuously updated to ensure accurate capture of the user's recitation voice and improve recognition accuracy.
[0065] In some possible implementations, the recitation module can also be used to: obtain the user's recitation voice of the poem during the user's recitation process, and score the recitation voice.
[0066] Specifically, the recitation module can be used for speech recognition technology based on deep learning, such as Hidden Markov Model (HMM) combined with Deep Neural Network (DNN), or Conformer model. These models can convert the user's voice signal into text for comparison with the standard poetry text. Then, acoustic features are extracted from the voice signal, such as MFCC (Mel-Frequency Cepstral Coefficients) or Fbank (Filterbank) features. The neural network model can be used to score the acoustic features from multiple dimensions, such as pronunciation accuracy, fluency, completeness, rhythm, and intonation. It can accurately score the voice of the user reciting poetry and provide targeted feedback to help users improve the accuracy and fluency of poetry recitation.
[0067] In some possible implementations, the system provided by the embodiments of the present application may also include: an original text module; the original text module can be used to display the original content of the poem and read and play the original content using a preset rhythmic change rule.
[0068] In some possible implementation methods, the system provided by the embodiments of the present application may also include: an appreciation module; the appreciation module is used to extract the original information of the poem (which may include the original text of the poem, punctuation marks, and line format, etc.), the translation information (which may include the explanation of the original text of the poem), the annotation information (annotations on rare characters and allusions in the poem), the creation background information (including the author's life, creation time, and creation motivation, etc.) and the cultural heritage information (including analysis of the cultural connotation, artistic value and historical significance contained in the poem), classify and integrate the original information, translation information, annotation information, creation background information and cultural heritage information in a structured form, generate knowledge system information, and present the knowledge system information.
[0069] The presented knowledge system information may be, for example, as follows:
[0070] 1. Original Poems
[0071] Poem Name
[0072] author
[0073] dynasty
[0074] Original content
[0075] 2. Translation
[0076] Modern Chinese Translation
[0077] 3. Annotations
[0078] Annotations for rare characters
[0079] Allusion Notes
[0080] Cultural background notes
[0081] 4. Background
[0082] Biography
[0083] Creation time Motivation
[0084] Historical background
[0085] 5. Cultural heritage
[0086] Cultural Connotation
[0087] Artistic Value
[0088] Historical significance
[0089] Impact and evaluation.
[0090] In some possible implementations, the system provided by the embodiment of the present application may also include: a video module; the video module is used to extract the artistic conception information and emotional atmosphere information contained in the original text information of the poem, generate a visual image matching the content of the poem according to the artistic conception information and emotional atmosphere information, and display the visual image. The video module cleverly integrates video technology to vividly present the artistic conception depicted by the poem in a visual form, so that users can more intuitively appreciate the visual sense and emotional atmosphere created by the poem, and further deepen their understanding and memory of ancient poems.
[0091] This application proposes a poetry learning system, including a reading module and a recitation module;
[0092] The follow-up module is used to establish a follow-up timestamp according to the title, author and content of the poem and play the poem in segments according to the follow-up timestamp. During the process of playing the poem or the user following the poem, the text mapped by the timestamp is displayed dynamically and progressively. The recitation module is used to display the recitation content and mark the text to be displayed and / or hidden according to the type of display mode, and render and display the corresponding text according to the marking. During the user's recitation, the starting position and the end position of the recognition range are adjusted according to the boundary information in the user's voice content, and the target word position is searched within the recognition range, and the recognition range is updated according to the target word position. Through dynamic display and segmented playback, the system allows users to learn more clearly by following the audio, enhance oral expression skills, and reduce fatigue caused by long-term concentration. In addition, the progressive dynamic display can also help users better grasp the rhythm and rhyme of the poem, improve the fun and effect of learning, and solve the problem of low learning efficiency caused by lack of immediate feedback and interactivity in traditional learning, as well as the problem of slow learning progress and low memory efficiency caused by lack of personalized guidance in traditional recitation methods. By dynamically adjusting the recognition range and providing real-time feedback, the system can help users memorize poetry content more efficiently while reducing the time wasted on repeatedly reciting already mastered parts.
[0093] The above are some specific implementations of the poetry learning system provided by the embodiment of the present application. Based on this, the present application also provides a corresponding method. The method provided by the embodiment of the present application is introduced below, and the method can be referenced to the system poetry learning method described above.
[0094] Figure 2 The flowchart of the poetry learning method provided by the embodiment of the present invention is referred to as the second specific implementation mode, and the Figure 2 The method may include:
[0095] S201: In the follow-up mode, a follow-up timestamp is established according to the title, author and content of the poem and the poem is played in segments according to the follow-up timestamp. During the poem playing process or the user's follow-up process, the text mapped by the timestamp is displayed progressively and dynamically.
[0096] S202: In the recitation mode, according to the type of display mode, the recitation content is displayed and the text to be displayed and / or the text to be hidden is marked, and the text is rendered and displayed according to the marking. During the user's recitation, the starting position and the ending position of the recognition range are adjusted according to the boundary information in the user's voice content, and the target word position is searched within the recognition range, and the recognition range is updated according to the target word position.
[0097] Optionally, during the process of playing poems or during the user's shadow reading process, the text mapped by the time stamps is gradually and dynamically displayed, including:
[0098] During the process of playing poems or during the user's shadow reading process, as the audio is played, the text is gradually displayed in the order of time stamps, and fade-in and fade-out animation control is performed on the text based on the start time and the end time.
[0099] Optionally, the embodiments of the present application can also detect boundary information in the user's speech content, where the boundary information includes speech pauses, semantic transitions, or prosodic changes;
[0100] According to the boundary information, the start position and the end position of the recognition range are dynamically adjusted to divide the speech stream into multiple sub-segments with clear boundaries, the position of the target words is determined within each sub-segment, and the recognition range is updated according to the position of the target words.
[0101] Display the original content of the ancient poem and play the reading of the original content using the pre-set prosodic change rules.
[0102] Optionally, the embodiments of the present application can also extract the original information, translation information, annotation information, creation background information, and cultural heritage information of the poem;
[0103] Classify and integrate the original information, translation information, annotation information, creation background information, and cultural heritage information in a structured form to generate knowledge system information;
[0104] Present the knowledge system information.
[0105] Optionally, the embodiments of the present application can also extract the artistic conception information and emotional atmosphere information contained in the original information of the poem;
[0106] Generate a visual image that matches the content of the poem according to the artistic conception information and the emotional atmosphere information, and display the visual image.
[0107] Optionally, the embodiments of the present application can also record the speech of the user shadow reading the poem to obtain recorded speech information; in response to the user triggering the recording playback function, compare and play the pre-recorded reading audio of the poem with the recorded speech information.
[0108] Optionally, the embodiments of the present application can also obtain the recited speech of the user during the process of the user reciting the poem and score the recited speech.
[0109] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.
[0110] The device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes the method described in the second embodiment of the present application.
[0111] The computer storage medium stores codes, and when the codes are executed, the device executing the codes implements the method described in the second embodiment of the present application.
[0112] The "first" and "second" in the names such as "first" and "second" (if any) mentioned in the embodiments of the present application are only used as name identifiers and do not represent the first or second in order.
[0113] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute some of the methods described in the embodiments of the present application.
[0114] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the method embodiment, since it is basically similar to the system embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.
[0115] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.
Claims
1. A poetry learning system, characterized in that: include: Follow-up reading module and recitation module; The follow-up reading module is used to establish a follow-up reading timestamp according to the title, author and content of the poem and play the poem in sections according to the follow-up reading timestamp. During the process of playing the poem or the user following the reading, the text mapped by the timestamp is displayed dynamically and progressively; The recitation module is used to display the recitation content and mark the text that needs to be displayed and / or the text that needs to be hidden according to the type of display mode, and render and display the text according to the marking. During the user's recitation, the starting position and the ending position of the recognition range are adjusted according to the boundary information in the user's voice content, and the target word position is searched within the recognition range, and the recognition range is updated according to the target word position.
2. The system according to claim 1, characterized in that The follow-up reading module is specifically used for: When playing poetry or the user is following along, as the audio plays, the text is gradually displayed in timestamp order and the text is gradually animated based on the start time and end time.
3. The system according to claim 1, characterized in that The recitation module is specifically used to: detect boundary information in the user's voice content, wherein the boundary information includes voice pauses, semantic transitions or rhythm changes; According to the boundary information, the starting position and the ending position of the recognition range are dynamically adjusted to divide the speech stream into multiple sub-segments with clear boundaries, the position of the target word is determined in each sub-segment, and the recognition range is updated according to the position of the target word.
4. The system according to claim 1, characterized in that The system further comprises: an original text module; The original text module is used to display the original text content of ancient poems and to read and play the original text content using a preset rhythmic change rule.
5. The system according to claim 1, characterized in that The system further comprises: an appreciation module; The appreciation module is used to extract the original information, translation information, annotation information, creation background information and cultural heritage information of the poem; Classify and integrate original information, translation information, annotation information, creative background information and cultural heritage information in a structured form to generate knowledge system information; Presenting the knowledge system information.
6. The system according to claim 1, characterized in that The system further comprises: a video module; The video module is used to extract the artistic conception information and emotional atmosphere information contained in the original text information of the poem; A visualization image matching the content of the poem is generated based on the artistic conception information and the emotional atmosphere information, and the visualization image is displayed.
7. The system according to claim 1, characterized in that The follow-up reading module is also used for: Record the user's voice reading the poem to obtain recorded voice information; In response to the user triggering the recording playback function, the pre-recorded poetry reading audio is compared and played with the recorded voice information.
8. The system according to claim 1, characterized in that The recitation module is also used to: During the user's recitation process, obtain the user's recitation voice of the poem; The recited speech is scored.
9. A poetry learning method, characterized in that: include: In the follow-up reading mode, a follow-up reading timestamp is established according to the title, author and content of the poem, and the poem is played in segments according to the follow-up reading timestamp. During the poem playing process or the user's follow-up reading process, the text mapped by the timestamp is displayed progressively and dynamically; In the recitation mode, according to the type of display mode, the recitation content is displayed and the text to be displayed and / or the text to be hidden is marked, and the text is rendered and displayed according to the markings. During the user's recitation, the starting position and the ending position of the recognition range are adjusted according to the boundary information in the user's voice content, and the target word position is searched within the recognition range, and the recognition range is updated according to the target word position.
10. The method according to claim 9, characterized in that The text mapped by the timestamp is displayed progressively and dynamically during the poetry playback process or the user's reading process, including: When playing poetry or the user is following along, as the audio plays, the text is gradually displayed in timestamp order and the text is gradually animated based on the start time and end time.