CN116049523A - System for intelligently generating ancient poetry situation video by AI and working method thereof - Google Patents
System for intelligently generating ancient poetry situation video by AI and working method thereof Download PDFInfo
- Publication number
- CN116049523A CN116049523A CN202211398608.5A CN202211398608A CN116049523A CN 116049523 A CN116049523 A CN 116049523A CN 202211398608 A CN202211398608 A CN 202211398608A CN 116049523 A CN116049523 A CN 116049523A
- Authority
- CN
- China
- Prior art keywords
- image
- sentence
- video
- ancient poetry
- paraphrasing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/265—Mixing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The invention belongs to the field of teaching application of information technology, and provides a system for intelligently generating an ancient poetry situation video by AI and a working method thereof, wherein the system comprises an ancient poetry paraphrasing retrieval module, a Chinese-English conversion module, a prompt sentence extraction module, a single sentence image generation module and a video synthesis module; the working method comprises the following steps: (1) ancient poetry paraphrasing search; (2) Chinese paraphrasing and English paraphrasing are converted; (3) extracting a prompt sentence; (4) generating a single poem image; (5) video composition. The invention constructs an AI intelligent ancient poetry situation video generating system, which automatically generates situation videos corresponding to the content according to the ancient poetry text, can provide a large amount of video learning resources for teacher teaching and student self-learning activities, reduces understanding difficulty, provides a new way for generating the ancient poetry learning videos, and promotes the intellectualization of the ancient poetry teaching resources generation.
Description
Technical Field
The invention belongs to the field of teaching application of information technology, and in particular relates to a system for intelligently generating ancient poetry situation video by using an AI and a working method thereof.
Background
Ancient poetry teaching is an important part in primary and secondary school Chinese teaching, but the mood and emotion contained in ancient poetry are often more difficult to understand than white text.
In order to facilitate understanding of students, the current ancient poetry teaching process mainly adopts an online-published mode of making micro-lessons by using ancient poetry videos or teachers, and has the following problems: (1) limited number of video resources: only a portion of the poetry has contextual videos; and (2) the work load of the ancient poetry video production is large: automated tools are lacking to quickly generate ancient poetry videos. These problems make it difficult for the existing ancient poetry teaching video resources to meet the actual teaching requirements.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a system for intelligently generating an ancient poetry situation video by using an AI and a working method thereof, which can automatically generate the situation video for the ancient poetry.
The object of the invention is achieved by the following technical measures.
The invention provides an AI intelligent generation system for ancient poetry situation video, which comprises an ancient poetry paraphrasing retrieval module, a Chinese-English conversion module, a prompting word extraction module, a single sentence image generation module and a video synthesis module;
the ancient poetry explanation retrieval module is used for crawling full-text translations of the ancient poetry from websites such as the analysis and translation of the ancient poetry which are opened on a network by taking the titles and authors of the ancient poetry as key fields;
the Chinese-English conversion module converts the Chinese translation of the ancient poetry into English translation by using a pre-trained NLLB-200 model;
the prompt sentence extraction module extracts keywords according to the English translation and the main language overall description, the detail description, the artistic style and the picture quality to form a prompt sentence;
the single sentence image generation module generates a situation image of each sentence poem by using the extracted prompt sentence based on a Stable diffration model, then generates a abstract of the situation image by using an image abstract model, supplements the abstract to the prompt sentence, and carries out iterative optimization to obtain a final image;
the video synthesis module interpolates images generated by the single poetry into video clips by adopting a frame interpolation network, synthesizes the content of the ancient poetry into audio, and fuses the audio with video data according to the time interval of the video clips to obtain the final complete situation video of the ancient poetry.
The invention also provides a working method of the system for intelligently generating the ancient poetry situation video by the AI, which comprises the following steps:
(1) The method comprises the steps of firstly, according to the key fields of the titles and authors of the ancient poems, crawling the full-text paraphrasing of the ancient poems from the network.
(2) The Chinese paraphrasing is converted into English paraphrasing, and the Chinese paraphrasing is translated into English paraphrasing by sentence by using a pre-trained NLLB-200 model by adopting a transformer network architecture.
(3) Extracting a prompt sentence, namely firstly extracting keywords in English paraphrasing sentences, generating detailed description words of the keywords on the basis, and finally complementing artistic styles and image quality description words to obtain a final prompt sentence.
(4) Generating a single sentence poem image, converting a prompt sentence into an initial situation image by adopting a Stable distribution model, generating an image abstract for the situation image, supplementing the image abstract to the original prompt sentence, continuously generating the image by using the supplemented prompt sentence, and executing the process for 2 times to obtain a final image.
(5) And (3) video synthesis, namely expanding a situation image generated by a single poetry into a video clip, converting each sentence of Chinese poetry text into an audio file by using a TTS model, and finally writing video clip data and audio data into an ancient poetry situation video by using an FFmpeg library according to the interval time of the video clip.
According to the system for intelligently generating the context video of the ancient poetry by the AI and the working method thereof, the system for intelligently generating the context video of the ancient poetry by the AI is constructed, and the system automatically generates the context video corresponding to the content according to the text of the ancient poetry, so that a large amount of video learning resources can be provided for teacher teaching and student self-learning activities, and the understanding difficulty is reduced. In addition, no other automatic generation method for the ancient poetry situation video exists at present, and the invention provides a new path for the ancient poetry situation teaching.
Drawings
FIG. 1 is a diagram of an AI intelligent generation ancient poetry situation video system architecture in an embodiment of the invention.
Fig. 2 is a flowchart of an operation method of the AI intelligent generation ancient poetry situation video system according to the embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and embodiments, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
As shown in fig. 1, the present embodiment provides a system for intelligently generating a context video of an ancient poetry, which includes an ancient poetry paraphrasing search module, a chinese-english conversion module, a prompt sentence extraction module, a single sentence image generation module, and a video synthesis module;
the ancient poetry explanation retrieval module is used for crawling full-text translations of the ancient poetry from websites such as the analysis and translation of the ancient poetry which are opened on a network by taking the titles and authors of the ancient poetry as key fields;
the Chinese-English conversion module converts the Chinese translation of the ancient poetry into English translation by using a pre-trained NLLB-200 model;
the prompt sentence extraction module extracts keywords according to the English translation and the main language overall description, the detail description, the artistic style and the picture quality to form a prompt sentence;
the single sentence image generation module generates a situation image of each sentence in the poetry by using the extracted prompt words based on the Stable diffration model, then generates a abstract of the situation image by using an image abstract model (such as an OFA model), and supplements the abstract to the prompt sentences for iterative optimization to obtain a final image;
the video synthesis module interpolates images generated by the single poetry into video clips by adopting a frame interpolation network, synthesizes the content of the ancient poetry into audio, and fuses the audio with video data according to the time interval of the video clips to obtain the final complete situation video of the ancient poetry.
The embodiment also provides a working method of the system for intelligently generating the ancient poetry situation video by using the AI, as shown in fig. 2, comprising the following steps:
(1) The method comprises the steps of retrieving the paraphrasing of the ancient poetry, and crawling the full-text paraphrasing of the ancient poetry from the network by taking the topics and authors of the ancient poetry as key fields;
(1-1) paraphrasing crawling, establishing a session link based on Python language and https:// www.gushiwen.cn/website, replacing the names of the ancient poetry titles and authors needing to be searched with the following addresses https:// so. And obtaining hyperlinks corresponding to poems according to the definition mode of the class, and obtaining text contents corresponding to the hyperlinks, wherein the contents corresponding to the translations are complete paraphrases of the ancient poems.
And (1-2) storing the paraphrasing, namely storing the acquired poetry full-text paraphrasing according to sentences, wherein each sentence corresponds to one sentence in the ancient poetry.
(2) The Chinese paraphrasing is converted into English paraphrasing, and the Chinese paraphrasing is translated into English paraphrasing by sentence by using a pre-trained NLLB-200 model by adopting a transformer network architecture.
And (2-1) initializing a model, introducing AutoModelForSeq2SeqLM, autoTokenizer types from a transducer library, and loading an NLLB-200-Distilled-600M pre-training model.
(2-2) paraphrasing translation, coding Chinese paraphrasing sentence by using AutoTokenizer, then generating an English word segmentation device by using AutoModelForSeq2SeqLM class, and finally performing decoding operation on the obtained English word segmentation device by using AutoTokenizer class to obtain English translation of each poem.
(3) Extracting a prompt sentence, namely firstly extracting keywords in English paraphrasing sentences, generating detailed description words of the keywords on the basis, and finally complementing artistic styles and image quality description words to obtain a final prompt sentence.
And (3-1) extracting keywords, namely firstly extracting the whole sentence semantic feature vector of each English translation by adopting a Bert model, then extracting the feature vector of each word by adopting an N-Gram model, calculating the similarity between the feature vector of each word and the whole sentence semantic feature vector, and selecting the word with the maximum similarity as the keyword.
(3-2) detail description word generation, in which the words and sentences in front of the keyword and the clauses in back are searched as the detail description words and sentences of the keyword in the english paraphrasing.
(3-3) automatically completing the prompt sentences, dividing a plurality of artistic styles according to scenery, objects, figures, seasons, events and holidays, automatically completing artistic style descriptive terms of the prompt sentences according to the types of poems, and uniformly adopting high-quality descriptive terms for image quality to obtain final prompt sentences.
(4) Generating a single sentence poem image, converting a prompt sentence into an initial situation image by adopting a Stable distribution model, generating an image abstract for the situation image, supplementing the image abstract to the original prompt sentence, continuously generating the image by using the supplemented prompt sentence, and executing the process for 2 times to obtain a final image.
(4-1) initial image generation, initializing a StableDiffuse pipeline class loading pre-trained stable-diffration-v 1-4 model, transmitting a prompt statement into the StableDiffuse pipeline, and generating an initial situation image.
(4-2) image abstract generation, which adopts a transducer network architecture to generate, and uses a pre-training OFA model to generate abstract description for the situation image.
And (4-3) performing iterative optimization, supplementing the obtained abstract description information into an original prompt sentence, executing the steps (4-1) and (4-2) again by using the supplemented prompt sentence, and repeating the step (4-3) twice to obtain a final situation image of the verse.
(5) And (3) video synthesis, namely expanding a situation image generated by a single poetry into a video clip, converting each sentence of Chinese poetry text into an audio file by using a TTS model, and finally writing video clip data and audio data into an ancient poetry situation video by using an FFmpeg library according to the interval time of the video clip.
And (5-1) expanding the video clip by using the single poetry situation image, cutting the key words in the prompt sentences as image main bodies, super-resolving the cut images to the original size, and inserting frames between the original image and the cut images by using a frame insertion network to obtain the video clip.
And (5-1-1) cutting an image main body, inputting an image generated by a single sentence poem into a YOLOv5 network for target detection, selecting a keyword with highest similarity in the step (3-1) as a detection target, acquiring a bounding box corresponding to the detection target, expanding the width and the height of the bounding box by 1.5 times respectively, taking the expanded bounding box as a cutting frame, and cutting an original image generated by the words and sentences.
(5-1-2) cutting the image super-resolution, determining an amplification ratio S according to the size of the original image and the size of the cut image generated by the verse, then carrying out super-resolution S times on the cut image by adopting an RCAN network, and cutting the super-resolution image to the size of the original image.
And (5-1-3) image interpolation, wherein an original image generated by a verse and a cut image after super resolution are used as a starting frame and an ending frame, an intermediate frame image is generated by utilizing a FILM network, and then the original image, the interpolated intermediate frame image and the ending frame image are continuously subjected to frame interpolation, and 118 frames are inserted in total.
(5-2) audio synthesis, namely converting the Chinese ancient poetry text into audio files sentence by using a TTS model, calculating the time of each sentence of audio, and adding blank sounds less than 5 seconds to enable the time of each sentence of audio to be 5 seconds.
(5-3) merging the audio and video, reading the video clips into the cache according to the sequence of the poems by using the FFmpeg library, reading the synthesized audio file into the cache, and writing the synthesized audio file into the same video file.
What is not described in detail in this specification is prior art known to those skilled in the art.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents and improvements made within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (7)
1. A system for AI intelligence to generate ancient poetry situation video, its characterized in that: the system comprises an ancient poetry paraphrasing retrieval module, a Chinese-English conversion module, a prompt sentence extraction module, a single sentence image generation module and a video synthesis module;
the ancient poetry explanation retrieval module is used for crawling full-text translation of the ancient poetry from an ancient poetry analysis and translation website which are opened on a network by taking the questions and authors of the ancient poetry as key fields;
the Chinese-English conversion module converts the Chinese translation of the ancient poetry into English translation by using a pre-trained NLLB-200 model;
the prompt sentence extraction module extracts keywords according to the English translation and the main language overall description, the detail description, the artistic style and the picture quality to form a prompt sentence;
the single sentence image generation module generates a situation image of each sentence poem by using the extracted prompt sentence based on a Stable diffration model, then generates a abstract of the situation image by using an image abstract model, supplements the abstract to the prompt sentence, and carries out iterative optimization to obtain a final image;
the video synthesis module interpolates images generated by the single poetry into video clips by adopting a frame interpolation network, synthesizes the content of the ancient poetry into audio, and fuses the audio with video data according to the time interval of the video clips to obtain the final complete situation video of the ancient poetry.
2. A method of operating the AI intelligent ancient poetry context video generating system of claim 1, wherein the method comprises the steps of:
(1) The method comprises the steps of retrieving the paraphrasing of the ancient poetry, and crawling the full-text paraphrasing of the ancient poetry from the network by taking the topics and authors of the ancient poetry as key fields;
(2) Converting the Chinese paraphrasing into English paraphrasing, and translating the Chinese paraphrasing into English paraphrasing by sentence by adopting a trans former network architecture and utilizing a pre-trained NLLB-200 model;
(3) Extracting a prompt sentence, extracting key words in the English paraphrasing sentence, generating detailed description words of the key words on the basis, and complementing artistic styles and image quality description words to obtain a final prompt sentence;
(4) Generating a single sentence poem image, converting a prompt sentence into an initial situation image by adopting a Stable difference model, generating an image abstract for the situation image, supplementing the image abstract to the original prompt sentence, continuously generating an image by using the supplemented prompt sentence, and executing the process for 2 times to obtain a final image;
(5) And (3) video synthesis, namely expanding a situation image generated by the single poetry into a video clip, converting each sentence of Chinese poetry text into an audio file by using a TTS model, and finally writing video clip data and audio data into the ancient poetry situation video by using an FFmpeg library according to the interval time of the video clip.
3. The method for operating the system for intelligently generating the context video of the ancient poetry according to claim 2, wherein the paraphrasing search of the ancient poetry in the step (1) is specifically:
(1-1) paraphrasing crawling, establishing a session link with an ancient poetry website based on Python language, replacing the title and the author name of the ancient poetry to be searched with the title and the author name field in the network URL address according to the rule of the network URL address, acquiring the coding content of the replaced webpage, and searching the translation content therein to obtain the complete paraphrasing of the ancient poetry;
and (1-2) storing the paraphrasing, namely storing the acquired poetry full-text paraphrasing according to sentences, wherein each sentence corresponds to one sentence in the ancient poetry.
4. The method for intelligent AI-generated system for generating contextual video of ancient poetry according to claim 2, wherein the chinese paraphrasing and english paraphrasing converting in step (2) is specifically:
initializing a model, namely introducing AutoModelForSeq2SeqLM, autoTokenizer types from a transducer library, and loading an NLLB-200-Distilled-600M pre-training model;
(2-2) paraphrasing translation, coding Chinese paraphrasing sentence by using AutoTokenizer, then generating an English word segmentation device by using AutoModelForSeq2SeqLM class, and finally performing decoding operation on the obtained English word segmentation device by using AutoTokenizer class to obtain English translation of each poem.
5. The working method of the system for intelligently generating the ancient poetry context video by using the AI according to claim 2, wherein the prompting sentence extraction in the step (3) is specifically:
extracting key words, extracting whole sentence semantic feature vectors of English translations of each sentence by adopting a Bert model, extracting feature vectors of each word by adopting an N-Gram model, calculating the similarity between the feature vectors of each word and the whole sentence semantic feature vectors, and selecting the word with the maximum similarity as the key word;
(3-2) generating detail description words, wherein words and sentences in front of the keywords and clauses in back of the keywords are searched in English definitions to serve as detail description words and sentences of the keywords;
(3-3) automatically completing the prompt sentences, dividing a plurality of artistic styles according to scenery, objects, figures, seasons, events and holidays, automatically completing artistic style descriptive terms of the prompt sentences according to the types of poems, and uniformly adopting high-quality descriptive terms for image quality to obtain final prompt sentences.
6. The method for operating the system for intelligently generating the ancient poetry context video by using the AI according to claim 2, wherein the generating of the single poetry image in the step (4) is specifically:
(4-1) generating an initial image, initializing a StableDiffuse pipeline class loading pre-trained stable-diffuse-v 1-4 model, transmitting a prompt statement into the StableDiffuse pipeline, and generating an initial situation image;
(4-2) generating an image abstract, generating by adopting a transducer network architecture, and generating an abstract description for the situation image by utilizing a pre-training OFA model;
and (4-3) performing iterative optimization, supplementing the obtained abstract description information into an original prompt sentence, executing the steps (4-1) and (4-2) again by using the supplemented prompt sentence, and repeating the step (4-3) twice to obtain a final situation image of the verse.
7. The method for operating the system for intelligently generating the ancient poetry context video according to claim 2, wherein the video composition in step (5) is specifically:
(5-1) expanding video clips by using the single poetry situation image, performing image clipping by taking keywords in the prompt sentence as an image main body, super-resolving the clipped image to the original size, and inserting frames between the original image and the clipped image by using a frame insertion network to obtain the video clips;
(5-1-1) cutting an image main body, inputting an image generated by a single sentence poem into a YOLOv5 network for target detection, selecting a keyword with highest similarity in the step (3) as a detection target, acquiring a bounding box corresponding to the detection target, expanding the width and the height of the bounding box by 1.5 times respectively, taking the expanded bounding box as a cutting frame, and cutting an original image generated by the sentence;
(5-1-2) cutting out the super-resolution of the image, determining an amplification ratio S according to the size of the original image and the size of the cut-out image generated by the verse, performing super-resolution S times on the cut-out image by adopting an RCAN network, and cutting out the super-resolution image to the size of the original image;
(5-1-3) image interpolation, namely taking an original image generated by a verse and a cut image after super resolution as a start frame and an end frame, generating an intermediate frame image by utilizing a FILM network, continuously interpolating the original image, the interpolated intermediate frame image and the end frame image, and inserting 118 frames altogether;
(5-2) audio synthesis, namely converting the Chinese ancient poetry text into audio files sentence by using a TTS model, calculating the time of each sentence of audio, and adding blank sounds less than 5 seconds to enable the time of each sentence of audio to be 5 seconds;
(5-3) merging the audios and videos, reading video clips into a cache according to the sequence of the poems by using the FFmpeg library, reading the synthesized audio files into the cache, and writing the synthesized audio files into the same video file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211398608.5A CN116049523B (en) | 2022-11-09 | 2022-11-09 | System for intelligently generating ancient poetry situation video by AI and working method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211398608.5A CN116049523B (en) | 2022-11-09 | 2022-11-09 | System for intelligently generating ancient poetry situation video by AI and working method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116049523A true CN116049523A (en) | 2023-05-02 |
| CN116049523B CN116049523B (en) | 2023-08-22 |
Family
ID=86114548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211398608.5A Active CN116049523B (en) | 2022-11-09 | 2022-11-09 | System for intelligently generating ancient poetry situation video by AI and working method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116049523B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116634178A (en) * | 2023-07-26 | 2023-08-22 | 清华大学 | Security scene monitoring video coding and decoding method and system with extremely low code rate |
| CN117808923A (en) * | 2024-02-29 | 2024-04-02 | 浪潮电子信息产业股份有限公司 | Image generation method, system, electronic device and readable storage medium |
| CN118037898A (en) * | 2024-04-15 | 2024-05-14 | 南京邮电大学 | Text generation video method based on image guided video editing |
| CN118470160A (en) * | 2024-07-11 | 2024-08-09 | 厦门亿学软件有限公司 | Four-dimensional artistic conception automatic construction method and system based on artificial intelligent context |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020051077A1 (en) * | 2000-07-19 | 2002-05-02 | Shih-Ping Liou | Videoabstracts: a system for generating video summaries |
| CN205486907U (en) * | 2016-01-01 | 2016-08-17 | 山西大同大学 | Ware is read to ancient poetry speech point |
| CN107045810A (en) * | 2017-03-03 | 2017-08-15 | 河南职业技术学院 | One kind classic poetry teaching equipment and method in tourism |
| CN112289339A (en) * | 2020-06-04 | 2021-01-29 | 郭亚力 | System for converting voice into picture |
| CN113392273A (en) * | 2020-12-31 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Video playing method and device, computer equipment and storage medium |
-
2022
- 2022-11-09 CN CN202211398608.5A patent/CN116049523B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020051077A1 (en) * | 2000-07-19 | 2002-05-02 | Shih-Ping Liou | Videoabstracts: a system for generating video summaries |
| CN205486907U (en) * | 2016-01-01 | 2016-08-17 | 山西大同大学 | Ware is read to ancient poetry speech point |
| CN107045810A (en) * | 2017-03-03 | 2017-08-15 | 河南职业技术学院 | One kind classic poetry teaching equipment and method in tourism |
| CN112289339A (en) * | 2020-06-04 | 2021-01-29 | 郭亚力 | System for converting voice into picture |
| CN113392273A (en) * | 2020-12-31 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Video playing method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 赵芬;: "小学语文古诗词教学中情境教学策略研究", 传播力研究, no. 11 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116634178A (en) * | 2023-07-26 | 2023-08-22 | 清华大学 | Security scene monitoring video coding and decoding method and system with extremely low code rate |
| CN116634178B (en) * | 2023-07-26 | 2023-10-31 | 清华大学 | Security scene monitoring video coding and decoding method and system with extremely low code rate |
| CN117808923A (en) * | 2024-02-29 | 2024-04-02 | 浪潮电子信息产业股份有限公司 | Image generation method, system, electronic device and readable storage medium |
| CN117808923B (en) * | 2024-02-29 | 2024-05-14 | 浪潮电子信息产业股份有限公司 | Image generation method, system, electronic device and readable storage medium |
| CN118037898A (en) * | 2024-04-15 | 2024-05-14 | 南京邮电大学 | Text generation video method based on image guided video editing |
| CN118470160A (en) * | 2024-07-11 | 2024-08-09 | 厦门亿学软件有限公司 | Four-dimensional artistic conception automatic construction method and system based on artificial intelligent context |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116049523B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116049523B (en) | System for intelligently generating ancient poetry situation video by AI and working method thereof | |
| Lörscher | Investigating the translation process | |
| CN106919646B (en) | Chinese text abstract generating system and method | |
| US20170308526A1 (en) | Compcuter Implemented machine translation apparatus and machine translation method | |
| CN111428467A (en) | Method, device, equipment and storage medium for generating reading comprehension question topic | |
| CN112395858B (en) | Multi-knowledge point labeling method and system integrating test question data and answer data | |
| CN109657096B (en) | Auxiliary statistical report generation method based on low school age teaching audio and video | |
| US20210319053A1 (en) | Method and System for Automated Generation and Editing of Educational and Training Materials | |
| JP2017199363A (en) | Machine translation device and computer program for machine translation | |
| CN114972848A (en) | Image semantic understanding and text generation based on fine-grained visual information control network | |
| Hassani et al. | LVTIA: A new method for keyphrase extraction from scientific video lectures | |
| CN117787409A (en) | Man-machine interaction method and device based on large language model and electronic equipment | |
| CN115983294A (en) | Translation model training method, translation method and translation equipment | |
| KR20040024619A (en) | Third language text generating algorithm by multi-lingual text inputting and device and program therefor | |
| Vybhavi et al. | Video transcript summarizer | |
| CN117332789A (en) | Semantic analysis method and system for dialogue scene | |
| Bertin-Lemée et al. | Rosetta-lsf: an aligned corpus of french sign language and french for text-to-sign translation | |
| Ayadi et al. | Automatic translation from Arabic to Arabic Sign Language: a review | |
| CN112085985B (en) | Student answer automatic scoring method for English examination translation questions | |
| Pulipaka et al. | Machine translation of English videos to Indian regional languages using open innovation | |
| Quach et al. | Recommending the workflow of vietnamese sign language translation via a comparison of several classification algorithms | |
| KR20230080849A (en) | Content specific captioning method and system for real time online professional lectures | |
| CN114298037A (en) | Text abstract acquisition method based on deep learning | |
| KR101587026B1 (en) | Device and method for automatically generating ontologies from term definitions contained into a dictionary | |
| Vecchi et al. | Transferring multiple text styles using CycleGAN with supervised style latent space |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |