Video generation method and device, equipment, medium and product
By obtaining text and image information in integrated media news files, using information processing models to generate news releases and driving virtual character broadcasts, the problems of lack of fun and low communication efficiency of traditional integrated media news are solved, and the rapid generation of efficient news videos is achieved. .
Patent Information
- Application Number
- CN202411227373.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-29
AI Technical Summary
The traditional graphic and text-based integrated media news lacks interest, resulting in poor user viewing and low communication efficiency. The traditional professional studio recording method is costly and long, making it difficult to quickly generate video news.
By obtaining text and image information in integrated media news files, using information processing models to generate news releases, and driving virtual character broadcasts, combining audio and video to generate news videos, improving the fun and dissemination efficiency of news videos.
It realizes the rapid generation of interesting news videos, improves user viewing and communication efficiency, and meets the timeliness of news content.
Smart Images

Figure CN119052603A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of news production technology, and in particular, relates to a video generation method, device, equipment, medium and product. Background Art
[0002] Converged media is a new type of media that makes full use of media carriers. It is a media that makes use of the advantages of radio, television and the Internet and has developed into a major carrier for disseminating news.
[0003] With the rapid development of information technology, integrated media news has gradually become an important force in disseminating news content. At present, the main carriers of integrated media news are graphic files, but the graphic files lack interest, which makes users have a poor viewing experience and makes the dissemination efficiency of integrated media news low. Summary of the invention
[0004] The embodiments of the present application provide a video generation method, device, equipment, medium and product, which can improve the interest of integrated media news and thus improve the dissemination efficiency of integrated media news.
[0005] In a first aspect, an embodiment of the present application provides a video generation method, comprising:
[0006] Acquire a converged media news file, where the converged media news file includes a text file and a first file, where the text file is a file recording text information of the news, and the first file is a file recording image information of the news;
[0007] Generate news releases based on text files;
[0008] Drive the target virtual character to broadcast news articles and generate audio and video;
[0009] Generate a news video based on the first file and the audio and video.
[0010] In a second aspect, an embodiment of the present application provides a video generating device, including:
[0011] An acquisition module is used to acquire a converged media news file, wherein the converged media news file includes a text file and a first file, wherein the text file is a file recording text information of the news, and the first file is a file recording image information of the news;
[0012] A generation module is used to generate news articles based on text files;
[0013] The generation module is also used to drive the target virtual character to broadcast news articles and generate audio and video;
[0014] The generation module is also used to generate a news video based on the first file and the audio and video.
[0015] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising:
[0016] a processor and a memory storing computer program instructions;
[0017] When the processor executes the computer program instructions, it is used to perform the video generation method of the first aspect mentioned above.
[0018] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the video generation method of the first aspect described above is implemented.
[0019] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when processed by a processor, implements the video generation method of the first aspect mentioned above.
[0020] The video generation method, device, equipment, medium and product provided in the embodiments of the present application can generate news articles through the text files included in the integrated media news files, drive the target virtual character to broadcast the news articles, generate audio and video, generate news videos based on the first file and audio and video included in the integrated media news files, and broadcast the news articles through the virtual characters, so that the generated news videos can increase the fun of the news videos, improve the user's viewing experience, and thus improve the dissemination efficiency of the news videos. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0022] Figure 1 A flowchart of a video generation method provided for some embodiments of the present application.
[0023] Figure 2 A flowchart of another video generation method provided for some embodiments of the present application.
[0024] Figure 3 A flowchart of another video generation method provided for some embodiments of the present application.
[0025] Figure 4 A schematic diagram of a video generating device provided in some embodiments of the present application.
[0026] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0027] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.
[0028] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0029] Before describing the technical solutions provided by the embodiments of the present application, in order to facilitate the understanding of the embodiments of the present application, the present application first specifically describes the problems existing in the related art:
[0030] In recent years, with the rise of short videos, video media with a single piece of news as the core has become more popular with the public than traditional text-based integrated media content, and has shown more outstanding communication capabilities with its communication platform advantages and readability. However, the traditional professional studio recording method faces the dilemma of high production costs and long cycles, which is incompatible with the current demand for rapid dissemination. News content must adhere to the principles of authenticity, timeliness and accuracy. Therefore, how to quickly generate video integrated media news and overcome the boring impression of text-based integrated media news on users has become a problem to be solved.
[0031] Based on this, the embodiments of the present application provide a video generation method, device, equipment, medium and product, which can solve the above-mentioned problems. The video generation method provided in the embodiments of the present application is described in detail below.
[0032] In some embodiments, Figure 1 As shown, the embodiment of the present application provides a video generation method, including:
[0033] S110: Acquire a converged media news file, where the converged media news file includes a text file and a first file. The text file is a file recording text information of the news, and the first file is a file recording image information of the news.
[0034] The integrated media news file received by the user device can be obtained based on the user device. The integrated media news file can include a text file and a first file. The text file is a file that records the text information of the news, for example, it can be a text description of the news. The first file is a file that records the image information of the news, for example, the first file can be an image file or a video file.
[0035] S120: Generate a news release based on the text file.
[0036] News articles can be generated based on text files. Here, an information processing model can be used to generate news articles from text files. The information processing model is a model trained based on training samples. The training process of the information processing model includes:
[0037] Acquire training samples, which include multiple sample text files and multiple sample news articles generated based on the sample text files; input the multiple sample text files into an initial information processing model to obtain reference news articles, and train the initial information processing model based on the deviation between the sample news articles and the reference news articles to obtain an information processing model.
[0038] S130: driving the target virtual character to broadcast the news article and generate audio and video.
[0039] The target virtual cultural relic can be driven to broadcast news videos and generate audio and video. The target virtual character is a person with a virtual image set artificially. The user can select the target virtual character based on the virtual character material library, which can include a variety of virtual character materials with different images and taken from different angles.
[0040] In some examples, the target virtual character may be driven to broadcast a news release to obtain the audio of the news release, and then the audio and the virtual character image may be input into a preset audio-driven lip shape model to synthesize the audio and video of the virtual character broadcasting the news release.
[0041] In some examples, after generating audio and video, a video quality enhancement model can be used to process the audio and video to improve the quality of the audio and video. Specifically, the image parameters of the audio and video can be adjusted, such as adjusting the image contrast and image resolution to obtain audio and video with higher display effects.
[0042] S140: Generate a news video based on the first file and the audio and video.
[0043] A news video is generated based on the first file and the audio and video. Here, the first file can be spliced with the audio and video to obtain the news video.
[0044] The embodiment of the present application generates a news article based on a text file included in a converged media news file, drives a target virtual character to broadcast the news article, generates audio and video, generates a news video based on a first file and the audio and video included in the converged media news file, and broadcasts the news article by a virtual character. It is possible to quickly generate a news video based on the converged media news file and at the same time generate a news video, thereby increasing the fun of the news video, improving user perception, and facilitating improving the dissemination efficiency of the news video.
[0045] In some embodiments, in order to further improve the efficiency of generating news videos, the embodiments of the present application provide a video generation method, including:
[0046] The text file includes news element information and prompt information, and the prompt information includes at least one of the following: title information and annotation information;
[0047] Generate news articles based on text files, including:
[0048] Entity extraction algorithms are used to extract news element information and prompt information included in text files; news releases are generated based on the news element information and prompt information.
[0049] Here, the news element information may include time, place, people, cause of the event, course of the event and result of the event. The prompt information may include at least one of the title information and annotation information. The entity extraction algorithm may be used to extract the news element information and prompt information in the text file, and a news release may be generated based on the news element information and prompt information.
[0050] In some examples, the extracted news element information and prompt information can be used to generate news releases based on the above-mentioned information processing model, so that the generated news releases carry appropriate punctuation points, thereby making the target virtual character's reading of the news releases closer to the punctuation points of the real news anchor reading the news releases.
[0051] In some examples, the entity extraction algorithm included in the natural language processing (NLP) model can be used to generate news articles by using news element information as positive prompt information and using prompt information such as annotation information, title information, footnote information, etc. as negative prompt information.
[0052] The embodiment of the present application extracts news element information and prompt information included in a text file through an entity extraction algorithm, and generates news articles based on the news element information and prompt information, which can improve the efficiency of generating news articles, and then improve the efficiency of generating news videos, and meet the timeliness of news content requirements.
[0053] In some embodiments, in order to improve the user's perception of the news video, the method further includes:
[0054] The news releases are classified based on a preset sentiment classification algorithm to determine the target sentiment type of the news releases; based on the correspondence between the preset sentiment type and the virtual character, the target virtual character corresponding to the target sentiment type is determined.
[0055] The news releases can be classified based on a preset sentiment classification algorithm to determine the target sentiment type of the news releases. Specifically, the news releases can be classified using a sentiment classification algorithm included in a text sentiment classification model, which is a model included in NLP.
[0056] In some examples, the sentiment classification model can determine the positive sentiment type or the negative sentiment type of the news release, and can determine the target virtual character corresponding to the target sentiment type based on the correspondence between the preset sentiment types and the virtual characters.
[0057] In some examples, the image and language style of the virtual character have a preset correspondence with the emotion type. For example, when the emotion classification algorithm determines that the emotion classification of a news article is a positive emotion type, the image of the target virtual character is an image with a smiling expression and a humorous language style.
[0058] The embodiment of the present application classifies news articles through a sentiment classification algorithm, and determines a target virtual character based on the correspondence between the sentiment type and the virtual character, so that the news articles broadcast by the target virtual character are more in line with the emotional scene of the current news article.
[0059] In some embodiments, Figure 2 As shown, the first file includes a target image file; the news article includes a first sub-article and a second sub-article; the audio and video include a first video and a first audio;
[0060] Drive the target virtual character to broadcast news articles and generate audio and video, including:
[0061] S210: driving the target virtual character to broadcast the first sub-manuscript to generate a first video; and driving the target virtual character to broadcast the second sub-manuscript to generate a first audio.
[0062] When the first file includes the target image file, the target virtual character can be driven to broadcast the first sub-script to generate the first video, and the target virtual character can be driven to broadcast the second sub-script to generate the first audio, wherein the second sub-script is a script describing the target image file.
[0063] Generate news videos based on first-party files and news articles, including:
[0064] S220: In response to a first operation of the user, a second video is generated based on the target image file and the first audio, where the first operation is an operation input by the user to capture the target image file to obtain a video.
[0065] The user can input a first operation, shoot the target image file to obtain a video of the target image file, and then generate a second video based on the video of the target image file and the first audio, wherein the duration of the video of the target image file is the same as the duration of the first audio, so that the first audio is played while the video of the target image file is played.
[0066] S230: Generate a news video based on the first video and the second video.
[0067] The first video and the second video are spliced together to generate a news video.
[0068] In the embodiment of the present application, when the first file is set to include a target image file, the first video is generated by driving the target virtual character to broadcast the first sub-manuscript, and the first audio is generated by driving the target virtual character to broadcast the second sub-manuscript, and the second video is generated by combining the first audio and the target image file. The first audio is played while the user is watching the video of the target image file generated based on the target image file, thereby improving the user's viewing experience and making the news video generated based on the above-mentioned first video and second video more interesting, for example, improving the dissemination efficiency of the news video.
[0069] In some embodiments, in order to improve the production efficiency of the news video, in response to the user's target operation, before generating the second video based on the target image file and the first audio, the method further includes:
[0070] In the case where the first file includes multiple image files, multiple text description information is determined based on the multiple image files, and the text description information is used to describe the image information recorded in the image files; one image file corresponds to one text description information; based on the news release, the multiple text description information is matched to obtain a matching result; in the case where the matching result includes the target text description information included in the news release, the target image file corresponding to the target text description information is determined.
[0071] In the case where the first file includes multiple image files, the visual model included in NLP can be used to determine the text description information of each image file. For example, when the image file is an image of a puppy running, the visual model can output the text description information of "dog running". The above multiple text description information can be matched with the news release, and when the news release includes target text description information, the target image file corresponding to the target text description information is determined. For example, when the text description information includes "dog running" and "tree", if the news release includes the text of "dog running", it can be determined that the image file corresponding to "dog running" is the target image file.
[0072] The embodiment of the present application determines the text description information corresponding to each image file when the first file includes multiple image files, matches the text description information with the news release, and determines the target image file. This can filter out image files that do not match the text content included in the news release, thereby improving the efficiency of generating news videos.
[0073] In some embodiments, Figure 3 As shown, the first file includes a video file;
[0074] Drive the target virtual character to broadcast news articles and generate audio and video, including:
[0075] S310: Identify shooting information of the video file, where the shooting information includes at least one of a shooting scene, a shooting angle, and a shooting lens motion type.
[0076] When the first file includes a video, the shooting information of the video file can be identified by the above-mentioned NLP visual model, and the video file can be input into the visual model. The visual model can output at least one of the shooting information of the video file, including the shooting scene, shooting angle, and shooting lens movement type. Here, the shooting scene includes long shot, panoramic shot, medium shot, close shot or close-up, the shooting angle includes depression angle, elevation angle, flat angle, front or side angle, and the shooting lens movement type includes push, pull, shake or move.
[0077] S320: In response to a second operation of the user, driving the target virtual character to broadcast a news article and generate audio and video, wherein the second operation is an operation of shooting information of the target virtual character selected by the user.
[0078] The user can input a second operation to set the audio and video shooting information and drive the target virtual character to broadcast the news release.
[0079] The embodiment of the present application determines the shooting information of a video file when the first file includes a video file, and then responds to the user's second operation to set the shooting information of the audio and video, so that the news video generated based on the audio and video and the video file has video aesthetics, thereby improving the user's viewing experience.
[0080] Based on the same inventive concept, an embodiment of the present application also provides a video generating device.
[0081] In some embodiments, Figure 4 As shown, the embodiment of the present application provides a video generating device, including:
[0082] The acquisition module 401 is used to acquire a converged media news file, which includes a text file and a first file. The text file is a file recording text information of the news, and the first file is a file recording image information of the news.
[0083] A generating module 402, for generating a news article based on a text file;
[0084] The generation module 402 is also used to drive the target virtual character to broadcast the news article and generate audio and video;
[0085] The generation module 402 is also used to generate a news video based on the first file and the audio and video.
[0086] In some embodiments, the text file includes news element information and prompt information, and the prompt information includes at least one of the following: title information, annotation information;
[0087] Generate modules, which can be used for:
[0088] Use entity extraction algorithm to extract news element information and prompt information included in text files;
[0089] Generate news releases based on news element information and prompt information.
[0090] In some embodiments, the apparatus further includes a determination module, which may be specifically configured to:
[0091] Classify news articles based on a preset sentiment classification algorithm and determine the target sentiment type of the news articles;
[0092] Based on the correspondence between the preset emotion types and the virtual characters, a target virtual character corresponding to the target emotion type is determined.
[0093] In some embodiments, the first file includes a target image file; the news article includes a first sub-article and a second sub-article; the audio and video include a first video and a first audio;
[0094] Generate modules, which can be used for:
[0095] Driving the target virtual character to broadcast the first sub-article to generate a first video; and driving the target virtual character to broadcast the second sub-article to generate a first audio;
[0096] In response to a first operation of the user, a second video is generated based on the target image file and the first audio, wherein the first operation is an operation input by the user to shoot the target image file to obtain a video;
[0097] Based on the first video and the second video, a news video is generated.
[0098] In some embodiments, the generation module may be specifically used to:
[0099] In the case where the first file includes a plurality of image files, a plurality of text description information is determined based on the plurality of image files, the text description information being used to describe the image information recorded in the image files; one image file corresponds to one text description information;
[0100] Matching the news release with multiple text description information to obtain matching results;
[0101] When the matching result includes that the news article includes the target text description information, a target image file corresponding to the target text description information is determined.
[0102] In some embodiments, the first file comprises a video file;
[0103] Generate modules, which can be used for:
[0104] Identify shooting information of the video file, where the shooting information includes at least one of a shooting scene, a shooting angle, and a shooting lens motion type;
[0105] In response to a second operation of the user, the target virtual character is driven to broadcast a news article and generate audio and video, wherein the second operation is an operation of shooting information of the target virtual character selected by the user.
[0106] The device of the above embodiment is used to implement the corresponding video generation method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.
[0107] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in an application embodiment.
[0108] The electronic device 500 may include a processor 501 and a memory 502 storing computer program instructions.
[0109] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0110] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.
[0111] In certain embodiments, memory 502 includes a read-only memory (ROM). The ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of the above, where appropriate.
[0112] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of the present application.
[0113] The processor 501 implements any one of the video generation methods in the above embodiments by reading and executing computer program instructions stored in the memory 502 .
[0114] In one example, the electronic device may further include a communication interface 503 and a bus 504. Figure 5 The processor 501, the memory 502, and the communication interface 503 are connected via a bus 504 and communicate with each other.
[0115] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.
[0116] Bus 504 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 504 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.
[0117] The electronic device of the above embodiment is used to implement the corresponding video generation method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.
[0118] In addition, in combination with the video generation method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the video generation methods in the above embodiment is implemented.
[0119] In addition, in combination with the video generation method in the above embodiment, the embodiment of the present application can provide a computer program product for implementation. When the computer program product instructions are executed by a processor of an electronic device, any one of the video generation methods in the above embodiment is implemented.
[0120] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.
[0121] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.
[0122] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or devices based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.
[0123] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (device) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.
[0124] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices, modules and units can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application.
Claims
1. A video generation method, characterized in that: include: Acquire a converged media news file, wherein the converged media news file includes a text file and a first file, wherein the text file is a file recording text information of the news, and the first file is a file recording image information of the news; Generate a news release based on the text file; Driving the target virtual character to broadcast the news article and generate audio and video; Generate a news video based on the first file and the audio and video.
2. The video generation method according to claim 1, characterized in that: The text file includes news element information and prompt information, and the prompt information includes at least one of the following: title information and annotation information; The step of generating a news release based on the text file includes: Extracting the news element information and the prompt information included in the text file using an entity extraction algorithm; A news article is generated based on the news element information and the prompt information.
3. The video generation method according to claim 1, characterized in that: Before the driving target virtual character to broadcast the news article and generate audio and video, the method further includes: Classifying the news article based on a preset sentiment classification algorithm to determine the target sentiment type of the news article; Based on the preset correspondence between the emotion type and the virtual character, a target virtual character corresponding to the target emotion type is determined.
4. The video generation method according to claim 1, characterized in that: The first file includes a target image file; the news article includes a first sub-article and a second sub-article; the audio and video include a first video and a first audio; The driving target virtual character to broadcast the news article and generate audio and video includes: Driving the target virtual character to broadcast the first sub-script to generate a first video; and driving the target virtual character to broadcast the second sub-script to generate a first audio; The step of generating a news video based on the first file and the news article includes: In response to a first operation of a user, generating a second video based on the target image file and the first audio, wherein the first operation is an operation input by a user to shoot the target image file to obtain a video; A news video is generated based on the first video and the second video.
5. The video generation method according to claim 4, characterized in that: Before generating the second video based on the target image file and the first audio in response to the user's target operation, the method further includes: In the case where the first file includes a plurality of image files, a plurality of text description information is determined based on the plurality of image files, the text description information being used to describe the image information recorded in the image files; one image file corresponds to one text description information; Based on matching the news release with the multiple text description information, a matching result is obtained; In a case where the matching result includes that the news release includes target text description information, the target image file corresponding to the target text description information is determined.
6. The video generation method according to claim 1, characterized in that: The first file includes a video file; The driving target virtual character to broadcast the news article and generate audio and video includes: Identify shooting information of the video file, where the shooting information includes at least one of a shooting scene, a shooting angle, and a shooting lens motion type; In response to a second operation of the user, the target virtual character is driven to broadcast the news article and generate audio and video, wherein the second operation is an operation of shooting information of the target virtual character selected by the user.
7. A video generating device, characterized in that: include: An acquisition module is used to acquire a converged media news file, wherein the converged media news file includes a text file and a first file, wherein the text file is a file recording text information of the news, and the first file is a file recording image information of the news; A generating module, used for generating a news article based on the text file; The generation module is also used to drive the target virtual character to broadcast the news article and generate audio and video; The generation module is also used to generate a news video based on the first file and the audio and video.
8. An electronic device, characterized in that: The device comprises: a processor, and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the video generation method according to any one of claims 1 to 6.
9. A readable storage medium, characterized in that: The readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the video generation method according to any one of claims 1 to 6 is implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is processed by a processor, the video generation method according to any one of claims 1 to 6 is implemented.
Citation Information
Cited By
Digital anchor virtual image generation method and system based on big data artificial intelligence
CN120070688A
Digital anchor virtual image generation method and system based on big data artificial intelligence
CN120070688B
