Video generation method and device for PowerPoint, storage medium and electronic equipment

Abstract

The invention relates to a video generation method and device for a PowerPoint, a storage medium and electronic equipment. The method comprises the following steps: when a generation instruction is obtained, obtaining generation information of a target presentation file from the generation instruction; generating a target presentation file according to the generation information; obtaining the presentation voice of the target presentation file; and generating a presentation video of the target presentation file according to the target presentation file and the presentation voice. The technical problem of low efficiency of manually operating the presentation manuscript to demonstrate is solved.

Description

Technical Field

[0001] The present application relates to the field of presentations, and in particular to a method, device, storage medium and electronic device for generating a video of a presentation. Background Art

[0002] In the prior art, presentations are required to be used for explanation in many scenarios. However, presentations need to be manually edited, generated, and performed manually, resulting in low demonstration efficiency. Summary of the invention

[0003] The present application provides a method, device, storage medium and electronic device for generating a video of a presentation, so as to solve the technical problem of low efficiency of performing presentations by manually operating the presentation.

[0004] In a first aspect, the present application provides a method for generating a video of a presentation, comprising: when a generation instruction is obtained, obtaining generation information of a target presentation from the above generation instruction; generating the above target presentation according to the above generation information; obtaining a demonstration voice of the above target presentation; and generating a demonstration video of the above target presentation according to the above target presentation and the above demonstration voice.

[0005] In a second aspect, the present application provides a video generation device for a presentation, comprising: a first acquisition module, for acquiring generation information of a target presentation from the generation instruction when a generation instruction is acquired; a first generation module, for generating the target presentation according to the generation information; a second acquisition module, for acquiring a demonstration voice of the target presentation; and a second generation module, for generating a demonstration video of the target presentation according to the target presentation and the demonstration voice.

[0006] In a third aspect, the present application provides an electronic device comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the memory stores a computer program, and the processor is configured to implement any one of the above-mentioned methods for generating a video for a presentation when executing the computer program.

[0007] In a fourth aspect, the present application further provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the video generation method of any of the above-mentioned presentations of the present application.

[0008] The above-mentioned technical scheme provided by the embodiment of the present application has the following advantages over the prior art: the scheme provided by the embodiment of the present application, by obtaining the generation information of the target presentation from the above-mentioned generation instruction when the generation instruction is obtained; generating the above-mentioned target presentation according to the above-mentioned generation information; obtaining the demonstration voice of the above-mentioned target presentation; generating the demonstration video of the above-mentioned target presentation according to the above-mentioned target presentation and the above-mentioned demonstration voice, so that when the generation instruction is obtained, the presentation can be generated according to the generation instruction, and the presentation can be automatically played with dubbing to obtain the demonstration video of the presentation, without the need for the user to perform complicated operations throughout the process, thereby improving the efficiency of obtaining the demonstration video of the presentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0011] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0012] Figure 1 A flowchart of a method for generating a video of a presentation provided in an embodiment of the present application;

[0013] Figure 2 A flowchart of generating a demonstration video of a presentation provided in an embodiment of the present application;

[0014] Figure 3 A flowchart of another method for generating a video of a presentation provided in an embodiment of the present application;

[0015] Figure 4 A flowchart of another method for generating a video of a presentation provided in an embodiment of the present application;

[0016] Figure 5 A flowchart of another method for generating a video of a presentation provided in an embodiment of the present application;

[0017] Figure 6 A flow chart for generating a presentation provided in an embodiment of the present application;

[0018] Figure 7 A schematic diagram of the structure of a video generation device for a presentation provided in an embodiment of the present application;

[0019] Figure 8 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are 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 making creative work are within the scope of protection of this application.

[0021] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0022] In order to solve the technical problem of low efficiency of manually operating presentations in the prior art, the present application provides a method for generating a video of a presentation, which can achieve the effect of improving the efficiency of generating a video of a presentation.

[0023] Figure 1 The flowchart of a method for generating a video of a presentation provided in an embodiment of the present application is as follows. Figure 1 As shown, the video generation method of the above presentation includes:

[0024] S102, when the generation instruction is obtained, obtaining generation information of the target presentation from the generation instruction;

[0025] S104, generating a target presentation according to the generated information;

[0026] S106, obtaining a demonstration voice of a target presentation;

[0027] S108, generating a demonstration video of the target presentation according to the target presentation and the demonstration voice.

[0028] The presentation in this embodiment is a document that is made from a static file into a dynamic file for browsing. The basic component unit is a slide, which can be presented through a presentation tool. There are many tools used for presentation, such as Microsoft PowerPoint, referred to as PPT, or WPS Office, referred to as WPS, etc. Generally, a presentation consists of multiple slides, and the slides are switched by operation to achieve presentation of the presentation.

[0029] When a user wants to present a presentation, he first needs to use PPT or WPS to edit the presentation. After generating the presentation, he needs to present it manually, such as turning pages manually. This process makes the presentation operation of the user's presentation complicated, and it is impossible to present the presentation in a variety of scenarios. For example, if you want to present on a park screen, you need to carry the presentation first, connect to the host of the park screen, present the presentation on the main set, and display the presentation on the park screen. If the method proposed in this application is used, when generating the presentation, it can be generated in an automated manner, and then when presenting, the presentation is also generated as a demonstration video in an automated manner. By playing the demonstration video, the presentation can be demonstrated, thereby improving the efficiency of generating the video of the presentation, and further improving the efficiency of presenting the presentation.

[0030] The generation instruction mentioned in this embodiment can be an instruction initiated by the user, or it can be a generation instruction initiated by the client when receiving the user's instruction after the user initiates the instruction. The generation instruction can be an instruction for generating a target presentation, or it can be an instruction for generating a demonstration video of the target presentation. The generation instruction can carry generation information, and the generation information is information used to determine the content on the slides in the target presentation. The generation information can carry a variety of information, for example, it can carry at least one of the following information: the number of slides in a target presentation to be generated, the theme of the target presentation, the number of target presentations to be generated, the content in the target presentation, and the title.

[0031] Since the generated information may be the user's requirements for the target presentation, such as the subject and outline to be generated, the target presentation may be generated according to the generated information. Specifically, a large language model may be used to determine the detailed content of the target presentation to be generated according to the generated information. After the detailed content is generated, the detailed content is filled into the presentation template to obtain the target presentation.

[0032] After the target presentation is generated, speech may be generated according to the text in the target presentation. The generated speech may include all text contents in the presentation, or the main text contents.

[0033] After the speech of the target presentation is generated, the slides of the target presentation can be displayed and the speech can be played synchronously. This creates the effect of the speech reading the text in the slides. At the same time, the display of the target presentation and the speech reading process are recorded to obtain a demonstration video, which can show the presentation process of the presentation by playing the demonstration video.

[0034] For example, Figure 2 As shown, Figure 2 In the method, a target presentation is generated according to generation information in a generation instruction, and then speech of the text in the target presentation is generated, and a demonstration video is generated using the target presentation and the speech.

[0035] The solution provided by the embodiment of the present application obtains generation information of the target presentation from the generation instruction when the generation instruction is obtained; generates the target presentation according to the generation information; obtains the demonstration voice of the target presentation; and generates a demonstration video of the target presentation according to the target presentation and the demonstration voice. Therefore, when the generation instruction is obtained, the presentation can be generated according to the generation instruction, and the presentation can be automatically played with dubbing to obtain a demonstration video of the presentation. The user does not need to perform complicated operations throughout the process, thereby improving the efficiency of obtaining the demonstration video of the presentation.

[0036] In this embodiment, if Figure 3 As shown, one implementation method of obtaining the demonstration voice of the target presentation is:

[0037] S302, generating a voice file of the target presentation according to the text content in the target presentation, wherein the voice file includes the voice of the text content of the target presentation.

[0038] In this embodiment, for the text content in the target presentation, speech of all text content can be generated. For example, for each page in the target presentation, each page may contain text content, and speech can be generated for each text content in each page. A relationship between speech and the target presentation is established, and one target presentation corresponds to one speech file, and the speech file contains the speech of each text content in each page of the target presentation.

[0039] In another example, speech may be generated for part of the text content in the target presentation. For example, for the titles of the slides of the target presentation, speech may not be generated. Alternatively, speech may be generated for the body of each slide. Alternatively, keywords may be set in the generation instruction, and when generating speech, speech is generated for the text associated with the keywords, and speech is not generated for other text. The purpose of doing this is to not generate speech for irrelevant text, reduce the length of the video, and avoid long-term playback of undisputed content.

[0040] In this embodiment, the speech speed of the generated speech can also be determined according to the amount of content in the target presentation. If the content is large, the speech speed can be slightly faster, and if the content is small, the speech speed can be slightly slower. This is also to make the duration of the presentation video reasonable.

[0041] In this embodiment, if Figure 4 As shown, one implementation method of generating a demonstration video of a target presentation according to the target presentation and the demonstration voice is:

[0042] S402, converting each page of the target presentation into a picture format;

[0043] S404, when displaying each page of the target presentation in the picture format, playing the voice of each page in the voice file;

[0044] S406, recording each page of the target presentation in picture format and the voice of each page to obtain a presentation video.

[0045] In this embodiment, when the target presentation is generated as a demonstration video, the target presentation can be displayed starting from the first page of the target presentation. When the first page is displayed, the voice corresponding to the text content of the first page is played synchronously. After the voice corresponding to the text content of the first page is played, the next page can be displayed, and the voice of the text content of the next page is played at the same time. During the process of displaying the target presentation and playing the voice, the process can be recorded using recording software to obtain a recorded video. The recording software can be started in advance and controlled to start or pause by the method in this embodiment.

[0046] The recording software in this embodiment can record the slides of the displayed target presentation and the voice. Since the voice is generated based on the text content in the slides and is located in the terminal like the slides, it can be directly captured by the recording software. The recording software can stop recording after the voice playback of the text content of the last slide is completed, and the recorded content is saved as a presentation video.

[0047] In this embodiment, all slides and corresponding voices can be recorded to obtain a demonstration video, or each slide and corresponding voice can be recorded to obtain a video corresponding to each slide, and then the videos can be spliced ​​to obtain a demonstration video.

[0048] In this embodiment, one way to convert each page of the target presentation into a picture format is to use a PDF conversion tool to convert each page of the target presentation into a PDF format; and use a picture conversion tool to convert each page of the PDF format of the target presentation into a picture format.

[0049] In this embodiment, when converting the target presentation into a picture format, two conversions can be performed. First, the target presentation is converted into a PDF file. Each page in the PDF file records a slide of the target presentation, thereby converting a target presentation into a PDF file. Then, for the target presentation in PDF format, each page of PDF is converted into a picture. The purpose of this is that if the target presentation is directly saved in a picture format, errors may occur due to the difficulty of conversion, such as the converted picture is not clear enough, or is inconsistent with the original content, etc. By converting the PDF format first and then converting it into a picture format, the difficulty of each conversion can be reduced, thereby improving the accuracy of the converted picture.

[0050] In this embodiment, when displaying each page of the target presentation in picture format, one implementation method for playing the voice of each page in the voice file is to start from the first page of the target presentation, take each page as the current page, and perform the following operations: display the current page of the target presentation; while displaying the current page, play the voice of the current page in the voice file; after a predetermined time after the voice of the current page is played, take the next page of the current page as the new current page, until the last page of the target presentation is displayed.

[0051] In this embodiment, each slide in the target presentation can be displayed, and the voice corresponding to the slide can be played while the slide is displayed. Since the amount of text content in the slide is uncertain, the length of the voice is also uncertain. The above content mentions that the target presentation with more text content can increase the speech speed, but if the speech speed is changed according to the amount of content for each slide, the speech speed of the voice between multiple slides will be inconsistent. Therefore, in order to ensure the consistency of the speech speed of the voice in the demonstration video, a part of the text in the slide can be intercepted to generate the voice. If the amount of text is too much, a part of the text can be omitted according to the degree of association with the preset keywords, and the voice is not generated. For each slide when it is displayed, after the voice is played, a predetermined time can be waited, and then the next slide is displayed, and the voice of the next slide is played at the same time. If the voice of a slide is very long, the waiting time can be reduced after the voice of the page is played, and then the next slide is displayed, thereby saving some time.

[0052] In this embodiment, one implementation method of recording each page of the target presentation in picture format and the voice of each page to obtain a demonstration video is to start recording the target presentation and the corresponding voice when the first page of the target presentation is displayed; when a pause command is received, the recording of the recording software is paused, and the playback of the voice of the target presentation is paused; when a continue command is received, the recording of the recording software is continued, and the playback of the voice of the target presentation is continued.

[0053] In this embodiment, the recording software records the entire process of displaying the slides and playing the corresponding voice. If the recording software is paused, the voice can also be paused. At this time, the recording software has no recorded content. If the recording continues, the voice continues to play. Since the recording software and the voice are paused and recorded synchronously, the content in the recorded demonstration video is not interrupted and is continuous.

[0054] In another example, the recording software is different from the software for displaying the slides and playing the audio. Therefore, if they are controlled synchronously, there may be a time difference between the two, or the audio playback cannot be easily stopped. Therefore, when the recording software is paused, the position of the audio playback can be recorded, but the audio software is not paused. When the recording software resumes playback, the audio of the slide page is replayed from the position of the audio playback.

[0055] In this embodiment, if Figure 5 As shown, one implementation method of generating a target presentation according to the generated information is:

[0056] S502, determining at least the page content, the number of pages and the template used of the target presentation using the large language generation model according to the generation information;

[0057] S504, generating a target presentation according to the page content, the number of pages and the template used.

[0058] In this embodiment, the generation of the target presentation can be assisted by a large language model. The large language model can generate the content in the target presentation according to the content input or set by the user, including but not limited to the theme, number of slide pages, outline, title, subtitle, title description, subtitle description, content description, etc. The content generated by the large language model can be filled into the template selected by the user, or into a template that matches the artistic conception and style of the content generated by the large language model, so as to obtain the target presentation. If the user selects the template, the large language model can also identify the area in the template that can be filled with content, identify the style of the template, etc., and then generate the content. When the target presentation is generated based on the page content, the number of pages and the template used, the generated content replaces the original content in the template.

[0059] In this embodiment, when generating a demonstration video, a target presentation is first generated, and then a demonstration video is generated according to the target presentation. Figure 6 This is a flow chart of generating a target presentation in this embodiment.

[0060] Before generating the target presentation, you can upload the presentation template. The template table SQL can be as follows:

[0061]

[0062]

[0063] When the user initiates a creation instruction or the system initiates a creation instruction, a generation task can be created to generate a presentation. The parameters to be set include: presentation theme, presentation outline, number of presentations generated, presentation template, whether to use a random template, presentation style, presentation target audience, etc. Determine whether the user selects a template. If a template is selected, the configuration information of the selected template is directly read. If random is selected, a template is randomly selected and the configuration information is read. The template configuration information can include the following fields:

[0064] need_main_idea_desc: Whether the presentation title description is required

[0065] sub_idea: presentation outline, used to calculate the number of presentation outlines that need to be generated

[0066] need_sub_idea_desc: Whether the presentation outline needs description information

[0067] every_page_config: Configuration information for each page of presentation. The specific configuration information is as follows:

[0068] "page_type: Page type

[0069] sec_sub_idea: page content subtitle

[0070] need_sec_sub_idea_desc; whether a subtitle description of the page content is required

[0071] sec_sub_idea_content_num: Page content quantity

[0072] need_sec_sub_content_desc: Whether page content description is required

[0073] need_page_desc: Whether a description is needed at the bottom of the page

[0074] need_back_desc: whether a back page description is required"

[0075] If the user only generates a presentation and enters the outline content, the outline entered by the user is used directly, and only the description of the outline needs to be generated. The outline description can be generated using a large language model.

[0076] If no outline is entered, an outline will be generated. The number of outlines needs to be obtained from the template selected by the user or a random template. The outline generation uses a large language model.

[0077] If the user generates presentations in batches, it is necessary to generate an outline based on the presentation topics input by the user and summarize the title of each presentation based on the outline.

[0078] Generate content for each page of the presentation configuration read, first generate chapter page content, chapter page contains chapter title and chapter title description. Generate chapter subtitle for each chapter, generate page content for each chapter subtitle, and finally generate presentation end page content.

[0079] After the presentation content is generated, you can use the python-presentationx package to replace the content. First convert it to PDF format, then convert it to image format. You can use the unoconv tool to save each page of the presentation in PDF format, and then use the pdf2image package to convert PDF to image format.

[0080] When automatically generating speech videos, the Text To Speech (TTS) tool is used to generate a voice file including each page of speech according to the text content of each page, and then the ffmpeg software is used to generate a speech video for each page of the presentation. Finally, ffmpeg is used to merge all the videos to complete the video generation.

[0081] Figure 7 A schematic diagram of the structure of a video generation device for a presentation provided in an embodiment of the present application. Figure 7 As shown, the video generation device of the above presentation includes:

[0082] A first acquisition module 702 is used to acquire generation information of a target presentation from the generation instruction when the generation instruction is acquired;

[0083] A first generating module 704, configured to generate a target presentation according to the generated information;

[0084] The second acquisition module 706 is used to acquire the demonstration voice of the target presentation;

[0085] The second generating module 708 is used to generate a demonstration video of the target presentation according to the target presentation and the demonstration voice.

[0086] The presentation in this embodiment is a document that is made from a static file into a dynamic file for browsing. The basic component unit is a slide, which can be presented through a presentation tool. There are many tools used for presentation, such as Microsoft PowerPoint, referred to as PPT, or WPS Office, referred to as WPS, etc. Generally, a presentation consists of multiple slides, and the slides are switched by operation to achieve presentation of the presentation.

[0087] When a user wants to present a presentation, he first needs to use PPT or WPS to edit the presentation. After generating the presentation, he needs to present it manually, such as turning pages manually. This process makes the presentation operation of the user's presentation complicated, and it is impossible to present the presentation in a variety of scenarios. For example, if you want to present on a park screen, you need to carry the presentation first, connect to the host of the park screen, present the presentation on the main set, and display the presentation on the park screen. If the method proposed in this application is used, when generating the presentation, it can be generated in an automated manner, and then when presenting, the presentation is also generated as a demonstration video in an automated manner. By playing the demonstration video, the presentation can be demonstrated, thereby improving the efficiency of generating the video of the presentation, and further improving the efficiency of presenting the presentation.

[0088] The generation instruction mentioned in this embodiment can be an instruction initiated by the user, or it can be a generation instruction initiated by the client when receiving the user's instruction after the user initiates the instruction. The generation instruction can be an instruction for generating a target presentation, or it can be an instruction for generating a demonstration video of the target presentation. The generation instruction can carry generation information, and the generation information is information used to determine the content on the slides in the target presentation. The generation information can carry a variety of information, for example, it can carry at least one of the following information: the number of slides in a target presentation to be generated, the theme of the target presentation, the number of target presentations to be generated, the content in the target presentation, and the title.

[0089] Since the generated information may be the user's requirements for the target presentation, such as the subject and outline to be generated, the target presentation may be generated according to the generated information. Specifically, a large language model may be used to determine the detailed content of the target presentation to be generated according to the generated information. After the detailed content is generated, the detailed content is filled into the presentation template to obtain the target presentation.

[0090] After the target presentation is generated, speech may be generated according to the text in the target presentation. The generated speech may include all text contents in the presentation, or the main text contents.

[0091] After the speech of the target presentation is generated, the slides of the target presentation can be displayed and the speech can be played synchronously. This creates the effect of the speech reading the text in the slides. At the same time, the display of the target presentation and the speech reading process are recorded to obtain a demonstration video, which can show the presentation process of the presentation by playing the demonstration video.

[0092] For example, Figure 2 As shown, Figure 2 In the method, a target presentation is generated according to generation information in a generation instruction, and then speech of the text in the target presentation is generated, and a demonstration video is generated using the target presentation and the speech.

[0093] The solution provided by the embodiment of the present application obtains generation information of the target presentation from the generation instruction when the generation instruction is obtained; generates the target presentation according to the generation information; obtains the demonstration voice of the target presentation; and generates a demonstration video of the target presentation according to the target presentation and the demonstration voice. Therefore, when the generation instruction is obtained, the presentation can be generated according to the generation instruction, and the presentation can be automatically played with dubbing to obtain a demonstration video of the presentation. The user does not need to perform complicated operations throughout the process, thereby improving the efficiency of obtaining the demonstration video of the presentation.

[0094] For other examples of this embodiment, please refer to the above examples and will not be described in detail here.

[0095] like Figure 8 As shown, an embodiment of the present application provides an electronic device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0096] A memory 113, for storing computer programs;

[0097] In one embodiment of the present application, the processor 111 is used to implement the video generation method of the presentation provided by any one of the aforementioned method embodiments when executing the program stored in the memory 113.

[0098] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a method for generating a video of a presentation as provided in any of the aforementioned method embodiments is implemented.

[0099] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as 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 device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0101] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0102] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for generating a video of a presentation, characterized in that: include: When the generation instruction is obtained, generation information of the target presentation is obtained from the generation instruction; generating the target presentation according to the generation information; Obtaining the demonstration voice of the target presentation; A demonstration video of the target presentation is generated according to the target presentation and the demonstration voice.

2. The method according to claim 1, characterized in that The step of obtaining the demonstration voice of the target presentation includes: A voice file of the target presentation is generated according to the text content in the target presentation, wherein the voice file includes the voice of the text content of the target presentation.

3. The method according to claim 2, characterized in that Generating a demonstration video of the target presentation according to the target presentation and the demonstration voice includes: converting each page of the target presentation into a picture format; When displaying each page of the target presentation in picture format, playing the voice of each page in the voice file; Record each page of the target presentation in picture format and the voice of each page to obtain the presentation video.

4. The method according to claim 3, characterized in that: The step of converting each page of the target presentation into a picture format comprises: Use a PDF conversion tool to convert each page of the target presentation into PDF format; Use the image conversion tool to convert each page of the target presentation's PDF format into image format.

5. The method according to claim 3, characterized in that: When displaying each page of the target presentation in picture format, playing the voice of each page in the voice file includes: Starting from the first page of the target presentation, with each page as the current page, do the following: Displaying the current page of the target presentation; While displaying the current page, playing the voice of the current page in the voice file; After a predetermined time has passed after the voice of the current page is played, the next page of the current page is used as a new current page until the last page of the target presentation is displayed.

6. The method according to claim 5, characterized in that The step of recording each page of the target presentation in picture format and the voice of each page to obtain the presentation video comprises: When the first page of the target presentation begins to be displayed, recording the target presentation and the corresponding voice begins; When receiving the pause instruction, pausing the recording of the recording software and pausing the playing of the voice of the target presentation; When the continue instruction is received, the recording software continues recording while the voice playback of the target presentation continues.

7. The method according to claim 1, characterized in that Generating the target presentation according to the generation information includes: According to the generated information, at least determine the page content, the number of pages and the template used of the target presentation using a large language generation model; The target presentation is generated according to the page content, the number of pages and the template used.

8. The method according to claim 7, characterized in that The generating the target presentation according to the page content, the number of pages and the used template comprises: The page content is used to replace the template content in the used template to obtain the target presentation.

9. A video generation device for presentation, characterized in that: include: A first acquisition module is used to acquire generation information of a target presentation from the generation instruction when a generation instruction is acquired; A first generating module, configured to generate the target presentation according to the generating information; A second acquisition module is used to acquire the demonstration voice of the target presentation; The second generating module is used to generate a demonstration video of the target presentation according to the target presentation and the demonstration voice.

10. An electronic device, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor coupled to the at least one bus; At least one memory connected to the at least one bus, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method for generating a video of a presentation as described in any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium storing computer-executable instructions for executing the method for generating a video of a presentation as described in any one of claims 1 to 8 of the present application.

Images