Powerpoint generation method and device, equipment, storage medium and computer program product

Abstract

The invention discloses a PowerPoint generation method and device, equipment, a storage medium and a computer program product, relates to the technical field of large models, and discloses a PowerPoint generation method, which comprises the following steps: in response to a PowerPoint generation instruction, extracting a content outline from an original text through a large language model; generating a target presentation template through the large language model based on a template rule instruction input by a user; and generating a target PowerPoint according to the content outline and the target PowerPoint template. Through the mode, the content outline is directly extracted based on the presentation file generation instruction and the large language model, so that the template of the presentation file can be automatically generated according to the template generation rule set by the user, and then the presentation file is automatically generated according to the content outline and the generated template; the presentation file corresponding to the text is self-defined and generated based on the user demand, and the office efficiency of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of large model technology, and in particular to a presentation generation method, apparatus, device, storage medium and computer program product. Background Art

[0002] There are already many software and applications on the market that can automatically generate PPT presentations, but these applications can only apply and generate pre-set templates based on the text given by the user, and cannot automatically generate or edit PPT templates based on user needs, resulting in low user office efficiency.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a presentation generation method, device, equipment, storage medium and computer program product, aiming to solve the technical problem that PPT with preset style can only be generated based on text and cannot be customized according to user needs.

[0005] To achieve the above purpose, the present application proposes a presentation generation method, which comprises:

[0006] In response to a presentation generation instruction, extracting a content outline from the original text by a large language model;

[0007] Generate a target presentation template through the large language model based on the template rule instructions input by the user;

[0008] A target presentation is generated according to the content outline and the target presentation template.

[0009] Optionally, in response to the presentation generation instruction, the step of extracting a content outline from the original text by using a large language model comprises:

[0010] When receiving the presentation generation instruction, determining the target file according to the presentation generation instruction;

[0011] Extracting the original text from the target file;

[0012] Extract content outline from raw text through a large language model.

[0013] Optionally, the step of generating a target presentation template through the large language model based on the template rule instruction input by the user comprises:

[0014] Obtaining a template rule instruction input by a user, and determining a template generation rule according to the template rule instruction;

[0015] A target presentation template is generated through a large language model according to the template generation rules.

[0016] Optionally, the step of generating a target presentation template through a large language model according to the template generation rule includes:

[0017] When the template generation rule is a predetermined template generation rule, calling and displaying a plurality of preset templates from a preset database;

[0018] In response to a user's instruction to select a template, determining a target template among the preset templates fed back by the user;

[0019] A target presentation template is generated based on the target template using the large language model.

[0020] Optionally, the step of generating a target presentation template through a large language model according to the template generation rule includes:

[0021] When the template generation rule is an upload template rule, obtaining an uploaded reference presentation;

[0022] extracting a reference template according to the reference presentation;

[0023] A target presentation template is generated based on the reference template by using the large language model.

[0024] Optionally, the step of extracting a reference template according to the reference presentation includes:

[0025] Determining presentation architecture information according to the reference presentation, and extracting a reference template according to the presentation architecture information; and / or,

[0026] The reference presentation is input into the large language model, and a style-mimicking template is generated by the large language model as a reference template.

[0027] Optionally, the step of generating a target presentation template through a large language model according to the template generation rule includes:

[0028] When the template generation rule is a keyword generation rule, extracting and displaying a plurality of candidate keywords from a preset database;

[0029] In response to the keyword selection instruction, determining a target keyword from the candidate keywords;

[0030] Generate a target keyword template according to the target keyword through a large language model;

[0031] A target presentation template is generated by using the target keyword template and the large language model.

[0032] Optionally, the step of generating a target presentation according to the content outline and the target presentation template includes:

[0033] Determining outline content filling information according to the content outline and the target presentation template;

[0034] The content outline is split according to the outline content filling information and filled into the target presentation template to obtain the target presentation.

[0035] Optionally, the step of generating a target presentation according to the content outline and the target presentation template includes:

[0036] Determining document page display sequence information and page content filling sequence information according to the content outline and the target presentation document template;

[0037] Determine the document generation and display order according to the document page display order information and the page content filling order information;

[0038] The target presentation is generated and displayed page by page according to the order in which the documents are generated and displayed.

[0039] Optionally, after the step of generating the target presentation according to the content outline and the target presentation template, the step further includes:

[0040] In response to the template replacement instruction, obtaining the template to be replaced;

[0041] Determining a text replacement scheme for the target presentation according to the template to be replaced;

[0042] The template of the target presentation is replaced with the template to be replaced according to the text replacement scheme.

[0043] Optionally, after the step of generating the target presentation according to the content outline and the target presentation template, the step further includes:

[0044] In response to the template editing instruction, determining template modification information according to the template editing instruction;

[0045] Determining the page to be modified of the target presentation according to the template modification information;

[0046] The template of the page to be modified is modified, and the text of the page to be modified is modified accordingly.

[0047] Optionally, after the step of generating the target presentation according to the content outline and the target presentation template, the step further includes:

[0048] generating a speech text according to the target presentation and the original text;

[0049] Determining the paginated speech text of the target presentation according to the speech text;

[0050] During the target presentation, the paged speech text is displayed in the page corresponding to the target presentation.

[0051] In addition, to achieve the above purpose, the present application also proposes a presentation generating device, the presentation generating device comprising:

[0052] An outline extraction module, for extracting a content outline from the original text by using a large language model in response to a presentation generation instruction;

[0053] A template generation module, used to generate a target presentation template through the large language model based on the template rule instructions input by the user;

[0054] A file generation module is used to generate a target presentation according to the content outline and the target presentation template.

[0055] Optionally, the outline extraction module is further used to determine a target file according to the presentation generation instruction when receiving the presentation generation instruction; extract the original text from the target file; and extract the content outline from the original text through a large language model.

[0056] Optionally, the template generation module is further used to obtain a template rule instruction input by a user, and determine a template generation rule according to the template rule instruction; and generate a target presentation template through a large language model according to the template generation rule.

[0057] Optionally, the template generation module is also used to call and display multiple preset templates from a preset database when the template generation rule is a predetermined template generation rule; determine a target template among the preset templates fed back by the user in response to a user selecting a template instruction; and generate a target presentation template based on the target template through the large language model.

[0058] Optionally, the template generation module is further used to obtain an uploaded reference presentation when the template generation rule is an upload template rule; extract a benchmark template based on the reference presentation; and generate a target presentation template based on the benchmark template through the large language model.

[0059] In addition, to achieve the above-mentioned purpose, the present application also proposes a presentation generation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the presentation generation method described above.

[0060] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the presentation generation method described above are implemented.

[0061] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the presentation generation method described above.

[0062] One or more technical solutions proposed in this application have at least the following technical effects:

[0063] This application extracts the content outline from the original text through a large language model in response to a presentation generation instruction; generates a target presentation template through the large language model based on the template rule instruction input by the user; and generates a target presentation according to the content outline and the target presentation template. In this way, the content outline is directly extracted based on the presentation generation instruction and the large language model, so that the presentation template can be automatically generated according to the template generation rules set by the user, and then the presentation is automatically generated according to the content outline and the generated template, realizing the customized generation of the presentation corresponding to the text based on user needs, and improving the user's office efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0065] In order to more clearly illustrate the embodiments of the present application 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.

[0066] Figure 1 A flowchart of the first embodiment of the method for generating a presentation document of the present application is provided;

[0067] Figure 2 A schematic diagram of the display sequence provided for an embodiment of the method for generating a presentation document of the present application;

[0068] Figure 3 A flowchart diagram of the second embodiment of the method for generating a presentation document of the present application is provided;

[0069] Figure 4 This is a schematic diagram of the module structure of the presentation document generating device according to an embodiment of the present application;

[0070] Figure 5 A schematic diagram of the device structure of the hardware operating environment involved in the presentation generation method in the embodiment of the present application.

[0071] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0072] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0073] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0074] The main solution of the embodiment of the present application is: in response to a presentation generation instruction, extract a content outline from the original text through a large language model; generate a target presentation template through the large language model based on the template rule instructions input by the user; and generate a target presentation according to the content outline and the target presentation template.

[0075] In this embodiment, for the convenience of description, the following description is made by taking the identification computer as the execution subject.

[0076] Due to the existing technology, there are many software and applications that can automatically generate PPT presentations on the market. However, these applications can only apply and generate pre-set templates based on the text given by the user, and cannot automatically generate or edit PPT templates based on user needs, resulting in low user office efficiency.

[0077] The present application provides a solution, through which it is possible to directly extract a content outline based on presentation generation instructions and a large language model, so that a presentation template can be automatically generated according to the template generation rules set by the user, and then the presentation can be automatically generated according to the content outline and the generated template, thereby achieving custom generation of presentations corresponding to text based on user needs and improving the user's office efficiency.

[0078] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a server, etc. The following takes a computer as an example to illustrate this embodiment and the following embodiments.

[0079] Based on this, the present application embodiment provides a method for generating a presentation, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the presentation generation method of the present application.

[0080] In this embodiment, the presentation generation method includes steps S10 to S30:

[0081] Step S10, in response to the presentation generation instruction, extracting a content outline from the original text by using a large language model;

[0082] It should be noted that the presentation generation instruction is continuously received. When the presentation generation instruction is triggered by the user through operation, voice, etc., the pre-trained large language model is directly introduced to understand the content and generate an outline of the original text to obtain a content outline.

[0083] In a feasible implementation, in order to accurately obtain a content outline based on a presentation generation instruction, step S10 includes: upon receiving a presentation generation instruction, determining a target file according to the presentation generation instruction; extracting original text from the target file; and extracting a content outline from the original text through a large language model.

[0084] It should be understood that when a presentation generation instruction is received, the target file is first determined according to the presentation generation instruction. The target text can be any type of file, such as a word document, a notepad file, and the like.

[0085] In the specific implementation, after the target file is determined, the text information of the target file is extracted to obtain the original text, and then the content outline can be extracted from the original text through the large language model. The target file can be a paper, report, academic article, etc. If there is image or video information in the target file, the large language model can be used to understand and summarize the semantics and convert it into text.

[0086] Step S20, generating a target presentation template through the large language model based on the template rule instruction input by the user;

[0087] It should be noted that, based on the template rule instructions input by the user, a presentation template that meets the user's needs is generated based on the large language model. The specific generation methods include but are not limited to direct generation, style imitation, keyword generation, etc.

[0088] Step S30, generating a target presentation according to the content outline and the target presentation template.

[0089] It should be understood that the nesting of text and generation of PPT according to the content outline and the target presentation template can be specifically performed by generating sections and pages one by one in a pre-set order, so that the user can pause and adjust at any time.

[0090] In a feasible implementation, in order to accurately generate a target presentation, step S30 includes: determining outline content filling information according to the content outline and the target presentation template; splitting the content outline according to the outline content filling information and filling it into the target presentation template to obtain the target presentation.

[0091] In the specific implementation, first determine the outline content filling information according to the content outline and the target presentation template, that is, the correspondence between the content just filled into each block of the target presentation template and other information, so that the content outline can be split into texts and filled into the target presentation template to obtain the final target presentation.

[0092] In a feasible implementation, in order to display in sequence when generating a presentation, step S30 includes: determining the document page display sequence information and the page content filling sequence information according to the content outline and the target presentation template; determining the document generation and display sequence according to the document page display sequence information and the page content filling sequence information; generating and displaying the target presentation page by page according to the document generation and display sequence.

[0093] It should be noted that, first, the document page display order information and the page content filling order information are determined according to the content outline and the target presentation template, wherein the document page display order information refers to the display order of each page of the presentation, and the page content filling order information refers to the display order of each module in each separate page, so that the document generation display order can be obtained, and then the presentation generation and composition based on the document generation display order is obtained. The animation played to the user can be obtained, so that a more vivid PPT generation process can be achieved, and the user can pause at any time and adjust and edit the module just generated, so that subsequent presentations can be adjusted accordingly based on the user's adjustments, avoiding the user's modification after the complete generation, which will cause the entire presentation to be redone, thereby improving the generation efficiency.

[0094] It should be understood that if Figure 2 The figure shows a schematic diagram of the presentation generation and display order, in which each page is generated in the order of 1-3, and each module in page 1 is generated in the order of abc, and then the generation animation of a, b, c can be set to special effects such as "fly in" and "flash".

[0095] In a feasible implementation, in order to make timely adjustments when the user needs to replace the template, after step S30, it also includes: in response to the template replacement instruction, obtaining the template to be replaced; determining the text replacement plan of the target presentation based on the template to be replaced; replacing the template of the target presentation with the template to be replaced according to the text replacement plan.

[0096] In a specific implementation, when a template replacement instruction triggered by a user is received, the template to be replaced input by the user is first determined according to the template replacement instruction, and then the text replacement scheme of the target presentation is determined according to the template to be replaced. The template to be replaced can be a template specified by the user, or a template generated again by a large language model with new keywords and styles provided to the user. The text replacement scheme refers to a scheme in which the text in the target presentation is replaced with the module of the template to be replaced.

[0097] In a feasible implementation, in order to make timely modifications when the user adjusts the template, after step S30, it also includes: responding to a template editing instruction, determining template modification information according to the template editing instruction; determining the page to be modified of the target presentation according to the template modification information; performing template modification on the page to be modified, and making corresponding modifications to the text of the page to be modified.

[0098] It should be noted that, upon receiving a template editing instruction triggered by the user, the template modification information input by the user is determined according to the template editing instruction, that is, which modules and parts of the template of the target presentation are modified by the user. After determining the template modification information, the page that needs to be modified is determined as the page to be modified according to the template modification information. Finally, the template of the page to be modified is edited and modified, and corresponding adjustments are made to other affected pages.

[0099] In a feasible implementation manner, in order to automatically generate a speech when the target presentation is displayed to facilitate user presentation, after step S30, it also includes: generating a speech text based on the target presentation and the original text; determining the paginated speech text of the target presentation based on the speech text; and displaying the paginated speech text in the pagination corresponding to the target presentation during the display of the target presentation.

[0100] It should be understood that the entire speech text is first generated based on the target presentation and the original text, and the speech text is the content of the original text refined and corresponds to the text in the target presentation. After obtaining the speech text, the speech text is split to obtain the paged speech text corresponding to each page of the target presentation PPT.

[0101] In a specific implementation, after the paginated speech text is obtained, the paginated speech text is played and adjusted page by page according to the PPT playback progress during the PPT playback process, thereby assisting the user in making a PPT presentation.

[0102] This embodiment provides a presentation generation method, which extracts a content outline from the original text through a large language model in response to a presentation generation instruction; generates a target presentation template through the large language model based on a template rule instruction input by a user; and generates a target presentation according to the content outline and the target presentation template. In this way, the content outline is directly extracted based on the presentation generation instruction and the large language model, so that the presentation template can be automatically generated according to the template generation rules set by the user, and then the presentation is automatically generated according to the content outline and the generated template, so that the presentation corresponding to the text can be customized based on user needs, which improves the user's office efficiency.

[0103] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , step S30 includes steps S301 to S302:

[0104] Step S301, obtaining a template rule instruction input by a user, and determining a template generation rule according to the template rule instruction;

[0105] It should be noted that firstly, the template rule instruction pre-input by the user is obtained, that is, the rule for generating the template is pre-set by the user, so that the method and rule for generating the template can be determined.

[0106] Step S302: Generate a target presentation template through a large language model according to the template generation rule.

[0107] It should be understood that after the template generation rules are determined, the target presentation template is generated according to the generation method defined by the specific rules.

[0108] In a feasible implementation, in order to select a target presentation template when it is determined that a predetermined template is selected for direct generation, step S302 includes: when the template generation rule is a predetermined template generation rule, calling and displaying multiple preset templates from a preset database; in response to a user's template selection instruction, determining a target template among the preset templates fed back by the user; and generating a target presentation template based on the target template through the large language model.

[0109] In a specific implementation, when the template generation rule is a predetermined template generation rule, the rule set by the user is to select and use one from a plurality of preset templates. At this time, multiple preset templates are called from a preset database to be displayed to the user and wait for the user to select. Then, the target template selected by the user is determined based on the user's template selection instruction, so that the target presentation template can be obtained by adjusting and modifying the current text through a large language model.

[0110] In a feasible implementation, in order to generate a template of the same style based on a template uploaded by a user, step S302 includes: when the template generation rule is an uploaded template rule, obtaining an uploaded reference presentation; extracting a benchmark template based on the reference presentation; and generating a target presentation template based on the benchmark template through the large language model.

[0111] It should be noted that, first, when determining that the template generation rule is the upload template rule, the reference presentation uploaded by the user is obtained, and then the template is extracted from the reference presentation, and the redundant text and pictures are deleted to obtain the benchmark template. Finally, the template is adjusted and generated based on the benchmark template through the large language model to obtain the target presentation template.

[0112] In a feasible implementation, in order to accurately extract a benchmark template, the step of extracting a benchmark template based on the reference presentation includes: determining presentation architecture information based on the reference presentation, and extracting a benchmark template based on the presentation architecture information; and / or, inputting the reference presentation into the large language model, and generating a style-mimicking template through the large language model as a benchmark template.

[0113] It should be understood that there are two ways to determine the reference template. The first is to determine the presentation architecture information based on the reference presentation, that is, directly extract the architecture and template of the reference presentation to directly form the reference template. The second is to input the reference presentation into the big language model to determine the template style of the reference presentation, and then generate a template with the same or similar style keywords as the reference template based on the big language model.

[0114] In a feasible implementation, in order to generate a template based on keywords provided by a user, step S302 includes: when the template generation rule is a keyword generation rule, extracting and displaying multiple candidate keywords from a preset database; in response to a keyword selection instruction, determining a target keyword from the candidate keywords; generating a target keyword template through a large language model according to the target keyword; and generating a target presentation template through the target keyword template and the large language model.

[0115] It should be noted that first, all available alternative keywords are extracted from a preset database and displayed to the user, so that the user can select keywords, and the keywords selected by the user are used as target keywords. The target keywords are then input into the large language model, so that a target keyword template matching the target keywords can be generated based on the large language model. Finally, the target keyword template is combined with the large language model to adjust the domain and style of the original text to obtain the final target presentation template.

[0116] This embodiment obtains the template rule instruction input by the user, determines the template generation rule according to the template rule instruction, and generates the target presentation template through the large language model according to the template generation rule. In this way, it is realized that the presentation template is generated according to different template generation rules based on the template rule instruction input by the user, so that the template generation with a wider degree of freedom can be realized that is closer to the user's needs.

[0117] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the presentation generation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0118] This application also provides a presentation generation device, please refer to Figure 4 , the presentation document generating device comprises:

[0119] The outline extraction module 10 is used to extract the content outline from the original text through a large language model in response to the presentation generation instruction.

[0120] The template generation module 20 is used to generate a target presentation template through the large language model based on the template rule instructions input by the user.

[0121] The file generation module 30 is used to generate a target presentation according to the content outline and the target presentation template.

[0122] This embodiment extracts the content outline from the original text through the large language model in response to the presentation generation instruction; generates the target presentation template through the large language model based on the template rule instruction input by the user; and generates the target presentation according to the content outline and the target presentation template. In this way, the content outline is directly extracted based on the presentation generation instruction and the large language model, so that the template of the presentation can be automatically generated according to the template generation rules set by the user, and then the presentation is automatically generated according to the content outline and the generated template, so that the presentation corresponding to the text can be customized based on user needs, which improves the user's office efficiency.

[0123] In one embodiment, the outline extraction module 10 is further used to determine a target file according to the presentation generation instruction when receiving the presentation generation instruction; extract the original text from the target file; and extract the content outline from the original text through a large language model.

[0124] In one embodiment, the template generation module 20 is further used to obtain a template rule instruction input by a user, and determine a template generation rule according to the template rule instruction; and generate a target presentation template through a large language model according to the template generation rule.

[0125] In one embodiment, the template generation module 20 is also used to call and display multiple preset templates from a preset database when the template generation rule is a predetermined template generation rule; determine a target template among the preset templates fed back by the user in response to a template selection instruction by the user; and generate a target presentation template based on the target template through the large language model.

[0126] In one embodiment, the template generation module 20 is further used to obtain an uploaded reference presentation when the template generation rule is an upload template rule; extract a benchmark template based on the reference presentation; and generate a target presentation template based on the benchmark template through the large language model.

[0127] In one embodiment, the template generation module 20 is further used to determine the presentation architecture information based on the reference presentation, and extract a benchmark template based on the presentation architecture information; and / or input the reference presentation into the large language model, and generate a style-mimicking template through the large language model as a benchmark template.

[0128] In one embodiment, the template generation module 20 is further used to extract and display multiple candidate keywords from a preset database when the template generation rule is a keyword generation rule; determine a target keyword from the candidate keywords in response to a keyword selection instruction; generate a target keyword template based on the target keyword through a large language model; and generate a target presentation template through the target keyword template and the large language model.

[0129] In one embodiment, the file generation module 30 is further used to determine outline content filling information based on the content outline and the target presentation template; split the content outline according to the outline content filling information and fill it into the target presentation template to obtain the target presentation.

[0130] In one embodiment, the file generation module 30 is also used to determine the document page display sequence information and the page content filling sequence information according to the content outline and the target presentation template; determine the document generation and display sequence according to the document page display sequence information and the page content filling sequence information; and generate and display the target presentation page by page according to the document generation and display sequence.

[0131] In one embodiment, the file generation module 30 is further used to obtain the template to be replaced in response to a template replacement instruction; determine a text replacement scheme for the target presentation based on the template to be replaced; and replace the template of the target presentation with the template to be replaced based on the text replacement scheme.

[0132] In one embodiment, the file generation module 30 is also used to respond to a template editing instruction, determine template modification information according to the template editing instruction; determine the page to be modified of the target presentation according to the template modification information; perform template modification on the page to be modified, and make corresponding modifications to the text of the page to be modified.

[0133] In one embodiment, the file generation module 30 is further used to generate a speech text based on the target presentation and the original text; determine the paginated speech text of the target presentation based on the speech text; and display the paginated speech text in the pagination corresponding to the target presentation during the display of the target presentation.

[0134] The presentation generation device provided by the present application adopts the presentation generation method in the above embodiment, which can solve the technical problem that a PPT with a preset style can only be generated based on text and cannot be customized according to user needs. Compared with the prior art, the beneficial effects of the presentation generation device provided by the present application are the same as the beneficial effects of the presentation generation method provided by the above embodiment, and other technical features in the presentation generation device are the same as the features disclosed in the above embodiment method, which will not be described in detail here.

[0135] The present application provides a presentation generating device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the presentation generating method in the above-mentioned embodiment one.

[0136] Reference below Figure 5 , which shows a schematic diagram of the structure of a presentation generating device suitable for implementing the embodiment of the present application. The presentation generating device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The presentation generating device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0137] like Figure 5As shown, the presentation generating device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the presentation generating device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the presentation generation device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a presentation generation device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0138] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0139] The presentation generation device provided by the present application adopts the presentation generation method in the above embodiment, which can solve the technical problem that a PPT with a preset style can only be generated based on text and cannot be customized according to user needs. Compared with the prior art, the beneficial effects of the presentation generation device provided by the present application are the same as the beneficial effects of the presentation generation method provided by the above embodiment, and other technical features in the presentation generation device are the same as the features disclosed in the method of the previous embodiment, which will not be described in detail here.

[0140] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0141] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0142] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the presentation generation method in the above-mentioned embodiment.

[0143] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0144] The computer-readable storage medium may be included in the presentation generating device; or may exist independently without being assembled into the presentation generating device.

[0145] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the presentation generation device, the presentation generation device: responds to the presentation generation instruction, extracts the content outline from the original text through the large language model; generates the target presentation template through the large language model based on the template rule instruction input by the user; and generates the target presentation according to the content outline and the target presentation template.

[0146] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0147] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0148] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0149] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned presentation generation method, and can solve the technical problem that a PPT with a preset style can only be generated based on text and cannot be customized according to user needs. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the presentation generation method provided in the above-mentioned embodiment, and will not be described in detail here.

[0150] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned presentation generation method when executed by a processor.

[0151] The computer program product provided by the present application can solve the technical problem that a PPT with a preset style can only be generated based on text and cannot be customized according to user needs. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the presentation generation method provided in the above embodiment, and will not be described in detail here.

[0152] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

[0153] The present invention discloses A1. a method for generating a presentation, the method comprising:

[0154] In response to a presentation generation instruction, extracting a content outline from the original text by a large language model;

[0155] Generate a target presentation template through the large language model based on the template rule instructions input by the user;

[0156] A target presentation is generated according to the content outline and the target presentation template.

[0157] A2. As described in A1, the step of extracting the content outline from the original text by using a large language model in response to the presentation generation instruction comprises:

[0158] When receiving the presentation generation instruction, determining the target file according to the presentation generation instruction;

[0159] Extracting the original text from the target file;

[0160] Extract content outline from raw text through a large language model.

[0161] A3. As described in the method of A1, the step of generating a target presentation template through the large language model based on the template rule instruction input by the user comprises:

[0162] Obtaining a template rule instruction input by a user, and determining a template generation rule according to the template rule instruction;

[0163] A target presentation template is generated through a large language model according to the template generation rules.

[0164] A4. The method as described in A3, wherein the step of generating a target presentation template through a large language model according to the template generation rule comprises:

[0165] When the template generation rule is a predetermined template generation rule, calling and displaying a plurality of preset templates from a preset database;

[0166] In response to a user's instruction to select a template, determining a target template among the preset templates fed back by the user;

[0167] A target presentation template is generated based on the target template using the large language model.

[0168] A5. As described in A3, the step of generating a target presentation template through a large language model according to the template generation rule comprises:

[0169] When the template generation rule is an upload template rule, obtaining an uploaded reference presentation;

[0170] extracting a reference template according to the reference presentation;

[0171] A target presentation template is generated based on the reference template by using the large language model.

[0172] A6. As described in A5, the step of extracting a reference template based on the reference presentation comprises:

[0173] Determining presentation architecture information according to the reference presentation, and extracting a reference template according to the presentation architecture information; and / or,

[0174] The reference presentation is input into the large language model, and a style-mimicking template is generated by the large language model as a reference template.

[0175] A7. As described in A3, the step of generating a target presentation template through a large language model according to the template generation rule comprises:

[0176] When the template generation rule is a keyword generation rule, extracting and displaying a plurality of candidate keywords from a preset database;

[0177] In response to the keyword selection instruction, determining a target keyword from the candidate keywords;

[0178] Generate a target keyword template according to the target keyword through a large language model;

[0179] A target presentation template is generated by using the target keyword template and the large language model.

[0180] A8. As described in A1, the step of generating a target presentation according to the content outline and the target presentation template comprises:

[0181] Determining outline content filling information according to the content outline and the target presentation template;

[0182] The content outline is split according to the outline content filling information and filled into the target presentation template to obtain the target presentation.

[0183] A9. As described in A8, the step of generating a target presentation according to the content outline and the target presentation template comprises:

[0184] Determining document page display sequence information and page content filling sequence information according to the content outline and the target presentation document template;

[0185] Determine the document generation and display order according to the document page display order information and the page content filling order information;

[0186] The target presentation is generated and displayed page by page according to the order in which the documents are generated and displayed.

[0187] A10. The method as described in A1, wherein the step of generating a target presentation according to the content outline and the target presentation template further comprises:

[0188] In response to the template replacement instruction, obtaining the template to be replaced;

[0189] Determining a text replacement scheme for the target presentation according to the template to be replaced;

[0190] The template of the target presentation is replaced with the template to be replaced according to the text replacement scheme.

[0191] A11. The method as described in A1, wherein the step of generating a target presentation according to the content outline and the target presentation template further comprises:

[0192] In response to the template editing instruction, determining template modification information according to the template editing instruction;

[0193] Determining the page to be modified of the target presentation according to the template modification information;

[0194] The template of the page to be modified is modified, and the text of the page to be modified is modified accordingly.

[0195] A12. The method as described in any one of A1-A11, after the step of generating the target presentation according to the content outline and the target presentation template, further comprises:

[0196] generating a speech text according to the target presentation and the original text;

[0197] Determining the paginated speech text of the target presentation according to the speech text;

[0198] During the display process of the target presentation, the paged speech text is displayed in the page corresponding to the target presentation.

[0199] The present invention also discloses B13. a presentation manuscript generating device, the device comprising:

[0200] An outline extraction module, for extracting a content outline from the original text by using a large language model in response to a presentation generation instruction;

[0201] A template generation module, used to generate a target presentation template through the large language model based on the template rule instructions input by the user;

[0202] A file generation module is used to generate a target presentation according to the content outline and the target presentation template.

[0203] B14. As described in the method of B13, the outline extraction module is also used to determine the target file according to the presentation generation instruction when receiving the presentation generation instruction; extract the original text from the target file; and extract the content outline from the original text through a large language model.

[0204] B15. As described in B13, the template generation module is also used to obtain the template rule instructions input by the user, and determine the template generation rules according to the template rule instructions; generate the target presentation template through the large language model according to the template generation rules.

[0205] B16. As described in the method of B15, the template generation module is also used to call and display multiple preset templates from a preset database when the template generation rule is a predetermined template generation rule; determine a target template among the preset templates fed back by the user in response to a template selection instruction by the user; and generate a target presentation template based on the target template through the large language model.

[0206] B17. As described in the method of B15, the template generation module is also used to obtain an uploaded reference presentation when the template generation rule is an uploaded template rule; extract a benchmark template based on the reference presentation; and generate a target presentation template based on the benchmark template through the large language model.

[0207] The present invention also discloses C18. a presentation generating device, the device comprising: a memory, a processor and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the presentation generating method as described above.

[0208] The present invention also discloses D19. a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the presentation generation method as described above are implemented.

[0209] The present invention also discloses E20. a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the presentation generation method as described above are implemented.

Claims

1. A method for generating a presentation, characterized in that: The method includes: In response to a presentation generation instruction, extracting a content outline from the original text by a large language model; Generate a target presentation template through the large language model based on the template rule instructions input by the user; A target presentation is generated according to the content outline and the target presentation template.

2. The method according to claim 1, characterized in that The step of extracting a content outline from the original text by using a large language model in response to the presentation generation instruction includes: When receiving the presentation generation instruction, determining the target file according to the presentation generation instruction; Extracting the original text from the target file; Extract content outline from raw text through a large language model.

3. The method according to claim 1, characterized in that The step of generating a target presentation template through the large language model based on the template rule instruction input by the user comprises: Obtaining a template rule instruction input by a user, and determining a template generation rule according to the template rule instruction; A target presentation template is generated through a large language model according to the template generation rules.

4. The method according to claim 3, characterized in that The step of generating a target presentation template through a large language model according to the template generation rule comprises: When the template generation rule is a predetermined template generation rule, calling and displaying a plurality of preset templates from a preset database; In response to a user's instruction to select a template, determining a target template among the preset templates fed back by the user; A target presentation template is generated based on the target template using the large language model.

5. The method according to claim 3, characterized in that The step of generating a target presentation template through a large language model according to the template generation rule comprises: When the template generation rule is an upload template rule, obtaining an uploaded reference presentation; extracting a reference template according to the reference presentation; A target presentation template is generated based on the reference template by using the large language model.

6. The method according to claim 5, characterized in that The step of extracting a reference template according to the reference presentation comprises: Determining presentation architecture information according to the reference presentation, and extracting a reference template according to the presentation architecture information; and / or, The reference presentation is input into the large language model, and a style-mimicking template is generated by the large language model as a reference template.

7. A presentation document generating device, characterized in that: The device comprises: An outline extraction module, for extracting a content outline from the original text by using a large language model in response to a presentation generation instruction; A template generation module, used to generate a target presentation template through the large language model based on the template rule instructions input by the user; A file generation module is used to generate a target presentation according to the content outline and the target presentation template.

8. A presentation document generating device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the presentation generation method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the presentation generation method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the presentation generation method according to any one of claims 1 to 6 are implemented.

Images