Method and device for generating a presentation, electronic device and storage medium

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for generating presentations, relating to the field of artificial intelligence, specifically to NLP, large model, LLM, and deep learning technologies. The specific implementation involves: acquiring input information associated with the presentation to be generated; displaying multiple presentation templates and, in response to detecting a template selection operation, determining a target template from the multiple templates; displaying a presentation outline based on the input information; and displaying the presentation based on the presentation outline and the target template.

Description

Technical Field

[0001] This disclosure relates to the field of AI (Artificial Intelligence), specifically to the technical fields of NLP (Natural Language Processing), large models, LLM (Large Language Model), and deep learning, and particularly to methods, devices, electronic devices, and storage media for generating presentations. Background Technology

[0002] With the continuous promotion of office software, PPT and similar presentations can be applied to many fields. For example, in the education field, they can improve teaching efficiency and enhance classroom interaction; in the training field, they can visually assist trainees in quickly understanding; in the corporate publicity field, they can enhance brand image and intuitively and accurately convey corporate information, product advantages, and market positioning; in the management consulting field, they can help clients clearly understand the work results of the consulting team and ensure that both the consulting team and the client have a consensus on the understanding of the problem and the solution, and so on, to name just a few. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for generating presentations.

[0004] According to one aspect of this disclosure, a method for generating a presentation is provided, comprising:

[0005] Retrieve the input information associated with the presentation to be generated;

[0006] Display multiple presentation templates and, in response to detecting a template selection operation, determine the target template from the multiple presentation templates;

[0007] Based on the input information, display the presentation outline;

[0008] Present the presentation according to the presentation outline and the target template.

[0009] According to another aspect of this disclosure, a presentation generation apparatus is provided, comprising:

[0010] The first acquisition module is used to acquire input information associated with the presentation to be generated;

[0011] The first determining module is used to display multiple presentation templates and, in response to detecting a template selection operation, determine a target template from the multiple presentation templates.

[0012] The first display module is used to display the presentation outline based on the input information;

[0013] The second display module is used to display the presentation based on the presentation outline and the target template.

[0014] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the presentation generation method proposed in the foregoing aspect of this disclosure.

[0018] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided for computer instructions used to cause the computer to execute the presentation generation method proposed in the foregoing aspect of this disclosure.

[0019] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the presentation generation method proposed in the above aspect of this disclosure.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0021] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0022] Figure 1 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment 1 of this disclosure;

[0023] Figure 2 A schematic diagram of the client interface provided in this embodiment of the disclosure. Figure 1 ;

[0024] Figure 3 This is a flowchart illustrating the method for generating a presentation document according to Embodiment 2 of this disclosure;

[0025] Figure 4 A schematic diagram of the client interface provided in this embodiment of the disclosure. Figure 2 ;

[0026] Figure 5 A schematic diagram of the client interface provided in this embodiment of the disclosure. Figure 3 ;

[0027] Figure 6 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment 3 of this disclosure;

[0028] Figure 7 A schematic diagram of the client interface provided in this embodiment of the disclosure. Figure 4 ;

[0029] Figure 8 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment 4 of this disclosure;

[0030] Figure 9 This is a schematic diagram of the presentation outline provided for an embodiment of this disclosure;

[0031] Figure 10 This is a flowchart illustrating the method for generating a presentation document according to Embodiment 5 of this disclosure;

[0032] Figure 11 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment Six of this disclosure;

[0033] Figure 12 A schematic diagram of the client interface provided in this embodiment of the disclosure. Figure 5 ;

[0034] Figure 13 These are schematic diagrams illustrating the implementation principles of various embodiments of this disclosure;

[0035] Figure 14 This is a schematic diagram illustrating the generation principle of the presentation document provided in the embodiments of this disclosure;

[0036] Figure 15 This is a schematic diagram of the structure of the presentation document generation apparatus provided in Embodiment 7 of this disclosure;

[0037] Figure 16 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0038] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0039] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for generating presentation documents according to embodiments of the present disclosure. Before detailing the embodiments of the present disclosure, commonly used technical terms will be introduced for ease of understanding:

[0040] Large models are machine learning models with a massive number of parameters and complex computational structures, typically built from deep neural networks and possessing billions or even hundreds of billions of parameters. The purpose of large models is to improve their expressive power and predictive performance, enabling them to handle more complex tasks and data. Large models have wide applications in various fields, including natural language processing, computer vision, speech recognition, and recommender systems.

[0041] LLM, a type of deep learning-based natural language processing model, is characterized by its large number of model parameters and complex neural network structure. It possesses powerful language understanding, context awareness, and language generation capabilities, and can automatically learn useful feature representations from input data to generate relevant text.

[0042] Figure 1 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment 1 of this disclosure.

[0043] The presentation document generation method of this disclosure can be applied to a client. Here, a client refers to a software program or similar application running on an electronic device that provides services to the user.

[0044] Among them, electronic devices can be any device with computing capabilities, such as personal computers, mobile terminals, etc. Mobile terminals can be hardware devices with various operating systems, touch screens and / or displays, such as mobile phones, tablets, personal digital assistants, wearable devices, etc.

[0045] like Figure 1 As shown, the method for generating this presentation may include the following steps S101 to S104:

[0046] Step S101: Obtain the input information associated with the presentation to be generated.

[0047] The presentations to be generated include, but are not limited to: PPT (PowerPoint) and PPT-like presentations.

[0048] In any embodiment of this disclosure, the input information associated with the presentation to be generated can be user input, or it can be obtained by parsing the content of a document uploaded by the user, or it can be generated based on related words (including but not limited to associated words and preset words) clicked by the user, etc. This disclosure does not limit it in this way.

[0049] Among them, suggested keywords, also known as auto-suggested keywords or search dropdown keywords, are determined based on the user's historical search behavior and popular search trends. Historical search behavior includes, but is not limited to, the keywords searched, the search time, and the search frequency; popular search trends can be triggered by various factors such as current events, social events, and popular culture.

[0050] Preset words are words or phrases that are pre-set based on factors such as user search behavior, seasonal changes, and trending events.

[0051] The input methods for information may include, but are not limited to, touch input (such as swiping, clicking, etc.), keyboard input, and voice input.

[0052] Step S102: Display multiple presentation templates and, in response to detecting a template selection operation, determine the target template from the multiple presentation templates.

[0053] In this embodiment of the disclosure, multiple presentation templates can be recommended or displayed to the user in advance based on user preferences. The user can then manually select a target template from the multiple presentation templates displayed on the client side according to their needs. At this time, upon detecting the template selection operation triggered by the user, the client can respond to the template selection operation and determine the target template required by the user from the multiple displayed presentation templates.

[0054] As an example, the client can display multiple presentation templates as follows: Figure 2 As shown, users can click Figure 2 Choose a presentation template from the available templates as the target template.

[0055] Step S103: Display the presentation outline based on the input information.

[0056] In this embodiment of the disclosure, the client can display a presentation outline based on the input information. For example, the client can process the input information by calling a large model (or LLM) to obtain the presentation outline output by the large model and then display the presentation outline.

[0057] Step S104: Present the presentation according to the presentation outline and target template.

[0058] In this embodiment of the disclosure, the client can display the presentation based on the presentation outline and the target template.

[0059] As an example, the client can send a presentation outline and a target template to the server. The server then generates the presentation text corresponding to each node in the presentation outline. For instance, the server can use a large model to generate the presentation text corresponding to each node in the presentation outline. Afterward, the server can use each node and its corresponding presentation text to populate the target template, obtain the presentation, and send the presentation to the client. Accordingly, after receiving the presentation sent by the server, the client can display the presentation.

[0060] The presentation generation method disclosed in this embodiment can automatically generate a presentation outline based on user-provided input information, and then generate the final presentation based on the presentation outline and the presentation template selected by the user. This not only improves the efficiency of presentation generation but also meets the personalized presentation generation needs of different users, thus improving the user experience. Furthermore, by understanding user preferences in advance and recommending or displaying multiple presentation templates based on those preferences, the user can select a target template of interest from the recommended or displayed templates before generating the presentation outline. After the presentation outline is generated, the presentation is generated based on the user's pre-selected target template and the presentation outline. This not only simplifies the user's operation but also reduces the user's waiting time for the presentation, further improving the user experience.

[0061] It should be noted that the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution disclosed herein are all carried out with the consent of the user, and all comply with the provisions of relevant laws and regulations, and do not violate public order and good morals.

[0062] To clearly illustrate how the client determines the target template required by the user from multiple presentation templates in any embodiment of this disclosure, this disclosure also proposes a method for generating presentations.

[0063] Figure 3 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment 2 of this disclosure.

[0064] like Figure 3 As shown, the method for generating this presentation may include the following steps S301 to S306:

[0065] Step S301: Obtain the input information associated with the presentation to be generated.

[0066] The explanation of step S301 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0067] In any embodiment of this disclosure, when the client detects a document upload operation triggered by the user, it can respond to the document upload operation by obtaining the target document uploaded by the user, parsing the content of the target document to obtain the document content, and determining the input information associated with the presentation to be generated based on the document content.

[0068] As an example, the client's display interface can be as follows: Figure 4 As shown, this display interface can show a theme input control ( Figure 4 The control is referred to as "Input Topic" (41) and the document upload control ( Figure 4 The control, referred to as "Upload Document" (42), allows users to upload documents by clicking it. Figure 4 The “Upload Document” control 42 in the middle is used to trigger the document upload operation and upload the target document. Thus, in this disclosure, the document content in the target document can be used as input information associated with the presentation to be generated.

[0069] In any embodiment of this disclosure, when the client detects a topic input operation triggered by the user, it can respond to the topic input operation, obtain the document topic associated with the presentation to be generated by the user, and determine the input information associated with the presentation to be generated based on the document topic.

[0070] As an example, users can click Figure 4 The "Input Topic" control 41 in the middle is used to trigger the topic input operation, and in Figure 4 The document topic is entered in the input box shown in the middle area 43, so that the client can determine the input information associated with the presentation to be generated based on the document topic.

[0071] In one example, the client can directly use the document topic as input information associated with the presentation to be generated.

[0072] In another example, the client can indirectly determine the input information associated with the presentation to be generated based on the document's theme.

[0073] For example, the client's display interface may also show: guiding text; wherein, the guiding text is used to guide the user to input the desired document topic, for example, the guiding text may be as follows: Figure 4 In the input box shown in area 43, area 44 shows the message "Help me write a PPT, the topic is:". In this disclosure, the client can generate input information associated with the presentation to be generated based on the document topic and the guiding text. For example, the client can concatenate the guiding text with the document topic to obtain input information associated with the presentation to be generated.

[0074] For example, the client's display interface can also show background text, which can be displayed in the input box to prompt the user to enter the desired topic. For instance, the background text could be like this: Figure 4 The input box shown in area 43 reads "Please enter the theme you want to create".

[0075] This allows users to intuitively understand how to input the required document topic, improving the user experience. Furthermore, by requiring only the user to input the document topic, without needing to manually enter guiding text containing the presentation's intent, the user's input is reduced, further enhancing the user experience.

[0076] In any embodiment of this disclosure, when the client detects a text input operation triggered by the user, it can respond to the text input operation by obtaining the input information associated with the presentation document to be generated by the user.

[0077] As an example, the client's display interface can be as follows: Figure 5 As shown, users can directly enter the input information associated with the presentation document to be generated in the input box shown in area 51.

[0078] In any embodiment of this disclosure, when the client detects a selection operation triggered by the user, it can respond to the selection operation by selecting a target word associated with the presentation document to be generated from at least one candidate word displayed, and generate input information associated with the presentation document to be generated based on the target word.

[0079] The candidate words include related words and / or preset words. The related words are determined based on historical search behavior and popular search trends.

[0080] As an example, target words can be directly used as input information associated with the presentation to be generated.

[0081] As another example, the guiding text can be concatenated with the target words to obtain the input information associated with the presentation to be generated.

[0082] In summary, different methods can be used to obtain input information associated with the presentation document to be generated, which can improve the flexibility and applicability of this method.

[0083] Step S302: Display multiple candidate template themes; among them, different candidate template themes have different template styles.

[0084] In any embodiment of this disclosure, in addition to different template styles, different candidate template themes may also include at least one of the following differences: different template background colors; different template fonts; different template font colors; different template transparency; different title backgrounds; different icons for special fonts; different background images, etc.

[0085] This can enhance the richness and diversity of presentation templates, improve their visual appeal and attractiveness, and thus meet the needs of generating presentations for different occasions and themes.

[0086] In any embodiment of this disclosure, the candidate template theme may be a pre-configured template theme.

[0087] In any embodiment of this disclosure, the candidate template theme may also be: a template theme selected or recommended from pre-configured template themes.

[0088] As an example, the candidate template topic can be determined by the server using steps A through C, and then sent to the client:

[0089] Step A: Obtain user preference information and historical behavior data associated with the client.

[0090] User preference information refers to subjective information such as personal preferences, interests, and needs that users exhibit while using the client.

[0091] Historical behavioral data refers to objective records generated by users during their historical use of the client, including various behavioral data such as browsing, clicking, purchasing, and commenting.

[0092] Step B: Obtain the popularity scores of multiple template themes.

[0093] For example, the popularity score for each template theme reflects the level of attention (or popularity, trend) of that template theme at the current point in time. This popularity score can be measured by various metrics, such as the number of times the template theme is used (or clicked), page views, likes, comments, and shares.

[0094] Step C: Based on the popularity scores of multiple template themes, user preference information, and historical behavior data, determine candidate template themes from multiple template themes.

[0095] For example, the server can use a recommendation algorithm to determine the template topics that the client is interested in and that have a relatively high popularity value from multiple template topics based on the popularity values ​​of multiple template topics, user preference information, and historical behavior data. These are referred to as candidate template topics in this disclosure.

[0096] In summary, this technology can recommend personalized candidate template themes that users are interested in, thereby improving the user experience.

[0097] Step S303: In response to detecting the theme selection operation, determine the target template theme from multiple candidate template themes and display at least one presentation template under the target template theme.

[0098] In this embodiment of the disclosure, the user can manually select the desired target template theme from multiple candidate template themes displayed on the client according to their own needs. At this time, when the client detects the theme selection operation triggered by the user, it can respond to the theme selection operation, determine the target template theme required by the user from the multiple candidate template themes displayed, and display at least one presentation template under the target template theme.

[0099] Step S304: In response to detecting a template selection operation, determine the target template from at least one presentation template under the target template theme.

[0100] In this embodiment of the disclosure, a user can manually select a desired target template from at least one presentation template under a target template theme displayed on the client, according to their own needs. In this case, upon detecting the template selection operation triggered by the user, the client can respond to the template selection operation by determining the desired target template from at least one presentation template under the target template theme.

[0101] As an example, the target template selected by the user can be as follows: Figure 5 As shown in region 52.

[0102] Step S305: Display the presentation outline based on the input information.

[0103] Step S306: Present the presentation according to the presentation outline and target template.

[0104] The explanation of steps S305 to S306 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0105] The presentation generation method of this disclosure recommends multiple candidate template themes to the client through the server. The client only displays each presentation template under the candidate template themes. This not only simplifies user operation and reduces the time it takes for users to select a target template, but also meets the personalized template selection needs of different users.

[0106] To clearly illustrate how the presentation outline is displayed based on input information in the above embodiments, this disclosure also proposes a method for generating a presentation.

[0107] Figure 6 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment 3 of this disclosure.

[0108] like Figure 6 As shown, the method for generating this presentation may include the following steps S601 to S607:

[0109] Step S601: Obtain the input information associated with the presentation to be generated.

[0110] Step S602: Display multiple presentation templates and, in response to detecting a template selection operation, determine the target template from the multiple presentation templates.

[0111] The explanation of steps S601 to S602 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0112] Step S603: Obtain the first prompt template; wherein, the first prompt template is used to prompt the large model to perform the outline generation task.

[0113] The first prompt template is a pre-set or configured prompt template used to instruct the large model (or large language model) to perform the outline generation task.

[0114] It should be understood that the first prompt template can also be maintained and dynamically updated according to actual application needs, and this disclosure does not limit this.

[0115] Step S604: Generate the first prompt message based on the first prompt template and the input information.

[0116] In this embodiment of the disclosure, input information can be used to fill in the first prompt template to obtain the first prompt information.

[0117] Step S605: Process the first prompt information by calling the large model to obtain the initial outline text output by the large model.

[0118] Large models can be deployed on the backend (i.e., the server).

[0119] In this embodiment of the disclosure, the client can perform NLP processing on the first prompt information by calling the large model to obtain the initial outline text output by the large model.

[0120] Step S606: Format the initial outline text to obtain a presentation outline with the set format, and display the presentation outline.

[0121] It should be noted that the initial outline text output by the large model is in plain text format, while the structure of the presentation outline needs to be a tree structure, that is, the presentation outline needs to include multi-level directory outlines. Therefore, in order to ensure that the generated outline can meet the actual application requirements, in this disclosure, the initial outline text can be formatted to obtain a presentation outline with a set format, and the presentation outline can be displayed.

[0122] As an example, let's take a Markdown (or Markdown-it) format with a tree diagram as an example. You can use Markdown-it technology to format the initial outline text to get a Markdown-it formatted presentation outline.

[0123] It should be noted that steps S603 to S606 can also be executed by the server. This embodiment only shows that they are executed by the client.

[0124] As an example, the client's display interface can be as follows: Figure 7 As shown, the presentation outline automatically generated by the algorithm can be as follows: Figure 7 As shown in region 71.

[0125] Step S607: Present the presentation according to the presentation outline and target template.

[0126] The explanation of step S607 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0127] The presentation generation method of this disclosure includes a first prompt message that can serve as prior information or task information, indicating the task information to be performed by the large model, thereby improving the prediction accuracy of the large model. Furthermore, considering that the initial outline text output by the large model is in plain text format, while the presentation outline structure needs to be a tree structure, this disclosure performs format processing on the initial outline text to obtain a presentation outline with a set format, which can improve the standardization of the generated presentation outline and ensure that the generated presentation outline meets the actual application requirements.

[0128] To clearly illustrate how a presentation is displayed based on a presentation outline and a target template in any embodiment of this disclosure, this disclosure also proposes a method for generating a presentation.

[0129] Figure 8 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment 4 of this disclosure.

[0130] like Figure 8 As shown, the method for generating this presentation may include the following steps S801 to S805:

[0131] Step S801: Obtain the input information associated with the presentation to be generated.

[0132] Step S802: Display multiple presentation templates and, in response to detecting a template selection operation, determine the target template from the multiple presentation templates.

[0133] Step S803: Display the presentation outline based on the input information; wherein the presentation outline is a tree structure.

[0134] The explanation of steps S801 to S803 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0135] Step S804: In response to detecting an outline modification operation, perform at least one of the following update operations on the presentation outline: update the position of at least one node in the presentation outline, update the content of at least one node in the presentation outline, delete at least one node in the presentation outline, or add at least one node in the presentation outline.

[0136] It should be noted that the presentation outline automatically generated by the algorithm may contain some aspects that users are not entirely satisfied with. Therefore, after the presentation outline is automatically generated, it can be displayed to allow users to modify or edit it. For example, users can modify or edit the presentation outline by clicking, dragging, or other methods.

[0137] As one possible implementation, when the client detects a user-triggered outline modification, it can perform at least one of the following update operations on the presentation outline:

[0138] The first step is to update the position of at least one node in the presentation outline. For example, users can adjust the node position by dragging and dropping.

[0139] The second step is to update the content of at least one node in the presentation outline.

[0140] Third, delete at least one node from the presentation outline.

[0141] Fourth, add at least one new node to the presentation outline.

[0142] As an example, an algorithm-generated presentation outline can be as follows: Figure 9 As shown, users can edit the content of each node in the presentation outline, adjust the node position, etc. Users can click... Figure 9 The "-" icon shown in area 91 can be used to reclaim the child nodes under a given node. Furthermore, users can also click... Figure 9 Use the "+" icon shown in area 92 to expand the child nodes under a given node.

[0143] Step S805: Display the presentation based on the updated presentation outline and target template.

[0144] In this embodiment of the disclosure, the presentation can be displayed based on the updated presentation outline and target template.

[0145] As an example, the client can send the updated presentation outline and target template to the server. The server then generates the presentation text corresponding to each node in the updated presentation outline. For instance, the server can use a large model to generate the presentation text corresponding to each node in the updated presentation outline. Afterward, the server can use each node and its corresponding presentation text to populate the target template, obtain the presentation, and send the presentation to the client. Accordingly, after receiving the presentation from the server, the client can display the presentation.

[0146] The presentation generation method of this disclosure allows users to update the presentation outline according to their own needs, so that the generated presentation can meet the user's personalized needs and improve the user experience.

[0147] To clearly illustrate how a presentation is displayed based on a presentation outline and a target template in any of the above embodiments, this disclosure also proposes a method for generating a presentation.

[0148] Figure 10 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment 5 of this disclosure.

[0149] like Figure 10 As shown, the method for generating this presentation may include the following steps S1001 to S1006:

[0150] Step S1001: Obtain the input information associated with the presentation to be generated.

[0151] Step S1002: Display multiple presentation templates and, in response to detecting a template selection operation, determine the target template from the multiple presentation templates.

[0152] Step S1003: Display the presentation outline based on the input information.

[0153] The explanation of steps S1001 to S1003 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0154] Step S1004: In response to detecting a trigger operation on the first target control in the display interface, display the presentation according to the presentation outline and the target template.

[0155] The client's display interface can show a first target control and a second target control. The first target control is used to indicate that the content should be consistent with the original text, and the second target control is used to indicate that the content should be expanded.

[0156] In this embodiment of the disclosure, when the client detects that the user has triggered a trigger operation on the first target control in the display interface, the client can respond to the trigger operation and directly display the presentation based on the presentation outline and target template. The implementation principle is similar to steps S104 or S805, and will not be elaborated here.

[0157] As an example, the client's display interface can be as follows: Figure 5 As shown, the first target control can be as follows: Figure 5 The "Keep in Sync" control shown in area 53 in the middle, the second target control can be as follows: Figure 5 The "Expand Appropriately" control shown in the middle area 54 can directly display the presentation based on the presentation outline and target template when the user clicks the "Keep in Sync" control in area 53.

[0158] Step S1005: In response to detecting a trigger operation on the second target control in the display interface, obtain the initial document based on the presentation outline and the target template.

[0159] In this embodiment of the disclosure, when the client detects that the user has triggered a trigger operation on the second target control in the display interface, the client can respond to the trigger operation and directly obtain the initial document based on the presentation outline and the target template.

[0160] As an example, the client can send a presentation outline and a target template to the server, which will then generate the presentation text corresponding to each node in the presentation outline. For instance, the server can use a large model to generate the presentation text corresponding to each node in the presentation outline. Afterward, the server can use each node and its corresponding presentation text to populate the target template, obtain the initial presentation, and send the initial presentation to the client.

[0161] Step S1006: Expand the initial document to obtain a presentation document, and then display the presentation document.

[0162] In this embodiment of the disclosure, the client can also expand the initial document to obtain the final presentation document.

[0163] In any embodiment of this disclosure, the following steps a to c can be used to expand the initial document to obtain the presentation document:

[0164] Step a: Obtain the second prompt template; the second prompt template is used to prompt the large model to perform the text expansion task.

[0165] The second prompt template is a pre-set or configured prompt template used to instruct the large model (or large language model) to perform text expansion tasks.

[0166] It should be understood that the second prompt template can also be maintained and dynamically updated according to actual application needs, and this disclosure does not limit this.

[0167] Step b: Generate the second prompt message based on the second prompt template and the initial document.

[0168] For example, the second prompt template can be filled with the text content in the initial document to obtain the second prompt information.

[0169] Step c: Process the second prompt information by calling the large model to obtain the presentation.

[0170] For example, by calling the large model to process the second prompt information, the text content output by the large model can be obtained. Using this text content to fill the target template, a presentation can be obtained.

[0171] It should be noted that step S1004 and steps S1005 to S1006 are two parallel implementation methods. In actual application, only one needs to be executed.

[0172] In summary, the second prompt can serve as prior information or task information, indicating the tasks to be performed by the large model, thereby improving its prediction accuracy. Furthermore, expanding the content of the presentation can enrich its content, further meeting users' personalized presentation generation needs and improving the user experience.

[0173] The presentation document generation method of this disclosure allows users to determine whether to expand the content of the presentation document according to their own needs, which can meet users' personalized document generation needs and improve the user experience.

[0174] To clearly illustrate any of the above embodiments, this disclosure also proposes a method for generating a presentation document.

[0175] Figure 11 This is a flowchart illustrating the method for generating a presentation document provided in Embodiment Six of this disclosure.

[0176] like Figure 11 As shown, the method for generating this presentation may include the following steps S1101 to S1110:

[0177] Step S1101: Obtain the input information associated with the presentation to be generated.

[0178] Step S1102: Display multiple presentation templates and, in response to detecting a template selection operation, determine the target template from the multiple presentation templates.

[0179] The explanation of steps S1101 to S1102 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0180] Step S1103: Perform intent recognition on the input information to obtain the target intent.

[0181] For example, deep learning techniques can be used to identify the intent of the input information and obtain the target intent. For instance, a client can invoke a large model to identify the intent of the input information and obtain the user's actual target intent.

[0182] Step S1104: Determine whether the target intent matches the set presentation generation intent. If yes, proceed to step S1105; otherwise, proceed to step S1106 and subsequent steps.

[0183] It should be noted that step S1105, along with step S1106 and subsequent steps, are two parallel implementation methods. In actual application, only one needs to be executed.

[0184] Step S1105: Based on the input information, display the presentation outline, and based on the presentation outline and the target template, display the presentation.

[0185] In this embodiment of the disclosure, when the target intent matches the presentation generation intent, the client can display a presentation outline based on the input information, and display the presentation based on the presentation outline and the target template. The implementation process can be found in the relevant descriptions in the above embodiments, and will not be repeated here.

[0186] Step S1106: Determine whether the target intent matches the vertical intent under the specified domain. If yes, proceed to step S1107; otherwise, proceed to step S1108 and subsequent steps.

[0187] The designated field can be the field that the client is interested in. For example, for a learning application client, the target field it is interested in can be the education field, and for a medical application client, the target field it is interested in can be the medical field.

[0188] Vertical intents include demand intents within a specific domain.

[0189] In this embodiment of the disclosure, if the user's target intent does not match the presentation generation intent, there is no need to execute the presentation generation step. Instead, it is possible to further determine whether the target intent matches the vertical intent under the specified domain. If yes, step S1107 is executed; otherwise, step S1108 and subsequent steps are executed.

[0190] It should be noted that step S1107, along with step S1108 and subsequent steps, are two parallel implementation methods. In actual application, only one needs to be executed.

[0191] Step S1107: Using a processing strategy that matches the vertical category intent, the input information is processed to obtain the first response information, and the input information is responded to based on the first response information.

[0192] In this embodiment of the disclosure, when the user's actual target intent matches the vertical intent, a set processing strategy matching the vertical intent can be adopted to process the input information, obtain the first response information, and respond to the input information based on the first response information.

[0193] For example, in the education sector, users can be provided with learning materials and online courses; in the healthcare sector, users can be provided with health consultations, appointment booking, and other services.

[0194] It should be noted that step S1107 can also be executed by the server; this embodiment only demonstrates execution by the client.

[0195] In summary, by adopting a processing strategy that matches the intent of a specific vertical category to process the input information, we can achieve targeted problem-solving for users and meet their actual knowledge acquisition needs.

[0196] Step S1108: Query whether there is a preset response information that matches the input information in the specified field. If yes, proceed to step S1109; otherwise, proceed to step S1110.

[0197] In this embodiment of the disclosure, if the user's actual target intent does not match the vertical category intent, the system can further query whether there is a preset response information that matches the input information in the specified domain. If yes, step S1109 is executed; otherwise, step S1110 is executed.

[0198] It should be noted that steps S1109 and S1110 are two parallel implementation methods, and in actual application, only one needs to be executed.

[0199] Step S1109: Reply to the input information based on preset response information.

[0200] In this embodiment of the disclosure, if there is preset response information that matches the input information in a specified field, the preset response information can be used directly to reply to the input information.

[0201] Step S1110: Send a query request carrying input information to the server and receive the query response sent by the server. Based on the second response information in the query response, reply to the input information.

[0202] The query request is used to request the server to process the input information and obtain the second response information.

[0203] In this embodiment of the disclosure, when there is no preset response information matching the input information in the specified domain, the input information can be processed based on a real-time request. That is, in this disclosure, the client can send a query request carrying the input information to the server. When the server receives the query request, it can respond to the query request, process the input information, and obtain the second response information. For example, a large model can be used to process the input information to obtain the second response information. After that, the server can send a query response carrying the second response information to the client. Correspondingly, after receiving the query response, the client can use the second response information in the query response to reply to the input information.

[0204] In summary, when there is a pre-set response that matches the input information within a specified domain, directly responding to the input information based on that pre-set response can improve problem-solving efficiency and reduce user waiting time. Conversely, when there is no pre-set response that matches the input information within a specified domain, processing the input information based on real-time requests can improve the accuracy of problem-solving and enhance the user experience.

[0205] The presentation generation method of this disclosure, when the user's intent matches the presentation generation intent, displays a presentation outline based on the input information, which can more accurately respond to user needs, reduce erroneous operations caused by misunderstandings or misjudgments, and ensure that the generated presentation content meets the user's actual needs.

[0206] In any embodiment of this disclosure, a presentation slide (PPT) is used as an example. This disclosure provides a PPT template in advance to generate a PPT outline for use by the entire website:

[0207] 1. Create pre-made AI dialogues based on the URL (Uniform Resource Locator) address of the page visited by the user and the query (information or question entered by the user).

[0208] 2. Map the query as follows Figure 12 The three-level category cards shown allow users to click on related words or pre-created words, send prompts, and engage in dialogue with the intelligent AI typewriter effect.

[0209] 2.1 For the input boxes on the display interface:

[0210] Triggering timing: Anchored to the "Input Topic" control, or when the user clicks the "Upload Document" control, clicks the suggested keywords, clicks send, presses Enter, or deletes. When the user exits the AIPPT vertical category, the input box will not display any guiding text or background text.

[0211] Display style: The input box displays the guiding text "Help me write a PPT, the theme is:"; the input box displays the background text "Please enter the theme you want to create"; position: consistent with the toolbar page, placed at the bottom.

[0212] 2.2 Regarding associative words:

[0213] First screen: PPT campaign keyword pre-launch / backup.

[0214] Quantity: Take the first N (for example, N can be 3).

[0215] Non-first screen: Online logic for tool pages.

[0216] Location: Above the input box.

[0217] 3. Query word splitting - PPT-like dialogue, forming a tree diagram in Markdown-it format for PPT outlines, supporting user editing and modification of PPT outlines, and generating PPTs.

[0218] If the user's intent matches the PPT generation intent, the application will automatically navigate to the AIPPT vertical tool page; otherwise, the application's tool page will be navigated to the PPT generation intent.

[0219] 4. PPT template selection: Supports users to upload custom documents (such as Word, PPT, etc.) and generate PPT outlines [Upload includes 2 entry modes: user-defined theme input, and document upload (document formats include but are not limited to: doc, docx, pdf, etc.)].

[0220] In addition, it supports whether the uploaded content is expanded: keep it consistent or expand it appropriately, and generate a query-id as a unique identifier.

[0221] The presentation formats of PPT templates include, but are not limited to, list presentation and chart presentation. The styles of PPT templates can include clean versions, rich versions, etc.

[0222] The PPT template themes can include different background colors, fonts, font colors, transparency, title backgrounds, special font icons, background images, etc., which users can expand to include.

[0223] 5. In AI dialogue mode, select the preview of the PPT template outline, have a dialogue with the template, synchronize the results, and generate a PPT outline.

[0224] 6. Input theme mode to generate PPT outline (users can also edit PPT outline, customize mode, context theme content, drag and drop to replace node positions, etc.), and hit vertical category intent recognition.

[0225] As an example, using a PowerPoint presentation as an example, the implementation principles of the various embodiments of this disclosure can be as follows: Figure 13 As shown, it mainly includes the following parts:

[0226] Part 1: When a user is browsing the client's tool page, if the user is already logged in, it can be determined whether the user's intent matches the PPT generation intent. If so, proceed to the AIPPT vertical class in Part 3.

[0227] If not, then further determine whether the user's intent matches the vertical intent under the client's area of ​​interest. If the user's intent matches the vertical intent, then respond to the user's query based on the pre-refreshed pre-set reply information.

[0228] If the user's intent does not match the vertical category intent, the user query will be processed based on a real-time request.

[0229] Part Two: When a user browses the client's tool page, if the user is not logged in, the system will respond to the user's query based on the pre-refreshed preset reply information.

[0230] For example, a user can click the function btn (Button) to copy, download, or edit the reply information, or to ask a new question. At this time, a login pop-up can also be displayed to guide the user to log in. After the user logs in, the new question can be processed, or the answers to the question asked before logging in can be displayed.

[0231] If no pre-refreshed, pre-defined reply information exists, a three-level category card can be displayed to guide the user to click on the category card or related keywords, thereby calling the larger model to process the user's query. At this point, a login pop-up can be displayed to guide the user to log in. After the user logs in, the answers to the questions asked before logging in can be shown.

[0232] Part 3: For PPT accounts, enter the AIPPT vertical class: Users can enter a PPT theme and click the Enter key or the Send key on the display interface. Then, a login pop-up window can be displayed to guide users to log in. After logging in, users can select a PPT template, call the backend large model to process the input information, obtain the PPT outline, and generate the PPT based on the PPT template and PPT outline.

[0233] Alternatively, users can click the document upload control. At this time, a login pop-up window can pop up to guide the user to log in. After the user logs in, the document upload pop-up window can be displayed. After the user uploads the document, they can select a PPT template, call the backend big model to process the document content, obtain the PPT outline, and generate the PPT based on the PPT template and PPT outline.

[0234] As an example, let's take a PowerPoint presentation as an example. The principle behind the generation of a PowerPoint presentation can be explained as follows: Figure 14 As shown, for the AIPPT vertical category, you can enter "prompt" and click on the suggested words:

[0235] If the user's intent matches the PPT generation intent, the large model is used directly to output the PPT outline based on the prompt (without displaying the welcome card and background text), and the user can edit the PPT outline;

[0236] If the user's intent does not match the PPT generation intent, then the online logic on the toolbar is executed (see details for implementation logic). Figure 13 (Related descriptions in the text).

[0237] In addition, users can swipe up to view their history.

[0238] With the above Figures 1 to 14 Corresponding to the presentation generation method provided in the embodiments, this disclosure also provides a presentation generation apparatus. Since the presentation generation apparatus provided in the embodiments of this disclosure is similar to the one described above... Figures 1 to 14 The presentation method provided in the embodiments corresponds to the presentation generation method, and therefore the implementation method of the presentation generation method is also applicable to the presentation generation apparatus provided in the embodiments of this disclosure, and will not be described in detail in the embodiments of this disclosure.

[0239] Figure 15 This is a schematic diagram of the structure of the presentation document generation apparatus provided in Embodiment 7 of this disclosure.

[0240] like Figure 15 As shown, the presentation generation device 1500 may include: a first acquisition module 1510, a first determination module 1520, a first display module 1530, and a second display module 1540.

[0241] The first acquisition module 1510 is used to acquire input information associated with the presentation to be generated;

[0242] The first determination module 1520 is used to display multiple presentation templates and, in response to detecting a template selection operation, determine the target template from the multiple presentation templates.

[0243] The first display module 1530 is used to display the presentation outline based on the input information.

[0244] The second presentation module 1540 is used to display the presentation based on the presentation outline and target template.

[0245] In one possible implementation of this disclosure, the first determining module 1520 is configured to: display multiple candidate template themes; wherein the different candidate template themes have different template styles; in response to detecting a theme selection operation, determine a target template theme from the multiple candidate template themes and display at least one presentation template under the target template theme; in response to detecting a template selection operation, determine a target template from at least one presentation template under the target template theme.

[0246] In one possible implementation of this disclosure, the candidate template topic is determined by the server using the following modules and sent to the client:

[0247] The second acquisition module is used to acquire user preference information and historical behavior data associated with the client;

[0248] The third acquisition module is used to acquire the popularity values ​​of multiple template themes; the popularity value is used to represent the degree of attention a template theme receives at the current point in time.

[0249] The second determination module is used to determine candidate template topics from multiple template topics based on the popularity values ​​of multiple template topics, user preference information, and historical behavior data.

[0250] In one possible implementation of this disclosure, different template themes may further include at least one of the following differences: different template background colors; different template fonts; different template font colors; different template transparency; different title backgrounds; different icons for special fonts; and different background images.

[0251] In one possible implementation of this disclosure, the first display module 1530 is configured to: obtain a first prompt template; wherein the first prompt template is used to prompt the large model to perform an outline generation task; generate first prompt information according to the first prompt template and input information; process the first prompt information by calling the large model to obtain the initial outline text output by the large model; perform format processing on the initial outline text to obtain a presentation outline with a set format, and display the presentation outline.

[0252] In one possible implementation of this disclosure, the presentation outline is a tree structure. The second display module 1540 is used to: display the presentation outline; in response to detecting an outline modification operation, perform at least one of the following update operations on the presentation outline: update the position of at least one node in the presentation outline, update the content of at least one node in the presentation outline, delete at least one node in the presentation outline, or add at least one node in the presentation outline; and display the presentation based on the updated presentation outline and the target template.

[0253] In one possible implementation of this disclosure, the first acquisition module 1510 is configured to perform any of the following: in response to detecting a document upload operation, acquire the uploaded target document, parse the content of the target document to obtain document content, and determine input information based on the document content; in response to detecting a topic input operation, acquire the document topic associated with the presentation to be generated, and determine input information based on the document topic; in response to detecting a text input operation, acquire the input information associated with the presentation to be generated; in response to detecting a selection operation, select a target word associated with the presentation to be generated from at least one displayed candidate word, and generate input information based on the target word; wherein, the candidate words include associated words and / or preset words, and the associated words are determined based on historical search behavior and popular search trends.

[0254] In one possible implementation of this disclosure, a document upload control and a topic input control are displayed on the display interface. The document upload operation is generated by triggering the document upload control, and the topic input operation is generated by triggering the topic input control.

[0255] The interface also displays guiding text; the guiding text is used to guide users to input the topic of the document they need, and the input information is generated based on the topic of the document and the guiding text.

[0256] In one possible implementation of this disclosure, a first target control and a second target control are displayed on the display interface. The first target control is used to indicate that the content should be kept consistent with the original text, and the second target control is used to indicate that the content should be expanded.

[0257] The second display module 1540 is used to: respond to the detection of a trigger operation on the first target control in the display interface, display the presentation according to the presentation outline and the target template; respond to the detection of a trigger operation on the second target control in the display interface, obtain the initial document according to the presentation outline and the target template; expand the initial document to obtain the presentation, and display the presentation.

[0258] In one possible implementation of this disclosure, the second display module 1540 is configured to: obtain a second prompt template; wherein the second prompt template is used to prompt the large model to perform a text expansion task; generate second prompt information based on the second prompt template and the initial document; and process the second prompt information by calling the large model to obtain a presentation document.

[0259] In one possible implementation of this disclosure, the first display module 1530 is configured to: perform intent recognition on the input information to obtain the target intent; determine whether the target intent matches the set presentation generation intent; if the target intent matches the presentation generation intent, then display the presentation outline according to the input information.

[0260] In one possible implementation of this disclosure, the presentation generation apparatus 1500 further includes:

[0261] The judgment module is used to determine whether the target intent matches the vertical intent under the specified domain if the target intent does not match the presentation generation intent; wherein, the vertical intent includes the requirement intent under the specified domain.

[0262] The processing module is used to process the input information and obtain the first response information by adopting the processing strategy that matches the vertical intent if the target intent matches the vertical intent.

[0263] The reply module is used to respond to the input information based on the first reply information.

[0264] In one possible implementation of this disclosure, the presentation generation apparatus 1500 further includes:

[0265] The query module is used to query whether there are preset response messages that match the input information in the specified domain if the target intent does not match the vertical intent.

[0266] The response module is also used to respond to the input information based on the preset response information if such information exists.

[0267] The sending module is used to send a query request carrying the input information to the server if there is no preset reply information; wherein, the query request is used to request the server to process the input information and obtain the second reply information;

[0268] The receiving module is used to receive query responses sent by the server.

[0269] The response module is also used to reply to the input information based on the second response information in the query response.

[0270] The presentation generation apparatus of this disclosure can automatically generate a presentation outline based on user-provided input information, and then generate the final presentation based on the outline and a user-selected presentation template. This not only improves presentation generation efficiency but also meets the personalized presentation generation needs of different users, enhancing the user experience. Furthermore, by understanding user preferences in advance and recommending or displaying multiple presentation templates based on those preferences, the user can select a target template of interest from the recommended or displayed templates before generating the presentation outline. After the presentation outline is generated, the presentation is generated based on the user-selected target template and the outline, simplifying the user's operation, reducing waiting time for the presentation, and improving the user experience.

[0271] To implement the above embodiments, this disclosure also provides an electronic device, which may include 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, the instructions being executed by the at least one processor to enable the at least one processor to perform the presentation document generation method proposed in any of the above embodiments of this disclosure.

[0272] To implement the above embodiments, this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the presentation document generation method proposed in any of the above embodiments of this disclosure.

[0273] To implement the above embodiments, this disclosure also provides a computer program product, which includes a computer program that, when executed by a processor, implements the presentation document generation method proposed in any of the above embodiments of this disclosure.

[0274] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0275] Figure 16A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. The electronic device may include the server and client described in the above embodiments. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0276] like Figure 16 As shown, the electronic device 1600 includes a computing unit 1601, which can perform various appropriate actions and processes according to a computer program stored in ROM (Read-Only Memory) 1602 or loaded from storage unit 1607 into RAM (Random Access Memory) 1603. The RAM 1603 may also store various programs and data required for the operation of the device 1600. The computing unit 1601, ROM 1602, and RAM 1603 are interconnected via bus 1604. An I / O (Input / Output) interface 1605 is also connected to bus 1604.

[0277] Multiple components in device 1600 are connected to I / O interface 1605, including: input unit 1606, such as keyboard, mouse, etc.; output unit 1607, such as various types of monitors, speakers, etc.; storage unit 1608, such as disk, optical disk, etc.; and communication unit 1609, such as network card, modem, wireless transceiver, etc. Communication unit 1609 allows device 1600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0278] The computing unit 1601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1601 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 1601 performs the various methods and processes described above, such as the presentation generation method described above. For example, in some embodiments, the presentation generation method described above can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1608. In some embodiments, part or all of the computer program can be loaded and / or installed on device 1600 via ROM 1602 and / or communication unit 1609. When the computer program is loaded into RAM 1603 and executed by the computing unit 1601, one or more steps of the presentation generation method described above can be performed. Alternatively, in other embodiments, the computing unit 1601 may be configured to perform the above-described presentation generation method by any other suitable means (e.g., by means of firmware).

[0279] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0280] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0281] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0282] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0283] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0284] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is established by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers integrated with blockchain technology.

[0285] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0286] According to the technical solution of this disclosure, a presentation outline can be automatically generated based on the input information provided by the user, and the final presentation can be generated based on the presentation outline and the presentation template selected by the user. This not only improves the efficiency of presentation generation, but also meets the personalized presentation generation needs of different users and improves the user experience.

[0287] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0288] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method of generating a presentation, wherein, The method is executed by a client, and the method comprises: obtaining input information associated with a to-be-generated presentation; wherein: the input information is generated according to a user-required presentation theme and a guide script; the guide script is displayed in a display interface, and is used to guide a user to input the presentation theme; a plurality of candidate template themes sent by a server are displayed, a target template theme is determined from the plurality of candidate template themes in response to monitoring a theme selection operation, and at least one presentation template under the target template theme is displayed in response to monitoring the template selection operation; a target template is determined from the at least one presentation template; wherein: a manner in which the server determines the candidate template theme comprises: the server obtains user preference information and historical behavior data associated with the client; obtains a plurality of template theme heat values, the heat values being used to represent a degree of attention of the template theme at a current time point; the candidate template theme is determined from the plurality of template themes according to the heat values of the plurality of template themes, the user preference information and the historical behavior data; after the target template is determined, a first prompt template used to prompt a large model to perform an outline generation task is obtained; first prompt information is generated according to the first prompt template and the input information; the first prompt information is processed by calling the large model; an initial outline text output by the large model is format-processed to automatically obtain a presentation outline in a set format, and the presentation outline is displayed; the presentation is displayed according to the presentation outline and the target template.

2. The method of claim 1, wherein, The different template themes further comprise at least one of the following differences: different template background colors; different template fonts; different colors of template fonts; different template transparencies; different title backgrounds; different icons of special fonts; different background pictures.

3. The method of claim 1, wherein, The presentation outline is in a tree structure, the presentation is displayed according to the presentation outline and the target template, comprising: the presentation outline is displayed; in response to monitoring an outline modification operation, at least one of the following update operations is performed on the presentation outline: updating a position of at least one node in the presentation outline, updating content of at least one node in the presentation outline, deleting at least one node in the presentation outline, and adding at least one node in the presentation outline; the presentation is displayed according to the updated presentation outline and the target template.

4. The method of any one of claims 1-3, wherein, The input information associated with the to-be-generated presentation is obtained by any one of the following: in response to monitoring a document uploading operation, a target document uploaded is obtained, content of the target document is parsed to obtain document content, and the input information is determined according to the document content; in response to monitoring a theme input operation, a presentation theme associated with the to-be-generated presentation is obtained, and the input information is determined according to the presentation theme; in response to monitoring a text input operation, input information associated with the to-be-generated presentation is obtained. In response to monitoring the selection operation, a target word associated with the to-be-generated presentation is selected from the displayed at least one candidate word, and the input information is generated according to the target word; The candidate words include association words and / or preset words, and the association words are determined according to historical search behaviors and hot search trends.

5. The method of claim 4, wherein, The display interface also displays a document uploading control and a theme input control, the document uploading operation is generated by triggering the document uploading control, and the theme input operation is generated by triggering the theme input control.

6. The method of claim 1 or 2, wherein, The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded; The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded; The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded; The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded; The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded.

7. The method of claim 6, wherein, The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded.

8. The method of claim 1 or 2, wherein, The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded.

9. The method of claim 8, wherein, The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded.

10. The method of claim 9, wherein, The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded. The display interface also displays a first target control and a second target control, the first target control is used to indicate that the original text If the preset reply information does not exist, a query request carrying the input information is sent to a server; wherein, the query request is used to request the server to process the input information to obtain second reply information; A query response sent by the server is received, and the input information is replied based on the second reply information in the query response.

11. A presentation generating apparatus, wherein, The device is executed by a client, and the device comprises: A first obtaining module is configured to obtain input information associated with a to-be-generated presentation; wherein, the input information is generated according to a user demand for a presentation theme and a guide script; the guide script is displayed in a display interface, and is used to guide a user to input the presentation theme; A first determining module is configured to display a plurality of candidate template themes sent by a server, determine a target template theme from the plurality of candidate template themes in response to monitoring a theme selection operation, display at least one presentation template under the target template theme, and determine a target template from at least one presentation template in response to monitoring the template selection operation; wherein, the server determines the candidate template theme in the following manner: the server obtains user preference information and historical behavior data associated with the client, obtains a plurality of template theme heat values, the heat value is used to represent the attention degree of the template theme at a current time point, and determines the candidate template theme from the plurality of template themes according to the heat values of the plurality of template themes, the user preference information and the historical behavior data; A first display module is configured to, after determining the target template, obtain a first prompt template for prompting a large model to perform an outline generation task, generate first prompt information according to the first prompt template and the input information, process the first prompt information by calling the large model, format process an initial outline text output by the large model to automatically obtain a presentation outline in a set format, and display the presentation outline; A second display module is configured to display the presentation according to the presentation outline and the target template.

12. The apparatus of claim 11, wherein, The different template themes further comprise at least one of the following differences: Different template background colors; Different template fonts; Different colors of template fonts; Different template transparencies; Different title backgrounds; Different icons of special fonts; Different background pictures.

13. The apparatus of claim 11, wherein, The presentation outline is in a tree structure, The second display module is configured to: Display the presentation outline; In response to monitoring an outline modification operation, perform at least one of the following update operations on the presentation outline: update a position of at least one node in the presentation outline, update content of at least one node in the presentation outline, delete at least one node in the presentation outline, and add at least one node in the presentation outline; Display the presentation according to the updated presentation outline and the target template.

14. The apparatus of any one of claims 11-13, wherein, The first obtaining module is configured to perform any of the following: In response to monitoring the document uploading operation, the uploaded target document is acquired, and content analysis is performed on the target document to obtain document content, and the input information is determined according to the document content; In response to monitoring the theme input operation, a document theme associated with the to-be-generated presentation document is acquired, and the input information is determined according to the document theme; In response to monitoring the text input operation, input information associated with the to-be-generated presentation document is acquired; In response to monitoring the selection operation, a target word associated with the to-be-generated presentation document is selected from at least one candidate word displayed, and the input information is generated according to the target word; The candidate word includes an association word and / or a preset word, and the association word is determined according to historical search behavior and hot search trends.

15. The apparatus of claim 14, wherein, The document uploading control and the theme input control are also displayed on the display interface, the document uploading operation is generated by triggering the document uploading control, and the theme input operation is generated by triggering the theme input control.

16. The apparatus of any one of claims 11-13, wherein, The first target control and the second target control are displayed on the display interface, the first target control is used to indicate that the original text content is kept unchanged, and the second target control is used to indicate that the original text content is expanded; The second display module is configured to: In response to monitoring the triggering operation of the first target control in the display interface, the presentation document is displayed according to the presentation document outline and the target template; In response to monitoring the triggering operation of the second target control in the display interface, the initial document is acquired according to the presentation document outline and the target template; The initial document is expanded to obtain the presentation document, and the presentation document is displayed.

17. The apparatus of claim 16, wherein, The second display module is configured to: Acquire a second prompt template; wherein the second prompt template is used to prompt a large model to perform a text expansion task; Generate second prompt information according to the second prompt template and the initial document; The large model is called to process the second prompt information to obtain the presentation document.

18. The apparatus of any one of claims 11-13, wherein, The first display module is configured to: Perform intent recognition on the input information to obtain a target intent; Determine whether the target intent matches a set presentation document generation intent; If the target intent matches the presentation document generation intent, the presentation document outline is displayed according to the input information.

19. The apparatus of claim 18, wherein, The device further includes: A judgment module configured to determine whether the target intent matches a vertical intent in a specified field if the target intent does not match the presentation document generation intent; wherein the vertical intent includes a demand intent in the specified field; A processing module configured to process the input information using a processing strategy matched with the vertical intent to obtain first reply information if the target intent matches the vertical intent; A reply module configured to reply to the input information based on the first reply information.

20. The apparatus of claim 19, wherein, The device further includes: A query module configured to query whether there is preset reply information matched with the input information in the specified field if the target intent does not match the vertical intent; The reply module is further configured to reply to the input information based on the preset reply information if the preset reply information exists. The sending module is configured to send a query request carrying the input information to a server if the preset reply information does not exist, wherein the query request is used to request the server to process the input information to obtain second reply information. The receiving module is configured to receive a query response sent by the server. The reply module is further configured to reply to the input information based on the second reply information in the query response. 21.An electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for generating a presentation according to any one of claims 1-10.

22. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method for generating a presentation according to any one of claims 1-10. 23.A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method for generating a presentation according to any one of claims 1-10.

Images