Presentation generation method, device, equipment and storage medium

Abstract

The present invention relates to artificial intelligence technology and provides a method, apparatus, device, and storage medium for generating a presentation. The method comprises: obtaining a target page style tag, multiple target text information, and target text relationship tags corresponding to each target text information input by a user, wherein the target text relationship tags are used to indicate text relationships; determining a target image based on the target text information and a preset image library; determining a target template page based on the target page style tag, the target text relationship tags, and a preset template library; generating configuration information based on the target text information, the target image, and the target template page; generating a target presentation based on the configuration information and a preset software development kit, wherein the software development kit is used to set the layout format of the target text information and the target image within the target template page. The solution provided by an embodiment of the present invention can improve the efficiency of producing presentations with a unified style, thereby reducing time costs.

Description

Technical Field

[0001] The present invention relates to, but is not limited to, the field of artificial intelligence technology, and in particular to a presentation generation method, apparatus, device, and storage medium. Background Art

[0002] With the widespread adoption of office software, presentations have become widely used in all aspects of social life. For example, presentations are used in work reports, corporate promotions, product launches, wedding celebrations, project bidding, management consulting, education and training, and other fields. As the application of presentations expands, the demand for slideshow production is also increasing. Presentations have become an indispensable form of expression in modern work. While presentation styles for the same application scenario are generally similar, the specific style requirements of different users may vary.

[0003] Currently, in order to create a presentation that meets style requirements and has a unified style, users need to spend a lot of time selecting materials with appropriate styles, and then use the text information to be presented and the selected materials to create presentation pages. In addition, they must ensure that the styles of each page are unified. The efficiency of creating presentations with a unified style is low, resulting in increased time costs. Summary of the Invention

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] The embodiments of the present invention provide a presentation generation method, apparatus, device, and storage medium, which can improve the efficiency of producing presentations with a unified style, thereby reducing time costs.

[0006] In the first aspect, the present invention also provides a presentation generation method, including: obtaining a target page style tag input by a user, multiple target text information and a target text relationship tag corresponding to each target text information, the target text relationship tag being used to indicate the text relationship of the target text information; determining a target image based on the target text information and a preset image library; determining a target template page based on the target page style tag, the target text relationship tag and a preset template library; generating configuration information based on the target text information, the target image and the target template page; generating a target presentation based on the configuration information and a preset software development kit, wherein the software development kit is used to set the layout format of the target text information and the target image within the target template page.

[0007] In some embodiments, the template library is established through the following steps: obtaining multiple presentation materials and text relationship tags, wherein each presentation material includes a page material and a text material, and the text relationship tag is used to indicate the text relationship of the text material; based on the text relationship tag, classifying each of the page materials to determine multiple categories of template pages; performing style analysis on the page materials to obtain page style tags; and establishing the template library based on the template pages and the page style tags.

[0008] In some embodiments, the image library is established through the following steps: acquiring a plurality of image materials; performing style analysis on the image materials to obtain image style labels; and establishing an image library based on the image materials and the image style labels.

[0009] In some embodiments, the software development kit is created through the following steps: classifying the attributes of the presentation material to determine multiple attribute contents, wherein the attribute contents include image attributes, icon attributes, shape attributes, text attributes, table attributes, chart attributes and motion attributes; and creating a software development kit corresponding to each of the attribute contents.

[0010] In some embodiments, the generating of configuration information based on the target text information, the target image and the target template page includes: determining the target attribute content corresponding to the target text information, the target template page and the target image based on attribute classification; and generating corresponding configuration information based on the target text information, the target template page and the target image based on the target attribute content.

[0011] In some embodiments, determining the target image based on the target text information and a preset image library includes: performing sentence processing on the target text information to obtain multiple text sub-sentences; performing keyword extraction on each of the text sub-sentences to determine the target keywords corresponding to each text sub-sentence; and screening out the target image from all image materials in the image library based on the target keywords and the image style tags.

[0012] In some embodiments, the image material includes picture material and icon material, the image library includes a picture library and an icon library, the image style tag includes a picture style tag and an icon style tag, the picture style tag is determined by the picture material, the icon style tag is determined by the icon material, the picture library is established by the picture material and the picture style tag, and the icon library is established by the icon material and the icon style tag.

[0013] In the second aspect, the present invention also provides a presentation generation device, including: an acquisition unit, used to acquire a target page style tag, a target image style tag, multiple target text information and a target text relationship tag corresponding to each target text information input by a user, wherein the target text relationship tag is used to indicate the text relationship of the target text information; an image determination unit, used to determine the target image based on the target text information and a preset image library; a page determination unit, used to determine the target template page based on the target page style tag, the target text relationship tag and a preset template library; a configuration generation unit, used to generate configuration information based on the target text information, the target image and the target template page; a presentation generation unit, used to generate a target presentation based on the configuration information and a preset software development kit.

[0014] In a third aspect, an embodiment of the present invention further provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the presentation generation method as described in the first aspect above is implemented.

[0015] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the presentation generation method described in the first aspect above.

[0016] An embodiment of the present invention includes: obtaining a target page style tag input by a user, multiple target text information and a target text relationship tag corresponding to each target text information, wherein the target text relationship tag is used to indicate the text relationship of the target text information; determining a target image based on the target text information and a preset image library; determining a target template page based on the target page style tag, the target text relationship tag and a preset template library; generating configuration information based on the target text information, the target image and the target template page; generating a target presentation based on the configuration information and a preset software development kit, wherein the software development kit is used to set the layout format of the target text information and the target image within the target template page. According to the solution provided by an embodiment of the present invention, an image with similar content is determined as a target image through target text information and an image library, and a template page with a unified style and the same text relationship is determined as a target template page through the target page style tag, the target text relationship tag and a preset template library. Configuration information matching the software development kit is generated through the target text information, the target image and the target template page, and then a target presentation that meets the style characteristics represented by the target page style tag is generated, which can improve the production efficiency of presentations with a unified style, thereby reducing time costs.

[0017] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation to the technical solution of the present invention.

[0019] Figure 1 is a flowchart of a presentation generation method provided by one embodiment of the present invention;

[0020] Figure 2 is a flow chart of establishing a template library provided by another embodiment of the present invention;

[0021] Figure 3 is a flow chart of establishing an image library provided by another embodiment of the present invention;

[0022] Figure 4 is a flowchart of creating a software development kit provided by another embodiment of the present invention;

[0023] Figure 5 is a flow chart of generating configuration information provided by another embodiment of the present invention;

[0024] Figure 6 is a flow chart of determining a target image provided by another embodiment of the present invention;

[0025] Figure 7 is a system block diagram of a presentation generation method provided by another embodiment of the present invention;

[0026] Figure 8 is a structural diagram of a presentation generating device provided by another embodiment of the present invention;

[0027] Figure 9 It is a structural diagram of an electronic device provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0029] In the description of the present invention, “several” means one or more, “more” means more than two, “greater than”, “less than”, “exceed”, etc. are understood to exclude the number itself, and “above”, “below”, “within”, etc. are understood to include the number itself.

[0030] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and the like in the specification, claims, or accompanying drawings are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0031] With the widespread adoption of office software, presentations have become widely used in all aspects of social life. For example, presentations are used in work reports, corporate promotions, product launches, wedding celebrations, project bidding, management consulting, education and training, and other fields. As the application of presentations expands, the demand for slideshow production is also increasing. Presentations have become an indispensable form of expression in modern work. While presentation styles for the same application scenario are generally similar, the specific style requirements of different users may vary.

[0032] Currently, in order to create a presentation that meets style requirements and has a unified style, users need to spend a lot of time selecting materials with appropriate styles, and then use the text information to be presented and the selected materials to create presentation pages. In addition, they must ensure that the styles of each page are unified. The efficiency of creating presentations with a unified style is low, resulting in increased time costs.

[0033] In response to the problems of low efficiency and high time cost in producing presentations with a unified style, the present invention provides a presentation generation method, device and storage medium, the method comprising: obtaining a target page style tag, multiple target text information and target text relationship tags corresponding to each target text information input by a user, the target text relationship tags being used to indicate the text relationship of the target text information; determining a target image based on the target text information and a preset image library; determining a target template page based on the target page style tag, the target text relationship tags and a preset template library; generating configuration information based on the target text information, the target image and the target template page; generating a target presentation based on the configuration information and a preset software development kit, wherein the software development kit is used to set the layout format of the target text information and the target image within the target template page. According to the solution provided by an embodiment of the present invention, an image with similar content is determined as a target image through target text information and an image library, and a template page with a unified style and the same text relationship is determined as a target template page through the target page style tag, the target text relationship tag and a preset template library. Configuration information matching the software development kit is generated through the target text information, the target image and the target template page, and then a target presentation that meets the style characteristics represented by the target page style tag is generated, which can improve the production efficiency of presentations with a unified style, thereby reducing time costs.

[0034] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence.

[0035] Artificial intelligence (AI) is the study of the design principles and implementation methods of various intelligent machines, enabling them to perceive, reason, and make decisions. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning. With the advancement of AI technology, research and application are expanding across a wide range of fields, including smart homes, smart customer service, virtual assistants, smart speakers, smart marketing, driverless and autonomous driving, robotics, smart healthcare, and smart cities. As technology advances, AI will be applied in even more areas and play an increasingly important role.

[0036] Machine Learning (ML) is a multidisciplinary field that encompasses probability theory, statistics, approximation theory, convex analysis, and algorithmic complexity theory. It specifically studies how computers can simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance.

[0037] Machine learning is at the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications span all areas of artificial intelligence. Machine learning and deep learning typically include technologies such as artificial neural networks, belief networks, reinforcement learning, transfer learning, and inductive learning.

[0038] First, some terms involved in this invention are analyzed:

[0039] A Software Development Kit (SDK) is generally a collection of development tools that software engineers use to build application software for a specific software package, software framework, hardware platform, operating system, etc.

[0040] Convolutional Neural Networks (CNN) are a type of feedforward neural network that includes convolutional calculations and has a deep structure. It is one of the representative algorithms of deep learning.

[0041] Application Programming Interface (API) is a set of predefined interfaces (such as functions, HTTP interfaces), or a convention for connecting different components of a software system. It is used to provide a set of routines that applications and developers can access based on a certain software or hardware without having to access the source code or understand the details of the internal working mechanism.

[0042] Natural Language Processing (NLP) is an important field in the fields of computer science and artificial intelligence. It studies various theories and methods that can achieve effective communication between humans and computers using natural language. Natural language processing is a science that integrates linguistics, computer science, and mathematics. Therefore, research in this field involves natural language, that is, the language people use in daily life. Therefore, it is closely related to the study of linguistics, but there are important differences. Natural language processing is not a general study of natural language, but the development of computer systems that can effectively realize natural language communication, especially the software systems therein.

[0043] Classification is a very important method in data mining. The concept of classification is to learn a classification function or construct a classification model based on existing data. This function or model can map the data records in the database to one of the given categories, so that it can be applied to data prediction.

[0044] Term Frequency–Inverse Document Frequency (TF-IDF) is a commonly used weighting technique for information retrieval and data mining.

[0045] The TextRank algorithm is a graph-based ranking algorithm for keyword extraction and document summarization. It is improved from Google's page importance ranking algorithm PageRank algorithm. It uses the co-occurrence information (semantics) between words within a document to extract keywords. It can extract keywords and keyword phrases from a given text, and use extractive automatic summarization methods to extract key sentences from the text.

[0046] The embodiments of the present invention are further described below with reference to the accompanying drawings.

[0047] like Figure 1 As shown, Figure 1 This is a flowchart of a presentation generation method provided by one embodiment of the present invention, wherein the method includes but is not limited to the following steps:

[0048] Step S110, obtaining a target page style tag, a plurality of target text information, and target text relationship tags corresponding to each target text information input by the user, where the target text relationship tags are used to indicate the text relationship of the target text information;

[0049] Step S120, determining a target image based on the target text information and a preset image library;

[0050] Step S130, determining a target template page based on the target page style tag, the target text relationship tag, and a preset template library;

[0051] Step S140, generating configuration information according to the target text information, the target image and the target template page;

[0052] Step S150 , generating a target presentation according to the configuration information and a preset software development kit, wherein the software development kit is used to set the layout format of target text information and target images in the target template page.

[0053] It can be understood that a presentation refers to a file generated by multimedia information such as text, pictures, audio and other elements for content dissemination and display, such as slide documents (PowerPoint, PPT), Xiwo courseware, etc.; usually, a presentation is composed of multiple slides, each slide is independent of each other, and users can insert pictures, animations, tables, notes and handouts on each slide to make the complex content of the presentation easy to understand and leave a deeper impression. Special effects and dynamic display effects can also be added to the presentation to increase the fun; in order to make a presentation with a unified style, the target image that matches the target text information is determined through the target text information and image library, and the target page style tag, target text key, etc. are used to create a presentation with a unified style. Through the system tags and template library, a target template page with a unified style is determined, and then configuration information is generated. The configuration information is then combined with the preset software development kit SDK to automatically generate a target presentation with a unified style. Based on this, an image with similar content is determined as a target image through the target text information and image library, and a template page with a unified style and the same text relationship is determined as a target template page through the target page style tags, target text relationship tags and the preset template library. Configuration information matching the software development kit is generated through the target text information, target image and target template page, and then a target presentation that meets the style characteristics represented by the target page style tags is generated, which can improve the production efficiency of presentations with a unified style and thus reduce time costs.

[0054] It should be noted that the target template page is equivalent to a slide, and the operations for making a slide include but are not limited to: setting the font, color, and text box of the slide's text, pictures, and tables, adding pictures to the specified location of the slide, modifying the style of the table in the slide, and adding special effects dynamic display effects; the user makes each page of the slide according to the target text information and production needs by implementing the corresponding slide production operations, and after all slides are produced, a presentation is obtained; generally speaking, the format of the document material, page layout, page background and other page formats can be pre-set for each page of the slide; of course, these page formats can also be set after the display content is added; at the same time, users can also modify or adjust these page formats based on their own preferences; however, manual slide production by users is inefficient and takes a lot of time. Generating presentations through configuration information and software development kits can improve production efficiency and thus reduce time costs.

[0055] It should be noted that the target page style tag is one of multiple pre-determined page style tags. The target page style tag is used to characterize the style characteristics of the target template page. The style characteristics represented by the page style tag include but are not limited to: business, simplicity, art, cartoon and romance; template pages with different style characteristics are applicable to different scenarios, and users input the corresponding target page style tag according to the application scenario; style characteristics refer to the page format of the template page, the special effects dynamic display effects and page color of the template page, etc.; page color refers to the color information of the page background. For example, when the style feature is romantic, the color information of the page background corresponds to pink; users use presentations that meet style requirements, which helps improve the display effect of the presentation.

[0056] It should be noted that the target text relationship label is used to indicate the text relationship of the target text information. The target text relationship label is determined by manual annotation. The page layout of the template page corresponds to the text relationship. The text relationship includes at least one of the following: title page relationship, directory page relationship, sub-directory page relationship, conclusion page relationship, concept description relationship, parallel relationship, contrast relationship, total score relationship, sorting relationship, cause-effect relationship, dialogue relationship, time series relationship, bar chart relationship, line chart relationship, pie chart relationship, scatter plot relationship, general table relationship, iceberg chart relationship, straw hat chart relationship, climbing chart relationship, standard general relationship, etc. The relationships among the family asset quadrant diagram, family asset classification, pool diagram, step diagram, V-shaped diagram, asset rotation diagram, city diagram, case study and company introduction are listed below. Among them, the bar diagram, line diagram, pie diagram, scatter diagram and general table relationships belong to chart relationships. The iceberg diagram, straw hat diagram, climbing diagram, Standard & Poor's family asset quadrant diagram, family asset classification, pool diagram, step diagram, V-shaped diagram, asset rotation diagram, city diagram, case study and company introduction relationships belong to special composition relationships.

[0057] In actual practice, users usually use presentation masters for production. When there is a need to produce batches of presentations with a unified style, multiple users are required to produce a certain amount of presentations respectively. The presentations produced by different users using presentation masters will have different styles. In particular, for the same company, in order to ensure the company's image, the presentations produced by each employee in the company are required to meet the characteristics of unified style and beautiful pages. Employees input the target page style tag, multiple target text information and the target text relationship tag corresponding to each target text information, and then generate the target presentation through configuration information and software development kits. This can ensure that each presentation meets the characteristics of unified style and beautiful pages, help improve the company's image, and can also improve the efficiency of employees in producing presentations and reduce time costs.

[0058] In addition, refer to Figure 2 In one embodiment, Figure 1 The steps of establishing the template library in step S130 in the illustrated embodiment include but are not limited to the following steps:

[0059] Step S210: Acquire multiple presentation materials and text relationship tags, wherein each presentation material includes a page material and a text material, and the text relationship tags are used to indicate the text relationship between the text materials;

[0060] Step S220: Classify each page material based on the text relationship tags to determine multiple categories of template pages;

[0061] Step S230: Perform style analysis on the page material to obtain a page style label;

[0062] Step S240: Create a template library based on the template page and page style tags.

[0063] It can be understood that each presentation material contains at least one page material and a text material corresponding to the page material. The text relationship label is used to indicate the text relationship of the text material. The text relationship label is determined by manual annotation. The page layout of the page material is determined by the text relationship of the text material. The text relationship labels corresponding to page materials with different page layouts are different. Classifying the page materials is equivalent to dividing page materials with the same page layout into template pages of the same category. Through style analysis, the page style label corresponding to each page material can be determined. Usually, the trained page style classification model is used for style analysis to ensure the reliability of the style analysis results. In the template library, each template page has its corresponding page style label, which is convenient for searching and filtering when generating the target presentation.

[0064] It should be noted that the presentation materials are obtained from the presentation material library, and the presentation materials are among the most used presentation materials in the presentation material library, which can ensure the aesthetics of the presentation materials, thereby ensuring the aesthetics of the generated target presentation; the ways to obtain the presentation material library include but are not limited to: websites and cloud disks.

[0065] It is worth noting that the method of manually annotating text relationship labels is a technology well known to those skilled in the art and will not be elaborated here.

[0066] In specific practice, the page style classification model is trained through the following steps: the training page and the corresponding training page style label are used as training data, and the convolutional neural network is trained to obtain the page style classification model.

[0067] In addition, refer to Figure 3 In one embodiment, Figure 2 The steps of establishing the image library in step S120 in the illustrated embodiment include but are not limited to the following steps:

[0068] Step S310, obtaining multiple image materials;

[0069] Step S320: performing style analysis on the image material to obtain an image style label;

[0070] Step S330: Create an image library based on the image materials and image style tags.

[0071] It can be understood that style analysis of image material refers to image classification. Image classification is an image processing method that distinguishes different categories of objects based on the different characteristics reflected in the image information. It uses computers to perform quantitative analysis of images, classifying the image or each pixel or region within it into one of several categories, replacing human visual interpretation. Style analysis can determine the image style label corresponding to each image material. Style analysis is usually performed using a trained image style classification model to ensure the reliability of the style analysis results. Image categories include but are not limited to: people, buildings, vehicles, daily necessities, etc., or classification into photography and paintings. Image style labels include but are not limited to: people, buildings, vehicles, daily necessities, photography, and paintings.

[0072] It should be noted that the image materials are obtained from the image material library, and the presentation materials belong to the most used image material library, which can ensure the aesthetics of the presentation materials and thus ensure the aesthetics of the generated target presentation; the ways to obtain the image material library include but are not limited to: websites and cloud disks.

[0073] In specific practice, the image style classification model is trained through the following steps: the training images and the corresponding training image style labels are used as training data to train the convolutional neural network to obtain the image style classification model; after obtaining the image material, the image material is preprocessed to adjust the pixels of the image material to meet the preset image pixel specified range. For example, the image pixel specified range in the presentation is less than 300*400. For image materials with pixels of 400*500, after preprocessing and compression, image materials with pixels of 300*375 are obtained. The image library is established by the preprocessed image materials, which can ensure that the image materials in the image library can be used to generate the target presentation. In addition, in the generated presentation, the user can also adjust the pixels of the target image.

[0074] In addition, refer to Figure 4 In one embodiment, Figure 2 Step S250 in the illustrated embodiment further includes but is not limited to the following steps:

[0075] Step S410: categorize the presentation materials to determine multiple attribute contents, wherein the attribute contents include: image attributes, icon attributes, shape attributes, text attributes, table attributes, chart attributes, and motion effect attributes;

[0076] Step S420: Create a software development kit corresponding to each attribute content.

[0077] It can be understood that each presentation material contains at least one page material and the text material corresponding to the page material. The content of each presentation material is classified according to attributes. There are seven types of attributes, namely picture attributes, icon attributes, shape attributes, text attributes, table attributes, chart attributes and motion attributes. According to the above seven types of attributes, different underlying APIs are called and encapsulated respectively. Each API is used to generate the corresponding attribute content, and then generate the slides of the target presentation. Then, based on different underlying APIs, software development kits corresponding to different attribute categories are created, and the configuration information and software development kit SDK are combined to realize the adaptive layout of the template page, automatically fill in text information and image materials, and automatically edit the format attributes of the template page.

[0078] In addition, refer to Figure 5 In one embodiment, Figure 1 Step S120 in the illustrated embodiment further includes but is not limited to the following steps:

[0079] Step S510, based on the attribute classification, determining target attribute content corresponding to the target text information, target template page, and target image;

[0080] Step S520 : Based on the target attribute content, corresponding configuration information is generated according to the target text information, the target template page and the target image.

[0081] It can be understood that the content of each presentation material is classified according to attributes, and there are seven types of attributes. First, the target attribute content corresponding to the target text information, target template page and target image is determined, and then for each target attribute content, the corresponding configuration information is generated by the target text information, target template page and target image, so that each configuration information matches the corresponding software development kit to ensure the effective generation of the target presentation.

[0082] like Figure 6 As shown, in one embodiment, Figure 1 The text generation model training method of step S140 in the illustrated embodiment includes but is not limited to the following steps:

[0083] Step S610, performing sentence segmentation processing on the target text information to obtain multiple text sub-sentences;

[0084] Step S620: extract keywords from each text subclause to determine the target keywords corresponding to each text subclause;

[0085] Step S630 : Filtering out a target image from all image materials in the image library based on the target keyword and the image style tag.

[0086] It is understandable that the target text information is usually composed of multiple sentences. The target text information can be processed into Chinese or English text sentences by punctuation marks to obtain multiple text sub-sentences; or according to the semantic information of each sentence, the sentence can be divided into multiple text sub-sentences by a natural language model; then, the text keyword extraction model is used to extract keywords from each text sub-sentence, and then the target keyword is determined; in the image library, each image material has a corresponding image style label, and the target keyword and all image style labels are compared. The image material with the same image style label as the target keyword is used as the target image. For example, if the target keyword is vehicle, the image material with the image style label of vehicle is used as the target image. This can ensure that the text and image of each slide on the target presentation correspond to each other, thereby ensuring the quality of the target presentation.

[0087] In specific practice, the algorithms used in the text keyword extraction model include but are not limited to: TF-IDF algorithm and TextRank algorithm.

[0088] In one embodiment, the image material includes picture material and icon material, the image library includes a picture library and an icon library, the image style tag includes a picture style tag and an icon style tag, the picture style tag is determined by the picture material, the icon style tag is determined by the icon material, the picture library is established by the picture material and the picture style tag, and the icon library is established by the icon material and the icon style tag.

[0089] It can be understood that picture materials refer to photos obtained by taking pictures or paintings obtained by drawing. The classification of picture materials includes but is not limited to: people, buildings, vehicles, daily necessities, etc., and then determine the picture style labels and establish a picture library; icon materials (Icon) are highly editable in presentations, and properties such as fill color can be changed. Icons are also divided into different categories according to the content they indicate, and then determine the icon style labels and establish an icon library.

[0090] In addition, reference Figure 7 , Figure 7 It is a system block diagram of a presentation generation method provided by another embodiment of the present invention.

[0091] It can be understood that a template library and an image library are established separately, wherein the steps for establishing the template library are as follows: obtain multiple presentation materials, analyze the presentation materials, and determine 29 categories of text relationship labels, wherein each presentation material includes page materials and text materials, and the text relationship labels are used to indicate the text relationship of the text materials. Based on the text relationship labels, each page material is classified and processed, and multiple categories of template pages are determined. The page materials are style analyzed to obtain page style labels, and a template library is established based on the template pages and page style labels; the steps for the image library are as follows: obtain multiple image materials, perform style analysis on the image materials, obtain image style labels, and establish an image library based on the image materials and image style labels; then create a software development kit SDK, the steps are as follows: classify the attributes of the presentation materials, determine seven categories of attribute content, namely, picture attributes, icon attributes, shape attributes, text attributes, table attributes, chart attributes and motion attributes, and then call the encapsulated underlying AP I, and create a software development kit corresponding to each attribute content; in order to produce a presentation with a unified style, the target image that matches the target text information is determined through the target text information and image library, and the target template page with a unified style is determined through the target page style tag, the target text relationship tag and the template library, and then configuration information is generated, and then the configuration information is combined with the preset software development kit to automatically generate a target presentation with a unified style; based on this, the image with similar content is determined as the target image through the target text information and image library, and the template page with a unified style and the same text relationship is determined as the target template page through the target page style tag, the target text relationship tag and the preset template library, and the configuration information matching the software development kit is generated through the target text information, the target image and the target template page, and then a target presentation that meets the style characteristics represented by the target page style tag is generated, which can improve the production efficiency of presentations with a unified style, thereby reducing time costs.

[0092] It is worth noting that the processing method of calling the encapsulated underlying API is a technology well known to those skilled in the art and will not be described in detail here.

[0093] In addition, reference Figure 8 The present invention further provides a presentation generating device 800, comprising:

[0094] An acquisition unit 810 is configured to acquire a target page style tag, a target image style tag, a plurality of target text information, and target text relationship tags corresponding to each target text information input by a user, wherein the target text relationship tags are used to indicate text relationships between the target text information;

[0095] An image determination unit 820 is configured to determine a target image based on target text information and a preset image library;

[0096] The page determination unit 830 is used to determine the target template page according to the target page style tag, the target text relationship tag and the preset template library;

[0097] The configuration generating unit 840 is configured to generate configuration information according to the target text information, the target image and the target template page;

[0098] The presentation generating unit 850 is used to generate a target presentation according to the configuration information and a preset software development kit.

[0099] It can be understood that the specific implementation of the presentation generation device 800 is basically the same as the specific embodiment of the above-mentioned presentation generation method, and will not be repeated here; based on this, through the target text information and image library, an image with similar content is determined as the target image, and through the target page style tag, target text relationship tag and preset template library, a template page with a unified style and the same text relationship is determined as the target template page, and the configuration information matching the software development kit is generated through the target text information, target image and target template page, and then a target presentation that meets the style characteristics represented by the target page style tag is generated, which can improve the production efficiency of presentations with unified style, thereby reducing time costs.

[0100] In addition, refer to Figure 9 An embodiment of the present invention further provides an electronic device. The electronic device 900 includes a memory 910, a processor 920, and a computer program stored in the memory 910 and executable on the processor 920.

[0101] The processor 920 and the memory 910 may be connected via a bus or other means.

[0102] The non-transient software program and instructions required to implement the presentation generation method of the above embodiment are stored in the memory 910. When executed by the processor 920, the presentation generation method of the above embodiment is executed, for example, the above-described Figure 1 Steps S110 to S150 of the method, Figure 2 Steps S210 to S240 of the method, Figure 3 Steps S310 to S330 of the method, Figure 4 Steps S410 to S420 of the method, Figure 5 Steps S510 to S520 of the method, Figure 6In the method steps S610 to S630, a target page style tag, multiple target text information and target text relationship tags corresponding to each target text information are obtained by the user, wherein the target text relationship tags are used to indicate the text relationship of the target text information; a target image is determined according to the target text information and a preset image library; a target template page is determined according to the target page style tag, the target text relationship tags and a preset template library; configuration information is generated according to the target text information, the target image and the target template page; a target presentation is generated according to the configuration information and a preset software development kit, wherein the software development kit is used to set the layout format of the target text information and the target image within the target template page. Based on this, through the target text information and image library, an image with similar content is determined as the target image, and through the target page style tag, target text relationship tag and preset template library, a template page with unified style and the same text relationship is determined as the target template page. Through the target text information, target image and target template page, configuration information matching the software development kit is generated, and then a target presentation that meets the style characteristics represented by the target page style tag is generated, which can improve the production efficiency of presentations with unified style and thus reduce time costs.

[0103] In addition, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. The computer-executable instructions are executed by a processor or controller, for example, by a processor in the above electronic device embodiment, so that the above processor can execute the presentation generation method in the above embodiment, for example, execute the above-described Figure 1 Steps S110 to S150 of the method, Figure 2 Steps S210 to S240 of the method, Figure 3 Steps S310 to S330 of the method, Figure 4 Steps S410 to S420 of the method, Figure 5 Steps S510 to S520 of the method, Figure 6In the method steps S610 to S630, a target page style tag, multiple target text information and target text relationship tags corresponding to each target text information are obtained by the user, wherein the target text relationship tags are used to indicate the text relationship of the target text information; a target image is determined according to the target text information and a preset image library; a target template page is determined according to the target page style tag, the target text relationship tags and a preset template library; configuration information is generated according to the target text information, the target image and the target template page; a target presentation is generated according to the configuration information and a preset software development kit, wherein the software development kit is used to set the layout format of the target text information and the target image within the target template page. Based on this, through the target text information and image library, an image with similar content is determined as the target image, and through the target page style tag, target text relationship tag and preset template library, a template page with unified style and the same text relationship is determined as the target template page. Through the target text information, target image and target template page, configuration information matching the software development kit is generated, and then a target presentation that meets the style characteristics represented by the target page style tag is generated, which can improve the production efficiency of presentations with unified style and thus reduce time costs.

[0104] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0105] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data) and is volatile and non-volatile, removable, and non-removable. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0106] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above implementation. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for generating a presentation, characterized in that: include: Obtaining a target page style tag input by a user, multiple target text information, and target text relationship tags corresponding to each of the target text information, wherein the target text relationship tags are used to indicate text relationships between the target text information, the target text relationship tags are determined by manual annotation, and the page layout of the template page corresponds to the text relationships; Determining a target image based on the target text information and a preset image library; Determining a target template page according to the target page style tag, the target text relationship tag, and a preset template library; Determining target attribute content corresponding to the target text information, the target template page, and the target image based on attribute classification; wherein the attribute classification is used to determine the attribute content; Based on the target attribute content, generating corresponding configuration information according to the target text information, the target template page and the target image; Generate a target presentation according to the configuration information and a preset software development kit, wherein the software development kit is used to set a layout format of the target text information and the target image within the target template page; The software development kit is created by the following steps: Get multiple presentation materials; Attribute classification is performed on the presentation material to determine a plurality of attribute contents, wherein the attribute contents include image attributes, icon attributes, shape attributes, text attributes, table attributes, chart attributes, and motion effect attributes; Create a software development kit corresponding to each of the attribute contents.

2. The method according to claim 1, characterized in that The template library is established through the following steps: Obtaining text relationship tags corresponding to the presentation materials, wherein each presentation material includes a page material and a text material, and the text relationship tags are used to indicate the text relationship between the text materials; Based on the text relationship tags, each of the page materials is classified and processed to determine template pages of multiple categories; Performing style analysis on the page material to obtain a page style tag; The template library is established according to the template page and the page style tag.

3. The method according to claim 1, characterized in that The image library is established through the following steps: Get multiple image materials; Performing style analysis on the image material to obtain an image style label; An image library is established based on the image material and the image style label.

4. The method according to claim 3, characterized in that The step of determining a target image based on the target text information and a preset image library includes: Performing sentence processing on the target text information to obtain multiple text sub-sentences; Perform keyword extraction on each of the text subclauses respectively to determine target keywords corresponding to each text subclause; Based on the target keyword and the image style tag, a target image is screened out from all image materials in the image library.

5. The method according to claim 3, characterized in that The image material includes picture material and icon material, the image library includes a picture library and an icon library, the image style tag includes a picture style tag and an icon style tag, the picture style tag is determined by the picture material, the icon style tag is determined by the icon material, the picture library is established by the picture material and the picture style tag, and the icon library is established by the icon material and the icon style tag.

6. A presentation document generating device, characterized in that: include: an acquisition unit, configured to acquire a target page style tag, a target image style tag, a plurality of target text information, and target text relationship tags corresponding to each of the target text information, the target text relationship tags being used to indicate text relationships between the target text information, the target text relationship tags being determined by manual annotation, and the page layout of the template page corresponding to the text relationships; An image determining unit, configured to determine a target image based on the target text information and a preset image library; A page determination unit, configured to determine a target template page according to the target page style tag, the target text relationship tag, and a preset template library; A configuration generating unit is configured to determine target attribute content corresponding to the target text information, the target template page, and the target image based on attribute classification; wherein the attribute classification is used to determine the attribute content; Based on the target attribute content, generating corresponding configuration information according to the target text information, the target template page and the target image; A presentation generating unit, configured to generate a target presentation according to the configuration information and a preset software development kit; The software development kit is created by the following steps: Get multiple presentation materials; Attribute classification is performed on the presentation material to determine a plurality of attribute contents, wherein the attribute contents include image attributes, icon attributes, shape attributes, text attributes, table attributes, chart attributes, and motion effect attributes; Create a software development kit corresponding to each of the attribute contents.

7. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the presentation generation method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium storing computer-executable instructions, characterized in that: The computer-executable instructions are used to execute the presentation generating method according to any one of claims 1 to 5.

Images