Text editing system driven by large language model

Abstract

The invention provides a text editing system driven by a large language model, and the system comprises a language processing module which carries out the semantic understanding, grammar error correction, vocabulary optimization and content optimization processing of main body data inputted by a user, carries out the generation of subordinate data according to the processed main body data, and enables the subordinate data and the main body data to be spliced into a creation content; the editing interface interacts with a user and is used for adjusting the created content; the picture processing module is used for searching matched image data according to the creation content and carrying out image optimization processing on the image data; the personalization module is used for creating options for adjusting the creation content in the editing interface; and the creativity generation module provides generation suggestions of the slave data according to the main body data. The method has the beneficial effects that an efficient, intelligent and personalized rich text editor is realized, convenient text creation experience is provided for a user, the problems of low editing efficiency, insufficient picture processing capability and the like in the prior art are solved, and the user is assisted in creative text creation to a certain extent.

Description

Technical Field

[0001] This invention belongs to the field of computer technology, and in particular relates to a text editing system driven by a large language model. Background Technology

[0002] Some existing rich text editing platforms attempt to introduce automated features such as autocorrect and grammar checking. However, these features are often quite basic, lacking a deep understanding of the text's semantics and context, and thus failing to provide high-quality editing suggestions.

[0003] In addition, some platforms offer limited template libraries, but these templates often lack flexibility and personalization, failing to meet the diverse creative needs of users. Regarding image processing, existing platforms typically only allow for basic insertion and adjustments, lacking features such as intelligent search and optimization.

[0004] While some platforms offer basic layout templates and grammar checks, they fall short in creative output and image processing. Users still need to spend a significant amount of time brainstorming and searching for images when creating content on these platforms, and the layout quality rarely reaches professional standards. Summary of the Invention

[0005] In view of this, the present invention aims to propose a large language model-driven text editing system in order to solve at least one of the above-mentioned technical problems.

[0006] To achieve the above objectives, the technical solution of the present invention is implemented as follows: The first aspect of this invention proposes a large language model-driven text editing system, comprising: The language processing module performs semantic understanding, grammatical error correction, vocabulary optimization, and content optimization on the main data input by the user. It generates subordinate data based on the processed main data and combines the subordinate data with the main data to create content. The editing interface is used by the user to adjust the created content; The image processing module searches for matching image data based on the content being created and performs image optimization processing on the image data; The personalization module is used to create options for adjusting the content in the editing interface; The creative generation module provides suggestions for generating subordinate data based on the main data.

[0007] Furthermore, the language processing module includes: The input receiving unit receives text data entered by the user in the editing interface; The semantic understanding unit performs semantic analysis on the input text using deep learning; The syntax correction unit is used to detect potential syntax errors and provide suggestions for correction. The vocabulary optimization unit provides vocabulary optimization suggestions based on text content and context; The content optimization unit is used to optimize the structure of text; The intelligent continuation unit generates relevant supplementary content based on user input.

[0008] Furthermore, the editing interface includes: The text input area is used for user interaction and to receive edited content. The layout settings area provides the content to be edited with layout parameters and corresponding options, including at least font, font size, color, line spacing, and paragraph spacing. The image insertion area is used to edit images within the content being edited; The preview area is used to display the results of editing content in real time after it has been processed by the layout settings area and the image insertion area.

[0009] Furthermore, the image processing module includes: The image search unit searches for matching images based on user input; The image optimization unit performs optimization processing on the output results of the selected image search unit, including at least color adjustment, contrast optimization, and sharpness enhancement.

[0010] Furthermore, each unit of the personalization module is used to provide personalized adjustments to the editing interface, the personalized adjustments including: Create multiple fonts, text colors, background colors, and layout styles as options in the editing interface; provide domain options in the editing interface, and set a corresponding terminology library for each domain option.

[0011] Furthermore, the semantic understanding unit performs semantic analysis by representing the text by word vectors and modeling the contextual relationships; the intelligent continuation writing unit generates relevant supplementary content through generative adversarial networks and variational autoencoders.

[0012] Furthermore, the working process of the image search unit and the image optimization unit includes: The convolutional neural network is used to extract features from the text content input by the user and calculate the similarity with the features of the images in the image library to obtain image resources with a high degree of matching with the text content. The image selected by the user is processed by image processing algorithms to perform histogram equalization and color balance adjustment, and by generative adversarial network to perform style transfer and detail enhancement operations.

[0013] A second aspect of the present invention provides an electronic device including a processor and a memory communicatively connected to the processor and used to store processor-executable instructions, the processor being used to execute the text editing system described in the first aspect above.

[0014] A third aspect of the present invention provides a server comprising at least one processor and a memory communicatively connected to the processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the processor to cause the at least one processor to perform a text editing system as described in the first aspect.

[0015] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the text editing system described in the first aspect.

[0016] Compared with existing technologies, the large language model-driven text editing system described in this invention has the following advantages: By leveraging large language model technology, we can achieve deep understanding of rich text content, grammatical error correction, content optimization, and intelligent continuation, thereby improving the efficiency and accuracy of text editing.

[0017] It integrates AI image search functionality to quickly match suitable image resources, and automatically adjusts the visual effects of images through AI image optimization technology to improve the overall quality of documents.

[0018] It offers personalized font, color, layout style, and terminology settings to meet the needs of different users and enhance the user editing experience.

[0019] Through creative suggestions and intelligent continuation units, we provide users with creative inspiration and help them generate new ideas and content during the text creation process.

[0020] Build a multi-functional rich text editor that integrates text processing, image processing, personalization settings, and creative generation, enabling collaborative work among modules and improving editing efficiency. Attached Figure Description

[0021] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a schematic diagram of the workflow of the text editing system described in an embodiment of the present invention. Detailed Implementation

[0022] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0023] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0024] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0025] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] Large language model-driven text editing systems include: The language processing module performs semantic understanding, grammatical error correction, vocabulary optimization, and content optimization on the main data input by the user. It generates subordinate data based on the processed main data and combines the subordinate data with the main data to create content. The editing interface is used by the user to adjust the created content; The image processing module searches for matching image data based on the content being created and performs image optimization processing on the image data; The personalization module is used to create options for adjusting the content in the editing interface; The creative generation module provides suggestions for generating subordinate data based on the main data.

[0027] The language processing module includes: The input receiving unit receives text data entered by the user in the editing interface; The semantic understanding unit performs semantic analysis on the input text using deep learning; The syntax correction unit is used to detect potential syntax errors and provide suggestions for correction. The vocabulary optimization unit provides vocabulary optimization suggestions based on text content and context; The content optimization unit is used to optimize the structure of text; The intelligent continuation unit generates relevant supplementary content based on user input.

[0028] The editing interface includes: The text input area is used for user interaction and to receive edited content. The layout settings area provides the content to be edited with layout parameters and corresponding options, including at least font, font size, color, line spacing, and paragraph spacing. The image insertion area is used to edit images within the content being edited; The preview area is used to display the results of editing content in real time after it has been processed by the layout settings area and the image insertion area.

[0029] The image processing module includes: The image search unit searches for matching images based on user input; The image optimization unit performs optimization processing on the output results of the selected image search unit, including at least color adjustment, contrast optimization, and sharpness enhancement.

[0030] Each unit of the personalization module is used to provide personalized adjustments to the editing interface, the personalized adjustments including: Create multiple fonts, text colors, background colors, and layout styles as options in the editing interface; provide domain options in the editing interface, and set a corresponding terminology library for each domain option.

[0031] The semantic understanding unit performs semantic analysis by representing the text by word vectors and modeling the contextual relationships; the intelligent continuation writing unit generates relevant supplementary content through generative adversarial networks and variational autoencoders.

[0032] The working process of the image search unit and the image optimization unit includes: The convolutional neural network is used to extract features from the text content input by the user and calculate the similarity with the features of the images in the image library to obtain image resources with a high degree of matching with the text content. The image selected by the user is processed by image processing algorithms to perform histogram equalization and color balance adjustment, and by generative adversarial network to perform style transfer and detail enhancement operations.

[0033] like Figure 1 As shown, in some embodiments, the structure and operation of the text editing system are as follows: Large Language Model Processing Module: The text input receiver captures the user's input data in real time when the user enters text in the editing interface and transmits it to the semantic understanding unit. The semantic understanding unit uses deep learning algorithms, such as Transformer, to encode the input text and extract text features, thereby achieving semantic understanding of the text; this process includes word vector representation of the text and modeling of contextual relationships. The grammar correction unit analyzes the text grammatically, constructs a syntax tree, and identifies potential grammatical errors. At the same time, it combines the results of semantic understanding to provide users with appropriate modification suggestions. The vocabulary optimization unit uses word embedding technology to find words that are highly similar to the input words based on the text content and context, and provides users with optimization suggestions such as synonym replacement and professional term recommendations. The content optimization unit optimizes the text structure, such as adjusting sentence order and optimizing paragraph layout, to make the text more in line with user needs. In addition, by analyzing the text's sentiment and logical relationships, it provides users with suggestions for enriching their expression. The intelligent continuation unit predicts subsequent text content based on the text content already entered by the user, using deep learning models such as generative adversarial networks (GANs) and variational autoencoders (VAEs), thus achieving intelligent continuation.

[0034] Editing interface: The editing interface provides users with an intuitive and easy-to-use operating environment. Users can input and edit text content in the text input area, and the layout settings area displays the current layout parameters in real time, which users can adjust as needed. The image insertion area allows users to insert images and perform simple editing operations. The preview area displays the layout effect of the currently edited text in real time, making it convenient for users to preview and adjust.

[0035] Image processing module: The AI ​​image search unit uses a deep learning model, a convolutional neural network (CNN), to extract features from the text content input by the user and calculate the similarity between the features and the image features in the image library to find image resources that match the text content highly. The AI ​​image optimization unit intelligently optimizes user-selected images. First, it preprocesses the images using image processing algorithms such as histogram equalization and color balance adjustment. Then, it utilizes a deep learning model, Generative Adversarial Network (GAN), to perform operations such as style transfer and detail enhancement to improve the overall visual effect of the images.

[0036] Personalization settings module: Font settings: The system has a variety of built-in font styles, and users can choose a suitable font according to their own aesthetic preferences; the system uses font rendering technology to apply the font selected by the user to the editing interface; In the color settings, users can choose text color, background color, etc.; the system applies the user's choices to the editor through the CSS style sheet style management mechanism. For layout style settings, the system provides a variety of predefined layout styles, each of which includes a complete set of layout rules, such as heading size and paragraph spacing. After the user selects a style, the system applies these rules to the edited text. The system allows users to customize or select preset terminology databases for their specific fields. These databases are integrated into the text input process, and the system automatically recommends professional terms as the user enters relevant content to enhance the professionalism of the text.

[0037] How the Creative Generation Module Works The Creative Suggestion section analyzes the text content entered by the user, combines semantic understanding from a large language model with creative prompts, and provides the user with possible creative directions and suggestions.

[0038] An electronic device includes a processor and a memory communicatively connected to the processor and used to store processor-executable instructions, the processor being used to execute the aforementioned text editing system.

[0039] A server includes at least one processor and a memory communicatively connected to the processor, the memory storing instructions executable by the at least one processor to cause the at least one processor to perform a text editing system.

[0040] A computer-readable storage medium storing a computer program that, when executed by a processor, implements a text editing system.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

[0042] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A text editing system driven by a large language model, characterized in that, include: The language processing module performs semantic understanding, grammatical error correction, vocabulary optimization, and content optimization on the main data input by the user. It generates subordinate data based on the processed main data and combines the subordinate data with the main data to create content. The editing interface is used by the user to adjust the created content; The image processing module searches for matching image data based on the content being created and performs image optimization processing on the image data; The personalization module is used to create options for adjusting the content in the editing interface; The creative generation module provides suggestions for generating subordinate data based on the main data.

2. The large language model-driven text editing system according to claim 1, characterized in that, The language processing module includes: The input receiving unit receives text data entered by the user in the editing interface; The semantic understanding unit performs semantic analysis on the input text using deep learning; The syntax correction unit is used to detect potential syntax errors and provide suggestions for correction. The vocabulary optimization unit provides vocabulary optimization suggestions based on text content and context; The content optimization unit is used to optimize the structure of text; The intelligent continuation unit generates relevant supplementary content based on user input.

3. The large language model-driven text editing system according to claim 1, characterized in that, The editing interface includes: The text input area is used for user interaction and to receive edited content. The layout settings area provides the content to be edited with layout parameters and corresponding options, including at least font, font size, color, line spacing, and paragraph spacing. The image insertion area is used to edit images within the content being edited; The preview area is used to display the results of editing content in real time after it has been processed by the layout settings area and the image insertion area.

4. The large language model-driven text editing system according to claim 1, characterized in that, The image processing module includes: The image search unit searches for matching images based on user input; The image optimization unit performs optimization processing on the output results of the selected image search unit, including at least color adjustment, contrast optimization, and sharpness enhancement.

5. The large language model-driven text editing system according to claim 1, characterized in that, Each unit of the personalization module is used to provide personalized adjustments to the editing interface, the personalized adjustments including: Create multiple fonts, text colors, background colors, and layout styles as options in the editing interface; provide domain options in the editing interface, and set a corresponding terminology library for each domain option.

6. The large language model-driven text editing system according to claim 2, characterized in that: The semantic understanding unit performs semantic analysis by representing the text by word vectors and modeling the contextual relationships; the intelligent continuation writing unit generates relevant supplementary content through generative adversarial networks and variational autoencoders.

7. The large language model-driven text editing system according to claim 4, characterized in that, The working process of the image search unit and the image optimization unit includes: The convolutional neural network is used to extract features from the text content input by the user and calculate the similarity with the features of the images in the image library to obtain image resources with a high degree of matching with the text content. The image selected by the user is processed by image processing algorithms to perform histogram equalization and color balance adjustment, and by generative adversarial network to perform style transfer and detail enhancement operations.

8. An electronic device comprising a processor and a memory communicatively connected to the processor and used for storing processor-executable instructions, characterized in that: The processor is used to execute the text editing system described in any one of claims 1-7.

9. A server, characterized in that: It includes at least one processor and a memory communicatively connected to the processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the processor to cause the at least one processor to perform the text editing system as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the text editing system of any one of claims 1-7.

Images