386 results about "Text editing" patented technology

The invention relates to the technical field of semantic recognition, can be applied to business scenes such as financial science and technology and medical health, and discloses an interactive code generation method, device and equipment and a medium. And a visual preview interface is generated in combination with the context, multi-round modification through interactive adjustment or text editing is supported, and finally user interface element codes are generated. According to the method, natural language processing, context sensing and visual interactive correction are combined, so that the closed-loop process of interface codes from generation to dynamic adjustment is realized, the customization degree and the service adaptability of a generated result are improved, and the problems that an existing tool template is rigid, semantic understanding is deviated, and a multi-round correction mechanism is lacked are solved.

The invention provides a method for editing facial image attributes based on a text of a diffusion model. The method realizes flexible facial editing with high quality and identity consistency. The method comprises the following steps: constructing a description control face diffusion model comprising a noise prediction network and a variational auto-encoder, wherein the noise prediction network comprises a plurality of text alignment face Transform modules and an optimization residual feature module; the method comprises the following steps: inputting an original image and target text description based on a pre-training model, optimizing a target embedding generated by the input target text description by a text alignment face Transform module to obtain an optimized embedding, and performing model fine tuning after optimization is completed; and performing linear interpolation on the target embedding and the optimized embedding to obtain an initial editing result, introducing ArcFace-Loss as identity loss, extracting face features of an original image and the initial editing result through a pre-training model, calculating feature similarity and minimizing the loss, and ensuring consistency of face identities after editing.

The invention discloses an instruction-driven personalized fashion image editing method. The method comprises the following steps: 1, defining categories of editing tasks, and constructing an original image-reference image-target image-text editing instruction quaternary data set for different editing tasks; 2, constructing a target semantic network, generating target image semantic information following an editing instruction and an original image, and taking the target image semantic information as human body semantic information of an editing model; 3, constructing a unified editing network, including constructing a semantic control network, adding a visual joint module and applying a low-rank fine tuning module, so that a plurality of editing tasks use the same framework to obtain corresponding editing capabilities; and 4, constructing a multi-task low-rank adjustment module, and enabling the framework to have the capability of aligning different editing instructions to different editing tasks through joint training. Finally, an independent and unified framework among different tasks is realized. According to the method, experiments are carried out on a constructed specific data set, and good results are obtained in both quantitative and qualitative aspects.

The embodiment of the invention provides an image editing and model training method and device, a storage medium and a program product. In the embodiment of the invention, an image-text editing model is provided, image editing is carried out on a target text area of an original image from a font dimension and a style dimension, guarantee is provided for the accuracy of image editing through text coding features and character morphological features in the font dimension, and the consistency with a background is kept; in the style dimension, by injecting text style features, the original image style and additional styles are kept, and the availability rate of image editing is improved. Image editing is carried out from the two dimensions of font and style, and the image quality of the obtained image can be improved. Furthermore, in the layout dimension and model training process, local and transverse and longitudinal modification of various alignment modes is supported through a layout loss function and adaptive learning layout information, and the image quality is further improved.

The invention discloses an image-text content management method based on a React framework, and belongs to the field of React, and the method comprises the following steps: creating a project through create-react-app, installing a dragging function, an API request, a rich text editor and other dependencies, and building a Node. Js-based RESTful API and MongoDB database for storing image-text content and layout information. And creating text, picture and container components, supporting dynamic rendering and dragging functions, and updating page preview in real time through React state management. The rich text editor supports picture insertion, style modification and storage in a JSON format. And after the user drags or edits, the state is updated, the data is sent to the server through the API, and the back end analyzes and updates the database. When the page is loaded, the content is dynamically generated, the component is loaded as required, and the performance is improved by using a virtual rolling technology. And a test is compiled through Jest and React Testting Library, so that the correctness of the function is verified. The front end is deployed to Netlife, and the rear end service is deployed to AWS.

The invention discloses an engineering design document compliance inspection method, electronic equipment and a storage medium, and the method is based on an OCR and a large language model, and comprises the following steps: standardizing the character recognition and extraction of a document; standardizing character error check and manual correction of the text; performing structured processing on the corrected standard text; vectorization processing of core text content and construction of a standard query system; presetting a specification set range corresponding to each chapter of the design document; carrying out vectorization and similarity query on characters selected by a user in the text editor; corresponding standard content is provided for the user; the method can improve the efficiency and accuracy of specification reference in the document, facilitates the dynamic update management of specification contents, and facilitates the guarantee of the correctness of reference specifications.

The invention provides a human face living body detection method and device. The method comprises the following steps: acquiring a to-be-recognized human face image; inputting a to-be-recognized face image into the trained face anti-counterfeiting model, and obtaining a judgment result of face living body detection output by the face anti-counterfeiting model; the face anti-counterfeiting model comprises an inherent content cue word extraction module, a first text editor, an image encoder, a learnable content cue word extraction module, a second text editor, a cross-modal guide module and a classifier. According to the face in-vivo detection method and device provided by the invention, the instance-level composite prompt is generated by combining the fixed template and the learnable prompt, and feature fusion is dynamically adjusted by using the cross-modal guide module, so that the generalization ability of a face anti-counterfeiting system in an unknown field is improved, and the accuracy and reliability of face in-vivo detection are improved.

A data processing system implements receiving a user marking of a textual area in a graphic design image; constructing a prompt including the image, the marking, and instructions to a generative model to identify character(s) in the area, to determine design context attribute(s) of the character(s) with respect to the image, and to create a new image based on one changed design context attribute, the attribute(s) including a character design and semantics of the character(s), and a position of the area in the image; providing the prompt to the model and receive the character(s), the attribute(s), and the new image; providing the character(s), the attribute(s), and the new image to a client device; and causing the client device to display at least one of the new image or an editable text box over the area in the image, the box showing the character(s) based on the attribute(s).

The embodiment of the invention provides a text processing method and device, electronic equipment and a storage medium. The method comprises the steps that in response to a text adding triggering operation, an added to-be-processed text is displayed in a text editing interface through a first typesetting path, and the to-be-processed text comprises a plurality of text characters; in response to a character typesetting trigger operation input for the to-be-processed text, determining a to-be-typeset text corresponding to the to-be-processed text and a second typesetting path corresponding to the to-be-typeset text, the to-be-typeset text being a text composed of partial or all text characters in the to-be-processed text; the to-be-typeset text is displayed in the text editing interface through a second typesetting path, and the first typesetting path and / or the second typesetting path comprise at least one curve path. According to the technical scheme, the typesetting path of the to-be-processed text can be simply and conveniently adjusted, diversified presentation of the text typesetting style is achieved, and the visual effect of the text is enriched.

The invention discloses a writing assistance method and device and a storage medium, and the method comprises the steps: reading a file name of a patent-related text, the file name comprising a file identifier, and the file identifier being associated with writing reference information of the patent-related text; acquiring the writing reference information associated with the file identifier; wherein the obtained writing reference information is displayed while the content of the patent related text is displayed. The information support capability of text editing can be improved, and the working efficiency is improved.

The invention discloses a stylized visual text editing method, a stylized visual text editing system, stylized visual text editing equipment and a storage medium, which are corresponding schemes, and the related schemes aim to solve the problem of style consistency existing in image text editing of an existing diffusion model, and the stylized visual text editing efficiency is improved by combining visual features of a font image and an input text image. The method comprises the following steps of: extracting style embedded information from a text image, and inputting the style embedded information as an enhanced style condition into a diffusion model to realize fine control on a diffusion process, so that the diffusion model can generate a text image with high readability and style consistency, and can realize maintenance of an original text style or style migration based on a reference image.

The invention relates to the technical field of small sample image classification, in particular to a small sample classification method for multi-granularity image-text prototype matching based on a task-driven structure. The method comprises the following steps: constructing a support set and a query set; inputting the two features into a multi-granularity feature set extraction network, and extracting low-level, middle-level and high-level image features by a multi-level image feature extraction network consisting of an image modal input improved ResNet12 and an embedded task-driven mapper selection module; the text mode calls a large language model (LLM) three times successively to progressively generate word-level, sentence-level and paragraph-level semantic descriptions, and a text editor is combined to form multi-view text features; the image and text feature set is input into a semantic graph interactive fusion network, and multi-level information fusion is realized through node and edge construction, cross-modal attention, graph convolution and a gating mechanism; the matching score of each layer is calculated through the fusion features through a multi-granularity prototype matching network, so that classification prediction is carried out, and the performance of the model is optimized by adopting a multi-granularity composite weighted loss function in a training stage.

The invention relates to a document processing method and device based on rich text data, computer equipment, a medium and a product. The method comprises the following steps: analyzing HTML (Hypertext Markup Language) contents in a rich text editor to obtain an HTML node tree; determining a document storage component and a style definition component of the template document according to the document format standard definition; traversing nodes of the HTML node tree, and mapping the nodes to a document storage component and a style definition component to obtain a document storage structure and a document style structure under the document format standard definition; and based on the document storage structure and the document style structure, generating an XML document under the document format standard definition, and processing the template document according to the XML document to obtain a target document. By the adoption of the method, data security can be guaranteed, the rich text editor content or the webpage content can be flexibly supported to be converted and inserted into the Word template, meanwhile, the template predefined style is reserved, and therefore the document requirement under the multi-service scene is met.

The present disclosure provides an image generation method and a related device. The method comprises: displaying a text editing area and an image effect setting control on an image display interface; in response to editing text content in the text editing area, determining a target prompt on the basis of the text content; in response to an operation on the image effect setting control, determining at least one target parameter; and on the basis of the target prompt and the target parameter, displaying a generated target image in a first display area of the image display interface.

The invention provides an intelligent speech recognition editor capable of efficiently processing large-scale texts. Belongs to the technical field of speech recognition and text editing. The editor comprises a voice recognition module which is used for receiving audio input, converting the audio input into a text and transmitting the text to a front end in real time through WebSocket / SSE; the text editing module is used for rendering and editing a text through a WebAssembly + virtualization technology; the data storage module is used for carrying out text caching by using IndexedDB / Local Storage; and the front-end UI interaction module is used for carrying out task distribution by adopting React / Vue in combination with WebWorker. According to the method, only the currently visible text area is rendered by adopting a block rendering technology and a virtualization technology, and the historical text is loaded as required in a lazy loading mode, so that the processing of million-level characters can be easily supported, and smooth operation and no blockage of an editor are ensured.

The invention discloses a rich text editing content isolation rendering method, device and system and a storage medium, and relates to the technical field of data processing. The method comprises the steps of obtaining rich text content, and preprocessing the rich text content to obtain preprocessed content; judging browser compatibility, and selecting an isolation rendering method according to the browser compatibility; and performing isolated rendering on the preprocessed content according to the isolated rendering method. By adopting the rich text editing content isolation rendering method provided by the embodiment of the invention, correct and consistent rendering effects of the rich text content on different browsers can be ensured, and the rich text content is effectively isolated from other page elements, so that potential safety risks are avoided, and the user experience is improved. According to the embodiment of the invention, the condition that the content is cut off or a scroll bar appears is avoided, the click experience of the user can be further optimized, and unnecessary page redrawing and rearrangement are reduced, so that the rendering performance of the page is improved, and the difficulty of subsequent maintenance and modification is reduced.

The present disclosure relates to systems, methods, and non-transitory computer readable media for utilizing a diffusion prior neural network for text guided digital image editing. For example, in one or more embodiments the disclosed systems utilize a text-image encoder to generate a base image embedding from the base digital image and an edit text embedding from edit text. Moreover, the disclosed systems utilize a diffusion prior neural network to generate a text-image embedding. In particular, the disclosed systems inject the base image embedding at a conceptual editing step of the diffusion prior neural network and condition a set of steps of the diffusion prior neural network after the conceptual editing step utilizing the edit text embedding. Furthermore, the disclosed systems utilize a diffusion neural network to create a modified digital image from the text-edited image embedding and the base image embedding.

The invention provides a text editing optimization method and device, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of document editing. According to the specific implementation scheme, a to-be-optimized editing text is obtained, wherein the to-be-optimized editing text comprises a formula character string edited by a user; segmenting the formula character string to obtain a symbol sequence; performing grammatical analysis on the symbol sequence according to a preset grammatical rule to construct an abstract syntax tree; and performing semantic analysis and processing on the abstract syntax tree to obtain an optimized formula character string. According to the method and the device, the syntactic analysis and the semantic analysis are sequentially performed after the formula character string is segmented, so that the code format of the formula character string is automatically adjusted to meet the specification, the optimized character string structure is more rigorous, the layout is clearer, and the readability and the maintainability of the formula character string are improved.

The invention relates to the technical field of generated image editing, and provides a text-guided generated image editing method, which comprises the following steps of: firstly, performing multiple reasoning on an image generated by a given stable diffusion model by utilizing a multi-modal pre-training model BLIP model to generate a plurality of corresponding detailed text descriptions; then, performing intelligent text editing on a description text needing to be edited by using ChatGPT, and modifying a specific visual concept so as to meet a specific editing task for guiding an image; then, a CLIP model is used for calculating text embedding vectors before and after editing, so that the average direction of text editing is obtained; then, the average direction of text editing is added to an original description text embedding vector, the corresponding relation between the text and the image is controlled based on a cross attention mechanism of a stable diffusion model so as to accurately control the text guiding editing process of the image, and based on the average semantic direction of multiple sentences, robustness is achieved, and high isolation is achieved.

The invention relates to an auxiliary editing method and system based on a rich text editor, and the method comprises the steps: selecting a text in response to the rich text editor, obtaining the selected text, adding a label, and displaying operation options, including "searching through a learning library" and "intelligently generating a picture"; in response to the operation option selected by the user, executing a corresponding auxiliary editing process; when the user selects'retrieval through the learning library ', calling a learning library service interface, querying by taking the tag text as a keyword, outputting a matched field, and displaying a'replacement' operation option; when the user selects'intelligent picture generation ', calling an AIGC question and answer interface to generate a picture, and displaying an'insertion' operation option; and in response to a replacement or insertion option selected by the user, matching the position information of the tag text through the regular expression, and replacing the tag text with the to-be-replaced field or inserting a picture behind the tag text. According to the method, the accuracy and flexibility of content editing are improved, and the method is suitable for various editing scenes.

A computer-implemented process is programmed to detect a type or category of document that is being drafted and to suggest one or more phrases or sentences to add to the original and / or substitute for the original, the suggested text being potentially more personable and sincere than the writer's original text. Suggested text phrases are selected from a large corpus of previously manually drafted sentences and phrases. Selected text phrases are ranked and filtered to result in suggesting a manageable set of text phrases. With this approach, adding specially chosen content to existing content can change the warmth or tone of the text while preserving its meaning. Unlike prior approaches, in an embodiment, the process is programmed to artificially understand the intent of the original text as a basis of suggesting other content to add. Furthermore, embodiments may interoperate with a visual or graphical user interface that is programmed to enable users to see what the change to the text will be and whether they want it before they engage with the suggestion.

The invention discloses an intelligent vehicle elastic planning and control method based on large language model guidance under network attack, and belongs to the field of vehicle information safety and control, and the method specifically comprises the steps: firstly, building an intelligent vehicle auxiliary decision making and control system, and installing the system on a to-be-detected vehicle; the automatic driving decision-making unit generates an expected driving intention of the current to-be-detected period; the path planning unit generates a corresponding reference trajectory sequence. A vehicle reachable set estimator calculates a maximum allowable motion reachable range. The scene text editor completes scene description of the driving environment in combination with the perception information and converts the scene description into a structured text; the large language model performs comprehensive judgment on an expected driving intention and a planned reference trajectory sequence based on a maximum allowable motion reachable range and structured text description, and gives a final auxiliary decision variable. And based on the reachable set estimation value, constructing a vehicle motion controller based on data driving, and obtaining a control instruction to complete execution. According to the invention, the adaptability and robustness of the real vehicle operation environment are improved.

The invention provides a rich text editor component, a structured exporting method and a content editing system, and relates to the technical field of computers. According to the method, a componentization packaging module is used for packaging a rich text editor core library into a single file component based on a front-end componentization framework and completing initialization and destruction of an editor instance in the life cycle of the single file component; the attribute parameter module is used for defining and receiving configuration parameters from the upper calling component, and the configuration parameters at least comprise an editor mode type, a content export format and a remote content address; the core logic module is used for realizing key operation logic of the editor; and the business editor module is used for calling the rich text editor component in a declarative mode in a business application page, so that rapid integration without compiling bottom layer codes is realized. According to the embodiment of the invention, the development efficiency and function flexibility of the rich text editor can be improved.

Systems, methods and non-transitory computer readable media for editing user interfaces from free text and / or sketches are provided. Digital data associated with a design of a user interface may be received. A presentation of the user interface based on the design may be caused. A selection of a portion of the user interface may be received. A textual input in a natural language and / or a sketch may be received. The textual input and / or the sketch may be analyzed to determine at least one change to a portion of the design of the user interface corresponding to the selected portion of the user interface. The determined at least one change may be implemented to generate a modified design of the user interface. A second presentation of the user interface based on the modified design may be caused.

The embodiment of the invention discloses a cross-platform rich text editing method, which comprises the following steps: identifying an input device, predefining a typesetting rule and a rendering rule based on a programming language, packaging a programming code, and loading the programming code into a browser of a corresponding type of the input device; configuring an input method and shortcut key logic matched with the input equipment according to the programming code, and simulating an interaction effect based on the browser and the input equipment by utilizing a webpage canvas tool; obtaining character information input by a user through the input device, analyzing the character information through the typesetting rule, obtaining the typesetting rule of each piece of character information, and dynamically adjusting the line feed rule, the paragraph alignment mode and the line height of the character information according to the size limitation of the current editing area; user operation events are monitored in real time, and typesetting and rendering results are updated. According to the method and the device, cross-platform rich text typesetting and rendering functions are realized by pre-defining typesetting and rendering rules.

Systems and methods are provided for generic text-driven image editing, and example implementations of these systems and methods may be referred to as' UniTune '. The UniTune may receive any image and text edit description as input, and may perform edit while maintaining high semantics and visual fidelity of the input image. The UniTune does not require any additional input such as a mask or sketch. According to one aspect of the present disclosure, by properly selecting parameters, an example system described herein may fine-tune a large diffusion model (e.g., Image) on a single image, causing the model to visually and semantically remain fidelity to the input image while still allowing expressive operation.

The present disclosure describes a technical solution that enables a trained large language model (LLM) to generate a revised text in a manner that enables the LLM to preserve formatting that was present in the original text. When a text-editing instruction is received for a text passage having a formatting tag, the text passage is processed to identify the formatting tag in the text passage. The LLM is prompted to generate a revised text passage, using a prompt that includes the text-editing instruction and that also includes a formatting-specific instruction to format the revised text passage using the formatting tag in the revised text passage. The revised text passage is received and caused to be displayed based on the formatting tag, such that the formatting of the original text is maintained.

To provide a verification apparatus, a verification method, and a verification program that are capable of verifying contents of sentences such as outputs of large language models, which superficially appear to be natural but include false contents, and performing appropriate processing.SOLUTION: A verification apparatus 64 includes: a text selection unit 132 that extracts a verification target portion from an inputted text; a support network creation unit 134 and a contradiction network creation unit 136 that are for collecting, from a set of existing texts, a support text that supports contents of the verification target portion and a contradiction text that contradicts the contents of the verification target portion; and a text editing device 108 that selectively executes, on the basis of whether or not a prescribed relationship is established between the support text and the contradiction text that are collected, processing for maintaining the verification target portion and processing for editing the verification target portion.SELECTED DRAWING: Figure 1

The invention relates to the technical field of data processing and report generation, in particular to a reasonable drug use report generation method and system combined with artificial intelligence. The method comprises the following steps of: selecting a report type; constructing a report analysis model and analyzing report data; intensively analyzing report data by utilizing a domain knowledge graph; generating a structured report; according to feedback information of the user, an algorithm for report analysis and report generation is optimized; editing a data part and a conclusion part of the report by utilizing the two rich text editing areas; rejecting report contents which do not need to be displayed; and exporting a final editing result. In combination with an artificial intelligence technology, the method is used for automatically analyzing report data and generating a report, so that the analysis efficiency and accuracy are improved; by introducing a self-learning mechanism, a report analysis and generation algorithm is optimized, and the report generation quality is improved; by providing a friendly interface and a rich editing function, personalized requirements of different users are met, and the method has a wide application prospect in the medical field.

The invention relates to an image processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps of determining a to-be-recognized image in response to an image recognition trigger event; when the to-be-recognized image comprises a text image, a same-screen display image area and a text editing area; the to-be-recognized image is displayed in the image area; displaying an editing guide prompt for the text editing area; the editing guide prompt is used for indicating to edit a text included in the text image in the text editing area; in response to a text editing event triggered for the text editing area, displaying a text obtained by editing in the text editing area; and in response to a text editing completion event, obtaining an identification text of the to-be-identified image, the identification text including the text obtained by editing. By adopting the method, the flexibility of image recognition can be improved.