137 results about "Text editing" patented technology

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 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 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.

The invention discloses a model training method and device and an image processing method and device, and belongs to the technical field of image processing. The method comprises the following steps: acquiring a reference image data set; wherein the reference image data set is used for extracting a photography concept function, the photography concept function comprises an adjustment function and a weighting function, and the adjustment function is used for adjusting image colors and details; adjusting the initial diffusion model based on the photography concept function and a text editing instruction corresponding to the photography concept function to obtain an adjusted diffusion model; and training the adjustment diffusion model based on the training data set to obtain a target diffusion model.

A text editor or a plugin thereto automatically generates authorship tokens to identify content authored by a human author or an artificial author. The authorship tokens are applied to the work while the work is being produced. Thus, subsequent review of the work can identify regions produced by a human author and other regions produced by an artificial intelligence.

The invention discloses an online response system for online text editing, relates to the technical field of online response, and solves the technical problems of insufficient context understanding depth and subjective result integration decision. And establishing a scene-keyword mapping library and a three-dimensional sorting retrieval mechanism, optimizing a retrieval keyword by fusing context information in an associated scene so as to enable response to meet real-time requirements of a user, and avoiding a non-response condition through scene positioning and fuzzy association in a non-associated scene, so that the user experience is improved. A matching degree score, a knowledge base source authority degree, an interaction preference matching degree and a historical behavior tendency degree are incorporated into a scoring model, subjective rules are replaced by objective data, decision-making is dynamically performed based on score difference, decision-making deviation caused by a single index is avoided, the user recognition degree of a conflict processing result is improved, and the user experience is improved. And meanwhile, the credibility of the result is enhanced by processing the process traceability label.

Provided are improved machine learning-based text editing models. Specifically, example implementations include a flexible semi-auto-regressive text-editing approach for generation, designed to derive the maximum benefit from non-auto-regressive text-editing and autoregressive decoding. In contrast to conventional sequence-to-sequence (seq2seq) models, the proposed approach is fast at inference time, while being capable of modeling flexible input-output transformations.

1. The name of the design product: the main body of the dialogue graphical user interface of an electronic device. 2. The use of the design product: for an electronic device. 3. The design points of the design product: the protected part of the graphical user interface in the electronic device. 4. The picture or photo that best shows the design points: change state figure 1. 5. The use of the graphical user interface: the graphical user interface is used for dialogue. The protected part of the graphical user interface is used for dialogue and text editing. The graphical user interface can be interacted with by the user clicking on it or by operating the mouse or tapping the keyboard. The main view shows the main body of the graphical user interface, which includes an editing area on the left and a dialogue area on the right; by selecting part of the text in the editing area and clicking the "AI adjustment" button in the floating toolbar, the graphical user interface changes from the main view to change state figure 1; by selecting an option in the drop-down menu of the "AI adjustment" button, such as "a little richer", the graphical user interface changes from change state figure 1 to change state figure 2, and the selected text in the editing area is replaced by the text modified by AI adjustment. 6. Other circumstances that need to be explained: the part of the graphical user interface shown by the dashed line in each view does not constitute the protected part of the design.

A computer-implemented method for generating a control program for an automation system includes receiving input data for a control program of an automation system by a development environment, generating the graphical diagram of the graphical programming language based on the input data with the aid of a graphical editor unit, displaying the graphical diagram in the graphical editor unit, translating the graphical diagram into a textual intermediate representation of the graphical diagram by a translation module, displaying the textual intermediate representation of the graphical diagram in a textual editor unit, and generating the control program based on the textual intermediate representation of the graphical diagram, and / or based on the graphical diagram.

The invention discloses a legal text auditing method and device and a medium. The method comprises the steps of obtaining a to-be-audited legal text; extracting risk terms in the legal text based on a semantic analysis model; the risk terms are input into a legal knowledge graph for retrieval to obtain a first retrieval result, the risk terms are input into a vectorization case semantic library for retrieval to obtain a second retrieval result, and the legal knowledge graph comprises structural data of a plurality of legal provisions and relationships among the legal provisions; the vectorized case semantic library comprises vector data of a plurality of unstructured legal cases; and inputting the risk terms, the first retrieval result and the second retrieval result into a large legal text auditing model, so that the large legal text auditing model outputs an auditing result of the legal text. The method can dynamically adapt to the legal text, and can improve the accuracy of legal text risk identification and the text editing efficiency.

The application provides an editable presentation document automatic generation method, system and device, and the method introduces SVG as an intermediate description language to solve the problem that the output result of the prior art is a non-editable picture. By converting a PPT template into SVG code and combining a prompt word template, the SVG content generated by a large model contains semantic information and conforms to a preset visual style. A conversion mechanism is used to parse and convert the SVG code into editable objects in a standard PPTX file, so that the generated PPT document can maintain the visual effect while supporting text editing and graphic adjustment in mainstream office software. Compared with the prior art, the application can improve the efficiency of making a presentation, enhance the editability of the output file, and meet the personalized customization requirements.

The invention provides a document processing method and device, electronic equipment and a storage medium. The method includes; performing analysis processing on the unstructured document so as to obtain html (Hypertext Markup Language) data and css (Data Service) data of the unstructured document; performing feature extraction processing on the html data and the css data to obtain visual features, semantic features and structural features; and generating a constraint rule of the static reservation area, a constraint rule of the text editing area, a constraint rule of the media replacement area and a constraint rule of the data binding area based on the static reservation area, the text editing area, the media replacement area and the data binding area. According to the document processing method, the conversion effect from the unstructured document to the component can be improved, and the flexibility of component generation is improved, so that various requirements of a front-end framework are met.

An example method includes outputting a graphical user interface including: a graphical keyboard comprising a plurality of character keys, the plurality of character keys including two to eight character keys; a text-editing region; and a word-suggestion region. The method also includes detecting a first user input at a location of the presence-sensitive display associated with a particular character key from the plurality of character keys. The method further includes, responsive to detecting the first user input, determining a first character associated with the particular character key. The method additionally includes outputting the first character for display within the text-editing region and a set of suggested words for display within the word-suggestion region. The method also includes, responsive to receiving a transition input via an input device of the computing device, transitioning a focus region from a location of the text-editing region to a location of the word-suggestion region.

Systems and methods are directed to redacting and reinstating personal identifying information (PII) from text data. A PII management system accesses an input text and identifies, using one or more redaction components, PII mentions in the input text to be redacted. A placeholder manager of the PII management system replaces each unique PII string of a final set of PII mentions with a non-PII string to generate redacted text, whereby the non-PII string is generated by the placeholder manager. The placeholder manager also generates a mapping dictionary that maps each unique PII string to the non-PII string that replaces it. The mapping dictionary is used to reinsert one or more unique PII strings after processing of the redacted text. The redacted text is then transmitted to a downstream component for the processing.

The application relates to an RPA process design system based on a VS Code plug-in and belongs to the technical field of process automation. The system comprises a text editing module, a graphical parameter configuration module, an engineering management module and an execution adaptation module. The text editing module loads preset instruction libraries and method signature libraries, receives structured instructions, performs format checking and parameter completion, analyzes and generates a memory instruction sequence list; the graphical parameter configuration module listens to the instruction selection state, generates a parameter form, verifies the validity of input parameters, generates instruction-parameter data and stores the data into a to-be-processed data pool; the engineering management module generates a standard directory structure, performs version control and conflict detection; and the execution adaptation module extracts data and converts the data into an executable script and performs verification. The system can efficiently realize the design, management and execution of an RPA process, and improves the convenience and accuracy of robot process automation design.

1. The name of the design product: the main body of the dialogue graphical user interface of an electronic device. 2. The use of the design product: for an electronic device. 3. The design points of the design product: the protected part of the graphical user interface in the electronic device. 4. The picture or photo that best indicates the design points: change state figure 1. 5. The use of the graphical user interface: the graphical user interface is used for dialogue. The protected part of the graphical user interface is used for dialogue and text editing. The graphical user interface can be interacted by the user's click on the graphical user interface or by operating the mouse or tapping the keyboard. The main body of the graphical user interface shown in the front view includes an editing area on the left and a dialogue area on the right; by inputting a modification instruction in the input bar of the dialogue area, such as "the last paragraph is a bit flat, please increase vivid description, strengthen emotional expression, and appropriately describe some scenes", the graphical user interface changes from the main view to change state figure 1; by clicking the send button of the input bar in change state figure 1, the graphical user interface changes from change state figure 1 to change state figure 2, and the text paragraph corresponding to the modification instruction in the editing area is replaced by the text paragraph modified according to the modification instruction. 6. Other circumstances that need to be explained: the part of the graphical user interface shown by the dashed line in each view does not constitute the part claimed by the design.

The invention discloses a compact family structure text description grammar with high reduction degree. The compact family structure text description grammar comprises a family expression rule and an individual information expression rule. In the family expression rule, parents and children are defined as a group of family members, the parents, the parents and the children and the children are separated by different symbols, and after a group of family data is ended, different symbols are used for expressing ending description. The individual information and the information identifier in the individual information expression rule are respectively expressed by specific characters. The invention defines a structured plain text format for recording family pedigree. The core of the method is to imitate the layout of family trees: intergenerations are vertically distributed, and individuals of the same generation are horizontally aligned. The design has both human readability and machine processability, on one hand, data presentation is clear and visual, and lossless editing by using a text editor is supported; and on the other hand, compared with a traditional format, the data volume of the file is remarkably reduced, and the comfort level of user experience is improved.

The application designs a sensitive data prediction method based on user editing track in a collaborative editing scene, relates to the field of data security, and comprises the following steps: obtaining user historical text data, screening target text containing sensitive data, performing theme division, word segmentation, extracting keywords and position information to establish a text editing track; for each keyword of the text keyword set, a context window mechanism is adopted to select a sensitive word set and divide the sensitive word security level; according to the keyword editing clue, the theme label and the sensitive word set with the level division, a graph attention network is used to construct a user track model based on keywords; inputting the editing process text, identifying the keywords and labels, combining the received person role identity level, and inputting the track graph model to obtain a predicted sensitive word set. The application creates a model based on the user editing track, can accelerate the identification efficiency of sensitive data, reduce the risk of leakage, and improve the sensitive word identification accuracy under different text themes.

The present disclosure provides a document processing method and device, an electronic device and a storage medium. The method comprises: performing parsing processing on the unstructured document to obtain html data and css data of the unstructured document; performing feature extraction processing on the html data and the css data to obtain visual features, semantic features and structural features; and generating constraint rules of the static reserved area, constraint rules of the text editing area, constraint rules of the media replacement area and constraint rules of the data binding area based on the static reserved area, the text editing area, the media replacement area and the data binding area. The document processing method can improve the conversion effect from the unstructured document to the component and improve the flexibility of the component generation, thereby meeting the diverse needs of the front-end framework.

The application provides an application program determination method, an electronic device, a chip system and a readable storage medium, relates to the terminal field, the method is applied to a first electronic device, and the method comprises the following steps: a first interface is displayed, the first interface comprises a first region, the first region is used for editing a first rule, the first rule is used for filtering N application program identifiers to obtain M application program identifiers; in response to a first operation on the first region, a first executable program related to the first rule is generated, the first operation is a text editing operation related to the first rule, and the first executable program is used for being executed by the first electronic device, filtering the N application program identifiers to obtain the M application program identifiers. Therefore, the application can edit the rule for filtering and processing the application program in a visual manner, generate an executable program related to the rule, reduce the threshold for rule editing, and improve the efficiency of rule editing.

The invention provides a comprehensive system for monitoring and analyzing student engagement with AI tools across various educational platforms. It includes a Teacher Dashboard for real-time analytics on student interactions with AI tools. The system tracks human prompts, text edits, and interaction frequency, generating personalized feedback to ensure genuine learning. Teachers can manage large student enrollments, contact colleagues within the system, and utilize a Grading Assistance Tool that suggests grades based on an algorithm analyzing AI engagement and learning outcomes.

1. The name of the design product: text editing module of video creation graphical user interface of electronic device. 2. The use of the design product: the design product is used for an electronic device. 3. The design points of the design product: the part of the graphical user interface requested for protection. 4. The picture or photo that best indicates the design points: design 1 change state diagram. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: overall use: video creation interaction, partial use: the function of realizing quick text track creation and management through user operation change. 7. Other circumstances that need to be explained: the design protects the text editing module; design 1: the main view of design 1 is the display interface of the selected text track on the current timeline, the "new next sentence" option is selected, and the newly input text creates a new text track at the back end of the currently selected text track, as shown in the design 1 change state diagram; design 2: the main view of design 2 is the display interface of not selecting any text track on the current timeline, the "new next sentence" option is selected, and the newly input text creates a new text track at the back end of the nearest text track on the timeline, as shown in the design 2 change state diagram; the use state reference diagram is an effect diagram showing the user interaction interface, the main view of design 1 and the change state diagram correspond to design 1 use state reference diagram 1-2, and the main view of design 2 and the change state diagram correspond to design 2 use state reference diagram 1-2.

The invention discloses a content input method and device, electronic equipment and a storage medium. The content input method comprises the steps that a copywriting editing interface of a social application is displayed; a first operation in the copywriting editing interface is responded, generated copywriting content is displayed in the copywriting editing interface, and the copywriting content is generated according to interface content in the copywriting editing interface and the recognized current copywriting generation scene; and in response to a second operation for the copywriting content, filling the copywriting content into an input area in the copywriting editing interface. The method can improve the copywriting input efficiency of the user.

The application discloses a style visual text editing method, system, device and storage medium, which are corresponding solutions, and the related solutions aim to solve the style consistency problem existing in the image text editing of the existing diffusion model, extract style embedding information from the visual features of the glyph image and the input text image, and input the style embedding information as an enhanced style condition into the diffusion model, so as to realize fine control of the diffusion process, so that the diffusion model can generate a text image with high readability and style consistency, and can realize the keeping of the original text style or style migration based on a reference image.

The embodiment of the invention provides a voice editing processing method and device.The voice editing processing method comprises the steps that in the voice editing processing process, based on a voice text of dialogue voice input by a user in an interaction component of an application program, interaction action data of the user for the voice text are firstly obtained, and the interaction action data are sent to the interaction component; and detecting whether a voice editing intention exists or not according to the interaction action data and the interaction environment data, further determining an intention type of the voice editing intention when detecting that the voice editing intention exists, and displaying a voice editing identifier corresponding to the intention type on the interaction component. And acquiring a voice editing fragment collected after the voice editing identifier is triggered, and performing editing adaptation processing on the voice text based on the voice editing fragment, thereby realizing editing processing on the voice text by perceiving the voice editing intention.

Methods and systems for prompting a large language model (LLM) to process inputs from multiple user elements to generate a revised block of text are described. One or more text-editing instructions related to respective one or more selected text portions in a block of text are received. A prompt is generated for a LLM to generate a revised block of text, the prompt including at least a portion of an annotated block of text, the annotated block of text including each text-editing instruction inserted into the block of text relative to each respective selected text portion. The prompt is provided to the LLM and a revised block of text is received and outputted.

1. Name of the product in this design: Graphical User Interface for AI Content Creation in Electronic Devices. 2. Purpose of this design: An electronic device. 3. The key design feature of this product is its graphical user interface. 4. Images or photos that best illustrate the design points: Interface change state diagram 6. 5. Purpose of the graphical user interface: The graphical user interface of this product is used to realize the creation of novel chapters and other content. 6. Human-computer interaction method of graphical user interface: The main view is the main interface of the AI ​​content creation platform when the user enters; when a certain tag is clicked under the "Tags" module of the main interface, the interface jumps to the interface change state diagram 1. Click on "Volume 1" on the left side of the interface in Figure 1, and the interface will jump to Figure 2; move the mouse to "Volume 1" on the left side of the interface in Figure 2, and the interface will jump to Figure 3; click the "+" to the right of "Volume 1" on the left side of the interface in Figure 3, and the interface will jump to Figure 4; click on "Chapter Management" on the left side of the interface in Figure 4, and the interface will jump to Figure 5; click on "Batch Generate Chapter Outlines" in Figure 5, and the interface will jump to Figure 6; click on "Batch Apply Chapter Outlines" on the right side of the interface in Figure 6, and the interface will jump to Figure 7; move the mouse to the lower right corner of the second chapter text editing area in the middle of the interface in Figure 7, and the interface will jump to Figure 8; click the "One-Click Generate" button in Figure 8, and the interface will jump to Figure 9; swipe up on the text in the "Inspiration Card" section on the right side of Figure 9, and the interface will jump to Figure 10.

The invention provides a Word document generation method and system, electronic equipment and a storage medium. The method comprises the following steps: displaying a Web page containing a text editing area; obtaining input content and format requirements in the text editing area; judging whether the input content contains a structure identifier or not; if not, calling a semantic recognition model to perform structured analysis on the input content; if yes, performing hierarchical structure analysis on the input content according to a regularization rule and / or calling a semantic recognition model to perform structured analysis on the input content; and adjusting the input content according to the analysis result and the format requirement, and generating a Word document. Word document generation does not depend on a template, a fixed template does not need to be designed in advance, a text of a fixed structure does not need to be provided according to the template, a user can obtain the standard Word document by submitting the text of the free format through the Web page, operation is convenient and fast, universality is high, and flexibility is high.