381 results about "Text box" patented technology

The invention discloses an engineering drawing label identification method and system based on multi-modal information extraction, and the method comprises the steps: obtaining an engineering drawing image, carrying out the preprocessing of the image, and setting a data structure Schema for controlling an extraction target and a relation mode; detecting a drawing label area in the drawing through the trained drawing label detection model to obtain a bounding box coordinate of each drawing label, mapping the detected bounding box coordinates back to a coordinate system of the original image, and cutting out a corresponding drawing label image from the original image; performing text recognition on the cut-out signature image, and extracting text content and corresponding textbox coordinate information; and inputting the clipped signature image and the text recognition result into a trained multi-modal information extraction model, performing information extraction according to a set Schema, and outputting a structured extraction result. According to the method, the extraction target can be flexibly defined, unified extraction of the two-tuples and the three-tuples is supported, and the extraction accuracy is high.

Implementations relate to a drafting assistant that assists users in generating prompts for a language model that generates responses for text boxes for a web page. Implementations may receive a prompt from a user regarding an input for the text box, generate a modified prompt by incorporating contextual information identified from the web page, and provide the modified prompt to a generative language model, which generates a response for the modified prompt. The response is presented to the user and can be used as the input for the text box. Implementations dynamically engineer / enhance prompts based on the context of the web page, thereby facilitating more accurate and relevant responses from the generative language model.

The invention belongs to the technical field of document analysis, and particularly relates to a multi-algorithm collaborative PDF document intelligent analysis system which comprises a preprocessing module used for recognizing the type of a PDF document, performing layout correction on a scanning document PDF and uniformly adjusting the scanning document PDF into a vertical storage format; the layout analysis module is used for identifying page element categories based on a target detection algorithm, and processing element superposition and separation problems through a merging de-duplication or priority discarding strategy; and the text processing module is used for analyzing all places with characters in the PDF based on the OCR, outputting the characters and corresponding textbox coordinates, and dividing the contents of the text blocks in combination with layout analysis. The system can extract characters of the PDF of the scanned copy, distinguish element types such as titles, texts, tables and formulas, solve the problem of confusion of cross-page tables, column texts and characters with similar shapes, and can completely reserve the content structure of the document.

The invention relates to an RPA system based on natural language interaction and an implementation method thereof. The system comprises a user input module, an intention recognition module, a process planning module, an execution module, an inspection module and an output module. A user inputs a natural language instruction through a textbox or a microphone, the intention recognition module recognizes the intention of the user through an artificial intelligence large language model, and the process planning module plans an operation target and operation steps according to the intention of the user and a screen interface. The execution module controls the mouse and the keyboard to execute planned operation on the operation target through the technology related to automatic testing, the checking module checks whether the execution result meets the intention of the user or not after the operation is completed, and finally the output module feeds back the execution result to the user. According to the method, a common user can easily create a complex automatic process through a natural language, and the use threshold of an RPA system is greatly reduced.

The invention discloses a table data recovery method based on an OCR model, and the method comprises the steps: S1, recognizing table types through employing a lightweight model, and enabling the table types to comprise a wired table and a wireless table; s2, respectively acquiring a logic coordinate and a physical coordinate of a detection frame of the wireless table and a cell physical coordinate of the wired table; s3, recovering a logical structure of the table according to the detected table coordinates, and determining a row-column relationship of the table; s4, performing character recognition on the image by using a text recognition model, obtaining the position and content of a character box, performing accurate matching of characters and cells by calculating the coordinate overlap ratio of the OCR recognition character box and the cell box, and determining the character content in each cell; and S5, for the cells which are not matched with the characters, cutting the cell areas, carrying out secondary OCR identification on the image areas of the cells, and supplementing missing character contents. According to the method, the automatic identification and analysis capability of the complex table data is improved.

The invention discloses a rule and regulation intelligent question-answering method and device based on two-stage retrieval and a large model, and belongs to the field of rule and regulation file-based intelligent question-answering, and the method comprises the following steps: carrying out file abstract extraction on each file based on a large model question-answering form, and constructing an abstract vector library; cutting and partitioning all the files, respectively vectorizing text boxes of all text blocks by adopting a sparse vector model and a dense vector model, and constructing a content vector library; in the first stage, files most relevant to questions of a user are retrieved, two vector libraries are retrieved in a mixed retrieval mode, and weighted calculation is conducted on retrieval on the two sides to obtain the first K most relevant files; in the second stage, the text blocks most relevant to the questions of the user are retrieved, and the first k most relevant text blocks are obtained through mixed retrieval; and during answering, taking the first k most relevant text blocks as reference texts, and enabling the large model to answer based on the reference texts. According to the invention, more accurate answers can be generated.

The invention relates to a visual document information extraction method based on an attention correction graph neural network, and the method comprises the steps: firstly extracting entity node images, texts and layout features according to entities, text contents and textbox information, and obtaining n entity node indexes closest to each entity node in a document to generate an edge adjacency matrix; the entity node features and the edge adjacency matrix are input into a GraphSAGE graph network model to learn node features, graph convolution and an attention correction mechanism based on structural features are fused in the process, the edge weight is calculated and corrected according to node feature distance and degree information, feature representation is output after multi-layer graph convolution and correction operation, and the edge adjacency matrix is obtained. And inputting the full connection layer to complete node classification, sampling the document to obtain entity node pairs and edge features, and inputting the full connection layer to perform edge classification after fusion. According to the method, by means of the GraphSAGE model, multi-modal information is effectively fused, the node and graph structure characteristics are accurately captured, the node relation and weight are dynamically adjusted, and the entity node classification accuracy is remarkably improved.

The invention discloses a code generation method and device of a front-end component and a computer program product. Relates to the field of front-end development, and comprises the following steps: responding to a dragging instruction of a user, dragging a front-end component to a visual interface, responding to a configuration instruction of the user, configuring attributes, styles and events for the front-end component, and obtaining a configured front-end component, the front-end component comprising at least one of a button, a textbox, a card and a table; determining a first target data model of the configured front-end component, and generating a front-end code of the first target data model based on the component knowledge base and the code generator; responding to a natural language instruction for describing the business logic of the front-end component by the user, and inputting the natural language instruction into the large language model to obtain a front-end logic code of the front-end component; and determining the front-end code and the front-end logic code as target codes of the front-end component. Through the method and the device, the problem of low code development efficiency of the front-end component in related technologies is solved.

The invention discloses an image text recognition method and device, a computer program product and electronic equipment. The method comprises the steps of obtaining a to-be-recognized target image; a plurality of pre-trained neural network models are utilized to perform preprocessing operation on the target image, and the preprocessing operation at least comprises textbox detection, direction correction and textbox expansion; and performing text recognition on the preprocessed target image by using a pre-trained text recognition model to obtain corresponding target text content. The technical problem that the text content in the picture cannot be quickly and accurately recognized in the prior art is solved.

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 invention discloses a document content matching method and system based on multiple modes. The method comprises the steps of obtaining a to-be-recognized image and preprocessing the to-be-recognized image; performing picture direction correction on the preprocessed to-be-recognized image to obtain a corrected image; performing OCR character recognition on the corrected image and marking a textbox; performing text direction correction on the corrected image based on the textbox to obtain a corrected text; multi-modal document information extraction is carried out based on the corrected text, and modal complementary enhancement processing is carried out on the extracted multi-modal document information; and carrying out information matching on the processed multi-modal document information and returning a matching result. According to the method, the accuracy and practicability of multi-modal document information extraction and document content matching are remarkably improved by performing deep feature fusion, cross-modal association, modal complementarity enhancement, generalization ability, efficiency and the like on various data source features such as multi-modal text content and text position.

The invention provides a medical document semantic entity recognition method and system based on spatial semantic enhancement, and the method comprises the steps: detecting a text region in a medical document through an OCR technology, and extracting text content and bounding box coordinate information thereof; based on the spatial geometrical relationship between the textboxes, calculating the distance and angle between the textboxes, fusing the spatial semantic features with the text hiding state, and constructing a spatial-temporal feature matrix; through a multi-head attention mechanism, deep interaction is carried out on the fused geometric and text features, and the understanding of the model on the semantic relationship between the texts is further strengthened; and inputting the enhanced features into a classification head for accurately identifying and classifying semantic entities. According to the scheme, the spatial semantic information is introduced, so that the model can better understand the spatial layout of the text in the document, and the accuracy and robustness of multi-category semantic entity recognition in the complex medical document are remarkably improved.

The invention discloses a character recognition method and system based on a large model and an OCR technology, and relates to the technical field of character recognition, and the method comprises the steps: extracting picture information, carrying out the unified preprocessing, generating a text detection box of a character region through a DBNet lightweight text detection model, and obtaining a text position; quickly identifying characters in the textbox by using a lightweight OCR model to obtain text content, and generating an identification information group; carrying out average value calculation on the confidence coefficient of the lightweight OCR model result, and analyzing the overall confidence coefficient; and for the result with low confidence coefficient, inputting the corresponding identification information group into the multi-modal large model, and carrying out secondary identification. According to the method, the text position set and the text character string sequence are combined into the identification information group, so that the effect of structured storage of detection and identification results is achieved, subsequent information retrieval and multi-modal fusion analysis are facilitated, and the effect of optimizing the subsequent processing efficiency and precision is achieved through the combination of the confidence coefficient screening step.

The invention relates to the technical field of text recognition, in particular to a seal image-based text recognition method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a to-be-recognized seal image and a preset seal image text recognition model, inputting the to-be-recognized seal image into the seal image text recognition model, and carrying out the recognition of the to-be-recognized seal image. Performing textbox detection according to the to-be-recognized seal image and the target detection module to obtain a textbox detection image; classifying the plurality of initial textboxes according to the textbox detection image and a text classification module to obtain a textbox classification result; according to the textbox detection image, the textbox classification result and a text direction correction module, performing text direction correction on the plurality of initial textboxes to obtain a textbox correction image; and performing text recognition on the plurality of corrected textboxes according to the textbox corrected images and a text recognition module to obtain a text recognition result of the to-be-recognized seal image.

The invention provides a presentation file generation method and device based on a large model, electronic equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of intelligent office and large models. According to the specific implementation scheme, a theme input by a user is received, and then a target PowerPoint template matched with the theme is selected from a plurality of PowerPoint templates; a nested relation tree of the target PowerPoint template is obtained, the nested relation tree comprises a plurality of nodes and logic nested relations among the nodes, and each node represents a textbox included in the target PowerPoint template; and based on the theme and the nested relation tree, utilizing a large language model to generate text content conforming to the theme for the text box included in the target presentation file template, and filling the text content into the text box included in the target presentation file template to obtain the presentation file. The presentation file with more diversified text layout structures is generated.

Embodiments of the invention disclose a text detection method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a target scene image; determining an image entropy value and image texture complexity of the target scene image; obtaining target recognition precision and target recognition efficiency of the target scene image; determining n convolution layers and m textbox layers in a target neural network according to the image entropy, the image texture complexity, the target recognition precision and the target recognition efficiency; performing convolution on the target scene image to obtain n feature maps; acquiring m feature maps from the n feature maps; determining m initial frame sets of the m feature maps according to the target recognition precision, the target recognition efficiency and the scale corresponding to each feature map in the m feature maps; determining m first texts and m first backgrounds of the m feature maps according to the m initial frame sets; and determining a target text according to the m first texts, the m first backgrounds and the scale corresponding to each feature map in the m feature maps.

The embodiment of the invention discloses an architectural drawing signature character recognition and control method and device, equipment and a medium. A specific embodiment of the method comprises the steps of obtaining an original architectural drawing image; performing full-graph character perception detection on the original building drawing image to obtain coordinate information of a full-graph detection textbox; generating an image label ROI image based on the coordinate information of the total image detection textbox; self-adaptive direction correction is carried out on the picture label ROI image, and a picture label ROI image after direction correction is obtained; performing scale space transformation enhancement on the ROI image of the picture label after the direction correction to obtain an enhanced ROI image of the picture label; performing structured semantic analysis extraction on the enhanced drawing tag ROI image to obtain structured drawing metadata; and based on the structured drawing metadata, downstream physical equipment is controlled to execute associated automation operation. The implementation mode provides key technical support for digital management of the constructional engineering drawings.

The invention discloses a paragraph division method, system and device based on text semantic information fusion, a medium and a program. The method comprises the following steps: identifying a character image to be identified to obtain textboxes, traversing each textbox, and merging the textboxes into lines according to relative positions to obtain a position information merged text; according to the distance between the lines in the position information merging text, identifying the spatial position of the text, and according to an identification result, performing paragraph merging on the text lines to obtain a paragraph information merging text; performing text semantic information fusion processing on the paragraph information merging text based on a semantic analysis model to obtain paragraph text information; and traversing each row in the paragraph character information, and carrying out paragraph calculation layout to obtain divided paragraphs. According to the method, text fusion and paragraph division can be rapidly carried out, missing paragraph division is supplemented by combining semantic information of the text needing paragraph division, and the accuracy is improved.

A ship license plate detection method based on multi-scale feature fusion and an attention mechanism comprises the following steps: firstly, collecting ship license plate data of a real scene, and preprocessing an image to obtain standardized image data; a LabelImg labeling tool is adopted to label the picture, a labeled textbox is a quadrilateral box, and a structured ship license plate detection data set is generated; and constructing a ship license plate detection model based on multi-scale feature fusion and an attention mechanism, inputting an obtained data set into a network for training, and performing detection by adopting the trained model. According to the invention, the condition of leak detection of the ship license plate is effectively reduced, and the detection accuracy is improved.

The invention discloses an ancient book text detection method based on a joint enhanced feature pyramid network, and the method comprises the steps: collecting an original image and a corresponding textbox label from an ancient book document image detection data set, and dividing the original image and the corresponding textbox label into a training set and a test set; constructing a joint enhanced feature pyramid network, wherein the joint enhanced feature pyramid network comprises a character structure extraction module and a dual-path fusion module; an ancient book text detection network model is constructed based on the joint enhanced feature pyramid network, the ancient book text detection network model comprises an encoder, a decoder, a classification head and a detection head, and the joint enhanced feature pyramid network is adopted in the decoder; inputting the preprocessed ancient book document images in the training set into an ancient book text detection network model for training; and inputting ancient book document images in the test set into the trained ancient book text detection network model, generating character box position information, and performing character cutting for evaluation. According to the invention, high-precision ancient book text detection is realized.

In various embodiments, systems and methods for design-aware replacement font suggestions are provided. In some embodiments, a substitute font-suggestion algorithm holistically considers how the original string of text from the original layout appears when re-rendered in a same-sized text frame using a potential replacement font. In some embodiments, the substitute font-suggestion algorithm generates a first image of a text frame including the text string using the first font and generates a plurality of second images of the text string using candidate replacement fonts. A ranking of the candidate replacement fonts is generated based on computing a score for each of the individual second images that represents similarity between the first image and the individual second images. Based on the assessed similarities, a ranked listing of substitute font suggestions is displayed.

The invention relates to the technical field of artificial intelligence, and discloses a paper text processing method based on intelligent glasses. The method comprises the steps that intelligent glasses are awakened through an awakening word, a user can conduct image recognition through a voice instruction, and whether a textbox is complete or not is judged. If the textbox is complete, character recognition is carried out; if not, the intelligent glasses help the user to adjust through voice guidance until the textbox is completely displayed. If the recognized characters are not the language set by the user, the intelligent glasses automatically translate the recognized characters into the user language, and voice synthesis is carried out to generate a voice file. And after generation, inquiring the user whether to play the voice, and if not, encrypting and storing the voice file. The problems that current text detection precision is not high, the reading process is not natural, user control is complex, and a feedback mechanism is single are solved.

The present disclosure relates to a detection model training method and apparatus, and a text bounding box detection method and apparatus. The training method comprises: inputting into a detection model to be trained a sample image carrying a text label, wherein the text label comprises a reference text bounding box and a reference probability value of a preset deletion symbol being drawn on text within the reference text bounding box; performing detection on the sample image by means of the detection model, so as to determine a text detection result of the sample image, wherein the text detection result comprises a predicted text bounding box and a predicted probability value of the preset deletion symbol being drawn on text in the predicted text bounding box; and on the basis of a target loss function, converging the text detection result and the text label, so as to obtain a trained detection model, wherein the target loss function comprises a first loss function used for evaluating the accuracy of the predicted text bounding box, and when the overlap ratio between the predicted text bounding box and the reference text bounding box is in different overlap ratio intervals, the first loss function is configured with penalty terms of different weights.

The invention belongs to the technical field of retrieval enhancement generation. According to the title and entity retrieval-based multi-document knowledge graph question and answer method and system, each document is analyzed to obtain a title set, a table set and a text block set corresponding to each document; generating a plurality of simulation question and answer pairs based on the number of characters of each textbox in the text block set, and performing entity extraction and relation extraction on the simulation question and answer pairs by adopting a large language model to obtain an entity set and a relation set; constructing a title layer according to the title set and the title hierarchical structure, constructing a text block layer according to the text block set and the table set, and constructing an entity network layer according to the entity set and the relation set; determining a sub-knowledge graph of each document according to the title layer, the text block layer and the entity network layer, and determining a multi-document knowledge graph according to the sub-knowledge graph of each document; determining question answers according to the query questions and the multi-document knowledge graph; according to the method and the device, cross-document information reasoning is realized, and question answering precision is improved.

The invention provides a table restoration method and device based on optical character recognition, which are used for respectively carrying out structure recognition on rows and columns of a table and recognizing texts in the same row by utilizing text detection, so that a row textbox is recognized more accurately, and more accurate table structure restoration is realized. Comprising the steps that firstly, textbox detection is conducted on input data to obtain a scanning result, the input data can specifically comprise images or other unreadable documents and the like, the input data comprises an input table, and the scanning result comprises information of at least one textbox in the input table; the information comprises coordinates, length, width or area of a textbox; performing text detection on the at least one textbox to determine a row textbox, and determining a column textbox according to the at least one textbox; the row textbox and the column textbox are then merged to obtain an output table, which is generally a readable table.

The invention discloses a text recognition method, a model training method, equipment and a storage medium, and relates to the technical field of optical character recognition, and the method comprises the steps: obtaining a sample image, and corresponding label textbox information and label text information; inputting the sample image into the single vision model and the residual network model to obtain first sample textbox information and first sample text information; inputting the sample image and the processing requirement into a multi-modal AI large model to obtain second sample textbox information and second sample text information; determining a distillation loss value according to the label textbox information, the first sample textbox information, the second sample textbox information, the label text information, the first sample text information and the second sample text information so as to update parameters of the text recognition model; and inputting the to-be-recognized image into the text recognition model to obtain a text recognition result. According to the method, the generalization ability of text recognition can be improved, and the application scene of text recognition is expanded.

Optical character recognition data for an image is used to generate a text box. The text box is formed to include text that has a colour and font determined based on analysis of the image. The colour may be determined using k-means clustering and the font determined using a trained image classification model. The text box may be located over the image at a location corresponding to the detected text in the image. The image may be inpainted at the location of the text box to remove the detected text from the image.

The invention relates to the technical field of electric energy meter full-automatic verification assembly lines, and discloses an electric energy meter intelligent visual detection method and system, and the method comprises the steps: monitoring the in-place state of a full-compatible tray in real time, and automatically adjusting the full-compatible tray to the optimal recognition height; a high-precision positioning device is used for accurately positioning the tray; the control system starts the compatible wire connecting and disconnecting mechanism, completes wire connection with the electric energy meter, triggers the electric measurement system to power on the electric energy meter, and lightens the liquid crystal screen; a space attention mechanism is introduced, automatic textbox recognition is carried out, an obtained image is detected through a detection model and compared with a standard template, and the qualification of the electric energy meter is judged; and the electrical testing system is powered off and performs self-inspection, the tray is reset and released, and appearance inspection of the electric energy meter is completed. The method is reasonable in design, simple in assembly, easy to debug, stable in operation, high in recognition speed and high in accuracy, the economic cost can be reduced, and the utilization rate of a special machine is improved.

The invention relates to the technical field of photovoltaic panels, in particular to a decommissioned photovoltaic panel label identification method, which comprises the following steps: acquiring an image of a decommissioned photovoltaic panel, and constructing a data set; obtaining a character image area in the photovoltaic panel label by using the network detection model, and generating a character textbox; correcting the text box image containing the characters; identifying and expanding lines of the keyword textbox by utilizing a dynamic line threshold value; converting an image coordinate of the expanded keyword textbox into a pixel coordinate, and cutting the expanded keyword textbox according to a boundary value of the pixel coordinate to obtain a sub-image of the expanded keyword textbox; and extracting characters in the sub-images of the expanded keyword textbox by using a character recognition model. According to the method and the device, the problem that the character recognition model cannot accurately recognize the keywords due to the fact that the recognition frames of the keyword tags are serial during extension is solved.

The invention relates to the technical field of data generation, and discloses a training content generation method and system based on a deep learning model and a storage medium, and the method comprises the steps: obtaining basic content data, and extracting text, table and format content to generate structured data; identifying a content structure and extracting training knowledge elements through deep learning model semantic analysis, and constructing a knowledge graph in combination with an association relationship between the elements; calculating the occurrence frequency, the content chapter and the core degree of the training knowledge elements to obtain a difficulty coefficient; obtaining training parameters, calculating a knowledge coverage coefficient and a knowledge depth coefficient, and generating initial content in combination with the first text framework and the large language model; and performing full-content verification and correction through the second text framework to obtain training content. According to the method, the training content is automatically generated, the problems of low efficiency, high cost, unstable quality and the like of manual question setting are solved, and the scientificity and pertinence of the training content are improved.