2247 results about "Image content" patented technology

The present invention provides a screenshot content extraction method based on a multimodal large model, which is used to extract OTA hotel structured information, including the following steps: obtaining a screenshot image with hotel information; performing text recognition on the image through an optical character recognition model to obtain a text information box set; performing text area positioning on the image through an image positioning model, and extracting the text content of the text area to obtain a text content set; inputting the text content set into a text large model, extracting structured information through preset prompt words, and obtaining first structured information; inputting the image into a visual language model, extracting structured information through prompt words, and obtaining second structured information; comparing and fusing the first structured information and the second structured information to obtain hotel structured information. The present invention can understand the image content more comprehensively and accurately, significantly improve the accuracy of hotel structured information extraction, and reduce the error rate of information extraction.

The present disclosure provides a method for securing document content. A document security manager receives a digital document containing original text and image content. The original text content is processed to identify text portions by parsing annotations, analyzing proximate text, extracting content within the determined scope, and determining encryption attributes. The original image content is processed to identify image portions by detecting user-defined selections or employing a neural network to identify sensitive objects. Encrypt content requests are generated including the identified text and image portions with associated attributes and metadata. The requests are transmitted to a cryptographic engine, which returns encrypted content. A partially encrypted document is built by replacing original content with masking symbols, applying visual obfuscation, embedding encrypted content as metadata, and updating document properties to indicate encrypted content.

The embodiment of the invention provides a project research and development data key information processing method and device. A research and development content recognition system and a self-adaptive research and development knowledge graph are constructed. Unified processing and time sequence alignment of text, voice and image contents are realized through multi-modal information decomposition and fusion. Semantic completion and error correction are carried out based on research and development of a semantic analysis model, a knowledge graph structure is dynamically constructed and optimized, and a structured document with a traceability relation is generated. The system adopts a deep neural network model to extract research and development key information, constructs a multi-level document framework, and realizes intelligent conversion from research and development data to a project application document. According to the method, the defects of the traditional technology in the aspects of multi-modal information processing and knowledge structure optimization are effectively overcome, and the research and development data management and project declaration efficiency is remarkably improved.

The invention belongs to the technical field of rail transit, and discloses a rail transit environment foreign matter intrusion detection method and system based on a visual model. The method comprises the following steps: firstly, extracting a suspicious region sub-graph in an original image through preprocessing, and respectively extracting a coarse-grained global feature vector and a fine-grained local feature vector by using an image encoder; meanwhile, text prompt information matched with the image content is generated, and a corresponding text feature vector is extracted; the multi-level similarity of the image feature vector and the text feature vector is calculated, and the respective weight fusion is combined to obtain a comprehensive abnormal score; and finally, dynamically modeling abnormal score distribution based on a Gaussian mixture model to realize foreign matter invasion judgment. According to the method, image and text multi-modal information is fused, the detection precision of foreign matters in a complex scene is improved through multi-scale feature association, the dynamic environment adaptability is enhanced by adopting an adaptive threshold strategy, and the problems that a traditional method is high in false detection rate and insufficient in generalization ability in a complex background of a railway are effectively solved.

The invention relates to the field of liquid crystal display, and discloses a liquid crystal display screen dynamic contrast optimization method and system, and the method comprises the following steps: collecting ambient light intensity and backlight module temperature parameters in real time, and combining with image content entropy analysis to dynamically generate a non-uniform backlight partition grid; a brightness diffusion physical model is constructed based on hardware parameters such as the refractive index of the light guide plate and the LED spacing, and the optimal brightness of each partition is solved by adopting a temperature self-adaptive improved particle swarm algorithm; driving voltage is generated through piecewise nonlinear gamma mapping and inverse function iterative calculation, and the driving voltage is adapted to the nonlinear response characteristics of the backlight module; a hardware accelerator is used for executing a diffusion equation and optimization calculation in parallel, and model parameters are dynamically adjusted in combination with feedback of an optical sensor, so that a closed-loop control link is formed. According to the method, the contrast performance and the dynamic scene adaptability of the display screen are comprehensively improved through dynamic partition adaptive to the environment, an optimization algorithm driven by a physical model and real-time processing accelerated by hardware.

The invention discloses an end-to-end underwater three-dimensional reconstruction method and system based on an underwater imaging model, and belongs to the technical field of underwater image processing. According to the method, deep learning pose estimation is combined with an underwater imaging model; firstly, a multi-frame underwater image sequence is collected as input, a deep neural network is constructed, and the network mainly comprises two core sub-modules: a pose estimation network; secondly, a three-dimensional reconstruction network is adopted, dense point cloud or voxel reconstruction is completed according to the predicted pose and image content, pose estimation and the three-dimensional reconstruction process are integrated in the same system, and overall joint optimization is achieved; and in combination with a self-adaptive underwater imaging model, modeling is performed on physical processes such as underwater illumination attenuation and scattering, so that the reality sense and the accuracy of a reconstruction result are improved. According to the method, high-quality three-dimensional reconstruction of images in a complex underwater environment is realized, and the method can be widely applied to ocean engineering, underwater robots, submarine topography surveying and mapping and underwater cultural relic protection.

A method, apparatus, non-transitory computer readable medium, and system for media processing includes obtaining a text prompt and a style input, where the text prompt describes image content and the style input describes an image style, generating a text embedding based on the text prompt, where the text embedding represents the image content, generating a style embedding based on the style input, where the style embedding represents the image style, and generating a synthetic image based on the text embedding and the style embedding, where the text embedding is provided to the image generation model at a first step and the style embedding is provided to the image generation model at a second step after the first step.

The present disclosure provides a method for securing document content. A document security manager receives a digital document containing original text and image content. The original text content is processed to identify text portions by parsing annotations, analyzing proximate text, extracting content within the determined scope, and determining encryption attributes. The original image content is processed to identify image portions by detecting user-defined selections or employing a neural network to identify sensitive objects. Encrypt content requests are generated including the identified text and image portions with associated attributes and metadata. The requests are transmitted to a cryptographic engine, which returns encrypted content. A partially encrypted document is built by replacing original content with masking symbols, applying visual obfuscation, embedding encrypted content as metadata, and updating document properties to indicate encrypted content.

The invention relates to the technical field of video coding, in particular to a video coding method and system based on multi-channel concurrent software and hardware mixing, and the method comprises the following steps: analyzing brightness distribution and edge structures, screening effective frames, calculating frame priorities, dividing image blocks and combining processing units, counting the number of frame streams, and analyzing frequency concentration. And evaluating image coherence and a load state, and outputting a processing channel adjustment record. According to the invention, through screening of image content features, occupation of redundant frames on coding resources is reduced, through dynamic configuration of frame priorities, timeliness and accuracy of target frame scheduling are improved, an aggregation strategy of a block structure is combined, picture consistency after image processing is enhanced, and task frequency trend identification is utilized, so that image processing efficiency is improved. According to the method, accurate resource matching of a high-load flow section is achieved, joint judgment of image boundary continuity and structure hopping frequency is adopted, an allocation strategy of a processing channel is optimized, an image structure and channel scheduling form linkage, and stability and adaptive capacity are improved.

The invention belongs to the related technical field of construction safety inspection, and particularly relates to a construction site safety inspection method based on a multi-modal large language model, which comprises the following steps of: introducing the multi-modal large language model, and applying the multi-modal large language model for multiple times in combination with a knowledge base containing safety standard specifications and evaluation rules to obtain a construction site safety inspection result. The method specifically comprises the following steps: obtaining image content description through an image and a preset visual perception system prompt text; intelligently decomposing user input query into a plurality of sub-query tasks through user input query, image content description and preset task decomposition system prompt; searching construction safety management standard data related to each sub-query from the construction safety knowledge base, and analyzing and reasoning the sub-query based on the image content description in combination with the searched standard data to obtain the reasoning and conclusion of the sub-query; and finally, obtaining a total reasoning and conclusion based on each sub-query data. The method can accurately, scientifically and comprehensively realize the safety inspection of the construction site.

The invention belongs to the technical field of natural language processing and multi-modal information extraction, and particularly relates to a multi-modal named entity recognition method based on semantic alignment and cross-modal graph fusion, which comprises the following steps: S1, acquiring a data sample containing a text sequence and image content; s2, encoding the text and the image into vectors respectively; s3, similarity is calculated through a trainable bilinear function, and optimization is carried out through loss comparison; s4, cross-modal attention is used to enhance association information between modals; s5, determining the proportion of reserved image information through a modal matching module; s6, introducing a gating mechanism to dynamically fuse visual and text features; s7, realizing local and global information complementation by a cross-modal graph fusion model; and S8, inputting the fused representation into the CRF layer to predict the entity type. According to the method, fine semantic alignment can be realized in a weak image-text correlation context, and balance between local entity recognition and global semantic understanding can be achieved.

The invention discloses a multi-agent automatic image retouching system based on content analysis, and the method comprises the steps: 1, receiving the input of an original image, calling a finely-adjusted multi-mode large model to carry out the combined semantic-visual analysis of the image, extracting key semantic elements in the image, and carrying out the recognition of the key semantic elements; comprising but not limited to background coordination degree, illumination condition, figure hair style definition, weather quality and composition layout rationality content information. Based on these information, the system performs comprehensive image quality scoring on the image, which combines image style, aesthetic level, definition and subjective quality multi-dimensional evaluation criteria. Meanwhile, based on a multi-dimensional image quality scoring result and understanding of image semantic content, the system automatically generates a repair and optimization strategy set for specific defects so as to guide a subsequent image quality enhancement process. The invention relates to the field of multi-modal model and multi-agent cooperation, and can meet the increasing requirements of rapid optimization and high-quality propagation of image contents.

The invention discloses an image encryption system and method in an intelligent power grid environment, and aims to solve the problem that an encryption strategy is static and lacks self-adaptive capability in the prior art. The image encryption system comprises terminal equipment, edge equipment and central equipment, and a dynamic key generation unit on the terminal equipment generates a dynamic key by cooperatively utilizing a physical unclonable feature (PUF) of the equipment and a real-time load of a power grid; the hierarchical encryption unit performs encryption of different intensities based on image content complexity. A topology sensing transmission module of the system analyzes power grid topology by using a graph neural network (GNN) and dynamically optimizes transmission. In addition, the image encryption system further integrates low-density parity check code encoding and decoding and a self-adaptive decryption strategy so as to enhance the anti-interference capability. According to the invention, by constructing a sensing, decision-making and execution integrated adaptive security system, the security, high efficiency and robustness of smart grid image data transmission are significantly improved.

The invention relates to a computer-implemented method for automatically detecting anatomical structures (3) in a medical image (1) of a subject, the method comprising applying an object detector function (4) to the medical image, wherein the object detector function performs the steps of: (A) applying a first neural network (40) to the medical image, wherein the first neural network is trained to detect a first plurality of classes of larger-sized anatomical structures (3a), thereby generating as output the coordinates of at least one first bounding box (51) and the confidence score of it containing a larger-sized anatomical structure; (B) cropping (42) the medical image to the first bounding box, thereby generating a cropped image (11) containing the image content within the first bounding box (51); and (C) applying a second neural network (44) to the cropped medical image, wherein the second neural network is trained to detect at least one second class of smaller-sized anatomical structures (3b), thereby generating as output the coordinates of at least one second bounding box (54) and the confidence score of it containing a smaller-sized anatomical structure.

The invention discloses an AI intelligent image-text situation content accurate layout full-marketing generation method, and particularly relates to the technical field of image-text recognition. The method comprises the following steps: performing semantic analysis on a text input by a user, extracting a deliberate graph item, reverse semantics, an auxiliary emotion item and a tonality keyword, and constructing a multi-semantic field group; the field groups are injected into a collaborative generation engine composed of an image generation sub-model and a semantic prediction sub-model, and the semantic prediction sub-model predicts graph attribute tags and guides the image generation sub-model to conduct regional attention intervention; after the image is generated, the matching degree of the image content and the field group structure is evaluated through a structure-level semantic consistency judgment mechanism, and regeneration is triggered if the image content and the field group structure are inconsistent; finally, the image content with the aligned structure is output and subjected to image-text combination typesetting with the original text, and image-text situation content meeting the multi-platform marketing application requirement is generated. According to the method, the semantic accuracy, the structural consistency and the visual expression quality are remarkably improved while the generation efficiency is ensured.

The invention discloses a backlight source partition dimming control method, and belongs to the field of data security, and the control method comprises the following specific steps: I, analyzing the data features of an input image, recognizing a highlight motion region, and predicting and optimizing a current backlight partition dimming strategy; iI, adjusting a backlight area in real time according to the brightness, contrast and color change of the input content, and constructing a multi-level light diffusion coupling model after partition adjustment; the backlight partition can be adaptively adjusted according to the image content, the local contrast ratio and energy efficiency are improved, more uniform light distribution is achieved, the problems of halo and uneven brightness are reduced, the dimming precision is improved, the service life of a light source is prolonged, the light overflow effect of the partition edge is effectively reduced, and the picture layering sense is improved; the subjective image quality experience is effectively improved, the light efficiency utilization rate is improved, meanwhile, image quality and power consumption optimization can be considered, brightness adjustment better conforms to human eye visual characteristics, visual fatigue is reduced, and it is ensured that the optimal image quality is maintained under the lowest power consumption.

The invention relates to the technical field of computer graphic interactive processing, in particular to a real-time interactive image generation system based on a multi-point touch canvas. The input acquisition unit is used for acquiring original touch data from an operating system and preprocessing the original touch data; the gesture recognition and analysis unit is used for performing high-level semantic behavior analysis on the contact data sequence processed by the preprocessing module; the interaction control and parameter mapping unit is used for receiving the semantic event output by the gesture recognition and analysis unit, analyzing the semantic event into an image control command and generating an executable command sequence; and the image generation unit generates interactive image content dynamically responded in real time based on an internal graph state management mechanism. By introducing the adaptive Kalman filtering and trajectory prediction auxiliary mechanism, the filtering intensity of the contact data can be dynamically adjusted, the efficient suppression of finger jitter and the consistent reconstruction of the contact ID are realized, and the input stability and data continuity under the multi-point touch operation are remarkably improved.

The invention discloses a multi-modal driving test scene generation method and system, and the method comprises the steps: obtaining a plurality of groups of model training samples, each group of model training samples comprising a user natural language description, a driving scene visual image, a risk point thermodynamic diagram, and a safety key scene description code; constructing a driving test scene generation framework, and training the driving test scene generation framework by using the multiple groups of model training samples to obtain a trained driving test scene generation framework; wherein the driving test scene generation framework comprises an image content coding model, a risk point mining model, a thermodynamic diagram coding model and a large language model, the risk point mining model and the thermodynamic diagram coding model are connected in series, and the output end of the image content coding model and the output end of the thermodynamic diagram coding model are connected with the input end of the large language model; and generating a multi-modal driving test scene according to the input user natural language description and the driving scene visual image by using the trained driving test scene generation architecture.

The invention discloses a cross-modal eye fundus image generation method and system based on a generative adversarial network, relates to the technical field of medical image processing, and constructs an eye fundus focus perception and edge consistency generative adversarial network by taking a cyclic consistency generative adversarial network as a baseline. The core of the method is that a lesion perception mixed attention module is embedded in a bottleneck layer of a generator so as to strengthen the extraction capability of fine features of a lesion area; an edge information extraction module is designed, and key edge features are accurately extracted in combination with Roberts edge detection, wavelet transform and non-local mean denoising; and a joint loss function containing edge consistency loss is constructed, and the semantic consistency of a focus structure during cross-modal generation is ensured by minimizing the feature difference between the source image and the generated image. According to the method, the problems of disordered content, inconsistent structure and unstable training of the generated image in the prior art are effectively solved, and the simulation degree and clinical availability of the generated image are remarkably improved.

The invention belongs to the technical field of data processing, and particularly relates to a potential safety hazard real-time identification method and system based on a multi-modal large model, the system comprises the multi-modal large model, a field knowledge base and a multi-modal inference engine, the multi-modal large model is responsible for visual feature extraction and scene semantic understanding of an input field image, and the field knowledge base is responsible for field knowledge base analysis; processing a natural language query provided by a user; the domain knowledge base stores construction safety related laws and regulations, guidelines and historical cases, and factual basis is provided for the system through a structured storage and efficient retrieval mechanism; the multi-modal reasoning engine coordinates the whole process of visual understanding, task decomposition, knowledge retrieval and report generation, and is a core control module for realizing multi-modal reasoning and decision making. And refined understanding of entities and hidden dangers in a construction scene is realized. According to the system and the method thereof, the image content and the text specification can be dynamically fused, and missing detection or misjudgment caused by modal splitting in a traditional method is avoided.

The invention relates to the technical field of medical image processing, and discloses a method for intelligently describing liver space-occupying lesion ultrasonic image content by using LLM. A liver ultrasonic image sequence, a patient historical medical record text and a blood biochemical index vector are obtained through a multi-modal data acquisition module, and features are extracted through a cross-modal contrast learning network to generate embedded vectors and align the embedded vectors. And inputting the aligned image embedding vector into a dynamic context sensing decoder, and generating a description text semantic mark sequence by using a layered multi-head attention mechanism. The confidence coefficient is evaluated through an uncertainty calibration module, and the text is optimized through a post-processing reordering mechanism when the confidence coefficient is lower than a threshold value. A real-time interaction optimization mechanism is further arranged, and the model is updated according to feedback of doctors. According to the method, multi-modal data are fused, description accuracy and reliability are improved, text quality is optimized, clinical requirements are met, and liver disease diagnosis is assisted.

The invention discloses an image generation method, a model determination method and an image generation system, and relates to the technical fields of large model technology and image processing. The method comprises the steps that an initial object image to be processed and a mask image are determined, the image content of the initial object image comprises at least one to-be-displayed object located on a pure color background, and the mask image is used for representing an image area to which the to-be-displayed object is to be displayed in an initial scene image; using the image processing model to take the initial object image as visual reference information of the mask image, and predicting to obtain a predicted object image corresponding to the mask image; and superposing the predicted object image to the initial scene image to obtain a target scene image, the target scene image being used for representing a display result of the to-be-displayed object in the image area. The technical problem that the image generation effect is poor in the prior art is solved.

Approaches presented herein provide for the generation of image content including fine objects, such as those that may be less than one pixel in width. Fine objects such as hairs can be represented by curve equations, and curves defined by these equations can be given an inflated width in order to perform conservative hit testing to efficiently identify pixels that a hair might intersect. Once candidate pixels are identified through ray tracing or sampling, for example, false positives or pixels with little hair representation can be removed from consideration. For remaining pixels, a linear representation of the inflated curve can be used to determine intersection points and vertices of a pixel quad corresponding to a hair, which can be used to generate a convex geometric shape representative of the object. The percentage of the pixel area occupied by this geometric shape can be used to determine an alpha or blending value for blending the pixel value of this hair or object with the background pixel color.

The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital designs utilizing a diffusion neural network to preserve readability and design composition while modifying image content background images and design assets. In some embodiments, the disclosed systems access a text prompt defining visual attributes of a digital design. Furthermore, the disclosed systems generate a modified text prompt by replacing chromatic information within the text prompt. Additionally, the disclosed systems determine an adaptive strength for a diffusion neural network from the text prompt. Also, the disclosed systems generate a modified digital design utilizing the diffusion neural network to process the modified text prompt according to the adaptive strength.

The invention relates to the technical field of natural language processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a document interpretation and report generation method, device, equipment and medium, which comprises the following steps: receiving an original document set to generate a structured document object, executing optical character recognition on an image content set to generate a recognition text set, the recognition text set and the text content set are combined into a unified text sequence, element item extraction is executed based on the interpretation template parameter set to generate an interpretation element set, a retrieval enhancement context is retrieved and generated from the domain knowledge base, and the unified text sequence, the interpretation template parameter set and the retrieval enhancement context are input into a language model to generate an interpretation result. And generating report content based on the historical report template set. According to the method, automatic closed loop of document interpretation and report generation is realized through multi-modal unified processing and semantic enhanced reasoning, the efficiency is improved, and the manual dependence and compliance risk are reduced.

The invention discloses a method and device for generating medical image question and answer thinking chain data in multiple stages. According to the method, by introducing a multi-stage model collaborative reasoning mechanism, extraction of key image content, enhanced generation of image description and construction of a thinking chain are completed in sequence, so that the accuracy, pertinence and interpretability in a medical image question and answer task are improved; the problems that an existing model is inaccurate in image detail recognition, opaque in reasoning process, generalized in question and answer content and the like are solved.

The invention discloses an image video super-resolution enhancement method based on a degradation generative adversarial network, and relates to the field of image processing, and the method comprises the steps: carrying out the image collection and preprocessing; building and training a super-resolution enhancement model; and carrying out super-resolution enhancement on the image based on the degradation generative adversarial network model. According to the method, an image content self-adaptive dynamic degradation kernel generation mechanism is adopted, the degradation process of the image under different equipment and organization structures is truly simulated, a dynamic up-sampling and residual error correction network guided by the degradation kernel is adopted, the detail reduction capability and the structure fidelity of the super-resolution image are remarkably improved, and the super-resolution image quality is improved. The image texture authenticity and key organization density consistency are effectively enhanced, the balance of training games between a generator and a discriminator is realized, and the model stability and convergence quality are improved.

The invention discloses a user non-inductive resource efficient scheduling method and device for a VR application and a storage medium, and belongs to the field of VR application. The method comprises the following steps: respectively extracting track time sequence features and video content features from user track data and image content data; respectively calculating attention weights of track time sequence features and video content features through a cross attention mechanism, adaptively and dynamically adjusting the attention weights of the features, and generating fusion feature information; inputting the fused feature information into a viewport prediction model, and outputting a viewport position prediction result in a future time window; dynamically selecting a multi-stream data source to perform resource scheduling by taking the viewport position prediction result and the current network state as resource scheduling conditions; and allocating a first code stream channel and network resources meeting the set QOS standard to a high-priority region concerned by the user in the viewport position prediction result. The dynamic change and scene switching of user behaviors are effectively handled, and the user experience quality is ensured.

The invention relates to the technical field of human resource management, and provides an intelligent paper marking system and method for talent selection and recruitment. The method comprises the following steps: cutting test paper according to a preset test paper template by using an image processing technology to obtain a plurality of plates corresponding to the test paper; converting the image content of each section of the cut test paper into a text format which can be edited and processed by adopting a character recognition technology; setting a preliminary scoring standard according to question type information and knowledge point information corresponding to the test paper, and optimizing the preliminary scoring standard by using a large language model; performing semantic understanding and logic analysis on the converted test paper text answers from a plurality of scoring dimensions including semantic accuracy, logic integrity and knowledge point coverage by using two preset scoring large models to give corresponding scoring information, and marking advantage information and defect information in the answers; and obtaining a comprehensive score corresponding to the test paper according to score information printed by each score big model for each question of each test paper.

The invention relates to the field of municipal communication pipelines, and discloses a municipal communication pipeline-based laying construction management system, which comprises the following steps of: acquiring images, position information and voice data of a construction site, preprocessing the acquired content by utilizing a lightweight edge calculation model, and judging whether data exception exists or not; on the basis of spatio-temporal information matching and an image content recognition algorithm, construction data collected on site are compared with the engineering plan model, and whether areas which are not constructed according to specifications are recognized or not is judged; uniformly converting the unstructured data into construction record items in a standard format by using a multi-modal feature fusion method, and judging whether the unstructured data is successfully converted or not; dynamically updating a construction progress state in combination with a project construction plan and real-time acquired data, and generating a visual Gantt chart display; and training the historical engineering data based on a machine learning model, and automatically pushing early warning information to a management terminal. The method has the advantage of improving the communication pipeline construction management capability.