2556results about "Drawing from basic elements" patented technology

An attitude display system for use in an aircraft has at least one display unit visible by a pilot within a cockpit. A symbology generator is configured for receiving input from at least one attitude sensor and generating symbology image data representative of a pear-shaped attitude indicator, distorted vertically to represent a pitch of the aircraft and rotated to represent a roll angle of the aircraft. The symbology generator may further be configured for adding a horizontal line that represents a horizon, a regular trapezoid representing a downward gravity vector at a base of the trapezoid, a pitch angle of the aircraft, split wings representing an angle of attack of the aircraft, and a stall warning in a sawtooth crack shape. A tail portion of a T-shape with the curved top edge is itself curved in a direction opposite that of an aircraft spin direction.

The invention relates to a stylized font generation method based on a diffusion model, and aims to solve the problems of font stroke structure disorder and style deviation in the prior art and realize accurate and stylized font generation. The method is divided into two stages: a first stage, performing pre-training of a font style classification task, including constructing a font style label, designing a style feature extraction network, and training by using a data set to obtain a pre-trained style encoder so as to extract font style features; and in the second stage, training of the generation model is started, style encoder parameters are frozen in the process, content features, stroke order structure features and style features serve as conditions, model parameters are optimized through mean square loss and contrast loss, and therefore a high-quality generation image is trained and generated. According to the method, the structural accuracy and style expressive force of font generation are remarkably improved, and efficient technical support and application value are provided for font library construction and design.

The invention relates to the technical field of computer vision and industrial automation, in particular to a shoe sole three-dimensional gluing contour extraction system and method based on vision single-line laser, and aims to solve the problems that virtual calibration target spots cannot be accurately generated based on shoe sole geometry, the positions and sizes of the target spots are difficult to determine by combining curvature extreme values and principal component analysis in the prior art, and the production cost is low. The problem that a double-branch deep learning model cannot be adopted to fuse feature prediction transformation, and the re-projection error is increased is solved; a virtual calibration target spot is automatically generated based on sole geometry through a feature fusion calibration module, a grid is generated through point cloud processing and Poisson reconstruction, the position and size of the target spot are determined by combining a curvature extreme value and principal component analysis, a corresponding relation is established by utilizing two-dimensional and three-dimensional feature matching, initial alignment is realized through ICP and re-projection error optimization, and the target spot position and size are determined. A double-branch deep learning model is adopted to be fused with feature prediction transformation, iterative optimization is carried out through space consistency errors, and re-projection errors are reduced.

A system and method for automatically extracting data from tables and graphs in scientific literature, particularly in life sciences and healthcare, is presented. The invention employs a hybrid approach combining computer vision, natural language processing (NLP), and a large language model (LLM)-based data extraction module. A neural network enhances accuracy by providing contextual information. The system performs table structure detection, optical character recognition (OCR), Vision Transformers (ViTs) for text recognition, and graph-to- table conversion. An LLM refines the extracted data using advanced prompt engineering. A user interface enables data review, validation, and iterative refinement. The system employs a novel two-stage approach: de-rendering tables and graphs into a machine-readable format, followed by interpretation and user-defined mapping. A knowledge graph enhances extraction by resolving ambiguities and inferring relationships. Designed for scalability and continuous improvement, the invention significantly enhances data extraction efficiency and accuracy, accelerating research and knowledge discovery.

The invention relates to the field of human resource management, and discloses a tobacco enterprise human resource management auxiliary calibration method based on big data, and the method comprises the steps: obtaining multi-source heterogeneous data related to enterprise internal human resources, and constructing a structured human resource data model in combination with a data standardization processing mechanism and an abnormality elimination strategy; post portrait modeling is carried out on the structured human resource data model, a capability dimension nesting analysis method is introduced, key capability factors and weight distribution required by each post are extracted, and a post capability demand graph is constructed; based on the post capability demand map, fusing the staff portraits and the historical job data, and identifying the deviation between posts and the staff through a multi-dimensional feature matching algorithm to form a preliminary calibration suggestion set; and a dynamic service association analysis method is introduced, and key matching parameters in the preliminary calibration suggestion set are dynamically corrected in combination with latest service demand data and real-time task assignment information. The method has the advantage of improving the management efficiency.

The Marker Fingerprinting system provides a method for identifying and correlating serial or sequential data patterns across diverse domains such as geological, biological, and financial datasets. This innovation transforms single- or multi-attribute data series into feature matrices, generating unique hash tokens—or fingerprints—that encapsulate specific data patterns. Using advanced signal analysis and spectral transformations, it enables efficient processing and pattern recognition within complex datasets. Fingerprints from reference patterns are matched against target datasets, with quantitative confidence metrics derived from weighted algorithms assessing match accuracy. Iterative data conditioning enhances robustness by addressing noise and inconsistencies, ensuring reliability at scale. The invention improves decision-making by delivering rapid and accurate pattern identification with quantified reliability, making it particularly suited for applications like geological top picking, seismic data analysis, and other fields requiring precise data correlation

In various examples, various types of sensor data from multiple ego-machines are used to infer lanes and / or generate lane graphs for use in autonomous systems and applications. In some embodiments, one or more DNNs may be used to infer lane data indicating a representation of a lane shape using sensor data from various vehicles to represent a 3D environment. The inferred lane data may include cross-section indicators that indicate cross-sections of a lane and / or connection indicators that indicate a lane channel connecting two locations (e.g., two lane portions). The inferred lane data may be used to generate a lane graph that represents lanes on a road and, in some cases, lane dividers (e.g., polyline represented as a solid line, a dashed line, a double line, etc.). A lane graph may be used, for example, to model the environment around a vehicle, facilitate localization, provide guidance for autonomous driving, etc.

The invention discloses a wind resource assessment report generation method based on a large model technology. The method comprises the following steps: processing multi-source data, and constructing a domain knowledge base and a fine tuning database; field adaptive RAG enhancement is carried out, professional literatures, historical cases and industry specifications in a field knowledge base are retrieved by adopting a retrieval enhancement generation technology, and wind resource assessment contents meeting technical standards are generated through a multi-modal fusion word vector technology; performing large model fine tuning, and optimizing the generative large model through a gradient-free optimization algorithm Wind-DFO on the basis of a fine tuning database by adopting a field self-adaptive fine tuning strategy; and automatically generating a report, arranging and matching multiple templates through an AI workflow, embedding a data visualization chart, executing verification of a grammar layer, a logic layer and a compliance layer, and outputting a standardized wind resource assessment report. The accuracy, specialty and efficiency of report generation are remarkably improved, and the problems that a traditional method depends on artificial experience, the data utilization efficiency is low, and standardization is insufficient are solved.

The invention provides a production operation dynamic supervision method, which comprises the following key steps: S1, data integration: widely collecting data of different production links, transmitting the data to a database through a network interface, and constructing a comprehensive data basis; s2, establishing a visual monitoring platform to integrate data to drive development, vividly displaying a production state by means of a three-dimensional model, a chart and a report, and helping a manager to intuitively insight; s3, intelligent analysis and early warning: deeply mining a data rule trend by using big data and an artificial intelligence algorithm, accurately setting an early warning threshold value, and giving an alarm in time when the threshold value is exceeded, so as to effectively prevent risks; and S4, collaborative management and decision support are carried out, department information barriers are broken, efficient sharing and collaboration are realized, scientific decision support is provided for managers, and production plans, maintenance strategies and emergency plans are optimized. According to the method, through multi-link collaborative operation, the production operation dynamic management and control capability is comprehensively enhanced, and efficient, safe and robust development of enterprises is powerfully promoted.

The invention discloses an intelligent war game deduction method based on reinforcement learning, and the method comprises the steps: constructing a dynamic battlefield model: constructing an adjustable battlefield simulation platform, and defining the landform, resources and army distribution elements in a battlefield; a reinforcement learning strategy is generated and optimized, an intelligent strategy generation algorithm based on deep reinforcement learning is designed, and an efficient combat strategy is generated in multiple rounds of training by constructing a state space and an action space and combining a situation reward function; a double-agent chess playing training mechanism is introduced, black parties and white parties are modeled into reinforcement learning agents, red parties and blue parties are modeled into reinforcement learning agents, and a real battlefield game is simulated through multiple rounds of alternate training; result visualization deduction: a dynamic decision visualization function is provided, and battlefield situation, troop dynamics and a strategy execution process can be displayed in real time; according to the method, the problems of rule solidification, limited strategy generation capability, insufficient antagonism and the like in the prior art are solved.

The invention discloses a structured data self-learning method based on a graph neural network, and the method comprises the following steps: S1, analyzing structured data, extracting entity fields and relation fields, and constructing a structure candidate graph; s2, generating a node embedding feature matrix, and initializing and recording the adjacency relation of candidate edges; s3, constructing a graph neural network model, inputting node features and an adjacent matrix, and defining a task loss function; s4, evaluating the gradient contribution degree of edge connection by adopting a gradient sensitive sparse adjacency self-learning algorithm, and updating the graph structure representation; s5, introducing an embedded interpretability gradient backtracking mechanism, correcting an edge connection relation and enhancing interpretability; s6, training the graph neural network by using the corrected structure, and updating the node embedding and graph structure; and S7, outputting a final graph structure and an interpretability index, and generating a graph modeling visualization result. According to the method, efficient modeling and explanatory analysis of structured data are realized through a dynamic graph structure learning and gradient backtracking mechanism.

The invention discloses a corn germination image segmentation method based on an elite adaptive rime algorithm. Relates to the technical field of agricultural seed detection and image processing, in particular to the technical field of corn germination image segmentation based on an elite adaptive rime algorithm. According to the method, a dual-adaptive weight mechanism and an elite reselection strategy are introduced into a rime optimization algorithm, the convergence capability of the algorithm is enhanced, and multi-threshold segmentation is carried out on the corn kernel germination image in combination with the Kapur entropy. And the image segmentation precision is effectively improved. The method comprises the following steps: acquiring a corn germination image data set; drawing a two-dimensional histogram, and inputting the two-dimensional histogram into a Kapur entropy function to obtain an objective function fobj; an elite solution module is initialized; a dual-adaptive weight mechanism is added; a soft rime strategy and a hard rime strategy are improved; updating the elite solution after the rime search strategy module; and the target function fobj is input into a rime improvement algorithm, and an optimal threshold value is obtained.

The invention provides an intelligent self-adaptive video editing method and system based on deep learning, and relates to the technical field of video processing.The method comprises the steps that firstly, a semantic mapping relation between a to-be-edited video material and a preset editing requirement is established, and an editing requirement mapping result is generated, the preset editing demand comprises a content style and a rhythm control demand, and then semantic feature association processing is carried out based on the mapping result to obtain a semantic association feature set comprising lens unit content semantic features and rhythm association features; then calling a pre-trained editing decision model (including a semantic matching module and a rhythm adjusting module) to carry out editing strategy matching on the set, generating a preliminary editing strategy set, generating an initial video editing scheme according to the preliminary editing strategy set, carrying out parameter adjustment on the initial scheme according to a strategy optimization suggestion output by the model, and carrying out video editing on the initial scheme; and a final video editing scheme is obtained, and intelligent self-adaptive editing of the video is realized.

The invention discloses a landslide risk assessment method based on an extreme rainfall and geology coupling model, and relates to the technical field of geological disasters. Comprising the following steps: S1, constructing a three-dimensional probability density field of a fracture network and a non-Gaussian random field model of a permeability coefficient tensor; s2, setting a physical kernel layer according to the non-Gaussian random field model, setting a data driving layer through space-time Transform coding, and constructing a graph attention network model; s3, generating an adversarial network through physical information, constructing extreme rainfall coupling data, and updating the non-Gaussian permeability coefficient random field model according to the graph attention network model; and S4, acquiring an entropy generation rate according to the mechanical field data, the seepage field data and the temperature field data, and determining a risk level. Physical interpretability grading early warning of landslide risks is realized, and meanwhile, risk space distribution can be visually displayed through a sliding surface probability cloud picture, so that accurate decision support is provided for disaster prevention and control.

The invention belongs to the field of damage assessment, and relates to a typical engineering target rapid damage assessment method based on an image recognition technology, and the method comprises the steps: building different types of image damage feature damage assessment criteria: obtaining damage pictures and anti-explosion damage data, carrying out the classification of damage grades, drawing a P-I curve graph, defining the damage grade and the critical state of damage, and carrying out the calculation of the damage assessment criteria; adopting a cyclic interpolation method to obtain a failure critical condition, a critical progressive impulse and a critical progressive overpressure, substituting into a classical P-I curve expression for fitting to obtain a failure critical curve expression, and further simulating to obtain a failure critical area; establishing a corresponding relationship between the damage assessment criterion-damage critical area and the damage level of the image damage feature under the engineering target category; a damage picture is shot, the damage area is extracted, the damage area is compared with the image damage feature damage evaluation criterion, and the damage level is rapidly determined. According to the method, the mapping relation between the image damage characteristics and the structural mechanical response is established, so that the damage level is quickly researched and judged.

In various examples, various types of sensor data from multiple ego-machines are used to infer lanes and / or generate lane graphs for use in autonomous systems and applications. In some embodiments, one or more DNNs may be used to infer lane data indicating a representation of a lane shape using sensor data from various vehicles to represent a 3D environment. The inferred lane data may include cross-section indicators that indicate cross-sections of a lane and / or connection indicators that indicate a lane channel connecting two locations (e.g., two lane portions). The inferred lane data may be used to generate a lane graph that represents lanes on a road and, in some cases, lane dividers (e.g., polyline represented as a solid line, a dashed line, a double line, etc.). A lane graph may be used, for example, to model the environment around a vehicle, facilitate localization, provide guidance for autonomous driving, etc.

The invention discloses a deep learning-based cold resistance evaluation system for medicago sativa L., and the system comprises a data generation module which is used for generating a phenotypic image and corresponding physiological data of medicago sativa L. under low-temperature stress through a diffusion model embedded with plant low-temperature response physical constraints; the evaluation model module is used for extracting cold resistance characteristics from the image and physiological data by adopting a causal-driven dual-channel adaptive network; and the decision module comprises a hierarchical model distillation unit and a federal reinforcement learning unit, and the hierarchical model distillation unit and the federal reinforcement learning unit realize joint training of model compression and decision strategy optimization through an edge-cloud collaborative architecture, output a cold-resistant decision and realize visualization through an augmented reality interface. The method can effectively solve the core problems of traditional medicago sativa cold resistance assessment in the aspects of data generation, model generalization, decision-making efficiency and the like.

The invention provides a ship trajectory optimization method and system based on a visual language model and multi-modal collaborative decision, and relates to the field of ship trajectory prediction.The method comprises the steps that a trajectory prediction model is established, and a ship trajectory optimization model is established based on the visual language model; establishing a ship trajectory optimization cue word template based on chain thinking; first multi-modal data is obtained, and the first multi-modal data at least comprises a track classification label; generating a basic trajectory prediction result according to the first multi-modal data through a trajectory prediction model; generating second multi-modal data according to the basic trajectory prediction result and the first multi-modal data; and through the ship trajectory optimization model, according to the ship trajectory optimization cue word template based on chain thinking and the second multi-modal data, an optimized trajectory prediction result is generated, and the ship trajectory prediction method has the advantage of improving the accuracy of ship trajectory prediction.

The invention relates to the technical field of water meter flow, in particular to an ultrasonic water meter flow curve fitting system, which is characterized in that an edge computing device is used for primarily processing original data at a data acquisition end, a mean filtering algorithm is used for removing noise data, and the data after acquisition is subjected to filtering, denoising, abnormal value elimination and normalization processing; a dynamic evaluation model is constructed by adopting a time sequence prediction algorithm, the model calculates and predicts various data of future ultrasonic water meter flow by continuously inputting real-time data, and the model is optimized according to a prediction result, so that errors of the model are continuously reduced in the training process, and the prediction accuracy of the model is improved; modeling and fitting are conducted on the flow curves, calculated by the neural network model, of the ultrasonic water meter in different working states through the fitting model, the fitted curves can serve as a basic data source of a user water consumption behavior and system load characteristic advanced analysis model, and energy-saving analysis and fault positioning are facilitated.

Technology is disclosed herein for the integration of spreadsheet environments with LLM services. In an implementation, an application service receives a natural language input from a user associated with a spreadsheet hosted by a spreadsheet application. The application service generates a prompt based on the natural language input which includes asking a large language model (LLM) service to classify a statement in the input as referring to one of multiple capabilities of the spreadsheet application. The application service inputs the prompt to the LLM service and receives an output from the LLM service which identifies a determined one of the multiple capabilities. The application service generates a revised prompt based on the input and the determined one of the multiple capabilities and inputs the revised prompt to the LLM service.

Systems and methods are provided for generating visualization data associated with raw data using a machine learning model. For example, the machine learning model may automatically generate a set of candidate analytics and / or a scenario for visualizing the raw data based on summary data. Given the summary data and answers to prompts for visualizing data, the generated candidate analytics may reflect a context of the raw data as intended by the user. A visualization code scaffold according to a visualization specification may be used to generate programmatic output that corresponds to the candidate analytics, which may thus be used to generate a visualization accordingly. In some examples, an infographic may further be generated based on the visualization and a prompt using a diffusion model.

The invention belongs to the technical field of water supply network water quality monitoring, and provides a water supply network trihalomethane prediction method based on a fusion model. Comprising the steps of original water quality data set acquisition, data preprocessing, CNN-BiLSTM-MultiHead Attention fusion prediction model construction, hyper-parameter optimization space and model evaluation function definition, model prediction and output evaluation, model parameter iteration and verification evaluation, model verification, sample importance display, to-be-detected water quality data set collection and trihalomethane prediction. According to the method, the convolutional neural network, the bidirectional long-short-term memory network and the multi-head attention mechanism are fused, so that the change characteristics of a plurality of conventional water quality indexes in the water supply network are efficiently learned and extracted, and better prediction precision can still be kept under the condition of less training data; and the prediction performance and generalization ability of the model in the aspect of predicting a plurality of target variables by using a plurality of input variables are remarkably improved.

The invention discloses a building block assembly specification generation method based on dynamic stress and related equipment. According to the method, data is extracted based on images of building block components, dynamic stress characteristics are calculated and coded in a partitioned mode, a stress transmission relation is determined, key nodes are identified, an assembly step sequence is decomposed according to the key nodes, and finally an assembly specification considering dynamic stress is generated. According to the method, geometric and connection information of building block components is extracted, and dynamic stress characteristics and a transmission relation of the building block components are further calculated and analyzed, so that key stress nodes which are crucial to structural stability are identified. On the basis of the key nodes, the splicing process is decomposed into a step sequence considering stress balance, so that a splicing instruction containing stress analysis is generated, the stability of components in the building block splicing process is improved, professional splicing guidance containing dynamic stress information is provided for a user, and the building block splicing efficiency and success rate are effectively improved.

The invention provides a SuperPoint variant network image feature extraction method and system based on a multi-attention mechanism, a SuperPoint variant network is designed, the SuperPoint variant network comprises a backbone coding network, an interest point decoding network and a descriptor decoding network, an RE-SE module is designed in the backbone coding network, and the rotation robustness of the backbone coding network is enhanced; an SW-MA module is applied to the POI decoding network, so that the local feature extraction capability of the POI decoding network is improved; an EN-GA module is applied in a descriptor decoding network, the calculation amount is reduced through downsampling, and the network pays attention to more abstract features. The SuperPoint variant network provided by the invention can maintain high-precision interest point detection and descriptor matching capability in a complex scene, and further improves the pose estimation precision and robustness of the SLAM system.

The invention belongs to the technical field of image data processing, relates to a ground identification generation method and system based on an airport detailed rule AIP map, and aims to solve the problems that an existing identification generation method is incomplete in information, poor in adaptability and insufficient in compliance. The method comprises the following steps: acquiring an ICAO rule vector; constructing a knowledge graph based on identification information in an airport detailed rule AIP graph, and obtaining AIP graph symbol features; performing cross-modal feature alignment on the satellite image and the AIP symbol features, extracting multi-scale features of the satellite image, constructing a three-layer feature fusion network in combination with the feature-enhanced AIP symbol features, and weighting to obtain comprehensive features; and inputting the comprehensive feature and the ICAO rule vector into a condition GAN generator to generate an identification image. According to the method, three types of heterogeneous data of the satellite image, the AIP map and the ICAO rule are deeply fused, the accuracy is higher, and the method can adapt to different standards and environments.

The invention provides an atmosphere furnace surge flask bubble monitoring system and method based on machine vision. The image acquisition module is used for acquiring a multi-dimensional video image in a target area, wherein the multi-dimensional video image comprises a motion state of bubbles in liquid, real-time data reading on an atmosphere furnace digital display controller and an accurate indication condition of a gas cylinder pressure reducing valve gas pressure pointer display area; the data processing unit carries out fine processing on the acquired video image; the characteristics of bubbles are highlighted; the boundary of the bubble is accurately determined; calculating the flow velocity of the bubbles by using an optical flow method, and obtaining an accurate result by analyzing the position change of the bubbles between adjacent frames; counting the number and size of bubbles based on contour analysis; and the analysis and alarm module performs correlation analysis on the bubble parameters and the environmental parameters, generates a relation curve, presets a threshold value, and triggers alarm when the parameters are abnormal. According to the invention, real-time dynamic detection and deep analysis of parameters of bubbles in the surge flask of the atmosphere furnace can be accurately realized.

The invention relates to the technical field of artificial intelligence, in particular to a video GIS intelligent analysis method based on deep learning, and the method comprises the steps: detecting a target in a video in real time through a predefined target detection model, and generating a space-time mark which comprises a bounding box and category information; thirdly, associating target tracks of different cameras by using a dynamic graph model and a dynamic graph neural network to form a space-time ID and a track chain; then, combining a visual inertial odometer and a geographic information system to calibrate a homography matrix, and mapping the trajectory chain to a geographic coordinate system to obtain space-time trajectory data; then, constructing a neural network model and a trajectory generation model, and respectively predicting crowd density distribution and pedestrian motion trajectories; and finally, carrying out real-time alarm according to the track and the multi-level geo-fencing rule. According to the invention, intelligent analysis of video data is realized, target tracking and alarm capabilities are improved, and the method is widely applicable to the fields of crowd management and safety monitoring.

The invention discloses a biological information drawing system based on multiple agents. Relates to the field of artificial intelligence, and comprises a supervisor agent used for receiving a drawing request of a user, analyzing semantics of the drawing request, generating a drawing task and sending the drawing task to a drawing agent; the drawing agent comprises a biological information drawing library and is used for analyzing semantics of the drawing task, determining a biological information drawing template corresponding to the semantics from the biological information drawing library, generating a drawing code based on the semantics and the biological information drawing template and executing the drawing code to obtain a target drawing, the biological information drawing library comprises a plurality of biological information drawing templates. Through the method and the device, the problem of low biological information drawing efficiency in related technologies is solved.

The invention discloses an AI diffusion model pattern generation platform and method, the generation platform comprises a visual interaction module, an image generation module and a pattern mapping module, and the image generation module comprises a training sub-module and a reasoning sub-module; the generation method comprises the following steps: preprocessing a text input by a user and an optional structure image, and outputting standardized data; a semantic embedding vector is generated through text coding; carrying out LoRA fine tuning to obtain a style weight module; a ControlNet structure condition is injected; performing diffusion sampling to generate candidate patterns; performing CLIP scoring to screen an optimal pattern; and outputting the optimal pattern and previewing the carrier map. According to the platform and the method provided by the invention, the LoRA low-rank fine tuning, the ControlNet structure condition control and the CLIP similarity evaluation algorithm are fused, so that the effects of customizing the special style pattern with a small number of samples at low cost and accurately controlling the structure and style of the pattern are realized.

The invention provides a structured data representation method, a structured data conversion method, a structured data scheduling method, a structured data conversion device, a structured data scheduling device, a structured data conversion system, a medium and electronic equipment. The representation method comprises the following steps: responding to an operation of dragging a module from a module library to a visual editing canvas by a user to form a node corresponding to the dragged module; responding to the operation that a user establishes visual connection between input ports and output ports of different nodes on the canvas to form edges, wherein the edges define a data flow and calculation dependency relationship between the nodes; a structured data representation of a machine-readable AI model structure is generated based on all the nodes on the canvas and user-configured parameters thereof, and a set of edges defining the edge interconnection relationship. According to the representation method, conversion from graphical representation to structured data of the artificial intelligence model is completed.