Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

52results about How to "Avoid computational overhead" patented technology

Communication content security encryption method

The invention discloses a communication content security encryption method, and relates to the technical field of communication content security encryption, and the method comprises the following steps: receiving a to-be-encrypted data stream from a communication device, the data stream comprising a plurality of data packets, and each data packet carrying a to-be-encrypted communication content; the method comprises the following steps: classifying received data streams, dividing the data streams according to priorities and data types of the data streams, and applying a preprocessing algorithm to different types of data so as to optimize encryption operation. According to the method, the data flow is classified and preprocessed, so that the amount of data needing to be encrypted is reduced, and the workload of encryption operation is reduced. A proper encryption algorithm is dynamically selected according to the data priority and the equipment performance, delay is reduced, and the processing speed is increased. The lightweight encryption algorithm is used to automatically adjust encryption strength, reduce CPU and memory consumption, reduce energy consumption, reduce equipment heating, prolong battery life, and optimize system performance.
Owner:DATANG INVESTMENT HOLDING DEVELOPMENT (SHANGHAI) CO LTD

Enterprise data asset auditing method and system based on big data

The invention belongs to the technical field of data asset management, and discloses an enterprise data asset auditing method and system based on big data, and the method comprises the steps: collecting financial information data, business operation data, management decision data and external industry data of an enterprise; preprocessing the collected financial information data, business operation data, management decision data and external industry data to obtain a financial feature data set, a business operation feature data set, a management decision feature data set and an external industry feature data set; performing feature extraction and weighted fusion on the financial feature data set, the business operation feature data set, the management decision feature data set and the external industry feature data set to obtain a comprehensive feature data set; constructing an audit risk prediction model, inputting the comprehensive feature data set into the audit risk prediction model, and predicting to obtain an audit risk coefficient of the enterprise data assets; and a more comprehensive view angle is provided, and the data asset risk of the enterprise can be evaluated more accurately.
Owner:SHENZHEN JIANAN RUNXING SAFETY TECH CO LTD

Polyethylene pipe sweat soldering defect detection system based on microwaves

The invention discloses a microwave-based polyethylene pipe hot-melt welding defect detection system, and relates to the technical field of polyethylene pipe hot-melt welding joint defect detection, and the method comprises the following steps: firstly, collecting microwave reflection signals of normal and defect-containing hot-melt welding joints, and carrying out normalization; the processed signals are sliced, sliced fragments are labeled, time domain and frequency domain features are extracted, and a defect sample data set is constructed; carrying out feature selection on the extracted features, and selecting 10 features with the highest contribution to the recognition accuracy; constructing a support vector classifier model, performing training by using the data set after feature selection, and performing hyper-parameter optimization on the model to obtain an optimal classification model; designing and realizing a polyethylene pipe hot-melt welding defect detection system, and detecting whether a welding position contains defects and defect positions or not; according to the invention, accurate detection of polyethylene pipe hot melting welding defects can be realized, defects and positions can be rapidly identified, and technical support is provided for quality safety detection of polyethylene pipes.
Owner:SOUTHWEST PETROLEUM UNIV

Meat freshness anti-light interference detection method, device and program product

The invention provides a meat freshness anti-light interference detection method and device and a program product, and the method comprises the steps: making a meat freshness data set through employing an image collection system under different illumination conditions, carrying out the preprocessing of an obtained image, optimizing a MobileNetV3 model through employing an Officent Channel Attention module, and carrying out the detection of the meat freshness through employing the MobileNetV3 model, thereby achieving the detection of the meat freshness through employing the MobileNetV3 model, and achieving the detection of the meat freshness through employing the MobileNetV3 model. After training, a meat freshness detection model with high accuracy and light weight is obtained. According to the invention, by introducing an anti-light interference technology and an improved deep learning model, the accuracy and adaptability of detection are significantly improved; non-contact detection is adopted, so that food safety is guaranteed; comprehensive detection results and suggestions are provided in a program product, so that the practicability is enhanced; the advanced image recognition technology is converted into convenient mobile application, and the use threshold is lowered. The method provides a simple, reliable and economical meat freshness detection approach for common consumers, and has a wide application prospect.
Owner:JIANGSU ACAD OF AGRI SCI

Hierarchical system tuning method and system based on large language model

The invention discloses a hierarchical database system tuning method and system based on a large language model, and relates to the technical field of database system tuning. The method comprises the steps that expert knowledge in the database field is processed based on a large language model, a cue word integration algorithm is used for converting the knowledge into structured knowledge capable of being used by a computer so as to optimize a search space, and a coarse granularity-fine granularity Bayesian optimization algorithm is used for determining optimal configuration, so that configuration optimization of a system level is completed; a parameter screening algorithm, a space pruning algorithm and a context Bayesian optimization algorithm are utilized, and an optimal execution plan is generated by selecting an appropriate optimization prompt for each query in the complete workload, so that configuration optimization of query levels is completed. According to the method, the search space is optimized by utilizing expert knowledge, the optimized space is explored by utilizing a Bayesian optimization algorithm, multi-level optimization is performed on the database system from a system configuration level and a query level, and the optimization efficiency and the system performance are improved.
Owner:ZHEJIANG NEW INTERNET EXCHANGE CENT CO LTD +1

Non-paired cross-modal medical image conversion method based on contour guide path regularization

The invention belongs to the technical field of medical images and deep learning, and particularly relates to a non-paired cross-modal medical image conversion method based on contour guide path regularization, which comprises the following specific steps: constructing a conversion path from a source domain to a target domain; a path regularization method is applied to smooth path transition and ensure the stability in the image conversion process; according to a path regularization technology based on contour guidance, the model can be focused on a key anatomical region, the structural consistency and accuracy of the generated CT image are further improved, and the training time can be remarkably shortened by reducing additional training steps. The invention aims to simplify the unsupervised training normal form and overcome the defects of the traditional GAN-based single-step generation method in the aspect of capturing the complex anatomical structure of the medical image. While the training time and the sampling time are considered, the problem that the quality of the generated medical image is limited is overcome.
Owner:GUANGDONG UNIV OF TECH

Fast expansion method based on run length coding

The invention relates to a quick expansion method based on run length coding, which comprises the following steps of: S1, taking a binary image as an input region and carrying out run length coding to obtain a run length; inputting expansion parameter height and width; s2, judging whether the height and width of the expansion parameters are less than or equal to 0; s3, judging whether the input area is rectangular or not; s4, calculating the number of possible maximum distribution runs, wherein the maximum run number is obtained by multiplying the run number of the input area by the input expansion height; s5, calculating the number of times required to be iterated; s6, executing expansion in the horizontal direction; s7, expansion in the vertical direction is executed; and S8, merging all the moved run length codes. According to the method, the run length coding technology is introduced, the algorithm execution process and the data representation mode are optimized, the defects and problems existing in the prior art are solved from the aspects of storage, calculation, internal storage, real-time performance and the like, the efficiency and performance of binary image expansion operation are improved, and important technical progress is brought to the field of image processing.
Owner:BEIJING FOCUSIGHT TECH

River surface space-time image validity identification and speed measurement method based on deep learning

The invention discloses a river surface space-time image validity identification and speed measurement method based on deep learning, and the method comprises the steps: collecting a natural river video in a model training stage, and synthesizing and screening out space-time images STI of different scenes; dividing the textural features into effective, unreliable and invalid three classes according to whether the textural features can represent the actual flow velocity, and further training a classification network model; semi-automatic marking of texture principal direction MOT is carried out on the effective STI, data expansion is carried out by adopting overturning, rotating and color jitter modes to construct an MOT regression data set, and a regression network model combining grouped convolution and a convolution attention module optimization residual module is trained; in the flow velocity measurement stage, the classification network model is identified as effective STI, MOT is detected by applying a regression network model and converted into flow velocity, and interpolation correction is performed on unreliable, invalid and blind area flow velocity in combination with a section flow velocity distribution law to obtain a section flow velocity field. According to the invention, after training is completed, accurate flow measurement and flow velocity correction can be realized without manual parameter adjustment and addition of an experimental river data set.
Owner:HOHAI UNIV

Lightweight integrated model system for public opinion popularity prediction and training method thereof

The invention discloses a lightweight integrated model system for public opinion popularity prediction and a training method thereof, and the system is characterized in that the system comprises a public opinion popularity prediction model module, the public opinion popularity prediction model comprises a plurality of parallel basic networks and a multi-head attention layer which is used for converting the output of the basic networks into a two-dimensional matrix form as input and is constructed based on a recurrent neural network; the deployment module is configured to deploy the public opinion popularity prediction model as a complete prediction model and a lightweight integration model to the server module and the browser module through a deep learning framework; the acquisition module is configured to acquire public opinion data of the social platform as a training set or to-be-predicted data; the server module is configured to store the complete prediction model and obtain a training set to complete training of the complete prediction model; and the browser module is configured to load model parameters of the trained complete prediction model to the lightweight integrated model, acquire to-be-predicted data, input the to-be-predicted data into the lightweight integrated model, and complete public opinion popularity prediction.
Owner:SICHUAN JIUZHOU SOFTWARE CO LTD

Channel prediction method and system based on multi-cycle feature convolutional network

The invention provides a channel prediction method and system based on a multi-cycle feature convolutional network. According to the method, context sensing weighted input and a dynamic multi-model pool mechanism are introduced. A terminal device obtains environmental context features in real time, dynamically calculates the weight of each time step in a historical channel state information sequence based on the features, and generates a weighted optimized input sequence. Meanwhile, the network equipment pre-trains and maintains a plurality of multi-period feature convolutional network models specific to different environments, and the network can effectively capture the complex time-varying rules in the period and during the weeks in the channel, so that the accuracy of channel state information prediction is improved. And the terminal equipment immediately selects and activates the optimal sub-model in the model pool for prediction according to the real-time context features, and locally performs increment fine adjustment. According to the invention, through management of the data input end and rapid and adaptive switching of the prediction model end, the precision of channel prediction and the adaptive capacity to environmental sudden change are effectively improved.
Owner:NANJING UNIV OF POSTS & TELECOMM

An AI-based DDR5 memory interface chip adaptation method and system

The application relates to the technical field of chip design, in particular to an AI-based DDR5 memory interface chip adaptive method and system.The method comprises the following steps: obtaining a configuration instruction stream, extracting current and historical configuration instructions, and predicting target pins, switching time and target modes.Before the switching time, target electrical parameters are calculated according to pin electrical characteristics, historical switching records and channel load characteristics.During the switching, the target parameters are loaded and the temporary impedance matching network is switched in.After the switching, a fine-tuning increment is generated according to the deviation of the signal quality and the threshold value, and the updated electrical parameters are obtained by superposition, and the matching network is disconnected after the updated electrical parameters are written back to the register.According to the timing error and the fine-tuning increment generated by multiple switching, the weight parameters are updated and deployed back to the chip.Through AI prediction and the dynamic switching and fine-tuning of the temporary impedance matching network, seamless, stable and low-delay mode switching of the memory interface chip in the reconfigurable computing system is realized.
Owner:GUANGDONG QIMINGXIN STORAGE TECHNOLOGY CO LTD

Line character fusion character string recognition method and system for ancient book optical character recognition

PendingCN122737964AMake up for the lack of recognitionretain the advantage
The application discloses a line character fusion character string recognition method and system for ancient book optical character recognition, and belongs to the technical field of ancient book digitization. The method takes an ancient book character string as a recognition unit, adopts a transformer to model a global context, triggers a single character expert branch through a confidence degree guiding mechanism, and performs fine-grained verification on low-confidence difficult characters. A visual-semantic-character shape joint fusion strategy is combined to complete candidate reordering, and the recognition efficiency of high-frequency characters, the recognition accuracy of long-tail characters, variant characters and complex character shapes are taken into account. The system comprises visual coding, line-level recognition, single character verification and candidate fusion modules, can effectively solve the recognition bottleneck of large character sets and long-tail distribution of ancient books, improve the fidelity and reasoning efficiency of variant characters, greatly reduce the manual correction cost of ancient book digitization, and is suitable for large-scale ancient book digitization scenarios.
Owner:杭州宇原科技有限公司 +1

Method and system for processing tasks

The present application relates to a method for processing a task, comprising: a neural network (NN) model for processing the task receiving input data, the NN model comprising a plurality of layers in a sequence, one or more premature-exit points disposed between the plurality of layers, dividing the NN model into two or more sub-blocks, each sub-block comprising one or more layers, an output sub-NN and a confidence estimation sub-NN are arranged at each of the one or more pre-exit points; the output sub-NN at the early leaving point generates early leaving output data related to the task based on the feature map output by the sub-block corresponding to the early leaving point, and the confidence estimation sub-NN at the early leaving point predicts the confidence of the early leaving output data of the early leaving point based on the feature map output by the sub-block corresponding to the early leaving point; and on the basis of the predicted confidence coefficient, determining that the early-leaving output data is used as an output result of the task or providing the feature map output by the sub-block corresponding to the early-leaving point to the next sub-block for processing.
Owner:ROBERT BOSCH GMBH

Transmission tower tilt detection method and system based on point cloud completion and robust fitting

The application discloses a transmission tower tilt detection method based on point cloud completion and robust fitting, comprising: tower point cloud integrity pre-detection; missing area recovery is performed on the point cloud determined as incomplete; K-center robust fitting method is used to calculate the tilt ratio of the complete point cloud; and the final tilt percentage is output according to the tilt percentage difference of the point cloud. The transmission tower tilt detection system based on point cloud completion and robust fitting comprises a tower point cloud integrity pre-detection module, a PFAR Net point cloud completion module, a K-center robust fitting tilt calculation module and a threshold trigger type weighted fusion output module connected in sequence. The transmission tower tilt detection method and system based on point cloud completion and robust fitting enhance sparse structure geometry modeling through a neighborhood-point attention mechanism, and eliminate the splicing boundary cracks through a displacement field fusion refinement network; the completion chamfer distance is reduced compared with the original PF-Net, and the generated point cloud is highly consistent with the true missing area.
Owner:XIAN UNIV OF TECH

A patent retrieval and technology monitoring method for multi-source heterogeneous data

This invention relates to a method for patent retrieval and technology monitoring of multi-source heterogeneous data. It constructs a multimodal semantic representation including text, images, and time-series fragments, and generates a joint temporal representation vector by combining attention perturbation entropy and term evolution distance. A unified semantic space is established based on historical technology anchors, dynamically monitoring and quantifying semantic shifts to achieve real-time determination of drift trends. When substantial semantic drift occurs, local semantic correction is performed using gated contrastive learning and an anchor-aware adaptation layer to guide the orderly alignment of newly added modal features, ensuring the continuation and expansion of the original semantic topology. Simultaneously, an anchor decay and candidate new anchor generation mechanism is designed, combining cross-validation from patent citations, industry reports, and policy documents to achieve incremental expansion of the semantically stable anchor set. This scheme effectively improves the fusion accuracy, real-time adaptability, and dynamic topology update capability of multimodal patent data.
Owner:SHANDONG BITGO DATA TECHNOLOGY CO LTD

Method for simulating and planning of device cluster job based on multi-agent cooperation

PendingCN122509035AWith dynamic envelope characteristicsImprove robustnessPathPingReachability
The present application relates to the field of simulation technology, specifically to a device cluster job simulation planning method based on multi-agent cooperation, which constructs a land grid model and a yield density upper and lower bound channel, determines the capacity critical threshold interval by forward cumulative scanning, generates a target point based on the interval midpoint and passability constraints, and realizes cooperative device path guidance. The target point offset gating mechanism is introduced to control path re-planning triggering, improve path stability and responsiveness. The interval boundary is dynamically modified during the job process by combining the measured yield, and the final meeting point is locked when the interval length and meeting distance conditions are met. After the simulation is completed, the attribution analysis is performed by locking the deviation and cumulative displacement indicators, the row sequence is adjusted and iteratively re-simulated and optimized by combining the row accessibility, and the optimal job scheme is output. The method can improve the efficiency and simulation accuracy of device cooperative operation in complex environments.
Owner:LIANYUNGANG SHUANGYA MACHINERY CO LTD

Power grid fault traveling wave positioning method based on fusion optimization algorithm

The application provides a power grid fault traveling wave positioning method based on a fusion optimization algorithm, comprising: establishing a dynamic virtual fault framework model of a power grid, randomly generating a plurality of virtual fault particles containing position coordinates, and constructing an initial virtual fault particle cluster; using a shortest path algorithm to calculate the topological path length of each virtual fault particle in the virtual fault particle cluster to all measurement points in the power grid, and then calculating a virtual fault space-time feature vector; setting the traveling wave arrival time when a real fault occurs as a target clustering centroid in a feature space, and calculating a feature matching fitness; constructing a non-convex optimization problem with the optimal feature matching fitness as a target, solving the problem using a fusion optimization algorithm, and thus obtaining a fault positioning result and a traveling wave velocity, so as to realize traveling wave positioning. The application can solve the problems of local optimum, slow convergence speed and high calculation cost in the prior art.
Owner:EAST CHINA JIAOTONG UNIVERSITY +1

False data injection attack method for multi-elastic-joint robot system

The invention provides a false data injection attack method for a multi-elastic-joint robot system, and belongs to the technical field of multi-agent network attacks based on computer data processing. Firstly, a multi-elastic joint robot nonlinear dynamic mathematical model is constructed and converted into a high-order all-drive quasi-linear multi-robot system dynamic model based on an all-drive system theory; and then designing a distributed consistency controller containing a linearization item and a neighbor error related item, establishing closed-loop global dynamics and deducing a state analytical solution in combination with equivalent conversion of the model. Designing a false data injection attack strategy, and constructing an attacked system dynamic model; a closed-loop terminal state error in the presence or absence of attacks is taken as a target function, an attack optimization problem is converted into a combinatorial optimization problem, a greedy algorithm is designed by applying a sub-module optimization theory, and a suboptimal solution in polynomial time is obtained and is taken as an optimal scheme of false data injection attacks of the system. According to the method, the applicability of the complex nonlinear multi-agent system is improved, and the calculation complexity is reduced.
Owner:OCEAN UNIV OF CHINA

Improved tabu search topology optimization method and device for offshore wind farm power collection system

ActiveCN121881863BStrong global explorationStrong local development capabilitiesDesign optimisation/simulationConstraint-based CADCollection systemControl engineering
The application provides an improved tabu search topology optimization method of a marine wind farm power collection system, which is based on the positions of wind turbines to intelligently preliminarily group and sort, to form an initial connection scheme, to connect all the wind turbines in each group with the minimum cost, to calculate the group cable cost, to check whether the lines cross, to impose a penalty in the total cost if the lines cross, to ensure that the scheme is feasible, to compare the current scheme with the historical best, to update the record and intelligently exchange the wind turbine groups to explore a new scheme, to repeat the optimization process until the number of iterations is satisfied, and to finally output a globally optimal topology scheme. The application has the advantages of better optimization effect, significantly improved economy, higher calculation efficiency, stronger engineering practicability, better algorithm robustness, better scheme reliability, high design automation degree and strong auxiliary decision-making capacity.
Owner:POWERCHINA ZHONGNAN ENG

A neural network training and optimization system oriented to medical knowledge

PendingCN122654666ASuppress applicable boundary drift phenomenonReduce the risk of erroneously generalizing to universal conclusionsMedical knowledgeEngineering
The present application relates to the technical field of model optimization, and is a neural network training and optimization system for medical knowledge, specifically comprising: boundary feature collection on medical knowledge training samples to obtain boundary indexes reflecting the relationship between conclusions and condition distribution; forming a condition decoupling representation according to the boundary indexes, which is used to describe the separation trend between conclusions and applicable conditions; using the condition decoupling representation to correct the evaluation of model training intermediate quantity, obtaining sample-level boundary loss indexes, and aggregating to obtain knowledge cluster-level boundary loss indexes; jointly mapping the knowledge cluster-level boundary loss indexes and external disturbances to obtain boundary expansion probability and enclose the knowledge cluster to be reviewed according to the boundary expansion probability; using probe samples to perform targeted verification on model output, and tracing abnormal output to knowledge anchor points to be corrected to perform differential optimization processing. The present application solves the problem of condition boundary loss of neural network models in the prior art.
Owner:BEIJING ZILUOLAN TECHNOLOGY CO LTD

Image processing-based LED display screen display unevenness adjustment method and system

PendingCN122658218AImprove display uniformityImprove architecture robustnessImaging processingLED display
The application relates to an LED display screen display non-uniformity adjusting method and system based on image processing, which comprises the following steps: converting the obtained real-time multi-source physical state parameters into a two-dimensional pixel-level feature map through spatial interpolation mapping; obtaining a transient environmental deviation matrix, combining a cumulative lighting duration map to obtain a long-acting aging deviation matrix; weighting and fusing the two to obtain an overall deviation matrix, and generating a target update instruction set according to the comparison result of the regional gray variance of the overall deviation matrix and a preset gradient threshold; in response to the instruction set, superimposing a preset static reference correction matrix and the overall deviation matrix to generate a preliminary dynamic correction matrix, and performing boundary smoothing processing on the preliminary dynamic correction matrix through a spatial edge-preserving filtering algorithm to obtain an adaptive target correction coefficient matrix; finally, mapping and converting a video source data frame and the matrix point by point into an actual driving signal rendering output. The application can improve the accuracy of LED display screen display non-uniformity adjustment.
Owner:ANHUI HENGGUANG SEMICONDUCTOR CO LTD

Pollution attack node identification method, device and storage medium based on self-checking technology

The present invention discloses a contamination attack node identification method, device and storage medium based on self-checking technology. The present invention comprises the following steps: first, in the system initialization stage, the source node needs to determine the total number of layers of the network and allocate corresponding random number seeds to the nodes in the network; secondly, data transmission is performed: then the source node starts malicious node identification: if one or more of the destination nodes find that there is a contamination attack in the network during the data transmission stage, it will immediately send an alarm message to the source node and trigger the identification process of the malicious node. Finally, after completing the identification process of all the first-layer nodes, the source node informs the possible malicious nodes and starts the identification process layer by layer. The present invention can effectively identify potential contamination attack nodes in the network, thereby ensuring the transmission performance and network stability of the network.
Owner:HANGZHOU QULIAN TECHNOLOGY CO LTD

AI Agent-Based Creative Process Decision-Making Execution Method and Device

This invention provides a method and apparatus for decision-making and execution in a creative workflow based on an AI agent. The method includes: normalizing natural language instructions to obtain normalized text; inputting the normalized text into a rule engine to generate a first modality and its first confidence level; if the first confidence level is greater than or equal to a first threshold, determining the first modality as the target modality; otherwise, inputting the normalized text into a pre-trained modality classification model for inference to generate a second modality and its second confidence level; if the second confidence level is greater than or equal to a second threshold, determining the second modality as the target modality; otherwise, triggering a user fallback confirmation process to receive user confirmation of the target modality; and forwarding the natural language instructions to the work creation engine corresponding to the target modality to generate the target work. This invention achieves automated and intelligent determination of creative modalities, simplifies user operation processes, and improves user interaction experience and the efficiency of creative workflow decision-making and execution.
Owner:WUHAN MAIYI INFORMATION TECH CO LTD

Enhanced generation method based on topology-aware graph encoding and adaptive subgraph retrieval

The application provides an enhanced generation method based on topology-aware graph coding and adaptive subgraph retrieval, including multi-granularity semantic-aware segmentation and knowledge graph construction, structure feature matrix construction and explicit topology position coding generation, constrained subgraph diffusion and dynamic pruning based on semantic-topology joint scoring, and graph-text consistency loss constraint generation based on attention matrix structured alignment; in the coding layer, explicit topology position coding is used to avoid the overhead and excessive smoothing caused by online GNN aggregation; in the retrieval layer, connected subgraphs instead of fragmented nodes are used as enhanced context; in the alignment layer, the internal attention matrix of the large language model is directly constrained to be consistent with the subgraph adjacency matrix, the structured guidance is realized from the reasoning mechanism level, so that the logical illusion is inhibited and the multi-hop reasoning accuracy is improved.
Owner:XIAMEN UNIV

A multi-path adaptive full-focusing ultrasound imaging method for composite material corner regions

ActiveCN122259725BSolving Detection ChallengesImprove simulation accuracy
This invention relates to a multipath adaptive full-focus ultrasound imaging method for corner areas of composite materials. The method includes: acquiring full-matrix ultrasound data of the corner area of ​​the composite material; constructing a quasi-P-wave group velocity sound velocity model based on the characteristic parameters of the composite material; constructing a surface-layered discrete model with a local coordinate system, and abstracting it into a directed graph G based on the quasi-P-wave group velocity sound velocity model; searching for a set of candidate propagation paths from array elements to arbitrary nodes in the directed graph G, and constructing multiple full-focus imaging TFM images based on the candidate propagation paths and the full-matrix ultrasound data; calculating path score factors based on the multiple full-focus imaging TFM images, and performing pixel-by-pixel weighted fusion of the multiple full-focus imaging TFM images based on the path score factors to obtain a fused imaging result. Compared with existing technologies, this invention has advantages such as strong adaptability and improved focusing stability and imaging reliability in corner areas.
Owner:SHANGHAI RES INST OF MATERIALS CO LTD

Osgearth-based satellite orbit eci anchor rendering method

ActiveCN122597740Breduce loadEnsure geometry rendering accuracy
The application discloses a satellite orbit ECI anchoring rendering method based on osgEarth and relates to the technical field of three-dimensional geographic information system visualization.The method comprises the following steps: storing orbit geometry in the ECI coordinate system statically, performing GMST rotation rendering through a MatrixTransform node every frame;monitoring the satellite position deviation, correcting the error through a double-path mechanism of anchor point translation and asynchronous resampling; supporting double-mode orbit display, coordinating the main thread and the background thread by using an asynchronous request identification matching filter mechanism; realizing earth occlusion culling by judging the intersection between the line of sight and the earth sphere in the GPU pixel shader; and driving the satellite propagation and the ground entity kinematics model by using a unified simulation time axis.The application solves the problems of orbit line drift, high-orbit penetration artifacts and time-space reference inconsistency, and realizes efficient, accurate and drift-free rendering and sky-ground collaborative display in a large-scale satellite scene.
Owner:TIANJIN XUNLIAN TECH CO LTD +1

Vehicle detection method, lane line detection method and vehicle positioning method

The invention relates to a vehicle detection method, a lane line detection method and a vehicle positioning method. The invention firstly discloses a vehicle detection network and a lane line detection network. The vehicle detection network comprises a CSPDarknet backbone network, a feature pyramid and a prediction head which are connected in sequence, and the lane line detection network comprises an OfficientNet backbone network, a bidirectional feature pyramid and a segmentation head; secondly, a parking space positioning method is disclosed based on the vehicle detection network and the lane line detection network, and the overall vehicle positioning efficiency is improved through asynchronous processing of a vehicle detection task and a lane line detection task.
Owner:SHANXI JIAOJIAN MASCH HUAYANGHU CO LTD

A privacy-preserving vector database query method

This invention discloses a privacy-preserving vector database query method, comprising: each server obtaining a query vector secret share and performing a linear transformation to obtain a transformed query vector secret share; sending the locally held transformed vector data secret share and the transformed query vector secret share to semi-trusted hardware; the semi-trusted hardware performing a nearest neighbor search to obtain the nearest neighbor vector and its corresponding index; sharing the nearest neighbor vector and the one-hot vector corresponding to the index with each server; each server performing a dot product calculation between the one-hot vector secret share and the locally held label secret share to obtain a query result label secret share; performing an inverse linear transformation on the nearest neighbor vector secret share to obtain a query result vector secret share; and sending the query result label secret share and the query result vector secret share to the user terminal; the user terminal reconstructing the query result vector and the query result label.
Owner:CSG EHV POWER TRANSMISSION

A high-dimensional binary data hybrid index method and system based on hash table and B+ tree, a computer device and a storage medium

The application discloses a high-dimensional binary data hybrid index method based on a hash table and a B+ tree and relates to the technical field of data index, which comprises the following steps: receiving an operation request, wherein the operation request comprises a binary query hash code and a Hamming distance threshold; processing the operation request by using a pre-constructed hybrid index architecture and outputting a query result; the hybrid index architecture comprises a first index layer and a second index layer; the first index layer comprises a hash table and is used for processing point operations; the second index layer comprises a B+ tree and is used for processing range operations; and the operation request is processed by the precision lock before the operation request is processed by the first index layer and the second index layer, so that collision interception and state verification are realized, linear consistency is ensured, the Z-order encoding function is used to map and process the query hash code to obtain a key, part of the original Hamming space locality is reserved, the calculation of the Hamming distance is accelerated in parallel by combining the SIMD instruction, and finally, the retrieval effect with low delay and high throughput is realized.
Owner:HENAN UNIVERSITY OF TECHNOLOGY