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

1110 results about "Computational Technique" patented technology

Computational imaging. Computational imaging is a set of imaging techniques that combine data acquisition and data processing to create the image of an object through indirect means to yield enhanced resolution, additional information such as optical phase or 3D reconstruction.

Concrete mixing plant automatic control system based on intellectualization

The invention discloses a concrete mixing plant automatic control system based on intelligence, and belongs to the technical field of automatic control. Comprising a multi-modal sensing data acquisition module, an intelligent batching optimization module, a digital twin simulation module, a self-adaptive energy consumption management module, a fault self-diagnosis and predictive maintenance module, a dynamic quality tracing module and a multi-target collaborative scheduling module. Real-time synchronization of sensor data and a virtual model is realized in combination with an edge computing technology, dynamic and visual technical support is provided for full-flow simulation of the concrete mixing plant, and complex working conditions in production are reflected more truly; the system predicts a potential problem through a machine learning algorithm, triggers an early warning signal based on a multi-dimensional threshold rule, and generates a preventive maintenance plan in advance; the digital twin platform supports AR and VR interaction interfaces, so that an operator can visually observe the operation states of a virtual model and actual equipment.
Owner:GUIZHOU ZHONGGUOLEI BUILDING MATERIALS CO LTD

Heterogeneous data processing optimization system based on intelligent edge computing

The invention relates to the technical field of intelligent edge computing, and discloses a heterogeneous data processing optimization system based on intelligent edge computing. Comprising a heterogeneous data acquisition module, an edge preprocessing module, an intelligent optimization scheduling module, a heterogeneous fusion analysis module and a self-adaptive feedback control module. According to the system, data streams of different formats and protocols can be collected from a plurality of heterogeneous data sources in real time, and multi-modal correlation analysis is carried out after preprocessing and intelligent scheduling. Meanwhile, the system performance is optimized through self-adaptive feedback control, and a resource efficiency evaluation module and a safety compliance verification module are further arranged. According to the method, the problems of delay, accuracy, resource allocation, safety compliance and the like in heterogeneous data processing are effectively solved, the data processing efficiency and the system stability are improved, and the method is suitable for heterogeneous data processing scenes in the fields of industry, traffic, medical treatment and the like.
Owner:冯梓原

Karst collapse risk analysis method and system based on geological big data mining

The invention discloses a karst collapse risk analysis method and system based on geological big data mining, and the method comprises the steps: collecting multi-source heterogeneous geological data, and carrying out the data fusion through employing a Tucker decomposition-based tensor decomposition algorithm; cleaning, complementing and standardizing the fused data; feature selection and construction: selecting features related to the karst collapse risk; carrying out feature extraction on the preprocessed data; based on the features extracted by the feature engineering, constructing a risk assessment model by using a graph convolutional neural network, and optimizing model performance through an ensemble learning method; carrying out risk assessment and prediction by utilizing the trained model, and carrying out visualization through a geographic information system; and real-time risk assessment is realized based on an edge computing technology, and the model is continuously optimized. According to the method and the system, complex heterogeneous data can be processed, the time change trend of geological parameters can be accurately captured, the prediction accuracy under complex geological conditions is high, and the timeliness of early warning is greatly improved.
Owner:CHANGJIANG GEOTECHNICAL ENG CORP

Digital twin three-dimensional scene modeling method based on webGPU

The invention discloses a digital twin three-dimensional scene modeling method based on a webGPU, and relates to the technical field of three-dimensional scene modeling and graphic computing, multi-source sensing data are asynchronously sampled from sparse point cloud, a video texture sequence, a scene semantic tag graph and a structure boundary tuple, and a six-dimensional structure unit group is generated through a normalization operator; constructing a structural unit atlas with nodes representing component entities and edges representing constraint relations, and introducing a tension balance mechanism and multi-scale constraints to generate a modeling path prior model; constructing a graph calculation and graph rendering dual-channel assembly line in the WebGPU, and executing parallel texture mapping and boundary fitting operation; a dynamic sensing module is used for capturing scene disturbance and driving atlas response, and incremental reconstruction of the model is achieved; and finally, mapping the model to a Web terminal, and supporting microscopic semantic query and multi-layer data linkage. According to the method, the response speed, semantic consistency and structural adaptability of three-dimensional modeling in a complex environment are improved.
Owner:ZHEJIANG ZHEFENG YUNZHI TECH CO LTD

Food quality evaluation method and system based on big data

The invention relates to the technical field of food quality, in particular to a food quality evaluation method and system based on big data, and the method comprises the following steps: based on food freshness detection data, synchronously collecting food real-time images and environmental sensor data, including temperature, humidity, illumination and gas components, and carrying out data format unification and time synchronization calibration. According to the invention, technical support is provided for real-time monitoring and evaluation of food freshness and environmental conditions by synchronously collecting food real-time images and environmental sensor data, food quality can be accurately quantified through refined data integration and feature analysis, and particularly, the analysis of color, form and surface texture is more accurate. The time difference learning technology is combined with the cloud computing technology, so that the prediction capability of the food quality change trend is effectively enhanced, the food quality management has preventive and accurate future quality prediction, risks in production and supply chains are reduced, and the food safety and consumer satisfaction are improved.
Owner:SHANDONG AGRICULTURAL UNIVERSITY

Neural morphology calculation system and method based on spiking neural network

The invention relates to a neuromorphic computing system and computing method based on a spiking neural network, and the system comprises a neuromorphic processor which is used for constructing a hardware-based spiking neural network through employing a plurality of physical neurons, and carrying out the pulse coding and target recognition of a real-time input image; the central processing unit is realized on the basis of an RISC-V instruction architecture and is used for executing a control instruction required for constructing the pulse neural network; the neuromorphic processor is also used for carrying out online learning on the pulse neural network under the control of the control instruction; and the memory is used for storing program instructions required by the operation of the central processing unit and data transmitted between the central processing unit and the neuromorphic processor. The invention further provides a neuromorphic calculation method. According to the technical scheme of neural morphology calculation, high balance among precision, calculation speed and energy efficiency is achieved, and dynamic and complex task data can be processed accurately and efficiently with low power consumption.
Owner:JINAN UNIVERSITY

Computational techniques for three-dimensional reconstruction and multi-labeling of serially sectioned tissue

This document generally describes methods and systems for generating digital reconstructions of tissue from humans or other species. The method can, for example, include receiving, at a computing system, image data of a tissue sample, where one or more sections of the tissue sample are stained with hematoxylin and eosin (H&E), registering the image data to generate registered image data, identifying tissue subtypes based on application of a machine learning model to the registered image data, annotating the identified tissue subtypes to generate annotated image data, and determining a digital volume of the tissue sample in three dimensional (3D) space based on the annotated image data. The disclosed technology can provide for single-cell analysis and other analysis of tissue samples, such as early detection of cancer in human tissue samples.
Owner:JOHNS HOPKINS UNIVERSITY

Glacier area calculation method based on fusion of unmanned aerial vehicle and satellite remote sensing data

The invention relates to the technical field of remote sensing data processing and glacier area calculation, in particular to an unmanned aerial vehicle and satellite remote sensing data fused glacier area calculation method, which comprises the following steps of: cooperatively acquiring a satellite multispectral image and unmanned aerial vehicle high-resolution optical and LiDAR data, performing time synchronization, high-precision space registration and data enhancement processing, and calculating the glacier area through the unmanned aerial vehicle and satellite remote sensing data fusion. A satellite image glacier macroscopic feature and an initial mask are extracted by using a convolutional neural network and an NDSI / NDWI algorithm, and unmanned aerial vehicle image microscopic texture, edge and topographic features are acquired through a local binary pattern, edge detection and LiDAR point cloud; based on pyramid layering and a conditional random field, adopting a variance weighting algorithm to realize multi-scale feature level fusion; and after segmentation through an Otsu algorithm, calculating the area through a pixel counting method and introducing gradient correction, and evaluating the reliability through three types of precision. The method breaks through the limitation of a single data source, fuses macroscopic and microscopic features, improves the boundary positioning precision and calculation efficiency, and is suitable for glacier dynamic monitoring in a complex environment.
Owner:NORTHWEST INST OF ECO ENVIRONMENT & RESOURCES CAS

Display color adjusting method and system

The invention discloses a display color adjustment method and system, and the method comprises the steps: collecting the spectral data of ambient light in real time through a multispectral sensor according to the environment where a display is located; according to the visual preference of the user, utilizing a visual response model to extract visual features of the user; according to the environment light field dynamic data set and the user visual preference data set, color parameters of a display are adjusted through a dynamic optimization algorithm, and optimized color parameters are generated; according to the optimized color parameters, color presentation of the display is adjusted in real time through a color management engine, and the color management engine ensures low delay and high precision of color adjustment through a streaming computing technology and a distributed architecture to generate a final display effect. According to the embodiment of the invention, the method can adapt to the change of ambient light in real time, considers the visual preference of a user, and achieves the efficient and precise color adjustment.
Owner:GUANGZHOU XUNZHONG INFORMATION TECH CO LTD

Three-dimensional medical image visual language model pre-training method for reconstructing hybrid strategy

The invention discloses a three-dimensional medical image visual language model pre-training method for reconstructing a hybrid strategy, which belongs to the technical field of medical image calculation and comprises the steps of constructing a medical image text pair data set, a language text mask reconstruction strategy, a visual image mask reconstruction strategy, a semantic perception fusion strategy and multi-task joint learning. According to the method, the large language model is finely adjusted, the diagnosis and attribute information in the medical report is extracted by using the finely-adjusted large language model, the efficient prompt is generated, and the large language model has relatively high generalization ability, so that the cost of manual annotation is greatly saved; according to the semantic perception fusion strategy, the text feature obtained by the text encoder and the image feature obtained by the image encoder are combined to obtain the new text feature, so that the text perceives the diagnosis and attribute information of the image in advance, the alignment of the image and the text in the embedding space is further optimized, and the pre-training efficiency is improved.
Owner:XIDIAN UNIV

Neuromorphic visual target tracking method and system based on image processing

The invention provides a neuromorphic visual target tracking method and system based on image processing, and relates to the technical field of neuromorphic calculation, and the method comprises the steps: fusing the input of an event camera and a conventional image sensor, constructing a combined input tensor, and introducing a multi-scale convolution and synaptic event driving mechanism. Quick response and stable feature extraction of a high-speed moving target are realized, and coding block mistaken deletion and tracking loss caused by quick movement of the target are effectively avoided, so that system delay is reduced. Meanwhile, in combination with significance entropy difference evaluation and a dynamic brightness enhancement mechanism, the target judgment accuracy under low illumination and complex backgrounds is improved; redundant noise blocks are screened out through a significance weight function and confidence calculation, the redundancy calculation burden is relieved, and the lightweight characteristic of the system is guaranteed. A memory trajectory tensor and dynamic template adjustment mechanism based on a recurrent neural network is further introduced, time sequence consistency verification and self-adaptive updating are achieved, and the stability and robustness of the tracking process are enhanced.
Owner:DDPAI TECH CO LTD

Emotion detection system based on facial recognition

The invention discloses an emotion detection system based on facial recognition, and relates to the technical field of computer vision and emotion calculation. A video stream time sequence analysis module is used for extracting a facial micro-expression image sequence of continuous frames, a time sequence feature vector containing a micro-expression intensity gradient, an illumination robustness coefficient and a facial action unit cooperation feature is generated, and a multi-mode dynamic sensing module is combined to carry out real-time analysis on an emotion classification probability, voice emotion parameters and physiological signals. And the fusion decision module performs dynamic weighted fusion on the multi-modal data based on the scene adaptive weight, and finally generates a comprehensive emotion score. Through multi-modal time sequence modeling and a dynamic weight optimization mechanism, the accuracy and environmental adaptability of emotion recognition are remarkably improved, and real-time perception and accurate decision making of customer emotion are realized in a target scene.
Owner:NORTHEAST FORESTRY UNIV

Image classification method of hybrid quantum neural network model based on PQC

The invention discloses an image classification method of a hybrid quantum neural network model based on PQC, and belongs to the technical field of quantum computing. On the basis of a classic neural network structure, a classic convolutional layer is replaced by the parameterized quantum circuit, the trainable parameter quantity in the network structure is reduced, the designed entangled structure Ub is added in the parameterized quantum circuit, and the feature capture capability of the structure and the learning efficiency of the whole network are improved. A mixed quantum neural network architecture is utilized, a corresponding entanglement structure Ub is designed according to a given label sample and acts on a parameterized quantum circuit, and the entanglement structure Ub is combined with a classification module formed by a classic matrix product state network structure; the feature extraction capability of the parameterized quantum circuit structure and the performance of the overall network structure are continuously improved, so that a better classification effect is achieved, prediction is performed on a test set to evaluate the model performance, and finally parameter optimization and iterative updating in the model are performed by using a classical optimization method. And a hybrid quantum neural network structure with excellent performance can be obtained. Compared with an existing network structure, the performance is improved well.
Owner:ANHUI UNIVERSITY OF TECHNOLOGY

Power grid energy storage capacity demand determination method and system based on multiple time scales

The invention discloses a power grid energy storage capacity demand determination method and system based on multiple time scales, relates to the technical field of power grid energy storage capacity demand calculation, and aims to solve the problem of inaccurate energy storage capacity demand calculation. By generating multiple scenes, quantitatively screening key scenes and incorporating various uncertain factors, energy storage capacity calculation focuses on high-influence scenes, the coping capacity of the scheme to actual risks is enhanced, decision scientificity is improved, ultra-short-term to long-term multi-time scales are divided, core contradictions of all the scales are captured in a targeted mode, limitation of a single scale is avoided, and energy storage capacity calculation efficiency is improved. According to the method, capacity requirements and equipment distribution are integrated, operation rules are defined, visual documents are generated, multi-scale energy storage cooperative operation is achieved, the stability of a power grid is guaranteed, meanwhile, cost is reduced, scheme landing performance and operation efficiency are improved, multi-time-scale power grid state prediction is carried out based on a dynamic database, and historical rules and real-time data are combined, so that the power grid state prediction efficiency is improved. And the prediction coordination is ensured through multi-dimensional verification.
Owner:STATE GRID TIBET ELECTRIC POWER CO LTD ECONOMIC & TECH RES INST

Multi-level privacy protection remote human body scanning method and system

The invention provides a multi-level privacy protection remote human body scanning method and system, and relates to the technical field of privacy protection and data security. Comprising the steps that high-precision body data such as the body temperature, the heart rate, the blood oxygen level and a three-dimensional body model are collected through combination of an infrared sensor, an ultrasonic sensor and an optical sensor; encrypting the data by adopting three levels of encryption algorithms, namely symmetric encryption, asymmetric encryption and fully homomorphic encryption; transmitting the encrypted data through a secure TLS / SSL transmission protocol to ensure the confidentiality and integrity of the data in the transmission process; at a receiving end, decrypting the data by using a corresponding decryption method; a distributed storage technology is adopted for data storage, and secondary encryption and fragmentation storage are carried out, so that the security of the data is improved; and through a differential privacy technology and a multi-party security computing technology, the privacy in the data use process is further protected. According to the invention, through a multi-level technical means, all-around security and privacy protection from data acquisition, transmission, storage to use are realized.
Owner:SHAOXING NIANXINSHE TECHNOLOGY CO LTD

Pig behavior identification method and system

InactiveCN119131877ARealize functions such as growth assessmentHigh precisionCharacter and pattern recognitionBiological modelsData setSimulation
The invention relates to a pig behavior identification method and system. The pig behavior identification method comprises the following steps: acquiring a pig behavior image, and preprocessing the image to obtain a pig behavior identification data set; carrying out lightweight improvement on an original Y0L0v8 model framework, recording the original Y0L0v8 model framework as a YOL0-PIG model, and training the YOL0-PIG model; and running the trained YOLO-PIG model on the fog computing node, and performing real-time target detection and tracking on the video data to obtain the position, the motion trail, the behavior type and the state information of the pig. According to the scheme provided by the invention, the position, the motion trail, the behavior type and the state information of the pig can be detected through the improved YOLO-PIG model, video data processing and analysis tasks are distributed at the edge end in cooperation with a fog computing technology, and real-time rapid identification of the behavior of the pig in the pig house is realized.
Owner:YUNNAN AGRICULTURAL UNIVERSITY

Cross-platform virtual-real fusion scene construction method and system based on AI space calculation

The invention discloses a cross-platform virtual-real fusion scene construction method and system based on AI space calculation, and relates to the technical field of artificial intelligence and space calculation, and the method comprises the steps: carrying out the multi-scale feature fusion based on a received cross-modal conversion instruction set, and generating an initial image sequence; carrying out implicit field coding on a target object by combining a three-dimensional reconstruction algorithm to obtain an initial parameterized model; performing space-time alignment on the multi-view video stream, loading a digital scene asset package in combination with physical sensing data and a preset spatial index structure, and establishing a bidirectional data channel between a virtual scene and a physical sensor; performing rendering and illumination parameter adjustment on the initial parameterized model to obtain an optimized parameter model; performing differential coding processing on the optimization parameter model to obtain a target virtual-real scene fusion model; and distributing the target virtual-real scene fusion model to a preset terminal. The invention provides a virtual-real fusion construction method for end-to-end collaborative optimization, which is suitable for cross-platform live broadcast or dynamic interaction scenes.
Owner:ZHONGJING TECH (GUANGZHOU) CO LTD

Lightweight ViT based on image feature cutting and cloud edge knowledge distillation

The invention discloses a lightweight ViT based on image feature cutting and cloud edge knowledge distillation, belongs to the technical field of computer vision and edge computing, is used for efficiently deploying a ViT model on an edge device with limited computing power, and comprises the steps of designing a lightweight ViT Block and a sub-sampling Block. The method comprises the following steps: designing an image feature cutting module, collecting images by edge equipment, screening highly uncertain samples in the images as a knowledge distillation data set, and transmitting the knowledge distillation data set and local model parameters to a cloud end. A ViT model is deployed for the edge equipment with limited resources and weaker performance to carry out an image processing task, and the ViT is subjected to lightweight processing; therefore, the Flops of the model is reduced while the accuracy of the model is ensured.
Owner:NANJING UNIV OF POSTS & TELECOMM

Cutting path planning algorithm for semiconductor workpiece based on image processing

Disclosed is a cutting path planning algorithm for semiconductor workpiece based on image processing, belonging to the technical field of image calculation, and solving the technical problem of manually cutting off the heterocrystal region on the wafer, which includes the following steps: 1, obtaining a semantic boundary of an image; 2, finding a largest inscribed rectangle MRect in the single crystal image X1; 3. dividing the contour region in the single crystal region to find the corresponding cutting line; 4. determining the final cutting line. The cutting line planned by the application may realize automatic cutting of the wafer, and may better reserve the required single crystal region.
Owner:TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY

Intelligent parking unattended vehicle access management system and method based on edge calculation

The invention relates to the technical field of edge computing, in particular to an intelligent parking unattended vehicle access management system and method based on edge computing. The method comprises the following steps: a vehicle detection positioning unit obtains multi-modal data based on a multi-modal sensor array module, and realizes real-time positioning of a vehicle and real-time updating of a parking space state through a Kalman filtering algorithm in combination with a QBCN information interference variable; the license plate recognition unit completes license plate feature extraction and recognition on the basis of a multispectral imaging technology and a lightweight CRNN model under the condition of abnormal illumination. The edge calculation decision unit combines a real-time rule engine and a space-time anomaly detection algorithm, optimizes a resource allocation strategy, and realizes low-delay decision and localization control; the payment authentication unit adopts a block chain intelligent contract, dynamic rate calculation, multi-factor identity authentication and abnormal payment fusing protection; and the edge cloud collaboration unit realizes model differential updating, cross-domain task scheduling and energy efficiency optimization through federated learning and space-time data compression technologies.
Owner:中雄科技集团股份有限公司

Positioning method of large-space intelligent glasses, head-mounted display equipment and storage medium

The invention relates to a positioning method of large-space intelligent glasses, head display equipment and a storage medium, belongs to the technical field of meta-cosmic space calculation, and is suitable for a meta-cosmic positioning function that the head display equipment of players in a multi-user interaction large space can directly interact without learning or reasoning of a central server. A plurality of different texture pictures are arranged on the bottom surface or the ceiling of a large space, any camera on the intelligent glasses is used for collecting images, the texture pictures are recognized from the images collected by the camera T, picture information corresponding to the texture pictures is obtained, the world position of the camera T can be obtained through geometric calculation, and the texture pictures are displayed on the intelligent glasses. The method can be quickly realized on local head-mounted display equipment, so that the learning process of a server or the delay of image reasoning and position information returning and errors caused by a positioning sensor are avoided, and the problem of errors caused by long distance of a large-space site or shielded texture pictures is also avoided.
Owner:LUMIERA LTD

Information operation and maintenance monitoring system

The invention discloses an information operation and maintenance monitoring system, which belongs to the technical field of information operation and maintenance monitoring and comprises a heterogeneous data acquisition layer, a streaming processing engine, an intelligent analysis center, a closed-loop control module, a visual platform and a safety protection system. Physical equipment, virtualized resources and a cloud native environment can be fully covered, the breadth and depth of data acquisition are ensured, the adaptive sampling and edge computing technology improves the efficiency and real-time performance of data acquisition, the data transmission delay and the central processing pressure are reduced, a streaming processing engine and an intelligent analysis center are combined with various algorithms and models, and the real-time performance of data acquisition is improved. Millisecond-level data processing and anomaly detection are realized, the accuracy and timeliness of fault identification are improved, the root cause positioning and fault prediction functions help operation and maintenance personnel to quickly position the root cause of a problem and formulate preventive measures, and the fault occurrence probability and the influence range are reduced.
Owner:GINZA GROUP CO LTD

High-precision positioning mobile terminal device for electric power pipeline augmented reality inspection

The invention relates to the technical field of mobile positioning calculation, in particular to high-precision positioning mobile terminal equipment for augmented reality inspection of power pipelines, which comprises a PDA (personal digital assistant) handheld terminal, a camera is fixedly connected to one side of the PDA handheld terminal, a display is arranged at one end, far away from the camera, of the PDA handheld terminal, and an electronic compass, a gyroscope and a processing system are arranged in the PDA handheld terminal; the processing system comprises an image acquisition module, a calibration module, a positioning module, an inspection data acquisition module, a GIS (Geographic Information System) data request module, a data standardization processing module, an SAR (Synthetic Aperture Radar) space construction module, a reality rendering enhancement module and a display module. And the GIS two-dimensional spatial data of the electric power pipeline are converted into visual augmented reality SAR data, so that the maintenance difficulty of the urban cable pipeline data is reduced, and the efficiency of cross-department business cooperation in an electric power enterprise is improved.
Owner:K9 TECHS CO LTD +1

Urban intelligent drainage management system based on cloud-side cooperation

The invention discloses an urban intelligent drainage management system based on cloud-side cooperation. The system is designed to integrate advanced sensing technology, edge computing, cloud computing and artificial intelligence algorithms. The system core comprises a data acquisition module, an edge computing node, a cloud server and a user interaction interface, the data acquisition module is responsible for collecting key operation data of a drainage network in real time, and the edge computing node performs primary processing and real-time analysis on the data to quickly respond to abnormal conditions; the cloud server undertakes complex data analysis tasks and provides long-term trend prediction and optimization strategies; a user interaction interface adopts a visual design, supports multi-platform access, and provides real-time data visualization and operation control; the system also introduces a block chain technology and a community participation mechanism. The invention relates to the technical field of Internet of Things and cloud computing. The efficiency and response speed of urban drainage management can be better improved, and the urban waterlogging problem caused by rainstorm natural disasters is reduced.
Owner:CHINASOFT INTERNATIONAL SOFTWARE (SUZHOU) CO LTD

Tunnel apparent disease detection method and system based on deep learning and knowledge distillation

The invention relates to the technical field of tunnel crack detection and artificial intelligence edge calculation, and provides a tunnel apparent disease detection method based on deep learning and knowledge distillation, which comprises the following steps: step 1, introducing spectral domain information enhancement to an original tunnel image, the edge texture features of the disease area in the image are enhanced through methods such as multi-scale wavelet transform and small-scale enhancement. Step 2, constructing a high-performance teacher model, introducing a flexible up-sampling structure to adapt to feature recovery requirements of different levels of semantic information, introducing an efficient visual coding module to enhance feature fusion capability of different scale channels, and designing a scale adaptive weighted loss function at the same time; by introducing a frequency spectrum enhancement mechanism, structural features of disease areas with low contrast, fuzzy edges and the like are remarkably enhanced in an image preprocessing stage, clearer information input is provided for a model, and the stable recognition capability of a system in environments of uneven illumination, complex background and the like is enhanced.
Owner:INST OF GEOLOGY CHINA EARTHQUAKE ADMINISTRATION

Marine video concentration and intelligent retrieval method and system based on edge nodes

The invention provides a ship video concentration and intelligent retrieval method and system based on edge nodes, and belongs to the technical field of edge computing, and the method comprises the steps: S1, collecting ship video data; s2, an edge node generates a concentrated video and metadata through an improved Gaussian mixture model, an improved DeepSORT algorithm and a dynamic concentration proportion adjustment algorithm; s3, synchronously concentrating the index information of the videos and the metadata by each edge node through a publishing-subscribing mode; s4, training a lightweight intelligent retrieval model through a knowledge distillation algorithm; s5, calling the lightweight intelligent retrieval model to match the corresponding concentrated video clip, and returning a retrieval result; and S6, collecting feedback information of the user on the retrieval result, and performing incremental optimization on the lightweight intelligent retrieval model through an elastic weight consolidation algorithm. According to the invention, efficient monitoring management is realized through edge localization processing, cross-node cooperation and closed-loop optimization architecture, and the actual requirements of ship safety monitoring and operation management are met.
Owner:CHENGDU XIWU SECURITY SYST ALLIANCE

Light guide plate dot density detection method, system and device and storage medium

The invention discloses a light guide plate dot density detection method, system and device and a storage medium, and relates to the technical field of light guide plate dot density detection, and the method comprises the following steps: converting a historical light guide plate image into a historical light guide plate binary image based on a graying processing method and a binary processing method; obtaining a standard dot area and a dot area range based on the historical light guide plate binary image; obtaining a detection normal fitting area and a detection incomplete fitting area based on the standard dot area, the dot area range and the detection light guide plate binary image; calculating and obtaining the dot density of the detection light guide plate based on the detection normal fitting area and the detection incomplete fitting area; the method is used for solving the problem that errors are generated in dot density calculation due to the fact that edge incomplete dots are not analyzed and calculated in an existing light guide plate dot density calculation technology.
Owner:TWL OPTRONICS SUZHOU

Emotion analysis method, system and equipment based on multi-modal information and large language model and medium

The invention discloses an emotion analysis method, system and device based on multi-modal information and a large language model and a medium, belongs to the technical field of natural language processing and multi-modal calculation, and aims at solving the technical problem of how to overcome the defects of data distribution difference, modal credibility deviation and low generated data quality in the prior art. According to the technical scheme, the method comprises the following steps: collecting multi-modal data; multi-modal data preprocessing and feature extraction: preprocessing the text data, the image data and the audio data respectively and extracting corresponding features; feature alignment: mapping features of different modes of texts, images and audios to a unified potential space by adopting a cross-modal alignment algorithm, and eliminating semantic gaps among the modes; weight distribution: adopting a dynamic weight distribution mechanism to adaptively and dynamically distribute weights of different modes; performing cross-domain attribute-level sentiment analysis; evaluating the credibility; and calibrating the confidence coefficient.
Owner:INSPUR ENTERPRISE CLOUD TECHNOLOGY (SHANDONG) CO LTD

Industrial space intelligent association optimization system based on multi-dimensional data analysis

The invention provides an industrial space intelligent association optimization system based on multi-dimensional data analysis, which relates to the technical field of industrial space association and comprises the following modules: a data acquisition module, a data preprocessing module, an association analysis module, an optimization decision module, a prediction and feedback module and an intelligent self-learning module. The multi-source heterogeneous data collection and edge computing technology is adopted, real-time data collection from multiple sources such as a sensor network, satellite remote sensing and a public database is supported, data of all nodes in an industrial chain can be rapidly and accurately obtained through multi-dimensional data collection in a complex industrial environment, and the data of all nodes in the industrial chain can be rapidly and accurately obtained through an efficient data preprocessing module. The system can process data in various formats, including industrial chain data, economic activity data, geographic space data and the like, realizes unified normalization and cleaning of different data sources, and ensures the accuracy and consistency of the data.
Owner:SHENZHEN NATURAL RESOURCES & REAL ESTATE ASSESSMENT & DEV RES CENT (SHENZHEN GEOLOGICAL ENVIRONMENT MONITORING CENT)

Heterogeneous computing power cooperative scheduling system and method for mixed precision training

The invention discloses a heterogeneous computing power cooperative scheduling system and method for mixed precision training, and belongs to the technical field of artificial intelligence computing. The system comprises a computational graph analysis and operator portrait module which is used for analyzing and dividing a model computational graph and extracting operator features; the heterogeneous hardware capability sensing and matching module is used for managing performance files and real-time states of heterogeneous hardware in the cluster and matching optimal execution hardware for each calculation partition; and the data flow coordination and pipeline parallel controller is used for generating a global execution plan, managing cross-device data dependence and communication and calculating overlapping optimization execution efficiency through communication. According to the method, the problem of low scheduling efficiency of mixed precision training in a heterogeneous environment is solved, automatic and accurate mapping from a calculation task to heterogeneous hardware is realized, the training speed is remarkably improved, the training cost is reduced, and the overall resource utilization rate of a cluster is improved.
Owner:HANHOU (BEIJING) TECH CO LTD