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

1010results about How to "Improve processing speed" patented technology

Data acquisition processing method and system based on digital twin platform

The invention relates to the technical field of data acquisition and processing, in particular to a data acquisition and processing method and system based on a digital twin platform, and the method comprises the following steps: S1, the digital twin platform determines the position of a sensor based on a coordinate system, and creates a specific model for marking; s2, collecting multi-source data in an actual environment in real time; s3, carrying out primary processing on the collected data through edge computing equipment; s4, performing data fusion and enhancement by using a preset multi-modal data fusion algorithm; s5, carrying out dynamic simulation and prediction on an actual environment; s6, generating an optimization control instruction; and S7, regularly carrying out model calibration and parameter adjustment, and continuously optimizing the precision of the digital twin model. By integrating edge calculation and a multi-modal data fusion technology, high efficiency and accuracy of data processing are realized, meanwhile, the prediction accuracy is improved by combining physical simulation and machine learning, and the response speed and decision quality of the system are remarkably improved.
Owner:WENZHOU CHENXIN MASCH TECH CO LTD

Self-adaptive power grid state transformer area intelligent fusion terminal and control method thereof

The invention discloses a self-adaptive power grid state court intelligent fusion terminal and a control method thereof, relates to the technical field of intelligent power grids, and solves the defects that an existing fusion terminal is insufficient in self-adaptive capability and limited in data processing and analysis capability. Learning power grid state change in real time through a deep power grid dynamic control algorithm and a prediction analysis engine combining LSTM and random forest, and autonomously adjusting a control strategy; the edge calculation and distributed processing module is utilized, so that the data processing flow is optimized, and the data processing speed and efficiency are greatly improved; the application of time sequence analysis and a machine learning model further excavates and understands a complex data mode; the resource configuration efficiency is improved through an intelligent scheduling algorithm, and a cross-layer coordination mechanism is established through a distributed coordination algorithm, so that rapid issuing and feedback collection of a control instruction are ensured; according to the invention, the intelligent degree of the existing fusion terminal is greatly improved.
Owner:POWER RES INST OF STATE GRID SHAANXI ELECTRIC POWER CO LTD +1

Data storage method and system based on legal knowledge service platform and storage medium

The invention relates to the technical field of data storage, in particular to a data storage method and system based on a legal knowledge service platform. The method comprises the following steps: acquiring legal knowledge service data; performing data feature extraction based on data types, use frequencies, importance and timeliness on the legal knowledge service data, and performing clustering analysis to obtain classification result data; constructing a self-adaptive multi-level storage architecture model based on the classification result data; storage schemes of a hot data layer, a warm data layer and a cold data layer are determined according to the multi-level storage architecture model, and a data migration strategy model based on a historical access mode is established, so that an automatic data migration strategy among different levels is obtained. According to the method, the multi-level storage architecture model of the hot data layer, the temperature data layer and the cold data layer is constructed, hierarchical storage is performed according to the use frequency and importance of the data, and the access efficiency of the data and the utilization rate of storage resources are improved.
Owner:无锡中铠信息咨询服务有限公司

Image feature information extraction processing method and device

The invention discloses an image feature information extraction processing method and device, which can realize efficient and accurate processing of invoice and business ticket images, not only can automatically classify and preprocess the images and improve the distinction degree of characters and backgrounds, but also can accurately extract and identify key information, including character information and graphic marks, so that the image feature information extraction processing method and device can be applied to invoice and business ticket processing. Through semantic understanding and structured processing, in combination with a multi-modal fusion algorithm, the accuracy and integrity of information extraction are improved, and meanwhile, an intelligent verification and user interaction correction mechanism is introduced, so that the correctness of information is ensured. Finally, standardized output data can be directly connected with an enterprise financial system, all processing records and original images are safely stored, and powerful support is provided for financial management and auditing of enterprises. The automatic level of invoice and business ticket information processing is remarkably improved, the frequency of manual intervention is reduced, the processing speed and accuracy are greatly improved, and the error rate and the operation cost are reduced.
Owner:LEXIANG DIGITAL CO LTD

Real-time fault prediction method and system for central air-conditioning system based on digital twinning

The invention provides a central air-conditioning system real-time fault prediction method and system based on digital twinning, and the method comprises the steps: deploying various types of sensors for multi-dimensional detection, and collecting the data of the sensors; edge computing nodes are deployed around the central air conditioning unit; a digital twinborn model based on the central air conditioning unit is constructed according to the preprocessed data, a dynamic view of key performance indexes is provided, and the state of the central air conditioning unit is mapped and simulated in real time; designing a fault prediction model, and predicting and identifying faults; deploying the fault prediction model at an edge computing node and operating the fault prediction model, and performing real-time fault monitoring and diagnosis; when a fault is found, the AI-drive maintains decision support, and automatically adjusts a fault prediction model parameter or arranges a maintenance strategy; and constructing a learning loop based on performance feedback, and optimizing a fault prediction model and a maintenance strategy. Quantum calculation, the digital twinning technology and edge calculation are fused, and the operation efficiency and reliability of the central air conditioning system are remarkably improved.
Owner:GUANGZHOU CHUANGBO MECH & ELECTRICAL EQUIP INSTALLATION

Robot pose estimation method based on laser point cloud and visual SLAM

The invention discloses a robot pose estimation method based on laser point cloud and visual SLAM, and relates to the technical field of robot sensing and positioning, and the method comprises the steps: in a data collection and integration link, installing a specific camera and a radar to collect and compress data; a data preprocessing and feature strengthening stage: processing the image and the point cloud to improve the quality and extract the features; a cross-modal network is constructed through feature fusion and accurate matching, and a special matching mode is adopted; space-time calibration and coordinate unification are realized by means of a high-precision circuit; multi-modal fusion and reinforcement learning are applied to loop detection and intelligent optimization; correcting filtering and visualizing uncertainty by combining pose smoothing and intelligent output with a prediction model; according to the method, the pose estimation precision, reliability and environmental adaptability of the robot are effectively improved, resource utilization is optimized, the pose uncertainty is visually evaluated, and the overall performance and the intelligent level of the robot are improved.
Owner:ZHEJIANG SHUREN UNIV

Traffic accident identification method based on unsupervised pre-training and multi-modal large model

The invention discloses a traffic accident identification method based on unsupervised pre-training and a multi-modal large model, and the method comprises the following steps: S1, collecting and sorting video data in a traffic monitoring scene, selecting a video clip without a traffic accident as a data sample, extracting a video key frame, carrying out the unsupervised pre-training of a mask auto-encoder, and carrying out the unsupervised pre-training of the mask auto-encoder; reconstructing a video clip which is shielded randomly; s2, calculating a reconstruction error between the original video and the reconstructed video to evaluate the reconstruction quality, and screening out key frame video clips with poor reconstruction quality; according to the invention, through unsupervised training of the mask auto-encoder, even under the condition of limited annotation data, more traffic accident-free segments can be filtered, video segments in which traffic anomalies possibly exist can be rapidly screened out, and by constructing fine-tuning training of multi-modal traffic data on a multi-modal large model, the real-time performance of the model is improved. The method can improve the recognition accuracy and efficiency of a traffic accident in a complex scene, provides real-time alarm and detailed analysis, and takes countermeasures in time.
Owner:VEILYTECH

Disease and pest identification, prevention and early warning system and method

The invention relates to the technical field of disease and pest identification and control, in particular to a disease and pest identification and control early warning system and method, and the system comprises a data collection module, a polarization data analysis module, an image super-resolution processing module, a feature extraction module, a disease prediction module and a decision support module. According to the method, early recognition and accurate prediction of plant diseases and insect pests are achieved by integrating capture and analysis of spectrum polarization data, image super-resolution processing and time sequence analysis, fine structural changes of plant leaves are accurately captured through the polarized light technology, fine lesion features can be revealed by deeply analyzing the polarization data, and the accuracy of the plant diseases and insect pests is improved. The local spectrum enhancement technology further refines the image quality, it is ensured that the change of the cellular level can be accurately recognized, deep learning analysis is carried out in combination with environmental data, the disease development trend can be effectively predicted, and the processing speed and accuracy are improved.
Owner:成都海关技术中心

Data acquisition method and system based on industrial internet operating system

The invention relates to the technical field of industrial internet data acquisition, in particular to a data acquisition method and system based on an industrial internet operating system, and the method comprises the following steps: S1, detecting and recognizing data sources of a plurality of industrial devices and sensors; s2, collecting original data from a data source in real time, and preprocessing the original data; s3, distributing part of calculation tasks to a plurality of edge nodes; s4, storing the data in a distributed database or cloud storage in a classified manner; s5, performing fragmentation processing on the data in the cache; s6, performing data synchronization and consistency verification; and S7, converting the data into a corresponding format. According to the invention, by implementing efficient data fragmentation processing, a dynamic storage strategy and secure data consistency verification, the processing speed and storage efficiency of the industrial internet data acquisition system and the security and integrity of data are remarkably improved, and the requirements of high efficiency and high reliability of modern industrial production are effectively supported.
Owner:NANTONG SHIPPING COLLEGE

Cable vibration signal feature extraction and mode recognition method and cable maintenance method

The invention relates to the technical field of signal processing, in particular to a cable vibration signal feature extraction and mode recognition method and a cable maintenance method. The cable vibration signal feature extraction method comprises the following steps: S1, collecting vibration data along a cable in a differentiated state, and dividing data grades according to signal strength to obtain an optimized compressed data set; s2, segmenting the optimized compressed data set according to a signal change frequency to generate a segmented compressed signal set; s3, based on the segmented compression signal set, key time point extraction is carried out, feature mapping is established, and time frequency feature mapping is obtained; and S4, performing abnormal signal feature point identification through time-frequency feature mapping, recording the time and the frequency band where abnormal features are located, and generating an abnormal signal feature library. According to the method, the abnormal information can be identified more quickly and accurately, the prediction capability of potential abnormity is enhanced, and more targeted maintenance and prevention measures can be formulated.
Owner:CHONGQING TAISHAN CABLE CO LTD

Industrial automatic quality detection device based on image recognition

The invention relates to the field of automatic detection, and discloses an industrial automatic quality detection device based on image recognition, which is used for realizing quality detection of continuous image sequences in the production process of industrial products. The industrial automatic quality detection method based on image recognition comprises the following steps: by applying multi-channel image acquisition, an LSTM model, a GAN-EIS model and an EIS model, through a series of technical means, realizing efficient and accurate quality detection of a continuous image sequence in an industrial product production process. The method comprises the following steps: acquiring an industrial product image sequence by using multi-channel image data and a fusing processing technology; then, capturing change characteristics in a time dimension through an LSTM model, and predicting a potential quality problem; thirdly, generating a large number of fine defect images by using a GAN-EIS model, and enhancing a training data set; and finally, performing defect identification in combination with an EIS model, and comprehensively judging the quality condition of the product in combination with a time sequence change identification result.
Owner:CHANGZHOU INST OF TECH

Long-time sequence information prediction method based on multi-scale double-source fusion network model

PendingCN119670019AImprove adaptabilityReduce calculation biasTime domainAlgorithm
The invention discloses a long time sequence information prediction method based on a multi-scale double-source fusion network model, time domain and frequency domain features are modeled at the same time, the ability to understand a complex time sequence is enhanced, an efficient multi-scale attention module of cross-space learning can capture short-term and long-term dependency relationships at the same time, and the prediction accuracy is improved. The modeling capability of different time scale information is improved, dynamic weighted fusion of time domain and frequency domain features is realized by a gating mechanism, and the flexibility and robustness of the model are improved. And through standardization and size projection, feature deviation and memory occupation are reduced, model convergence is accelerated, and the overall memory demand is reduced. The efficient multi-scale attention module accurately captures features, weakens noise and abnormal value influences, and reduces unnecessary calculation and memory consumption. The gating mechanism dynamically adjusts the feature weight, preferentially processes key information, and reduces the memory demand.
Owner:HANGZHOU QITAI ELECTRONIC TECHNOLOGY CO LTD

Data security protection supervision system

The invention relates to the technical field of data supervision, in particular to a data security protection supervision system, which comprises an access monitoring module, a behavior abnormity monitoring module, a security configuration module and a data risk management module, and is characterized in that based on user access behavior data, access frequency and security level information are collected, and user behavior characteristics are automatically extracted; an access control snapshot is obtained. According to the method, through dynamic permission configuration and real-time abnormal activity monitoring, data access safety is remarkably improved, user behavior characteristics are automatically extracted, behavior deviation is analyzed, quick response to potential risks is ensured, and through the continuously-updated safety strategy and risk assessment, the safety of data access is greatly improved. The security measures are allowed to timely adapt to the constantly changing threat environment, and through detailed risk management, the processing speed and accuracy are improved, so that the data supervision is more efficient, the possibility of data leakage and abuse is reduced, and the flexibility and reliability of the system in the aspect of protecting data privacy and integrity are ensured.
Owner:SHANDONG WANLIHONG INFORMATION TECH

Power grid fault on-line identification system and method based on big data

The invention discloses a power grid fault online identification system and method based on big data, and relates to the technical field of power systems, and the method comprises the steps: collecting multi-source data of a power grid system through a sensor; data filtering is performed through a hierarchical storage strategy, a data lake is constructed in combination with multi-dimensional data indexes, and multi-source data is stored in a classified manner; aggregating and converting data in a data lake by adopting a real-time stream processing framework, and extracting high-dimensional features related to a fault by combining wavelet transform with principal component analysis; based on the high-dimensional features, identifying the real-time state of the power grid by using a graph neural network in combination with a deep learning model; and according to the identification result of the real-time state, combining a power grid topological structure, and carrying out fault positioning through a time difference method and a graph theory algorithm. The power grid fault on-line identification system based on big data provided by the invention can efficiently manage and store a large amount of multi-source data in a power grid, and improves the data processing and access speed.
Owner:BEIJING SHENGXINNUO TECH CO LTD

Fruit stem pose recognition method applied to pomelo picking equipment

The invention discloses a fruit stem pose recognition method applied to pomelo picking equipment, and the method comprises the following steps: carrying out the preprocessing of image data of a to-be-recognized scene, and obtaining the preprocessed image data; the image data comprises an RGB image and a depth image; inputting the preprocessed image data into the optimized instance segmentation model to obtain a depth map of a single pomelo fruit; on the basis of the depth map of the single pomelo fruit, an elliptical fruit posture feature region is recognized, and an elliptical inclination angle of the fruit posture feature region is obtained in combination with a Hough ellipse detection algorithm; and calculating the position and posture of the pomelo stem according to the ellipse inclination angle of the fruit posture feature region. According to the method, through integration of multiple advanced technologies, the whole process optimization from image data preprocessing to fruit stem pose accurate identification is realized, the identification precision and the working efficiency of pomelo fruit picking automation equipment are improved, and the false picking rate and the fruit damage rate are reduced.
Owner:SOUTH CHINA AGRICULTURAL UNIVERSITY

Implementation of high-response alternating current servo algorithm based on cnc look-ahead technology

The invention provides high-response alternating current servo algorithm implementation based on a cnc look-ahead technology, relates to the technical field of program control machine tools, and comprises a control system comprising a self-adaptive look-ahead speed control algorithm, an accurate motor control system and a real-time feedback adjustment system. The CNC look-ahead speed control optimization algorithm is combined with a self-adaptive look-ahead technology, precise motor control and real-time feedback adjustment, the machining speed and the machining precision of the CNC machine tool are optimized, the distance and the time of look-ahead prediction are adjusted in real time according to the curvature change of a machining path, the influence of system time lag on the machining precision is reduced, and the machining precision of the CNC machine tool is improved. The change trend of a future path can be predicated prospectively according to the curvature change of a machining path, a speed control strategy is optimized accordingly, the response speed of a numerical control system to an input instruction is improved by optimizing the speed control strategy, meanwhile, error compensation and self-adaptive adjustment are carried out in combination with real-time feedback information, and the speed control accuracy is improved. And stable and efficient machining of the machine tool is ensured.
Owner:YIFANG INTELLIGENT CONTROL (SHANGHAI) CNC TECHNOLOGY CO LTD

Data processing method and system based on financial information bill

The invention relates to the technical field of financial data processing, in particular to a data processing method and system based on financial information bills. The data processing method comprises the following steps: acquiring multi-modal financial information bill data; and performing bill modal decomposition on the multi-modal financial information bill data to generate financial information bill modal decomposition data. Bond information price income prediction needs a large amount of financial data, such as market interest rate, bond expiration date, face interest rate and the like, the data are similar to the data form of bill modal decomposition, and a more accurate model can be obtained through standardization and feature extraction of multi-modal data. Therefore, valuable input is provided for bond price and income prediction. According to the invention, through multi-modal data fusion, counterfeited feature comparison modeling, abnormal bill clustering analysis and dynamic risk assessment, the security and accuracy of financial bill identification are improved.
Owner:YOUAN INFORMATION TECHNOLOGY (HEBEI) CO LTD

Distributed intelligent control system and air purifier

The invention relates to the technical field of air purification, in particular to a distributed intelligent control system and an air purifier. The system comprises a distributed intelligent control network establishment module, an air purification area quality data acquisition module, an air purifier local purification control module and an air purification area dynamic adjustment optimization module. An air purification sensor array and an intelligent control unit are installed and deployed in each air purifier, distributed control node design and air quality data real-time collection are carried out, and meanwhile edge calculation preprocessing and quality index parameter calculation are carried out; according to the method, the air quality index parameter sets of the areas where the air purifiers are located are obtained, distributed purification operation control and purification state feedback analysis are carried out, purification strategy dynamic adjustment is carried out, and an air purifier dynamic optimization purification strategy is generated so as to execute purification optimization decision-making work of the areas where the air purifiers are located. The air purification effect can be better improved.
Owner:JINAN CHAOJIXING ENVIRONMENTAL PROTECTION TECHNOLOGY CO LTD

CBCT image tooth segmentation method based on deep learning

The invention relates to a CBCT image tooth segmentation method. The method comprises the following steps: generating a two-dimensional oral cavity panoramic film from a CBCT image; carrying out tooth two-dimensional segmentation and tooth ID classification on the two-dimensional oral cavity panoramic film by adopting a deep learning algorithm; calculating a key point coordinate of a two-dimensional single tooth and mapping the key point coordinate to a three-dimensional CBCT image coordinate; respectively cutting the CBCT image to obtain an area of each tooth; segmenting each three-dimensional tooth region by adopting a deep learning algorithm; and assigning ID to all the tooth segmentation results, and splicing to obtain a three-dimensional tooth segmentation result. According to the method, accurate segmentation of the tooth area in the CBCT image can be realized, complex conditions such as tight tooth arrangement, similar shapes and artifact interference can be effectively handled, the problems of tooth segmentation result fusion, ID confusion and metal artifact interference can be effectively solved, and resource consumption is remarkably reduced by determining the tooth key points on the panoramic film, so that the tooth segmentation efficiency is improved. The overall segmentation efficiency is improved, and the segmentation time is shortened, so that the accuracy of the segmentation result and the processing speed are improved.
Owner:BONDENT TECH

Glass surface wet anti-slip bionic friction pad and preparation method thereof

The invention relates to the technical field of high polymer materials and preparation thereof, and discloses a wet anti-slip bionic friction pad on a glass surface, which is inspired by a micro-nano structure of toe pads of organisms such as tree frogs and long-horned grasshoppers with wet friction increasing characteristics, and a bulge array is added on the surface of a high-friction material, so that the friction coefficient of the friction pad is increased; the microstructure arrays can discharge a water film on the surface of the friction pad under the capillary action in a wet environment, and the effective contact area between solids is increased, so that the friction pad and a friction surface are always kept in a dry friction state, and stable friction force is ensured. The friction pad comprises a connecting layer, a supporting layer and a tail end protruding straight column array, a tail end contact layer is in a hexagonal straight column shape, the diameter of an inscribed circle of a hexagonal micro-column structure ranges from 5 micrometers to 5000 micrometers, column bodies are densely arranged in a hexagonal mode, the height of the column bodies ranges from 10 micrometers to 1500 micrometers, the tail ends of the column bodies are planes, the interval between every two column bodies ranges from 2 micrometers to 600 micrometers, and tight drainage grooves are formed.
Owner:WUXI FANDER WAAL TECHNOLOGY CO LTD

Television box intelligent interaction control unit image processing method and equipment

The invention relates to a television box intelligent interaction control unit image processing method and device. The method comprises the following steps: carrying out feature analysis on an input video stream of the television box to obtain an enhanced video stream; the method comprises the following steps: collecting visual and voice interaction information of a user based on an intelligent interaction control unit, and inputting the visual and voice interaction information into a double-branch Transform model for multi-modal information fusion to obtain a fusion feature vector; performing conjoint analysis to obtain a user interaction intention and an interaction response strategy; performing local contrast enhancement and motion compensation to obtain a high-quality video frame sequence; and performing scene adaptive color space mapping and dynamic color temperature adjustment on the high-quality video frame sequence according to the environment light information acquired in real time and the pre-stored color characteristics of the display device to obtain an output video stream. According to the implementation of the method, limited computing resources can be fully utilized, efficient video processing and natural man-machine interaction are achieved, and meanwhile the display effect is dynamically optimized according to environmental changes.
Owner:SHENZHEN YUEXINTONG TECH CO LTD

Sewage treatment intelligent control system based on feedforward algorithm and feedback control

The invention discloses a sewage treatment intelligent control system based on a feedforward algorithm and feedback control, and particularly relates to the technical field of sewage treatment intelligent control. Comprising a sewage treatment time division module, a sewage treatment data acquisition module, a sewage treatment feedforward algorithm establishment module, a sewage treatment feedback control execution module, a sewage treatment intelligent analysis module and a sewage treatment intelligent evaluation module. A sewage treatment response output index and a sewage treatment feedback output index are obtained based on a scientific data analysis decision, and a sewage control stability evaluation coefficient is obtained through further analysis and is used for evaluating whether an intelligent management control mode of sewage is abnormal or not. The method can achieve the automatic and intelligent dynamic management of the sewage treatment process through the prediction and analysis of the sewage treatment trend by means of an intelligent algorithm, and improves the treatment efficiency and quality.
Owner:SUZHOU SUSHEN WATER TECH CO LTD

MSR and adaptive dark light image enhancement method applying LUT gamma correction post-processing

The invention discloses a self-adaptive dark light image enhancement method based on MSR and LUT gamma correction post-processing. The method comprises the steps of 1, inputting image quality evaluation; the method comprises the following steps: 1) calculating contrast, brightness mean and information entropy of an original image; 2) self-adaptive quality judgment: step 2, applying a multi-scale Retinex algorithm to an original image needing to be enhanced, decomposing the original image into images of different scales, performing Retinex enhancement processing on the image of each scale so as to reserve detail information of different scales, and realizing balance of dynamic range compression, edge enhancement and color constancy by adjusting parameters of the Retinex algorithm; step 3, performing gamma correction post-processing by applying LUT; the method comprises the following steps: 1) creating a grayscale image gamma correction integral lookup table LUT; and 2) applying gamma correction of the integral lookup table LUT. The method has the characteristics of comprehensive image quality self-judgment mechanism, obvious improvement of the overall image quality and good real-time performance.
Owner:SHAANXI UNIV OF SCI & TECH

Transparent material / metal heterogeneous material ultrafast laser welding method based on burst mode

The invention discloses a transparent material / metal dissimilar material ultrafast laser welding method based on a burst mode, and belongs to the technical field of laser micro-nano machining, and the transparent material / metal dissimilar material ultrafast laser welding method comprises the steps that the surface roughness and flatness of a pre-welded piece are treated through a mirror grinding and polishing technology, so that a sample piece reaches the optical contact condition, the pre-welded piece is in lap joint with a tool platform through a specially-made clamp, and the pre-welded piece is welded to the tool platform; when a visual Newton ring appears on a contact surface and an ultrafast laser focus is located at a material interface, using a burst mode under an ultrafast laser processing platform to increase the number of sub-pulses, welding a micro-area, equally dividing the energy of a single pulse into a plurality of pulses, and then emitting light in a pulse sequence mode, by using the burst mode containing multiple pulses, the heat accumulation effect can be achieved more easily, the ablation efficiency and the connection strength and stability of the transparent material and the metal heterogeneous material are improved while the machining rate is increased, and the method has wide application prospects.
Owner:SHANGHAI UNIV OF ENG SCI +1

Communication system and method based on Internet of Things information technology

The invention relates to the technical field of Internet of Things, in particular to a communication system and method based on the Internet of Things information technology, the system comprises a network monitoring module, a scheduling optimization module, a transmission efficiency adjustment module and a retransmission management module, and the network monitoring module continuously captures network access points of Internet of Things equipment based on real-time bandwidth demand data. According to the invention, through real-time monitoring and adoption of the LSTM prediction model, rapid change of network conditions can be adapted, and a data transmission process can be dynamically adjusted, so that delay and packet loss in data transmission are reduced, data analysis in a transmission process is further enhanced through introduction of the DQN model, and the data transmission efficiency is improved by evaluating whether a transmission event succeeds or not. According to the method, the overall success rate of transmission can be effectively improved, a random forest algorithm is adopted to customize a retransmission mechanism for each data packet and network condition, the retransmission precision and efficiency are improved, the processing speed and accuracy of a communication system are improved, and it is ensured that excellent efficiency can still be kept in a network environment with high requirements.
Owner:OPTICAL NETWORK VIDEO TECH(SHENZHEN) CO LTD

Scheduling supervision method based on combination of power network topology and natural language processing

The invention discloses a scheduling supervision method based on combination of power network topology and natural language processing, and the method comprises the steps: obtaining data in the power network topology, including data in an SCADA system and data in PMU equipment; power network topology identification based on machine learning; the natural language processing module comprises power grid network structure analysis, permission range matching and user side operation instruction analysis; real-time monitoring and alarming are dispatched, and a detection report is automatically generated. According to the method, the recognition difficulty of the user side operation text is reduced, the text processing efficiency and accuracy are improved, and it is ensured that when the system receives the user operation instruction, whether the instruction is within the permission range of the user or not can be verified in real time; through automatic text analysis and authority matching, manual intervention is reduced, the processing speed and execution efficiency of the dispatching instruction are improved, efficient operation of a power system is ensured, and the safety and stability of power dispatching are integrally improved.
Owner:CHINA SOUTHERN POWER GRID COMPANY

Field rock ore spectral data preprocessing method

The invention discloses a field rock and ore spectral data preprocessing method, and belongs to the technical field of noise elimination of ground feature spectral data. The method comprises the following steps: identifying and extracting characteristics with the most information content in data, reducing the complexity of the data, retaining key information of the data, carrying out clustering analysis by utilizing a DBSCAN algorithm, identifying and processing noise in the data, finding out a data cluster with any shape, and carrying out accurate data preprocessing, effective characteristic extraction and dimensionality reduction and fine clustering analysis, so as to improve the accuracy of data clustering. Data visualization is obtained, and the analysis process of spectral data is optimized. According to the data visualization tool provided by the invention, researchers can intuitively understand data features and clustering results, and data can be analyzed and explained more deeply. The visual support is to improve the data interpretability.
Owner:CHENGDU INST OF ENVIRONMENTAL GEOLOGY & RESOURCE DEV CO LTD

Highway intelligent informatization ETC charging device and control method thereof

The invention relates to the technical field of road traffic safety, and discloses an expressway intelligent informatization ETC charging device, which comprises an on-board unit (OBU) used for being installed on a vehicle to store and transmit vehicle information; the road side unit (RSU) is arranged in a highway toll collection area and is used for receiving the vehicle information from the vehicle-mounted unit and sending the information to the central control system; the antenna is connected to the road side unit and is used for performing wireless communication with a vehicle-mounted unit; the central control system is connected to the road side unit and used for processing the received vehicle information and controlling the charging process; and the behavior prediction module is used for predicting the driving path and behavior of the vehicle based on the historical data and the real-time state of the vehicle. By integrating a behavior prediction module, a self-adaptive charging adjustment module and a traffic collaborative management module, the system can dynamically adjust a charging strategy and traffic flow control based on real-time data and environmental information.
Owner:HIGHWAY MONITORING & RESPONSE CENT MINIST OF TRANSPORT OF THE P R C

Wetland carbon reserve estimation method and system based on remote sensing technology

The invention relates to the field of intelligent carbon reserve estimation, and particularly discloses a wetland carbon reserve estimation method and system based on a remote sensing technology. And performing local area segmentation and image semantic feature association on the remote sensing image of the wetland area by using an image analysis and processing algorithm based on deep learning so as to intelligently obtain the vegetation type and quantity of each area, and obtaining a carbon reserve estimated value of the wetland based on the vegetation type and quantity of each area. In this way, the remote sensing technology can be utilized to cover a wide-range wetland area. Meanwhile, the deep learning algorithm can extract accurate features from the remote sensing image, the automatic image processing flow reduces manual intervention, the efficiency and processing speed of wetland carbon reserve estimation are improved, and the accuracy of carbon reserve estimation is also improved.
Owner:JIANGXI ACAD OF FORESTRY

Sound source imaging calculation method and system, electronic equipment, storage medium and computer program product

The invention provides a sound source imaging calculation method and system, electronic equipment, a storage medium and a computer program product, and the method comprises the steps: carrying out the preprocessing of obtained audio data, so as to obtain a center frequency in a scanning frequency range, and the audio data are collected through a microphone array; sound intensity grids are divided within the visible range of the video collection device. And determining an Euclidean distance matrix and an array steering vector from the microphone array to the sound intensity grid. And obtaining an output power spectrum matrix according to the array steering vector and the cross-spectrum matrix. And coloring the sound intensity grids to obtain a thermodynamic diagram. The sound source imaging method is optimized and innovated by utilizing the parallel computing capability of the CUDA technology, the accurate positioning of the sound source is realized, the processing speed and the positioning precision of the CUDA architecture model are improved, and powerful technical support is provided for the development of the sound source imaging field.
Owner:NR ELECTRIC CO LTD +1