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

25results about How to "Improve association accuracy" patented technology

Target tracking method and device based on adaptive correlation gate, and storage medium

The invention discloses a target tracking method and device based on an adaptive correlation gate, and a storage medium. The method comprises the steps of determining a tracking target motion state and a filtering model according to a tracking target type; determining an associated gate according to the type of the tracking target and the motion state of the tracking target; calculating the association probability between the tracking target and the measurement target in the association gate, and setting the association probability to 0 for the measurement target which does not fall into the association gate to obtain an association probability matrix; calculating a distribution relation between the tracking target and the measurement target based on the association probability matrix between the tracking target and the measurement target; re-calculating the Euclidean distance between the tracking target and the measurement target which are not distributed, generating a new association probability matrix, and calculating a new distribution relation; and updating the tracking target motion state and the filtering model of the tracking target according to the latest distribution relation. According to the invention, the stability and accuracy of target tracking can be improved.
Owner:COWA TECHNOLOGY CO LTD +1

Cross-device association method based on mobile intelligent terminal sensor data fusion analysis

The invention discloses a mobile intelligent terminal sensor data fusion analysis-based cross-device association method, which comprises the following steps of: acquiring various sensor data of two types of devices as model training data; performing preprocessing operations such as splitting, equalization and normalization on the data; a neural network model is designed, the similarity of sensor data collected by two types of equipment needs to be compared, so that a twin neural network is adopted as a discrimination model, the similarity of output vectors of the two convolutional neural networks is calculated by adopting a cosine distance, and a loss function is further calculated based on the similarity; utilizing the designed twin neural network to train a model corresponding to each scene; and setting a similarity threshold value, if the similarity threshold value is exceeded, data matching succeeds, otherwise, cross-device association is realized. The method is the first method for associating the multiple mobile intelligent terminal devices of the user, the collected user data volume is small, the association speed is high, and the association accuracy is high.
Owner:北京耀琦科技有限公司

High-frequency ground wave radar formation target tracking method and system

The invention discloses a high-frequency ground wave radar formation target tracking method and system, and particularly relates to the technical field of target tracking. Comprising the following steps: constructing a position feature vector and an appearance feature vector of a formation target based on high-frequency ground wave radar echoes; constructing nodes by using the position feature vectors and the appearance feature vectors of the formation targets; screening adjacent nodes of the known node Node based on the position feature vector, and calculating a likelihood function; constructing a prototype network model based on the formation target appearance feature vector, and calculating the Euclidean distance between the appearance feature vector of a known node Node and the appearance feature vector of an adjacent node Adjacent; on the basis of a likelihood function Lsiran and an Euclidean distance Euddis, the correlation similarity between a known node Node and an adjacent node AdJacent is calculated, so that a connection edge is constructed; and training based on a graph neural network loss function to realize formation target matching tracking. By adopting the technical scheme of the invention, the problem that the formation target cannot be tracked in the prior art is solved, and accurate tracking of special targets such as formation is realized.
Owner:HARBIN INST OF TECH AT WEIHAI

Track association method based on local and global similarity fusion

A flight path association method based on local and global similarity fusion belongs to the technical field of flight path association, and comprises the following steps: S1, preprocessing obtained flight path pair data, including abnormal value elimination and time coincidence part interpolation alignment; s2, respectively extracting local similarity features and global similarity features of the track pairs; s3, performing weighted fusion on the local and global similarity features, inputting the local and global similarity features into a random forest classifier model for training, and determining an optimal weight combination of different similarity features; and S4, carrying out weighted fusion on the local and global similarity features of the unknown track pair according to the optimal weight combination, and inputting the local and global similarity features into the trained random forest classifier model to carry out association judgment. According to the method, the influence caused by misjudgment of local similarity features can be reduced under the condition that the overlap ratio of the track to time is low, and the method still has good association accuracy.
Owner:ZHEJIANG UNIV OF TECH +1

Obstacle association method and device, computer equipment and storage medium

The invention provides an obstacle association method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining measurement data from at least one sensor, and enabling the measurement data to comprise a plurality of obstacle measurements and detection information thereof; for each obstacle measurement to be associated, selecting a target reference point type from a plurality of predefined candidate reference point types according to detection information of the obstacle measurement to be associated; determining a measurement reference point from the detection information of the obstacle measurement based on a target reference point type selected for each obstacle measurement; determining a matching measure between a measurement reference point and a track reference point based on the measurement reference point measured by the obstacle and the track reference point determined for the fused track; according to the calculation result of the matching measurement between all the obstacle measurements and all the fused tracks, the association relationship between the obstacle measurements and the fused tracks is determined, and the accuracy and the reliability of obstacle association can be remarkably improved by adopting the method.
Owner:CHINA FAW CO LTD

A data association method and device, electronic equipment and computer readable storage medium

This application provides a data association method, apparatus, electronic device, and storage medium. The method includes acquiring a set of measurement tracks and a set of system tracks at the current time. The strategy track set includes a visual track subset, a forward radar track subset, and a side-rear radar track subset. The method involves matching the visual track subset and the system track set according to a first association rule to determine system-visual data pairs. It also involves matching the forward radar track subset and the system track set according to a second association rule to determine system-forward radar data pairs. Furthermore, it involves matching the side-rear radar track subset and the system track set according to a third association rule to determine system-side-rear radar data pairs. Finally, it involves updating the system track set based on the determined system-visual data pairs, system-forward radar data pairs, and system-side-rear radar data pairs.
Owner:CHINA FAW CO LTD

A power distribution network multi-source heterogeneous operation data association method and device

ActiveCN122333395BReliable and unified fusion resultsimprove accuracy
The application relates to a power distribution network multi-source heterogeneous operation data association method and device, and belongs to the technical field of power system operation data processing. According to multi-source heterogeneous operation data of a target device node, a candidate device node set is determined, an association relationship between device nodes is determined through joint similarity of the target device node and each candidate device node in the candidate device node set, finally, multi-source heterogeneous operation data of the target device node and associated candidate device nodes are fused based on the association relationship between the target device node and the candidate device nodes, a reliable asynchronous, multi-source heterogeneous data unified fusion result can be provided, the accuracy and engineering usability of power distribution network unified semantic object construction are improved, and the problem that current multi-source heterogeneous data objects are difficult to unify, the same object has different names and different places have the same name, and association errors occur frequently is solved.
Owner:STATE GRID JIANGSU ELECTRIC POWER CO LTD RESEARCH INSTITUTE

Intelligent management method, system and equipment for rosewood waste and medium

The invention relates to the technical field of rosewood waste management. The invention provides a rosewood waste intelligent management method, system and equipment and a medium. The method comprises the steps that point cloud collection is conducted on waste through a preset three-dimensional vision device to obtain point cloud data; performing feature extraction on the spectral data to obtain a spectral feature vector, and performing morphological reconstruction on the point cloud data to obtain a morphological feature vector; performing similarity matching processing on the spectral feature vector, the morphological feature vector and a pre-constructed wood feature library to obtain wood type probability distribution; searching a plurality of paths in a pre-constructed waste-process-value knowledge graph based on the space-time correlation factor and the wood type probability distribution to obtain a target process node set; and performing process parameter optimization on the target process node set to obtain a collaborative process parameter packet so as to achieve the technical effects of improving the correlation accuracy of the waste and the production equipment, enhancing the distinguishing capability of similar rosewood materials and optimizing the self-adaptive adjustment efficiency of a high-value process path.
Owner:ZHEJIANG GUANGSHA COLLEGE OF APPLIED CONSTRTECH

Radar and AIS track association method, device and equipment based on spatiotemporal attention

A radar and AIS track association method, device and equipment based on spatiotemporal attention, the method includes: obtaining radar track data and AIS track data; using a multi-layer perceptron to enhance the dimension of the track data and extract the local spatial features of the track data; encoding the track data by position to obtain the time series features of the track data; splicing the local spatial features of the track data with the time series features of the track data, and inputting the spliced ​​features into the Transformer encoder to encode the global spatiotemporal features of the track data to obtain the spatiotemporal feature encoding vector of the track data; using a cross-attention mechanism to calculate the spatiotemporal feature encoding vector of the radar track data and the spatiotemporal feature encoding vector of the AIS track data to obtain an association probability matrix; and associating and matching the radar track with the AIS track based on the association probability matrix. The present invention can realize the intelligent association and fusion of multiple ship information in complex waters, with stronger scene adaptability and higher association accuracy.
Owner:WUHAN UNIV OF TECH

Shielding pedestrian re-identification method based on main body target discrimination

ActiveCN119091467AAccurate identification of subject targetsImprove association accuracyBiometric pattern recognitionNeural learning methodsHuman bodyVisual technology
The invention relates to a blocked pedestrian re-identification method based on main body target discrimination, and belongs to the technical field of computer vision. The method comprises the following steps: firstly, obtaining a pedestrian snapshot slice, and carrying out human body instance segmentation on the pedestrian snapshot slice to obtain a segmentation mask set; scoring each mask in the set, and determining a main target segmentation mask of the current pedestrian snapshot slice according to the score of the mask; and finally, identifying the shielded pedestrian based on the main body target segmentation mask. According to the method, the main body target can be accurately distinguished, and image-level interference information filtering is performed on the occluded pedestrian slices based on the main body target, so that the interference of the background in the picture and non-target pedestrians on the feature learning of the main body target is effectively relieved, and the association accuracy of the pedestrian re-identification model under the occlusion condition is improved.
Owner:BEIHANG UNIV +1

A three-layer association method based on event template similarity recommendation

The present invention discloses a three-layer association method based on event template similarity recommendation, and specifically relates to the field of big data security technology. The present invention performs three-layer association of database logs and application logs around templates through the proposed method, greatly improving timeliness and accuracy. The present invention first proposes to apply the DBSCAN clustering algorithm to URL request and response parameter aggregation, which helps to improve the accuracy of the entire algorithm. The recommended collaborative filtering algorithm is applied to the field of three-layer association technology, and word2vec similarity matrix matching is proposed to realize the three-layer association of application log events and database log templates, greatly improving the association accuracy.
Owner:QUANZHI TECH (HANGZHOU) CO LTD

A multi-source target fusion method based on multi-modal detection information

PendingCN122692889Aavoid mutual interferenceImprove association accuracy
The application provides a multi-source target fusion method based on multi-modal detection information, which comprises the following steps: firstly, acquiring multi-source heterogeneous sensing data and performing space-time unified pretreatment; judging the dynamic and static state according to the target position change; performing single-source double-time cross calibration on the static target, using the azimuth angle, the pitch angle and the sensor displacement of the adjacent two time points, obtaining the calibrated position through triangulation and confidence weighting, and performing cross-source association with type constraint; for the dynamic target, the correlation matrix is generated by using recursive trajectory similarity calculation and density hierarchical clustering; the association cluster is identified by depth-first search, and the robust fusion is performed by using the random sample consensus method, and high-precision target information is output. The application is suitable for multi-source heterogeneous detection information fusion of air / ground manned / unmanned detection platforms in land confrontation environment, and can generate high-confidence and anti-deception target intelligence to support command decision.
Owner:西安应用光学研究所

Battery storage gas production test method, equipment, medium and program product

The invention provides a battery storage gas production testing method and device, a medium and a program product, and relates to the technical field of battery performance testing. The method comprises the following steps: receiving oil bath temperature setting information of a user side to heat silicone oil in an oil bath pan, and then receiving test parameter data including sampling time and the like; then, after the association between the target battery object to be tested and the oil bath pan and the balance is determined according to a preset mode, a test starting instruction is received; and then controlling the balance to sample weight data according to the sampling time, determining the volume change condition of the to-be-tested object of the battery according to a plurality of weight data, and determining a test result in combination with information corresponding to the oil bath pan. And finally, the test result is stored according to the data storage path and sent to a user side for display, and an accurate, convenient, efficient and traceable solution is provided for the gas production test of the battery.
Owner:YUANNENG TECH (XIAMEN) CO LTD

A traffic multi-target association method based on spatial grouping and feature matching

ActiveCN121121168BImprove association accuracyImprove robustness
The application relates to the technical field of intelligent traffic perception, in particular to a traffic multi-target correlation method based on spatial grouping and feature matching. First, a spatial position grouping algorithm is used to pre-classify detection targets, a dynamic grouping model is established based on the spatial density distribution and grouping relationship of the targets, and the target search space is effectively reduced; then, multi-dimensional correlation metrics are calculated, a correlation matrix is constructed, the motion consistency and feature similarity of the targets are comprehensively evaluated, the optimal matching result of all the matching successful track records in the same group is recorded, the matching result is output in a delay mode, when more than 50% of the targets in the same group are all matched successfully or the target matching times exceed 10 times, the point record with the most matching times in the track is output as the current matching result. The traffic multi-target correlation method based on spatial position grouping and feature matching can significantly improve the accuracy and real-time performance of multi-target correlation by fusing the spatial distribution characteristics, motion features and delay output of the targets.
Owner:WEIDU ZHISHEN (BEIJING) TECHNOLOGY CO LTD

Correlation analysis method for multi-source defect data of semiconductor wafer

The invention discloses a correlation analysis method for multi-source defect data of a semiconductor wafer, and relates to the technical field of wafer defect detection in semiconductor manufacturing. Aiming at the pain points of non-uniform types of multi-source defect data, difficulty in cross-parameter association, improper processing of repeated records and single similarity algorithm in the prior art, the method disclosed by the invention realizes uniform adaptation of the multi-type defect data, complete retention of repeated data, differential algorithm configuration, cross-batch parameter adaptation and deep association of a time sequence and a process; according to the method, a standardized report containing process optimization suggestions is generated through template loading, dynamic parameter adaptive calibration, multi-dimensional feature weighted fusion, configurable spatial similarity algorithm, cross-batch time sequence correlation analysis, defect-process parameter mapping correlation key technologies, output numerical values, space and comprehensive correlation coefficients; the method is high in compatibility, complete in analysis dimension and high in decision value, can be seamlessly integrated to an existing wafer quality control system, and provides comprehensive support for optimization of a semiconductor manufacturing process.
Owner:WUXI ZHIXIAN FUTURE TECHNOLOGY CO LTD

A test method, device, medium and program product for battery storage gas generation

The present application provides a test method, device, medium and program product for battery storage gas production, which relates to the field of battery performance testing technology. The method includes: receiving the oil bath temperature setting information from the user end to heat the silicone oil in the oil bath pot, and then receiving test parameter data including sampling time. Then, after determining the association between the target battery to be tested and the oil bath pot and the balance in a preset manner, receive a command to start the test. Then control the balance to sample weight data according to the sampling time, determine the volume change of the battery to be tested based on multiple weight data, and determine the test results in combination with the corresponding information of the oil bath pot. Finally, the test results are stored according to the data storage path and sent to the user end for display, providing an accurate, convenient, efficient and traceable solution for battery gas production testing.
Owner:YUANNENG TECH (XIAMEN) CO LTD

A layered self-adaptive multi-modal flight data intelligent association alignment method

PendingCN122286646AImprove association accuracyImprove robustnessFlight vehicleDynamic models
This application discloses a hierarchical adaptive intelligent association and alignment method for multimodal flight data, comprising: acquiring multi-source airborne flight data and preprocessing it; mapping data of different modes in the preprocessed multi-source airborne flight data to a common feature space to obtain cross-modal alignment features, wherein an aircraft physical dynamic model is introduced as a constraint during the mapping process; performing local precise association and global semantic association in parallel based on the cross-modal alignment features; wherein the local precise association is used to obtain pixel-level or point-level matching results, and the global semantic association is used to obtain globally consistent semantic association results; and fusing the results of the local precise association and the global semantic association to obtain association information of corresponding granularity. This invention effectively solves the "data silo" problem caused by differences in format, spatiotemporal reference, and modality of multi-source flight data, significantly improving association accuracy, robustness, and system adaptability.
Owner:SICHUAN UNIV

Cross-device association method based on mobile intelligent terminal sensor data fusion analysis

ActiveCN119004386Breduce data volumeImprove association accuracyBiological models
The present invention discloses a cross-device association method based on mobile smart terminal sensor data fusion analysis, which includes the following steps: collecting multiple sensor data of two types of devices as model training data; performing pre-processing operations such as splitting, equalization, and normalization on the data; designing a neural network model. Since the present invention needs to compare the similarity of sensor data collected by the two types of devices, a twin neural network is used as a discriminant model, and the cosine distance is used to calculate the similarity of the output vectors of the two convolutional neural networks, and the loss function is further calculated based on the similarity; the designed twin neural network is used to train the corresponding model for each scenario; a similarity threshold is set, and if the threshold is exceeded, the data matching is successful, otherwise it fails, thereby realizing cross-device association. The method of the present invention is the first method for associating multiple mobile smart terminal devices of a user, and the amount of user data collected is small, the association speed is fast, and the association accuracy is high.
Owner:北京耀琦科技有限公司

Bioinformation processing device, bioinformation processing method, and program

InactiveEP4410193A4accurate associationImprove association accuracyImage enhancementImage analysis
A bioinformation processing device includes a signal reception unit configured to receive a signal related to bioinformation reflected from at least one person to be measured, a candidate region identification unit configured to calculate an arrival direction of the signal and / or a distance to the at least one person to be measured from the signal received and identify a candidate region of the at least one person to be measured using the arrival direction and / or the distance calculated, an information generation unit configured to generate bioinformation corresponding to the candidate region of the at least one person to be measured from the signal received, a position information acquisition unit configured to acquire position information of the at least one person to be measured, and a bioinformation association unit configured to associate the at least one person to be measured with the bioinformation generated, based on the position information acquired.
Owner:OMRON CORP

Human body and human hand association method, device, equipment and storage medium

ActiveCN114051632BImprove association accuracyImage enhancementImage analysis
An embodiment of the present application provides a method, apparatus, device and storage medium for associating a human body with a human hand, wherein the method comprises: acquiring an image to be detected whose content includes a human body and a human hand; determining a human body detection frame of the human body and a hand detection frame of the human hand in the image to be detected; determining an association probability between the human body detection frame and the hand detection frame; determining an external frame of the human body detection frame and the hand detection frame; and determining a degree of association between the human body and the human hand in the external frame based on key points of the hand in the external frame and the association probability.
Owner:QINGZHILAN (SHENZHEN) TECHNOLOGY CULTURE CO LTD

Powerful model test case recommendation method and related device

PendingCN122507622Afully captureAvoid invalid calculations
This invention belongs to the field of large-scale power language models and discloses a method and related apparatus for recommending test cases for large-scale power models. It constructs state data including attack success rate and recommendation latency, utilizes reinforcement learning pre-trained depth-determining models to adaptively select the current knowledge graph exploration depth, dynamically adjusts the knowledge graph propagation range based on historical recommendation results, and employs a relation-aware attention mechanism in recursive propagation to weighted aggregate neighbor tail entities. Entity features under different relations are projected onto the corresponding relation space for semantic matching. A bidirectional interactive aggregator is combined to fuse its own features with neighboring features through addition and multiplication, enhancing feature representation capabilities. A layered aggregation mechanism concatenates features from various depths into a fusion vector and sorts them by inner product to select test cases, enabling the recommendation results to incorporate hierarchical semantic information from multi-hop propagation. This achieves synergistic optimization of recommendation accuracy and response speed, effectively supporting rapid evaluation of the security performance of large-scale power models.
Owner:STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO

A flexible fixed LED street lamp circuit board welding device and method

The present invention relates to the technical field of circuit board welding, and more specifically, to a flexible fixed LED street lamp circuit board welding device and method. It is inflated after the circuit board is in place, and the following process is formed: a circuit board with a larger area is squeezed, causing the distance of the blocking piece to change. At this time, after inflation, the change in the distance of the blocking piece causes a change in the inflation time, that is, the larger the area of ​​the circuit board, the longer its inflation time. At this time, the length of time for squeezing the squeezing block will not cause a change in the inflation time, thereby solving the problem that it is difficult for staff to grasp the force of pressing down the circuit board due to the influence of this variable, so that the expansion size of the airbag is only positively correlated with the size of the circuit board area. In the present invention, the gas source starts to supply gas to the gas pipeline after the blocking piece is opened to the maximum extent.
Owner:ZHONGSHAN YUCHENG SOLAR TECH CO LTD

A convolution-bidirectional long short-term memory multi-source track association method and system based on spatiotemporal attention

The present invention discloses a convolution-bidirectional long short-term memory multi-source track association method and system based on spatiotemporal attention, which belongs to the field of track association. The method uses a CNN network and a first attention mechanism module to jointly construct a feature attention module to convert the multi-source track data after spatiotemporal registration into a feature sequence; uses a BiLSTM network and a first attention mechanism module to jointly form a time attention module to capture the temporal characteristics of the trajectory data; uses a fully connected layer to map the output data to a new feature space, and uses a classifier to score; and determines the correlation relationship between the multi-source track data by calculating the correlation score. The present invention uses CNN to fully extract track space features, and combines the attention mechanism to ensure that important features play a key role; uses BiLSTM to fully extract track time features, and combines the attention mechanism to screen out the most important state information in the historical sequence, which overcomes the problem of incomplete information utilization in traditional methods and improves the association accuracy.
Owner:HUAZHONG UNIV OF SCI & TECH

Method and device for maintaining a catalog of space objects fusing post-detection multi-source observation data

This invention proposes a method and apparatus for maintaining a space target catalog database by fusing post-hoc multi-source observation data, belonging to the field of space situational awareness. The method includes: acquiring and preprocessing post-hoc observation data of the observed space target; calculating observation arc segments using the preprocessed observation data, using the obtained initial orbit determination results as the orbital features of the observation arc segments, and then matching the observation arc segments with the orbital data of targets in the catalog database, using the successfully matched observation arc segments as the associated arc segments of the target; fusing multiple associated arc segments of the target for precise orbit determination, and updating and maintaining the catalog database using the results of the precise orbit determination. This invention can quickly preprocess the input multi-source observation data and complete the association matching between the data and space targets, and finally fuse the multi-source observation data for precise orbit determination, ensuring computational efficiency and process integrity, and realizing the maintenance of the space target catalog database.
Owner:QINGBO AEROSPACE (BEIJING) TECHNOLOGY CO LTD

Target association method, electronic equipment and computer readable storage medium

ActiveCN118939435Areduce consumptionImprove association accuracyResource allocationEngineeringComputer vision
The invention discloses a target association method, electronic equipment and a computer readable storage medium. The method comprises the following steps: acquiring a first target object and a second target object in a target scene; wherein the first target object and the second target object are matched with different detection categories; based on a first target point corresponding to the current first target object and second target points corresponding to the second target objects, obtaining a target distance between the current first target object and each second target object; acquiring a preset reference distribution condition, and acquiring association confidence between the current first target object and each second target object based on the reference distribution condition and the target distance; and based on the association confidence, determining an association result between the current first target object and the second target object. In this way, the accuracy of association between different targets can be improved.
Owner:ZHEJIANG DAHUA TECH CO LTD