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

1211results about How to "Reduce computational overhead" patented technology

Ambient sound event detection method based on multi-modal data fusion

The invention relates to the technical field of environmental sound event detection, in particular to an environmental sound event detection method based on multi-modal data fusion, which utilizes a microphone array, a camera and a sensor to synchronously acquire audio, video and environmental data to form a multi-modal data source. And the collected multi-modal data is preprocessed, so that the data quality and the accuracy of subsequent analysis are improved. And key features are extracted from the processed data, and the features are fused to form multi-modal features. And a deep learning model is constructed, and multi-modal features are used for training, so that a model capable of identifying an environmental sound event can be obtained. And performing optimization such as pruning, quantification and knowledge distillation on the trained model, and deploying the model on edge equipment to realize real-time preliminary feature extraction and event detection. The problems that an environment sound event detection method in the prior art is poor in robustness, low in real-time performance and limited in generalization ability are solved.
Owner:NANJING LONGYUAN INFORMATION TECH CO LTD

Large language model reasoning optimization method based on cascade and speculative decoding strategy

The invention relates to the technical field of language model reasoning, and discloses a large language model reasoning optimization method based on cascading and speculation decoding strategies, which comprises the following steps: S1, inputting cue words of a user to a small language model family, and quickly generating a plurality of draft text tokens by using a cascading strategy; s2, inputting a current text sequence into the large oracle model, verifying by using a speculative decoding strategy, cutting off a rejected text token, and generating a text output token of the large language model; s3, the step S1 and the step S2 are cycled until the large oracle model generates the result representing the end of the generation task; gt, endgt; and a label. According to the method, a cascading strategy and a speculation decoding strategy are introduced, the advantages of the two strategies are combined, and a new speculation cascading technology is designed, so that the reasoning speed and efficiency are improved. The cascading strategy is formed by combining a plurality of language models with different levels and different parameter sizes, and the speculative decoding strategy is used for reducing waiting time by deducing in advance and generating part of results.
Owner:PIO CLOUD COMPUTING (SHANGHAI) CO LTD

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

PCBA surface defect detection method and system based on image recognition

The invention provides a PCBA surface defect detection method and system based on image recognition, and the method comprises the steps: collecting and constructing a multi-class PCBA overall defect image data set, and carrying out the preprocessing; constructing a pre-training neural network model, and classifying the preprocessed PCBA overall defect image data set; constructing a local target identification method based on a YOLOX network according to an overall defect classification result; and carrying out local defect detection on the PCBA surface based on a local target identification method. According to the method, the overall classification and local detection strategies are comprehensively applied to reduce the burden of the model, and the detection precision and speed are improved. And an attention mechanism is introduced to improve the performance and generalization ability of the model. Data enhancement, consistency processing, classification labeling and the like are carried out on an image data set, and the defect detection effect of the model is improved. And multiple optimization strategies such as structure improvement, loss function improvement and pruning lightweight are adopted for the network model, so that the image target detection performance is effectively improved.
Owner:SHENZHEN FUYAN STAR TECH CO LTD

Denoising network model based on diffusion model and oracle rubbing image restoration method

The invention discloses a denoising network model based on a diffusion model and an oracle rubbing image restoration method, which can improve the universality of the restoration method, improve the diversity of restoration results, reduce the calculation overhead and reduce the manual dependence. The denoising network model is adjusted based on an existing U-Net network and comprises a convolutional trunk network, an encoder, a middle layer, a decoder, a deep convolutional layer and a feedforward neural network which are connected in sequence; segmenting the input image by the convolutional trunk network; the encoder comprises a plurality of groups of cascaded paired visual state space blocks and image merging blocks; the decoder comprises a plurality of groups of cascaded paired visual state space blocks and image expansion blocks; performing down-sampling and up-sampling operations on the image merging block and the image expansion block respectively; the visual state space block adopts the architecture of an existing Mama module, and a two-dimensional selective scanning module is selected to replace an S6 module of the Mama module.
Owner:XIAMEN UNIV

Robot path planning method and system and storage medium

The invention discloses a robot path planning method and system and a storage medium, and the method comprises the steps: building an environment topology model based on sensor data and map information, building an adaptive map data structure, carrying out the global planning of a rough level through employing a low-resolution map, and carrying out the local optimization of a detail level through employing a high-resolution map. Adaptive dynamic switching is carried out between the two levels according to a path planning task; constructing a two-way alternate search strategy, and performing path search by combining an environment topology model and map information; environment change is monitored in real time, the connectivity probability of each edge in the probability graph is dynamically updated, and a path search strategy is adaptively adjusted according to the change of the probability graph; and establishing a backup path selection model based on reinforcement learning, and dynamically adjusting a backup path in combination with environment change and main path search. Through a bidirectional alternate search strategy, the path search efficiency is improved, the problem of path repetition caused by bidirectional search is solved, and the optimal path from the starting point to the end point can be found more quickly.
Owner:WUHAN TIANBANGJIE CONSTRUCTION ENGINEERING CO LTD

Visual time sequence feature network implementation method based on multi-module feature fusion

The invention discloses a visual time sequence feature network implementation method based on multi-module feature fusion. The system comprises a visual time sequence feature encoder VTFE, a multi-scale self-attention fusion module MSAF, an efficient feature reconstruction engine EFRE and an adaptive feature refinement processor AFRP. The VTFE module fuses a convolutional neural network and an extended long-short-term memory network, and realizes high-precision capture of spatial-temporal features. The MSAF module processes characteristic frequency domain information through fast Fourier transform, and the recognition capability of complex boundaries and noise is enhanced. The EFRE module optimizes feature reconstruction through depth separable convolution and jump connection to maintain global consistency. The AFRP module integrates multi-level features and improves the detail expression ability through deep convolution and an attention mechanism. The method is excellent in performance on a large-scale OCT data set, the segmentation precision of the retina edema and the recognition capability of a fine structure are remarkably improved, and an efficient and non-invasive auxiliary tool is provided for early diagnosis of ophthalmic diseases.
Owner:HANGZHOU DIANZI UNIV

Satellite remote sensing image cloud classification method based on space-time coding guidance

The invention discloses a satellite remote sensing image cloud classification method based on space-time coding guidance, and particularly relates to the technical field of satellite image processing and deep learning, and the method comprises the following steps: carrying out the preprocessing of the original data of a geostationary meteorological satellite and a Cloud Sat satellite; preprocessing operation such as cutting, projection conversion and feature selection is carried out on the geostationary meteorological satellite data, a top cloud type is selected for the Cloud Sat data to serve as a label, and space-time matching is carried out on the processed geostationary meteorological satellite data and the Cloud Sat data to obtain a training and testing data set; and establishing a GTCCT model, performing time and geocoding on the input data, inputting the coded feature data into a network for training, and finally obtaining the GTCCT model for cloud classification.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Big language model acceleration system and method based on binary quantization

The invention discloses a large language model acceleration system and method based on binary quantization, and the system comprises an extraction and quantization unit, a grouping packaging and splicing unit, an operation realization unit, and an inverse quantization and output unit, and comprises the specific steps: extracting parameters needing matrix / vector multiplication in a model; performing binary quantization processing on parameters of the model matrix / vector multiplication operation; splicing the grouped binary quantized parameters into single integer data bit by bit according to an order when matrix / vector multiplication is calculated by adopting a grouping and packaging algorithm; matrix / vector multiplication which is equivalent to original model reasoning and is friendly to hardware is executed; the result is converted back to the floating point data type through an inverse quantization algorithm, a final calculation result of the large language model in the matrix / vector multiplication operation is obtained, the final calculation result is transmitted into a subsequent network layer, and calculation acceleration for the matrix / vector multiplication operation in the large language model is completed. According to the method, the accuracy is ensured, and meanwhile, the speed is increased during large language model reasoning.
Owner:ZHEJIANG UNIV

Security authentication method and system of Internet of Things equipment, medium and equipment

The invention relates to the technical field of Internet of Things security, and provides a security authentication method and system for an Internet of Things device, a medium and a device, and the method comprises the steps: responding to an authentication request of the Internet of Things device, the authentication request comprising a unique identifier, a current timestamp and a comprehensive feature vector of the Internet of Things device; after the current timestamp and the comprehensive feature vector are connected, generating a random challenge value through a random function and sending the random challenge value to obtain a returned Internet of Things equipment response value; after the authentication key, the comprehensive feature vector and the random challenge value are connected, an expected response value is generated through a secure hash function, and whether the Internet of Things equipment is successfully authenticated or not is judged through comparison; and if the authentication is successful, generating a session key, connecting the authentication key with the session key, and updating the authentication key through a secure hash function. The common security threats such as replay attack and man-in-the-middle attack are effectively prevented, and the uniqueness and security of each authentication are ensured.
Owner:SHANDONG ZHENGZHONG COMP NETWORK TECH CONSULTING +1

Micro-expression recognition method and system based on state space model and double-flow fusion

The invention discloses a micro-expression recognition method and system based on a state space model and double-flow fusion, and relates to the technical field of expression recognition, and the method comprises the steps: extracting a starting frame image and a top frame image of a micro-expression continuous video frame sequence; inputting the initial frame image and the top frame image into a micro-expression recognition model based on a double-flow fusion network, extracting an optical flow image, and performing face key point detection and clipping operation on the top frame image and the optical flow image respectively; carrying out image block embedding operation to obtain texture features of the top frame image after cutting and motion features of the optical flow image; the two features learn the global dependency relationship and the local correlation between the image blocks from the positive direction and the negative direction through a parallel multi-layer bidirectional Mama fusion module, and deep image features and motion features are extracted after feature fusion; and the deep features of the two modes are interacted through a double-flow cross attention classification module, comprehensive features are learned, and a plurality of classifiers are combined to identify and output the micro-expression type more accurately.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)

Efficient graphic rendering system based on artificial intelligence core computing power

The invention relates to the field of graphic rendering, in particular to a high-efficiency graphic rendering system based on artificial intelligence core computing power, which comprises an intelligent task decoupling module for performing task decoupling on a graphic rendering task; the AI enhanced texture generation optimization module is used for learning a dynamic scene change rule to generate a texture map in real time, reducing calculation overhead in a repeated texture region by using a multiplexing algorithm, and performing super-resolution compensation on low-resolution textures by using a deep convolutional neural network; the AI driving illumination and shadow calculation module is used for predicting an illumination transmission path in a scene by using AI and reconstructing a dynamic shadow effect so as to realize high global illumination and shadow simulation; the task result synchronization module is used for synchronizing rendering data output by each subtask; according to the method, the high-quality texture map is dynamically generated, super-resolution compensation is carried out on the low-resolution texture, repeated calculation is avoided through a texture multiplexing algorithm, the calculation overhead is remarkably reduced, and the real-time rendering efficiency of a large-scale complex scene is improved.
Owner:CHANGSHA SHAOGUANG SEMICONDUCTOR CO LTD

Intelligent question answering method and system based on semantic vector optimization and dynamic prompt

The invention discloses an intelligent question and answer method and system based on semantic vector optimization and dynamic prompt, and the method comprises the steps: inputting a target question into a trained question and answer model, and obtaining an answer corresponding to the target question; wherein the trained question and answer model comprises an input layer, an embedded layer, a semantic vector generation module, a feature compression module, a dynamic prompt generation module, an answer generation module, a linear layer and an activation function layer which are connected in sequence; wherein the output end of the feature compression module is further connected with the input end of the RAG retrieval module, and the output end of the RAG retrieval module is connected with the input end of the dynamic prompt generation module; according to the trained question and answer model, the training process comprises the steps that a semantic vector generation module is constructed, and the semantic vector generation module is pre-trained; and setting the pre-trained semantic vector generation module in the question and answer model, training the question and answer model, and when the total loss function value does not decrease any more, stopping training to obtain a trained question and answer model.
Owner:SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN +4

Encryption algorithm dynamic selection method and system, and cloud computing-based secure communication method and system

The invention discloses a dynamic selection method and device of an encryption algorithm and a secure communication method and system based on cloud computing. The dynamic selection method comprises the following steps: firstly, acquiring a current network condition; calculating the score of each available encryption algorithm according to the current network condition; and finally, selecting the available encryption algorithm with the highest score as a target encryption algorithm, thereby completing dynamic selection of the encryption algorithms. According to the dynamic selection method of the encryption algorithm, not only can the most appropriate encryption algorithm be selected, but also the user experience can be improved, so that the data can be effectively protected in different environments and conditions. The system comprises a client device, an edge computing node and a cloud computing platform, wherein the client device is responsible for initiating a request; the edge computing node is specifically used for executing preliminary decryption, verification, sensitivity analysis and preprocessing of data and real-time application of a security policy; the cloud computing platform is specifically used for deep processing of data and is responsible for security policy updating of the system.
Owner:CHINA UNITED NETWORK COMM GRP CO LTD

Construction behavior safety risk identification method based on knowledge graph and large language model

The invention relates to a construction behavior safety risk identification method based on a knowledge graph and a large language model. The method comprises the following steps: S1, obtaining a key knowledge entity data set in the field of construction safety; s2, constructing a construction safety accident knowledge graph containing construction safety knowledge; s3, generating a word embedding matrix, wherein the word embedding matrix is used as an initial weight matrix of a word embedding layer in the large language model; s4, taking the embedded vector and the training set text of the large language model as a large language model training set to obtain a trained construction behavior safety risk identification model; and S5, obtaining an actual construction scheme, inputting the construction scheme into the construction behavior safety risk identification model, and outputting an identification result. Compared with the prior art, the method has the advantages of improving the accuracy and reliability of construction behavior safety risk identification of a large language model in the construction safety field and the like.
Owner:SHANGHAI JIAOTONG UNIV

Unmanned aerial vehicle target detection method based on feature fusion and detection head collaborative optimization

The invention discloses an unmanned aerial vehicle target detection method based on feature fusion and detection head collaborative optimization, and the method comprises the steps: obtaining a multi-scale feature map through employing a backbone network formed by stacking a convolution module CBS and a residual module C2f, sequentially transmitting the feature maps of various scales to a multi-level feature fusion module (ML-FFM), carrying out the feature fusion from a deep layer to a shallow layer, and carrying out the detection of a target target. Semantic information of shallow layer features is enhanced; inputting the fused feature map into a refined feature enhancement module (RFEM), eliminating position conflicts and redundant information based on a space-time attention mechanism, and optimizing details and positioning capability of deep features; and the enhanced feature map is sent to a prediction head based on Transform for detection, and target classification and positioning of the aerial image of the unmanned aerial vehicle are completed. According to the method, the problems that the unmanned aerial vehicle aerial image is large in scale change, and small targets are high in proportion and dense in distribution are solved, so that the precision of target detection in the unmanned aerial vehicle aerial image is improved. The modules proposed in the method can significantly reduce the calculation amount, and are suitable for the real-time detection scene of the unmanned aerial vehicle.
Owner:HOHAI UNIV +1

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

Image confrontation sample cleaning method based on pixel reconstruction

The invention discloses an image adversarial sample cleaning method based on pixel reconstruction, samples are cleaned through an image pixel reconstruction network, the robustness facing unknown attacks is improved by using random transformation operation, and the cleaning effect is improved by using a network optimization target aiming at the cleaning effect and task performance. The purified sample is a cleaned sample, and counterdisturbance in the sample is cleaned. According to the invention, a lightweight neural network model is adopted to realize an image pixel reconstruction process, and an adversarial sample cleaning network is formed. According to the cleaning network provided by the invention, the output result can be obtained without multiple denoising processes, and only one cleaning process is needed, so that the calculation overhead is greatly reduced. The invention also designs a random transformation operation of Gaussian noise addition based on the texture map, which can effectively destroy adversarial noise, prevent the cleaning network from generating overfitting to a known adversarial disturbance mode during training, and further improve generalization of unknown adversarial sample cleaning.
Owner:SICHUAN UNIV

Multi-focus image fusion method based on multilayer semantics and multi-scale self-attention

The invention relates to a multi-focus image fusion method based on multi-layer semantics and multi-scale self-attention, and the method is characterized in that the method comprises the steps: obtaining a source image, inputting the source image into an MSI-Dtrans model, carrying out the feature extraction of the source image through Haar wavelet transform, obtaining the feature information of different scales, and carrying out the fusion of the multi-focus image through the MSI-Dtrans model. Inputting the feature information of different scales into a dynamic Transform for processing, and obtaining an initial focus image; wherein the network architecture of the MSI-Dtrans model adopts a multi-stage up-down sampling structure of a U-shaped network and is obtained through training of a training set, and the training set comprises multiple image pairs generated based on blurred images of different degrees and training labels; and fusing the initial focus image with the source image to obtain a final fused image. According to the invention, image distortion is effectively avoided and a good visual effect is achieved.
Owner:CHONGQING NORMAL UNIVERSITY

Joint precoding design method in sensing integration scene

The invention discloses a joint precoding design method in a communication and sensing integrated scene. Aiming at a non-cellular cooperative communication and sensing integrated system, the invention provides a joint precoding design scheme based on unsupervised deep learning, and the scheme comprises the steps: building a signal and channel model in a communication and sensing integrated scene; constructing a deeply expanded joint communication sensing precoding design network; the collected training data is utilized to train the deep-expanded joint communication sensing precoding design network; in the deployment stage, the joint communication sensing pre-coding design network is used for outputting optimization algorithm process parameters, and then communication pre-coding vectors and sensing pre-coding vectors under different time slots of the communication and sensing integrated scene are obtained by using the constructed optimization algorithm process. According to the method, deep learning driving is fully utilized, various interferences which are mutually coupled and are difficult to process in the cellular-free cooperative sensing integrated system are inhibited, the problem that the algorithm is complicated in the prior art is solved, and the calculation overhead is greatly reduced.
Owner:SOUTHEAST UNIV

Point cloud rendering method based on multiple threads and LOD

The invention discloses a multi-thread and LOD-based point cloud rendering method, and relates to the field of video rendering, and the method comprises the steps: dividing point cloud data into n data blocks; calculating an initial position of each data block in the point cloud file, and creating n threads; extracting m pieces of LOD point cloud data with different levels of detail from the octree of each data block; calculating the proportion # imgabs0 # of the size of the current point cloud in a rendering viewport and the distance # imgabs1 # from a viewpoint to a camera, and calculating the detail level # imgabs4 # of the current to-be-rendered LOD point cloud according to a preset viewport proportion threshold value # imgabs2 # and a preset sight distance threshold value # imgabs3 #; according to # imgabs5 #, selecting point cloud data of a corresponding detail level from the m pieces of LOD point cloud data; for each interactive operation event, parallel coordinate transformation and illumination calculation are carried out on the LOD point cloud data to be rendered currently in different threads; submitting a calculation result to a renderer for rendering; aiming at low rendering efficiency in the prior art, the method and the device can efficiently render large-scale point cloud data.
Owner:LEIKE ZHITU (TAIAN) AUTOMOTIVE TECH CO LTD +1

Cross-regional air conditioner regulation and control strategy modeling method and cross-regional air conditioner regulation and control method and system

The invention provides a cross-regional air conditioner regulation and control strategy modeling method and a cross-regional air conditioner regulation and control method and system, and is applied to the technical field of intelligent regulation and control of air conditioners. The method comprises the steps that clustering processing is conducted on air conditioner load data of users in all regions, and a clustering result is obtained; constructing a regional cold supply system simulation model corresponding to the clustering cluster based on the users in the same clustering cluster in the clustering result; the operation safety of an actual regional cooling system is considered, modeling is carried out on the regulation and control process of the simulation model based on the Markov decision process, and an optimization strategy model is constructed by taking expected return maximization of a value function corresponding to an operation strategy of the simulation model as a target; and training an optimization strategy model based on simulation operation data of the simulation model. According to the method, the problems that in the process that the DCS participates in power grid load regulation and control, a trial-and-error training-based model is prone to system damage in practical application, and single-model regulation and control cannot guarantee the load regulation and control effect of a whole power grid are solved.
Owner:CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +2

Semiconductor device parameter extraction method based on reinforcement learning enhanced equalization optimizer

The invention relates to the technical field of semiconductor device parameter extraction, in particular to a semiconductor device parameter extraction method based on a reinforcement learning enhanced equalization optimizer, and the method comprises the steps: constructing a semiconductor device model, and determining input, output and optimization targets based on the semiconductor device model; and starting a parameter extraction algorithm based on the input, the output and the optimization target, and obtaining the optimal parameter of the semiconductor device, the parameter extraction algorithm being constructed by combining reinforcement learning with an equalization optimizer. According to the method, the efficiency and the precision of MOSFET parameter extraction can be improved by adaptively adjusting the iteration parameters of the optimization algorithm.
Owner:NAT UNIV OF DEFENSE TECH

Three-dimensional occupied grid network sensing method and device and medium

ActiveCN119495068AAccurate prediction results of environmental perception around autonomous drivingreduce uncertaintyInternal combustion piston enginesBiological modelsView cameraImaging processing
The invention relates to a three-dimensional occupied grid network sensing method, which comprises the following steps of: acquiring a multi-view camera image shot by automatic driving of a vehicle, inputting the multi-view camera image into an image processing backbone network, and extracting two-dimensional image features; performing view angle conversion on the two-dimensional image features to obtain three-dimensional body features; constructing matching cost body features according to the geometric correspondence of the sampling points at different moments; a convolutional neural network is adopted to extract weights containing depth correction information from the matching cost body features, the weights act on the three-dimensional body features at the current moment, and the three-dimensional body features after depth information correction are obtained; and inputting the three-dimensional body features into an occupied grid decoder, projecting the three-dimensional body features to a discrete semantic space, and generating a three-dimensional semantic occupied grid. Compared with the prior art, by constructing the matching cost body, more accurate depth information and geometric understanding can be obtained, the calculation overhead under a long time sequence is reduced, and accurate and efficient modeling of the automatic driving environment can be realized.
Owner:SHANGHAI ARTIFICIAL INTELLIGENCE INNOVATION CENT

Method and device for detecting and positioning surface defects of PCB (Printed Circuit Board)

The invention discloses a method and a device for detecting and positioning surface defects of a PCB (Printed Circuit Board). The method comprises the following steps: acquiring a reference image and a sample image of the PCB; processing the light and shade distribution of the sample image to obtain a sample image with uniform illumination; correcting a pixel difference between the sample image and the reference image to enable the reference image and the sample image to achieve pixel-level alignment; carrying out defect detection index calculation on the reference image and the sample image according to regions, and detecting and positioning defects. According to the method, the detection accuracy and efficiency are improved, the hardware cost and the calculation overhead are reduced, and deployment and implementation in the actual production and manufacturing process are easy; meanwhile, due to the high automation attribute, the detection reliability and the flexible adjustment capability, the method has wide application prospects and practical value.
Owner:NO 24 RES INST OF CETC

Double-neural network model predictive control method for flexible joint of robot

The invention discloses a double neural network model predictive control method for a robot flexible joint, and belongs to the technical field of robot intelligent control, and the method comprises the steps: carrying out the modeling of a nonlinear dynamic system of a flexible joint robot, and building a dynamic model; setting a GRU neural network model to approach a dynamic model of the system; based on a GRU neural network model, constructing a hybrid control NNMPC controller including position, speed and torque; optimization of the NNMPC controller is optimized on the basis of a nonlinear optimization solver; and setting an NARX neural network model to approach a solution of an NNMPC controller, and forming a dual-neural network model predictive control method. According to the double-neural-network model prediction control method for the flexible joint of the robot, two neural networks are introduced to work cooperatively, one neural network is used for approaching the dynamics of the system, the other neural network is used for accelerating the optimization solving process of the model prediction controller, the calculation overhead possibly caused by a traditional method in a high-dimensional nonlinear system is reduced, and the calculation efficiency is improved. Therefore, real-time control is realized.
Owner:XINJIAN ELECTROMECHANICAL TRANSMISSION (SHANGHAI) CO LTD

Large language model weight quantization method and system based on optimal quantization coding and application

The invention discloses a large language model weight quantization method based on optimal quantization coding, and the method comprises the steps: partitioning, normalization, quantization coding generation, quantization and inverse quantization, and achieves the weight quantization of a large language model, and comprises the following steps: 1, dividing a to-be-quantized weight matrix into a plurality of data blocks; step 2, carrying out normalization processing on elements in each data block; step 3, according to the normalized weight matrix value distribution characteristics, generating a quantization target code by adopting a clustering method; step 4, mapping elements in each data block after normalization processing in the step 2 to the index value of the quantization target code in the step 3 to realize element quantization; and 5, searching a floating-point number corresponding to the index value in the quantization target code, and multiplying the floating-point number with the normalized constant of the data block to obtain an inverse quantization floating-point number. The invention further discloses a system and application for implementing the method, and the system and the application have wide application scenes.
Owner:SHANGHAI QUSU CHAOWEI TECHNOLOGY CO LTD

Liver tumor segmentation method based on SCAF-TransUNet

The invention discloses a liver tumor segmentation method based on SCAF-TransUNet, and the method comprises the steps: firstly, segmenting a liver image into semantically related superpixel regions through SLIC superpixel preprocessing, enabling a model to be more accurately focused on a tumor and other key regions, reducing the calculation redundancy, and improving the efficiency and precision of feature extraction; secondly, a CECA module introduced in jump connection replaces a traditional full connection layer through one-dimensional convolution, the attention mechanism between channels is simplified, capture of the channel dependency relation is enhanced, and meanwhile the feature extraction precision is kept; finally, the FPN is added in the decoder, and the fusion capability of the multi-scale features is further enhanced. According to the FPN, feature maps with different resolutions are fused layer by layer, so that the model can effectively combine global semantic information and local detail features before up-sampling, and the processing capacity for complex liver boundaries and small tumors is improved. Finally, the improvements significantly improve the accuracy and robustness of the liver tumor segmentation task.
Owner:SHENYANG UNIVERSITY OF TECHNOLOGY

Unmanned aerial vehicle group distributed management method based on mobile active secret sharing technology

The invention discloses an unmanned aerial vehicle group distributed management method based on a mobile active secret sharing technology, which supports off-line of a trusted institution and comprises the following steps: the trusted institution TA generates public parameters; a mobile base station MS and an unmanned aerial vehicle UAV participating in communication respectively register with a trusted mechanism in a registration stage, and acquire information such as a secret key and a certificate; the UAV joins the MS and is administered by the MS, and after mutual identity authentication, the MS distributes secret shares to the UAV; performing identity authentication on the unmanned aerial vehicle group; the unmanned aerial vehicles of the two groups share the share, group fusion is achieved, and after a new share is obtained, each unmanned aerial vehicle updates the certificate of the unmanned aerial vehicle. According to the method, the sub-secrets of the unmanned aerial vehicles are autonomously updated through a mobile active secret sharing technology, and fusion of completely decentralized unmanned aerial vehicle groups is realized. Secondly, an efficient certificate self-updating method is designed. The unmanned aerial vehicle can update the certificate only by calculating a threshold signature. Detailed safety certification and comprehensive experiments show that dynamic autonomous management of the distributed unmanned aerial vehicle group can be realized, and the method has good safety characteristics and relatively low calculation overhead.
Owner:ANHUI UNIV