652 results about "Network usage" patented technology

Computer-implemented techniques for multimodal content relevance prediction using neural networks involves processing multimodal content comprising a digital image and text. Initially, dense embeddings are obtained: an image embedding from a pretrained convolutional neural network, and a text embedding from a pretrained transformer network. These embeddings encapsulate the features of the image and text respectively. Two pretrained dense neural sub-networks then reduce the dimensionality of these embeddings. A third dense neural sub-network determines a numerical score for the multimodal content using the reduced embeddings and an additional feature embedding. This score reflects various aspects of the multimodal content, leading to an action taken based on this numerical evaluation, providing a comprehensive and nuanced understanding and management of multimodal digital content.

The invention relates to the technical field of agricultural wireless sensor networks, and discloses an agricultural wireless sensor network topology reconstruction method based on an energy consumption balance model. The method comprises the following steps: acquiring multi-dimensional energy consumption data of each node, including node residual energy, communication load intensity and an environment interference coefficient; extracting a node energy health degree based on residual energy, generating a communication priority sequence according to communication load intensity, and analyzing an environment interference coefficient to generate an interference distribution thermodynamic diagram; inputting the result into an energy consumption balance evaluation model to generate a topology reconstruction strategy; and a self-adaptive topology adjustment map is constructed through a distributed optimization algorithm, and a node connection relation optimization scheme is output. The system is correspondingly provided with a multi-dimensional data acquisition module, an energy consumption state analysis module and the like. The problems of unbalanced energy consumption, non-uniform communication load, environmental interference and the like of the agricultural wireless sensor network can be effectively solved, the network performance is improved, the service life of the network is prolonged, and the development of precision agriculture is promoted.

The invention provides a steel surface defect detection method and device, and belongs to the technical field of steel defect detection.The steel surface defect detection method comprises the steps that a defect detection network based on a YOLO architecture is constructed, and the defect detection network comprises a lightweight feature extraction network, a self-adaptive multi-scale feature fusion network and a head network; the lightweight feature extraction network comprises four layers of architectures, and each layer of architecture comprises a first convolutional layer and a space expansion feature module; the feature space expansion module comprises a second convolutional layer and an element multiplication operator module; the adaptive multi-scale feature fusion network comprises an adaptive fusion module and a feature space expansion module; training the constructed defect detection network based on the historical steel defect image, and performing channel pruning on the trained defect detection network by using LAMP (Loop-Mediated Isothermal Amplification); and acquiring a to-be-identified steel image, and inputting the to-be-identified steel image into the pruned defect detection network for defect detection. According to the method, the defect detection precision of the network can be improved while the network complexity is reduced.

The invention discloses a main and distribution cooperative fault detection method and device based on a Mama network, and a medium. The method comprises the following steps: S1, measuring fault data of a main network and a distribution network, and constructing a training set; s2, representing a topological structure of the main and distribution network through an adjacent matrix of the graph, constructing the adjacent matrix and an edge feature matrix of the graph, and defining the weight of edges to obtain an edge feature matrix E and a feature matrix X as priori knowledge; s3, constructing a Mama network model based on the prior knowledge and the measurement data, wherein the Mama network model comprises a time sequence feature extraction network LSTM, a graph convolutional neural network, a prior knowledge and feature fusion module, a Softmax layer and a Mama network; and S4, training and testing the Mama network model by using the training set and adopting a joint loss function. According to the method, information propagation can be optimized, the calculation complexity is low, the unbalanced data processing capacity in the main and distribution cooperative power grid is effectively improved, and the model training precision and effect are improved.

The invention discloses a lightweight tea disease target detection method based on TeaDisease LiteNet, and the method comprises the following steps: collecting and marking tea disease images in a real environment, and constructing a tea disease data set; the method comprises the following steps of: dividing a main network into a training set, a verification set and a test set, performing data enhancement, using a MobileNetV3 module in the main network, using a Slim-neckAKConv module in the neck network, adding an iRMBEMA attention mechanism, using a Shape-IoU regression loss function, and using a SlideLossEMA classification loss function; the optimized target detection model is obtained through training, the model is used for tea disease detection, and the method has the technical characteristics that the problems that an existing tea disease detection model is high in calculation complexity, large in model parameter quantity, difficult to efficiently operate on equipment with limited resources and the like can be solved.

A system and method for interpreting a policy comprising a network usage permission description; configuring a first network interface circuit in response to the network usage permission description; and regulating communications, using the first network interface circuit, between end points of a first network zone of a vehicle and end points of a second network zone of the vehicle.

Systems and methods for inter-node verification of models are disclosed. Some embodiments of the present disclosure propose a method for a first network node to provide a model to a second network node together with configurations / instructions / semantics information for verifying (e.g., testing and / or validating) the model. In some embodiments, the model is an Artificial Intelligence (AI) and / or Machine Learning (ML) model. This may enable a first network node, responsible for training an AIML model and providing it to a second network node, to specify whether, when, and how the model can, should, or must be verified by the second network node prior to using the model. This allows the first network node to ensure that the model, for which it is responsible, is correctly set up, applied, or installed by the second network node and works as expected before the second network uses the model, for instance, for inference.

The invention provides a sea surface height abnormal data downscaling method based on deep learning, and relates to the technical field of data processing, and the method specifically comprises the following steps: preprocessing data including AVISO data, SWOT data and key auxiliary variables; an enhanced super-resolution generative adversarial network ESRGAN is constructed, a high-resolution feature map is generated, and the ESRGAN comprises a generative network and a discrimination network; using a plurality of loss function combinations to optimize the performance of the generative network and the discriminant network, including adversarial loss, perception loss and pixel loss; and evaluating the pixel-level error and the spatial detail consistency output by the ESRGAN by adopting a root-mean-square error and a structural similarity index respectively. According to the technical scheme, the problems that in the prior art, a data downscaling method is limited in applicability and generalization ability, and is difficult to adapt to fusion requirements of different regions and multi-source data are solved.

The invention discloses an eSIM service cost intelligent optimization method based on different operator information sources, and particularly relates to the technical field of operator network management. The method comprises the following steps: collecting eSIM tariff rules of a plurality of operators and real-time charging data of eSIM terminals, extracting tariff terms and conditional expense trigger mechanisms hidden in charging behaviors of different operators by using an association rule mining algorithm, and constructing a multi-level cost structure model; on the basis of a network registration behavior log of the eSIM terminal, predicting the probability that each operator signal source has an abnormal registration event, and evaluating the risk that each operator signal source triggers a hidden cost trap in combination with a multi-level cost structure model; and according to the real-time network signal parameters of the eSIM terminal, a signal source recommendation strategy is generated in combination with the risk assessment result, and the eSIM terminal is driven to execute a signal source switching operation, so that real-time adjustment and cost optimization control of communication network selection are realized, and the service stability of the eSIM in a cross-network use scene is improved.

The invention discloses an unmanned aerial vehicle cluster collaborative search method and system based on deep multi-agent reinforcement learning. The method comprises the following steps: defining a tracker unmanned aerial vehicle, a reconnaissance unmanned aerial vehicle and an intelligent target unmanned aerial vehicle; initializing an actor network, a commentator network and an experience playback buffer area for each unmanned aerial vehicle agent; each unmanned aerial vehicle agent selects an action and executes the action through an actor network according to the current state, and after the environment returns a new state and a corresponding reward, the interaction experience is stored in an experience playback buffer area; randomly extracting a batch of experience samples from the experience playback buffer area, and updating a commentator network; calculating gradients using the commentator network, and updating the actor network of each agent according to the gradients; and continuously performing interaction, data collection, network training and target network updating of the intelligent agent until a certain training period or performance standard is reached. According to the invention, the efficiency and safety of the unmanned aerial vehicle cluster for executing the collaborative search task in a complex environment can be improved.

The invention provides a farmland plot extraction method based on a multi-type double-branch convolutional neural network, and the method comprises the steps: creating a double-branch multi-task network DBMNet based on a multi-type convolution module, and designing a double-branch feature extraction module DBFE to replace a convolution layer of an original network, a dynamic linear constraint convolution module LCDC and a multi-scale deformable convolution feature extraction module MDFE are used to comprehensively extract edge features of an image and field block region features of different sizes and shapes, the perception ability of a network to information of different scales is improved, and thus the segmentation precision of the network is improved. The network uses boundary detection and distance regression tasks to improve the precision extraction of the farmland plot masks, so that the network has a better generalization effect. According to the method, the multi-type convolutional network is applied to the farmland plot extraction task, the experimental result shows that compared with other most advanced algorithms, the method has the best segmentation performance, discriminative features of the farmland plot can be effectively extracted, the segmentation precision is remarkably improved, the farmland plot is accurately extracted, and the method has great application potential and prospect.

The invention discloses an offline reinforcement learning method based on behavior action generation, and the method comprises the steps: collecting a first data set of an intelligent agent, and carrying out the preprocessing of the first data set, and obtaining an offline data set; constructing a first diffusion model for training to obtain a final diffusion model; for each state in the offline data set, acquiring M actions corresponding to the state from the final diffusion model to form a support action data set; constructing a strategy network, N value networks, a target strategy network and N target value networks; training the strategy network and the value network by using the offline data set and the support action data set, and updating network parameters of the target strategy network and the target value network at the same time; and making a decision by using the learned optimal target strategy network, so that the intelligent agent performs a reinforcement learning task in an offline environment. According to the method, the limitation of an existing offline learning method on strategy learning is reduced, and the completeness and execution effect of a robot or an automatic driving task are remarkably improved.

The invention discloses a photovoltaic power generation capability prediction method and system based on a space-time diagram neural network, and a medium. The method comprises the following steps: preprocessing historical data of a power system; a plurality of power stations are divided into a plurality of clusters, a power system is abstracted into a topological graph, and each cluster is regarded as a node of the topological graph; learning time features of the topological graph by adopting a time self-attention network model; learning spatial features of the topological graph by adopting a spatial graph convolutional network model; stacking the time self-attention network and the space graph convolutional network by adopting a factor type structure; and performing prediction by using a full connection layer. According to the method, the photovoltaic power generation system is modeled into the graph model, so that the spatial relationship and the time dependence among different power stations can be effectively captured, more efficient data processing is realized, redundant information is reduced, data streams can be optimized, and the requirements on storage resources are reduced by reducing direct operation on original data, so that the system is more efficient and more reliable. And the processing speed of the hardware is improved.

A monocular self-supervision depth estimation method fusing multi-resolution features and global context belongs to the technical field of computer vision, and comprises the following steps: firstly, providing an encoder based on a cross-stage feature high-resolution network, and enhancing the extraction capability of multi-scale features by improving a cross-stage connection mechanism of an HRNet network; secondly, a visual Transform module is introduced to improve complex down-sampling operation, and a multi-head self-attention mechanism is utilized to establish global pixel association; then, an improved decoder network is provided, a channel attention module is used for re-weighting coding features, multi-level features of an encoder are utilized more efficiently, and the balance between segmentation precision and calculation cost is achieved; and finally, proposing an improved attitude estimation network based on lightweight ResNet18, predicting 6-DoF relative poses of adjacent frames in combination with a four-layer convolutional decoder, and accurately estimating the depth of each object. According to the invention, the accuracy of depth estimation is improved, and the visual effect of the depth view is improved.

The invention discloses a self-adaptive wafer defect identification method and system in a semi-supervised field. The method comprises the following steps: acquiring a data set of a wafer defect source domain and a wafer defect target domain; the data set is preprocessed; constructing a cross alignment network, and respectively extracting image features of a source domain and a target domain of the preprocessed data set by using a feature extractor and an encoder; for the extracted image features, using a classifier to obtain an output probability, for unmarked data, determining and updating a false label threshold value of each category through a dynamic threshold value strategy, then using a sample-by-sample cross alignment method, a category-by-category cross alignment method and a consistency regularization method to calculate a loss function, and performing training; obtaining a trained cross alignment network; and the trained cross alignment network is used as a prediction model, and the wafer defect category for identifying the unmarked data of the target domain is output. According to the method, knowledge migration among different data sets can be effectively realized, and relatively high recognition accuracy is realized under the condition that the target domain data set only has a very small number of labels, for example, each category only has one label.

The invention relates to a textile product defect identification method based on improved YOLOv11. The method comprises the following steps: acquiring a textile product defect image data set; performing pretreatment; dividing into a training set and a verification set; the method comprises the following steps: introducing MConv into a YOLOv11 backbone network, adding a CCIAP module behind a C2PSA module, and applying BiFPN in a path aggregation network; performing prediction through YOLO Head to obtain N prediction feature maps; the overall loss of the network is calculated, and network parameters are optimized through back propagation; predicting the verification set image through a network to output AP values of various categories; repeating the above steps to obtain a trained YOLOv11 network; and detecting the test image or video by using the trained detector to obtain a detection result. According to the method, the MConv is introduced into the YOLOv11 network to enlarge the receptive field, the CCIAP module is added behind the C2PSA to improve the feature extraction capability, and the BiFPN is applied to the Neck layer to enhance the feature fusion capability, so that the target detection precision is improved and the real-time detection of textile product flaws is realized under the condition that the reasoning speed is not influenced.

Described herein are systems and methods for optimizing energy efficiency in a network utilizing a control plane or other network administration device or software suite. The control plane continuously monitors end-to-end network paths and collects real-time data about network topology, traffic patterns, and connected devices. By analyzing the collected network data, the control plane identifies power needs for network nodes and generates energy saving recommendations or instructions tailored to each node's specific capabilities. Network nodes can subscribe to the energy efficiency service provided by the control plane, receive network usage data, and execute energy saving operations based on the recommendations. The control plane dynamically updates the energy saving recommendations in response to changes in network conditions, enabling network nodes to optimize their energy efficiency without compromising network performance and availability. These updates can be based on current network conditions but can be generated from historical data and / or machine learning processes.

Embodiments provide a user device, UE, of a wireless communication network, the wireless communication network using one or more Artificial Intelligence / Machine Learning, AI / ML, models for one or more use cases, wherein the UE is configured or preconfigured with a plurality of AI / ML models for performing one or more certain operations, and wherein, dependent on one or more criteria, for performing the one or more certain operations, the UE is toswitch from a first AI / ML model to a second AI / ML model, ordeactivate one or more of the plurality of AI / ML models, orswitch from a current operation mode to a new operation mode.

The invention discloses a human body behavior recognition method and system based on space-time decoupling multi-scale feature fusion. The system comprises a local space-time multi-scale feature fusion network MDCNN and a space-time decoupling network DTST. Extracting different scale features of multichannel sensor data by using a multi-scale convolutional neural network, extracting shallow layer features and deep layer features of signals at the same time, and extracting features representing action information by fully utilizing complementary information among different level features; the method comprises the following steps of: decoupling a network into a time decoupling structure and a space decoupling structure through a time-space decoupling network based on Transform, so as to accurately extract time-space characteristics in an inertial signal; and finally, using a Softmax classifier to carry out action classification and recognition. According to the method, consistency and complementarity among multi-sensor data can be efficiently utilized, multi-scale spatial-temporal characteristics are fused, changes in time dimensions and relevant information in spatial positions are fully considered, different attention degrees are kept for signals of different sensing channels, and the recognition precision in human behavior recognition is improved.

The invention relates to the technical field of data processing, can be applied to business scenes such as financial science and technology, medical health and the like, and discloses a terminal state processing method, device, equipment and medium. And collecting network use data and log data of the target terminal, and generating terminal state information in combination with processing and analysis. According to the method, screening is performed by combining the physical identifier of the terminal with the network priority, the key terminal is automatically marked, the network interaction data and the wireless log information are further acquired, and the terminal state information is generated through joint processing, so that the identification accuracy of the key terminal and the wireless network state analysis depth are improved, and the user experience is improved. And fine management and visual monitoring of important communication terminals are realized.

The invention discloses a dynamic switching distributed file storage system based on an elastic data network, and the system comprises a multi-network architecture module which is used for deploying a plurality of independent network channels, and each network channel independently transmits data; the client elastic data network access module is used for accessing and storing data according to the data network and the priority, and automatically switching and recovering when the network fails; the intelligent data transmission module is used for selecting an optimal data transmission path; the data recovery module is used for calling the intelligent data transmission module and selecting an optimal path according to the network use condition; the network fault automatic detection and recovery module is used for detecting and processing network channel or path abnormity, detecting master and salve when a fault occurs, acquiring network health state data, and switching master and slave according to the network health state data; the data security processing module is used for encryption and verification; and the cache optimization module is used for collecting data access frequency data and heat dynamic data.

The invention provides a continuous anomaly detection method and system for a wind power equipment state monitoring system, and the method comprises the following steps: S1, collecting original multi-dimensional time series data related to the equipment state in the operation process of wind power equipment, and dividing the original multi-dimensional time series data into n tasks according to a time window; performing standardization and random mask preprocessing on the data of each task to generate n tasks to be trained; s2, constructing a continuous learning model based on a Gaussian mixture variational auto-encoder, wherein the continuous learning model comprises an encoder, a decoder and an attention priori network; s3, performing local training on the continuous learning model by using the (1-n) th to-be-trained task; s4, performing global training on the initial global decoder by using the (2-n) th to-be-trained task, and outputting a trained continuous learning model; and S5, inputting a to-be-detected sample into the trained continuous learning model, and outputting a detection result. The problem of disastrous forgetting in an existing anomaly detection method is solved.

A computer-implemented system and computer instructions stored on non-transitory computer readable medium for bilingual medical inquiry in both Arabic and English, including multiple-choice question answering, open-ended question answering, and multi-turn question answering. The system and instructions use a mixture of experts large language model (MOE LLM) having a router network connected to multiple expert networks. The MOE LLM is trained with medical domain data and is used to receive the input bilingual text in a format for a medical inquiry, and output text in a format of a response to the medical inquiry, in sequence. The system and instructions incorporate an English-to-Arabic translation pipeline having a language translation model to generate Arabic language medical instruction sets from English language medical instructions, for large scale use in Arabic and English medical inquiry.

The invention provides a network use behavior analysis and bandwidth allocation method and system based on a portable WIFI device, and the method comprises the steps: carrying out the grouping of user behaviors through employing a clustering method in machine learning according to a preliminary behavior feature set, carrying out the discrimination of use modes for different purposes, such as entertainment, work, learning, and the like, and carrying out the recognition of the user behaviors. Determining core category distribution behind the user behavior diversity; according to the resource pre-allocation instruction, obtaining an available state of a current network resource, dynamically adjusting a bandwidth allocation proportion in combination with predicted demand peak data, and determining specific execution parameters of an intelligent allocation mechanism; and obtaining real-time feedback data of the network equipment in the execution process through the adjusted resource allocation scheme, and judging whether the dynamic response speed meets the requirement of improving the service quality or not according to the fluctuation condition of the resource allocation efficiency to obtain a final optimization record.

A monitoring system is described for monitoring at least one slice of a communications network using at least one access network, an edge network and a core network. The system, comprises, for each slice, a plurality of intrusion detection modules configured to monitor elements associated with said section and comprising at least a first module for detecting intrusions at the access network level, a second module for detecting intrusions at the edge network level, and at least a third module at the core network level, each of the modules being configured to provide a piece of information representative of a local confidence level assigned to the section according to a behaviour of at least one element that it monitors. One of the third modules is additionally configured to evaluate, from the provided information, an overall confidence level for this section and to trigger an intrusion mitigation action for this section depending on the value of this overall confidence level.

Apparatuses, systems, and techniques to use two or more neural networks to encode two or more different portions of a a set of information are described. In at least one embodiment, two or more neural network encoders are used to encode two or more different portions of a set of information to be used by two or more networks that each include one of the two or more neural networks respectively.

The invention discloses a target speaker extraction method and system based on a multi-scale multi-modal alignment network, and relates to the technical field of target speaker extraction. According to the method, the multi-scale and multi-mode alignment network is constructed to extract the target speaker, on one hand, voice embedding of different time scales is obtained through multi-scale coding, and richer voice embedding is extracted through multi-direction depth coding; on the other hand, a modal alignment part based on comparative learning is introduced; the distance between electroencephalogram features and voice embedding is minimized on the same time step length during network training, and noise comparison estimation loss is constructed to be matched with scale-invariant signal distortion ratio loss constructed based on output of a voice decoding part to form a loss function used by the whole network; according to the method, the alignment of the cross-modal data is realized, the difficulty of multi-modal fusion is reduced, the adjustment of the overall parameters of the network is realized, and the overall performance of extracting the target speaker by the network is ensured and improved.

Systems and methods for object tracking are described. One or more aspects of the systems and methods include receiving a video depicting an object; generating object tracking information for the object using a student network, wherein the student network is trained in a second training phase based on a teacher network using an object tracking training set and a knowledge distillation loss that is based on an output of the student network and the teacher network, and wherein the teacher network is trained in a first training phase using an object detection training set that is augmented with object tracking supervision data; and transmitting the object tracking information in response to receiving the video.

A method of scheduling data transmission in a radio access network is provided. The radio access network comprises a scheduler configured to orchestrate communication of data between one or more base stations and a plurality of User Equipments, UEs, according to a set of instructions. The method comprises receiving real-time network usage data. The method further comprises dynamically modifying the set of instructions based on the network usage data. The method further comprises implementing the modified set of instructions so that the scheduler is configured to orchestrate communication of data between the one or more base stations and the plurality of UEs according to the modified set of instructions.

The invention discloses a distributed region-of-interest image compression method, and mainly solves the problems that the training speed of an existing image compression algorithm is low and distinguished feature extraction is not carried out according to the importance of different region features in the prior art. According to the implementation scheme, the method comprises the following steps: selecting a landsat remote sensing image data set from a public website, and dividing the landsat remote sensing image data set into a training set and a test set; a distributed training strategy is introduced into an image compression algorithm; constructing a multi-layer hyper-prior image compression and decompression network comprising a region-of-interest detection module, an analysis transformation sub-network, a synthesis transformation sub-network, a hyper-prior analysis sub-network and a hyper-prior synthesis transformation sub-network; training a multi-layer hyper-prior image compression and decompression network by using the training set; and inputting the test set into the trained network to obtain a compressed and decompressed image. Reasonable and efficient compression can be performed according to the feature importance of different regions of the image, the training speed is improved, the code rate is saved, and the method can be used for a scene of performing fine compression on important regions in the image.