499 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 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.

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 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 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.

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 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 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.

SYSTEMS AND METHODS IN THE FIELD OF SELF-SUPERVISED DETECTION OF FACIAL BOUNDARIES. Systems and methods for self-supervised learning (SSL) in facial detection networks are proposed. In one embodiment, a facial detection network comprises encoder components configured to encode facial features, the encoder components including trained components of a masked image modeling (MIM) network configured to process non-overlapping patches determined from the input image, the MIM network trained with an SSL objective; and decoder components configured by training to determine local matches between features to determine estimates for facial landmarks. In one embodiment, the MIM network is an MAE network.In one embodiment, the decoder components are derived from those of a second trained network comprising the encoder components as trained but fixed, wherein the decoder components of the second network are trained using locality constraint repulsion loss (LCR). Methods are proposed for SSL training of the encoder and decoder components. Figure for abstract: none.

The invention discloses an improved remote sensing image road extraction method based on a U-net network, and the method comprises the steps: constructing an improved U-net network architecture: an ERUN-Net network, employing a C-OfficientNet V2 network fused with a CBAM attention mechanism through a feature extraction module, employing a channel-space dual attention mechanism to enhance the multi-scale feature learning capability, and reducing the calculation complexity; deformable convolution and cavity space pyramid pooling are combined, a convolution kernel sampling area is dynamically adjusted, and a receptive field range is expanded; meanwhile, a multi-scale loss function MRE Loss is adopted, cross entropy loss, boundary loss and Dice loss are fused, and global classification, region overlapping and boundary positioning are optimized. The problems that a traditional U-Net model is poor in scale adaptability, wrong segmentation is blocked and the boundary is discontinuous are effectively solved, and higher road extraction integrity and marginal definition are achieved while the calculation efficiency is guaranteed.

A request for a virtual private network (VPN) server is received at a central server from a user device. The request includes an intended network usage. A list of VPN servers is transmitted to the user device. Network test results that include network statistics measured between the user device and the VPN servers of the list of VPN servers are received from the user device. VPN server scores for the VPN servers are updated based on the network test results, the intended network usage, and at least one network condition associated with the intended network usage. An updated list of VPN servers ordered based on the updated VPN server scores is generated. The updated list of VPN servers is transmitted to the user device.

The invention relates to the technical field of network advertisement processing, and discloses a method for intelligently identifying and automatically closing website advertisements based on a multi-modal large model. The method comprises the following steps: acquiring text data, image data and interactive behavior data of a website page in real time, and performing format standardization processing on each modal data to obtain a multi-modal original data set; extracting text features, image features and behavior features of the advertisement candidate area according to the data set, and establishing a feature association index; performing cross-modal semantic fusion on the feature association index through a pre-trained multi-modal large model to generate an advertisement recognition probability value; comparing the advertisement recognition probability value with a preset threshold value, judging whether the advertisement candidate area is a target advertisement or not, and generating a recognition result; and triggering a page element operation instruction based on the identification result, executing an automatic closing operation on the target advertisement area, and recording an operation log. According to the method, interference of advertisements on user browsing is effectively reduced, and network use experience is improved.

Embodiments herein disclose e.g. a method performed by a wireless device (10) for handling communication for the wireless device in a second wireless communication network. The second wireless communication network coexists with a first wireless communication network on a same bandwidth in frequency, wherein the first wireless communication network applies a first shift in frequency in uplink transmissions. The wireless device receives from a radio network node (12, 13), an indication indicating application of a second shift in frequency to uplink transmissions in case the second wireless communication network uses Frequency Division Duplex (FDD). The wireless device further applies the second shift in frequency to uplink transmissions, wherein the second shift defines a shift in frequency to a subcarrier relative to a subcarrier grid of the second wireless communication network or a shift in frequency to the subcarrier grid of the second wireless communication network.

A method and a user equipment (UE) are provided for explicitly linking repeated physical downlink control channels (PDCCHs). The UE receives the repeated PDCCHs from a network. Each of the repeated PDCCHs include downlink control information (DCI) that schedules reception of a same physical downlink shared channel (PDSCH) at the UE. The UE links the repeated PDCCHs having common PDCCH candidate numbers across search space (SS) sets of a control resource set (CORESET). The repeated PDCCHs are received in accordance with the UE and the network communicating using a multi-transmission and reception point (TRP) repetition scheme or a multi-TRP multi-chance scheme.

Cybersecurity reconnaissance, analysis, and scoring uses distributed, cloud or edge-based pools of computing services to provide sufficient scalability for analysis of IT / OT networks using only publicly available characterizations. An in-memory associative array manages a queue of configuration and vulnerability search tasks through at least one public-facing proxy network which uses configurable search nodes to approach the target network with search tools in a desired manner to control certain aspects of the search in order to obtain the desired results, especially when target network behavior adjusts based on counterparty characteristics. A data packet modifier reveals IP addresses of threat actors behind port scans and subsequently block the threat actors.

The invention discloses an urban electric vehicle charging station site selection planning method based on reinforcement learning, and the method comprises the steps: obtaining the road network and vehicle track data of a city, and obtaining node information; defining a reinforcement learning framework according to the node information; based on a-greedy attenuation strategy, selecting and executing an action to form a new state and a reward value, and expanding the new state and the reward value to an experience playback buffer pool; using a state value function and an action dominant function to improve the DQN network, using a priority-based experience playback mechanism to sample from an experience playback buffer pool to train the improved DQN network, constructing a target function by taking the score maximization of the scheme and the total cost not exceeding the budget as targets, and generating a plurality of candidate schemes; the score of each scheme is calculated, and the scheme meeting the objective function and having the highest score is the optimal scheme; the method can improve the sampling efficiency of high-value experience, shortens the convergence time, gives consideration to the balanced layout of multiple regions in a city, and remarkably improves the overall score and coverage effect of a charging station site selection scheme.

The invention belongs to the field of centralized control of power distribution stations, and particularly relates to a centralized control system and method of an intelligent power distribution station. A centralized control method of a power distribution intelligent station comprises the following steps: S10, establishing a communication network between each power distribution room node and a centralized control center according to a physical position relationship among power distribution rooms, and collecting operation data of devices in each unit in the power distribution rooms by using the power distribution room nodes; and S20, each power distribution room establishes an operation prediction model based on the local historical operation data, and the power distribution room nodes input the currently collected operation data into the operation prediction model to calculate the operation data after the preset short-term time and the preset long-term time as short-term prediction data and long-term prediction data. According to the scheme, the accuracy of abnormal data detection and prediction is improved, and the problem of low monitoring operation and maintenance reliability in a device aging or multi-power distribution room node cooperative monitoring scene in the prior art is solved; and the operation speed of detection and prediction is improved.

Techniques for protection scheme configuration in a communication network are disclosed. For example, a home communication network of given user equipment sends protection scheme configuration data to the given user equipment using a user equipment parameter update procedure, or a steering of roaming procedure in a visited communication network scenario.

Techniques are provided for migrating a volume utilizing an object copy work queue and an object copy driver module. Data of the volume is stored within objects stored across a storage tier and capacity tier of a source object store. As part of migrating the volume to a destination object store, the objects are migrated to the destination cluster. Directly copying the objects involves multiple read operations to the source object store and a write operation at the destination object store. The techniques provided herein improve the efficiency of the migration by initially sending metadata from the source object store to the destination object store for performing backend object copy operations to migrate the volume. This results in fewer operations and less network usage, thus improving the efficiency and cost of migrating the volume.

The present application provides systems and methods for adaptive network resource allocation using application prioritization and deprioritization. An application prioritization manager (APM) receives data about an application, or other contextual data, from various components, and prioritizes the application's network resources among other applications that are also prioritized. The APM generates scores for different factors that are derived from the data, such as application type, application network usage, whether an application is minimized, or whether an application is in focus, among others. The APM combines the scores for the different factors into a combined score for the application, and prioritizes the application among other applications based on their combined scores. The APM selects a prioritization mechanism for the application based on the combined score, such as traffic shaping, traffic policing, traffic scheduling, or other techniques that control aspects of the network traffic.