210 results about "Network usage" patented technology

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.

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.

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.

Embodiments of the present disclosure provide enhanced systems and methods for predicting optimal design flow parameters for optimized output targets for physical design synthesis of a given IC design. A Variational Autoencoder (VAE) along with a regression network are trained using a dataset comprising synthesis design construction flows from historical IC designs to provide a training data representation of the dataset constrained to a latent space of the VAE. The system generates feature vectors based on the training data representation of the dataset and updates the feature vectors with initial design characteristics of the given IC design. The system iteratively performs an input gradient search of the updated feature vectors to optimize an objective function of the design targets to identify locally optimal design parameters. The system identifies globally optimal design flow parameters for optimized design targets based on locally optimal design parameters.

Disclosed in the present invention are a knowledge-distillation-based dynamic fusion method, system and apparatus for missing multi-modal data. The method comprises: on the basis of a classification network, constructing a plurality of single-modal teacher models, and respectively preforming training on the classification network by means of each type of single-modal data to obtain corresponding single-modal teacher models; on the basis of a threshold network and a series of expert networks, constructing a multi-modal dynamic fusion network, wherein the threshold network is used for determining which expert networks are activated and outputting one one-hot vector, the length of the vector is the number of expert networks, the data used by each expert network is a subset of a plurality of modalities for feature fusion, and the multi-modal dynamic fusion network, on which training performed using data including complete modalities has been completed, is used as a student model; and using the teacher models to perform distillation training on the student model, and inputting actually acquired multi-modal data into the multi-modal dynamic fusion network to obtain a category prediction result. The present invention can increase the effective utilization rate of data and improve the prediction accuracy of multi-modal models.

A method for establishing a cross-issuer chargeback fraud detection system includes receiving a fraud analysis request for one or more chargebacks from a payment processor using an Application Programming Interface (API) over a computer network, extracting identifying information of transactions associated with the one or more chargebacks from the fraud analysis request, searching for a fraud analysis profile linked to the extracted identifying information in a profile database, determining whether the fraud analysis profile linked to the extracted identifying information exists in the profile database, upon determining that the fraud analysis profile linked to the extracted identifying information does not exist in the profile database, retrieving historical transaction data associated with the extracted identifying information from a historical transaction database, retrieving reported fraudulent activities from one or more financial institutions associated with the extracted identifying information, and aggregating the retrieved historical transaction data and reported fraudulent activities.

The invention provides a multi-modal large language model construction method for automatic accounting document auditing, and belongs to the technical field of large language models.The method includes the steps that table graph structure data are constructed, a graph convolutional network is input for node feature propagation, and a sequential dependency relationship is modeled in combination with a bidirectional long-short-term memory network; a cross-modal semantic alignment encoder is constructed to map a visual token sequence and a language token sequence to a unified semantic space, a conditional generative adversarial network is adopted to carry out data enhancement, a time sequence modeling framework of a dynamic graph neural network is constructed to process time-varying graph structure data, an active learning framework and a noise adaptation network are designed, and time-varying graph structure data processing is carried out. A knowledge distillation technology and a model optimization method are used, a multi-task uncertainty weighted loss balance algorithm is adopted for training to obtain a multi-modal large language model for accounting document automatic auditing, and the problem that in the prior art, it is difficult to accurately understand complex table structures and cross-modal semantic association is solved.

1. The name of the design product: graphical user interface for network usage management and monitoring of electronic equipment. 2. The use of the design product: for an electronic device. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best shows the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: display interface for network usage management and monitoring. 7. The human-computer interaction mode of the graphical user interface: design 1 front view is a statistical interface for network usage, sliding the screen upwards to enter the design 1 change state diagram; design 2 front view is a statistical interface for network usage, sliding the screen upwards to enter the design 2 change state diagram; design 3 front view is a management interface for network usage, sliding the screen upwards to enter the design 3 change state diagram; design 4 front view is a management interface for network usage, sliding the screen upwards to enter the design 4 change state diagram; design 5 front view is a management interface for network usage, sliding the screen upwards to enter the design 5 change state diagram; design 6 front view is a management interface for network usage, sliding the screen upwards to enter the design 6 change state diagram; design 7 front view is a statistical interface for network usage, sliding the screen upwards to enter the design 7 change state diagram; design 8 front view is a statistical interface for network usage, clicking the "management" button in the lower part of the interface to enter design 8 change state diagram 1, sliding the screen upwards to enter design 8 change state diagram 2; design 9 front view is a statistical interface for network usage, clicking the "management" button in the lower part of the interface to enter design 9 change state diagram 1, sliding the screen upwards to enter design 9 change state diagram 2. 8. Other circumstances that need to be explained: omit other views. The "X" in each view represents replaceable or changeable text, numbers or punctuation marks.

A machine learning-based proxy model may generate measurements of quality of user experience in a vehicle-based communication network in the absence of direct feedback from the users regarding the user experience. Once generated, the proxy model may be applied to observed operational parameters of the on-board network to quantify the user experience for any user in any given instance. User experience measurements (e.g., trends identified therein) may be utilized to identify and implement adjustments to hardware, firmware, software, and / or service procedures associated with implementation of the on-board network. These adjustments may be implemented between transits of the vehicle, or in some cases, during transit of the vehicle to improve the user experience over the duration of use of the vehicle-based communication network.

A Position Calculation Unit, e.g., a PPU for a wireless communication network is provided, wherein the position calculation unit comprises an input, e.g., comprising an interface, adapted for receiving information related to a dynamic cooperation cluster of access points (DCC devices, APs, TRPs), DCC, and adapted for receiving a channel estimation result related to a channel between devices of the DCC, such as APs, and a device to be located; and a calculator configured for determining a location of the device based on the information related to the DCC and the channel estimation result. The Position Calculation Unit is configured for providing information related to the location, e.g., for a location based service and / or for use by the network.

On-demand private network creation and management can include detecting that the managed device has entered into a defined private network area that defines an area in which the managed device should be connected to a private network. The private network can be defined by an anchor point and boundaries around the anchor point, the boundaries defining the defined private network area. Using a bootstrap account stored in a non-volatile memory of the managed device and a managed device profile associated with the managed device, the managed device can be authenticated. The managed device profile can define networks with which the managed device can communicate. Using a private network profile, a private network can be created. The private network profile can include data defining the anchor point and the boundaries around the anchor point. The managed device can be added to the private network to communicate with the private network.

The invention relates to the technical field of power transmission line monitoring, in particular to a power transmission line icing detection method, system and device based on deep transfer learning and a storage medium. According to the method, an insulator image data set containing five states of no icing, rime, mixed rime, glaze and snow coverage is constructed, a target detection model architecture comprising a feature extraction network and a prediction network is constructed, the feature extraction network adopts hierarchical feature learning to realize multi-scale feature extraction, and the prediction network adopts a task decoupling architecture to separate, classify, locate and predict; a transfer learning training strategy is implemented, a general target detection data set is used for learning general feature representation in the source domain pre-training stage, feature extraction network parameters are kept in the target domain fine tuning stage, a prediction network is initialized again, an icing data set is used for fine tuning training, and prediction capacity for icing recognition is established; and inputting a to-be-detected image into the trained model, and obtaining insulator position information and an icing type classification result.

The invention relates to a behavior-based control method of an autonomous underwater robot for comprehensive reinforcement learning. The behavior-based control method comprises the following steps: designing behaviors according to tasks; designing a control system based on behaviors, and solving the joint multi-objective function by using an interval planning algorithm to obtain an optimal action decision of the AUV; defining a state S, a reward function R and a reinforcement learning action A of the AUV, and establishing a simulation environment to collect training data; establishing a strategy network, and performing network training by using a DQN algorithm; integrating the network in a control system to solve dynamic behavior weight parameters for the joint multi-objective function; and data correction network parameters are recollected in the real environment, so that the performance of reinforcement learning in the real environment is improved. The method has strong environment interaction capability and learning capability, can improve the behavior performance of the AUV through an award and punishment mechanism learning experience strategy, and improves the performance of reinforcement learning implemented in simulation in a real environment through a secondary learning mode.

Systems and methods for enhancing image blocks of a frame of a video to be compressed are provided. The systems and methods enhance the image blocks to improve compression of the video to be compressed. In at least one embodiment, systems and methods are provided for using a learned prefiltering network, trained using a joint loss function, to enhance video content to improve compression.

Devices, networks, systems, methods, and processes for standardizing power usage measurement in various devices, components, etc. Measurement methods for power verification in AC or DC input power are often over simplified or done with a method that achieves inaccurate or highly suspect results. Different testing methods for the same device to be verified are often used, resulting in lack of consistency and any sense of accuracy and / or relevance. Part of this problem is the lack of unified electrical measuring and changes in operation based on network usage and ambient temperature. Thus, various embodiments described herein are directed to generating standardized power usage data and charts that can indicate a more accurate power usage level of an apparatus. This can allow for more effective network managing decisions and increase overall network sustainability.

The invention provides a network equipment waveform switching method and device, and relates to the technical field of industrial Internet of Things and the technical field of wireless communication network security, the method is applied to main equipment in a target network, and the method comprises the following steps: when it is detected that other equipment in other networks uses a specified waveform for communication, switching the waveform of the main equipment in the target network; screening out a target waveform which is not used by each other network from a waveform configuration library of the target network, wherein the similarity between the specified waveform and a current waveform adopted by the master device for communication is higher than a first set threshold value; and based on the target waveform, performing waveform synchronous switching with each associated device in the target network. According to the method, sensing-decision-switching closed-loop management of physical layer waveforms can be realized, the communication continuity is ensured, the anti-interference capability and safety of the network are remarkably improved, and the method is suitable for scenes with strict requirements on reliability, such as industrial Internet of Things and intelligent power grids.

A Holographic Transformer Network (HTN) system and method ingests and enriches semantic knowledge graph (KG) data using a holographic encoder and at least one non-GNN holographic transformer to produce graph node encodings in a node-count-mutable way. The produced node encodings can be used by a downstream network whose architecture is not tied to the static node defined by a particular vignette. The same network can be utilized for decision making even if the number of nodes in the graph (or entities in the simulation) increases.

Aspects of the present disclosure provide, in a system that uses multiple radio link types for different networks within the system, methods for selecting more than one radio link type for transmission and acknowledgement of a signal to overcome a problem of mismatch of RTT of signaling over the different radio link types. As a particular example, in an integrated system including both a terrestrial network (TN) portion and a non-terrestrial network (NTN) portion, after an original signal is transmitted over the NTN portion, acknowledgement of the original signal, and retransmissions as necessary, can be carried out over the NT portion.

Systems and methods for measurement gap signaling are described herein. A user equipment (UE) receives, from a network, a configuration for one or more measurement objects (MOs) at the UE and identifies any overlimit MOs (for which using per-frequency range (FR) measurement gaps would cause the UE to exceed a component carrier (CC) limitation of the UE) from among the one or more configured MOs. Upon identifying one or more such overlimit MOs, the UE sends the network a measurement gap instruction message configured to cause the network to use per-UE measurement gaps (rather than per-FR measurement gaps) corresponding to the overlimit MOs. An indication to use per-UE measurement gaps in the measurement gap instruction message may be made on a per-MO, per-CC, per-band, per FR, or per-band combination basis. In some cases, the measurement gap instruction message causes the network to use per-UE measurement gaps for all configured MOs.

Systems and methods related to distributed subsystems with embedded artificial intelligence (AI) compute in automotive systems are disclosed herein. A disclosed automotive computing architecture includes a network, a plurality of networked subsystems in operative communication using the network, and a set of AI accelerators in a one-to-one correspondence with the plurality of networked subsystems. The set of AI accelerators may conduct AI computations for their respective networked subsystems without using the network, reducing latency. The set of distributed AI accelerators may each be optimized for the specific workloads of their subsystems. By using distributed AI accelerators, each task can be handled by hardware optimized for its specific needs, resulting in higher efficiency, lower latency, and better power management. Furthermore, the distributed AI accelerators can provide greater scalability, redundancy, and fault tolerance, enabling better performance across diverse workloads.

Provided are an apparatus and a method for scheduling network resources. In response to a resource request for a resource consumer, the resource scheduler obtains resource prediction including the predicted network bandwidth and the predicted network usage pattern, and schedules bandwidths for the resource consumer based on resource requirement information, the resource prediction and resource availability. The network bandwidths for the resource consumer are allocated based on the predicted network bandwidth and the predicted network usage pattern, network bandwidths can be allocated based on demand and supply, and can thus be fully utilized, that is, network bandwidth utilizations at the endpoint and the levels of networks can be improved.

The invention relates to a message processing method and device for bandwidth guarantee speed limitation. The method comprises the following steps: identifying an IP address of a message to be processed; judging whether the IP address is matched with a pre-configured bandwidth guarantee user or not; if the IP address is matched with the bandwidth guarantee user, obtaining interface information corresponding to the message and bandwidth information on an interface; determining a bandwidth guarantee strategy based on the interface information and the bandwidth information; and processing the message data according to the bandwidth guarantee strategy. According to the message processing method and device for bandwidth guarantee speed limitation, occupation of network resources by bandwidth guarantee users can be controlled, and the network resources are reasonably distributed. A user is prevented from maliciously preempting bandwidth resources, and the network use environment is improved.

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.

Disclosed are implementations, including a method that includes monitoring dataflow streams in a network comprising multiple computing nodes, and determining network security characteristics for a dataflow stream, from the monitored dataflow streams, relating to security, authentication, and access events for accessing, via the dataflow stream, one or more of the multiple nodes. The method further includes determining potential violations by the dataflow stream of security policies defined for operation of the network, access functionality for the network, or identity attributes used by the network, based, at least in part, on the determined network security characteristics for the dataflow stream, and based on network-operation data comprising one or more of network security data, network identity data, and network access data. The network-operation data is stored in one or more data storage units in the network, and is configured to manage network access and operation for the multiple computing nodes.

This application proposes a base station dismantling and merging assessment method, apparatus, device, and storage medium, relating to the field of communication technology, for assessing base station dismantling and merging to ensure normal network usage experience for users after base station dismantling, merging, and upgrading. The method includes: the base station dismantling and merging assessment apparatus determining a target resource utilization rate. Further, the base station dismantling and merging assessment apparatus determines the bandwidth ratio of a first base station and the bandwidth ratio of a second base station; and based on the target resource utilization rate and the bandwidth ratio of the second base station, determines the load of a first site after the first base station is decommissioned; and based on the target resource utilization rate and the bandwidth ratio of the first base station, determines the load of a second site after the second base station is decommissioned. Further, if both the load of the first site and the load of the second site are greater than a preset site load, the base station dismantling and merging assessment apparatus determines that the first base station and the second base station are not suitable for dismantling and merging.

The present application relates to the technical field of pavement crack detection, and particularly relates to a lightweight pavement crack detection method, wherein a lightweight feature extraction module SandGlass and a coordinated attention mechanism are integrated into an encoding-decoding structure to construct a lightweight pixel-level crack detection network, a pavement image database is used to train the network model, so that the network model can realize the same detection effect as a larger network model under less computing power, the coordinated attention mechanism module suitable for mobile terminals is introduced to reduce the influence of noise and improve the accuracy of crack detection, and finally the encoding-decoding structure is improved to fuse feature maps of different levels, so that the final prediction result is closer to the actual pavement condition. Further, the improved method can be effectively applied to mobile devices to realize real-time and effective end-to-end detection.

A method, a network device, and a non-transitory computer-readable storage medium are described in relation to a multifaceted detection of fraudulent data usage service. The multifaceted detection of fraudulent data usage service may apply fraudulent detection to multiple facets of network usage including end device identifier analysis, end device registration analysis, traffic analysis, and end device examination analysis. The multifaceted detection of fraudulent data usage service may include weightings and scoring associated with the examinations.