59 results about "Network complexity" patented technology

The invention relates to the technical field of communication networks, in particular to an intention-driven satellite-ground convergence network on-demand arrangement system and method, and the method comprises an intention input layer which is used for receiving a multi-mode intention of a user; the intention analysis layer is used for analyzing the intention of the user to generate a recognizable network strategy; the arrangement control layer comprises a design state and an operation state; wherein the design state is used for dynamically generating a resource arrangement strategy based on an identifiable network strategy, and verifying the feasibility of the resource arrangement strategy in the digital twin network; the running state is used for generating an executable scheme based on the verified resource arrangement strategy; and the infrastructure layer comprises a satellite-ground unified atomic power abstraction module which is used for abstracting heterogeneous resources into standardized atomic power and executing an executable scheme. The scheme aims to provide a brand-new intention-driven satellite-ground fusion network arrangement architecture with dynamic generation, thorough decoupling and active prediction capabilities, so that the technical problem that complexity and dynamics of a 6G network cannot be handled at present is solved.

The application discloses an underwater target recognition method based on an improved YOLOv8 algorithm, which comprises the following steps: inputting an underwater image into an improved YOLOv8n model for underwater target detection, and obtaining an output underwater target recognition result. The method has the following advantages: DSConv is used in the convolution block of the P5 layer of the backbone network and the last layer of the neck network, which reduces the network complexity and improves the inference speed; the C2f_DiRMB module is used in the fourth C2f module of the backbone network, which introduces an inverted residual attention mechanism and a double-channel convolution, enhances the ability of the network to capture key global information, reduces the training parameters, and thus improves the understanding of complex scenes; finally, a small target detection head is added in the head network to improve the small target detection capability; and the underwater target recognition method improves the mAP@0.5%, mAP@0.5-0.95%, precision and recall by 0.5%, 0.8%, 0.5% and 1.0% respectively.

The invention discloses a near infrared spectrum reconstruction method based on stage perception mixed prior and a two-channel optical imaging system, and the method comprises the steps: constructing a deep expansion network model of stage perception mixed prior based on RGB guidance, and the network model comprises k cascade reconstruction stages, each reconstruction stage comprises a degradation perception residual gradient descent module and a near-end mapping module. According to the method, a degradation sensing residual error gradient descent module is introduced, the difference between a sensing matrix and an actual degradation process is effectively reduced through degradation learning, and the iteration process of a deep expansion network is divided into two stages of spectral space preliminary feature extraction and space detail deep extraction by applying a segmented optimization strategy; the network reconstruction precision is guaranteed, the optimization of the calculation efficiency is improved by adjusting the network complexity in stages, and the completeness and quality of the reconstructed image are guaranteed while the calculation overhead is reduced.

The invention discloses a water chilling unit small sample fault detection method and system based on transfer learning, and the method carries out the fault detection through an expansion causal convolution module, a dense neural network module and a classification layer which are connected in sequence. A sparse connection strategy is introduced into dense blocks of the fault detection model, and representative connection between far and near layers is only reserved in each dense block, so that the network complexity is reduced, the feature redundancy is reduced, and the feature multiplexing advantage is kept; meanwhile, the method utilizes a transfer learning strategy to transfer labeled data knowledge of a source domain to a target domain, and introduces a meta-learning thought in a fine tuning stage to carry out gradient updating. In addition, feature subsets with high discrimination ability are screened out from an original high-dimensional feature space in combination with importance scores and correlation analysis, so that the detection precision of model training is improved.

The invention discloses a communication network complexity evaluation and optimization method and device, equipment, a medium and a product. The method comprises the following steps: acquiring communication network complexity original information of each segmented network in an end-to-end communication network; the original information comprises evaluation data and weight of each preset first evaluation element and evaluation data of a preset second evaluation element; the first evaluation element is an evaluation element related to network complexity, and the second evaluation element is an evaluation element related to communication service volume; respectively calculating the network complexity of each segmented network according to the original information; and according to the segmented network weight and the network complexity of each segmented network in the end-to-end communication network, calculating the network complexity of the end-to-end communication network for optimizing the communication network. By adopting the method and the device, the cross-domain coordination, scheduling and optimization requirements of the end-to-end network are considered, the network complexity evaluation of the end-to-end communication network is realized, and the optimization of the communication network is facilitated.

The application discloses a billet detection method based on deep learning, and belongs to the technical field of billet detection, which is mainly used for the identification and positioning of billets in the process of discharging from a hot continuous rolling heating furnace. The multilayer feature extraction structure of the method is embedded with a CSA module, a SPPELAN network and an improved PANET network, the complex environment in which the billets are located is fully considered, end-to-end network construction from input of a detection picture to output of a prediction result is realized, and the problems of low precision and poor real-time performance of traditional methods are solved. Moreover, a residual network is used to extract image features, the network complexity and feature effectiveness are well balanced, and the model attention to the target and the prediction accuracy are improved. Meanwhile, the improved path aggregation network also makes the model pay more attention to billet features of different scales, and improves the detection precision. Therefore, the automation and intelligence degree of the method is high, and the industrial application prospect is good.

The invention relates to a nano tackifying fluid and supercritical CO2 fluid synergistic fracturing method. In the target stratum development area, nano tackifying fluid and supercritical CO2 fluid are adopted for collaborative fracturing, sand-carrying fluid and displacing fluid are combined to form a fracture network, and the corresponding relation between the construction parameter combination and the fracture flow conductivity and the corresponding relation between the construction parameter combination and the fracturing construction fluid amount are established; based on the corresponding relation, a multi-target optimization model with the fracture conductivity maximization and the fracturing construction liquid amount minimization as the target is constructed, and through population initialization, non-dominated sorting, crowding distance calculation, crossover variation selection and iterative updating, a construction parameter optimization result is output. The shale reservoir fracture flow conductivity and the fracture network complexity can be improved, the construction liquid amount is reduced, and the fracturing transformation effect and economical efficiency are improved.

This disclosure relates generally to image coding and particularly to methods and systems for neural image compression (NIC). The disclosed NIC decoder / encoder may include various neural network components that are configured to achieve a balance between network complexity and coding efficiency. Such a NIC decoder / encoder implementation particularly include a core decoder and a hyper decoder each including a neural network architecture adapted for achieving a lightweight decoder / encoder.

The invention provides a cross-network http calling method and device, electronic equipment and a readable storage medium, and the method comprises the steps: receiving an access request which is sent by a service requester and aims at a target intranet service, and the access request comprises an access domain name; the access domain name is a domain name created based on the IP address of the target intranet service, the target intranet port number and a preset domain name generation rule; extracting an IP address field and a port number field in the access domain name based on a pre-configured domain name matching rule; proxy the access request to the target intranet service based on the extracted IP address field and port number field, and obtaining a response result; and returning a response result to the service requester. According to the invention, for any newly-added intranet service, as long as the domain name of the access request of the intranet service accords with the domain name generation rule, automatic access can be realized through a dynamic proxy method without modifying the configuration of a reverse proxy server or restarting the service. The cross-network complexity is reduced, and the requirements of automation and rapid iteration are met.

The invention provides a communication method, terminal equipment and a core network element. The method comprises the following steps: a first terminal device sends first information to a first core network element through a user plane message; wherein the first information is used for indicating the information of the second terminal equipment. Under the condition that the first core network element collects the information of the second terminal device, the network side can obtain the information of the second terminal device so as to perceive the second terminal device. In this case, the first terminal device can obtain the information of the second terminal device without a private interface, thereby realizing unbinding of the first terminal device and the second terminal device. For a consumer, the consumer can purchase the first terminal device of any manufacturer, so that the network side can sense the information of the second terminal device. And for a manufacturer or a supplier of the second terminal equipment, the manufacturer or the supplier does not need to deploy the server, so that the cost and the network complexity are reduced.

The invention discloses a method-level test case sorting method based on change measurement and defect severity prediction, which comprises the following steps of: constructing an abstract syntax tree of each method, and analyzing differences in different software versions; the method comprises the following steps: abstracting a calling relation of a software runtime method into a software network MSN, extracting a network complexity index and a source code level measurement index of each method, constructing a defect severity prediction data set by combining the defect severity in the method, and constructing a defect severity prediction model by using a machine learning classifier to predict the defect severity in the method; and evaluating the test importance of the method based on the change measurement of the method and the predicted value of the defect severity, evaluating the priority of the test cases in combination with the coverage information of the test cases, and executing the test cases according to the priority sequence. According to the method, the change size of the method and the severity of the defect are considered, the method is of great significance in improving the regression test efficiency and improving the software quality, and technical support is provided for developing high-credibility software.

The present application belongs to the technical field of image processing, and particularly relates to a non-Lambertian surface photometric stereo model and method based on three-dimensional convolution. The present application discloses a non-Lambertian surface photometric stereo model based on three-dimensional convolution, which comprises an information fusion layer, an inter-frame feature extraction layer, a spatial feature extraction layer, a maximum pooling layer and a regression layer. The information fusion layer is used for fusing each image and corresponding light source information, so as to ensure one-to-one correspondence between the image and the light source in subsequent processing. The inter-frame feature extraction layer is used for extracting inter-frame information, obtaining information between input image frames, and estimating the normal map. The spatial feature extraction layer extracts structural information inside a single image for normal map recovery. The maximum pooling layer is used for dimension reduction, removal of redundant information, compression of features, simplification of network complexity, reduction of calculation amount and reduction of memory consumption.

The application discloses a lightweight three-dimensional model classification system based on multi-view grouping. A view sampling module projects a three-dimensional model into N views and sequentially renders N two-dimensional depth maps. A view grouping module divides the two-dimensional depth maps into multiple groups according to the geometric semantics of the three-dimensional model. A feature extraction module extracts features from each group of two-dimensional depth maps and outputs multiple feature maps. A feature fusion module inputs the multiple feature maps into a MobileViT Block module for further analysis to obtain a final prediction result. The two-dimensional depth maps are divided into multiple groups through good geometric semantics, and then multiple groups of views use an improved MobileNet V2 network to extract effective features. Finally, multi-view feature fusion obtains the feature recognition of the three-dimensional model. The network reduces the network complexity while ensuring the effectiveness of three-dimensional model classification.

This invention discloses a fault location method and related equipment for optical networks. It reduces the network complexity of fault location and improves the accuracy and efficiency of fault location in optical networks. The method shown in this invention includes: a network management device acquiring a first sampling set from a first optical network device, the first sampling set including multiple optical powers obtained by the first optical network device sequentially sampling a first optical signal multiple times during a first fault location time period, wherein at least one optical power included in the first sampling set is less than or equal to an optical power threshold; the network management device determining the fault type of the optical network based on the changing trend of the multiple optical powers.

The application discloses a fruit recognition and positioning method for crop fruit picking. The application introduces a Ghostnet lightweight module to obtain a GN-YOLOv5s model, replaces original convolution layers with depth separable convolution to extract features and reduce network calculation amount; secondly, to further reduce the model size, a regularization term about a scaling coefficient is introduced in the BN layer for sparse training, channels with a scaling factor gamma of 0-0.005 are screened out, pruning processing is performed to obtain a GS-YOLOv5s model; finally, to make the pruned model maintain high detection accuracy, a knowledge distillation method is adopted, a teacher network is used to assist the fine-tuning of the pruned model to obtain a PD-yolov5s, the hardware cost is reduced, and the model is convenient to deploy on a low-computing platform. The application can reduce network complexity, improve detection efficiency, make it be deployed on an embedded platform with small computing power, and obtain positioning information of dense crop fruits, which lays a foundation for subsequent action planning of a picking robot.

The invention discloses a hyperspectral image compression network and compression method based on multi-scale spectrum and spatial feature enhancement, and mainly solves the problems of insufficient hyperspectral image spectrum modeling, insufficient spatial feature extraction and high network complexity in the prior art. The network comprises a main encoder, a main decoder, a super-prior encoder, a super-prior decoder and an entropy model. The main encoder comprises a spectral attention gating data unit, a convolution unit and a multi-scale spatial adaptive feature attention enhancement unit, and is used for converting an input image into potential representation and removing spatial and spectral redundancy; the main decoder and the main encoder are symmetrical in structure; the super-prior encoder comprises a convolution layer and an activation layer and is used for extracting auxiliary information from the output of the main encoder; the super-prior decoder and the super-prior encoder are symmetrical in structure; the entropy model is Gaussian distribution based on output parameters of a super-prior decoder. After the network is trained, lossy compression of a hyperspectral image can be realized. The method reduces the network complexity and spectral distortion, improves the reconstruction quality of complex ground feature details, and is suitable for earth observation, meteorological monitoring and the like.

The application provides a feeding network, an antenna module and an apparatus. In the feeding network, the feeding network comprises M radio frequency interfaces, N antenna interfaces, at least M first distribution units, N second distribution units and Mx(N-1) phase shift units, M is less than or equal to N, and M and N are integers greater than 1; each radio frequency interface is configured to receive a first radio frequency signal; the first distribution unit is configured to process the first radio frequency signal into N second radio frequency signals; an input end of each second distribution unit is connected with at least one first distribution unit and / or at least one phase shift unit, and an output end of the second distribution unit is connected with the antenna interface; each phase shift unit is connected between the first distribution unit and the second distribution unit, and each phase shift unit is configured to adjust the phase of the received second radio frequency signal. In this way, the network complexity of the feeding network is low, the insertion loss is small, and the isolation is good.

This invention relates to a low-light adjustable brightness enhancement method guided by a reference brightness index, belonging to the field of computer vision image technology. The first step involves extracting features from the input low-light image and the reference brightness index using methods such as convolution, downsampling, and global average pooling to obtain a feature vector. The second step decomposes the feature vector into brightness and content feature components, combining the content component of the low-light image with the brightness component of the reference brightness index to achieve feature recombination. The third step reconstructs the recombinated feature vector using methods such as transposed convolution, upsampling, and skip connections. This invention is rationally designed, fully considering the different lighting needs of various application scenarios or users. It efficiently utilizes and preserves the brightness and content information of the image. Furthermore, the network complexity is low, achieving good brightness enhancement while maintaining a fast running speed, resulting in good overall performance in adjustable brightness enhancement of low-light images.

The application discloses a large-scale MIMO downlink CSI feedback method based on deep learning enhancement, modifies an encoder network, a decoder network and feedback content on the basis of an existing self-encoding network CsiNet, enhances the feature extraction capability of a CSI matrix, reduces network complexity, and makes the input of a deep learning network and the CSI matrix be in the same order of magnitude. A puzzle solving training strategy is added to balance the relationship between compression tasks and identification tasks in deep learning, retains the integrity of physical information of the CSI matrix, does not lose the distinguishability, and enhances the downlink CSI feedback performance.

The embodiment of the invention provides a social network feature-based team communication complexity analysis method and system, and the method comprises the steps: constructing a command and control social network model, carrying out the fuzzy evaluation of a task unit, determining the overall fuzziness of a task, carrying out the multi-dimensional evaluation of a communication medium, determining a comprehensive value of the richness of the medium, and carrying out the analysis of the richness of the medium. Constructing a task fuzziness-communication medium matching matrix, coupling the task overall fuzziness with a medium richness comprehensive value, determining a medium communication efficiency parameter, and performing complexity analysis on a command and control social network model according to the medium communication efficiency parameter to obtain a command and control social network model; the average path length complexity feature, the network diameter complexity feature and the network density complexity feature of the network are obtained, weighted optimization is carried out on the network edge according to the network complexity feature, an optimized command and control social network model is obtained, and the efficiency of team communication and task execution can be improved.

The application discloses an ultrasonic video recognition method and system based on diffusion attention. The method comprises the following steps: acquiring an ultrasonic video; inputting the ultrasonic video into a trained recognition model to obtain a classification prediction result; wherein the recognition model uses multiple stages to obtain the overall representation of the ultrasonic video, each stage comprises a space-time block representation module, a diffusion window attention module and a space-time block merging module, the space-time block representation module is used for space-time division of the input ultrasonic video to obtain a discrete space-time block set; the diffusion window attention module establishes the distance dependence relationship between the space-time blocks by alternately using a fixed window attention mechanism and a diffusion window attention mechanism; and the space-time block merging module is used for down-sampling the features output by the diffusion window attention module. The application designs a diffusion window attention mechanism, which can enhance the perception field of the features, thereby quickly obtaining the overall information of the video without increasing the network complexity.

The application relates to an image enhancement method, a vehicle snapshot method, equipment and a medium, and belongs to the technical field of image processing. The method comprises the following steps: performing preprocessing on original image data collected by an image collection component; inputting the preprocessed image data into an image enhancement model to obtain image data after brightness enhancement; the calculation efficiency of the image enhancement network can be improved by performing down-sampling processing on the image input into the student network. The image input into the teacher network is not subjected to down-sampling processing, the performance of the teacher network in image enhancement can be ensured, and the calculation speed of the student network can also be ensured, and the network complexity of the student network is lower than that of the teacher network. Then, the teacher network distills the learned knowledge to the student network, so that the student network can ensure the image enhancement performance while ensuring the calculation speed. Sharing the intermediate feature map output by the teacher network to the student network can also improve the training efficiency of the student network.

The application discloses a human behavior recognition method based on an improved deep residual network. The method comprises a training stage and a testing stage. In the training stage, an image dataset is acquired by using a camera, original frames of a training video are extracted by using a sparse sampling strategy of segmented sampling, and the extracted original frames are sent to an improved deep residual network with a channel attention mechanism for training. In the testing stage, original frames of a testing video are extracted, the original frames are sent to the improved deep residual network model obtained through training, and the final behavior category is determined by using a softmax classifier. According to the method, important features can be enhanced and unimportant features can be inhibited according to the importance of feature channels, so that the feature extraction capability of the model for input data is improved. The network has high running speed, high behavior recognition accuracy and low network complexity, and can effectively extract features and has good performance in some complex actions and difficult-to-recognize actions.

The application provides a stereoscopic well pattern space stress field active utilization method and device, including obtaining a plurality of fracturing schemes of a target well pattern; performing fracturing simulation on the target well pattern according to the fracturing schemes to determine a fracturing structure of the target well pattern, wherein the fracturing structure represents the number and shape of cracks in the target well pattern; determining a stress field active utilization coefficient and a fracture network complexity coefficient of the fracturing scheme according to the fracturing structure, wherein the stress field active utilization coefficient represents the stress field active utilization effect in the fracturing simulation process, and the fracture network complexity coefficient represents the proportion of the crack area in the fracturing simulation process; and selecting an optimal fracturing scheme according to the stress field active utilization coefficient and the fracture network complexity coefficient to fracture the target well pattern. Through the above method, the most sufficient fracturing scheme using the space stress field can be determined, and the optimal fracturing scheme can be selected through the product operation to guide the fracturing of the real target well pattern.

The application discloses a general enhancement method for target character recognition in a motion scene and a related device, uses a network structure construction strategy of a double branch, carries out data fusion and parameter exchange through an implicit text statistical branch and an explicit text recognition branch, can control the model size without increasing the model complexity, and reduces unnecessary parameters of the network. Meanwhile, a basic backbone network is provided for subsequent downstream tasks, and a solution can be provided for text analysis in more complex scenes. The offline learning method used in the application can reduce the cost when iterating and strengthening the model. With the increase of data diversity, the model can dynamically adjust the parameters each time, so that the iteration process can adaptively extract and update the parameters of the data, can improve the convergence speed of the iteration process while ensuring the performance of the model without increasing the network complexity.

The invention discloses a lightweight remote sensing image change detection method used under spatial misalignment. The method comprises the following steps of: firstly, extracting multi-scale features used for registration and change detection by utilizing a MobileNet V3 Marge; secondly, matching of semi-dense feature points is achieved through a space consistency module, a cross-scale space transformation model is established, and feature maps of different scales are aligned with one another; secondly, enhancing the spatial-temporal heterogeneity of the dual-time-phase features through a spatial-temporal difference collaboration module according to different-scale feature maps; and finally, fusing the multi-scale difference features to generate a change detection result. The SVCD data set, the SYSU-CD data set and the SECOND data set are selected for testing, and compared with a current mainstream change detection network. The result shows that the method can effectively construct the spatial transformation relation between the images to be registered, is obviously superior to other methods in the aspects of quantitative analysis and qualitative analysis, and has a certain advantage in the aspect of network complexity.

The application discloses a kind of based on KAN network's power amplifier linearization method and digital pre-distortion system, belong to wireless communication technical field, this method in digital pre-distortion processing process, introduced the Kolmogorov-Arnold Networks (KAN), constructs real time delay KAN digital pre-distortion network and real time delay KAN digital pre-distortion network;For real time delay KAN digital pre-distortion network, the input process of this network considers current time and previous time input signal, can correspond to the memory of power amplifier compensation;For vector decomposition time delay KAN digital pre-distortion network, on the basis of real time delay KAN digital pre-distortion network, further introduces phase recovery layer and fully connected layer, in the case where similar performance with previous KAN model is maintained, network complexity can also be simplified again;KAN digital pre-distortion method used in the application compared with original neural network-based digital pre-distortion method, use less network parameter, realize higher linearization capacity.

Embodiments of the present invention relate to the field of communications technology and disclose a method, apparatus, and computing device for resolving a PGW gateway based on location. The method comprises: receiving an attachment request from a user that carries the user's real-time TAC information; expanding the APN including the TAC information based on the real-time TAC information to construct a new FQDN; initiating an APN query to the DNS, and receiving a resolution result based on the new FQDN returned by the DNS to obtain PGW‑C information. Through the above-mentioned method, embodiments of the present invention can accurately access the same service area using 5G networks and 4G networks, realize 4G and 5G collaborative networking, reduce routing detours, latency, and interconnection bandwidth, and reduce network complexity.

The invention discloses a graph structure perception channel parameter frequency domain extrapolation method, which comprises the following steps of: constructing a graph structure perception attention mechanism, constructing a channel parameter extrapolation network comprising the graph structure perception attention mechanism, and utilizing a channel parameter sequence data set comprising known frequency points and corresponding target frequency points to carry out frequency domain extrapolation on the known frequency points and the corresponding target frequency points. A channel parameter extrapolation network is trained, a channel parameter sequence of a known frequency point is input into the trained network, the network firstly extracts local features through a multi-scale convolution module, then feature coding is performed through an encoder integrated with a graph structure perception attention mechanism, and the feature coding is performed through a multi-scale convolution module. And finally, the decoder outputs a channel parameter prediction sequence of the target frequency point, and the prediction precision of the channel parameters in the frequency extrapolation process is effectively improved through joint modeling of the multipath structure information. Experimental results show that under the condition of the same training data scale and network complexity, the method is superior to an existing method in a channel parameter extrapolation task.

The application discloses a near-infrared spectrum reconstruction method based on stage-aware hybrid prior and a double-channel optical imaging system, comprising a deep unfolding network model based on stage-aware hybrid prior guided by RGB, wherein the network model comprises k cascaded reconstruction stages, and each reconstruction stage comprises a degradation-aware residual gradient descent module and a proximal mapping module. The degradation-aware residual gradient descent module is introduced, the gap between the perception matrix and the actual degradation process is effectively reduced through degradation learning, the iterative process of the deep unfolding network is divided into two stages, i.e., spectral space preliminary feature extraction and spatial detail deep extraction, by using the segmented optimization strategy, the network reconstruction accuracy is ensured, the network complexity is adjusted in stages to improve the optimization of the calculation efficiency, and the integrity and quality of the reconstructed image are ensured while the calculation cost is reduced.