25 results about "Network formation" patented technology

This invention discloses a multi-agent collaborative decision-making method for ramp merging based on spatiotemporal interaction capture and action priority, belonging to the field of intelligent transportation technology. The method includes: acquiring a sequence of observation information from multiple agents and obtaining a spatiotemporal interaction code through temporal encoding and self-attention interaction encoding; gating the spatiotemporal interaction code based on ramp merging features (TTMP); inputting the enhanced code into a policy priority ranking network, sampling the action generation order using Plackett-Luce, and then reordering the enhanced code, before inputting it into a decoding policy network with cross-attention to form a spatiotemporal interactive Plackett-Luce multi-agent reinforcement learning model. The model then autoregressively generates actions for each agent according to the reordered order and integrates them to form a joint action, generating vehicle control commands to control vehicles to perform collaborative driving in the ramp merging area. This invention can dynamically model the multi-vehicle interaction relationship and the action priority dependency between individual decisions in a strong interaction scenario of ramp merging, thereby improving the stability of collaborative decision-making and traffic efficiency.

The application discloses a kind of asphalt pavement technical literature mining methods based on TongYiQianWan semantic graph, comprising: obtaining road engineering-computer vision cross field academic literature data, carries out multidimensional preprocessing and forms standardized data set;Improved double-tower semantic coding network is constructed, the uniform mapping of keyword and title semantic features is realized;Optimized GraphSAGE spatial feature extraction network is constructed;CNN-LSTM hybrid architecture is used to construct timing feature extraction network, and form a multidimensional fusion feature representation system;Weighted random forest classifier with class weight balance strategy is introduced;Key word co-occurrence prediction and technology trend quantitative prediction system is established, finally, multi-module collaborative Qwen-SGCL intelligent model is obtained;The training, verification and comprehensive performance evaluation of the model are completed.The application provides an efficient intelligent tool for intelligent mining and technology trend quantitative analysis of literature in the cross field of road engineering and computer vision.

This invention belongs to the field of computer application technology. It discloses an information aggregation and retrieval system and method based on artificial intelligence, comprising: receiving user task objectives; combining associated resource sets and search preferences; calling a semantic model to generate semantic anchors; thereby generating a university-specific contextual blueprint to form a standardized information foundation within the university; parallel scheduling of various information interfaces within the university according to permissions; expanding query intents; filtering and sorting results to form a blueprint-bound retrieval result set; performing university-specific scenario analysis; generating dynamic aggregation summaries and difference comparison tables; grouping according to preset logic and performing visualization processing to form a structured presentation view; collecting user interaction data in the structured presentation view to generate a university user feedback dataset; and optimizing the university-specific contextual blueprint and university-specific knowledge unit network to form a closed-loop link.

This invention relates to a battery pack balancing control method and system. The method includes: Step S1: treating the battery pack as an intelligent agent network and converting the battery pack balancing problem into a Markov game that can be handled by the DRL algorithm; Step S2: generating online expert data using the FCS-MPC algorithm; Step S3: training the intelligent agent network and a hybrid network based on different intelligent agent networks using the FCS-MPC-QMIX algorithm, and dynamically fusing the expert data into the objective functions of the intelligent agent network and the hybrid network during training to accelerate network convergence; Step S4: using the trained intelligent agent network and the hybrid network to achieve battery pack balancing control. This invention can provide balancing control for distributed battery energy storage systems.

A macro-scale outcrop rock fracture network structure quantitative characterization method and system, the characterization method comprising: arranging a physical scale at the rock slope outcrop to be measured, and shooting a rock slope outcrop image; inputting the image into a pre-trained semantic segmentation model, segmenting the fracture pixel region in the image, and outputting a binary segmentation mask image; taking the physical scale as a reference, calibrating the spatial scale of the rock slope outcrop image to be measured transmitted to the data processing terminal, and calculating the spatial resolution of the image; using the binary segmentation mask image and the spatial resolution to respectively extract statistical parameters of each fracture, extract fractal parameters of the fracture network, and extract topological parameters of the fracture network; integrating the extracted statistical parameters, fractal parameters and topological parameters, introducing a SHAP attribution model, and forming a digital file of the rock slope outcrop fracture network structure, and quantifying the importance ranking and correlation of each parameter in the fracture network formation process.

The application relates to the technical field of intelligent vehicle control, and discloses an automobile active suspension control method based on reinforcement learning and diffusion strategy, which comprises the following steps: performing asymmetric random mask processing on an input suspension state vector and a road elevation observation vector respectively, projecting the masked inputs to a unified latent space, and forming a joint representation based on a policy network; based on the joint representation, performing reverse denoising by using DDIM to generate a diffusion trajectory, and sampling multiple candidate actions in the later stage of the diffusion trajectory; conservatively evaluating the candidate actions by using an integrated value network, and obtaining a final control instruction by weighted fusion through softmax; in the training process, an experience replay buffer and an expert buffer are maintained, an end-to-end online training is performed by combining reinforcement learning loss, diffusion loss and reconstruction loss. The application can stably and efficiently train the diffusion control strategy, and significantly improves the adaptive control capability and ride comfort of the active suspension under complex road conditions.

This application relates to the field of communication technology, specifically providing a device networking method applied to a first device. The device networking method includes: upon discovering a second device to be networked based on a distributed soft bus, obtaining the device information of the second device; obtaining a preset identification code, and generating a first hash value based on the preset identification code and the device information; initiating network formation to the second device, so that the second device generates a second hash value based on its device information and the preset identification code; obtaining the second hash value sent by the second device, and determining whether the first hash value and the second hash value are the same; and confirming successful network formation when the first hash value and the second hash value are the same. This method addresses the difficulty of networking screenless devices, thereby improving the applicability of device networking.

The methods and apparatus disclosed herein provide a means of forming ad hoc networks based on the exchange of discovery burst signaling at the hardware level, according to deterministic hardware timing. Among several advantages, the use of deterministic hardware timing provides a basis for accurate, high-resolution estimation of the propagation delay between the corresponding nodes exchanging the discovery burst signaling. This accurate determination of the propagation delay at high resolution, in turn, provides a precise estimate of the ranging between the corresponding nodes, which allows for synchronization of time division multiple access (TDMA) transmissions between the nodes.

This invention proposes a group behavior analysis method based on scene features and location distance information, mainly involving the extraction and inference of contextual features through deep learning for individual and group behavior recognition. This method proposes a contextual feature extraction strategy that focuses on both local and global information, inferring interaction information through graph convolutional networks, and incorporating a self-attention graph pooling network to improve the accuracy of behavior recognition. First, a dual-stream feature extraction network is used to extract individual features. Then, a novel contextual feature extraction strategy is proposed, modeling individual location distance information to enrich individual features, and extracting global features from RGB frames as scene features. Next, the interaction information between individuals and the scene is inferred in a graph convolutional network, and group features are formed through a self-attention graph pooling network to obtain the behavior recognition result. This invention fully considers the contextual features of groups, solving the problem of insufficient utilization of contextual features in behavior recognition.

A system is provided for wireless online processing using a peer to peer network. In particular, the system may comprise a plurality of wireless computing devices in nearby proximity to one another that may form the peer to peer (“P2P”) network through a shared wireless communication channel. The system may identify the network connection strengths of each of the plurality of wireless computing devices and subsequently designate one or more devices as the hubs of the P2P network. Each of the wireless computing devices may have one or more online processes to be completed through the network connections formed by the P2P network. The processes may be propagated to the devices within the P2P network, where the data used to complete the processes may be encrypted within the memory or storage devices of each of the computing devices.

The application discloses a kind of high-efficiency differentiable neural architecture search methods based on topological structure optimization, comprising the following steps: according to computer vision task classification form, determine model structure and search network, form the computational graph of searchable structure; The architecture parameters of computational graph are determined by structure parameters and network parameters;Iterative optimization is carried out to the topological structure of computational graph, redundant structure is eliminated, and structure parameters are optimized;Carry out convolution operation;Optimize network parameters by convolution kernel reparameterization;And by convolution kernel standardization, decouple network parameters and structure parameters;Gradient descent algorithm is obtained after the optimized computational graph runs, and the optimal architecture parameter is determined;Train model structure, complete computer vision task classification.This method simplifies the network topological structure of differentiable neural architecture search, and sets the optimization algorithm of simplified structure targetedly;Help to complete network light weight and neural architecture search in complex visual task application.

This invention provides an offline community detection method for software ecosystems based on co-evolutionary optimization. Software ecosystem networks are often dynamic, forming dynamic networks. Based on the network formation mechanism, dynamic networks can be divided into offline and online networks. The goal of dynamic network community detection in software ecosystems is to efficiently reveal the community structure and evolutionary patterns of the system, contributing to understanding individual interaction behavior and promoting the healthy and sustainable development of software ecosystems. This invention segments the dynamic network into several continuous multi-layer networks based on the similarity of the network at different time periods. It considers both the saliency of the intra-layer network community structure and the similarity of the inter-layer network community division. Nine offline software ecosystem networks with different characteristics are constructed using data crawled from GitHub. Comparative experimental results show that the proposed offline community detection method for software ecosystems is superior.

A unified content delivery network system (UCDN) system formed by one or more networks of interoperable peer-to-peer networks. A hierarchical hybrid adaptive secure peer-assisted network system (referred to as SPAN-AI) using a hierarchical AI-driven approach under a unified secure content addressable architecture, the system is based on five key SPAN-AI subsystems: unified naming; unified discovery; hybrid adaptive routing; scalable publish subscribe; and embedded security; all five key SPAN-AI subsystems are securely integrated and jointly optimized via a hierarchical pluggable AI framework with associated simulation, training, and development pipelines embedded in AI agents with varying degrees of awareness and optimization capabilities at the peer-to-peer, edge, core, or other network levels (hierarchy).

The application provides a kind of ultrafine tailings cemented filling material slurry flocculation network formation time test method, and relates to the technical field of mine filling mining.The application prepares ultrafine tailings cemented filling material slurry and pure ultrafine tailings slurry body, uses dynamic rheometer to carry out strain amplitude test of fixed frequency, obtains the complement of linear viscoelastic region of two kinds of slurry body;Using dynamic rheometer, the frequency scanning test of fixed strain is carried out on the ultrafine tailings cemented filling material slurry, and the equilibrium frequency is obtained;Pre-shearing is carried out on the ultrafine tailings cemented filling material slurry, to ensure that all filling material slurries are in the same repeatable reference state;After the pre-shearing process, the time scanning test of fixed strain and frequency is directly carried out, to determine the flocculation network formation time of the ultrafine tailings cemented filling material slurry.The application helps to deeply understand the flocculation and sedimentation process of ultrafine tailings and the fluidity of ultrafine tailings cemented filling material slurry, so as to optimize the proportioning, and finally improve the utilization rate of ultrafine tailings.

This invention relates to the field of optical module communication technology and discloses an online dynamic adaptive compensation method for optical module performance degradation. It solves the technical problems of insufficient trend prediction capability, lack of adaptive dynamic adjustment capability, data dispersion, and lack of global coordination in existing optical module performance degradation monitoring and compensation methods. This invention acquires and preprocesses multi-source heterogeneous parameters, extracts core degradation features using a self-supervised model, and then uses a degradation trend prediction network to obtain core performance prediction values. This effectively captures the mutual influence between multiple processes and the evolution law of parameters, significantly improving the accuracy of performance degradation trend prediction. Furthermore, this invention automatically calculates the optimal compensation factor vector through a compensation decision network and uses proportional-integral-differential calculations to precisely adjust the production equipment. It can dynamically adjust the compensation amount according to the actual degradation state, and collects the actual values ​​and improvement rates after compensation to update each network, forming a closed-loop adaptive optimization.

The application provides a hierarchical lightweight point cloud semantic segmentation method and system fusing geometric residual, and the method comprises the following steps: selecting a point cloud dataset, preprocessing the point cloud dataset to obtain a point cloud training sample set and a test sample set; inputting the training sample set into a kernel point convolution network to form feature representation data with geometric perception ability; inputting the feature representation data into an encoder layer, explicitly modeling hierarchical context information from local details to global semantics through a parallel multi-branch structure and an adaptive fusion mechanism; connecting the context information and the encoder layer output information in residual connection to output point cloud semantic geometric feature information; inputting the point cloud semantic geometric feature information into a decoder layer to output a semantic prediction result, inputting the semantic prediction result into a point cloud test sample set to be segmented, automatically segmenting the test data and evaluating the precision. The application realizes high-precision automatic semantic segmentation of indoor scene three-dimensional point cloud data.

This invention discloses a data acquisition method, system, and device based on a multi-functional energy meter, relating to the field of data acquisition technology. The method includes: a concentrator sending a predetermined acquisition plan to a central coordinator via Ethernet communication; deploying edge stations for the multi-functional energy meter; after completing network formation with the central coordinator, the edge stations, according to the acquisition task configuration parameters, invoke an autonomous acquisition mechanism to perform acquisition execution at the edge application layer of the edge station, obtaining edge acquisition data; Ethernet communication and a high-speed power line communication network form a data transmission channel; the edge stations upload the edge acquisition data to the concentrator through the data transmission channel. This invention solves the technical problems of low communication efficiency, poor real-time performance, and excessive network load caused by traditional energy meter data acquisition relying on concentrator polling, achieving efficient and real-time data acquisition using an edge station autonomous acquisition mechanism, and reducing the burden on the concentrator and communication network.

This application provides a method and apparatus for automatic network formation of a set of routers, relating to the field of communication technology, to solve the problem that routers cannot automatically access the network in scenarios where a set of routers is connected to an existing router for network formation. The method includes: a first router sending a first encryption key to a master router, wherein the first router is a router in a first set of routers that has successfully accessed the local area network, and multiple routers in the first set of routers are configured with the same first encryption key, which is used by the master router to verify the identity of other routers in the first set of routers.

The application discloses a kind of based on artificial intelligence's cross-basin water diversion engineering optimization scheduling method, belong to cross-basin water diversion optimization technical field.The problems that the traditional cross-basin water diversion engineering optimization scheduling method in prior art is difficult to generate optimal scheduling plan due to easy strategy deviation;The application collects the storage capacity, flow, operation constraint and historical scheduling record of each node of test area reservoir, forms global dynamic embedding, and constructs reservoir node and water flow pipeline into graph structure, generates global embedding matrix as state input, trains basic global strategy network, forms global water diversion strategy network, divides global water diversion strategy network into macroscopic layer and microscopic layer, jointly trains by sharing global embedding information, forms layered water diversion strategy, converts global multi-step return into short-term and medium-term weighted return, generates scheduling optimization strategy.The application improves the global optimization and fine control of cross-reservoir water diversion, and can be applied to cross-basin water diversion planning.

The invention provides a peer-to-peer (P2P) network networking method, electronic equipment and a system. The method is applied to electronic equipment such as a mobile phone, a tablet personal computer and a personal computer. By implementing the method, after the pre-connection strategy is received, the electronic equipment can identify whether the target equipment in the pre-connection strategy comprises the first type of equipment or not. When the first type of equipment is included and the first type of equipment is online, the electronic equipment establishes P2P connection with the first type of equipment, and establishes P2P connection with other target equipment after establishing P2P connection with the first type of equipment; when the target equipment does not comprise the first type of equipment, the electronic equipment waits for a period of time and then establishes P2P connection with other types of target equipment in the pre-connection strategy, so that the P2P connection conflict problem between the equipment in the P2P networking process is avoided, and the benefit maximization of P2P pre-connection is realized.

The application relates to a method for operating a power converter (10) for exchanging electrical power (PDC, PAC) between a DC unit (11) and an AC network (13). The DC unit (11) is connected to a DC terminal (12) of the power converter (10) and exchanges DC power (PDC) with the power converter (10) depending on a DC voltage (UDC) at the DC terminal (12). The AC network (13) is connected to an AC terminal (14) of the power converter (10) and exchanges AC power (PAC) with the power converter (10) depending on a voltage waveform deviation between an AC voltage waveform (UAC) generated by a clocked bridge circuit (15) of the power converter (10) and a network voltage waveform (Ugrid) across the AC terminal (14).The power converter (10) uses a network-shaping AC control (20) to adjust the AC voltage profile (UAC) as a function of an AC power setpoint (PAC,set) and varies the AC power (PAC) in response to network events with an adjustable power response. The power response comprises a dynamic AC power deviation between the AC power (PAC) and a power setpoint. The method is characterized in that the induced power response to a network event is adjusted using an asymmetry characteristic (50, 51, 52, 53).The asymmetry characteristic (50, 51, 52, 53) specifies different gains of a parameter (p) of the AC control (20) and / or a DC controller (30) depending on the sign of a deviation (p-plim) of the parameter (p) from a parameter limit value (plim), wherein the parameter (p) in particular includes a DC voltage difference (ΔUDC) between the DC voltage (UDC) and a DC setpoint voltage (UDC,set) and / or an AC power difference (ΔPAC) between the AC power (PAC) and the AC power setpoint (PAC,set). The application further relates to a power converter and a power supply system.

This invention relates to the field of industrial automation control technology, specifically a fast ring network redundancy system for medium and large-sized PLCs based on optimized RSTP and its implementation method. The system includes a PLC master station, multiple remote I / O stations, and a host computer / engineering station. The PLC master station integrates a central processing unit, an embedded network switching chip, and a network management module, forming a tightly coupled collaborative control system. The network management module has built-in relevant functional units and a protocol engine to achieve parameter optimization, status monitoring, topology event processing, and control linkage. The implementation method includes network formation, master station startup configuration, and fault optimization convergence and intelligent response steps. In case of a fault, network self-healing is achieved through rapid protocol convergence, MAC table pre-synchronization, and TC message suppression and merging, synchronously triggering control logic linkage. This invention improves RSTP convergence performance, achieves deep network and control collaboration, avoids vendor lock-in based on open standards, reduces system costs, simplifies engineering implementation and maintenance, and is applicable to the field of medium and large-sized PLC industrial control.

The application discloses a kind of based on knowledge graph's curtain wall construction management method and system, and the entity and relationship are extracted from curtain wall construction data by knowledge extraction method, construct the multidimensional knowledge network including construction parameter, form semantic association structure. The semantic path between nodes is traversed using the associated query method, and potential conflict points in construction connection are identified. If the conflict involves job coordination, integrate building information model data, determine the coordination requirement level through the monitoring and early warning module, generate the optimized job sequence, and extract the process path from it, combine resource allocation logic to handle material and manpower distribution, and form a draft of the scheduling plan. Finally, integrate the feedback mechanism to update the relationship weight in the knowledge network, and realize dynamic management configuration under risk prediction. The application effectively solves the conflict identification, coordination optimization and resource scheduling problems in curtain wall construction through the construction and iterative update of knowledge network, improves construction efficiency, reduces risk, and realizes intelligent management.

This invention discloses a deep learning-based method for predicting coal mine engineering costs, comprising the following steps: Step 1: Acquiring data, performing preprocessing, and forming a cost time-series dataset; Step 2: Constructing a process-time simplex complex; Step 3: Forming a collapseable attention topology; Step 4: Implementing conservation difference enhancement to form a multi-scale cost representation and establishing a bidirectional invertible mapping; Step 5: Generating factual and counterfactual paths to form a perturbation comparison representation; Step 6: Constructing an improved Pyraformer network to form a joint hidden state representation; Step 7: Implementing hierarchical cost decoding to form the original prediction results; Step 8: Implementing cross-scale backtracking and consistent reconstruction to form the total cost prediction, stage cost prediction, and itemized cost prediction. This invention improves the accuracy, consistency, and perturbation adaptability of coal mine engineering cost prediction.

The application provides a game NPC behavior dynamic generation and optimization system based on reinforcement learning, and relates to the technical field of computer games.The method comprises the following steps: collecting player position, resource distribution and tribe attribute data in a current game environment to construct a multidimensional environment state space of autonomous NPC tribes; forming an initial behavior strategy through a policy network of a reinforcement learning model based on the multidimensional environment state space; collecting execution effect data of the initial behavior strategy in the game environment, evaluating the policy effect through a value network of the reinforcement learning model to obtain an evaluation result, performing policy optimization iteration based on the evaluation result, and forming an optimized behavior strategy; and dynamically generating a targeted tactical behavior combination according to the optimized behavior strategy, wherein the tactical behavior combination comprises a dynamic ambush strategy and a phased defense breaking strategy.The application can improve the immersion and challenge of the game.