19 results about "Data fusion center" patented technology

The invention relates to the technical field of big data analysis, and particularly discloses a marketing management system based on big data analysis. The system comprises a data fusion center, a real-time portrait engine, a multi-contact attribution analysis module, a strategy optimizer and an execution gateway, and multi-source user data are integrated, a user interest model is dynamically updated, contact contribution weights are quantized, and marketing strategies are intelligently generated. Universe user view construction, real-time interest tracking, accurate attribution analysis and automatic marketing decision making are realized, and finally the marketing efficiency and the input-output ratio are improved.

The invention discloses a highway-railway combined transportation scheduling method and system based on digital twinning and multi-agent cooperation. The method comprises the following steps: establishing a unique binding relationship of people, vehicles and goods in a transportation order based on an RFID binding algorithm, and synchronizing the unique binding relationship to a database; collecting railway transportation state data, road transportation state data and freight station operation data in real time; standardizing the railway transportation state data, the road transportation state data and the freight station operation data through a multi-source data fusion center; the connection time, the route and the parking position of the road vehicle are dynamically adjusted based on the LSTM collaborative scheduling model, and a road vehicle diversion and waiting duration estimation scheme under the emergency situation is output; railway carriage demands are predicted through LSTM, dynamic optimal matching of road trucks and railway carriages is dynamically matched based on a mixed integer programming model, an optimal matching scheme of the road trucks and the railway carriages is generated, unique binding of people, vehicles and goods is achieved by introducing an RFID technology, information barriers are broken, and real-time sharing and standardized interaction of data are achieved.

The invention discloses an expressway material supply early warning method based on meteorological data, and relates to the technical field of traffic engineering. Comprising the steps that a multi-source sensing module collects multi-dimensional information sources regularly, a data fusion center fuses the multi-dimensional information sources, a central processing unit establishes a congelation risk prediction model, a risk early warning module conducts congelation risk grading early warning, and an intelligent decision module conducts material supply scheduling optimization. According to the invention, the response time efficiency is greatly improved, the supply and demand matching precision is obviously improved, the purchasing efficiency and reliability are improved, the decision scientificity and cost are optimized, and the accident rate and economic loss are reduced; the problems of incomplete data, inaccurate prediction, one-sided evaluation, unbalanced scheduling and fuzzy response of the traditional highway anticoagulation and communication preservation material supply are solved, and the anticoagulation and communication preservation targets of accurate early warning, on-demand scheduling, controllable cost, safety and high efficiency are achieved.

The application discloses a kind of based on digital twin and multi-agent collaborative highway-railway intermodal dispatching method and system, including the unique binding relationship of people, car, goods in transport order based on RFID binding algorithm is established, and it is synchronized to database;Real-time acquisition railway transport state data, highway transport state data and freight station operation data;The standardization processing of railway transport state data, highway transport state data and freight station operation data is carried out by multi-source data fusion center;Based on LSTM collaborative scheduling model, the connection time, route and stop position of highway vehicle are dynamically adjusted, and the highway vehicle rerouting and waiting time estimation scheme under the output of sudden situation are output;Railway carriage demand is predicted by LSTM, and the dynamic optimal matching of highway truck and railway carriage is dynamically matched based on mixed integer programming model, to generate the optimal matching scheme of highway truck and railway carriage, introduce RFID technology to realize the unique binding of people, car and goods, break information barrier, realize data real-time sharing and standardized interaction.

Devices and methods are disclosed for in-network learning for dynamic wireless networks. For instance, a relay device (120a, b) for a wireless network (100) is disclosed, wherein the wireless network (100) comprises a plurality of edge devices (110a-n), each edge device (110a-n) configured to collect input data of one or more modalities of a plurality of modalities, one or more relay devices (120a, b) and a fusion center device (130). The relay device (120a, b) is configured to implement a relay machine learning, ML, model (121a-c) configured to aggregate encoded input data of a specific modality of the plurality of modalities into aggregated encoded input data of the specific modality, wherein the encoded input data of the specific modality is provided by one or more of the plurality of edge devices (110a-n) and wherein each of the one or more edge devices (110a-n) implements an encoder ML model (111a-n) configured to generate the encoded input data of the specific modality. Moreover, the relay device (120a, b) is configured to provide the aggregated encoded input data of the specific modality to the fusion center device (130) implementing a decoder ML model (131) configured to generate output data by decoding the aggregated encoded input data of the specific modality provided by the relay device (120a, b). The plurality of encoder ML models (111a-n) and the decoder ML model (131) are based on a first In-Network Learning stage of a first virtual wireless network, wherein the first virtual wireless network comprises a plurality of virtual edge devices implementing the plurality of encoder ML models (111a-n) for collecting input data of different modality and a virtual fusion center device implementing the decoder ML model (131). The relay ML model (121a-c) is trained with a second In-Network Learning stage of a second virtual wireless network comprising the plurality of virtual edge devices for collecting input data of the specific modality, each virtual edge device implementing the trained encoder ML model (111a-n), a virtual relay device implementing the relay ML model (121a, b), and a virtual fusion center device implementing a decoder ML model for input data of the specific modality.

This invention discloses a state update method based on relevant information age in an energy harvesting Internet of Things (IoT), comprising the following steps: establishing an evolution model of the network, energy consumption, and relevant information age in the energy harvesting IoT; based on the established IoT model, proposing a sensor state update optimization problem with the objective of minimizing the average relevant information age of the data fusion center; modeling the state update optimization problem as a partially observable Markov decision process with unknown sensor power; combining a flexible action commentator algorithm and a long short-term memory network, and proposing an action decomposition and mapping mechanism, designing a deep reinforcement learning algorithm to solve the established partially observable Markov decision process. The designed algorithm can effectively address the problems caused by unknown environmental dynamics, unobservable sensor power, and a large-scale discrete action space, and achieves the minimization of the average relevant information age of the data fusion center.

The invention discloses an iron and steel plant multi-mode monitoring data fusion system and a dynamic resource scheduling method based on an artificial intelligence internet of things. Comprising a multi-modal data acquisition layer which is deployed at ironmaking, steelmaking and rolling process nodes and transmits data to an edge calculation layer through an Internet of Things communication protocol; the edge calculation layer is used for fusing data features through a multi-modal attention mechanism to generate a primary fusion vector; data preprocessing and lightweight preprocessing are executed through a workshop-level gateway; the cloud data fusion center comprises a space-time alignment module, a multi-modal fusion engine and a dynamic resource scheduling module; computing resources are distributed based on the DRL model, emergency tasks with response delay smaller than 200 ms are scheduled to edge nodes, and complex tasks are unloaded to the cloud. The technical effect is remarkable, the multi-modal fusion accuracy is larger than 95%, the task delay is reduced by 40%, and the equipment fault prediction accuracy is larger than 90%.

The present application relates to the technical field of intelligent manufacturing and supply chain management, in particular to an intelligent management system for titanium plate inventory and production plan coordination. It comprises: a multi-source data fusion center for the supply chain management system to obtain operation data and generate a collaborative context original data set; a context quantitative analysis unit for receiving the collaborative context original data set and generating market agility demand points and inventory liquidity status points; a collaborative conflict evaluation unit for calculating a collaborative conflict index and determining a collaborative conflict context level; an evolutionary trend prediction unit for generating an evolution sequence of the future collaborative conflict index; and a dynamic decision management unit for generating an immediate conversion strategy in response to the collaborative conflict context level and generating a predictive inventory structure pre-configuration decision. The present application significantly improves the accuracy and objectivity of the decision, enabling enterprises to gain a deeper insight into the core contradictions of operations.

The invention discloses a false track identification method and system based on multi-radar detection, and relates to the technical field of radio navigation. The method comprises the following steps: deploying a data acquisition unit in a radar in a radar detection area, acquiring original trace point data of the radar in a preset monitoring period, transmitting the original trace point data of the radar to a data fusion center, and constructing a joint observation matrix of the radar detection area; then, steady-state observation relation analysis is carried out on the observation association graph sequence, a spatial steady-state feature library is dynamically updated, radar detection area track data generated by a data fusion center are collected, and the spatial steady-state feature library is combined to obtain a radar detection area track data fusion model; and finally, processing to obtain the type of the track of the radar detection area, and performing confidence feedback updating on the spatial steady-state feature library of the radar detection area, so that the track identification accuracy and reliability of multi-radar cooperative detection are improved.

The invention discloses an SVM (Support Vector Machine) cooperative spectrum sensing method and system based on PSO (Particle Swarm Optimization), and relates to the technical field of cognitive radio. The system at least comprises a cognitive user, an authorized user and a fusion center, an authorized user, namely a primary user (PU), transmits a signal in an authorized frequency band, and the signal is influenced by path loss and fading in a propagation process; a cognitive user is a secondary user SU, a plurality of SUs are randomly distributed in a network, energy sampling is periodically carried out on a target frequency band, and local observation data are obtained; the fusion center, namely, FC, receives observation data uploaded by each SU and is used for unified judgment; and a PSO module and an SVM judgment module are deployed at the fusion center. According to the method, a hyper-parameter automatic optimization module based on particle swarm optimization (PSO) is introduced into a fusion center, so that a kernel parameter and a penalty factor of an SVM classifier can be adaptively adjusted under the conditions of a dynamic channel and different signal-to-noise ratios, and a better compromise is obtained among detection precision, robustness and calculation efficiency.

The application discloses a kind of based on meteorological data's highway material supply early warning method, it is related to traffic engineering technical field, including multi-source perception module regularly collecting multidimensional information source, data fusion center carries out fusion to multidimensional information source, central processing unit establishes freeze risk prediction model, risk early warning module carries out freeze risk classification early warning and intelligent decision module carries out material supply scheduling optimization, the application makes that response timeliness greatly improves, supply-demand matching precision significantly improves, procurement efficiency and reliability improve, decision scientificity and cost optimization, and accident rate and economic loss reduce, through whole chain technical innovation, solve the problem of traditional highway anti-freeze and keep open material supply "data is not complete, prediction is not accurate, evaluation is one-sided, scheduling is unbalanced, response is fuzzy", realize "precise early warning, on-demand scheduling, cost controllable, safe and efficient" anti-freeze and keep open target.

The invention provides a comprehensive monitoring system for a hydropower station, which constructs a high-fidelity virtual model of power station equipment through a total-factor digital twin engine module, predicts the state of the equipment and provides situation pre-judgment capability. A deterministic transmission network which can be dynamically reconfigured is constructed by means of an intelligent elastic network architecture module, and differentiated service quality and transmission reliability are guaranteed. And the multi-modal data fusion center integrates and fuses multi-source heterogeneous data and a prediction result to generate unified panoramic situation awareness information, so that a comprehensive basis is provided for decision making. And the intelligent strategy generation module can form a distributed cooperative control strategy, so that the intelligence and cooperative efficiency of system control are improved. And the disaster recovery autonomous recovery module realizes rapid positioning and automatic recovery of system faults by using the strategy and the panoramic information. And finally, an intelligent resource scheduling module ensures efficient utilization of system resources and smoothness of overall operation. Therefore, comprehensive improvement of operation efficiency, safety and reliability is finally achieved.

The invention relates to a V2X joint resource allocation and task scheduling method based on perception-communication-computing integration, and belongs to the technical field of intelligent network connection traffic. In order to solve the problems of sensing-communication-calculation link separation, low resource utilization efficiency, prominent communication bottleneck and delay and the like in the prior art, the invention provides a unified joint optimization method. A vehicle integrated sensing and communication device collects environment samples and controls sensing errors; the scheduler selects a local computing or edge computing unloading mode according to a vehicle state and a channel condition; allocating bandwidth to the unloading task and uploading the unloading task to a road side unit for processing; performing air interface aggregation on the cooperative task to realize multi-vehicle data fusion; and the central scheduler applies an alternate optimization algorithm to jointly optimize the sensing sample number, the power, the calculation frequency, the bandwidth and the unloading proportion, and minimizes the task error or the total time delay under the constraint of the time delay and the energy consumption. According to the invention, cross-layer resource collaboration is realized, and the system perception quality and the resource utilization efficiency are effectively improved.

The application discloses a three-level distributed control system of an intelligent fire-fighting workstation based on an automatic driving chassis, wherein the first level is a cloud server layer, which is arranged in a remote data center and communicates with at least one fire truck through a mobile communication network; the second level is an edge computing layer, which is arranged on each fire truck and serves as a communication hub and a data fusion center between the fire truck and the cloud server layer; and the third level is a terminal device layer, which is arranged on a terminal device, the edge computing layer is connected with the cloud server layer and the terminal device layer respectively and serves as a data fusion and forwarding hub; the three-level distributed control system designed based on the application can realize the switching of the fire truck between an autonomous patrol mode and an autonomous fire extinguishing mode after discovering a fire, the network interruption and the network continuation function after network interruption, and the cooperative control of multiple fire trucks, and solves the technical problems of a data island, protocol heterogeneity, difficulty in considering real-time performance and intelligence, and network interruption vulnerability of an existing fire truck control system.

This invention discloses a sports health monitoring and early warning system based on a smart wearable device. The system includes: a multimodal sensor array that simultaneously acquires electromyography (EMG) signals, photoplethysmography (PPG) signals, and inertial measurement unit (IMU) data; a muscle-vascular coupling analysis module that calculates the muscle-vascular phase synchronization index to distinguish between central and peripheral fatigue; a hemodynamic causal inference module that constructs a multimodal temporal causal graph through conditional mutual information to achieve causal-driven early warning; a dynamic adversarial domain adaptive module that optimizes personalized models within a federated learning framework; an energy-information flow collaborative optimization module that dynamically schedules sensor sampling strategies; and a multimodal data fusion center that outputs a multidimensional health risk assessment vector using a graph neural network. This invention, through causal-driven early warning, adversarial domain adaptation, and energy-information flow collaborative optimization, can significantly reduce false alarm rates, improve personalized monitoring accuracy, and extend device battery life.

The invention belongs to the technical field of aviation rescue and overwater safety, and particularly relates to an amphibious aircraft overwater rescue method and system based on dynamic cooperative control. Through a real-time communication cooperation mechanism and a multi-role task synchronization model, integrated data sharing and instruction interaction of an airborne terminal, a lifeboat terminal and a shore-based / air-based data fusion center are realized, the current situation of information islands among subjects in traditional rescue is broken, cooperation delay and instruction chaos are avoided, and the rescue efficiency is improved. And the efficiency of multi-role linkage operation is obviously improved. The dynamic path planning algorithm based on RRT-MPC can automatically fuse multi-source information such as hydrology, meteorology, obstacles and the like, can generate a safe and efficient route without depending on artificial experience, can dynamically avoid dangerous areas especially in complex environments such as strong water flow, dense submerged reefs, low visibility and the like, and solves the problem that a traditional path is easy to deviate from the safe route.

The invention discloses a multidimensional perception and heterogeneous fusion method and device for a maritime object. A cooperative sensing network is formed by maritime robots such as an unmanned aerial vehicle, an unmanned ship and an underwater unmanned ship, the unmanned aerial vehicle and the underwater unmanned ship continuously sense an overwater part and an underwater part of a target in a plurality of time slots, the unmanned ship serves as a data fusion center and receives sensing data from the unmanned aerial vehicle and the underwater unmanned ship, and the unmanned aerial vehicle and the underwater unmanned ship are integrated. And fusing the received continuous time slot sensing data, and automatically adjusting the position of the unmanned aerial vehicle and the unmanned ship according to the positions of the unmanned aerial vehicle and the unmanned ship. And finally, the unmanned ship reconstructs a complete three-dimensional point cloud model of the maritime object through a radar sonar heterogeneous data fusion method. The invention provides an integrated system architecture with multidimensional sensing and cooperative scheduling capabilities for maritime affair sensing.

The invention relates to the technical field of settlement management, in particular to a settlement management multi-module integration and working system which comprises an environment sensing system, and the output end of the environment sensing system is connected with a data fusion center. The output end of the data fusion center is provided with an intelligent decision-making system, and the output end of the intelligent decision-making system is provided with an execution control system. Through cooperative operation of five modules including the environment sensing system, the data fusion center, the intelligent decision-making system, the execution control system and the feedback optimization system, comprehensive intelligence and automation of building management are realized, the system adopts a modular design, and through security and protection monitoring, equipment monitoring, energy management, video analysis and standardized interfaces, the system can be widely applied to the field of building management. Physical integration is achieved through a standardized interface, the flexibility and expandability of system deployment are ensured, the data fusion center innovatively combines data cleaning, multi-dimensional alignment and feature extraction technologies, and the processing efficiency and accuracy of multi-source heterogeneous data are effectively improved.

The invention relates to the technical field of ground vehicle navigation and positioning, in particular to an integrated navigation method integrating fault recovery and multi-task uncertainty estimation, and solves the problems that when an existing IMU / ODO integrated navigation system seriously distorts ODO data due to slipping, a traditional FDI method only removes and does not supplement the ODO data, the system is forced to be degraded into a pure inertial navigation resolving mode, and the navigation efficiency is low. The invention provides an integrated navigation method integrating fault recovery and multi-task uncertainty estimation, which has slip sensing and intelligent recovery capabilities, organically integrates three core links of'detection, replacement and fusion ', and comprises the following steps: data initialization, detection, replacement and fusion. ODO anomaly detection based on innovation is executed, multi-task pseudo odometer replacement data is generated, according to an ODO anomaly detection result based on innovation, an observation mode is dynamically selected, a measurement noise covariance matrix is constructed, IEKF is adopted as a data fusion center, and measurement updating and time recursion are carried out.