130 results about "Algorithm design" patented technology

The invention discloses a large language model enhanced reinforcement learning training method for key automatic driving scene stable decision, and the method comprises the steps: constructing an LLM-based vehicle decision intelligent agent, and providing a high-level guidance strategy through a chain thinking technology and a knowledge experience pool; then, jointly constructing a dynamic intervention mechanism based on the environmental risk sign and the decision boundary parameter, thereby determining an LLM guidance opportunity; finally, through expert guidance algorithm design, the prior knowledge of the LLM is effectively integrated into the deep reinforcement learning strategy network by adopting an adaptive exploration-imitation fusion loss function. The DRL model is better in performance in a vehicle driving decision-making task and shows higher generalization ability in various scenes, and the robustness, the sample efficiency and the overall generalization level of the DRL model can be remarkably improved.

The invention provides a zero-sum game-based distributed elastic consensus optimal control method under denial of service attack of a multi-agent system, and the method specifically comprises the steps: firstly, constructing a multi-agent formation model in which a leader and a plurality of followers cooperatively move through graph theory knowledge and a multi-agent second-order state equation; secondly, in order to reduce the influence of denial of service attack on communication topology, a time-varying weight distributed elastic observer is provided to estimate the state of a leader, and the attacked condition of the leader is considered; then, by constructing an augmentation system, a distributed consistency tracking problem with a leader is converted into a local tracking problem between each follower and a virtual leader thereof; and finally, in order to solve the zero-sum game problem, introducing a Hamiltonian-Jacobian-Ansaxophone equation to realize optimal control input under maximum external disturbance, and realizing algorithm design by using single-evaluation reinforcement learning with experience playback and combining a gradient descent method.

The invention discloses an intelligent heuristic algorithm generation method for unmanned aerial vehicle routing inspection path planning, belongs to the technical field of unmanned aerial vehicle autonomous navigation and intelligent optimization, and aims to plan a routing inspection path with the total cost as low as possible on a building routing inspection three-dimensional point set for an unmanned aerial vehicle. Aiming at the problems of high path planning complexity and low efficiency of artificial design of a heuristic algorithm in a building coverage inspection task, the method comprises the following steps: firstly, constructing a constraint model of an unmanned aerial vehicle inspection scene, and converting multi-objective optimization requirements such as building coverage rate, total detection time and flight path length into a heuristic algorithm design problem; compared with a traditional manual design method, the method enables the heuristic algorithm to reach or exceed the design level of field experts on indexes such as building coverage integrity, path length and calculation efficiency, and provides an efficient path planning solution for intelligent inspection of the unmanned aerial vehicle.

The invention discloses a port field knowledge graph automatic construction method based on cooperation of multiple intelligent Agents, and the method comprises the steps: processing structured data, semi-structured data and non-structured data of a port field through intelligent Agents with an autonomous decision-making capability, and achieving the entity recognition, relation extraction and knowledge fusion; a plurality of intelligent Agents with the cooperation function are used for executing knowledge discovery, new knowledge verification, conflict detection, knowledge fusion and graph updating tasks respectively, cooperative communication among the intelligent Agents is achieved through a message queue, and dynamic evolution of a knowledge graph is completed; processing the knowledge graph by adopting a customized knowledge graph embedding method and a semantic fusion algorithm designed for professional terms and knowledge structures in the port field; and storing the processed knowledge graph data based on a distributed architecture, wherein the distributed architecture supports high concurrent processing and real-time response. According to the method, the port domain knowledge graph can be efficiently and automatically constructed.

The invention discloses a reinforcement learning-driven public building user energy consumption behavior simulation method, which comprises the following steps of: 1, acquiring basic data, and building a simulation environment model for simulating a mapping relationship between a user energy consumption behavior and building energy consumption as well as an environment comfort degree; 2, defining a state space and an action space of the intelligent agent, selecting a depth deterministic strategy gradient algorithm as a core learning algorithm of the intelligent agent, designing a multi-target comprehensive reward function of the core learning algorithm, and embedding a public building energy consumption control target; step 3, using an intelligent agent to interact with a simulation environment, simulating an energy consumption process of a user, and identifying different scenes according to a preset rule; 4, the intelligent agent iteratively updates network parameters in the core learning algorithm based on the number of samples collected in the interaction process, and after training convergence, a user energy consumption behavior optimization scheme is output.

The invention belongs to the technical field of advertisement media, and particularly relates to a reinforcement learning optimization channel weight double-attribution advertisement effect analysis system and method, and the method comprises the steps: collecting multi-source heterogeneous data, and carrying out the preprocessing, so as to obtain standardized data; a reinforcement learning algorithm is designed, weights are distributed according to dynamic time sequence attention, a double-weight coordination action space is constructed, and a multi-modal coding state and action requirements are obtained; multi-modal data is coded, text, time sequence and structured data are coded respectively, and feature vectors matched with the model are output through modal attention fusion; designing a reward function, and generating a reward signal for real-time optimization; and a real-time optimization mechanism is constructed, parameters are updated in a layered manner, gray scale verification is performed, multi-source heterogeneous data preprocessing and enhancement algorithm design are promoted, and a closed loop is formed. According to the method, the effectiveness and accuracy of advertisement effect analysis are effectively improved, and the adaptability to multi-source heterogeneous data and dynamic scenes is enhanced.

The invention discloses a large and small model collaborative robot autonomous assembly method and system, and belongs to the field of advanced manufacturing technology intellectualization. The problems that traditional robot assembly depends on manual programming, adaptability is poor, and an algorithm cannot be optimized autonomously are solved. The method comprises the following steps: receiving an assembly project request submitted by a user in a natural language; the request is decoupled into a structured action primitive through an arrangement agent, and tasks are allocated; an algorithm design agent retrieves and adapts an algorithm from an open source library based on the action primitive, and completes training in a sandbox environment; the verification agent is responsible for automatic data acquisition and labeling, and carrying out overall performance test and iterative optimization on an integrated algorithm in a simulation environment; and finally generating an executable field control script. According to the method, the problems of algorithm autonomous design, simulation verification and closed-loop optimization when the robot faces a complex assembly task are solved, the development threshold and the deployment risk are reduced, and the intelligent level and the flexible adaptive capacity of an assembly system are remarkably improved.

The invention relates to the field of intelligent scheduling allocation, in particular to an edge cloud computing resource allocation optimization method based on deep learning, which adopts a space-time prediction algorithm based on multi-head attention and gating mechanism optimization to design time coding and space coding. The spatial relationship and interaction between time sequence characteristics of the computing power load and edge server nodes are captured, and meanwhile, a multi-head attention mechanism and expansion causal convolution are combined, so that instantaneous computing power load fluctuation can be captured, and the long-term trend of the computing power load can be mined; therefore, a reliable basis is provided for subsequent computing power scheduling by predicting an accurate computing power load. The invention designs an alternating direction multiplier method based on genetic algorithm optimization, which is not only suitable for a nonlinear and multi-constraint optimization problem, but also can be expanded to a larger-scale distributed edge node cloud computing system, and meanwhile, a global optimal solution is quickly approached through the genetic algorithm, so that the quality of an initial solution is improved, and model convergence is accelerated; and the distributed collaborative allocation scheduling efficiency is improved.

This application provides a vehicle control method, device, electronic device, and medium, relating to the field of autonomous driving technology. It constructs a three-part loss function comprising decision variables, state variables, and control variables, and sums the outputs of these three components at each time step to obtain a first sum. The first sums from multiple time steps are then accumulated to form a unified target sum. Under the constraints of a first vehicle's dynamic mathematical model and first constraints, a sequence of driving variables that minimizes this target sum is jointly solved. Finally, the vehicle is directly controlled using this optimal target driving variable sequence. This effectively bridges the coupling channel between discrete decision-making (i.e., lane decision) and continuous trajectory planning, enabling lane decision-making and trajectory generation to work synchronously and collaboratively under the same optimization objective. This improves the safety, driving efficiency, and ride comfort of autonomous vehicles in complex traffic scenarios, achieving superior overall driving performance compared to traditional fragmented algorithm designs.

The present application relates to the technical field of power system stability control simulation analysis, and provides a transient simulation analysis and decision method, device and equipment for power grid harmonic oscillation, which comprises the following steps: combining the model and model parameters of electromagnetic transient offline simulation with the topology of the power grid to be analyzed to obtain an electromagnetic transient example, and then describing the calculation process of electromagnetic transient with a hierarchical directed acyclic graph, and taking each calculation model with redistributed resources as the electromagnetic transient algorithm; performing risk analysis on the harmonic oscillation condition according to the simulation result, and making an optimized decision on the harmonic oscillation suppression measures; through example design and electromagnetic transient algorithm design, an electromagnetic online simulation model is constructed to meet the simulation requirements of large power grids and realize the analysis and suppression decision of harmonic oscillation.

The invention provides a power system black-start partition decision method based on lightweight reinforcement learning, and the method comprises the steps: constructing a black-start model of a power system containing multiple physical constraints, and formalizing the black-start model into a Markov decision process, the Markov decision process comprises a state space, an action space, a reward function and a transfer process; decomposing the power system into a plurality of sub-regions by adopting a dynamic partition recovery strategy; based on the Markov decision process, a depth deterministic strategy gradient algorithm is adopted to design and train a lightweight strategy network of deep reinforcement learning; enabling the intelligent agent to interact with the environment in each sub-region through the lightweight strategy network of deep reinforcement learning, and learning an optimal decision strategy; and according to the optimal decision strategy, performing partition power supply capability recovery on the power system. According to the invention, black-start rapid optimization decision in a complex power grid environment is realized.

The present invention discloses a method and system for blur removal and jitter correction in visual monitoring of super high-rise buildings, comprising the following steps: a visual sensor acquires a video stream at a fixed frame rate, and locates an initial region of interest (ROI) by mapping prior information; the spatial gradient field is calculated for the ROI image of the current frame, and a Gaussian-weighted two-dimensional gradient structure tensor matrix is ​​constructed; for the clear image sequence that passes blur detection, variational mode decomposition is then used in the time domain to decouple the displacement time series into eigenmode functions of different frequencies, and the low-frequency components are reconstructed to preserve the true deformation of the building; the reconstructed low-frequency displacement signal is output as the final monitoring result. The present invention employs a lightweight algorithm design throughout, significantly reducing the matrix operation dimension of subsequent processing through a dynamic ROI clipping mechanism; the structural tensor eigenvalues ​​are solved using a direct algebraic analytical method, avoiding complex matrix iterative decomposition.

The invention provides a method and system for evaluating the integrated photovoltaic potential of buildings in a high-density urban area, and the method comprises the steps: obtaining the color point cloud data of a city through the photographing and surveying of an unmanned plane, introducing the physical priori knowledge through algorithm design, and assisting a neural network in extracting a feature vector for representing the characteristics of a building group from the data; comprising the steps of point cloud sampling, normal estimation, window-wall ratio estimation and geographic orientation angle calculation, so that the model can learn implicit relation between the urban form and a photovoltaic potential prediction result; aiming at a scene of comprehensively realizing photovoltaic integration popularization of medium and large-scale buildings, the power generation efficiency of building facades and photovoltaic modules mounted at different positions of windows and walls is considered, feature vectors are input into a regression prediction framework formed by a one-dimensional point cloud neural network, evaluation errors are reduced, systematic deviation of resolution is avoided, and the evaluation accuracy is improved. Data acquisition and prediction are facilitated, and the function of predicting the maximum photovoltaic power generation potential after the building is comprehensively paved with the BIPV is realized.

This invention relates to the field of stage equipment control technology, specifically disclosing a progressive speed control method for stage equipment that integrates safety constraints. By acquiring the motion characteristic information of the equipment in the current environment, performing risk assessment on abnormal information, constructing segmented safety thresholds based on dynamic safety position sensitivity, and finally obtaining a progressive speed with safety constraint mechanisms, this method solves the safety hazards caused by control system failures in existing methods. The method of this invention achieves low cost through lightweight algorithm design, significantly reducing hardware investment and deployment costs. Simultaneously, by combining dynamic safety distance updates with characteristic anomaly risk assessment, it greatly improves the resilience and fault tolerance of the control system, providing a high-precision and highly robust safety control solution for large stage machinery (such as stage wagons and rotating stages).

The application provides an improved multi-agent deep reinforcement learning unloading method, relates to the technical field of Internet of Vehicles and edge computing, and solves the technical problems of computing overhead, energy consumption and time delay in the task unloading process.The technical scheme comprises the following steps: S1: task unloading problem modeling;S2: improved unloading method design and implementation.The task queue smoothing algorithm designed by the application can accurately reflect the task load of the server and the mobile terminal, and assist the deep learning algorithm to make more accurate and stable unloading decisions.The application designs a smoothing penalty mechanism of a Sigmoid function in a reward function, and provides continuous and accurate gradient guidance for agent learning.The application corrects the action output by the deep reinforcement learning algorithm in real time in the early training stage through the closed-loop feedback mechanism of the PI controller, and improves the time delay performance of unloading.

We provide the system. [Solution] Means for collecting and analyzing multilingual information, A means of designing a new standard representation using a generative algorithm, means for converting the multilingual information into the standardized expression and compressing it, A means for optimizing the predictive model using the transformed information, A means of performing bidirectional communication with the user using a predicted model, A means of presenting information translated in real time, A system that includes this.

The invention belongs to the technical field of computer vision, three-dimensional reconstruction, scene perception and algorithm design, and discloses a three-dimensional reconstruction generation method and device for a complex scene. The invention discloses a three-dimensional reconstruction generation method for a complex scene. A transparent and reflecting object detection module, a three-dimensional reconstruction refined generation module and a next scanning site prediction module are included. The invention discloses a three-dimensional scanning device for a complex scene. The three-dimensional scanning device comprises an RGB image acquisition unit and a polarization camera, according to the method, high-quality, high-efficiency and high-autonomy three-dimensional reconstruction of transparent and reflective objects and complex shielding scenes is realized, and the method can be widely applied to the fields of industrial detection, cultural relic protection, reverse engineering and the like.

The invention discloses a table data analysis large model training and application method based on agent interaction reinforcement learning. Collecting multi-source data, generating a reference reply text, and converting to obtain multi-source word vector data; screening the multi-source word vector data through multiple times of repeated reasoning processing of a plurality of strong models; extracting data and inputting the data into a cold start model with preset weight parameters for training processing of supervised fine tuning of all parameters; inputting multi-source word vector data into the trained cold start model, and training by adopting a reinforcement learning method; and applying the cold start model trained by the reinforcement learning method to answer processing of text questions in an actual scene. According to the method, through reasonable multi-source data setting and matching, training process and algorithm design, the actual application effect of the large language model in the field of two-dimensional table data analysis is improved.

The invention discloses a path tracking control method suitable for crawler-type agricultural equipment. The method comprises the following steps: S1, building a navigation hardware control system on crawler-type equipment; s2, designing a Kalman filtering algorithm to filter the course angle of the crawler-type equipment; s3, correcting an equipment positioning error caused by the attitude angle; s4, a fusion algorithm of the Stanley algorithm and the Pure Pursuit algorithm is designed; s5, designing an enhanced SPP algorithm; s6, performing secondary optimization on the control law output by the SPP algorithm by using a fuzzy PID control algorithm; and S7, fitting a total control law equation in combination with the control algorithm, and converting the control law into the linear speed of the left and right tracks of the crawler-type equipment so as to realize steering and straight movement of the crawler-type equipment. According to the invention, a complex agricultural environment is regarded as a black box system, and item-by-item optimization is carried out by superposing an algorithm with high interpretability, so that the adaptability of a control system to the black box system is improved, and finally, the equipment path tracking precision is improved step by step.

The present application relates to the technical field of distributed model training, and provides a model distribution parallel training process automatic optimization method, system and device. The method comprises the following steps: defining a task plane according to the communication and computing power of a neural network model, dividing the task plane to obtain a divided task plane; constructing a training time consumption model according to the divided task plane to obtain total time consumption; using a tournament algorithm to design a genetic algorithm to solve the training time consumption model according to the total time consumption to obtain a training optimization result; and embedding the training optimization result into the neural network model for optimization and updating. The present application models the training process in detail under the scene of a mesh pipeline and a heterogeneous network and computing power equipment. According to the established training process-training time consumption model, a meta-heuristic algorithm is applied to search for an optimal solution to realize automatic optimization of the distributed parallel training process.

This invention relates to the field of servo control algorithm design for aircraft airborne pods, providing a method and system for calculating external disturbance reactance based on servo motor current feedback. The method acquires three-phase currents Ia, Ib, and Ic, and electrical angle θ, and obtains two-phase currents Id and Iq through Clarke and Park transforms, defining Iq as the external disturbance reactance estimate IQ. A setpoint r(t) and deviation e(t) = r(t) - IQ are established, and the PID controller output u(t) is calculated. u(t) is used as the q-axis control reference and written to the driver. In voltage control mode, it is mapped to Vq and Vd for inverse transformation and PWM modulation; in current control mode, it is mapped to the q-axis current reference Iqref and converted into corresponding voltage commands by the driver's current loop, driving the servo motor to generate electromagnetic torque to cancel out disturbance reactance. This invention eliminates the need for complex motor models and high-end inertial sensors, has low computational complexity, and can quickly and accurately estimate disturbances, ensuring stable control performance of the aircraft pod in complex flight environments.

The invention discloses a social network rumor suppression method and system based on a sphere domain index, and relates to the technical field of social network information processing. For the NP-hard characteristic of a rumor suppression problem under a competitive independent cascade model and the defect of high calculation cost of a traditional algorithm, efficient response under a multi-query scene is achieved through three-step progressive algorithm design. The method comprises the following steps: firstly, proposing an HMP-TC algorithm, replacing a forward sampling process in mixed sampling with typical cascade, and depicting a stable structure of rumor propagation; secondly, proposing an HMP-LB algorithm, constructing a landmark index structure based on point coverage, only maintaining influence ball domain information for index nodes, and correcting deviation through a probability weight; and finally, proposing a PTC-LB algorithm, introducing a protection sphere domain index formed by protection typical cascade and protection relation samples, and realizing non-sampling rapid optimization in a query stage. According to the method, on the premise of maintaining 90%-95% of rumor blocking effect, the single query speed is increased by 10-30 times, part of scenes can reach two orders of magnitude, and the quick response problem of rumor suppression in a large-scale social network is effectively solved.

The invention discloses a structural vibration detection method based on an inequality constraint hybrid least square algorithm in the technical field of structural vibration detection. The method comprises the following steps: S1, system model construction: establishing a linear discrete stochastic system state space model; s2, designing an algorithm: proposing a hybrid least square algorithm with input inequality constraints; s3, solving a system model: applying a proposed inequality constraint hybrid least square algorithm to a discrete system to realize simultaneous optimal estimation of a system state and input; and S4, performing comparison simulation: performing simulation by taking a two-layer shear structure as an example, comparing the state and input estimation of the shear structure under the conditions of no constraint and existence of inequality constraint, and verifying the effectiveness of the method. According to the invention, the hybrid least square algorithm of the input inequality constraint is provided, and the filtering effect is optimized by using part of input information, so that the accuracy of structural vibration detection is improved.

The invention discloses a neural network algorithm design method and a neural network operation method based on a resistive memory, and the method comprises the steps: determining the nonlinear response characteristics of the resistive memory, and determining the adjustment mode of the resistive memory according to the response characteristics; determining a parameterization method of back propagation of the neural network, wherein the number and the connection mode of the resistive memories and the inter-layer signal conversion mode of the neural network are determined according to the task of the neural network; according to the adjustment mode of the resistive memories, the number and the connection mode of the resistive memories and the signal conversion mode between layers of the neural network, the forward propagation process of neural network operation is realized; realizing a back propagation process of the neural network according to a parameterization method of back propagation of the neural network; and training the target task to obtain a trained neural network model. The hardware architecture does not need an analog-to-digital converter and the like which occupy a large amount of area and power consumption, so that the power consumption and the design area of storage and calculation hardware can be greatly reduced.

The application discloses an automatic driving environment perception method and system based on artificial intelligence, and relates to the technical field of automatic driving environment perception, in particular to an automatic driving environment perception method and system based on artificial intelligence.The application obtains original data through multi-source data collection; adopts a raw data optimization method of sensor calibration, dynamic and static data separation, data normalization, data enhancement and data set segmentation; adopts a double-branch transformer model as an environment perception model, and respectively captures irregular behavior patterns of moving targets and geometric topological constraints of road structures through a double-branch architecture; and adopts an improved ant colony optimization algorithm as a decision optimization algorithm, converts a multi-dimensional risk field into a calculable optimization target, and realizes optimal decision through global exploration of elite ants and local optimization of non-elite ants.

The invention relates to an intelligent obstacle avoidance walking stick system based on multi-sensor fusion and lightweight AI. The intelligent obstacle avoidance walking stick system is used for solving the problems that an existing intelligent walking stick is single in environment perception dimension, tumble detection accuracy and real-time performance are difficult to balance, and indoor and outdoor navigation scenes cannot be seamlessly switched. According to the system, through multi-sensor deep fusion and lightweight algorithm design, an intelligent obstacle avoidance walking stick system which is high in robustness, low in power consumption and capable of self-adapting to the environment is constructed, the system can run on an embedded processor of a walking stick, and traveling safety of visually impaired and old users is facilitated.

This invention relates to the field of industrial process technology, and more particularly to a soft measurement method for iron ore grinding particle size based on the Grey Wolf algorithm combined with LSTM. The method includes data preprocessing; improved Grey Wolf optimization algorithm design: initializing the Grey Wolf population using a Tent chaotic mapping strategy, and introducing a nonlinear adaptive convergence factor to dynamically adjust the exploration and development capabilities of the Grey Wolf optimization algorithm; optimizing the key hyperparameters of the LSTM network to obtain the optimal hyperparameter combination; constructing and training an LSTM soft measurement model, using multi-source real-time process parameters as input, to complete online real-time prediction of iron ore grinding particle size. The advantages of this invention are: addressing the limitations of traditional manual sampling and testing, such as long cycle times and data lag, as well as the high investment and maintenance costs of online detection instruments, by constructing a data-driven model, continuous online prediction of grinding particle size is achieved. Its response speed is significantly better than that of manual testing, providing a new technical approach for improving the real-time performance of process control.

The present application relates to a kind of solving method for the design of nonlinear system multiple small fault estimator, first establish the discrete-time system model containing actuator and sensor multiple fault and nonlinear term, then introduce nonsingular transformation and decompose the original system into two subsystems: subsystem 1 only contains external disturbance, subsystem 2 contains both actuator fault and sensor fault. Based on two subsystems, two iterative learning estimators 1 and 2 are designed, and an integrated solution method for designing two estimator parameters is applied using optimization algorithms. Finally, a multiple small fault estimation strategy for nonlinear systems is presented, and accurate estimation is achieved when multiple faults occur concurrently. The present application can accurately estimate the actuator and sensor faults of nonlinear discrete-time systems, while simultaneously counteracting the influence of external disturbances on fault estimation results, effectively estimating small faults in the system, and improving the system's fault handling capability and fault tolerance performance. The solving method of the present application is simple and easy to implement in practical engineering systems.

The invention discloses an LMI-based intelligent suspension robust control and state observation method, and relates to the technical field of suspension control, and the method comprises the following steps: S1, splitting a control system into a non-matching disturbance subsystem and a matching disturbance subsystem; s2, determining state feedback control of an LMID algorithm according to the weight matrix of state control; determining disturbance compensation of a disturbance observer part in an LMID algorithm based on a weight matrix of a matching disturbance subsystem and disturbance estimation, and realizing the LMID algorithm by using an LMIob observer; and S3, taking the sprung acceleration based on the IMU in the suspension system as the input quantity of the LMIob observer, and obtaining state estimation of the control system. The method is designed based on an LMID algorithm of LMI, the algorithm has disturbance observation properties, the robustness of the algorithm can be improved, a weight matrix is introduced, and flexible adjustment of state control and disturbance estimation is achieved.

The invention discloses an MEC task unloading method based on opportunity constraint, and relates to the technical field of cloud computing, and the method comprises the steps: building a time delay energy consumption model, a fuzzy privacy model and an opportunity constraint model through the fuzzy data input quantity and the fuzzy CPU cycle number of a fuzzy to-be-processed task; establishing a joint optimization model through a time delay energy consumption model, a fuzzy privacy model and an opportunity constraint model; solving the joint optimization model to obtain a task unloading strategy and a network selection strategy; distributing the fuzzy to-be-processed task to an unloading position according to a task unloading strategy; and performing resource transmission according to the network selection strategy. According to the method, the joint optimization model is solved through the designed unloading algorithm, and the optimal solution about the task unloading position strategy and the network data transmission selection strategy is obtained. And distributing the tasks to the corresponding unloading positions. And according to the network data transmission selection strategy, distributing task data to different networks according to the proportion so as to transmit the data.