58results about How to "Improve planning efficiency" patented technology

The invention provides a unified context and multi-level memory cooperation system and method for an LLM agent, and belongs to the field of artificial intelligence. The system comprises a unified context module which is used for aggregating and structuring all input information required for organizing agent operation, and providing an integrated context view for an LLM agent core; the LLM agent core is used for executing task planning, tool calling, result evaluation and response generation based on the context provided by the unified context module; and the multi-level memory system is connected with the unified context module and the LLM agent core and is used for hierarchically storing, managing and feeding back experience and knowledge of the agents. According to the method, the problems that an existing LLM intelligent agent is limited in context, low in memory efficiency and lack of self-correction capacity are solved, and the intelligent level and reliability of complex task processing are remarkably improved.

The invention belongs to the technical field of path planning and robot motion planning, and particularly relates to a multi-strategy fusion improved RRT * sampling planning method and device and a storage medium, and the method comprises the steps: constructing a dual-search tree through a starting point and a target point in a three-dimensional working space, and selecting a to-be-expanded search tree through a random mode; halton-Bridge mixed sampling is adopted to generate sampling points, so that the global coverage uniformity is improved, and the narrow channel sampling capability is enhanced; calculating the dynamic step length of the exponential decay based on the local obstacle proportion; adopting a hierarchical guidance expansion strategy, preferentially expanding towards a target, introducing an improved artificial potential field to guide expansion when the expansion fails, and taking the bottom with random expansion; performing RRT * neighborhood father node reselection and reconnection optimization on the new node; greedy pruning, self-adaptive interpolation and cubic B-spline smoothing are carried out on a path after the double trees are connected, and an executable smoothing track is output; according to the scheme, planning efficiency, success rate and path quality are improved.

This invention provides a method and system for UAV path planning based on a fusion algorithm, relating to the field of UAV autonomous navigation and path planning technology. The method includes the following steps: acquiring the starting coordinates, ending coordinates, and obstacle information in the flight environment of a flight mission, and constructing a flight environment spatial model; defining path constraints and optimization objectives, and generating an initial set of feasible paths based on the flight environment spatial model, path constraints, and optimization objectives; performing weighted fusion and guided enhancement on the initial set of feasible paths to obtain a weighted fused path and a guided enhanced path; employing a particle swarm optimization algorithm to construct an initial particle swarm based on the initial feasible path set, the weighted fused path, and the guided enhanced path, and iteratively optimizing the initial particle swarm to obtain a globally optimal particle; and decoding the globally optimal particle to obtain the final flight path. This invention significantly improves the efficiency and quality of UAV path planning in complex static obstacle environments.

The application discloses a kind of multi-target vehicle path optimization method, system, electronic equipment and medium, it is related to vehicle scheduling and intelligent optimization field, the method includes: the customer point sequence and vehicle data of current time of acquisition are input in each main task subproblem model and each auxiliary task subproblem model, obtain the planning scheme of current main task and the planning scheme of current auxiliary task;Current planning scheme is determined as initial population, and the initial population of main task is iteratively optimized according to the initial population of auxiliary task using the way of evolutionary migration, obtain optimal planning scheme, and the subproblem model is obtained based on decomposition model to deep reinforcement learning model training;Main task decomposition model is obtained by decomposing main task model, and auxiliary task decomposition model is obtained by decomposing auxiliary task model;Main task model is constructed based on five targets;Auxiliary task model is constructed based on two targets in five targets.The application can improve the planning efficiency and accuracy of vehicle path.

This application discloses a low-altitude defense platform deployment system and method. The system includes: a data acquisition module for acquiring relevant data of the defense area and information on available platforms; a capability quantification module for uniformly quantifying the capability parameters of each platform to obtain standardized capability descriptions; an AI agent search module, comprising multiple parallel-working AI agents and a shared memory area; each AI agent iteratively executes the generation of candidate deployment schemes, calculation of constraint violations, and evaluation of comprehensive performance scores, and updates the locally optimal deployment scheme based on the evaluation results, exchanging scheme information through the shared memory area to guide subsequent searches; and a scheme determination module for determining the globally optimal deployment scheme when termination conditions are met. This application improves the comprehensive protection effectiveness and planning efficiency of heterogeneous defense platform deployment schemes through capability quantification and multi-agent parallel collaborative search, achieving automated global optimization deployment under complex constraints.

The invention discloses an unmanned aerial vehicle spraying path planning method and device, and relates to the field of artificial intelligence and unmanned aerial vehicle application. The method comprises the following steps: constructing a path planning model according to a three-dimensional working environment, obstacle constraints, unmanned aerial vehicle performance and spraying requirements; mapping the flight paths into decision variables in one-to-one correspondence by adopting multi-dimensional continuous coding; constructing a multi-objective function containing the path length, the spraying uniformity, the flight rotation angle and the obstacle avoidance safety cost; an improved cordyceps sinensis optimization algorithm is called, and population initialization, logarithmic spiral reverse learning space expansion, exploration double-strategy updating, parasitic dynamic disturbance and embedded new solution iterative optimization are carried out; and after the maximum number of iterations is reached, outputting a globally optimal solution and converting the globally optimal solution into an unmanned aerial vehicle spraying path. The problems that in the prior art, unmanned aerial vehicle spraying path planning is low in efficiency and poor in precision degree are solved, and the method has the advantages of being wide in search range, high in optimization precision, high in dynamic adaptability and the like and can be widely applied to the fields of agricultural plant protection, urban disinfection, forest protection and the like.

This invention belongs to the field of task scheduling technology and discloses a hierarchical task scheduling method for UAV swarms for large-scale node inspection. The steps are as follows: S1: Initialize the UAV inspection task and input the upper-level task allocation model; S2: The upper-level task allocation model calculates the task allocation probability using an alternating optimization method and updates the task centroid; S3: Repeat S2 until the iteration threshold, and then use a hard allocation method to divide the inspection task into multiple task subsets; S4: Allocate the task subsets to the UAV swarm and send them to the lower-level path planning model; S5: The lower-level path planning model selects the optimal inspection node for the UAV at each time step and updates the task status; S6: Repeat S5 until the inspection path for each UAV is constructed, thereby obtaining a hierarchical task scheduling result for the UAV swarm covering all inspection nodes. This invention designs a task scheduling framework that combines an upper-level task allocation model and a lower-level path planning model, which can effectively support UAV inspection tasks.

This invention relates to the field of chip inspection technology, and more particularly to a chip non-destructive testing system based on embedded current scanning. The system includes a current scanning module, an information acquisition module, a data analysis module, an abnormal scanning region generation module, and a scanning path generation module. Instead of simply performing a higher-density secondary scan of the entire chip, this invention intelligently filters out abnormal scanning regions requiring special attention based on the initial scan results and calculates their scanning priority. This allows valuable inspection time and computing resources to be concentrated on the most suspicious and severe areas, avoiding unnecessary repeated scanning in normal areas. The system dynamically selects the optimal scanning path based on the regularity of the region shape; for example, parallel lines are used for regular regions, and radial lines are used for irregular regions. This makes the scanning path more closely match the geometric features of the defect, obtaining a more complete region characterization with fewer scanning points, resulting in higher path planning efficiency.

The invention discloses an automatic pool cleaning device, an automatic pool cleaning system and a method for controlling the automatic pool cleaning device. The method comprises the following steps: acquiring data about a boundary of a to-be-cleaned area in a pool; determining a path for cleaning the to-be-cleaned area; and controlling the automatic pool cleaning equipment to move according to the path so as to clean the to-be-cleaned area.

The invention discloses an energy storage power station collaborative planning method and system based on uncertainty propagation analysis. In order to solve the problems that an existing energy storage planning method is indefinite in physical mechanism and insufficient in interpretability, the planning method comprises the steps that operation data of a power system are obtained, and an analysis alternating current probabilistic power flow model used for establishing an analysis relation between system voltage statistical characteristics and line power statistical characteristics is constructed based on the operation data; constructing a propagation matrix representing the uncertainty propagation characteristics of the system based on the analysis of the AC probabilistic power flow model; performing spectral analysis on the propagation matrix to identify one or more dominant propagation modes which play a dominant role in the uncertainty of the system; and based on the one or more dominant propagation modes, determining a planning scheme of at least one type of energy storage power station, the category of the planning scheme including the access position capacity of the energy storage power station. According to the method, energy storage configuration is guided by using an uncertainty physical propagation mechanism, and the risk control effect, the calculation efficiency and the engineering interpretability of a planning scheme are remarkably improved.

The invention discloses a blue army task planning method based on knowledge and data driving, and relates to the technical field of military simulation modeling and computer simulation, and the blue army task planning method comprises a sensing layer, a fusion layer, a reasoning layer, a planning layer, an optimization layer and an output layer. Bidirectional interaction between the layers is achieved through data interfaces, and deep fusion of knowledge and data in the whole process is ensured; by constructing a dynamically updated knowledge graph and a knowledge-data mapping mechanism, domain knowledge can guide data modeling in the whole process, meanwhile, the data can optimize a knowledge system in real time, the limitation of a single driving mode is solved, and through testing, in a complex military drill scene, the knowledge and data can be fully fused. The matching degree of the fusion-driven planning scheme and the actual situation reaches 92%, is improved by 25% compared with a knowledge-driven scheme, and is improved by 30% compared with a data-driven scheme.

This invention discloses a method and system for processing personnel information for business administration based on big data, relating to the field of personnel information data processing technology. The method includes the following steps: acquiring personnel information; preprocessing the personnel information to obtain preprocessed text information; processing the preprocessed text information through an embedding layer based on a CNN-BERT model to obtain a word vector matrix; processing the word vector matrix sequentially through a CNN convolutional layer, pooling layer, and fully connected layer to obtain structured data; using an improved ant colony optimization algorithm to perform path optimization for multi-condition combined queries on the structured data to obtain the globally optimal retrieval path; retrieving personnel information that satisfies the multi-condition combined query from the structured data based on the globally optimal retrieval path; and adaptively updating the global pheromone of the improved ant colony optimization algorithm after each round of multi-ant colony collaborative search to accurately locate the target personnel information.

The application discloses a simplified visual graph modeling and planning method based on Delaunay triangulation, and first acquires polygonal obstacles in an environment, constructs a limited Delaunay triangulation network by using a centroid point set of the polygonal obstacles; obtains neighbor obstacles of each obstacle from the triangulation network to construct neighbor pairs; then constructs a global environment simplified visual graph by using a visibility relationship between adjacent obstacle vertices; maintains a local region where a starting point and an ending point are located into the global visual graph, and plans a global path by using a Dijkstra algorithm with fusion pruning; generates an elliptical window associated with the path, divides boundary points of obstacles in the elliptical window and elliptical boundary points into two types of samples by using the global path, and finally trains a support vector machine based on a radial basis function to obtain a safe and smooth path, so that the path planning method is more advanced and faster.

The invention discloses a base station deployment method, system and device based on reinforcement learning, and a medium. The method comprises the following steps: modeling a sequential deployment process of a base station as a decision process of reinforcement learning; in response to the reinforcement learning agent executing an action of deploying a base station in a current state to enter a next state, determining a coverage performance representing a network coverage range change; determining a quality performance representing a change in network communication quality; based on the coverage performance and the quality performance, constructing a comprehensive reward function to generate a comprehensive reward value used for guiding agent decision making; on the basis of the comprehensive reward value and the maximum future expected reward obtained according to the next state, the decision basis of action execution of the intelligent agent in the current state is updated; and repeatedly executing the steps of deploying the base station, generating the comprehensive reward value and updating the decision basis until a final base station deployment scheme meeting a preset condition is obtained.

The invention belongs to the technical field of path planning, and more specifically relates to a limited space unmanned aerial vehicle bridge simulation inspection path planning method. The method comprises the following steps: sensing and subscribing point cloud information of an environment by an unmanned aerial vehicle, wherein the point cloud information comes from a laser radar, a depth camera or a fusion point cloud; filtering: carrying out point cloud noisy point self-adaptive multi-level filtering on the point cloud information, executing nine-step self-adaptive noisy point filtering, and outputting filtered point cloud and a free space F; planning and bridge-imitating inspection path generation are carried out, an initial path is generated through a narrow channel RRT *, a safe flight inspection corridor SFIC is constructed, and a middle bridge-imitating inspection path is generated in the SFIC in an optimized mode. The problems of insufficient environmental perception precision, low safety and efficiency of path planning, lack of dynamic adaptability of path planning and low path quality during the inspection process of an existing unmanned aerial vehicle in a limited space in a bridge are solved.

The application provides a UAV path planning method and system based on local update of flow field, and belongs to the technical field of UAV path planning, and comprises the following steps: modeling an environment, and calculating a global static flow field; for a dynamic obstacle, updating a dynamic obstacle position based on a current position and a moving speed of the obstacle; when a UAV approaches the dynamic obstacle, calculating a dynamic repulsion force vector generated by the dynamic obstacle based on the dynamic obstacle position and a current position of the UAV, and performing local flow field dynamic update based on the dynamic repulsion force vector and the global static flow field; calculating a multi-dimensional evaluation function based on control pairs in a velocity sampling space guided by the flow field and a wind field, selecting a control pair with the highest score of the multi-dimensional evaluation function as an optimal control instruction, and controlling the UAV to update a position based on the optimal control instruction. The application improves real-time performance and dynamic adaptability of UAV path planning in a complex environment.

The present application relates to remote sensing control technical field, especially unmanned aerial vehicle path planning method, device, equipment and storage medium are provided.The present application obtains initial point cloud image according to the unmanned aerial vehicle path planning request, and determines initial unmanned aerial vehicle path according to initial path point position, collects target point cloud image of each initial path point in initial unmanned aerial vehicle path, finally compares the target point cloud image collected with preset point cloud image, so as to adjust initial unmanned aerial vehicle path, reach the purpose of planning unmanned aerial vehicle path, avoid the technical problem that the traditional unmanned aerial vehicle path planning process in prior art mainly relies on artificial completion on two-dimensional map, is easy to receive interference, improve the efficiency of unmanned aerial vehicle path planning.

The application discloses a trajectory planning method and device, electronic equipment and a storage medium, wherein the method comprises acquiring scene information of a target vehicle to generate a space-time corridor, wherein the space-time corridor comprises a plurality of steps corresponding to a plurality of time slices in an S-L-T three-dimensional space, and the step is a drivable range of the target vehicle in the corresponding time slice; a trajectory cost function is constructed based on state variables and control variables of the target vehicle, the state variables include position, speed and acceleration, and the control variables include impact degree; under the constraint of the space-time corridor, a driving trajectory of the target vehicle in the plurality of steps is planned based on the trajectory cost function, the driving trajectory comprises a plurality of spline curve segments corresponding to the plurality of steps respectively, and the constraint of the space-time corridor comprises an equality constraint on the state variables of the target vehicle and an inequality constraint on the state variables and the control variables of the target vehicle. In this way, the automatic planning of the driving trajectory of the vehicle in the automatic driving can be realized, and the availability of the automatic driving function of the vehicle is ensured.

The invention discloses a task planning method for an emergency communication unmanned aerial vehicle, and belongs to the technical field of emergency communication unmanned aerial vehicle task planning. The method comprises the following steps of task area geographical environment construction, communication unmanned aerial vehicle number planning, communication station deployment station planning, unmanned aerial vehicle path planning and unmanned aerial vehicle task planning scheme generation. According to the method, deployment station planning is performed on the unmanned aerial vehicle required by the emergency communication guarantee task based on the genetic algorithm and the wireless propagation model, and the maneuvering path of the unmanned aerial vehicle from the initial position to the deployment station is planned according to the A * algorithm, so that the planning efficiency of the emergency communication task is improved, and compared with manual planning operation, the planning efficiency is improved. And the experience requirements of emergency communication task planning on operators are greatly reduced.

The invention discloses a mechanical arm motion planning method and system, and the method comprises the steps: obtaining target and obstacle point clouds through a 3D camera, and carrying out the registration to obtain pose information, carrying out the URDF modeling and MoveIt configuration of a mechanical arm, and carrying out the improvement of an RRT-connect algorithm, and the method comprises the steps: introducing a dynamic target bias, directional heuristic sampling and elastic band smoothing algorithm mechanism, the planning efficiency and the path smoothness are improved; performing inverse kinematics solution on the path points to obtain a joint track; optimizing the trajectory by adopting self-adaptive polynomial interpolation, and performing cubic or quintic polynomial interpolation according to the complexity of an interpolation section; and finally, the track is converted into a control instruction through a Modbus TCP protocol, and the mechanical arm is driven to safely move to the target position. According to the method, the planning speed, the track quality and the motion stability of the mechanical arm in the complex environment are remarkably improved.

The application relates to the technical field of data reasoning, and discloses a mine equipment intelligent manufacturing production scheduling optimization system and method. The system comprises a topological graph generation module, an initial scheduling Gantt chart generation module, a demand intensity coefficient acquisition module, a flexible scheduling Gantt chart acquisition module and a final scheduling instruction set generation module. A topological graph is constructed based on the process connection of mine equipment. An initial scheduling Gantt chart is generated by taking a component task set as a vertical axis and a corresponding final assembly line task sequence as a horizontal axis. When a disturbance event occurs, an affected process dependency tree is extracted, a task delay cost is evaluated, and a demand intensity coefficient for manufacturing process rescheduling is output. A flexible scheduling Gantt chart is generated based on process beat deviation and equipment utilization in synchronous adjustment of a manufacturing process. A final scheduling instruction set is confirmed through process path dynamic correction and process optimization results. The application can improve the efficiency of a mine equipment manufacturing production process scheduling scheme.

This invention relates to the field of BeiDou navigation technology, specifically disclosing a path positioning and planning method and system based on BeiDou navigation. The method includes: receiving emergency rescue instructions, automatically planning emergency rescue routes and predicting travel time; collecting road condition information for the emergency rescue routes; analyzing the impact of road conditions on travel time based on the road condition information; collecting vehicle condition information for the emergency rescue routes; firstly analyzing whether vehicles can make way for emergency rescue vehicles based on the vehicle condition information; if so, analyzing the impact of vehicle conditions on travel time; comprehensively analyzing the impact of road conditions and vehicle conditions on travel time to determine the actual travel time; and finally recommending the emergency rescue route with the shortest actual travel time. This invention improves the accuracy of emergency rescue travel time prediction by analyzing the impact of road conditions and vehicle conditions on travel time, thereby improving the efficiency of emergency rescue route planning.

The present application relates to the technical field of code spraying path planning, and discloses a path planning method, device, equipment and medium for log pile code spraying, which comprises the following steps: collecting position information of the end face of each log in the log pile to be sprayed and corresponding diameter grade information; modeling the log pile to be sprayed into a dynamic layered network model; traversing the log nodes in the dynamic layered network model to generate a code spraying path; performing collision detection on the code spraying path, and optimizing the code spraying path according to the collision detection result; inputting the log code spraying sequence list corresponding to the optimized code spraying path to a code spraying device, and spraying codes according to the log code spraying sequence. The present application converts the log pile into a layered network model by combining the physical constraints of the log pile, traverses the log nodes, plans the code spraying path, embeds the collision detection logic, and dynamically optimizes the code spraying path, thereby replacing manual code spraying, reducing the time complexity of finding the optimal path, and improving the code spraying efficiency.

The application relates to the technical field of tourism route planning, and particularly discloses a personalized tourism route planning method, which comprises the following steps: S1, obtaining target point, avoidance point and passable point data; S2, constructing a Thiessen polygon network through the target point, the avoidance point and the passable point, and connecting the target points in sequence to obtain a reference path; S3, obtaining an initial path; S4, directly connecting the lines in the initial path to optimize the initial path; S5, screening out the connected avoidance points in the initial path, searching for a Thiessen polygon region adjacent to the avoidance point, deleting the line connected with the avoidance point in the initial path, connecting the searched Thiessen polygon regions in sequence to obtain an avoidance path, and connecting the two ends of the avoidance path with two breakpoints in the initial path after deletion, so as to complete the planning of the tourism route. The personalized tourism route planning method can improve the planning efficiency of the tourism route.

The invention discloses a warehouse layout planning method and device, and relates to the field of warehouse logistics. A specific embodiment of the method comprises the steps of obtaining storage layout description information, a preset business index and an expected value of a warehouse, and generating a storage layout code based on the storage layout description information; generating a storage layout map based on the storage layout code, and inputting the storage layout map into a preset evaluation model to obtain an evaluation value under each preset business index; in response to the situation that any evaluation value does not reach the corresponding expected value, optimizing the storage layout code and re-executing the conversion and evaluation operations until all the evaluation values reach the corresponding expected values; and executing a warehouse layout planning operation on the warehouse based on a warehouse layout map generated by the final optimized warehouse layout code. According to the embodiment of the invention, through a coding-evaluation-optimization automatic iteration process, intelligentization and high efficiency of warehouse layout planning are realized, and the quality and efficiency of warehouse layout planning are significantly improved.

The invention discloses an RRT path planning method and device based on a police-thief mechanism and discrete SAC, and a medium. The method comprises the following steps: initializing a fast random tree structure and node attributes; establishing a police-thief node mechanism, realizing node role division and dynamic pruning, and performing bridging optimization on nodes; a reinforcement learning decision network based on discrete Soft Actor-Critic is constructed, and joint decision making is carried out on the node expansion direction, the step length and the execution strategy of a police-thief mechanism; and updating reinforcement learning network parameters according to the reward shaping function until the optimal path is converged. The planning efficiency and the path quality are remarkably improved.

The application discloses a multi-model reasoning method and device based on a graph structure, a medium and a program product, wherein the method comprises the following steps: querying a task target node in a graph database and starting from the task target node, and performing reasoning path expansion in the graph database according to a corresponding driving model, wherein the graph database comprises a plurality of directed acyclic graphs, and each directed acyclic graph is obtained by mapping metadata of a registered analysis model; generating a task topology execution graph according to model nodes involved in the expanded reasoning path and the corresponding driving model; and sequentially scheduling actual execution of each model node according to the task topology execution graph, and obtaining an explanation result corresponding to the task target node. The application improves the reasoning execution efficiency by explicitly attributing the analysis model and optimizing the reasoning path by using graph calculation, and improves the intelligence, performance and interpretability of multi-model collaborative analysis.

This invention discloses a method, system, computer equipment, and storage medium for optimizing the form of buildings in urban space. The method includes: acquiring geographic information data within a target area, performing parametric modeling to construct a first sample dataset and a first sample index set; constructing a sample control set based on the number of buildings in the first sample dataset; further processing the first sample dataset using the sample control set to construct a second sample dataset; calculating on the second sample dataset and calling the first sample index set to obtain relevant indicators for evaluating the building space environment, generating a second sample index set; performing genetic algorithm optimization on the sample control set, the second sample dataset, and the second sample index set to form a final optimization result dataset; and visually displaying the genetic optimization process and the final optimization result dataset. This invention can effectively provide targeted overall and local building space environment optimization suggestions for different plots of land.

The invention provides a puncture path planning method and system based on ray projection and collision detection, and the method comprises the steps: obtaining a 3D voxel data model of a to-be-punctured object, and carrying out the focus and organ segmentation of the 3D voxel data model according to a pre-trained organ segmentation model; generating uniformly distributed direction vectors from the center of a target focus in the segmented 3D voxel data model to a surrounding space by adopting a Fibonacci spherical sampling algorithm to obtain an initial path set; and performing collision detection on each path in the initial path set, calculating the length of each path passing the collision detection, and determining a candidate puncture path set according to an ascending sequence of the lengths of the paths in combination with a preset candidate threshold value. The technical problems of low reliability and low efficiency of puncture path planning in the prior art are effectively solved.

The present application relates to the technical field of intelligent tourism service, and particularly refers to a travel track planning system with AI intelligent analysis function. A hybrid intelligent algorithm of improved genetic algorithm + deep reinforcement learning is adopted to construct a multi-objective optimization model with user satisfaction, time cost, traffic cost and scenic spot popularity as the core, so as to realize integrated intelligent planning and dynamic self-adaptive adjustment of travel path, time allocation and scenic spot selection. Multi-modal data intelligent sensing and fusion technology: unified representation of heterogeneous data, realization of global perception of user demand and environmental information. Hybrid intelligent optimization algorithm: combination of improved genetic algorithm and deep reinforcement learning, improvement of multi-objective optimization efficiency and precision. Lightweight and efficient computing architecture: reduction of computing power consumption, support for mobile terminal and high concurrency scene for rapid response. The accuracy of personalized matching is more than 95%; real-time response to environmental changes, millisecond-level triggering of dynamic adjustment; reduction of computing resource consumption by 30%; support for multi-scenario and multi-user type self-adaptive adaptation.