205 results about "Constraint matrix" patented technology

The invention provides a digital project management method and system based on artificial intelligence, and relates to the technical field of artificial intelligence. Constructing a multi-level resource constraint matrix; generating a resource collaborative optimization configuration model by using a deep neural network; calculating a real-time scheduling weight coefficient; constructing a resource scheduling objective function; solving an optimal resource scheduling scheme by adopting an improved ant colony algorithm; inputting the optimal scheme into an intelligent cooperative controller for dynamic adjustment; and intelligent cooperative scheduling of power grid engineering construction resources is realized. According to the invention, the resource scheduling efficiency and accuracy are improved.

The invention relates to the field of power plant control, discloses a virtual power plant control method, system and equipment based on a neural network, and is used for solving the core problems of high data dependence, low topology safety and difficulty in multi-scale collaboration in traditional virtual power plant control. According to the virtual power plant control method based on the neural network, a correction instruction set, a joint estimation value and a topology constraint matrix are input into a neural network controller, and a cooperative control signal is output through singular perturbation decoupling of a fast-varying subsystem and a slow-varying subsystem. And the cooperative control signal is issued to the distributed power supply inverter, the energy storage converter and the intelligent switch, and meanwhile, an execution result is monitored in real time and fed back to the phase space reconstruction module, so that closed-loop control is formed. By constructing the Lyapunov candidate function and calculating the virtual damping coefficient, the transient stability, real-time persistent homologous analysis and topology self-healing instruction generation of the system are enhanced, and the self-healing capability and the fault-resistant capability of the system are improved.

The invention discloses a combinatorial optimization automatic modeling-oriented training data generation method and system, and the method comprises the steps: receiving a problem description text, extracting key information through semantic analysis and knowledge reasoning, and constructing a structured optimization problem representation; reading the structured representation, extracting a target function component from the binary label matrix, extracting a constraint function component from the constraint relation adjacent matrix, extracting a variable definition component from the variable dependency matrix, and integrating the components to form a model component set; a value interval parameter is generated for the variable, a coefficient parameter is generated for the constraint matrix, a weight parameter is generated for the target function, and a parameterized model instance is obtained; and applying corresponding templates to scene elements, variables and constraint descriptions to generate a problem description text. Through the systematic information extraction and parameter generation method, automatic generation of high-quality training data is realized, and the diversity and practicability of the data are improved.

The invention discloses a method suitable for adding a control shunt under multiple scenes in a demand response execution process, and the method comprises the steps: obtaining real-time load data, historical load data, environment parameter data and user behavior data, and carrying out the processing through a tensor decomposition method and a support vector machine, and obtaining a scene feature vector and a scene type identifier; real-time load data and system constraint data are combined, a fuzzy comprehensive evaluation method and a graph neural network are adopted for processing, and a shunt response capability matrix and a control constraint matrix are obtained; processing by adopting a multi-objective optimization method to obtain an optimization objective function set, a weight coefficient matrix and a constraint condition set; and processing by adopting a genetic algorithm and a dynamic programming method to obtain a control strategy matrix and an execution time sequence vector. According to the invention, accurate control and dynamic optimization in the demand response process can be realized, and the execution efficiency and reliability of the control strategy are improved.

The invention relates to the technical field of oil and gas equipment operation control, in particular to an oil and gas equipment operation parameter self-adaptive fine tuning method and system, and the method comprises the steps: constructing an operation parameter optimization library driven by reinforcement learning, defining an action space containing equipment types, working condition modes and key parameter combinations, predicting accuracy, response efficiency and safety compliance are optimized in combination with a multi-target reward function, an optimized instruction set is generated, safety perception mixing precision fine adjustment is carried out in parallel, calculation precision is configured in a layered mode, errors are monitored in real time, a high-precision mode is switched if the precision exceeds the limit, and a reservoir engineering equation mechanism constraint matrix is embedded to guide parameter updating. A generative adversarial network is utilized to synthesize fault data, a Darcy seepage causal engine is integrated to correct a loss function, the system comprises an action space construction unit, a precision dynamic scheduling unit, a mechanism constraint embedding unit and a data causal cooperation unit, and the method and the system realize data-mechanism fusion, balance precision and real-time performance, and improve equipment operation safety and adaptability.

The embodiment of the invention discloses a heating and ventilation control method and device based on reinforcement learning and a medium, and relates to the technical field of heating and ventilation control, and the method comprises the steps: determining predicted temperature data corresponding to a target building through a pre-constructed Mamba time sequence prediction model, and carrying out the reinforcement learning pre-training through the predicted temperature data and a preset space-time constraint matrix, determining an initial heating and ventilation control strategy; performing initial regulation and control on a heating ventilation air conditioning system in the target building according to the initial heating ventilation control strategy, and collecting real-time building data corresponding to the target building; according to real-time building data, performing dynamic partitioning on a target building, determining a plurality of dynamic control partitions, constructing partition state space description based on the dynamic control partitions and the space-time constraint matrix, and performing targeted online reinforcement learning training through the partition state space description by using a progressive exploration strategy, so as to improve the training efficiency. And generating a heating and ventilation control strategy corresponding to the target building so as to control the target building through the heating and ventilation control strategy.

The invention discloses an efficient medicine logistics order scheduling and distribution method and system, and relates to the technical field of medicine logistics, and the method comprises the steps: constructing a multi-modal medicine feature extraction module, and outputting an order constraint matrix; establishing an adaptive space-time distribution network according to the order constraint matrix, and performing dynamic grid division on a distribution area to generate a multi-level distribution area model; constructing a double-layer heterogeneous graph neural network, and generating a distribution path planning candidate scheme set considering drug characteristics; defining a state space and an action space, constructing a dual-target reward function, and carrying out iterative training to obtain a distribution scheduling strategy model; and aggregating multi-region distribution empirical data by adopting a federated learning framework, and periodically updating the scheduling strategy model based on a differential privacy mechanism. According to the method, the multi-modal drug feature extraction module is constructed, and the image, text and storage condition information of the drug are fused, so that the drug storage requirement and the distribution limitation condition can be identified more accurately, and the identification accuracy of the distribution constraint is improved.

The invention provides a digital factory flexible production scheduling system based on MES, and relates to the technical field of digital management, and the method comprises the steps: capturing an order change instruction in real time through an integrated interface of the MES and ERP, and converting the order change instruction into a standard chemical order data stream; based on the structured data object, fusing the equipment real-time sensing data with a pre-stored process constraint matrix and dynamic material topological data, and generating a three-layer real-time resource model containing an equipment state vector, the process constraint matrix and the material topological data; layered optimization is executed based on a three-layer real-time resource model, in the first layer of optimization, an equipment state vector and a process constraint matrix are used as hard constraints, and an initial feasible solution set is generated; and the second-layer optimization executes multi-target evaluation on the initial feasible solution set to obtain a non-dominated solution set as a production scheduling plan. According to the invention, order-resource-execution full-process intelligent collaboration is realized.

The invention relates to the technical field of course arrangement systems, and particularly discloses an automatic course arrangement system based on an optimization algorithm, and the system comprises a training plan management module which is used for inputting training plan information according to teams, creating a training plan based on the training plan information, and modifying and deleting the training plan information; the course management module is used for providing course information input and maintenance functions and establishing course version management according to different years; the automatic course arrangement module is used for arranging courses by using an automatic course arrangement algorithm based on the course information, and the automatic course arrangement algorithm comprises the steps of obtaining the course information from the course management module, constructing a demand set and constructing a resource set, and the resource set comprises a class time set and a teaching field set; and constructing a mapping constraint matrix: M '* N' matrix, M 'being the number of elements in the demand set, N' being the number of elements in the resource set, and M 'being less than or equal to N', and based on the demand set and the resource set, performing course arrangement by using the mapping constraint matrix.

The invention belongs to the technical field of artificial intelligence, and discloses an artificial intelligence model training resource adaptive distribution system. The method comprises the following steps: acquiring and calculating graph structure data and hardware resource state data in real time, and calculating a data reuse rate and generating a candidate operator fusion scheme by constructing an operator execution time sequence constraint matrix and identifying an operator cluster of data locality characteristics; a resource competition hotspot prediction mechanism is introduced, memory bandwidth occupation fluctuation characteristics are analyzed, a resource conflict probability is calculated for a fusion scheme, and a dynamic balance optimization model of fusion income and resource conflicts is constructed. An optimal operator fusion decision sequence and a resource allocation strategy are generated through iterative solution, and accurate dynamic adjustment of computing resources in the training process is achieved. The training efficiency and the resource utilization rate are improved, the energy consumption is reduced, and the system stability is enhanced.

The invention discloses a method and a system for designing network control by utilizing a genetic algorithm and self-adaptive event triggering. The method comprises the following steps of: establishing a state space model and an observer model of a networked system and a mathematical model of transmission data which is possibly subjected to spoofing attack in a network in the system; designing a Lyapunov function, and designing a controller constraint condition matrix theta capable of realizing robust stability performance of the system; performing decoupling processing on the theta matrix, and converting the theta matrix into an LMI form; the designed controller conditions are solved in computer software, controller parameters meeting the system performance are calculated, and control of the control system under the event trigger control strategy is achieved; a designed controller is combined with a genetic algorithm, genetic algorithm parameters are set according to an obtained initial solution, a gamma minimum value is obtained according to optimized parameters needed by the system, a self-adaptive event trigger control strategy is adopted, more flexible and more reliable safety control can be achieved, and the method is suitable for various different types of control systems and application scenes.

The invention discloses a high boundary sensitivity three-dimensional inversion method based on an electromagnetic gradient constraint matrix, and belongs to the technical field of electromagnetic signal inversion, and the method comprises the steps: constructing an initial inversion model and a target function, and introducing a model roughness item based on electromagnetic gradient constraint into the target function; calculating the electromagnetic gradient anomaly response at each measuring point under each measuring frequency, obtaining an electromagnetic gradient anomaly response vector of each measuring point, performing normalization processing, combining into a matrix, obtaining an overall normalized observation gradient anomaly matrix, and constructing an electromagnetic gradient constraint matrix in a data space; converting the electromagnetic gradient constraint matrix in the data space into a model space through a frequency-depth weighted mapping matrix; and solving the target function by adopting an iterative optimization algorithm until the model converges. According to the method, the gradient constraint matrix based on the electromagnetic field is introduced, the dynamic adjustment of the change amplitude weight of each grid unit in the roughness item of the model is realized, and the target boundary identification precision is improved.

The invention relates to a path planning method and system for navigation guidance of a low-altitude aircraft, and the method comprises the steps: calculating a probability density value of pre-processed prior flight data based on kernel density estimation, mapping the normalized probability density value to a grid map of a rasterized environment model, generating a flight path safety experience distribution map, and carrying out the navigation guidance of the low-altitude aircraft. And expanding the boundary of the obstacle area based on the safety distance constraint matrix, generating a restricted area matrix, generating an initial path according to the bidirectional A *-KDE algorithm cost function, the flight line safety experience distribution map and the restricted area matrix, removing redundant nodes from the initial path, and carrying out smoothing processing to obtain a flight route. The flight route is obtained by using the prior flight data, the deviation between the flight route and the actual navigation path can be reduced, the obstacle area boundary is expanded based on the safety distance constraint matrix, the obstacle safety distance is fully considered, and the risk that the low-altitude aircraft collides with the obstacle can be reduced.

The invention discloses a risk knowledge graph construction and intelligent early warning method based on artificial intelligence, and the method comprises the following steps: collecting and preprocessing multi-source risk related data, and generating a composite input data set; constructing an enhanced TabPFN structure and introducing a risk logic rule constraint matrix to generate a risk prediction result set; mapping the risk prediction result set to a knowledge graph entity node and relation set to generate a risk knowledge graph structure; the method comprises the following steps: introducing Sheaf Neural Networks into a risk knowledge graph structure, and generating a consistency parameter set; the knowledge graph structure is updated, and risk knowledge graph enhanced representation is generated; and performing reasoning in combination with the risk prediction result set and the consistency parameter set, and outputting an intelligent early warning result set. According to the method, table data modeling and graph consistency propagation are fused, and the risk prediction accuracy and the early warning reliability are improved.

The invention relates to the technical field of intelligent construction, and discloses a reinforcement method, device and equipment based on a reinforcement optimization model and a storage medium, which are used for improving the generation efficiency of a reinforcement scheme and giving consideration to the economical efficiency and personalized requirements of the reinforcement scheme. The reinforcement optimization model-based reinforcement method comprises the following steps of: obtaining each reinforcement constraint parameter and a to-be-selected reinforcement set of a target business scene; performing dynamic configuration on a preset reinforcement optimization model based on each reinforcement constraint parameter and the to-be-selected reinforcement set to obtain a reinforcement optimization model corresponding to each constraint matrix set; integer programming is carried out through the reinforcement optimization models corresponding to the constraint matrix sets, a reinforcement scheme alternative list is obtained, and the reinforcement scheme alternative list comprises all candidate reinforcement schemes meeting the requirement for minimization of the constraint matrix sets and the target function; and determining a target reinforcement scheme in the reinforcement scheme alternative list according to each screening condition preset by the target business scene.

The embodiment of the invention discloses a monocular depth estimation method and device, electronic equipment and a storage medium, and relates to the technical field of multi-modal computer vision and natural language processing.The method comprises the steps that multi-scale visual features are extracted through a visual encoder, and scene semantic description is generated in combination with image and text description; semantic categories in scene semantic description are extracted through a large language model, and a semantic prototype is formed and mapped into a high-dimensional feature vector to serve as a semantic center; calculating the visual similarity between each pixel and the visual center and the semantic matching degree between each pixel and the semantic center, performing weighted fusion to obtain a pixel group, and mapping an object space relation in the RGB image into a structured constraint matrix according to scene semantic description; and dynamically fusing visual, semantic and geometric information by adopting a cross-modal attention mechanism to generate a depth map. According to the method, the problems of insufficient semantic understanding, lack of structural constraint and superficial layer of multi-modal fusion in the prior art are solved, and the depth estimation precision is remarkably improved.

The invention discloses a deep learning algorithm-based hydroelectric generating set maintenance disassembly planning method, and aims to solve the problems of high difficulty, low efficiency, resource waste and the like of large-scale hydroelectric generating set maintenance work. According to an original drawing, set equipment is subjected to three-dimensional modeling through SolidWorks software, and a three-dimensional visual model library containing equipment, maintenance tools and instruments and meters is constructed; then, determining disassembly information of the equipment to be disassembled, wherein the disassembly information comprises a disassembly priority sequence, a required tool and disassembly time; establishing a geometric constraint relationship between the equipment parts through the directed constraint graph and the constraint matrix; secondly, a disassembling sequence evaluation function is constructed by integrating quantitative indexes such as disassembling direction change, tool replacement, space movement distance and crane use conditions; finally, a deep learning algorithm is used for automatically optimizing and solving an optimal maintenance disassembly sequence; the maintenance efficiency of the hydroelectric generating set is effectively improved, time loss and resource waste are reduced, and the operation safety and efficiency of the hydroelectric generating set are improved.

The invention provides an AI-based old community reconstruction terrain simulation display method and system, and relates to the field of terrain simulation, and the method comprises the steps: obtaining the multi-source high-precision terrain data of an old community, and carrying out the cleaning and fusion; according to the topographic data set, identifying topographic key features and classifying land cover types in combination with a semantic segmentation technology so as to obtain a digital topographic feature map with semantic tags; resident investigation and survey data, policy specifications and economic cost constraints are obtained, constraint conditions are quantified, and a structured demand constraint matrix is generated; constructing a multi-objective optimization model, and iteratively generating and verifying a terrain reconstruction scheme set by adopting deep reinforcement learning; an immersive terrain simulation environment is constructed, a scheme is adjusted in real time, user behavior data is recorded, and a final optimization scheme is output; and performing visual achievement and dynamic demonstration to obtain a multi-terminal compatible transformation scheme package. According to the method, the defect that intelligent tool application in the prior art flows in the form and cannot be deeply combined with a core transformation link is overcome.

The invention relates to the crossing field of artificial intelligence technology and bioinformatics, and discloses a pig feed efficiency prediction model and system based on multi-omics data. Modulating a neural differential equation which runs on a priori knowledge graph and is realized by a graph neural network by using the matrix so as to solve and generate a continuous evolution trajectory of an individual physiological state; and finally, aggregating the tracks, combining the constraint matrix, and outputting a feed efficiency prediction value through a second preset model. The invention further provides a corresponding prediction system which comprises a static constraint module, a dynamic core module and a prediction module. According to the method, static genetic constraint and dynamic physiological process simulation are combined, genetic differences among different individuals can be reflected, and the biological consistency and individualization precision of a prediction model are improved.

The invention relates to the technical field of data processing, and discloses a railway construction data processing method and system. The method comprises the steps of performing semantic annotation on track laying, line measurement and construction monitoring data through RDF semantic association to obtain a semantic data set; setting smoothness constraint screening qualified data according to the gauge deviation and the elevation deviation; qualified data are input into an improved firework algorithm, and track geometric parameters are optimized through a curvature self-adaptive explosion mechanism; adopting improved Kriging interpolation to complement the track center line, the track surface elevation and the track gauge change data; and establishing a construction quality constraint matrix, and cooperatively adjusting track line shape, elevation control and track gauge precision through a sequential quadratic programming algorithm. According to the method, the technical problems of lack of multi-source data semantic association, insufficient professional algorithm adaptability and insufficient parameter collaborative optimization capability in railway construction are solved.

The invention relates to the technical field of satellite internet, and discloses a multi-satellite cooperative beam hopping resource allocation method and system based on interference avoidance, and the method comprises the steps: 1, constructing a multi-satellite beam hopping cooperative coverage interference analysis model; 2, modeling is carried out on a multi-satellite-hopping-beam multi-dimensional resource scheduling problem; 3, defining interference between spatial isolation measurement hopping beam patterns, constructing an interference constraint matrix, determining a shortest distance threshold value through a carrier-to-interference ratio threshold value, deducing an interference model in a same-rail scene and a different-rail scene, and bringing the carrier-to-interference ratio threshold value into optimization problem constraint; step 4, carrying out graph structure modeling based on GAT-PPO; 5, an Actor decision layer outputs a beam scheduling probability matrix and a power distribution vector in a double-branch mode, an action space is subjected to multiple constraints, and a reward function balances throughput and interference suppression; step 6, adopting a centralized training-distributed execution framework; according to the method, interference model analysis of multi-satellite cooperative coverage based on interference avoidance is constructed, and real-time analysis and scheduling of the interference condition are carried out.

The embodiment of the invention discloses a GNSS (Global Navigation Satellite System) dynamic positioning method, device and equipment and a storage medium, and relates to the technical field of navigation positioning, and the method comprises the following steps: determining an estimation state vector of a signal receiving end in a previous epoch and an estimation state vector of a current epoch based on GNSS observation data; multiplying the estimated state vector of the current epoch by a preset constraint matrix to obtain a constraint parameter, comparing the constraint parameter with a preset constraint condition threshold, and if the constraint parameter of the current epoch is greater than the preset constraint condition threshold and the constraint parameters of at most n continuous epochs are greater than the preset constraint condition threshold, constructing a virtual observation equation, and calculating to obtain a prediction state vector of the signal receiving end in the current epoch, and outputting a positioning result. According to the method, a possible output abnormal result is solved by utilizing extended Kalman filtering iteration in a complex environment, and dynamic constraint condition adjustment is realized by introducing inequality constraints.

The invention discloses a heterogeneous graph-based multi-modal teaching video abstract generation method. The method comprises the steps of obtaining a plurality of video samples to form a training set; establishing a multi-modal abstract generation model, training by using a training set, and executing the following operations by the model: respectively inputting a video frame sequence and a sentence sequence into a visual feature extraction model and a language model to obtain a visual feature vector set and a text feature vector set to form multi-modal feature representation; initializing an adjacent matrix; performing Hadamard product on the intra-modal constraint matrix, the inter-modal constraint matrix and the adjacent matrix to obtain an optimized heterogeneous graph; executing a double-stage fusion strategy; and screening a key video frame node set and a key sentence node set by using multi-modal unified representation output by the trained multi-modal abstract generation model, and correspondingly reserving a connection relationship in the optimized heterogeneous graph as a sub-adjacency matrix to obtain a multi-modal abstract graph. According to the method, teaching video abstracts with consistent semantics and rich contents can be generated, and the generalization ability is high.

The invention discloses a surveying and mapping system and method for outdoor geographic surveying and mapping, and particularly relates to the field of outdoor geographic surveying and mapping, and the system comprises a preparation module, a constraint module, a model optimization module, a space-time registration module, a verification module and an evaluation module. The preparation module is used for deploying an unmanned aerial vehicle LiDAR scanning unit, a ground mobile surveying and mapping module and a distributed base station in a target area, constructing a space-time synchronous sensor network, and establishing a dynamic three-dimensional reference framework with a timestamp based on a measurement area control point; the constraint module is used for constructing a multi-threshold constraint matrix according to the terrain roughness, the vegetation coverage and the sensor performance parameters; the model optimization module is used for establishing a two-dimensional optimization model integrating spatial precision and data timeliness and forming a dynamic surveying and mapping decision function; according to the method, by introducing the dynamic weight and G-N iterative optimization, the root mean square error of registration is reduced, the convergence times are reduced, and the problems that multi-sensor registration is prone to local optimum and low in efficiency are solved.

The invention discloses a power distribution system unit cluster net rack extension planning method and device based on reliability explicit constraint matrix reduction, and the method comprises the following steps: firstly, obtaining the system data of a to-be-planned region, and determining related parameters; secondly, a reliability explicit calculation method capable of reducing the matrix scale is adopted, an MILP model of multi-contact power distribution system unit cluster expansion planning is constructed, and an objective function calculation expression and various constraints are provided; comprising power flow constraints and network topology constraints considering network reconstruction under normal and fault conditions, virtual topology constraints under normal and fault conditions, and reliability index calculation equations and constraints; and finally, based on the input parameters, solving the MILP model by using a solver to obtain main line and tie line planning results of the to-be-planned region in each stage in the future. Aiming at the medium-voltage power distribution network and considering the reliability requirement of the planning area, the invention provides the multi-stage planning method for the power supply unit cluster in the power distribution network taking a multi-contact form as a target networking structure, an investment scheme can be determined in each planning stage, and the reliability and the economical efficiency of the planning are favorably improved.

The invention discloses a semi-supervised image clustering method based on adaptive graph learning, and the method comprises the steps: iteratively updating a sparse representation matrix and a paired constraint matrix until the value of a target function is unchanged or reaches a maximum iteration number; taking the updated pairwise constraint matrix as an input similar matrix, calling a spectral clustering algorithm to divide image sample data into a plurality of sample groups to finish clustering output; wherein the objective function is a weighted sum of a propagation consistency error based on a sparse representation matrix and a paired constraint matrix, an image sample data reconstruction error based on the sparse representation matrix, an L1 norm of the sparse representation matrix and a matrix correlation error based on the sparse representation matrix and the paired constraint matrix. The invention further discloses a system, a computer storage medium and a program for implementing the method. According to the method, the problem of separation of similar graph learning and constraint propagation can be solved, and the image clustering performance is improved.

The invention discloses an autonomous system organization mapping method and device based on a semi-supervised clustering algorithm, and the method comprises the steps: extracting the original data information of an autonomous system from a preset dimension, and carrying out the preprocessing of the original data information; integrating the preprocessed original data information to generate an autonomous system basic feature matrix and an autonomous system key feature constraint matrix; according to an SC-MP I algorithm, performing multi-round iterative clustering on the autonomous system basic feature matrix and the autonomous system key feature constraint matrix, and determining the number of clustered class clusters in a binary approximation mode to obtain a plurality of class clusters; and according to the characteristic mode of the autonomous system in each class cluster, determining the organization name and code of the class cluster, and obtaining a final autonomous system-organization mapping relationship. It is ensured that the data dimension is wide enough; the model can be easily deployed to a stable production environment, and excessive manual intervention on data is not needed; and the flexibility of the clustering mapping process is improved.

The invention provides a reactor nuclide density prediction method, a reactor nuclide density prediction system and electronic equipment. The method comprises the following steps: constructing a snapshot matrix of a reactor nuclide number density sequence; using a power function to constrain nuclides in the snapshot matrix to obtain a constraint matrix; wherein the index of the power function is a score; performing DMD prediction on the constraint matrix to obtain nuclide density with constraint; and reducing the nuclide density with constraints according to the power function, and determining the nuclide density according to a reduction result. According to the method, physical driving calculation and data driving modeling are combined, a constraint function related to nuclide behaviors is introduced into nuclide evolution snapshot data, and through modal extraction and inverse transformation recovery, the capturing capability of future nuclide behaviors is improved, and the prediction precision of the number density of reactor nuclides is improved. The DMD method based on the snapshot constraint can more accurately predict the nuclide number density evolution trend at the future moment, and has the advantages of stronger generalization ability and precision.

The invention discloses a collaborative decision-making method and device based on a spatio-temporal game, equipment and a medium. Road topology information, vehicle driving state information and road emergency information uploaded by a target vehicle are converted to generate a path distance threshold value and dynamic obstacle probability distribution, and a multi-dimensional constraint matrix is constructed in combination with the path distance threshold value and the dynamic obstacle probability distribution; with the maximum coverage of the driving area and the minimization of the total avoidance driving distance of the multiple vehicles in the driving area as optimization targets, the multi-dimensional constraint matrix and preset posterior information are combined, and the target path strategy amplitude is simulated and calculated; and sending the target path strategy amplitude and the multi-dimensional constraint matrix to the target vehicle, so that the target vehicle generates a path strategy at the next moment based on the current path strategy, the dynamic environment state acquired in real time and the target path strategy amplitude under the indication of the multi-dimensional constraint matrix. Therefore, the vehicle driving safety and the travel efficiency are improved.

The present invention discloses a flying thorn crystal path planning method and device, including initializing the coordinates of multiple control points of the flying thorn crystal to generate multiple initial control point coordinates; constructing a kinematic constraint matrix and a control point basis function matrix based on the coordinates of each initial control point and preset massive transfer motion data; using a preset solution algorithm to determine the target control order based on the kinematic constraint matrix, the control point basis function matrix and the coordinates of each initial control point; determining the target Bezier motion curve of the flying thorn crystal based on the target control order, the kinematic constraint matrix and the control point basis function matrix; solving the technical problem that the existing flying thorn crystal path planning method causes the obtained Bezier path to be too complex.