308 results about "Sequence model" patented technology

The invention discloses a welded pipe conveying abnormity prediction method and system based on large model reasoning, and aims to solve the problems that multi-source data is difficult to align, cross-station false correlation is caused, prediction lacks executable positioning and time sequence, and linkage control reliability is insufficient. Event alignment is carried out by taking a controller edge signal and an encoder zero position as time anchor points, a production line topology semantic graph containing time delay, capacity and interlocking attributes is constructed, and topology reachability and physical time delay constraints are applied in a self-attention long sequence model to carry out multi-step rolling prediction. And outputting a risk probability, refining the risk probability to spatial positioning of a roller way section or a shaft and the minimum executable intervention time, and generating a risk interval in combination with uncertainty estimation and calibration so as to drive an upstream beat self-adaptive speed reduction, shunting or stopping strategy. The technical effects of improving accuracy and interpretability, reducing false alarm and missing alarm, ensuring that linkage can be executed in advance and meeting edge time delay budget are achieved.

The invention discloses a composite structure damage form monitoring method and system based on deep learning, and the method comprises the following steps: collecting multi-source monitoring data of a composite structure in a loaded state, and carrying out the preprocessing; reconstructing a damage evolution trajectory in a high-dimensional phase space by adopting a delay coordinate embedding method, and executing dimension reduction to generate a chaotic dynamics low-dimensional trajectory; extracting singular attractor features, and generating a singular attractor feature set; carrying out sequence modeling through an improved Linformer damage identification network, and generating a prediction vector; training an improved Linformer damage identification network based on the prediction vector, and introducing nonlinear dynamic constraints to generate a damage identification network of the nonlinear dynamic constraints; and performing damage form classification and damage evolution prediction. According to the method, dynamics and deep learning are fused, composite structure damage monitoring is achieved, and the method has the advantages of being high in accuracy, high in stability and reliable in early warning.

The invention discloses an airport hub construction intelligent regulation and control method and system based on BIM + 5G, and relates to the technical field of construction scheduling optimization, and the method comprises the steps: collecting on-site real-time data to construct a path construction sequence model, constructing a dynamic construction state set with consistent space and time sequence through component coding and semantic attribute mapping, and constructing a dynamic construction state set with consistent time sequence; and constructing a minimum disturbance optimization algorithm of four-dimensional disturbance cost based on the construction disturbance mapping graph, outputting procedure sequence adjustment, resource rearrangement, path decoupling and environment avoidance intervention suggestions, and tracking a construction response state in real time based on an intervention execution feedback mechanism. According to the method, unified modeling of construction plans, resource allocation and green indexes is achieved by constructing a ternary structure and a construction disturbance mapping graph, the field state is dynamically collected in combination with a 5G and edge sensing system, process abnormity and resource conflicts are accurately recognized, an efficient and executable regulation and control strategy is generated based on a multi-target disturbance optimization algorithm, and the efficiency and the reliability of the system are improved. And the intelligence, responsiveness and energy-saving level of the construction process are obviously improved.

The invention provides an industrial equipment residual service life prediction method based on a DMM-JA model, and relates to the technical field of industrial equipment predictive maintenance, and the DMM-JA model comprises a dynamic bimodal fusion and multi-scale feature extraction module DBF-MSFEModule, an LSTM-Mama mixed sequence modeling module, a jump perception attention module and an output layer. The method comprises the following steps: preprocessing bimodal sensing data of industrial equipment; the preprocessed bimodal sensing data is processed through a dynamic bimodal fusion and multi-scale feature extraction module DBF-MSFEModule, and multi-scale fusion features are obtained; the multi-scale fusion features are input into an LSTM-Mamba mixed sequence modeling module, and joint time sequence features are obtained; the joint time sequence features are corrected through a jump perception attention module, and robustness features are obtained; and inputting the robustness characteristics into an output layer to obtain an RUL prediction result of the industrial equipment. Key features in the equipment degradation process can be accurately captured, and the accuracy of residual service life prediction is improved.

The invention discloses a multi-source heterogeneous engineering monitoring data fusion method based on deep learning, and relates to the technical field of engineering monitoring and artificial intelligence crossing. Collecting multi-source heterogeneous time series data; inputting the multi-source heterogeneous time sequence data into a dynamic space-time alignment module, performing time sequence alignment to obtain alignment data, and extracting time sequence characteristics of the alignment data through a sequence-to-sequence model; constructing a sensor topological graph through an adjacent matrix based on the sensor data, determining node features of the multi-source heterogeneous time series data through a statistical feature method, and inputting the sensor topological graph and the node features into a graph convolutional network for processing to obtain spatial features; inputting the structural crack image sequence data into the residual convolutional network to extract visual semantic features; and dynamically fusing the time sequence features, the spatial features and the visual semantic features through a space-time cross attention mechanism to obtain fused features. According to the method, the compatibility of engineering monitoring data fusion can be improved.

The invention relates to a big data security management system, and provides a security management system covering a whole life cycle aiming at the problems of untrusted source end, link leakage, centralized storage of single points, extensive authorization, disposal lag and the like. The system comprises an acquisition security module, a transmission encryption module, a storage security module, an access control module, a threat detection module, a situation awareness module, a traceability module and an emergency response module. A session basis is generated through multi-factor authentication, a dynamic key is derived according to time slices, and data fragments are encrypted one by one; distributed storage is adopted, and metadata is chained to be non-tampered; implementing fine-grained authorization by taking the attribute as a core; utilizing a sequence model linkage knowledge graph to identify abnormity and calculate a risk index; and when the threshold is exceeded, automatically reconstructing a log chain and executing isolation, alarm or recording. According to the system, trusted acquisition, confidential transmission, traceable storage, fine authorization and automatic disposal are realized, and the safety and compliance are remarkably improved.

The invention discloses a landslide image instance segmentation method based on a dual adaptation mechanism, relates to the technical field of image processing, and ensures that a model can have a better effect and numerical stability on data from different sources through a complete process from multi-source data collection to data normalization processing. The designed model is based on a multi-scale state alignment mechanism, in the forward process of the model, exponential moving average fusion is carried out on feature information in the same level, transmission fusion is carried out on feature information of different levels, feature robustness is enhanced, and error accumulation caused by local deviation is reduced. A meta-context incremental learning mechanism is designed, and input data are dynamically converted into a series of key value vector sequences. In the reasoning process of the model, data distribution different from a training domain is dynamically recognized, a gradient descent process is implicitly executed according to the characteristics of data, and model parameters are finely adjusted, so that the characterization capability is greatly improved, and efficient and robust instance segmentation is realized.

The invention discloses a bill recognition method and system based on artificial intelligence image enhancement, and relates to the field of image recognition. The method comprises the following steps: S1, extracting multi-dimensional quality features based on an original image of a bill and calculating a scene consistency factor; s2, adjusting a global enhancement weight according to a scene consistency factor, adjusting a local gain in combination with a detail fidelity factor, and performing adaptive enhancement on the original image to generate an enhanced image; s3, establishing an optical flow field model to analyze geometric deformation of the enhanced image, and performing adaptive correction in combination with local deformation rigidity to generate a corrected image; and S4, analyzing gradient features and character confidence of the corrected image, extracting a candidate character region, and performing context recognition by adopting a sequence model to obtain a text field set. Scene complexity is quantified through multi-dimensional quality features, and detail fidelity self-adaptive enhancement and optical flow deformation correction of high-frequency character distinguishing are combined, so that bill character definition and recognition accuracy are remarkably improved.

The invention relates to the technical field of computer processing, in particular to a Kafka cluster configuration parameter adjusting method and device, equipment and a medium, and is used for relieving problems caused by a fixed change means of code modification. The method comprises the following steps: according to related historical data of a Kafka cluster, predicting a first predicted load index in a future time period through a first time sequence model, and predicting a second predicted load index in the future time period through a second time sequence model; weighting the first predicted load indicator; weighting the second predicted load index; determining a predicted load index according to the weighted first predicted load index and the weighted second predicted load index; determining a plurality of first candidate adjustment actions according to the predicted load index; selecting a first candidate adjustment action from the plurality of first candidate adjustment actions as a first adjustment action; and adjusting a partition allocation index and a copy allocation index of the Kafka cluster configuration parameters by using the first adjustment action.

Aiming at the problems of low efficiency, strong subjectivity, insufficient modeling ability, complex hyperspectral data noise, weak waxiness spectrum difference and the like of a traditional rice grain waxiness discrimination method, the invention provides a hyperspectral rice grain waxiness discrimination method based on multi-branch collaborative modeling. The method comprises the following steps: S1, acquiring glutinous and non-glutinous rice grain images by using a hyperspectral imaging system to obtain spectral data; s2, preprocessing spectral data through a combined method of SG smoothing, an asymmetric weighted penalty least square method and multivariate scatter correction to reduce noise and interference; s3, constructing a multi-branch modeling architecture which comprises a CNN local feature extraction module, an SRU spectrum sequence modeling module and a HorNet global high-order modeling module, and outputting a discrimination result through a classifier after multi-branch features are subjected to fusion and pooling attention weighting; and S4, evaluating the performance. According to the method, high-precision lossless discrimination of the waxiness is realized, and a technical support is provided for germplasm screening and quality evaluation in rice breeding.

The invention provides a residual life lightweight prediction method and system based on feature decoupling and sparse optimization, and the method comprises the steps: efficiently extracting equipment degradation features through a double-branch architecture: capturing a time sequence degradation law through a GRU network, and generating a deep feature h1 in combination with an attention mechanism, one branch directly extracts a key feature h2 from an original sensor signal through a sparse attention mechanism, the other branch directly extracts a key feature h2 from the original sensor signal through a sparse attention mechanism, then two feature vectors are fused and processed through a lightweight decoder, and finally a residual life prediction value is output. The balance between precision and calculation efficiency is realized through feature decoupling and sparse optimization, and the method is particularly suitable for deployment in an edge calculation environment with limited resources.

The invention provides a phytoplankton chromatography sequence identification method and a phytoplankton chromatography sequence model building method, and belongs to the technical field of image enhancement identification. The method comprises the following steps: firstly, acquiring microscopic chromatography sequence data of phytoplankton, performing view field extraction and serialization recombination, and constructing a three-dimensional data set; then, constructing a three-dimensional recognition model containing physical perception and a sequence aggregation mechanism, extracting single-frame semantic features by the model by adopting a parameter-shared twin network, and introducing a physical definition prior module to calculate a space-frequency domain quality score of a slice; secondly, designing a deep perception sequence aggregation module, and adaptively aggregating key features of a high signal-to-noise ratio by taking definition scores as gating signals and combining spatial context information between slices; and finally, training and optimizing the model based on the image-level weak supervision label to obtain an optimal model. According to the method, the problems of information truncation and out-of-focus noise interference caused by extremely shallow depth of field of high-power microscopic imaging are solved, and full-depth-of-field stereoscopic perception can be realized under the condition that frame-by-frame fine labeling is not needed.

The invention belongs to the technical field of artificial intelligence and multi-modal emotion calculation, and discloses a multi-modal emotion recognition method based on a Mama state space model and cross-modal self-distillation. Through the organic combination of the efficient sequence modeling capability of the Mamba state space model and the knowledge sharing mechanism of cross-modal self-distillation, the advantages of the state space model in the aspects of time sequence modeling and calculation efficiency are fully played, and meanwhile, the limitation of a single model architecture is made up through a cross-modal attention mechanism; the technical bottlenecks of an existing multi-modal emotion recognition method in the aspects of long sequence processing efficiency, cross-modal information fusion and knowledge transfer sufficiency are effectively solved, and an efficient and reliable technical solution is provided for further development and practical application of the multi-modal emotion recognition technology.

The invention discloses a neural signal-based wounded rehabilitation effect evaluation model construction method, and relates to the technical field of medical rehabilitation, and the method comprises the steps: synchronously collecting electroencephalogram, myoelectricity and motion parameters, extracting multi-source features to construct feature vectors corresponding to training actions, and according to the feature vector data of multiple training actions of a wounded, constructing a neural signal-based wounded rehabilitation effect evaluation model; and capturing dynamic changes of neural signals and action control ability in the training action sequence based on the sequence model, and constructing an evaluation model. According to the invention, time-dependent learning is carried out on the corresponding characteristics of each training action by using the sequence model, dynamic changes of neural signals and action control ability along with the training actions can be captured, an improvement trend in a rehabilitation process is embodied, and an evaluation model aiming at an action training effect is constructed; the action indexes output by the evaluation model can reflect the instant effect and gradual improvement condition of each action in training, and help to identify rehabilitation inflection points and training bottlenecks.

The invention relates to the technical field of knowledge tracking, and discloses a graph enhanced double-memory collaborative knowledge tracking model based on an ACT-R cognitive architecture. Comprising a static knowledge structure coding module based on hypergraph projection, a batch-level dynamic learning track construction and coding module, a cross-graph gating fusion mechanism, a sequence modeling module and an expert hybrid prediction module. According to the method, long-term stable structured semantic association between concepts in declarative memory is modeled through a static knowledge structure diagram, a dynamic learning trajectory diagram based on batch reconstruction is designed to accurately capture an evolution rule of a behavior sequence in programmed memory, and on the basis, a cross-diagram gating fusion mechanism and a hybrid expert mechanism are introduced, so that the evolution rule of the behavior sequence in the programmed memory is accurately captured. And self-adaptive fusion and multi-path decision of double-graph features are realized.

The invention provides a self-adaptive weighted hybrid modeling method and system for data drift sensing. The method comprises the following steps: acquiring multi-dimensional time series data and performing feature interaction analysis and screening to generate a fusion factor set; inputting the fusion factor set into a mixed structure comprising at least one ensemble learning model and at least one sequence model for training; based on the verification set and the dynamic evaluation indexes, determining fusion weights of all models in the mixed structure, and constructing a dynamic weighted mixed model; and setting a data distribution drift detection mechanism, comparing the distribution difference between a current data window and a historical reference data set, and automatically starting a retraining process of the hybrid structure to update the model when the difference reaches a trigger condition. According to the method, through cooperation of data drift perception and an adaptive weighting mechanism, the problems that an existing hybrid model is rigid in fusion strategy and lags behind a retraining mechanism are solved, and the robustness and long-term effectiveness of the model in a non-stationary data stream are remarkably improved.

The invention discloses a road and bridge construction progress prediction method and system based on unmanned aerial vehicle vision, and belongs to the technical field of construction monitoring. Image and material approach data are collected through an unmanned aerial vehicle, construction components are recognized by combining target detection and a three-dimensional reconstruction technology, visual engineering quantity estimation and material consumption time sequence data are fused, and multi-source collaborative analysis and anomaly detection are achieved. The construction progress is automatically judged, the completion percentage is calculated, deviation root causes are actively identified through a dynamic risk feature library, and future completion time and risk early warning are predicted in combination with a time sequence model. Compared with a traditional method, the accuracy and real-time performance of construction progress monitoring are improved, full-process automatic management from data collection to intelligent early warning is achieved, the manual checking cost is effectively reduced, and the engineering risk prevention and control capacity is improved.

A text sequence recommendation method and system based on a large language model is disclosed, belonging to the technical field of recommendation algorithms. The method includes: a data preprocessing stage, a large language model pre-training stage, a sequence model fine-tuning stage and a matching stage. According to this disclosure, a large language model is introduced into a text sequence recommendation task, so that text can be better modeled by utilizing rich pre-training corpus of the large language model; meanwhile, sequence modeling is performed on the text, the capability of sequence recommendations modeling in a large model is activated, an ID-based recommendation paradigm in a traditional recommendation algorithm is eliminated, and recommendation task learning processing is better performed in a cold start scenario and a knowledge transfer scenario; and finally, a recommendation result is finally optimized by a sequence model.

The embodiment of the invention discloses an automatic rock extraction method and system based on deep learning and Mars rover camera images, and aims to solve the problems that an existing Mars rock segmentation algorithm is insufficient in generalization ability under a complex earth surface background, high in model calculation load and difficult to deploy on satellite-borne edge equipment. The core of the method is that a lightweight encoder-decoder network is constructed, and the network integrates three key modules: a frequency-assisted enhancement Mama module, which accurately captures rock texture and contour by fusing the global sequence modeling capability of Mama and the frequency domain enhancement of wavelet transform; the multi-scale feature intensifier is used for adaptively fusing multi-level features by using a parallel double attention mechanism; and the boundary perception auxiliary branch improves the integrity of the segmented contour through an explicit edge supervision and feature decoupling mechanism. According to the method, the rock extraction precision is remarkably improved, meanwhile, the model complexity and the calculation overhead are greatly reduced, the method is suitable for outer space exploration scenes with limited communication bandwidth and calculation resources such as Mars rovers, and effective balance of high precision and light weight is achieved.

The invention discloses an unmanned aerial vehicle autonomous navigation system based on a rasterized world model, and relates to the technical field of unmanned aerial vehicle control. According to the system, observation information of an unmanned aerial vehicle is input into a trained rasterized world model through an observation acquisition module; through cooperative work of a sequence model, a multi-modal self-encoder, a hidden space dynamics predictor, a multi-modal information prediction head and a grid predictor in a rasterized world model, a cyclic variable containing historical information, a prediction hidden state vector and a prediction local grid map are provided for an agent model. And action decision making is carried out based on the data through an intelligent agent model so as to accurately output the actions of the unmanned aerial vehicle. According to the system, by introducing the rasterized world model, multi-modal observation information can be effectively fused, and a three-dimensional structure of a local environment is predicted in real time, so that the spatial perception capability of an intelligent agent model to a complex environment is enhanced, and the decision-making performance of the intelligent agent model is improved.

The invention provides an image enhancement model-based image enhancement method and device, an image enhancement model training method and device, equipment, a medium and a program, and relates to the technical field of image processing, in particular to deep learning, computer vision and artificial intelligence technologies. The image enhancement method based on the image enhancement model comprises the following steps: dynamically dividing a target original image into image blocks, and extracting image features of each image block to obtain multi-scale image local features; performing feature dimension unification processing on the multi-scale image local features to obtain unified dimension image local features; inputting the unified dimension image local features into an improved sequence model of an image enhancement model, and outputting unified dimension image local enhancement features corresponding to the unified dimension image local features through the improved sequence model; and carrying out aggregation processing on the local enhancement features of the unified dimension images to obtain a target enhancement processing image corresponding to the target original image. According to the embodiment of the invention, the image enhancement processing effect is improved.

The invention provides a reinforcement learning-based power distribution network real-time scheduling method, computer equipment and a storage medium. The method comprises the steps of obtaining a real-time state sequence of a power distribution network; calling a preset target model to process the real-time state sequence to obtain a real-time scheduling instruction of the power distribution network; wherein the target model is obtained by performing sequence modeling pre-training and alternate optimization training on the initial model based on historical scheduling trajectory data of the power distribution network and an offline reinforcement learning framework; and performing resource scheduling on the power distribution network based on the real-time scheduling instruction. Based on the scheme, the overall performance of power distribution network dispatching can be improved.

The invention discloses an elastic load balancing scheduling method adaptive to multiple nodes, which relates to the technical field of power scheduling, constructs a multi-dimensional resource vector by periodically collecting multi-dimensional resource data, and predicts future overload nodes by fusing historical load characteristics and real-time data by using an LSTM time sequence model. A preheating copy is preset at a low-load node based on a multi-objective optimization algorithm to deal with burst traffic, continuous optimization of a resource allocation strategy is realized through dynamic resource recovery, and meanwhile, a node load trend and a health state are evaluated regularly to form a prediction-capacity expansion-load balancing-capacity reduction closed-loop control link; the preheating copies are deployed on the nodes with low resource utilization rate in advance, so that the processing pressure of the main node can be quickly shared, and the processing capacity and flexibility of the system are improved; through a dynamic resource adjustment strategy, efficient utilization of resources is realized, idle resources are reduced, and the operation cost is reduced.

The present application relates to the technical field of intelligent Internet of Vehicles, and in particular to a deep reinforcement learning-based task unloading method in a vehicular edge computing environment, comprising: acquiring tasks to be executed generated by a task vehicle, uploading the tasks to an RSU, generating a scheduling decision on the basis of the current states of the tasks and available resources, and allocating the tasks to service vehicles or executing the tasks locally; prioritizing the tasks by means of the analytic hierarchy process, and acquiring the current state of each of the tasks to be executed; on the basis of the states and the priorities of the tasks, using a model for scheduling to acquire service vehicle numbers and a task vehicle number for the tasks, and a computing unloading and scheduling policy; acquiring available computing resources of the current service vehicle; and, by means of the Actor-Critic algorithm, training a sequence-to-sequence model, so as to obtain an optimal task partial unloading and scheduling policy. The present application can fully use computing resources of service vehicles and edge servers, so as to allow for shorter execution delays of all tasks throughout the entire time period and higher task execution success rates.

The invention relates to the technical field of power system simulation, and discloses a power system time sequence simulation system considering security constraints. The system comprises a power grid topology analysis unit, a dynamic security domain calculation unit, a time sequence constraint modeling unit, a simulation track generation unit and a check feedback unit. The power grid topology analysis unit obtains element connection relations and electrical parameters, and generates a topology description file containing a node admittance matrix; the dynamic safety domain calculation unit obtains the voltage stability limit and the power angle stability boundary of each working condition, and forms a safety domain boundary set; a time sequence constraint modeling unit combines the set with a predefined time interval to build a security constraint time sequence model containing a transient process; the simulation trajectory generation unit solves a differential algebraic equation set by using an implicit trapezoidal integral method, and outputs a state variable trajectory with a timestamp; and the check feedback unit compares the track with the security domain boundary, marks an abnormal segment and generates a correction instruction. The system realizes fusion of security constraint and time sequence simulation.

The invention discloses a data processing method of a full-stack AI enterprise management system. The method comprises the following steps: constructing a time difference sequence of financial links; a delay fluctuation value is calculated through multi-scale wavelet transform and time sequence analysis, and an abnormal service link is identified by using an isolated forest algorithm; generating a consistency deviation index fusing a financial field matching rate and a domain rule weight based on a sequence-to-sequence model of an attention mechanism; inputting the deviation index and the time difference sequence into a space-time diagram convolutional network, and tracing a root business link; a timestamp synchronization strategy is adjusted according to the tracing path, and a financial rule engine is triggered to generate a correction entry; an LSTM model and a reinforcement learning agent are introduced, so that optimization verification and parameter adaptive adjustment are realized; and finally generating an abnormal positioning report and a risk assessment result. By means of the technical scheme, automatic detection, source tracing, correction and continuous optimization are carried out on abnormities in the enterprise management process, and the reliability, compliance and system autonomy ability of financial data circulation are improved.

Provided are improved machine learning-based text editing models. Specifically, example implementations include a flexible semi-auto-regressive text-editing approach for generation, designed to derive the maximum benefit from non-auto-regressive text-editing and autoregressive decoding. In contrast to conventional sequence-to-sequence (seq2seq) models, the proposed approach is fast at inference time, while being capable of modeling flexible input-output transformations.

The invention discloses a data analysis method and device based on a double-time-sequence model and electronic equipment, and relates to the technical field of data processing or other related fields, and the method comprises the steps: receiving a data analysis demand, and obtaining the flight information of a target flight and the current passenger ticket data from an aviation database; performing feature engineering processing based on the flight information and the current passenger ticket data to obtain a first type of features and a second type of features; inputting the first type of features into a first time sequence model, and outputting a first result; inputting the second type of features into a second time sequence model, and outputting a second result; and performing fusion processing on the first result and the second result based on a preset result fusion strategy, and executing a business decision of the target flight by using a fusion result. According to the invention, the technical problem of low decision accuracy caused by difficulty in guaranteeing the accuracy of data analysis for large-scale complex change data in a machine learning algorithm in the related technology is solved.

There is described a computing device (600) for generating a sequence model output (403), the computing device (600) for: obtaining a model input (101); generating, using the model (102), a plurality of first candidate output subsequences (403-1, 403-2, 403-N) from the model input (101), where each first candidate output subsequence (403-1, 403-2, 403-N) is a code forming a first segment of the sequence model output (403); analyzing each of the first candidate output subsequences (403-1, 403-2, 403-N) to select one of the first candidate output subsequences (403-1, 403-2, 403-N); a sequence model output (403) is generated from the selected first candidate output subsequences (403-1, 403-2, 403-N), where the selected first candidate output subsequences form a first segment of the sequence model output (403). In this manner, an optimal first candidate output subsequence (403-1, 403-2, 403-N) may be selected for generating a sequence model output (403).

The invention provides an underground coal mine unmanned aerial vehicle dynamic path planning system. Comprising a map construction unit, a risk prediction unit, a cost calculation unit, a path planning unit and an execution feedback unit. The system collects underground environment information through a multi-wire-harness laser radar, a depth camera, a gas sensor and an inertial measurement unit, constructs a real-time three-dimensional voxel map through point cloud splicing and inertial navigation fusion, and records gas concentration, temperature, dust density and SLAM uncertainty; according to the system, gas concentration, temperature, dust density and SLAM uncertainty are continuously recorded by using a three-dimensional voxel map, and a future delta t-oriented space-time risk field is constructed through a gas convection diffusion model, a temperature time sequence model and a micro-seismic threshold model, so that the unmanned aerial vehicle can know a risk evolution trend in advance in a path planning stage; and the problem that in a traditional scheme, a person enters a future high-risk area by mistake while dodging local obstacles is avoided.