4456 results about "Quantitative Evaluations" patented technology

The invention discloses a multi-agent collaborative task planning method, and is applied to the technical field of artificial intelligence. The method comprises the steps of decomposing a task into a plurality of sub-tasks through semantic recognition and generating corresponding semantic coding vectors; meanwhile, a preset agent resource library is called, and quantitative evaluation capability vectors of all agents in multiple skill dimensions are obtained; dynamically allocating the most adaptive target agent to execute the corresponding subtask based on matching calculation of the subtask coding vector and the agent capability vector; then parallelly driving the target agent to execute the subtasks, fusing processing results output by the target agent, and integrating to generate a task response text; and finally returning the response text to the user. According to the method, the task is split into the coding vectors corresponding to the sub-tasks through semantic recognition, and dynamic matching is performed in combination with the multi-dimensional capability vector of each agent, so that adaptation of task requirements and agent resources is realized, and the resource scheduling efficiency and execution reliability of a multi-agent system in a complex task scene are improved.

The invention provides a livestock breeding risk intelligent assessment method and system based on multi-source data fusion, and the method comprises the steps: collecting livestock individual vital sign data, breeding environment parameters, management behavior data and risk-related historical data through Internet of Things equipment, and carrying out the data preprocessing to form a standardized multi-source data set; extracting risk features of individual, group and environment levels based on the data set, and fusing the risk features to form a multi-dimensional risk feature library; utilizing machine learning to construct a differentiated risk assessment model; analyzing the incidence relation between the risk factor and the actual event through the Bayesian network to calibrate the model; realizing livestock risk grade dynamic division and early warning based on the calibrated risk scoring system; and finally, generating intervention suggestions for risk quantitative evaluation, risk prevention and control decision and loss evaluation. According to the method, accurate evaluation of livestock breeding risks is realized, decision support is provided for breeding safety management, and the method has relatively high application value.

The invention belongs to the technical field of rail transit intelligent monitoring, and particularly relates to an intelligent monitoring method and device for a rail transit air conditioning system. According to the method, the sensor array with the self-adaptive sampling frequency is used for collecting the multi-modal operation data, then the collected multi-modal operation data is preprocessed, the feature degradation track atlas is established, powerful data support is provided for subsequent fault early warning and diagnosis, and the fault diagnosis accuracy is improved. Historical abnormal events are introduced to dynamically correct the health state evaluation base line, the timeliness and accuracy of the evaluation base line are ensured, in comparative analysis of real-time operation data and the dynamic evaluation base line, a health degree scoring and dynamic threshold mechanism is adopted, quantitative evaluation of the health state of the air conditioner system is achieved, and the evaluation accuracy of the health state of the air conditioner system is improved. According to the method, a decision graph containing fault diagnosis and predictive maintenance suggestions is generated by analyzing the propagation path and time sequence relevance of abnormal parameters in the air conditioning system and combining an equipment topological relation graph, so that the troubleshooting and repairing efficiency is improved.

The invention relates to a computing power network resource scheduling method. The method comprises the following steps: acquiring floating point operation performance parameters and operation states of node processors and energy index data of data centers where the node processors are located, and calculating to generate a node list; constructing a global resource pool based on the list, and generating a resource distribution table containing the total calculation power of the region; obtaining calculation requirements and time delay constraints of the task queue, extracting feature vectors in combination with the resource distribution table, and generating a resource utilization rate table; obtaining network link flow data, predicting a link congestion probability through a long short-term memory network, and generating a flow control strategy table; and finally, updating resource pool network constraints according to the resource utilization rate table and the flow control strategy table, and remapping tasks by taking node effective computing power as a weight to generate a scheduling execution scheme. According to the method, accurate quantitative evaluation of the computing power resources is realized, the matching precision of tasks and the computing power resources is effectively improved, the resource utilization rate of the computing power network can be remarkably improved, and the overall scheduling efficiency and stability of the system are enhanced.

The invention relates to the technical field of building construction, in particular to a building construction safety intelligent early warning system based on multi-sensor fusion and deep learning. Comprising a multi-source sensing unit; an intelligent fusion unit; a depth analysis unit; and a dynamic response unit. According to the method, through a mixed deep learning model, personnel-equipment-environment space association in a 1m * 1m * 0.5 m space grid is extracted through an improved U-Net network, and a space risk association map is output; modeling data of 10 sampling periods by using a bidirectional LSTM network, and outputting a short-term prediction value; and carrying out weighted fusion through an attention mechanism to form a risk feature vector, and removing invalid anomalies in cooperation with parameter anomaly judgment and cross validation. And then a risk grade evaluation module introduces multiple coefficients to calculate a risk grade index, and a grid diffusion range is delimited according to grades, so that real-time identification, quantitative evaluation and range pre-judgment of construction safety risks are realized, and the problem that risk identification evaluation lacks scenarized accuracy and comprehensiveness is solved.

The invention discloses a semiconductor packaging device electromagnetic compatibility comprehensive test method and system, and belongs to the technical field of electromagnetic compatibility testing. The method comprises the following steps: collecting structure parameters, packaging topology and predefined function states of a to-be-tested packaging device, and constructing a polymorphic working model; establishing a disturbance injection control model according to each state and configuring disturbance source parameters; implementing dynamic disturbance injection and acquiring response data in a real working state of the device; performing time domain and frequency domain conjoint analysis on the response data, constructing an electromagnetic response dynamic feature sequence, inputting the electromagnetic response dynamic feature sequence into a machine learning model, extracting multi-dimensional coupling features and predicting tolerance; calculating performance indexes such as an interference tolerance score and a coupling strength index based on model output indexes, comparing the performance indexes with a standard, and evaluating a compatible risk level in a full state; the method realizes quantitative evaluation of the EMC performance of the packaging device with high reduction degree and multi-state coverage, and has the advantages of comprehensive test, accurate prediction, explainable attribution and the like.

The invention provides a dam intelligent early warning method and system based on a depth time sequence attention network, and the method comprises the steps: carrying out the time alignment and sliding window segmentation of environment variables and historical displacement data of dam monitoring, extracting multi-scale statistical features, fusing the multi-scale statistical features with original features, carrying out the unified normalization processing of a spliced high-dimensional vector, and carrying out the calculation of the unified normalization processing; model input is generated; based on the constructed DSA-Net, carrying out local feature extraction, bidirectional time sequence modeling and key moment weighting on an input sequence, and jointly outputting horizontal and vertical displacement predicted values; fusing double deformation prediction results into a unified radial deformation index, and dynamically setting an early warning threshold value band according to a historical residual error to realize self-adaptive deformation early warning; quantitative evaluation is carried out on the model prediction precision, online prediction and threshold determination of real-time observation data are realized by using the qualified model and an adaptive threshold mechanism, abnormal early warning is triggered, and alarm information is recorded. According to the invention, deep coupling of deformation dimensions and dynamic threshold early warning are realized.

The invention relates to the technical field of electrical equipment defect detection, in particular to an electrical equipment defect detection system and method based on deep learning, which are characterized in that a three-dimensional model of a power grid region is constructed, and based on historical defect data, a neural network model is adopted to mark an importance score of an inspection object in the three-dimensional model; quantitative evaluation of the equipment fault risk level is completed, and the matching degree of inspection resources and defect risk distribution is improved. A power grid three-dimensional model and importance scores are combined, a reinforcement learning model is utilized to construct an unmanned aerial vehicle inspection route planning strategy, the inspection route comprehensively considers power equipment defect risks and space factors in the planning stage, task allocation is optimized, and the problem that a static route cannot adapt to equipment changes is solved. In the inspection execution process, the unmanned aerial vehicle is dispatched according to the planning strategy, and the image flow is synchronously acquired for defect detection, so that the linkage of the inspection action and the detection process is realized, and the response efficiency and the detection quality of potential defects are improved.

The invention relates to the technical field of robot decision making, and provides a robot multi-modal fusion autonomous decision making method and system based on a large language model.The method comprises the steps that a robot obtains multi-modal environment information through a visual sensor, a touch sensor, an auditory sensor and a laser radar which are carried by the robot; performing preliminary filtering and noise reduction processing on the original sensor data, and synchronously recording all the sensor data by timestamps; performing space-time semantic alignment on the preprocessed multi-modal data, mapping pixel coordinates of a target in a visual target coordinate quantization original image to a robot coordinate system, performing uncertainty evaluation on a multi-modal signal through a dynamic Bayesian network, and taking entropy or variance as an uncertainty quantitative evaluation index. According to the method, the information quality is improved from a data fusion source, accurate and reliable basic support is provided for subsequent decision making, and decision making errors caused by data deviation are greatly reduced.

The invention belongs to the technical field of medical resource intelligent management, and relates to a hospital comprehensive monitoring analysis method and platform based on artificial intelligence, and the method comprises the following steps: generating a medicine management basic data set; generating a primary prediction signal; adjusting a prediction weight according to the conflict level and outputting a reliable demand prediction instruction; a quantitative evaluation value reflecting the medicine turnover efficiency, the immediate pressure and the cost loss is calculated, and when the quantitative evaluation value exceeds a preset safety alert threshold value, an inventory abnormity alarm signal is generated; outputting an allocation strategy instruction containing the medicine flow direction, the allocation quantity and the time efficiency; and comparing a deviation value between the reliable demand prediction instruction and the allocation strategy instruction, and when the deviation value continuously exceeds a preset deviation threshold value, triggering an update prompt of the drug safety use limit rule base. The problem that demand prediction and clinical rule verification are separated in a traditional mode is solved.

The invention provides a double-mechanism cooperative type curved surface component water immersion ultrasonic intelligent detection method and system, and relates to the technical field of ultrasonic detection, and the method comprises the following steps: scanning a workpiece by using a double-mechanism water immersion ultrasonic detection system, collecting and processing an ultrasonic echo signal, and generating an ultrasonic C scanning image. And performing defect identification on the ultrasonic C scanning image by using the constructed multi-scale feature fused deep convolutional neural network model to obtain the type, position, size and confidence of the defect. Quantitative evaluation is carried out based on the defect recognition result, a report is generated, and meanwhile visual display and database management of the defect recognition result are achieved. Through double-mechanism cooperative scanning and deep learning intelligent identification, the precision and efficiency of curved surface component defect detection are improved, and automatic identification, quantitative evaluation and visual display of defects are realized.

The invention relates to the crossing field of material design and artificial intelligence, in particular to a solid electrolyte intelligent inverse design method fusing a graph neural network and confidence analysis. According to the method, a prediction framework integrating multiple models is constructed, support vector regression, gradient boosting regression, a deep neural network and a graph neural network are included, component, process and structure parameter characteristics are fully fused, and the nonlinear mapping relation between input variables and performance parameters such as resistivity and conductivity is efficiently learned. In order to improve the credibility, a Bayesian neural network and a Monte Carlo method are further introduced, a confidence interval corresponding to each group of prediction results is output, and quantitative evaluation of the credibility of the prediction value is realized. In the inverse design module, high-dimensional submerged space parameters are generated based on a variational auto-encoder, and intelligent recommendation of parameter combination driven by target performance is realized in combination with strategies such as Bayesian optimization and a genetic algorithm. The design efficiency of the solid electrolyte and the success rate of material discovery can be effectively improved.

The invention discloses a rock multi-field coupling test system and a damage evaluation and prediction method thereof, belongs to the technical field of geotechnical engineering and geomechanics experiments, and solves the problem that the rock state under the multi-field coupling condition cannot be monitored in real time in the prior art. The system comprises a multi-physics field coupling loading system, a multi-field data monitoring system and a multi-field data acquisition system. The system can simulate and apply axial pressure, confining pressure, pore pressure and temperature of an in-situ environment to a rock sample, integrates an acoustic monitoring system, a deformation monitoring system and a CT scanning system to realize multi-dimensional real-time monitoring of rock sample damage, overcomes the limitation of a single monitoring method, realizes multi-system electrical connection by taking an upper computer as a data acquisition center, and realizes multi-dimensional monitoring of rock sample damage. And a multi-parameter model is constructed by fusing sound waves, deformation and CT data, so that the whole-process quantitative evaluation from microcrack initiation to macroscopic fracture is realized, and the damage evaluation is comprehensively performed.

The invention discloses a network space security situation awareness detection analysis system and method, and the system comprises a heterogeneous network flow feature deep extraction unit which obtains a flow feature vector through a distributed probe array and an adaptive sampling strategy; the edge computing gateway multi-dimensional threat feature mapping unit realizes feature space mapping through a multi-dimensional feature mapping matrix; the dynamic weight multi-head attention feature fusion unit fuses features by using an optimized multi-head attention mechanism; the time-space sequence security situation evolution modeling unit constructs an evolution model in combination with the time sequence and the fusion features; the security threat risk quantitative evaluation unit carries out risk quantification; and the heterogeneous security policy collaborative response unit generates a response instruction. According to the method, flow collection, feature mapping, fusion, modeling, quantification and response operation are sequentially executed based on all units of the system. According to the method, efficient perception and accurate response of the network space security situation are realized through a multi-unit cooperation and innovation model.

The invention relates to the technical field of risk analysis, in particular to a supply chain risk quantitative evaluation method and system based on a dynamic affair atlas, and the method comprises the steps: collecting multi-source heterogeneous data, constructing a four-dimensional space-time model comprising a time dimension, a geographic space dimension, a supply chain network space dimension and a risk influence space dimension, representing the supply chain event as four-dimensional spatio-temporal data; a supply chain entity is identified from the four-dimensional spatio-temporal data, risk events are extracted, a affair graph is constructed, and the affair graph takes the risk events as nodes and the evolution relation between the events as edges to calculate the relation weight between the events; calculating a probability quantized value of the risk conduction path based on the affair map, and obtaining a comprehensive risk score of the target entity; generating a risk mitigation strategy based on the comprehensive risk score; and monitoring the deviation between the actual risk occurrence condition and the prediction result, and updating the affair map and the risk mitigation strategy through adaptive parameter optimization and an incremental learning mechanism to form a self-evolutionary risk assessment system.

The invention relates to the technical field of image processing, and discloses a film lamination defect detection method and system based on image processing. The method comprises the following steps: acquiring and preprocessing a film-conducting layer interface by using a polarization enhanced imaging device to obtain an enhanced image; applying double-layer gradient edge detection to extract the edge of a fitting area, and marking a micro-defect sensitive area; an interface smoothness index and a fitting uniformity feature are obtained through multi-scale morphology feature extraction; inputting the features into a support vector classifier to identify bubbles-wrinkles; performing three-dimensional reconstruction on an identification result to generate a bubble distribution and stress field graph; and finally evaluating the fitting quality, and outputting an integrity score. According to the invention, automatic accurate detection and quantitative evaluation of tiny defects of the thin film-conducting layer bonding interface are realized.

The invention provides a crop growth state evaluation method based on the agricultural Internet of Things, and the method is characterized in that the method specifically comprises the following steps: S1, collecting the multi-dimensional data of a crop growth environment in real time, and outputting an original data set; s2, aligning the multi-dimensional data according to geographic coordinates, extracting features, and constructing a multi-modal fusion feature vector; s3, automatically identifying the current growth stage of the crop and the confidence of the current growth stage according to the fused feature vector; s4, calculating a crop health degree score and grading according to the growth stage information and the feature data, and identifying a stress state detection result at the same time; s5, according to a quantitative evaluation result, predicting a growth trend and generating a suggested decision scheme; and S6, the decision is monitored, the decision execution effect is fed back to the system, and the model parameters and the decision rules are continuously optimized. A closed-loop mechanism of evaluation, decision, feedback and optimization is formed, the applicability and evaluation precision of the system are continuously improved, and agricultural production is promoted to be upgraded to precision and intelligence.

The invention discloses a packaging box printed matter printing quality detection method, which comprises the following steps of: acquiring a high-resolution printing image through an image acquisition module, preprocessing and segmenting the printing image by an image processing module, optimizing image quality, classifying the preprocessed image by an image classification module according to characters, patterns and color blocks, and detecting the printing quality of a packaging box printed matter. The defect detection module performs multi-dimensional detection on the classified preprocessed images based on image parameter data, the quality analysis module quantitatively evaluates quality scores of characters, patterns and color blocks based on detection results, and the computer terminal generates a comprehensive score through weighting calculation and automatically generates a detection report; according to the packaging box printed matter printing quality detection method, complex defects such as font errors, stroke breakage, pattern deviation, color deviation and stains are effectively recognized through multi-dimensional defects, the manual reinspection cost is reduced through full-process automatic processing, and the quality of printed matter is visually reflected through a quantitative evaluation system.

The invention relates to a lightweight component surface defect quantitative evaluation method, system and device, and the method comprises the steps: obtaining a multispectral surface image, laser three-dimensional data and ultrasonic detection data of a lightweight component, and carrying out the fusion registration based on a preset multi-sensor synchronization protocol, and obtaining a component joint data set; performing dynamic pruning analysis on the component joint data set to obtain geometric contour features, and performing internal feature extraction on the component joint data set to obtain internal abnormal response features; stress gradient distribution data and volume ratio parameters are carried out on the geometric contour features and the internal anomaly features; and obtaining an original working condition data set of the lightweight component, carrying out service working condition coupling analysis on the multi-dimensional prediction matrix, and carrying out multi-dimensional quality l parameter identification to obtain component comprehensive quality information. According to the method, the morphology mechanical coupling feature extraction precision of composite defects such as cracks and holes can be improved.

The invention belongs to the technical field of semiconductor testing, and discloses a novel automatic detection system and method for the electrostatic protection performance of a power device. A distributed parasitic parameter network model is constructed by acquiring packaging structure parameters of a to-be-tested power device and physical layout data of a test fixture, key parasitic parameter distribution is identified in combination with a time domain reflection measurement technology, a waveform distortion coefficient is calculated, and a spatio-temporal evolution model of electrostatic pulse propagation is constructed. Based on the model, a compensatory predistortion waveform is generated to counteract the parasitic effect of a transmission path, a device port response signal is collected in real time, an energy dissipation characteristic spectrum is extracted through wavelet packet decomposition, and quantitative evaluation of the electrostatic protection performance is achieved. According to the invention, the test precision and repeatability are improved, and the method is suitable for electrostatic protection tests of various novel power devices, especially high-frequency wide-band gap devices.

The invention discloses an ocean multi-mode environment perception and intelligent ship navigation decision-making method based on a double-branch vision-semantic encoder. The method comprises the following steps: S1, acquiring a multi-source data image containing a ship and a surrounding environment thereof from an existing public maritime data set or platform; s2, training a double-branch vision-semantic encoder by using the multi-source data image, and inputting a to-be-processed image extracted in real time into a multi-modal feature matrix in the trained double-branch vision-semantic encoder; s3, based on the multi-modal feature matrix, obtaining positioning information of the ship and surrounding environment elements, and constructing a dynamic security domain model; and S4, in combination with the dynamic security domain model and the multi-ship relative position relationship, carrying out quantitative evaluation on the navigation risk, and generating a self-adaptive navigation strategy based on an evaluation result. According to the invention, high-precision ship positioning and environment element identification under complex weather and illumination conditions are realized by using all-weather characteristics and multi-scale visual feature coding of SAR imaging.

The invention relates to the fields of artificial intelligence, finance and medical treatment, and discloses an intelligent question and answer accuracy improving method and device, computer equipment and a storage medium, and the method comprises the steps: converting structured supervision fine tuning training data into a high-dimensional vector; constructing a multi-dimensional joint index for the high-dimensional vector, and storing the indexed high-dimensional vector in a distributed vector database; receiving a current dialogue text input by a user, and retrieving an associated question set from the distributed vector database through a similarity matching algorithm; dynamically splicing the retrieved associated questions, the corresponding answers and preset template instructions to generate enhanced cue words containing knowledge contexts; inputting the enhanced cue word into a large language model, and generating N candidate answers in parallel; and carrying out quantitative evaluation on the N candidate answers by adopting a multi-dimensional reward model, and selecting the answer with the highest score and returning the answer to the user. According to the scheme, the answering accuracy of the dialogue robot can be improved, so that the user experience is improved.

The invention discloses an artificial intelligence robot path planning method and system, and the method comprises the steps: 1, carrying out the comprehensive perception of an environment geometric structure, object semantics and dynamic obstacles, eliminating scene differences, and further constructing the topological graph representation of an environment; 2, pre-training a path planning model, designing a scene context encoder, encoding a scene specific rule into a low-dimensional vector, and outputting a scene context code and updated planning model parameters to provide a planning capability adapted to a new scene for the step 3; 3, dynamically adjusting a track according to real-time sensor data by adopting a hierarchical decision-making architecture; step 2, recording success / failure path segments in the new scene, regularly updating a local planning module, regularly feeding back empirical data in the new scene to the step 2, and triggering a conservative obstacle avoidance mode when the confidence coefficient is lower than a threshold value; and 4, constructing a quantitative evaluation system, building an automatic test platform, simulating diversified scenes and dynamic interference, and automatically generating a test case.

The invention relates to a model training method and device. The method comprises the steps of obtaining a first training image set; performing first fine tuning training on the pre-trained artificial intelligence model by using the first training image set to obtain a preliminary optimization model; acquiring a second training image set; constructing a composite reward function based on the second training image set; wherein the composite reward function is used for performing multi-dimensional quantitative evaluation on the quality output by the model; and performing second fine tuning training on the preliminary optimization model based on the second training image set and the composite reward function to obtain a final optimization model. Therefore, a two-stage differential fine-tuning model strategy is realized, so that the output result of the final optimization model is highly matched with the expectation of a real scene, the problem of insufficient model practicability is fundamentally solved, and the reliability and value of the model after deployment are greatly improved.

The invention provides a multi-dimensional electrical equipment insulation analysis and evaluation method, and relates to the technical field of electrical equipment insulation online detection and intelligent diagnosis. According to the method, an electrically isolated direct current detection channel is constructed in a neutral point small resistance grounding system, controllable direct current detection signals are injected, micro direct current leakage response signals are collected, and after zero drift correction, temperature compensation and power frequency ripple suppression are carried out, layered attribution is carried out in combination with primary system topology and an equipment ledger, and a multi-dimensional response matrix is formed. According to the method, environment and working condition normalization is realized through factor rejection and robust pull-back, a mechanism model containing leakage channel equivalent parameters and path constraints is established, multi-working-condition data is fused to calculate equivalent insulation parameters and credibility indication quantity, and a multi-dimensional insulation representation vector is generated. And performing time sequence analysis on the representation vector, extracting degradation and abrupt change characteristics, outputting a health index and a risk level, and realizing quantitative evaluation and intelligent early warning of the insulation state.

The invention discloses a health status assessment method and system based on a multi-modal biosensor, and the method comprises the steps: synchronously collecting a plurality of physiological signals of a plurality of target species objects, and generating a multi-modal physiological data flow with consistent time and space; inputting the multi-modal physiological data stream into a deep learning model, and outputting a high-dimensional feature vector fused with time-space characteristics; inputting the high-dimensional feature vector into a cross-species adaptation model based on transfer learning, and outputting a cross-species universality state vector representing the current health abnormal state and confidence of the target object; inputting the cross-species universality state vector into a lightweight risk assessment model, and outputting a quantitative assessment result reflecting the instant health risk level of the target object; and according to a quantitative evaluation result, automatically generating and triggering a personalized health intervention instruction for the target object. By utilizing the embodiment of the invention, the physiological difference of different species can be dynamically adapted, and the accuracy and the universality of health state evaluation are improved.

The invention discloses a cardiovascular medicine disease early warning analysis system based on big data, and relates to the technical field of disease early warning, and the system comprises a data processing and modeling module which is used for collecting physiological signal data and home behavior data of a patient, and constructing a physiological baseline model representing the personalized health state of the patient; the signal decoupling and correcting module is used for calculating to obtain corrected physiological indexes without the influence of behavior disturbance based on the home behavior data collected in real time; the risk quantitative evaluation module is used for generating a composite risk score representing the current cardiac function deterioration degree based on the deviation degree of the corrected physiological indexes and the physiological baseline model; and the early warning and adaptive optimization module is used for carrying out risk level judgment and triggering corresponding early warning. According to the method, behaviors and physiological signals are decoupled, personalized baselines are constructed, multi-dimensional risks are quantified, closed-loop optimization is formed, the problem of high false alarm and missing alarm in traditional early warning is solved, and accurate early warning and long-term effective monitoring are achieved.

The invention discloses a GPU computing power resource scheduling method and device based on load awareness and a medium, and relates to the technical field of computing power scheduling. The method comprises the steps that according to the video memory capacity and the number of calculation cores of the GPU, the video memory capacity is divided into a plurality of continuous fragments, the calculation cores are divided into a plurality of logic calculation groups, and sub-resource units are obtained; recording occupation states and load indexes of the sub-resource units in real time to obtain a resource pool; analyzing a job submitted by a user, and collecting an execution period of a kernel function, a video memory access mode and an instruction pipeline blocking rate when the job runs; and on the basis of a reinforcement learning algorithm, predicting a resource demand inflection point of the job according to the load fingerprint model, performing hierarchical scheduling on the sub-resource units based on virtualization isolation and multi-dimensional resource quantitative evaluation, and generating a preemptive allocation strategy of the sub-resource units. According to the method, efficient utilization and secure sharing of GPU resources are realized through collaborative design of dynamic granularity segmentation, load aware scheduling and hardware-level security isolation.

The invention provides an unmanned aerial vehicle multi-mode navigation positioning method, device and equipment, and the method comprises the steps: obtaining GPS, inertia and visual navigation mode positioning data through determining a target positioning precision index, and carrying out the evaluation to generate a multi-mode navigation state set; performing performance competition on each navigation mode based on the state set, establishing an inter-mode negotiation mechanism, and determining a mode priority sequence; establishing a navigation mode credibility matrix in combination with the priority sequence, and establishing an adaptive weight distribution sequence; analyzing a weight change trend and mode switching resource overhead, carrying out navigation mode dynamic screening through switching cost quantitative evaluation, and determining a dominant navigation mode and an auxiliary navigation mode; and performing frequency characteristic analysis on the dominant and auxiliary modes, determining a frequency domain fusion strategy based on a frequency coherence coefficient, generating a fusion positioning track, and outputting a high-precision positioning result through precision evaluation to realize intelligent multi-mode navigation positioning.

The invention provides a quantitative evaluation method for the ecological restoration effect of a surface mine, and the method comprises the steps: obtaining a multi-source remote sensing data set covering a target mine region, extracting an ecological element feature set, calling a pre-trained restoration effect evaluation model to carry out the time sequence correlation analysis, and generating an initial evaluation feature. The method comprises the following steps: performing time-space matching association analysis by combining a historical restoration record data set of a target mine, generating association evaluation features fusing restoration measure influences, and finally performing comprehensive quantitative analysis based on initial evaluation features and the association evaluation features, generating a quantitative evaluation result containing restoration effect grade division and key influence factor identification, and performing assessment. Therefore, the ecological restoration effect of the surface mine can be comprehensively, objectively and dynamically evaluated.