564results about How to "Reduce computing time" patented technology

The invention discloses a network management computing power session method and system based on 6G communication, sensing and computing integration, belongs to the technical field of mobile communication, and aims to solve the technical problem of how to realize flexible scheduling and on-demand distribution of computing power and network convergence resources in a 6G communication, sensing and computing integration network environment under the condition of not changing network equipment. A mobile network environment supporting a computing power-as-a-service mode is constructed for a user, and the adopted technical scheme is as follows: the method comprises the following steps of: deploying a computing network integration sensing network element, a computing network integration control scheduling network element and a computing network integration service arrangement network element on a core network side, so that the improved core network has a communication, sensing and computing power integration function; and through analysis and identification of computing power application request indexes, computing power business arrangement, computing power and network Qos configuration mapping, decision making and scheduling of computing network fusion resources, distributed cooperative computing tasks are issued, so that computing power session creation is completed, and different computing power requirements of the mobile terminal are met.

The invention discloses a power distribution network topology identification and state estimation method based on a message passing neural network and online deep learning, and the method comprises the steps: training a neural network through historical measurement data, building a power distribution network topology identification model, combining the obtained topology information with corresponding power grid measurement data, and constructing a graph data set; taking the obtained graph data set as a training set to train a message passing neural network to obtain a power distribution network state estimation model; and finally, inputting the real-time measurement data into a state estimation model of the topology identification model to obtain a real-time state estimation result under the section. According to the method, the power distribution network topology can be accurately identified under limited measurement data, accurate state estimation is provided for a power distribution system, and technical support is provided for subsequent safety assessment and optimized operation.

The invention discloses a two-way staggered assembly line parallel method for accelerating large model training, and compared with an existing method, the method introduces V-shaped staggered scheduling into a two-way assembly line to form a two-way staggered assembly line parallel mode, and improves the training efficiency of a large model and the use balance of a video memory. A V-shaped staggered assembly line and an inverted V-shaped staggered assembly line are fused to form a bidirectional staggered assembly line, the number of parallel devices is increased, meanwhile, the calculation time of a single micro-batch is shortened, the cavitation rate of the assembly line can be effectively reduced, and more balanced video memory occupation is achieved; in addition, a communication optimization strategy is introduced for overlapping or reducing part of communication overhead, and global gradient synchronization is performed by optimizing pipeline equipment mapping and utilizing a high-speed network in a server, so that the parallel training efficiency of the large model is further improved. The invention further provides a two-way interleaving assembly line parallel system and equipment which are used for achieving the two-way interleaving assembly line parallel method.

The invention provides a method for quickly establishing a three-dimensional near-seafloor speed model in a shallow sea area; the method comprises the following steps of extracting initial informationand extracting a common-center-point gather; calculating the slope of the initial travel time in the common-center-point gather; judging whether a shot point is located in the seawater layer or not,and if yes, correcting the shot point to the seafloor; calculating the speed and the depth of inflection points corresponding to respective offset distances; performing linear interpolation on the speed at each depth to obtain a one-dimensional speed model of the common center point; after all the common-center point domain gathers are processed, adopting the linear interpolation method, calculating the speed values of the rest grid points by utilizing the one-dimensional speed model of all common center points, and a speed model is output. By adoption of the method for quickly establishing the three-dimensional near-seafloor speed model in the shallow sea area, the influence of the seawater layer on ray propagation is overcome, and the influence of multiple excitation receiving modes on an inversion result is eliminated, and the problem that the conventional method needs to carry out multi-ray tracing forward modeling is avoided.

The invention discloses a free-form surface three-axis ball-end cutter equal approximation error finish machining tool path generation method which comprises the following steps: firstly, importing a free-form surface model to be machined, and setting data such as the radius, the line spacing, the approximation error maximum allowable value and the precision of a ball-end cutter; secondly, a group of section planes are planned according to the row spacing to intersect with the curved surface, the intersecting line serves as a cutter contact curve, and an equal-bow-height-error cutter contact iterative search method for driving cutter contact adjustment through the geometric distance is provided for the cutter contact curve on the section planes; the maximum distance between a cutter cutting envelope surface and a cutter contact track line is used as an approximation error, and an adaptive discrete method is adopted to carry out approximation error calculation; and finally, the cutter location points of the equal-bow-height-error cutter contact points serve as initial values, an equal-error cutter location point calculation method of step length self-adaptive adjustment iteration is provided, approximation errors between the cutter location points are all within an allowable range, and therefore the free-form surface three-axis ball-end cutter equal approximation error finish machining cutter path is obtained.

The invention discloses a stereo matching method based on context geometric features and distortion parallax optimization, which comprises the following steps of: firstly, shooting a calibrated left picture and a calibrated right picture through a binocular camera, extracting multi-scale context features of the two pictures, and calculating the similarity between feature points according to the feature points of the left feature graph and the right feature graph under different parallaxes; the matching cost is the matching cost, so that the constructed geometric cube contains rich geometric matching information. Meanwhile, context features are copied and expanded into context feature cubes with the same size according to parallax, and rich context information is contained. The geometric cube contains matching conditions of feature points of left and right views with different parallax errors, cost aggregation is guided through context features of the left view, and context feature information, feature point cost matching information under different parallax errors and geometric information of adjacent feature points are preliminarily fused to improve cost matching reliability. And generating a geometric attention weight cube. And filtering the contextual feature cube.

The invention discloses a memristor-based signal detection circuit and method, a receiver and equipment, and relates to the field of wireless communication, a voltage source module of the circuit is connected with a voltage input end of a memristor array module, and a current source module is connected with a current input end of the memristor array module; the current output end of the memristor array module is connected with the reverse input end of the operational amplifier module and one end of the feedback resistor module, the other end of the feedback resistor module and the output end of the operational amplifier module are connected with the input end of the multiplier module, and the output end of the multiplier module is connected with one end of the resistor module. The voltage of the voltage source module is set according to the emission vector set; the current of the current source module is set according to the received radio frequency signal, and the conductance value of the memristor is set according to the channel matrix, so that a relatively low bit error rate of signal detection can be realized on the basis of greatly reducing calculation time and power consumption, and meanwhile, the requirement on programmable bit precision of the memristor is also reduced.

The invention relates to an unmanned aerial vehicle route planning method and system based on lightweight artificial intelligence, and the method comprises the following steps: S1, obtaining the environment data of a distribution line, and fusing the data of multiple sensors in real time; s2, constructing an environment map based on the fused multi-sensor data; s3, key points are extracted from the environment map to serve as path nodes, the number of the nodes is reduced through a clustering algorithm, and a three-dimensional environment map with the key path nodes is obtained; s4, optimizing path calculation by adopting an improved A * algorithm and utilizing a heuristic search strategy according to the electric power line inspection plan, and constructing a path plan; and S5, deploying an edge terminal at the key node, and triggering real-time data storage and transmission only when necessary by adopting an event-based detection algorithm. Through the lightweight artificial intelligence algorithm design, the method can efficiently operate on an unmanned aerial vehicle platform with limited computing resources, and can effectively execute the inspection task in a complex distribution line environment at the same time.

The invention belongs to the field of oil-gas exploration seismic data processing, and relates to a first-motion wave travel time chromatography velocity inversion method, system and device and a medium. According to the method, the first arrival travel time and the grid unit travel time are acquired, and the minimum grid unit travel time is selected; an initial velocity field closer to a real structure is established through micro-logging constraint so as to replace a conventionally used gradient velocity field. The initial velocity field and the first arrival travel time are combined to construct the target function, the slowness information and the regularization information are added in the target function, the multi-information constrained target function is obtained, and the inversion stability and the calculation precision are improved. And adopting a Gaussian-Newton method to minimize the target function of the multi-information constraint, solving the minimized target function of the multi-information constraint, and carrying out iterative updating on a solving result to obtain an inversion velocity field. Explicit calculation and sensitive kernel function storage are not needed, the method is more suitable for large-scale data processing, and the calculation time of speed inversion and the requirement for storage space are reduced.

The invention relates to a permanent magnet synchronous motor design method based on a multi-objective optimization algorithm, and the method achieves the efficient design and optimization of a permanent magnet synchronous motor through the combination of finite element simulation, multi-physical field coupling analysis, neural network performance prediction, and a hybrid optimization algorithm of a genetic algorithm and particle swarm optimization. The method comprises the following steps: determining a plurality of design targets according to an application scene of a motor, selecting key design variables, performing data cleaning and normalization processing, performing electromagnetic field, thermal field and mechanical field simulation by using a multi-physics field coupled finite element model, predicting the performance of the motor by combining LSTM and Transform neural network models, expanding a training data set through a data enhancement technology, and performing data enhancement on the motor. Finally, a hybrid optimization algorithm combining a genetic algorithm and particle swarm optimization is adopted to carry out global optimization and adaptive adjustment of design parameters, and a Pareto optimal leading edge is utilized to find out an equilibrium solution between design targets, so that the accuracy and efficiency of motor design are improved, and the method is suitable for various motor design scenes.

The invention belongs to the technical field of electric digital data processing, and particularly relates to a manned submersible observation window stress prediction method based on machine learning, which comprises the following steps: acquiring strain and pressure data, and establishing a finite element model of an observation window; constructing a training set based on the strain and pressure data, and correspondingly constructing a machine learning hybrid model; training the machine learning hybrid model through the training set, and obtaining a stress prediction model; and predicting stress data of the observation window of the manned submersible in different environments through the stress prediction model. The stress prediction method based on data driving does not depend on a complex physical modeling process, stress distribution under complex working conditions can be predicted more quickly and accurately, calculation time and resource consumption can be greatly reduced, and a robust stress prediction result can be provided in a complex load environment; the calculation time is shortened, the prediction precision is improved, and an efficient and reliable prediction result is provided for structural safety assessment.

The invention discloses a virtual dynamic three-dimensional image fusion method and system based on pre-registration, and the method comprises the steps: obtaining a static three-dimensional image of a target region, and a dynamic three-dimensional CBCT image which at least comprises one respiratory cycle; performing breathing phase division on the dynamic three-dimensional CBCT image; obtaining a corresponding three-dimensional image frame on each phase node; registering the plurality of three-dimensional image frames obtained by division with the static three-dimensional image in sequence to obtain a single-frame deformation field; collecting breathing signals of a patient in real time during an operation; performing interpolation calculation on the single-frame deformation field based on the respiratory signal, and generating a complete deformation field in the whole respiratory cycle in real time; and applying the complete deformation field obtained by interpolation to the static three-dimensional image, so that the static three-dimensional image is virtually dynamic. Through a method of pre-registration of a pre-operative breathing phase node image and interpolation based on a real-time breathing phase in an operation, the calculation amount during real-time fusion in the operation is reduced, so that ultra-low-delay image fusion is realized.

The invention discloses a continuous-discontinuous numerical simulation method considering a rock mass thermal coupling problem, and the method comprises the steps: dividing a simulation region into a potential damage region and a non-damage region, and carrying out the grid division of the simulation region; then generating a thermal calculation node system and a force calculation node system for analog calculation, wherein a mapping relationship exists between the thermal calculation node system and the force calculation node system; jointing units are arranged on the grid boundary of the potential damage area, and the rock mass fracture process is simulated through damage of the jointing units; the simulation process is decomposed into a plurality of calculation steps, the heat conduction process and the mechanical calculation process in each calculation step are solved in sequence, whether the joint unit is damaged or not is judged according to the deformation and stress state of the joint unit, the mapping relation is updated until the last calculation step is finished, and the thermal fracture process simulation of the rock mass is completed. According to the method, artificial heat transfer parameters can be prevented from being introduced in the heat conduction simulation process, the fracture evolution rule of the local area of the rock mass is researched in a targeted mode, the calculation cost of the model is reduced, and the dynamic fracture process in the rock mass thermal coupling problem is effectively simulated.

The invention discloses a medium metasurface reverse optimization method based on a space coupling mode theory, and relates to the field of optics, and the method comprises the following steps: building a cut-off waveguide array based on a metasurface, calculating a guided mode and a propagation constant of each waveguide according to the cut-off waveguide array, and coupling adjacent waveguides through a coupling matrix, a waveguide array is obtained; an input light field is coupled into a waveguide array, propagation of light in waveguides is simulated based on a spatial coupling mode theory model, and near-field intensity distribution is converted into far-field intensity distribution by using a Rayleigh-Sommerfeld diffraction theory; and calculating the difference between the target intensity and the far-field intensity through a loss function, evaluating the effect of the current metasurface design, and gradually adjusting the geometric parameters of the waveguide unit through an optimization algorithm. According to the method, the problems of efficient modeling and optimization in metasurface design are solved through the space coupling mode theoretical model.

The invention relates to the technical field of topological optimization, and discloses a thermal coupling multi-scale parallel topological optimization method for additive manufacturing, and the method comprises the steps: dividing a macroscopic design domain into a plurality of macroscopic sub-design domains through a fuzzy C clustering method, and mapping the information of the macroscopic sub-design domains on the microcosmic level as the constraint condition of microcosmic optimization; performing equivalent static conversion on the transient temperature load, and introducing an equivalent thermal load into the multi-scale topological optimization model; macroscopic and microscopic thermal coupling finite element analysis is carried out according to the thermal coupling control equation, and a displacement vector matrix is solved by using an HHT-alpha method; sensitivity analysis is carried out on macro and micro objective functions and constraint conditions, and a moving asymptote MMA method is used as a solver for macro and micro design variable updating; and filling the microstructure into the macroscopic configuration to obtain an overall configuration, judging a convergence condition, and if the condition is met, outputting an optimal material distribution structure and an optimal microscopic configuration. The method can better reflect the real working state of the workpiece.

The invention provides a parallel iteration solving method and system for an electromagnetic finite element equation set, and relates to the technical field of electromagnetic finite elements, and the method comprises the steps: constructing a to-be-solved electromagnetic finite element equation set # imgabs0 #; dividing the electromagnetic finite element equation set into a plurality of calculation sub-tasks, and distributing a sub-matrix block # imgabs 1 # and a sub-right-end item vector # imgabs 2 # of the sub-tasks to each process in the super computer; by means of the initialized Hoseholder-GMRES algorithm, the processes are subjected to subtask calculation in parallel, and the local optimal solution # imgabs3 # of each process is obtained; summarizing the local optimal solution # imgabs4 # of each process to obtain an optimal solution # imgabs5 # of the electromagnetic finite element equation set; according to the method, the electromagnetic finite element, the Householder-GMRES algorithm and parallel computing are combined, and the solving efficiency of the linear equation set of the electromagnetic finite element is improved by utilizing a parallel optimization technology.

The invention discloses a junction temperature estimation method and device for a power semiconductor and a vehicle, and the method comprises the steps: obtaining the loss, temperature rise data and environment temperature of the power semiconductor in an electric period, the temperature rise data comprises temperature rise values of the temperatures of the power semiconductor under different operation conditions relative to the environment temperature; determining thermal impedance according to the loss and temperature rise data; and determining the junction temperature according to the loss, the thermal impedance and the environment temperature. According to the method, the load rate of the vehicle-mounted software can be reduced, additional hardware does not need to be added, so that test resources are simple, the accuracy is high, the practicability is high, the junction temperature calculation efficiency is improved, and the calculation time is saved.

The invention provides an optical calculation method and system based on on-chip diffractive optical feature extraction and a chip. The method comprises the following steps: loading data of an input end to an input optical signal; performing optical domain preprocessing on the input optical signal to obtain a preprocessed optical signal; the preprocessing mode comprises power distribution, time delay, amplitude and phase adjustment; performing feature extraction calculation on the preprocessed optical signal through an on-chip diffraction optical feature extractor to obtain optical feature information which is output in parallel; the optical characteristic information is transmitted to a receiving end. According to the method, feature extraction and preliminary calculation are carried out in the optical domain, the calculation time is greatly shortened, the high-speed requirement can be met, redundant data can be compressed, the speed, bandwidth and efficiency of the whole calculation system are improved, and the severe bottleneck caused by electronic calculation is solved.

The invention discloses a satellite-ground continuous variable quantum key distribution modulation variance optimization method. The method comprises the following steps: acquiring communication data of a satellite and a ground receiving station; constructing a satellite-ground CV-QKD communication channel transmission model according to the communication data, and simulating the transmission efficiency of a satellite-ground communication link and the transmittance change intensity of a transmission channel; obtaining a key generation rate under a parameter configuration condition based on satellite-ground CV-QKD according to a simulation result, and calculating a system modulation variance; establishing a modulation variance optimization model based on a residual structure of a full-connection layer and inputting a training set; and determining an error of the modulation variance optimization model according to the loss function, and carrying out back propagation on the error to optimize the modulation variance optimization model until the loss function is converged to obtain a final modulation variance optimization model. The method can solve the problems of high computational complexity, high computing power requirement and the like caused by optimizing protocol modulation variance parameters through a traditional local search algorithm or a global search algorithm, and is suitable for a satellite-ground CV-QKD communication system.

The invention relates to the technical field of pipe network monitoring, in particular to a water supply pipe network pipe burst alarm positioning system based on real-time pressure monitoring data, and the system comprises a pressure data collection module which collects pressure data from a plurality of pressure monitoring points of a water supply pipe network; the pressure drop threshold calculation module is used for determining an alarm pressure drop threshold of each pressure monitoring point based on historical pressure data; the voltage drop alarm module is used for calculating a current time window voltage drop value and comparing the current time window voltage drop value with a voltage drop threshold value; the association alarm module is used for clustering alarm information of adjacent pressure monitoring points and combining a plurality of alarm points which are close in space into a single alarm event; the alarm positioning module is used for matching a pipe explosion node corresponding to the current alarm information by utilizing a mode recognition algorithm and quickly positioning the pipe explosion node; according to the method, the system calculates the aggregation characteristics, the description capability and the credibility of the alarm event are enhanced, and the identification and positioning efficiency of the system on the pipe explosion event in the complex pipe network environment is improved.

The invention discloses a wind power plant wind speed prediction method, system and device and a storage medium, and the method comprises the steps: optimizing the white noise amplitude weight and noise addition times in adaptive noise ensemble empirical mode decomposition CEEMDAN through employing an improved energy valley optimization algorithm IEVO, and carrying out the CEEMDAN decomposition of the historical data of a wind power plant; the decomposed data is preprocessed by adopting sample entropy SE, so that the calculation complexity of the data is reduced; for the preprocessed data, introducing a random forest algorithm RF feature selection of a heuristic strategy for optimization, and eliminating redundant features; converting the optimized data from one-dimensional time sequence data into a two-dimensional image by using a GASF (Grubby Amplitude Shift Function), and extracting image features; the extracted image features are sent to a time sequence block converter Patch TST model for wind speed prediction, and a training algorithm GPTuner based on a gradient boosting decision tree is introduced into the Patch TST model to adjust model parameters; compared with a traditional method, the accuracy of wind speed prediction can be effectively improved, and stable operation of a wind power plant is guaranteed.

The invention provides an aircraft collision probability acquisition method and device based on non-central chi-square distribution. Relates to the technical field of aircraft collision. The method comprises the following steps of: acquiring a protection box radius of a spherical collision protection box which takes the mass center of any aircraft as a sphere center on the basis of area radiuses of collision areas of two aircrafts; for any aircraft, under a three-dimensional Cartesian coordinate system, the relative position vector of the mass center position of the aircraft relative to the mass center position of the other aircraft is determined, and nominal flight path data and actual flight path data in the cruising stage are obtained; determining a relative position error matrix and a corresponding characteristic value based on an error value between the nominal flight path data and the actual flight path data corresponding to each aircraft; and processing the relative position vector, the relative position error matrix and the corresponding characteristic values by adopting a preset three-degree-of-freedom non-central chi-square distribution algorithm to obtain the collision probability between the two aircrafts. The method improves the efficiency and accuracy of collision probability estimation.

The invention discloses a model predictive control-based train formation distributed cooperative control method, which comprises the following steps of: acquiring a train tracking speed running curve, train speed limiting information and a train running resistance coefficient, and establishing a train formation model; according to a preset model predictive control algorithm, in a set predictive control time domain, according to a train formation model, a control target and constraint conditions, state variables of positions and running speeds of all trains in a train formation and control variables of control forces of all the trains in the train formation are used to predict the train formation according to state variables of the positions and running speeds of all the trains in the train formation. Respectively generating optimization control problems of the leading train and the following train in the train formation; and based on a synchronization theory, solving an optimization control problem of each train to obtain a control force of each train in the formation, and inputting the control force into a train operation control system to realize distributed control of each train in the train formation. The method is based on a model predictive control algorithm, uses a synchronization theory, and reduces the use of computing resources and communication resources in practice.

The invention discloses a coordinated scheduling method and device for a mixed hydrogen-electricity combined system, and electronic equipment, and belongs to the technical field of electrical engineering, and the method comprises the steps: reconstructing a dynamic response process model of a hydrogen-mixed natural gas network into a linearization matrix adaptive to optimal scheduling; the response conditions of an electric power system and a natural gas system under the action of various flexible resources such as an electric hydrogen production device, a hydrogen-doped gas turbine and pipeline gas storage after a disturbance event can be accurately reflected; taking the linearization matrix as a hydrogen-mixed natural gas network security constraint, and constructing a double-layer optimization model considering different benefit subjects in the joint system; reconstructing the double-layer optimization model into a single-layer optimization problem and solving the single-layer optimization problem to realize scheduling; coordinated operation of an electric power system operator and a natural gas system operator is guided through two price signals, excitation compatibility and high dispatching efficiency are achieved on the economic benefit level, wind and light abandoning is reduced on the operation safety level, power load supply is guaranteed, and meanwhile gas network blocking is relieved.

The invention relates to the technical field of power grid demand response, and discloses a power grid dispatching demand response system and method.The system comprises a state vector generation module, a state sequence generation module, a demand factor extraction module, a factor correlation analysis module, a weighted feature generation module and a resource dispatching module; the method comprises the following steps: generating a state estimation value of a power grid, carrying out vector coding to obtain a state vector, carrying out splicing and dimension reduction to obtain a state sequence, extracting demand factors from demand data, calculating a relationship among the demand factors through correlation analysis, weighting the demand factors according to factor correlation to obtain demand weighting characteristics, and finally, obtaining a state estimation result. And a load management strategy is generated based on the characteristics and the state sequence, so that resource scheduling is performed on the power grid according to the load management strategy, and the accuracy of power grid scheduling demand response is improved.

The invention relates to a rapid prediction method for curing deformation of a resin-based composite material component. The method comprises the following steps: firstly, modeling a forming mold; secondly, thermal-chemical simulation is conducted on the composite material component, and temperature loads are applied to the molded surface of the forming mold in stages: in the heat preservation stage, the temperature distribution on the molded surface of the forming mold is uniform, and in the temperature rising stage and the temperature lowering stage, temperature fields of the temperature rising stage and the temperature lowering stage are obtained according to actual measurement data; and finally, carrying out thermo-mechanical analysis on the composite material component subjected to thermo-chemical simulation to obtain the stress, strain and deformation of the composite material component. According to the method, the simulation process is simplified, the simulation steps are reduced, the prediction efficiency is improved, the solving efficiency can be improved on the premise of ensuring the prediction precision, and a basis is provided for mold design and compensation.

The invention discloses a fuel cell parameter identification method based on data driving, and the method employs an improved dung beetle optimization (IDBO) algorithm to identify parameters delta 1, delta 2, delta 3, delta 4, Rc, b and theta, obtains optimal model parameters, improves the parameter identification precision of a fuel cell model, and builds a more accurate fuel cell model. The improved dung beetle optimization algorithm is improved as follows: a Cosine-Logistic-Tent composite chaotic mapping strategy is introduced in population initialization, and the uniformity and the ergodicity of the initial position of a dung beetle population are improved; a subtraction average optimizer is adopted to update the position of the dung beetle individual rolling ball, and the development and exploration ability of the algorithm is balanced; an adaptive t distribution disturbance strategy and a greedy strategy are introduced in a dung beetle group foraging stage, so that the global search capability of the algorithm is enhanced, and the calculation time is shortened.

The invention provides a consistency diagnosis method and device for an energy storage battery, and belongs to the field of intelligent diagnosis of an energy storage battery system, and the method comprises the steps: collecting original data of the energy storage battery at a set time interval, and sorting the original data according to a time field; cleaning the original data to obtain cleaned data; extracting all static time segments of the energy storage battery according to current information in the cleaned data, and screening out long static segments; screening the highest voltage and the lowest voltage according to the voltage information in the long standing segment, converting the highest voltage and the lowest voltage into corresponding highest capacity and lowest capacity, calculating a difference value between the highest capacity and the lowest capacity, and when the difference value is greater than a set threshold value, determining that the battery is an abnormal battery; screening out single batteries with outlier capacities from the abnormal batteries, and carrying out abnormity alarm; the capacity-based consistency diagnosis can more accurately evaluate and judge the energy performance of the energy storage unit in the charging and discharging process, and the accuracy of consistency detection is improved.

The invention discloses a log anomaly detection method and device, equipment, a storage medium and a program product, and the method comprises the steps: extracting log semantic information, timestamp information and log key information from structured log data, and determining a log time interval based on the timestamp information, generating time coding data according to the log semantic information and the log time interval; performing feature enhancement on the time coding data to obtain time feature information; generating log key coding data based on the log key information; performing feature enhancement on the log key coding data to obtain log key feature information; performing feature fusion on the time feature information and the log key feature information to obtain fusion feature information, performing log anomaly detection based on the fusion feature information subjected to feature weight adjustment processing, and performing analysis in combination with the time feature and the structural feature of the log, thereby effectively capturing global information and local information of the log. And the log anomaly detection efficiency and accuracy are greatly improved.

The invention discloses an automatic extraction method for semiconductor device model parameters, and the method comprises the steps: obtaining a multi-target response through the key parameters of a semiconductor device model, and constructing and training an agent model to predict a target response mean value and uncertainty parameters; constructing a multi-objective optimization collaborative circulation framework assisted by an agent model; generating a candidate parameter population in key parameters according to a position updating mechanism of a multi-objective optimization algorithm, predicting candidate parameters by using a trained proxy model, selecting the candidate parameters according to a prediction result to carry out real simulation evaluation, adding an obtained real sample into a non-dominated file, and updating the file based on a non-dominated relationship. Adding a training set dynamic updating agent model into the real sample, generating a potential search trajectory, selecting a representative representative Pareto approximate solution from the potential search trajectory, and updating the position of the population and the direction of the next-generation search trajectory according to the representative solution selected from the file; and terminating the circulation, outputting the solution set in the file, and checking.