68 results about "Parametric search" patented technology

Systems and methods for parameter search and adjustment are disclosed. A system can maintain a model configured to generate odds data for one or more live events. The system can receive a request to generate odds values for a first live event. The request can include a set of target values for the first live event. The system can determine that the model is to be updated based on the request. The system can generate, using a set of first parameters for the first live event and prior to updating the model, first odds for the first live event in response to the request. The system can update the model based on the set of target values in the request.

The invention discloses a production line layout scheme evaluation system based on a dynamic simulation technology, and the system comprises the steps: converting equipment coordinates, detecting equipment spacing and AGV channel interference, and generating a geometric data set containing position constraint; performing median filtering on the equipment state data to generate a state data set; drag-and-drop layout is carried out through the template, safety spacing and channel width are verified, and an initial layout parameter combination is generated; generating an orthogonal table through a Taguchi orthogonal experiment method, and constructing an optimization space less than or equal to 8 dimensions; performing parameter search by adopting a particle swarm optimization algorithm, and outputting optimized layout parameters; deploying a discrete event simulation engine, and generating a layout evaluation report; and generating a verification data set and performing t verification, and triggering parameter correction and updating the scheme label according to a verification result. The design can effectively improve the feasibility, efficiency and landing reliability of the layout scheme, and significantly reduce the trial and error cost and operation risk of enterprise production line planning.

The invention provides an efficiency optimization control method of a permanent magnet synchronous motor and related equipment. The method comprises the following steps: acquiring an output current of an inverter; constructing an inverter loss model based on the output current of the inverter and the inverter loss coefficient; constructing a total loss model based on the electromagnetic loss model, the inverter loss model and an equivalent conversion method; constructing a current population by taking the plurality of d-axis current values as individuals; and performing optimization solution based on the total loss model, the current population, a PID search algorithm and an artemisinin optimization algorithm to obtain a global optimal solution and control the permanent magnet synchronous motor. According to the scheme, the driver loss is added into the total loss model, and efficiency optimization can be carried out on the whole motor driving system; in order to solve the problem that a traditional method is not suitable for an IPMSM, a PID search algorithm and an artemisinin optimization algorithm are combined, parameter search is carried out on a motor efficiency optimal point by simulating an incremental PID controller adjusting mechanism, a global optimal solution is obtained, and therefore optimal control over the click efficiency is achieved.

The invention discloses an unmanned aerial vehicle subsystem health assessment method and system, and relates to the technical field of unmanned aerial vehicle health management, and the method comprises the steps: obtaining the data of a multi-source sensor of an unmanned aerial vehicle, screening the features strongly correlated with a fault state through a Spearman rank correlation coefficient, and obtaining key monitoring parameters; according to the self-adaptive mutation mechanism, the virtual evolution strategy and the double-objective optimization strategy, an improved multi-objective genetic algorithm optimization model is constructed, then key monitoring parameters are input, and a visual report of a health state assessment result and confidence rating is obtained. According to the method, the problems that traditional single-target optimization neglects the misjudgment rate, the parameter search efficiency is low and the evaluation credibility is insufficient are solved, accurate evaluation is achieved, the evaluation accuracy is improved to 84.86%, the key misjudgment rate is reduced to 0.009%, the convergence speed is improved by 40% compared with a traditional method, the safety and real-time performance of unmanned aerial vehicle health state recognition are remarkably optimized, and the method is suitable for popularization and application. The method is suitable for embedded system deployment.

The invention discloses a two-stage algorithm selection and hyper-parameter joint optimization method, which comprises the following steps of: in the first stage, processing a training set and a test set through row sampling operation and column dimension reduction operation to form a reduced data set; randomly sampling a certain number of configurations in the hyper-parameter space of each candidate algorithm, evaluating the performance of each candidate algorithm by using the reduced data set, and extracting an optimal performance score; in the second stage, a previous algorithm is screened according to the optimal performance score to form a candidate set, and a pruned hyper-parameter search space is formed so as to reduce the calculation complexity of processor hyper-parameter search; and performing hyper-parameter optimization on the pruned hyper-parameter search space by using the original data set, and outputting an optimal algorithm adaptive to the target technical task and hyper-parameter configuration thereof. Algorithm screening and hyper-parameter tuning adaptive to a specific scene are realized through a two-stage optimization strategy, and meanwhile, the method is suitable for a traditional table type dichotomy task and aims at improving the deployment efficiency and performance of a machine learning model.

The invention relates to the technical field of data processing, and discloses a computing power server system layer optimization method and system oriented to a high-load scene. The method comprises the steps of collecting micro performance indexes such as the CPU instruction cycle number and the page table missing frequency, constructing a three-layer causal directed acyclic graph through Granger causal inspection, reducing a parameter search space based on bottleneck node reverse backtracking, generating an interpretable optimization decision with a causal path and contribution degree quantification, and carrying out optimization on the basis of the interpretable optimization decision. The problems that the performance bottleneck root cause cannot be accurately positioned and the optimization result lacks transparency in the prior art are solved. According to the method, bottleneck node reverse backtracking and parameter space pruning are performed based on the causal atlas, so that the problem of low optimization efficiency caused by incapability of accurately positioning a performance bottleneck root cause and blind exploration of a parameter space in the prior art is solved.

The invention discloses a partial discharge signal wavelet denoising method based on all-parameter space traversal optimization. The method comprises the following steps: S1, initializing parameters; s2, a noisy signal is read; s3, constructing a wavelet basis traversal cycle; s4, constructing a decomposition layer number traversal cycle; s5, denoising and index calculation are executed; s6, comparing and updating a global optimal solution; and S7, carrying out loop iteration until all preset wavelet base order and decomposition layer combinations are traversed. According to the method, the parameter search space containing various wavelet bases and different decomposition layer numbers is constructed, so that automation and optimal matching of denoising parameters are realized; compared with a traditional method of selecting wavelet parameters depending on artificial experience, the method has the advantages that the influence of subjective factors on the denoising effect is effectively avoided, and the adaptability and robustness of the algorithm to different field environments and different types of partial discharge signals are remarkably improved.

The invention relates to the technical field of industrial process automatic control, and discloses an automatic control method for a water sample analysis process, which comprises the following steps: establishing a unit step response reference model for representing a normalized standard track of a controlled object; iteratively searching an optimal amplitude scaling and time elastic factor in the two-parameter search space to minimize the fitting residual error of the reference model and the real-time data; the optimal amplitude scaling factor is utilized to determine a projection steady-state value to drive an execution unit, and the sampling interval is adaptively adjusted according to the optimal time elastic factor, the time elastic factor is introduced to realize closed-loop compensation of system kinetic parameter drift, a steady-state target can be accurately locked in an unbalanced state, and the stability of the system is improved. And the problem of control model mismatch caused by device aging or environment fluctuation is solved.

The present application provides a kind of vital signs detection signal denoising method and device, it is related to physiological perception and signal processing technical field, including: based on millimeter wave radar's Doppler technique, obtains the original phase signal containing physiological signal;Original phase signal is carried out variational mode decomposition based on the search algorithm of variational mode decomposition super parameter optimization algorithm optimized by particle swarm optimization algorithm, obtain the vibration modal function information corresponding to the original phase signal;Wherein, the particle swarm optimization algorithm uses permutation entropy and fuzzy entropy as fitness function;After denoising processing is carried out to the vibration modal function, the vibration modal function after denoising processing is recombined, and high-precision denoising processing is obtained after physiological signal;From the high-precision denoising processing physiological signal, extract respiratory and heartbeat physiological signal.

The invention discloses a Xinanjiang model multi-target parameter calibration method, system and device based on multi-department collaboration and a medium, and belongs to the technical field of hydrology and water conservancy. The method comprises the steps of obtaining a drainage basin characteristic index value of a target drainage basin; according to the drainage basin characteristic index value, the actually measured drainage basin total outflow is calculated; based on the drainage basin characteristic index value of the target drainage basin, the Xinanjiang model and the actually measured drainage basin total outflow, a multi-department multi-target optimization model including multi-department target spaces is constructed, and the multi-department target spaces include multi-target spaces corresponding to all decision-making departments; and taking all parameters in a pre-obtained Xinanjiang model as a public parameter space, and performing parameter search in the public parameter space by adopting an evolutionary optimization algorithm based on the multi-department multi-objective optimization model until the maximum number of iterations is reached, thereby obtaining an optimal parameter solution set. According to the invention, in one calibration process, the parameter solution set meeting the differentiated requirements of different decision departments is obtained at the same time.

The invention relates to the field of integrated circuit layout design, provides a circuit device model parameter extraction and optimization method based on artificial intelligence, and aims at solving the technical problems that a traditional EDA tool is high in artificial dependence, low in optimization efficiency, poor in algorithm adaptability and split in tool. Automatic data interaction among the modules is realized through a standardized API; preprocessing and intention recognition are carried out on the multi-modal input, and user requirements are converted into formatted data; searching similar circuit historical parameters based on the knowledge base and generating a recommendation list; extracting a target curve through an image recognition model and carrying out standardization processing; dynamically matching an optimization algorithm according to circuit characteristics and adjusting hyper-parameters in real time; multi-tool collaborative optimization control is realized, and the parameter search progress is dynamically updated; and outputting the optimal parameter combination and carrying out verification iteration. The method is used for high-precision automatic optimization and full-process closed-loop verification of circuit parameters.

The invention provides a dam seepage parameter inversion method based on an improved reptile search algorithm, which is characterized by comprising the following steps of: aiming at prototype monitoring data of dam seepage characteristics when loads comprise water pressure, temperature and rainfall factors, firstly, separating an accurate hydrostatic pressure deformation component from the prototype monitoring data; independent fitting is carried out on effect components caused by water pressure to enhance the physical interpretability of an inversion process, so that a feasible path is provided for accurate identification of seepage parameters in a multi-field coupling environment; the method comprises the following steps: S1, separating historical monitoring data; s2, constructing a dam seepage numerical simulation model as an agent model; s3, performing seepage parameter search based on an improved reptile search algorithm RSA; according to the method, the precision and efficiency of seepage parameter inversion are remarkably improved, the physical interpretability of the inversion process is enhanced, and the dam seepage parameters are accurately and efficiently obtained.

The invention discloses a product key production parameter mining method and system based on user demand classification, and relates to the technical field of artificial intelligence. The method comprises the following steps: obtaining user preference data containing paired preference samples and a candidate parameter space formed by mass-producible parameter combinations; based on the data and the space, an improved self-adaptive direct preference optimization algorithm is adopted to train a strategy model, a dynamically calculated self-adaptive reward margin is introduced in the training process so as to adjust a model updating gradient according to a sample differentiation degree, and a Coubeck-Leibler divergence constraint is applied to limit parameter search in a candidate parameter space; and after the strategy model is converged, determining a group of product parameter combinations with the maximum posterior probability from the candidate parameter space according to the optimized model, and outputting the product parameter combinations as key production parameters.

The invention belongs to the related technical field of unmanned surface vehicle intelligent control and reinforcement learning optimization, and particularly relates to a gradient-free reinforcement learning method based on an acceleration and deceleration strategy, which comprises the following steps: reducing an original high-dimensional parameter search space to an effective low-dimensional parameter search space, evaluating the quality of an optimization result under the effective low dimension, and if the quality is not satisfied, executing the step 1; if the to-be-learned neural network does not exist, the effective low-dimension dimensionality is increased until an effective low-dimension parameter search space meeting the quality requirement is determined, a set of initial parameter solutions are randomly generated in the space, and each initial parameter solution is composed of values of all parameters of the to-be-learned neural network; determining a parameter solution updating direction based on the current group of initial parameter solutions; and moreover, the current group of initial parameter solutions are mapped back to the original high-dimensional parameter search space to serve as a group of strategy parameter solutions, and the accumulated total reward of each strategy parameter solution is independently evaluated, so that the initial parameter solutions are updated in combination with the parameter updating direction, and the updating operation is repeatedly executed. The sampling cost is low.

This invention discloses an optimization algorithm for stress cloud map inversion of hydropower unit bolts during service, relating to the field of hydropower unit bolt stress measurement technology. The algorithm includes the following steps: S1: Finite element simulation model construction, including the following steps: S2: Data cleaning of the physical field simulation data and field measurement data obtained in step S1 to obtain a physical field dataset; S3: Stress cloud map inversion model construction; S4: Optimal parameter search. This invention overcomes the shortcomings of existing technologies in actual environment modeling and structural optimization, providing a new technical approach for the maintenance and performance improvement of hydropower unit bolts. It achieves high-precision simulation in actual operating environments, overcoming the shortcomings of existing technologies in digital modeling. Based on theoretical physical constraints, it can construct a reinforcement learning algorithm to invert the stress distribution of bolts during long-term service, providing comprehensive information for structural health monitoring, while existing technologies have certain limitations in this regard.

The invention provides a die-casting island process parameter optimization method and system based on machine learning, and relates to the technical field of die-casting processes, and the method comprises the steps: obtaining process parameters in a die-casting process, calculating an energy loss value and an entropy weight of each process stage, recognizing a target process stage, and carrying out the local optimization. Constructing a low-dimensional space for the historical process parameters, and clustering based on geodesic distances; selecting a historical parameter with the optimal quality as a search starting point, and executing parallel parameter search to obtain an optimal process parameter combination; and an adjusting instruction is issued to the die-casting island control system. According to the method, the quality of die-casting products can be improved, energy consumption is reduced, and self-adaptive optimization is achieved.

Provided are a hyperparameter search method and a hyperparameter search device. The hyperparameter search method comprises: obtaining a hyperparameter set for a predetermined task feature dimension, each task feature dimension in the predetermined task feature dimension comprising a predetermined plurality of feature values, the hyperparameter set comprising a hyperparameter corresponding to each task feature combination in a plurality of task feature combinations, the plurality of task feature combinations being obtained by one-to-one combination of each feature value under each different task feature dimension, and the hyperparameter corresponding to each task feature combination being an optimal hyperparameter pre-searched in a first hyperparameter search range for each task feature combination; searching, from the hyperparameter set, a hyperparameter corresponding to a predetermined K task feature combinations according to a first task feature combination of a to-be-processed task, the first task feature combination being a combination of feature values of each task feature dimension in the predetermined task feature dimension of the to-be-processed task; and searching a hyperparameter corresponding to the to-be-processed task based on the searched hyperparameter.

The application belongs to the technical field of natural language processing, and specifically designs an integrated retrieval enhancement method of a large language model, an electronic device and a storage medium. The integrated retrieval enhancement method specifically is that a controller calls multiple retrievers according to user input, returns multiple-source multiple-document, and integrates and disturbs different documents into multiple knowledge sections through multiple processing modes, and respectively inputs a generation module. After the generation module returns multiple replies, the control module selects the optimal reply through the consistency between the replies and an objective scorer. The optimal parameter search is converted into a non-derivable optimization problem of a target function, the optimal retrieval enhancement configuration can be found through a meta-heuristic search algorithm, and the ability of the large language model on factual problems is effectively improved.

The present invention relates to the field of time series data prediction and provides an automatic learning method and system for time series data prediction. The method includes using Spark to acquire time series data and preprocess the time series data; setting a hyperparameter search space and a corresponding hyperparameter search algorithm for a neural network; and distributing tasks to a cluster so that the cluster uses the neural network to perform hyperparameter tuning and model training on the tasks to obtain the optimal hyperparameter combination. Ray Serve is then used to deploy the neural network with the optimal hyperparameters on each node for use in predicting time series data. The present invention can efficiently, quickly, and conveniently automatically complete model training, hyperparameter search optimization, and model deployment for time series data prediction.

This invention discloses a behavior-adaptive continuous identity authentication method and system. Through component attribution analysis, the basic continuous identity authentication model is deconstructed into multiple computational units. These computational units are used as components, and an ablation vector is designed to determine whether the component's parameters are set to zero during inference. Ablation experiments are conducted on the components based on a user behavior dataset to obtain a set of optimal-performing components. Through parameter search adaptation, scaling factors are applied to the parameters of key components based on the current user's behavior data. With the optimization objective of maximizing identity authentication accuracy, an optimization search is performed to obtain the optimal scaling factor. This optimal scaling factor is then applied to the key components of the basic continuous identity authentication model to generate an adaptive continuous identity authentication model for the current user's behavior, enabling continuous identity authentication for the current user. This invention improves the authentication accuracy and computational efficiency of continuous identity authentication, and is particularly suitable for mobile devices.

The application relates to the technical field of industrial process automation control, and discloses an automatic control method for a water sample analysis process, which comprises the following steps: establishing a unit step response reference model representing a normalized standard track of a controlled object; iteratively searching for an optimal amplitude scaling and a time elasticity factor in a double-parameter search space, so that the reference model and real-time data are fitted to minimize residual errors; and determining a projection steady-state value by using the optimal amplitude scaling factor to drive an execution unit, and adaptively adjusting a sampling interval according to the optimal time elasticity factor. The application realizes closed-loop compensation for system dynamics parameter drift by introducing the time elasticity factor, can accurately lock a steady-state target under a non-equilibrium state, and solves the problem of control model mismatch caused by device aging or environmental fluctuation.

The application discloses a tunnel point cloud registration processing method, system and platform fusing static noise features, generates and acquires first data corresponding to a tunnel, processes the first data by combining acceleration and curvature filtering, generates second data corresponding to the first data, adjusts the point cloud resolution corresponding to the second data by combining adaptive voxel downsampling, extracts and processes feature data corresponding to the second data, constructs a corresponding auxiliary point pair set based on noise auxiliary points, establishes a corresponding initial matching relationship by combining global depth consistency, iteratively optimizes and processes the initial matching by using a weighted geometric optimization algorithm, simultaneously searches for global parameters by using a particle swarm optimization algorithm, implements residual static noise filtering processing, generates corresponding third data, and generates a corresponding system and platform, thereby providing an efficient and robust solution for tunnel point cloud registration, and meeting high-precision construction quality detection and long-term maintenance requirements.

The invention provides a mutual inductor deviation identification method and system based on a pigeon inspired collaborative optimization algorithm, and relates to the technical field of a novel electric power system.The method comprises the steps that under a distributed mutual inductor network, measurement data of mutual inductor nodes are obtained through a synchronous vector measurement unit; based on the measurement data, solving a pre-established system parameter model containing a mutual inductor ratio correction coefficient to obtain a local optimal solution of the deviation of the mutual inductor ratio correction coefficient; and according to the local optimal solution, performing deep search in the parameter search space by using a pigeon inspired collaborative optimization algorithm to obtain a search result, and determining a mutual inductor deviation identification result according to the search result. Through the mode, a more accurate mutual inductor deviation identification result is obtained, and the accuracy of mutual inductor deviation identification is improved.

The application relates to the technical field of artificial intelligence, and provides a method, device and system for heterogeneous cluster parallel training of a large model. The method comprises the following steps: acquiring model structure parameter information representing a large model to be trained and device parameter information representing a heterogeneous cluster for training the large model; determining a parameter search space according to the parameter information, and searching for a target parameter combination in the parameter search space according to a preset search rule; and performing parallel training on the large model by the heterogeneous cluster based on the target parameter combination, wherein the target parameter combination is a parameter combination in the parameter search space, which makes the large model consume the least time in one round of training. The application provides an automatic search scheme of a target parameter combination to replace a parameter search scheme in the related art, so that the time consumption of the target parameter combination can be reduced, and the model development cycle can be shortened.

This invention belongs to the field of radiation source pulse sorting technology, specifically relating to a radiation source pulse sorting method, program, device, and storage medium. This invention models the determination process of the neighborhood radius and minimum number of neighborhood points for DBSCAN clustering in the pre-sorting of radiation source pulses as a multi-objective optimization problem, designs a multi-objective hoarfrost ice crystal optimization algorithm, and introduces multiple clustering performance indicators as optimization objectives under a unified evaluation framework to jointly constrain multiple structural performance aspects of the pre-sorting results. Simultaneously, an ice crystal subpopulation structure is introduced into the hoarfrost algorithm, integrating water molecule adsorption and soft frost search mechanisms, enabling the parameter search process to maintain both global search capability and good local search capability, ensuring the basic consistency of the pulse sequence structure in the pre-sorting results. This provides reliable input for the subsequent main sorting of each radiation source pulse sequence, reducing the problem of mis-batch sorting in radiation source pulses.

The application discloses a kind of PFC system real-time energy efficiency optimization method and system based on dynamic weight particle swarm algorithm, comprising: first, the multidimensional parameter search space of PFC system is constructed, and system operating state parameter is collected in real time. Then, initialize particle swarm population, and iteration optimization is carried out using dynamic weight particle swarm algorithm. Algorithm is updated particle position and speed by dynamically adjusting inertia weight, combining particle own historical optimum and population global optimum information, and finally finds global optimum energy efficiency parameter combination. Finally, according to the combination generation control instruction and issue to each execution unit of PFC system, realize the real-time adjustment of parameter and the closed-loop optimization of system energy efficiency. The application effectively improves the optimization speed and global optimization ability, and guarantees the efficient and stable operation of PFC system.

The invention discloses a chip accelerator collaborative optimization method based on an AutoCoDA framework, and belongs to the technical field of machine learning model optimization and hardware acceleration, and the AutoCoDA framework is an automatic collaborative design framework of an algorithm and a chip accelerator. The method comprises the following steps: constructing a resource prediction model for predicting hardware resource consumption; setting a parameter search space of the model, generating candidate configuration, and evaluating hardware resource consumption by using the resource prediction model; calculating a target function value based on the precision index configured by the candidate model and the predicted resource consumption value; on the basis of the target function value, updating a search strategy through an optimization algorithm, and iteratively searching optimal candidate model configuration; and the optimal candidate model configuration is converted into hardware executable codes, and integration and deployment are carried out on the target FPGA platform. According to the method, a hardware resource feedback mechanism is embedded in a machine learning model structure search process, so that the search efficiency is remarkably improved, and an optimal balance scheme of precision and resource occupation is automatically obtained.

The present invention discloses a GRNN smoothing factor setting method and system based on a variogram model, comprising: preprocessing sampled data; obtaining an omnidirectional experimental variogram of the preprocessed sampled data, and fitting the omnidirectional experimental variogram to obtain a range value; using the range value as a smoothing factor to perform GRNN prediction; constructing a GRNN model based on the smoothing factor that satisfies the prediction result and the preprocessed sampled data, and predicting the grade value at an unknown location using the GRNN model. The present invention makes it easier to obtain the optimal smoothing factor, improves the efficiency of parameter search, and has greater adaptability.

The application provides a search method and device for secondary permutation polynomial interleaving parameters, and belongs to the technical field of communication. The method comprises the following steps: receiving the data block length N of a communication system as an interleaving length; reducing redundancy candidates by equivalent class parameter compression; generating two candidate sets of parameters; performing permutation combination on the two candidate sets to obtain all parameter candidate pairs, and sequentially performing algebraic metric preliminary screening and S distance fine screening on the candidate parameter pairs to output high-performance interleaving parameters; and configuring the screened optimal QPP interleaving parameters into a Turbo code interleaver of the communication system to perform interleaving processing on actual signals. The application can be used in various communication systems, solves the problems of low search efficiency, large candidate set scale and insufficient local burst error suppression capability of existing QPP interleaving parameters, and effectively reduces the complexity of parameter search and simulation workload.