445 results about "Predicting performance" patented technology

Platforms, systems, and methods for genetic generalization in synthetic biology development. According to one aspect, there is provided a method for predicting performance associated with genetic edits, the method comprising: receiving, by a platform, information about a strain of a microorganism, wherein the information about the strain comprises information describing a plurality of genetic edits to a base strain of the microorganism; generating, by the platform, a set of genetic embeddings based on the information about the strain, wherein the generating comprises processing the information about the strain using one or more embedding models, wherein each of the one or more embedding models: receives the information about the strain of the microorganism as input; and applies computational transformations to the input using a corresponding embedding model to generate a multi-dimensional vector representation for each of the plurality of genetic edits.

The invention belongs to the technical field of aero-engine performance testing, particularly relates to a physical constraint-based aero-engine state prediction model construction method and system, and aims to solve the problems of high calculation complexity and poor data quality of an existing physical information model. The method comprises the following steps: acquiring historical operation data of the aero-engine and a physical constraint rule set of engineering simplification; predicting performance parameters by adopting a deep learning model; constructing a total loss function formed by weighting a data loss item and a physical loss item to train the model; wherein the physical loss item is generated based on the deviation degree of the predicted performance parameter and the engineering simplified physical constraint rule set, and is used for replacing the complex partial differential equation constraint. According to the method, the engineering simplified physical rule is introduced, so that the calculation overhead of model training is remarkably reduced, the model is effectively guided to learn the characteristics conforming to the physical rule, and the accuracy and generalization ability of the prediction model are remarkably improved under the condition of limited data.

The invention discloses an agricultural load prediction method and system based on multivariate time sequence decoupling multi-modal learning, and belongs to the technical field of agricultural load prediction. Comprising the steps of collecting historical agricultural load and meteorological data; decomposing historical agricultural load and meteorological data by using multivariate variational mode decomposition to obtain cycle, trend and residual mode components; and respectively constructing a time convolutional neural network, a bidirectional gating cycle unit and a support vector regression model for the decomposed period, trend and residual modal component data set, and fully mining feature information of each mode after decomposition, thereby realizing accurate prediction of agricultural load. According to the method, the potential nonlinear space-time coupling relationship between the agricultural load and the meteorological factor is captured, the prediction effect in a seasonal periodic fluctuation scene of the agricultural load and a long-term trend and agricultural load abnormal scene is improved, the agricultural load prediction precision is improved, and a support is provided for reliable and stable operation of a power grid.

The invention discloses a magnetic anomaly data de-noising method and de-noising system based on step-by-step U-Net, and relates to the technical field of geophysical exploration, and the method comprises the steps: carrying out the forward modeling calculation based on a magnetic anomaly model in a simulation region, and obtaining a synthetic magnetic anomaly data set; a U-Net step-by-step denoising network model is constructed; designing a self-adaptive multi-stage training mechanism based on mean square error minimization; training the U-Net step-by-step denoising network model through the training set, taking parameters of the U-Net step-by-step denoising network model as initial weights, and performing fine tuning on the U-Net step-by-step denoising network model by utilizing supervised learning; the verification set is used for verifying the effect, and the effectiveness of the whole step-by-step denoising network model is verified according to the prediction effect of the test set; a forward noise adding process and a reverse noise removing process are designed, network behaviors are automatically adjusted according to noise steps, the problems of high training cost and poor performance when a deep learning model processes colored noise are effectively solved, and the problem of low signal-to-noise ratio is better solved.

The invention belongs to the technical field of analog integrated circuit design automation, and discloses an analog integrated circuit cross-process performance prediction method and system based on Transform transfer learning, and the method comprises the steps: 1, carrying out the preprocessing of analog integrated circuit sample data; 2, serializing the sample data according to a preset sequence, mapping each parameter into vector representation, adding a global abstract vector, and splicing according to a fixed sequence to form an input sequence; 3, encoding the input sequence to obtain an output sequence; 4, inputting the global features into the regression head network, and outputting a performance index prediction value; 5, training is carried out, network parameters obtained through pre-training of the source technology are migrated to the target technology, fine adjustment is carried out on part of network parameters of a target technology data set, and cross-technology performance prediction is achieved; and 6, performing forward reasoning on operational amplifier design parameters under a given target process according to the steps 2-4 to obtain a performance prediction result. The method improves the stability and efficiency of performance prediction.

The invention discloses an aluminum-based material rolling process optimization method based on a response surface method and machine learning, which comprises the following steps: collecting related data of an aluminum-based material rolling process, and establishing a rolling process database; determining key rolling process parameters influencing the performance of the aluminum-based material based on the database; a mathematical model used for describing the key rolling process parameters and the relation between the interaction of the key rolling process parameters and the aluminum-based material performance indexes is established, and prediction results of the aluminum-based material performance indexes under different key rolling process parameter combinations are calculated according to the mathematical model. Aluminum-based materials with performance indexes meeting preset requirements and key rolling process parameter combinations corresponding to the aluminum-based materials are predicted to serve as a preliminary optimization result data set; and constructing a back propagation artificial neural network model optimized by a genetic algorithm to predict aluminum-based material performance indexes corresponding to different key rolling process parameter combinations, and screening out an optimal key rolling process parameter combination and an aluminum-based material performance index corresponding to the optimal key rolling process parameter combination from the aluminum-based material performance indexes. According to the method, the quality of the aluminum-based material is remarkably improved through the proposed collaborative optimization strategy.

The invention provides an intelligent storage location optimization method and system, and belongs to the technical field of storage management, and the method comprises the steps: obtaining the data information of commodities in a storage system, constructing a storage location optimization model, comprising a comprehensive objective function taking maximization of space utilization rate and sorting efficiency and minimization of storage cost as objectives and constraint conditions based on physical rules and business rules; solving the storage location optimization model by using an optimization algorithm, and generating a storage location distribution scheme and prediction performance data; executing the storage location allocation scheme, and collecting actual storage location data and actual operation performance data; comparing the actual storage location data with the storage location allocation scheme to obtain a scheme execution coincidence rate; comparing the actual operation performance data with the predicted performance data to obtain a performance deviation rate; and based on the scheme execution coincidence rate and the performance deviation rate, adjusting the constraint condition of the storage location optimization model and / or the weight coefficient of the comprehensive objective function to obtain an updated storage location optimization model, and carrying out storage location allocation.

A work order management system automates the process of scheduling maintenance tasks and generating corresponding work orders via analysis of monitored data generated by the industrial assets. The work order management system can monitor status and operational data from industrial devices on the plant floor, as well as mobile industrial robots that traverse the plant floor, and initiate creation of work orders based on a determination that the monitored industrial data indicates a current or predicted performance risk requiring investigation or maintenance. The system can leverage generative artificial intelligence (AI) or other types of AI in connection with determining when and how to schedule a maintenance task intended to mitigate asset risk.

In one embodiment, a device determines a mapping between a network destination and Border Gateway Protocol (BGP) peers located across a plurality of autonomous systems for which the network destination is reachable. The device causes, based on the mapping, performance of probing tests along a plurality of paths to the network destination and via the BGP peers, to obtain path performance measurements for the plurality of paths. The device uses a prediction model to generate predicted performance metrics for the plurality of paths based on the path performance measurements. The device configures, based on the predicted performance metrics for the plurality of paths, the BGP peers with BGP peering policies to convey application traffic associated with the network destination via particular path from among the plurality of paths.

The invention discloses a training method of an inference deployment configuration performance prediction model of a large language model and an inference deployment configuration recommendation method and device.The method comprises the steps that a first structural feature, a first interaction feature and throughput performance data under different structural parameters and configuration parameters of a sample model are obtained; comprising structure parameters, configuration parameters and operation resource quantization parameters of the large language model; taking the throughput performance data as a regression target, and training a regression model by using the first structural feature and the first interaction feature to obtain a reasoning deployment configuration regression model; the reasoning deployment configuration regression model is used for predicting throughput performance data of the large language model under given configuration. According to the method, systematic modeling is carried out on a complex mapping relation among a model structure, input and output characteristics, a parallel strategy, concurrent configuration and throughput performance, and the performance is accurately predicted in a data driving mode, so that optimal configuration is recommended, and efficient and reusable language model reasoning deployment optimization is realized.

The invention discloses a porous ceramic performance prediction and formula optimization method based on a machine learning technology, and the method comprises the following steps: collecting different structure parameters, preparation process conditions and performance data of porous ceramic, and constructing a data set; inputting the data set into a machine learning model for training, and establishing a structure-process-performance correlation model; based on the correlation model, target performance parameters are set, and the optimal structure parameters and the preparation process of the porous ceramic are obtained through reverse optimization of a machine learning algorithm; and preparing the porous ceramic according to an optimization result. By adopting the method, the porous ceramic can be efficiently and accurately optimized and designed, the performance of the porous ceramic can be improved, the research and development period can be shortened, and the cost can be reduced.

The invention discloses a multi-modal fusion-based advertisement content generation method, which comprises the following steps of: firstly, extracting unified features of original multi-modal data, and performing semantic fusion and similarity enhancement to obtain fusion representation; and outputting the initial creativity by the generative network in combination with user feedback, calculating a matching degree, generating a market adaptation adjustment vector, performing iterative optimization on the creativity, and performing optimization according to a prediction effect score, thereby finally generating high-precision and personalized advertisement content. According to the invention, the personalized level, market suitability and generation efficiency of the advertisement content are obviously improved, the trial and error cost is reduced, and efficient and intelligent advertisement creation is realized.

The invention provides a mountain road coal gangue slope ecological restoration method, which comprises the following steps: acquiring real-time monitoring data from a coal gangue slope through a sensor network, including weathering degree and compaction density indexes, and obtaining an initial feature set; according to the initial feature set, carrying out preliminary grouping on the side slopes by adopting a clustering analysis method, and determining a classification standard threshold value; feedback data in the restoration implementation process are obtained and compared with the preliminary groups, and the effect deviation degree is judged; if the effect deviation exceeds a preset threshold value, a classification standard threshold value is updated through a regression analysis model, and an adjusted classification system is obtained; for the adjusted classification system, extracting a corresponding repair scheme template from a database, and generating an optimization scheme version; performing virtual testing on the optimization scheme version through an analog simulation module to obtain a prediction effect index; and collecting subsequent monitoring data according to the final execution parameter, and performing iterative comparison with the prediction effect index to obtain a further adjustment signal.

The invention is suitable for the technical field of turbochargers, and provides a method for rapidly predicting the performance of a gas compressor of a vehicle turbocharger, which comprises the following steps of: obtaining a gas compressor performance MAP graph and structural parameters through a test; the performance of the gas compressor is predicted through the one-dimensional prediction model; obtaining the pressure ratio and efficiency deviation of the model prediction value and the test value under different working conditions; carrying out dimensionless conversion on the pressure ratio and the efficiency deviation through design point data, and constructing a machine learning training data set; training and verifying the dimensionless deviation by using machine learning; new compressor geometric parameters are calculated through a one-dimensional design program according to new design point requirements; performing performance prediction on the new gas compressor through the one-dimensional prediction model; and the new compressor performance predicted value is corrected through a machine learning model, and an accurate compressor performance MAP graph is obtained. According to the method, machine learning and a physical model are combined, and the performance characteristics of the turbocharger compressor can be accurately obtained under the condition that a large amount of workload is saved.

The invention discloses a Tokamak plasma rupture prediction method based on cWGAN and TCN, which takes AUC as a measurement index to evaluate the effectiveness of a model, and adopts a conditional Wasserstein generative adversarial network (cWGAN)-based minority class sample generation method for solving the problem that the number of minority class samples is limited. Gradient penalty (GP) is introduced in a training stage to improve the quality of generated samples and training stability, and an inverse frequency mini-batch minority class equilibrium training strategy is adopted to enable a generator to fully learn distribution characteristics of broken samples, so that high-quality minority class samples are generated and a training set is expanded. A Transform structure is introduced on the basis of a time convolutional network (TCN), local time sequence features are efficiently extracted by using the TCN, and the Transform enhances the expression ability of a model for a long-time dependency relationship and global features, so that the prediction effect is improved.

A work order management system automates the process of scheduling maintenance tasks and generating corresponding work orders via analysis of monitored data generated by the industrial assets. The work order management system can monitor control, status, or operational data from industrial devices on the plant floor, and initiate creation of work orders based on a determination that the monitored industrial data indicates a current or predicted performance risk requiring investigation or maintenance. The system can leverage generative artificial intelligence (AI) or other types of AI in connection with determining when and how to schedule a maintenance task intended to mitigate asset risk. The system can also factor contextual information when determining whether to create and schedule a work order, such as the cost of operator or maintenance time, scheduled plant downtimes, environmental factors (e.g., humidity), time of year, supplier issues, and other considerations.

The embodiment of the invention relates to the technical field of operation and maintenance, and discloses an intelligent fault self-healing and performance optimization method and device based on K8s and MCP, and the method comprises the steps: obtaining standard multi-dimensional data which is a comprehensive data set which accords with the MCP protocol specification and reflects the overall operation condition and performance of K8s; performing detection processing on the standard multi-dimensional data based on a fault detection model, identifying fault risk information, and positioning to a target fault based on the fault risk information and a preset knowledge graph; analyzing the standard multi-dimensional data by combining time sequence analysis with statistical analysis, predicting a prediction performance problem after the current moment, and identifying performance bottleneck information; generating a fault solving instruction based on the fault risk information and the target fault, and executing the fault solving instruction to realize fault self-healing; and generating a performance optimization instruction based on the performance bottleneck information and the prediction performance problem, and executing the performance optimization instruction to perform performance optimization. And the data interoperability is improved based on the MCP protocol specification.

The invention provides a loan default prediction method and device, and relates to the technical field of risk assessment. The method comprises the steps that historical data are acquired, the historical data comprise multiple pieces of historical user loan data, and each piece of historical user loan data comprises basic features and a corresponding loan default label; clustering the historical data, and performing default risk assessment on each clustered data set to obtain a risk level of each clustered data set; determining an oversampling strategy of each clustering data set based on the risk level of each clustering data set; on the basis of the oversampling strategy of each clustering data set, oversampling is carried out on each clustering data set; and based on the balanced data set, training a preset default prediction model to obtain a loan default prediction model for loan default prediction. And blind user manufacturing in a high-risk group is avoided, so that the model is more stable, and the loan default prediction effect is improved.

The invention discloses a repair material performance prediction and formula optimization method based on a machine learning algorithm, and particularly relates to the crossing field of artificial intelligence and material science, and the method comprises the steps: constructing a structured multi-modal feature library, carrying out the data processing through dual-index and differential noise filtering, constructing an isoproton model set guided by a physical mechanism, and carrying out the optimization of the repair material performance prediction and formula optimization. Comprising three targeted sub-models including a graph neural network, a time sequence convolutional network and a gradient boosting tree, outputs of the sub-models are dynamically fused through a meta-learner, combined prediction of material performance is achieved, a potential formula is actively searched in a high-dimensional solution space through dimension reduction mapping and Bayesian optimization, and the performance of the material is predicted. The method comprises the following steps: performing gradient-guided constraint optimization by using a differentiable physical-data fusion simulator to generate an optimal formula scheme, and finally realizing automatic feedback of new data and autonomous evolution of a model through a triggering rule and a local incremental learning mechanism based on uncertainty and deviation to form a complete self-evolution closed-loop system.

The invention relates to a method and a system for predicting a performance degradation trend of a proton exchange membrane fuel cell. The method comprises the following steps: acquiring state monitoring data of the proton exchange membrane fuel cell; a power spectrum threshold-Kalman joint algorithm PST-KF is adopted to carry out noise reduction smoothing processing on the state monitoring data; key feature parameter extraction is carried out on the output voltage degradation data after noise reduction by adopting a regular mutual information selection method; dividing the key feature parameter set into data sample subsets based on different performance degradation degrees by adopting a TG-ISODATA clustering algorithm, and dividing the data sample subsets into a training set and a test set; a performance degradation trend model SK-Mama is constructed; an improved WSA algorithm is adopted to optimize the SK-Mama model, and an IWSA-SK-Mama prediction model is constructed; performing training and performance evaluation on the IWSA-SK-Mama prediction model by using the training set and the test set; and then the performance degradation trend of the proton exchange membrane fuel cell is predicted through the trained model and the tested model. The method and the system can improve the prediction precision of the performance degradation trend of the proton exchange membrane fuel cell.

The invention belongs to the technical field of bridge construction monitoring, and discloses a bridge construction monitoring system based on the Internet of Things. The system comprises a prediction analysis early warning module, a control strategy generation module, a construction quality scheduling module and a visual decision support module, and is characterized in that multi-stage preprocessing is performed on a first processing data set to obtain a second processing data set, the second processing data set is analyzed to obtain a risk early warning report, and on the basis of the risk early warning report, a control strategy is generated; the method comprises the steps of generating a first processing data set, generating a strategy control report, performing conversion and execution sequence processing on the strategy control report to obtain a system instruction set, processing a second processing data set, a risk early warning report and the system instruction set, and providing support for manual decision making and instruction issuing based on a visual panel. The method has the remarkable advantages of being high in original data integration capacity, good in risk active prediction effect and high in control response efficiency.

An example method includes receiving, by a software-defined networking in a wide area network (SD-WAN) system having a first WAN link and a second WAN link for an SD-WAN service, WAN link characterization data for the first WAN link over a time period; determining, by the SD-WAN system based on processing the WAN link characterization data for the first WAN link using a machine learning model trained with historical WAN link characterization data for one or more WAN links, an indicator of a predicted performance metric of the first WAN link at a future time; and reassigning, by the SD-WAN system based on the indicator, an application from the first WAN link to the second WAN link.

The application relates to a business recommendation method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining current investment business data; calculating a correlation coefficient between the current investment business data and original input data; wherein the original input data is training data of a to-be-migrated model; inputting the current investment business data into the to-be-migrated model to obtain a first recommendation result; inputting the current investment business data into a business recommendation model to obtain a second recommendation result; wherein the business recommendation model is obtained by training historical investment business data; processing the correlation coefficient, the first recommendation result and the second recommendation result to output a target recommendation result; and the target recommendation result is used for recommending investment business. The target recommendation result obtained in the method can learn the knowledge in the to-be-migrated model, mine data from multiple angles, sufficiently utilize the model resources of the to-be-migrated model, and improve the prediction effect of the recommendation result.

The invention provides a chip testing method and device and a medium, and the method comprises the following steps: determining an intermediate performance value of each target clock domain according to the clock frequency and predicted performance value of each target clock domain of a to-be-tested chip; determining a minimum value in the plurality of intermediate performance values as a target performance value; performing a performance test on the to-be-tested chip to obtain an actual performance value of a target clock domain; and if the actual performance value is not less than the target performance value, determining that the to-be-tested chip passes the test. According to the chip test method provided by the invention, whether the to-be-tested chip passes the test can be known only by performing the performance test on the target performance value. In this way, the number of performance values needing to be subjected to performance testing is greatly reduced, and therefore the number of times of data simulation and consumption of analysis resources are reduced.

The invention discloses a volcanic gas reservoir productivity prediction method and system based on a digital core model, and belongs to the technical field of exploration. Comprising the following steps: acquiring a corresponding digital core three-dimensional image; a pore phase is determined after the three-dimensional image is segmented; carrying out microscopic two-phase gas-water flow simulation on the pore phase digital core to obtain a relative permeability curve, determining the permeability in different directions based on an LBM method, and obtaining effective permeability; establishing a productivity evaluation model of the volcanic gas reservoir under different well types and well completion modes by considering stress sensitivity and a high-speed non-darcy effect; and substituting the effective permeability into a productivity evaluation model of the volcanic gas reservoir for productivity evaluation. According to the method, the productivity of the gas well is verified on the basis of the permeability obtained by the productivity evaluation model and the microscopic digital core method, well test interpretation data and digital core calculation data are compared, the obtained theoretical yield error is smaller than 3%, and a good prediction effect is achieved.

The invention belongs to the technical field of sewage treatment, and mainly relates to a sewage treatment carbon source addition control method, which comprises the following steps: deploying various types of data sensors at a plurality of key nodes of a sewage treatment plant, collecting water quality data in real time, and transmitting the collected data to a central processing unit for centralized processing; the central processing unit analyzes the carbon source feeding amount by using a machine learning algorithm, and optimizes a carbon source feeding scheme by training a denitrification demand prediction model; through simulation and verification, a long-term stable carbon source adding scheme is generated, and an automatic control system is used for accurately adjusting the carbon source adding amount; water quality change data is monitored in real time and compared with prediction data, deviation is analyzed, and a machine learning model and a prediction effect are continuously optimized, so that accurate carbon source feeding control is realized; the carbon source use cost can be reduced, and meanwhile it is ensured that the water quality stably reaches the standard.

The application provides an extreme weather wind power prediction method based on reinforcement learning adaptive sampling, and relates to the field of wind power prediction. The method comprises the following steps: obtaining meteorological time series data and wind power data of a wind power station site, constructing a training set, a validation set and a test set, and respectively extracting a training subset, a validation subset and a test subset corresponding to extreme weather; designing a training framework based on reinforcement learning to obtain a Markov decision process component, build a parameterized sampling strategy network and a wind power prediction model; iteratively performing a cooperative optimization process of the sampling strategy network and the prediction model until the training converges, and outputting an optimized target prediction model and a target sampling strategy network. Through the reinforcement learning adaptive sampling method, the sampling strategy network and the prediction model form an optimized closed loop, effectively improving the accuracy of wind power prediction under extreme weather, and ensuring the prediction effect under normal weather.

The invention relates to a multi-task face sensing method and device, electronic equipment, a storage medium and a computer program product. The multi-task face sensing method comprises the steps that a to-be-detected face picture is acquired; a to-be-detected face picture is input into the multi-task face perception model, face features and positioning reference points are extracted from the face picture through the multi-task face perception model, and the positioning reference points are used for executing a positioning task about face key point detection; semantic reference points are calculated based on the positioning reference points through a multi-task face perception model, and the semantic reference points are used for executing semantic tasks about face state detection; and executing a positioning task and a semantic task based on the face features, the positioning reference points and the semantic reference points through a multi-task face perception model. Therefore, by explicitly utilizing the physical representation of the face key points, effective supervision for the semantic reference points is realized, the guiding effect of the face key points on the face perception task is enhanced, and the prediction effect of the face perception model can be improved.

The application discloses a social network link prediction method and device, the method comprises the following steps: decomposing a social heterogeneous network into a plurality of account association sub-views through a social network meta-path, using a graph convolution network to represent the accounts in each account association sub-view, fusing the features of the multiple views through an attention mechanism to generate an account feature vector, using the account feature vector to construct a social network link prediction model, and calculating a link score to realize link prediction. By using the social network meta-path to extract the multi-dimensional association relationship between the accounts, more heterogeneous information between the accounts is considered, and the attention mechanism fuses the features under the multiple account association sub-views to automatically calculate the contribution of various relationships to the link prediction effect, thereby solving the problem that the utilization rate of the social network heterogeneous association relationship is low in the prior art, and the link prediction accuracy is not high.

The invention relates to the technical field of communication, and discloses a multi-mode intelligent terminal radio frequency calibration method based on deep learning. The method comprises the following steps: acquiring multi-modal calibration associated data under sparse sampling; performing cross-modal feature fusion coding to generate a fusion feature vector; outputting predicted performance parameters through the space-time radio frequency response prediction model; constructing a reverse solution model to generate a global radio frequency calibration table; and carrying out uncertainty quantitative evaluation on the calibration parameters to mark high-risk points. According to the method, the deep learning agent model is used for replacing full-amount physical testing, the calibration cost is reduced, meanwhile, full-working-condition high-precision and equipment-level personalized calibration is achieved, and the result reliability is guaranteed.