497 results about "Outcome predictor" patented technology

The invention discloses a method for analyzing a matching degree between a demand and an output result based on text semantics. The method comprises the following steps: step 1, labeling a data set; step 2, technical document preprocessing; 3, training and predicting a single-parameter model; 4, integrating prediction results of the multi-parameter model; the method has the beneficial effects thatthe method is simple; deep learning and the NLP technology are applied to the field of project association degree calculation of enterprise project management for the first time. Calculating an association matching degree between the two projects according to project requirements and result description; the associated project positioning difficulty is effectively reduced; meanwhile, the demand side can be helped to quickly and efficiently locate high-quality projects adapting to the demand of the demand side; time and resource investment for achievement screening and matching are greatly reduced, the association matching degree between projects is calculated by means of text data of existing project achievement technical documents and project declaration guidelines, and then large enterprises are assisted in screening high-quality projects with the high matching degree in the project bidding and tendering link.

This application relates to a real-time power supply and demand forecasting method and system based on a cloud-native architecture. The method includes: deploying a data access service in a cloud-native cluster using containerized microservices to receive real-time supply and demand data streams and historical time-series data from a power trading system; writing the data streams to distributed storage and pushing them to the forecasting pipeline via a message queue; performing timestamp alignment, missing data handling, normalization, and smoothing / denoising on the supply and demand data by a preprocessing service to obtain a low-noise supply and demand sequence; updating model parameters in a rolling window by an ARIMA forecasting service and outputting linear forecast values ​​as the first forecast result; calculating the forecast residuals based on the first forecast result and the actual observations, constructing residual time-series samples, and outputting residual forecast values ​​by an LSTM forecasting service; and superimposing the first forecast result and the residual forecast values ​​by a fusion service to obtain the real-time supply and demand forecast result and publishing it to the real-time trading business interface.

This invention belongs to the field of seismic reservoir prediction and intelligent geophysical interpretation technology, specifically involving an intelligent reservoir prediction method for suppressing strong interference anomalies. The method first preprocesses seismic data and uses the generalized S-transform to obtain the time-frequency spectrum of the seismic signal. Then, based on the frequency component variation relationship, fluid flow properties are constructed to enhance reservoir fluid response characteristics and suppress strong response anomaly interference from non-reservoir areas. Furthermore, seismic data and fluid flow properties are jointly input to construct an intelligent reservoir prediction network based on a residual U-Net structure. Multi-scale feature extraction and fusion are achieved through an encoder-decoder structure and skip connections. Finally, the probability prediction result of the reservoir is output. This method can effectively fuse seismic structural information and fluid flow property information, improving the accuracy and stability of reservoir prediction under complex geological conditions, and has good generalization ability and application value.

This invention discloses a time series forecasting method and system based on cross-period phase alignment. The method involves acquiring time series data, performing standardization and cross-period alignment to obtain a phase representation of the time series data, mapping the phase representation to obtain a latent space representation, aggregating the latent space representation through a cross-phase routing layer to obtain aggregated information, distributing the aggregated information through a cross-phase routing layer to obtain a phase characterization, predicting the phase characterization to obtain future prediction results, and performing time-by-time prediction and reconstruction processing on the future prediction results to obtain the final prediction result. The cross-phase routing mechanism reduces pairwise phase interactions to a two-hop attention process from phase to router and back to phase, with complexity increasing linearly with the number of phases, thus reducing memory and computational requirements and improving operational efficiency.

A clinical decision support device, comprising: a parameter acquisition module, configured to acquire measured values for markers in a biomarker combination of a subject, wherein the biomarker combination at least comprises an alpha fetoprotein, an abnormal prothrombin, γ-glutamyltransferase, and an albumin; a risk assessment module, configured to input the measured values for the markers in the biomarker combination into a calculation model to obtain an output of the calculation model as a liver cancer risk prediction result of the subject; and an output module, configured to output the liver cancer risk prediction result of the subject. Also disclosed are a sample analysis system and a method for assessing a liver cancer risk of a subject, capable of better assessing a liver cancer risk of a subject.

This application provides a runoff prediction method, apparatus, electronic device, and computer-readable storage medium. The method includes: acquiring the forecast meteorological time series of a target watershed during the prediction period, historical meteorological time series, and historical runoff time series for historical periods; inputting the historical meteorological time series and historical runoff time series into an attention model to extract global contextual features of the target watershed; inputting the forecast meteorological time series, global contextual features, and initial noise data into a conditional diffusion probability model, performing multiple backdiffusion processes to obtain multiple predicted runoff time series of the target watershed during the prediction period; and calculating a specified quantile for each moment in the prediction period based on the multiple predicted runoff time series to construct a confidence interval, thereby obtaining runoff prediction information containing a risk probability distribution. This method avoids gradient vanishing when processing long-sequence data and outputs the probability distribution of the prediction results.

The specification discloses a model training method and device, equipment and a readable storage medium. According to a to-be-trained transformation network and a source model trained by a poisoned sample, a target model to be trained is determined. A clean sample obtained is input into the target model to obtain a prediction result output by the target model. According to the prediction result and a label of the clean sample, parameters of the transformation network are adjusted. When a prediction request is received, to-be-predicted data is input into the trained target model to obtain a prediction result of the to-be-predicted data. It can be seen that the reconstruction of the source model based on the transformation network avoids the input and / or output of the source model attacked by the poisoned sample being transformed by the transformation network without adjusting the model parameters of the source model, so as to avoid the source model obtaining an incorrect prediction result for the sample preset by the attacker, thereby ensuring the model performance and realizing a high defense effect and protecting the safety of private data.

This invention discloses a method for predicting load time-series adjustment potential based on error correction, comprising the following steps: S10, acquiring raw load response data; S20, performing RF processing on the raw load response data to obtain complete time-series data; S30, using SSA decomposition to extract time-series sub-modes and performing potential prediction, then summing the predictions of each sub-mode to obtain a preliminary time-series adjustment potential prediction result; S40, subtracting the preliminary time-series adjustment potential from the raw time-series adjustment potential to obtain the time-series adjustment potential error, and using a dynamic mode decomposition algorithm to correct the time-series adjustment potential error in the preliminary time-series adjustment potential prediction result to obtain the final time-series adjustment potential prediction result. This invention solves the problems of excessive complexity and limited generalization ability in traditional time-series potential prediction, effectively handles the influence of data disturbances, and improves the accuracy of potential analysis.

This invention relates to the field of parcel delivery volume prediction technology, and discloses a method for predicting logistics parcel delivery volume based on a multi-level network architecture. The method includes: acquiring raw data and standardizing the data; constructing a multi-level network hierarchy and a multi-dimensional weighted ranking model; displaying the data in multiple dimensions; calculating the confidence interval based on the prediction model and attaching a confidence level label to each predicted value; introducing a user behavior learning model to record user click habits and query preferences, and optimizing the network display order and recommendation logic; using an integrated prediction model to fuse time series analysis, regression analysis, and machine learning prediction methods to form a combined prediction result; establishing a prediction error feedback mechanism to compare the actual delivery volume with the predicted delivery volume and optimize model parameters; and adopting a hierarchical prediction strategy. This invention provides reliable support for logistics delivery planning and resource allocation, reduces operating costs, and improves service quality.

The application discloses an osteoporosis risk grading prediction method based on clinical prior logic gating, acquires multi-modal clinical data of a patient to obtain a standardized feature vector group, constructs and trains an osteoporosis risk grading prediction neural network model, including a double-flow feature coding module, a logic gating fusion module and a cascaded classification prediction module, inputs the standardized feature vector group after splicing processing to the trained neural network model, and outputs an osteoporosis risk grading prediction result. The application converts the diagnosis logic in the clinical guideline into an attention gating mechanism in the neural network by designing a double-flow architecture, and combines a screening-grading cascaded strategy, so that the existing structured data (demography, test single, medical history) in the hospital information system can be directly used to realize low-cost, high-precision and clinically interpretable osteoporosis risk grading without additional image examination.

The application discloses a kind of multi-time scale risk trend prediction methods and systems for collapse disaster, it is related to disaster risk prediction technical field.A kind of multi-time scale risk trend prediction system for collapse disaster, including have: data acquisition module, stage determination module, scale adjustment module, prediction constraint module, scale prediction module, risk fusion module and event extraction module.The application outputs each scale risk trend sequence and uncertainty representation under the bidirectional constraint of space-time constraint propagation network in scale prediction module, then by dynamic weight distributor, stage identification information and uncertainty representation are combined to calculate the fusion weight that changes with time, cross-scale consistency constraint is applied, the fusion risk trend curve with confidence interval is obtained, the prediction result of each time scale is adaptively weighted and constrained according to uncertainty.

The short-term load forecasting method based on SARIMA-random forest combination model comprises the following steps: grouping the original load data by using a sliding window, decomposing the to-be-tested week-before-next day data set of each group to obtain a trend item, a seasonal item and a residual item; establishing a SARIMA model, predicting the trend item to obtain a preliminary prediction result and a residual; clustering weather factors to obtain similar days, grouping to construct a weather-residual data set and establishing a random forest regression model, learning the influence of the weather factors on the residual, and selecting model parameters by using a grid search method; combining the prediction results of the model, and comparing the influence of weather clustering and residual training on the load prediction accuracy. The method can accurately predict the next day load under the condition that the historical load and weather factors of the to-be-tested day are known, and improves the prediction accuracy.

The embodiment of the application discloses a method and device for establishing a prediction model, which are applied to the technical field of deep learning. The main technical scheme comprises the following steps: obtaining a training data set, wherein the training data set comprises sample data of C categories and labels corresponding to the sample data; taking the sample data as the input of a first prediction model, taking the labels corresponding to the sample data as the target output of the first prediction model, training the first prediction model, wherein the first prediction model comprises a feature extraction network and a prediction network, the feature extraction network is used to extract feature representation by using the sample data, and the prediction network is used to obtain a prediction result for the sample data by using the feature representation; and in the training, a momentum gradient descent method is used to update parameters of the first prediction model, wherein the weight of the momentum in the parameter update is determined according to the difference degree between the long-tail data distribution and the uniform distribution of the training data set. The application can reduce the possibility of falling into a local optimum and improve the prediction effect.

The application provides a hydropower station reservoir flow prediction and scheduling optimization method, which separates different scale hydrological characteristics through multi-time scale processing of multi-source data, extracts reservoir inflow characteristics by cooperating with gray correlation analysis, avoids time structure aliasing, and makes the hydrological law clearer; the prediction interval is corrected by the deviation of the observed value of the reservoir inflow, the prediction result is dynamically adjusted with the actual hydrology, the error of the initial prediction is made up, the prediction accuracy is twice improved, and the problem of inaccurate reservoir inflow prediction is solved. In addition, the corrected prediction interval is used as an uncertainty set, a double-layer robust optimization model of safety margin constraint is combined with a confidence parameter adjustment, scheduling safety and benefit are balanced; different risk level strategies are generated by weighting and combining scheduling decision variables through a risk preference parameter, and the scientificity and stability of reservoir scheduling are improved.

The application discloses a source-load joint probability prediction method and system of a physically constrained graph attention network. The method collects multi-dimensional feature data of source-load nodes in a prediction area to construct an initial node feature matrix. A similarity matrix is generated through differentiable graph structure learning. A dynamic adjacency matrix is generated through normalization and introduction of a sparse mask. Spatial feature aggregation is performed through a multi-head graph attention network to obtain node spatial encoding. The node spatial-temporal hidden state is output through an encoder. The node spatial-temporal hidden state is input into a probability prediction head to output Gaussian distribution parameters of the source-load node power. A joint loss function is constructed. The joint loss function is used for soft constraint training to output a probability prediction result. Posterior projection hard constraint correction is performed in an inference stage to obtain a corrected prediction result. The application solves the problems of lack of physical consistency and inability to quantify uncertainty in the prior art.

This invention provides a method, apparatus, and device for multidimensional prediction of distributed transformer substations based on artificial intelligence, relating to the field of power data prediction technology. The method includes: filtering features closely related to the prediction target from the multidimensional feature information and operational data of the distributed transformer substations to obtain multiple multidimensional features of the substations; identifying the relative importance of each multidimensional feature of the substations in the prediction target, and assigning feature weights to each multidimensional feature of the substations based on the relative importance; fusing the multidimensional features of the substations based on the feature weights into input features, and inputting the input features into multiple prediction models to obtain multiple preliminary prediction results for the distributed transformer substations; and fusing the preliminary prediction results based on the model weights corresponding to each prediction model to obtain the final prediction result for the distributed transformer substations. This invention can balance the prediction performance of different models under scenarios such as extreme weather and load surges, improving the robustness, accuracy, and timeliness of the prediction results.

This invention relates to a method and system for short-term load forecasting across seasons in the electricity spot market. The method first collects electricity load, meteorological, and temporal characteristic data to construct a multi-dimensional input feature set, which is then divided into a training set and a validation set. Next, variational mode decomposition is used to decompose the original load data into three modal components, corresponding to three types of input feature sets. Then, with the goal of maximizing the validation set determination coefficient, seasonally differentiated hyperparameter optimization is performed using a particle swarm optimization algorithm. Temporal dependency prediction sub-models and multi-feature association prediction sub-models are constructed based on the optimized Long Short-Term Memory Network and Random Forest, respectively. The three types of input feature sets are then input into their respective sub-models, outputting two types of prediction results. Finally, the two types of results are weighted and integrated to obtain the short-term load forecast result. Compared with existing technologies, this invention has advantages such as significantly improved prediction accuracy.

The embodiments of the present disclosure disclose a movable platform action prediction method and a training method of an action prediction model, wherein the movable platform action prediction method comprises: acquiring multi-modal dynamic related information corresponding to the movable platform at a current time; determining visual latent features and action latent features in a unified latent space based on the dynamic related information, realizing short-time sequence real-time response; performing prediction processing on at least one of the multi-modal dynamic related information to obtain prediction latent variable features at future k time points relative to the current time, obtaining k prediction latent variable features, and realizing long-time sequence dynamic perception planning; and performing action prediction based on the visual latent features, the action latent features and the k prediction latent variable features to obtain an action prediction result at a next time point relative to the current time. The embodiments of the present disclosure improve the foresight, real-time and stability of action prediction.

The application discloses a multi-modal feature collaborative generation analysis method and system for tumor survival prediction, and relates to the technical field of computer vision. The method comprises the following steps: acquiring multi-modal data and preprocessing to obtain a training data set; learning a first feature mapping relationship between multiple modes based on complete mode samples, and training a generator based on missing mode samples and the first feature mapping relationship to obtain a target generator, which generates virtual coding features of the missing mode; acquiring partial mode medical data of a target object, inputting the partial mode medical data of the target object into the target generator to generate virtual missing mode coding features of the target object; extracting at least one other mode coding feature from the partial mode medical data, fusing the virtual missing mode coding features and the at least one other mode coding feature, and determining a survival prediction result of the target object according to the fused features. The application improves the accuracy and interpretability of tumor survival prediction.

The application belongs to the field of medical prediction, and discloses an information mining method for heterogeneous time series data, comprising: acquiring electronic medical record data and constructing a hypergraph, analyzing and calculating the hypergraph to obtain embedding representation data, weighting the embedding representation data based on an attention mechanism to obtain embedding sequence data, constructing a sequence learning model and performing hidden state access to obtain hidden representation data and weight data thereof, weighting the embedding sequence data to obtain embedding sequence hidden data; training the sequence learning model through time training parameter data, weighting the embedding sequence hidden data through the trained sequence learning model to obtain time dimension hidden data, constructing a full connection network to analyze the time dimension hidden data to obtain medical event prediction data. The technical scheme disclosed by the application can learn complex information in the time dimension by using time step information, and can obtain accurate medical event prediction results.

The application relates to a river closure date prediction method based on historical similar year performance driving, which comprises the following steps: using a plurality of feature selection algorithms and leave-one-out cross-validation to screen target predictor sets respectively matched with selected machine learning models and statistical models; based on parameter sensitivity analysis and a Bayesian optimization algorithm, sensitive hyperparameters of the machine learning models are optimized to obtain optimized machine learning models; the statistical models and the optimized machine learning models are configured as candidate river closure date prediction models; a K-neighbor algorithm is used to search a set of similar historical years in a historical observation data set according to current observation data, and a target river closure date prediction model is dynamically optimized according to the comprehensive prediction error of the candidate river closure date prediction models on the set of similar historical years, and a prediction result is output, so that the advantages of multiple models are effectively fused, the generalization limitation of a single model in a complex non-stationary environment is avoided, and the accuracy and robustness of the prediction result are significantly improved.

The application belongs to the technical field of data asset management, and particularly relates to a data asset operation decision method and system based on artificial intelligence. Firstly, multi-dimensional characteristic data of target data assets is collected, and the collected multi-dimensional characteristic data is vectorized and fused to form a feature representation F. Then, the feature representation F is quality evaluated. Next, the feature representation F, a comprehensive quality score Q and historical data are used to predict and evaluate a future expected value Vp, a predicted risk value Ri and a predicted cost value Zm of the target data assets. Secondly, a multi-objective decision function is constructed with the future expected value Vp maximization, the predicted risk value Ri minimization and the predicted cost value Zm optimization as targets. Strategy optimization is performed through an optimization algorithm, and a recommended operation action Aopt is generated. The prediction result can be automatically converted into an executable operation decision, and the dependence of the decision on artificial experience can be greatly reduced.

The application relates to the technical field of energy storage safety, and discloses a multi-scale multi-physical-field energy storage emergency space twin modeling method, which comprises the following steps: presetting macro low-dimensional and micro high-dimensional models in an edge computing device, measuring residual computing power, setting a concurrent threshold, calculating space-time gradient characteristics by using a macro model based on annular buffer data to mark a candidate region, calculating a thermodynamic urgency index, sorting the candidate region, and screening out an activated region, calling historical data to drive a micro model to perform super-real-time operation, completing internal state initialization, establishing a heterogeneous model physical boundary bidirectional coupling by using flux impedance matching, outputting a fault evolution prediction result, and generating a fixed-point emergency control instruction. By means of thermodynamic urgency scheduling and boundary coupling technology, the application solves the high-fidelity simulation problem under the condition of limited computing power on the edge side, and improves the prediction accuracy and response speed of the multi-scale multi-physical-field energy storage emergency space twin modeling.

The present application relates to the technical field of artificial intelligence, and particularly relates to an individualized medication prediction method based on artificial intelligence, comprising: acquiring a plurality of standard historical medical data sets; acquiring metabolic capacity scores and drug metabolism rates corresponding to all data groups; training to obtain relationship models corresponding to all standard historical medical data sets; acquiring liver metabolism parameters, gene expression parameters and each drug name in a treatment scheme of a patient to obtain a drug metabolism rate; and determining a corresponding prediction drug amount determination method according to whether the drug types in the treatment scheme have a competitive relationship. The present application integrates drug metabolism enzyme-related gene expression and liver metabolism function, simultaneously incorporates drug absorption competition and metabolism enzyme competition when drugs are used in combination, corrects the final output prediction drug amount when drugs are used in combination, so that the model is more suitable for the actual drug use scene, and the accuracy of the prediction result is increased.

The present application belongs to the technical field of hydrological prediction and water resources management, and specifically relates to a prediction method and system based on multi-scale decomposition of runoff sequence and dynamic weight reconstruction. The method first constructs a physical hydrological model based on meteorological driving data and generates a runoff simulation sequence; the simulation sequence is subjected to multi-scale decomposition by using variational mode decomposition, the decomposition parameters are adaptively determined by particle swarm optimization, and a plurality of mode components are obtained; a long short-term memory network is constructed to establish a mapping relationship between the contribution weights of the mode components, and dynamic weights varying with time and normalized are output; the mode components are weighted and reconstructed according to the weights, so as to realize deviation correction of the simulated runoff of the physical hydrological model on different time scale structures. In the prediction stage, the same decomposition is performed on the future runoff simulation sequence, and the trained model is directly used to output the runoff prediction result. The present application converts the runoff prediction problem into a dynamic weight distribution problem of multi-scale structure components, improves the prediction precision and migration ability while maintaining physical interpretability, and is suitable for scenarios such as basin runoff prediction, flood simulation, water resources scheduling and the like.

This invention discloses an industrial carbon emission detection and prediction method and system. It collects multi-source heterogeneous data from industrial production processes, and sequentially performs standardization, noise removal, outlier removal, and data fusion on the multi-source heterogeneous data to obtain initial carbon emission data. A hybrid detection and prediction model is constructed, employing an encoder to extract multi-factor correlation features from the multi-source data and a long short-term memory network to extract temporal fluctuation features of the carbon emission data. An attention mechanism is introduced to weight the correlation features and temporal fluctuation features. An improved IWOA whale optimization algorithm is used to optimize the hyperparameters of the hybrid detection and prediction model to obtain a target hybrid detection and prediction model. The initial carbon emission data is input into the target hybrid detection and prediction model, and the prediction results are output, including the current carbon emission detection value and the carbon emission prediction sequence. This improves the accuracy of carbon emission prediction results and the efficiency of carbon emission detection.

This invention provides a method for predicting the relative safety (RUL) of an aircraft system based on combined probability density. The specific steps are as follows: In the training module, preprocessed training data is input into an FFT model, and different quantile loss functions are set. After the loss functions converge, the predicted values ​​at each quantile are obtained. In the testing module, processed test data is input into a trained QRFFT model to obtain multi-quantile RUL prediction results. These results are then used as input to a KDE (Knowledge-Defined Allocation) model, and the RUL probability density distribution (PDF) is obtained through a Gaussian kernel function and optimal bandwidth. This model combines RUL point prediction, interval prediction, and probability density prediction functions. Experiments using real aircraft flight path data are conducted, and a new probability prediction evaluation index is introduced. Comparison with existing QR models in terms of point prediction accuracy and interval prediction performance shows that this invention has higher effectiveness and superiority.

This invention proposes a method and system for electricity consumption completion and prediction based on missing electricity consumption data. For historical electricity consumption data with random missing values, the method first acquires the historical electricity consumption data containing random missing values ​​and a mask, then uses a generative adversarial network (GAN) to perform data imputation, and finally uses a long short-term memory (LSTM) network to predict future electricity consumption. Finally, the GAN is fine-tuned under the constraints of the prediction results to achieve joint optimization of completion and prediction. This invention effectively mitigates the adverse effects of missing data on prediction accuracy through the collaborative mechanism between the data completion and prediction modules; it uses the temporal characteristics of the missing data restored by the GAN to ensure that the completion results are consistent with the real data in terms of statistical distribution and temporal patterns. This invention achieves joint optimization of completion and prediction through a prediction error inverse constraint generator, thus maintaining good prediction stability under different missing rates and seasonal conditions.

The application discloses a kind of soft measurement modeling methods of fermentation process based on time sequence diagram network, belongs to the technical field of soft measurement of fermentation process.It includes the following steps: (1) data acquisition and integration: the penicillin fermentation process under different conditions is obtained, and the data is divided, collected and integrated;(2) data selection: the data is selected, the redundant useless data is removed and the causal diagram between variables is established;(3) modeling training: algorithm model is constructed, and learning training is carried out;(4) model prediction: the trained algorithm model is used for prediction, and the prediction result is given.The application proposes a kind of soft measurement modeling method of fermentation process based on time sequence diagram network, improves the prediction accuracy of key product quality of fermentation process;The method uses graph convolution network and long short-term memory, extracts data in time and space dimensions, increases the generalization of model;The method can accurately measure the key product quality of different fermentation processes.