31 results about "Predictive learning" patented technology

The invention discloses a time enhanced knowledge tracking method based on dual-channel deentanglement, and belongs to the technical field of education data mining and cognitive modeling. According to the technical scheme, the method comprises the steps that time dynamic features and behavior reaction features in a learning interaction sequence are extracted and coded through a time domain encoder and a behavior domain encoder respectively; separating long-term trends and short-term fluctuations in the input features by using a multi-scale decoupling layer based on causal convolution; a time perception dual-channel attention module is adopted to independently decouple time and behavior characteristics after decoupling, and a nonlinear attenuation item based on a real interval is introduced to simulate memory forgetting; and finally, integrating dual-channel information through a gating fusion mechanism and predicting future answering performance of the learner. According to the method, optimization conflicts are effectively relieved, the robustness to a complex learning mode is enhanced, and knowledge state modeling which better accords with a cognitive law is realized.

The invention relates to the technical field of industrial data processing and intelligent control, and discloses an iron ore concentrate grinding medium intelligent regulation and control method and system based on real-time data processing, and the system comprises a sensing layer, an edge calculation layer, a cloud intelligent layer and an execution layer; according to the method, multi-dimensional data are obtained in real time and processed through a professional data preprocessing process, complex process characteristics are condensed into three core indexes including a particle size distribution index, a chemical component index and an energy consumption process index, and fuzzy worker experience is converted into an accurate numerical index; a reinforcement learning algorithm is introduced to enable the system to autonomously learn an optimal control strategy, so that the system has advanced intelligence of prediction, learning and global optimization; millisecond-level real-time response of index grading and medium regulation and control is achieved through the edge computing unit, timeliness of control is ensured, depth computing and model training are carried out based on cloud capacity, and automation and closed loop of the whole process from data collection to instruction execution are ensured.

The invention provides an online course MOOC learning prediction method based on heterogeneous feature fusion, and belongs to the field of computer-aided intelligent education. The method comprises the following steps: acquiring an MOOC data set, and preprocessing the data set to obtain a test set; constructing an IHFNet network comprising a multi-agent adaptive static feature selector module, a hierarchical time sequence feature extractor module and a heterogeneous feature fusion module; a multi-agent adaptive static feature selector module screens key static features; the hierarchical time sequence feature extractor module extracts behavior time sequence features with high discrimination ability; the heterogeneous feature fusion module carries out adaptive fusion on the key static features and the behavior time sequence features and carries out classification prediction; an IHFNet network is trained; and collecting MOOC data of a to-be-predicted learner, and inputting the MOOC data to the trained IHFNet network for learning risk prediction. According to the invention, modeling is carried out by fusing the static features of the learner and the behavior time sequence features, the feature representation ability of the learner is enhanced, and the learning risk prediction effect is improved.

The invention relates to an English text auxiliary teaching method and system based on AI vision. The method comprises the following steps: collecting a dynamic eye movement track, a mouth shape change video stream and micro-expression time sequence data when a student reads, and generating a dynamic behavior feature vector by using a convolutional neural network; and carrying out multi-dimensional matching on the vector and a preset pronunciation standard model, accurately positioning a pronunciation deviation region and an understanding difficulty point, and carrying out classification by virtue of a support vector machine to obtain a learning state label. And extracting a high-frequency deviation mode from the tag, constructing a comprehensive behavior matrix through association of a clustering algorithm and an eye movement backtracking trajectory, calculating a teaching level evaluation value, finally predicting a learning trend and determining a resource allocation weight by combining historical evaluation data and adopting a linear regression model, and optimizing and generating a personalized teaching plan. By adopting the method, pronunciation deviation and understanding disorder in English reading can be accurately positioned, so that the resource allocation weight is adaptive to the individual learning track of students, and a data-driven technical path is provided for English personalized teaching.

The application relates to a heat user abnormal behavior monitoring method and system. The method comprises the following steps: acquiring influence factors affecting heat consumption of a heat user, screening the influence factors, and determining a characteristic vector; preprocessing the characteristic vector to generate a preprocessed characteristic vector; dividing the preprocessed characteristic vector into a training set, a test set and a prediction set; constructing a variation prediction learning machine prediction model by using the training set; inputting the test set into the variation prediction learning machine prediction model to output optimal input layer weights and optimal hidden layer thresholds; inputting the prediction set, the optimal input layer weights and the optimal hidden layer thresholds into the variation prediction learning machine prediction model to determine a predicted value of the heat consumption of the heat user; acquiring an actual value of the heat consumption of the heat user, and determining a current operation state of the heat user according to a deviation between the predicted value of the heat consumption of the heat user and the actual value of the heat consumption of the heat user. The application can effectively improve prediction precision and improve monitoring accuracy.

The purpose of a disclosed technology is to make employee resignation prediction for assisting in implementing an employee resignation prevention measure at an appropriate timing.　A generation unit (41) generates a feature vector including a plurality of feature quantities from personnel related information sets in a prescribed period of time for each active employee and each resigned employee. A prediction unit (42) predicts an employee resignation probability of an active employee subjected to prediction resigning at each of a plurality of time points in the future by using a feature vector of the active employee subjected to prediction and a prediction model 31 that is obtained by performing learning of feature vectors generated for a plurality of resigned employees as positive examples and feature vectors generated for a plurality of active employees as negative examples and that provides a prediction of, when the feature vector of the active employee is inputted, an employee resignation probability indicating the possibility of the active employee resigning at each of the plurality of time points in the future.

The invention discloses a ship hydrostatic performance prediction large model training, deployment and implementation method based on a large model technology. Training a ship hydrostatic performance prediction learning large model according to real sample data of various types, main scales, tonnages and other real ship completion technical data; on the basis of the trained ship hydrostatic performance prediction learning large model, a model structure is adjusted, and a ship hydrostatic performance prediction large model is constructed for deployment; and inputting ship design elements and variable prediction tasks into the ship hydrostatic performance prediction large model to predict ship hydrostatic performance indexes. According to the method, designers can be replaced to complete ship hydrostatic performance estimation work, the working efficiency and level are improved, and basic service is provided for a ship concept designer (intelligent agent) based on artificial intelligence.

The application provides an online course dropout prediction method based on context-aware timing deep network, and belongs to the technical field of computer-aided intelligent education. A prediction data set containing static features and dynamic behavior features is collected; global statistical features are extracted from the dynamic behavior features, and a dynamic behavior matrix is constructed according to the dynamic behavior features; an online course dropout prediction network is constructed; the online course dropout prediction network is trained by using a training set, a binary cross-entropy loss is used as a loss function, and an L2 regularization term is introduced; data of a learner to be predicted is collected and input into the network for dropout risk prediction. The application realizes learner-course context and timing behavior feature fusion based on early data to improve the dropout risk prediction effect.

The SHAP-XGBoost algorithm-based power system inertia short-term prediction method determines power system short-term inertia prediction input features, and constructs an XGBoost-based short-term inertia prediction learning model; based on the established short-term inertia prediction learning model, an explanatory learning algorithm based on SHAP-XGBoost is proposed, and deep learning of the short-term inertia prediction learning model is realized; a power system short-term inertia prediction framework is constructed, and online deployment and application of the prediction model are realized. The explanatory mechanism of the XGBoost machine learning model is fully utilized, the high accuracy of the power system inertia short-term prediction is ensured, the feature correlation in the model can be mastered at the same time, and it is beneficial for the power grid dispatching department to formulate corresponding control measures.

The application relates to an image language fusion prediction learning method for cervical cytology unbalanced data, and relates to the technical field of computers. The method comprises the following steps: acquiring a cervical cytology whole slice image, and cutting the cervical cytology whole slice image into a plurality of patch images; detecting the plurality of patch images to screen a plurality of suspicious positive cell images from the plurality of patch images; acquiring clinical text corresponding to the cervical cytology whole slice image; extracting a plurality of second image features related to the clinical text from first image features of the plurality of suspicious positive cell images; fusing the plurality of second image features and text features of the clinical text to obtain image language fusion features, and predicting a cervical lesion category to which the cervical cytology whole slice image belongs based on the image language fusion features. The method can improve the prediction accuracy of the cervical lesion category.

A server of a health prediction system in one example includes a communication unit for performing wireless communication with a collection terminal for collecting user biometric information measured; an artificial intelligence unit which, when characteristic information about at least one measurement apparatus, generates a prediction model for a specific disease, and trains the prediction model on the basis of the collected user biometric information; and a control unit which, when the prediction model is trained, controls the artificial intelligence unit so that a prediction level related to the specific disease is calculated from the trained prediction model, determines a prediction result for the specific disease on the basis of the calculated prediction level and a preset threshold value, and transmits the determined prediction result to the collection terminal.

The invention discloses an anti-slagging control method for a coal slime circulating fluidized bed, and relates to the field of combustion of the coal slime circulating fluidized bed, which comprises the following steps: S1, data acquisition: monitoring the interior of the CFB by using a high-precision temperature sensor, a pressure sensor, an oxygen analyzer, a microwave material concentration sensor and a laser particle size analyzer; the method comprises the steps of S1, building a prediction model, S2, utilizing training and prediction learning of a vector machine (SVM) algorithm model machine to recognize potential slagging risks in advance, S3, optimizing combustion conditions, S4, carrying out a slag removal program, S5, carrying out data analysis, S6, carrying out equipment maintenance and S7, carrying out multi-system linkage coordination. According to the method, through data acquisition, prediction model establishment, combustion condition optimization, real-time monitoring and dynamic combustion parameter adjustment, the problem of unstable combustion caused by slagging is effectively avoided, it is ensured that the CFB can stably operate under various working conditions, the energy utilization efficiency is improved, and the frequency of slagging events in the CFB operation period can be greatly reduced.

This invention relates to the field of bioaerosol analyzer technology and discloses a method for predicting the mean time between failures (MTBF) of bioaerosol analyzers. The method involves integrating operational data from the operational logs of various bioaerosol analyzers; constructing time-series sequences characterizing the operational status of key components within the same bioaerosol analyzer; aligning these time-series sequences according to the actual runtime of their respective bioaerosol analyzers to construct a time-series matrix characterizing the operational status of different bioaerosol analyzers; extracting fault data features and fault timing features from the time-series matrix; calculating the MTBF of bioaerosol analyzers under the same operating environment parameter range based on the time-series matrix; and predicting the MTBF of a target bioaerosol analyzer using a predictive learning model. This invention is beneficial for optimizing the prediction strategy for the MTBF of bioaerosol analyzers.

The invention provides a method, device and equipment for determining a thickening CO2 flooding development scheme, a medium and a product, and relates to the technical field of oil and gas development. The method comprises the steps of obtaining a plurality of initial development schemes of a target oil reservoir, wherein the initial development schemes are obtained by permutation and combination of a plurality of preset values corresponding to a plurality of development characteristic parameters; inputting each initial development scheme into a pre-trained development dynamic prediction learning model to obtain development dynamic data corresponding to each initial development scheme; adopting a preset multi-target mathematical model to calculate a plurality of index values corresponding to each initial development scheme; determining a candidate development scheme set by adopting a multi-objective collaborative optimization algorithm according to the plurality of index values corresponding to each initial development scheme; and determining a thickening CO2 flooding target development scheme of the target oil reservoir based on the preset weight threshold values corresponding to the indexes. According to the method, through fusion of the preset multi-target mathematical model and the multi-target collaborative optimization algorithm, the optimization efficiency and precision of the thickening CO2 flooding development scheme are remarkably improved.

An information processing device includes a processor that executes first processing of deriving a predicted correct answer probability being a probability that a learner is predicted to correctly answer a first question, and deriving a time difference between a timing for displaying the first question and a timing for displaying hint information being information as a hint of the first question, based on the predicted correct answer probability, or second processing of acquiring a degree of difficulty of the first question answered by the learner, and deriving a time difference between a timing for displaying the first question and a timing for displaying the hint information, based on the degree of difficulty, and generates data for displaying the first question and the hint information for the learner, based on the time difference.

The application belongs to the technical field of target detection and self-learning, and particularly relates to a nuclear power plant equipment appearance defect self-learning identification method based on feature probability distribution. The method comprises the following steps: collecting defect appearance images of key equipment of a nuclear power plant; constructing a nuclear power plant equipment defect detection data set; extracting potential features of equipment appearance defects; capturing global features of defect appearances; generating feature queries; continuously adapting to new defect features in the training process; after reasoning is completed, a target classification head and a regression head will output category information and corresponding boundary box coordinates of each detection target; and for category prediction, learned category probability is multiplied by classification probability to generate final category prediction. The method has the beneficial effects that by combining a regional attention mechanism and a dynamic multivariate Gaussian distribution, the method effectively solves the problems of category imbalance and complex defect appearances of existing target detection algorithms in complex background environments.

The invention relates to an industrial robot self-supervision anomaly detection method and system, and the method comprises the steps: obtaining the collection data of a to-be-detected industrial robot, and carrying out the preprocessing of the collection data, and obtaining feature sample data; processing the feature sample data based on a preset cross-domain signal fusion model to obtain first intermediate data; processing the first intermediate data based on a preset self-supervised learning model to obtain second intermediate data; and processing the second intermediate data based on a preset anomaly positioning algorithm to obtain target detection data. According to the industrial robot anomaly detection method and device, the input collected data is preprocessed, cross-domain signal fusion and self-supervised learning are combined, self-supervised prediction learning is conducted on the feature sample data obtained through preprocessing, anomaly is positioned through the preset anomaly positioning algorithm, automatic and fine-grained industrial robot anomaly detection is achieved, and the detection accuracy is improved. And the response speed and robustness of anomaly detection are improved.

The invention discloses an unmanned aerial vehicle fault evaluation method and system based on a chain neural network. The method comprises the following steps: constructing a variable database; correlation coefficients of the variable combinations are obtained through a Pearson's correlation coefficient method, and the variable combinations lower than a correlation coefficient threshold value are removed; constructing a chain neural network model, wherein the variable prediction sub-model n is a prediction model for predicting the variable n by using the variable having correlation with the variable n in the correlation matrix; data related to the data factor items in the unmanned aerial vehicle fault-free time is collected and input into the chain neural network model for prediction learning training; related data of the unmanned aerial vehicle and the data factor items are collected in real time and input into the variable prediction sub-model set, and the alarm number is counted to serve as an unmanned aerial vehicle fault evaluation result. According to the invention, fault occurrence probability evaluation in flight of the unmanned aerial vehicle is realized, timely emergency command of stopping and landing of the unmanned aerial vehicle is facilitated, fault inspection is performed timely, further expansion of the fault of the unmanned aerial vehicle is prevented, and flight safety of the unmanned aerial vehicle is improved.

The invention provides an internationalized course intelligent adaptation and quality evaluation system driven by a neural network, which belongs to the technical field of education and comprises a topological feature extraction module, a space-time learning trajectory modeling module, a topological invariant prediction module, a course adaptation recommendation module, a quality evaluation module and an adaptive control module. According to the method, essential structure features of learning behaviors are extracted through a topological data analysis technology, a learning process is modeled as a trajectory on a knowledge manifold, a learning effect prediction model is constructed based on topological invariants, and personalized curriculum recommendation and multi-dimensional quality evaluation are realized. A differential geometry method is adopted to quantify learning path efficiency, a prediction framework driven by topology invariants is constructed to improve model stability, through the system, learning modes of learners with different cultural backgrounds can be deeply understood, the learning effect can be accurately predicted, learning resource configuration can be optimized, and data-driven decision support can be provided for internationalized education.

The invention provides a nuclear power gear transmission device fault diagnosis method based on multi-modal deep learning, and belongs to the technical field of gear fault diagnosis based on deep learning. Firstly, structural vibration, acoustics and operation condition parameters are collected through a sensor; secondly, constructing a graph neural network for dynamically coupling equipment physical topology and nuclear environment influence to perceive propagation characteristics of a fault in a spatial dimension, and capturing a slow evolution rule of the fault in a time dimension in combination with a time Transform network; then, a collaborative attention fusion mechanism is designed, deep dialogue and cross validation of microscopic vibration signals and macroscopic working condition background information are achieved, and interference caused by environment and working condition changes is removed; and finally, through the trained fault prediction learning model, a clear fault type and a confidence score are output. According to the invention, high-precision intelligent diagnosis of internal early weak faults of the nuclear safety level key gear transmission device in an extreme environment is realized.

The invention relates to the technical field of law and regulation intelligent learning, and discloses a law and regulation intelligent learning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target state of each preset law and regulation category of a to-be-learned person according to label information, obtaining historical mastering states of each preset law and regulation category of the to-be-learned person at a plurality of time points, the method comprises the steps of obtaining a to-be-learned person, inputting the to-be-learned person into a preset learning time prediction model to obtain a first predicted learning duration of each preset regulation category, setting a historical fingerprint of the to-be-learned person according to the first predicted learning duration so as to set a learning time ratio of each preset regulation category, and making a learning plan of the to-be-learned person according to the learning time ratio. And the to-be-learned person can learn according to the learning plan. The method has the beneficial effects that the learning efficiency of learners is improved, effective support is provided for cultivating high-quality legal talents, and personalized learning planning is realized.

The application belongs to the technical field of computers and specifically discloses a programming knowledge tracking method based on code prediction enhancement, which comprises the following steps: based on historical programming questions and corresponding historical programming answers, extracting embedded representations, obtaining historical question embedded representations and historical answer embedded representations; based on the historical question embedded representations, the historical answer embedded representations and the embedded representations of target programming questions, predicting the embedded representations of the source code input by the measured object for the target programming questions through a multi-head attention mechanism model, and taking the predicted embedded representations of the source code as programming answer prediction results; and based on the embedded representations of the target programming questions, the programming answer prediction results and the current knowledge state of the measured object, predicting the answer correctness probability of the measured object for the target programming questions, wherein the current knowledge state is obtained by analyzing the time sequence evolution of the knowledge state based on the historical programming answers of the measured object. The application can accurately predict the programming performance of learners.

The present application provides an ultrasonic time series data processing apparatus and a non-transitory storage medium. A Doppler processing section (18) or a beam data processing section (20) generates object time series data based on a received beam data string from a receiving section (16). An artifact prediction section (38) predicts a kind of artifact generated by the object time series data by inputting the object time series data to a learned artifact prediction learner (32). An artifact reduction section (40) performs artifact reduction processing based on the predicted kind of artifact. A display control section (24) notifies a user of a corrected ultrasonic image (62) on which the artifact reduction processing is performed or a prediction result of the artifact prediction section (38).

The application provides an online course dropout prediction method based on context-aware timing deep network, and belongs to the technical field of computer-aided intelligent education. A prediction data set containing static features and dynamic behavior features is collected; global statistical features are extracted from the dynamic behavior features, and a dynamic behavior matrix is constructed according to the dynamic behavior features; an online course dropout prediction network is constructed; the online course dropout prediction network is trained by using a training set, a binary cross-entropy loss is used as a loss function, and an L2 regularization term is introduced; data of a learner to be predicted is collected and input into the network for dropout risk prediction. The application realizes learner-course context and timing behavior feature fusion based on early data to improve the dropout risk prediction effect.

The present application belongs to the field of machine learning, 3D computer vision, monocular depth prediction and self-supervised learning, and provides a self-supervised monocular depth prediction training method based on pixel matching for predicting camera pose. The present application converts the abstract camera motion prediction process in self-supervised depth prediction learning into a process based on pixel matching, and solves the camera motion in a geometric manner, enhances its interpretability, and improves its generalizability. The camera motion solved by the traditional geometric method of the present application is more accurate, so that the self-supervised depth prediction learning is more stable in the training process and the effect is more robust in the scene of indoor environment or large change of camera motion pose.

The invention relates to the technical field of automatic driving decision control and artificial intelligence, in particular to a multi-scene automatic driving strategy rapid adaptation method based on a meta-optimization framework, and the method comprises the steps: constructing a multi-scene expert strategy model based on reinforcement learning, and obtaining a multi-scene experience pool; constructing a meta-optimization fast adaptation model containing a representation learning network and a prediction learning network; meta parameters of the meta optimization fast adaptation model comprise representation learning network parameters and prediction learning network parameters; dividing the data of the multi-scene experience pool into a plurality of tasks, and performing cooperative training on the plurality of tasks based on a meta-optimization rapid adaptation model to obtain representation learning network parameters of the model; and when the automatic driving vehicle enters a new scene, keeping the representation learning network parameters of the model frozen, and performing multi-step gradient updating on the prediction learning network parameters by using a new sample. The objective of the invention is to solve the problems of weak strategy generalization ability and neural network plasticity loss of an automatic driving model in an unknown scene.

The application discloses a multi-party secure electronic signature and certificate authentication method based on key component cooperation, and relates to the technical field of quantum technology.The steps of the method comprise the following steps: according to historical attack modes and key update periods, a prediction learning model containing short, medium and long periods is established, the comprehensive failure probability of each key component is outputted to determine the distribution weight of each key component; a cooperation gateway is deployed through a load balancer, and the distribution weight of each key component is dynamically adjusted in response to a preset instruction, while the identity verification strength in the cooperation signature process is dynamically adjusted in combination with a load parameter; a signature request is initiated by a user, a space index architecture is introduced, the protocol fingerprint of the key component is analyzed, the signature trigger area where each key component is located is identified in real time, and the entropy change rate is obtained, and in combination with the signature rate of each authentication party within a unit time, the encryption mode of the blockchain server for certificate authentication is dynamically adjusted; and the application is suitable for high-complexity business scenarios and improves the success rate of signature.

Systems and methods for automated data extraction and adaptation are disclosed. The system may receive a data input from an external source using various different input channels. The system may determine a data quality of the data input by comparing data fields of the data input to known metadata in the system. The system may reformat the data input based on the comparison to a format consumable by downstream applications and services. The system may apply various machine learning operations on the data input including a descriptive analytics analysis, a predictive learning analysis, and / or a prescriptive intelligence analysis.

Disclosed in the present disclosure is a predictive channel modeling method based on a generative adversarial network and a long short-term memory artificial neural network, which method effectively achieves a channel prediction function in different frequency bands and scenarios, and generates a large number of channel data sets for simulation experiments. The method comprises: firstly, inputting channel measurement data for existing frequency bands and scenarios for training; then, learning true channel data using a long short-term memory artificial neural network, and acquiring a channel time sequence feature; by means of adversarial learning of a generative adversarial network, greatly eliminating redundant information of the channel data, and on the basis of the measurement data, generating accurate channel data, and acquiring massive channel information; and finally, achieving the balance between a generative model and a discriminative model during the continuous iteration of the generative adversarial network, and then outputting a trained predictive channel model. A statistical channel feature obtained by means of prediction by a model can clearly specify the predictive learning for a channel distribution feature in the present disclosure, and real-time and complex prediction problems in wireless communication can be solved.

A method of using an artificial neural network to generate granular image level representations for driving, the method includes (a) obtaining a sensed information unit that captures a first element, (b) generating, by a machine learning process using the artificial neural network, a first set of tokens for the first element each representing a respective attribute characterizing the first element, (c) processing, by the machine learning process, the first set of tokens in correspondence with at least a second set of tokens generated for a second element, (d) producing, based on the processing, an image-level representation for the first element with respect to the second element, (e) determining, based on the image-level representation, an interaction between the first and second elements in real time; and (f) determining, based on the determined interaction, a driving related output with respect to the vehicle.