15 results about "Time perception" 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.

A large model memory enhancement method based on time perception consistency feedback and optimization comprises the following steps: 1, data preprocessing: obtaining a historical interaction text generated by each agent in a target scene, and processing the text by using a preprocessing module; 2, attribute mining: extracting agent personal attributes, site attributes, logic attributes and core arguments from each generated content; and 3, keyword management and memory storage: maintaining an independent keyword historical file and a memory library file for each agent, and constructing an evolvable memory which changes along with time. 4, performing memory retrieval and context construction; 5, performing multi-dimensional consistency evaluation, and generating a comprehensive score; and 6, self-adaptive optimization is carried out, and self-feedback and self-evolution of model behaviors are realized. By means of the method, the memory ability and historical consistency of the multi-agent large language model can be effectively enhanced.

The invention discloses a cognitive impairment risk intelligent matching intervention system based on multi-modal data, and belongs to the technical field of cognitive impairment, and the cognitive impairment risk intelligent matching intervention system specifically comprises the following steps: collecting a tactile interaction sequence and a face video data stream when a user executes a cognitive intervention task, and constructing an original multi-modal data set; extracting tactile operation track features and reconstructing a heart rate variability sequence, and generating a synchronous multi-mode feature set; identifying a difference interval of state fluctuation and extracting behavior and physiological features in the interval to form an instant physical and mental load parameter set; in combination with an interaction efficiency index in the task execution record, generating a joint state feature vector, and outputting a personalized adaptation instruction through a pre-trained sub-state-parameter association model; and constructing an adaptive strategy model by using the multi-modal features and an adaptive instruction to realize millisecond-level dynamic adjustment from the real-time multi-modal features to task parameters. According to the method, real-time perception and accurate matching of the cognitive emotion load of the user are realized, and the individuation degree and instantaneity of intervention are improved.

The invention relates to a non-invasive brain stimulation self-adaptive closed-loop regulation and control system. The system comprises a task interaction module which is configured to present a time sensing task to a target object and receive an interaction instruction of the target object; the non-invasive brain stimulation module is used for performing non-invasive brain stimulation; the sensing acquisition module is used for acquiring electroencephalogram data and behavioral data of a target object; the closed-loop regulation and control module comprises at least one block-level regulation and control primary unit, and each block-level regulation and control primary unit comprises a plurality of block-level regulation and control primary units; the trial secondary regulation and control primary unit is used for generating a first feature vector in real time on the basis of the currently collected electroencephalogram data and behavioral data so as to obtain a stimulation parameter of the next trial in the current block; the block-level regulation and control first-level unit is used for processing the currently collected electroencephalogram data and behavioral data to obtain a second feature vector, and based on the second feature vector, adaptive search is carried out under security constraints to obtain stimulation parameters of a next block. By adopting the method, the stability of the stimulation effect can be improved.

The invention discloses a remote sensing image change detection method and system based on double-flow SAM and time sequence perception, and aims to solve the problems of insufficient double-time-phase feature interaction, weak time sequence modeling, poor change region sensitivity and the like in the prior art. According to the method, a cross-time-frame attention type memory mechanism (CPMM) and a time perception two-dimensional space modeling module (Temporal-Aware SS2D) are innovatively introduced on the basis of SAM Encoder, the cross-time-frame attention type memory mechanism (CPMM) enhances alignment of a stable structure and features between time phases through lightweight two-way cross-time-phase modulation, and the time perception two-dimensional space modeling module (SSD) deeply fuses double-time-phase features in a dimension reduction space and fuses global context information. And constructing a framework with local detail retention and global time sequence semantic perception to accurately capture a change trend. According to the method, the adaptability, robustness and calculation efficiency of the model to the time-space characteristics of the remote sensing data are remarkably improved, and the accurate change detection of the high-resolution remote sensing image is realized while the high detection precision is kept.

The invention discloses a physical information guided wind speed field data downscaling method fusing terrain and time perception. The method comprises the steps of 1, multi-source physical constraint modeling and data construction; step 2, constructing a generative downscaling framework based on a conditional diffusion probability model; step 3, designing a noise prediction network structure fusing terrain and time prior; and 4, model training and rapid sampling reasoning. The method solves the problems that the texture of a wind speed field generated by an existing deep learning downscaling method is excessively smooth, high-frequency turbulence details are lost, and the terrain forcing effect and the wind speed seasonal / daily periodic physical law are ignored, and provides a framework combining explicit physical feature engineering and a conditional diffusion model. Through dual deep fusion of terrain and time information, high fidelity, physical consistency and reasoning efficiency of a generated result are considered.

The application relates to a non-invasive brain stimulation adaptive closed-loop regulation system, which comprises a task interaction module configured to present a time perception task to a target object and receive interactive instructions thereof; a non-invasive brain stimulation module for non-invasive brain stimulation; a sensing and collecting module for collecting electroencephalogram data and behavior data of the target object; and a closed-loop regulation module comprising at least one block-level regulation primary unit, each block-level regulation primary unit comprising a plurality of trial-level regulation primary units; the trial-level regulation primary unit is used for generating a first feature vector in real time based on the currently collected electroencephalogram data and behavior data, so as to obtain stimulation parameters of the next trial in the current block; and the block-level regulation primary unit is used for processing the currently collected electroencephalogram data and behavior data to obtain a second feature vector, performing adaptive search under safety constraints based on the second feature vector, and obtaining stimulation parameters of the next block. The method can improve the stability of the stimulation effect.

This invention discloses an online education group question-and-answer matching method based on user style and time awareness, relating to the field of question-and-answer matching using deep learning natural language processing technology. The method involves constructing a BigData dataset; dividing the BigData dataset into training, validation, and test sets; building user style-aware and time-aware question-and-answer matching models; training the models using the training set and obtaining performance metrics using the validation set to find the optimal hyperparameters; and inputting the test set into the final user style-aware and time-aware question-and-answer matching model to obtain the matching results. This invention enhances question extraction by recognizing user style through user style awareness, reducing the impact of noise caused by severe imbalances between the number of questions and other types of dialogue. It also reduces the noise caused by a large number of potential answers to a single question through time awareness. Compared with other traditional question-and-answer matching models, this method improves the model's question-and-answer matching performance and reduces the impact of data noise.

The invention discloses a bus bunching prediction method and system based on a time-aware network. The method comprises the following steps: preprocessing bus arrival data, fusing multi-source spatial-temporal characteristics, introducing time period codes, and processing abnormal and missing values; targeted denoising is performed on data with different characteristics based on Fourier analysis, so that the data quality is improved; a time perception neural network is established, local features and long-term dependence are captured through a CNN-LSTM architecture, a time decay factor mechanism is introduced, dynamic modeling of a time sequence information importance decay process is realized, and a long-term rule of data and short-term disturbance after time calibration are effectively integrated; and a dual attention mechanism of time dimension and feature dimension is fused, key features are extracted and integrated, and multi-step prediction of bus bunching is realized. According to the method, the non-linear relation and the space-time dynamic rule of the bus data can be fully captured, and the problem of unequal intervals in a bunching time sequence is effectively solved.

The application provides a network hot review confrontation performance self-adaptive evaluation method and system based on space-time perception and a terminal device, and is suitable for the technical field of network security. The method comprises the following steps: inputting multi-source network data into a multi-scale space-time data fusion model to generate multi-scale space-time features; generating a fusion feature vector through a feature depth fusion processing model based on the multi-scale space-time features; training a three-party strategy network model to be trained based on the fusion feature vector, determining a three-party game equilibrium strategy and an evaluation score corresponding to the three-party game equilibrium strategy; adjusting evaluation indexes through an adaptive evaluation model based on environmental state features to obtain new evaluation index weights; and determining an adaptive evaluation score based on the new evaluation index weights and the evaluation score.

A dynamic scene navigation method based on a two-stage optimization structure and a space-time perception mechanism comprises the steps that four frames of time sequence depth images are obtained through depth estimation and a future frame prediction network, current and future space changes are represented, time sequence depth features and a target state are subjected to joint modeling through a ViT structure with the minimum change, and the time sequence depth images are obtained; global attention association between an image area and a target is realized, and target-oriented spatial-temporal features are extracted; in the strategy learning stage, basic obstacle avoidance and target driving capabilities are learned in a low-dynamic environment by imitation learning, and then two-stage optimization is performed in a high-dynamic environment by combining reinforcement learning with an evaluation result of an imitation strategy, so that the strategy convergence speed and the environmental adaptability are improved. According to the method, the robust navigation performance in a high-dynamic narrow environment can still be realized under the condition that a global map is not needed.

The application discloses an industrial process remaining time prediction method and device and a storage medium, and belongs to the field of data processing. The method comprises the following steps: acquiring a track prefix sequence and inputting the track prefix sequence into an activity completion model to output a complete track prefix sequence after activity completion; extracting a semantic feature vector and a time interval feature vector of each activity in the complete track prefix sequence, splicing the semantic feature vector and the time interval feature vector to generate a fusion feature vector, and arranging the fusion feature vector in an activity order to form a feature sequence; inputting the feature sequence into a remaining time prediction model to output a predicted remaining time of an industrial process instance; wherein the activity completion model is obtained based on a BERT architecture and combined with contrast learning training, and the remaining time prediction model is based on a Transformer architecture and introduces a time perception attention mechanism. The effective repair of missing industrial process activities, the deep fusion of multi-dimensional features and the accurate modeling of time dynamic characteristics are realized, and the accuracy of the predicted remaining time is improved.

The invention relates to the technical field of human body motion analysis, in particular to a 3D human body posture estimation and multi-key-point time sequence analysis method. Comprising the following steps of multi-modal video access, human body key point space-time perception and extraction, 3D posture reconstruction and credibility modeling, key point time sequence feature quantification, time sequence stage perception and logic judgment, quantitative evaluation and intelligent diagnosis and result output, namely, analysis results are output in the forms of scores, texts, graphs or voices. The method is used for guiding a user to perform action correction, and solves the problems of insufficient time sequence semantic understanding, poor individual difference adaptability and lack of interpretability and targeted guidance of an analysis result in human body posture estimation and action analysis in the prior art.

The invention discloses an auditing manuscript verification optimization method and system based on space-time perception and a pseudo regulation generation strategy, and the method comprises the steps: firstly constructing an auditing knowledge base containing multi-level regulations and systems, and then carrying out the preprocessing of an auditing manuscript sample through the auditing knowledge base, and obtaining a preprocessed auditing manuscript; extracting timeline features in the preprocessed audit manuscript; according to the method, the functions of accurately restoring a legal environment in a specific time-space and introducing a pseudo-regulation generation strategy to fill a business and a legal semantic gap are realized, and a multi-level system can be fully covered through a multi-source bursting retrieval mechanism; meanwhile, a composite mode of space-time perception, reverse generation and bursting retrieval is adopted, so that the defects of law and regulation reference failure, high retrieval noise and unclear system application range in the existing auditing qualification can be fully eliminated, the auditing work is more compliant, intelligent and efficient, the accuracy and reliability of an auditing conclusion are guaranteed, and the auditing efficiency is improved. And the device is suitable for wide popularization and use.