1977 results about "Supervised learning" patented technology

A robotic surgical system includes one or more robotic actuators configured to interact with biological tissue during a surgical procedure. A plurality of sensors include at least one of fiber Bragg grating sensors, piezoelectric strain sensors, or magnetostrictive sensors to capture real-time mechanical, elasticity, or deformation data from biological tissues. deep learning engine trained on a dataset comprising tissue mechanical responses across multiple tissue types, pathological states, and patient demographics. Pre-contact predictive adjustment profiles are generated for anticipated tissue interactions using preoperative imaging data registered to intraoperative coordinates. Intraoperative deviations are detected from predicted mechanical behavior and autonomously recalibrate actuator forces. Upcoming surgical maneuvers are anticipated based on prior task sequences and adjust actuator stiffness or damping properties in preparation for anticipated contact. An emergency override of actuator forces is provided via an anomaly detection module when real-time sensor data deviates beyond a threshold from the predicted safe mechanical response range. A feedback loop iteratively refines the deep learning engine during the procedure using supervised learning updates, anomaly detection, and reinforcement learning strategies. The reinforcement learning model is optionally shared across procedures to optimize distributed actuator force patterns for minimizing localized and cumulative tissue stress.

The invention provides a semi-supervised image semantic segmentation method and system based on a visual basic model, and the method comprises the steps: constructing a multi-task model which comprises a visual basic model and a depth estimation basic model, and the visual basic model is connected with a task solution head, an adapter parameter efficient fine tuning module and a multi-modal cross fusion module; the task solution head comprises a semantic segmentation head and a depth estimation head; extracting semantic hierarchy features and a depth feature map of the RGB image, performing cross attention fusion on the semantic hierarchy features and the depth feature map, and inputting obtained fusion features into a semantic segmentation head and a depth estimation head respectively; semi-supervised learning is adopted to train a multi-task model, only parameters in the adapter parameter efficient fine tuning module and the multi-modal cross fusion module are trained, and a multi-task loss function is adopted. The image semantic segmentation model obtained through training can improve semantic segmentation performance, reduce training cost and is suitable for different tasks.

The invention relates to a power distribution network data intelligent analysis method based on data consanguinity and multi-modal fusion learning. The method comprises the following steps: S1, constructing a dynamically evolved data consanguinity topological graph; s2, designing a label-guided graph neural network architecture, embedding historical abnormal knowledge into a graph learning process, and outputting a deep semantic feature vector; s3, constructing a multi-modal fusion analysis framework, performing multi-dimensional feature fusion and data quality analysis, and identifying abnormal nodes; s4, designing a semi-supervised and incremental learning combined mixed training normal form, and performing model training and strategy optimization; and S5, based on the dynamic consanguinity topology constructed in the step S1 and the identified abnormal nodes, constructing a probabilistic reasoning framework, and fusing the model parameters obtained by optimization in the step S4 to realize quality abnormality root positioning and full-link visualization so as to form a complete data intelligent analysis scheme. According to the invention, efficient and accurate management of the topological data quality of the power distribution network is realized.

A method for training a machine learning (ML) model using a large language model (LLM) is provided. A system for detecting fraud which utilizes the LLM-trained ML model trained is also provided. An artificial intelligence (AI)-based method for monitoring alerts is also provided. The method for training an ML model using an LLM includes receiving tabular data for training the ML model, generating one or more natural-language strings comprising information from the tabular data, generating, via a base LLM, one or more prompts and completions based on the one or more generated natural-language strings, pre-training the base LLM using a plurality of generated prompts and completions, updating the base LLM via supervised learning using a cross-entropy loss function with ground-truth labels, and fine-tuning the updated LLM via reinforcement learning with human feedback using a reward model and a proximal policy optimization model to produce the LLM-trained ML model.

A computer implemented method for training a whole medical image foundation model, including: receiving a plurality of medical image datasets; extracting local sections of image data from the plurality of medical image datasets; obtaining one or more causal variables associated with the local sections and / or patient; training one or more self-supervised learning models based on the local sections of image data and the causal variables; combining the one or more trained self-supervised learning models with a deep learning network configured to combine a latent representation of the local sections of image data from the one or more trained self-supervised learning models into a patient-level representation; and combining, with the one or more trained self-supervised learning models and the deep learning network, at least one further network or function configured to accept the patient-level representation as input, the at least one further network or function operable to perform one or more patient-specific prediction tasks.

The invention discloses an abnormal traffic detection method and system based on deep learning and a generative adversarial network, and relates to the technical field of network security and artificial intelligence. In order to solve the core problems of scarcity of annotated data, unbalanced categories, difficulty in feature extraction and the like in abnormal traffic detection, the invention aims to construct a self-supervision-generation-attention three-layer collaborative detection architecture: general features are extracted from unannotated traffic through a self-supervision feature representation learning module, and the problem of annotation dependence is solved; a VAE-GAN generation enhancement module is used for generating high-quality samples for minority class abnormal traffic, and class balance is achieved; packet-level, flow-level and session-level multi-modal features are dynamically fused based on a multi-head attention mechanism, accurate detection is carried out in combination with a Transform-CNN-LSTM hybrid model, and interpretable analysis is provided. The method is characterized in that end-to-end high-precision abnormal flow detection is realized systematically through organic cooperation of data acquisition and preprocessing, self-supervised learning, generation enhancement, attention detection and a result output module.

The invention provides a semi-supervised target detection method for a visible light-infrared multi-mode fusion scene. The method comprises the following steps: constructing a semi-supervised visible light-infrared multi-modal image data set based on an LLVIP data set; on the basis of a YOLOv11 model architecture, constructing a target detection model oriented to multi-modal image feature fusion, and training the target detection model by using a semi-supervised visible light-infrared multi-modal image data set in a deep learning end-to-end mode to obtain a trained target detection model; and inputting a to-be-detected multi-modal image into the trained target detection model, and outputting a target detection result of the to-be-detected multi-modal image by the trained target detection model. The method is based on a semi-supervised learning normal form, so that the precision and robustness of target detection in a multi-modal fusion scene are improved, and the requirements for high efficiency and reliability of target recognition in practical application scenes such as intelligent traffic and intelligent security and protection are met.

The invention discloses a prefabricated cabin welding seam quality detection method based on self-supervised learning, and the method comprises the following steps: collecting a multi-source welding seam image and process parameters, carrying out the synchronous calibration, and constructing a multi-modal observation matrix; the image is input into a DINOv2 model based on a visual Transform, dense features are obtained, and inter-frame registration and sequence reconstruction are completed; performing difference analysis on adjacent frames, extracting spatial changes and marking potential defects; the dense features and the process parameters of the corresponding time periods are fused, joint features are constructed and classified according to rules, and a preliminary result is output; inputting the defect area and the process parameters into an improved DEER model, extracting an influence path and amplitude, and generating a sensitivity score and a confidence coefficient; final judgment is given in combination with the preliminary result, the sensitivity and the confidence coefficient, and feedback is formed according to judgment and process difference. According to the method, high-precision and explainable detection and process optimization of weld defects are realized, and the method is suitable for online / offline quality control and tracing.

The invention belongs to the technical field of aero-engine state monitoring and intelligent fault diagnosis, and discloses a multi-modal information fusion bearing fault diagnosis method based on self-supervised learning. The method comprises the following steps: firstly, through mask reconstruction self-supervision pre-training, extracting stable feature representation insensitive to mask disturbance from an unlabeled multi-modal signal, and dynamically updating each modal feature reference point by using an index moving average algorithm; in a downstream fault diagnosis task, a multi-modal joint decision model comprising a pre-training encoder, a single-modal classifier and a fusion classifier is constructed, and adaptive weighted fusion of multi-modal decision is realized through contribution degree calculation based on a cooperative game Shapley value in combination with a deviation degree of modal features and a reference point. According to the method, the dependence of the deep neural network on fault labeling data is effectively reduced, the accuracy and robustness of the diagnosis system in a multi-modal signal diagnosis scene are improved through a dynamic fusion mechanism, and the method is suitable for industrial scenes with limited sample label resources.

The invention discloses a digital archive online management system based on big data. The digital archive online management system comprises a digital acquisition layer which is used for carrying out semantic perception and structured extraction on heterogeneous archives; and the intelligent classification layer is used for mapping the collected archive entities, attributes and relationships to a dynamically expanded domain knowledge graph based on a knowledge graph construction technology and a graph neural network, realizing association mining and dynamic classification of cross-modal archives through node embedding and link prediction, adapting to evolution requirements of archive themes in combination with a weak supervised learning mechanism, and realizing dynamic classification of the cross-modal archives. A classification system with causal interpretation is formed; the storage retrieval layer is used for encoding the generation time, the space trajectory and the event causal chain of the archive into space-time causal metadata; the archive utilization layer is used for actively pushing associated archives and generating a personalized analysis report by analyzing user behavior preferences and scene requirements; and the backup layer is used for dynamically sensing the threat type and calling an evolutionary algorithm to adjust the backup frequency, the storage position and the recovery path.

The invention discloses a traffic network toughness diagnosis method under flood disasters based on a space-time diagram neural network, and relates to the crossing field of traffic engineering and artificial intelligence. The method comprises the following steps: collecting traffic topology, flood monitoring and traffic flow data, and carrying out space-time alignment; a flood coupling dynamic space-time diagram is constructed, a water depth-traffic capacity response mechanism is introduced, and real-time mapping from a disaster physical state to a network topology is realized by utilizing an attenuation function meeting physical monotonicity constraint and dynamically updating an edge weight of a diagram structure according to real-time water depth; inputting the dynamic graph into a pre-trained space-time graph neural network model, extracting space-time evolution characteristics and outputting a toughness diagnosis result; model training adopts a toughness label generated based on an anti-fact baseline to carry out supervised learning, and introduces a physical constraint loss function. According to the method, the problems of decoupling of disaster features and graph structures and unavailability of toughness labels in the prior art are solved, and the physical consistency and accuracy of diagnosis are improved.

The invention discloses a multi-mode emotion continuous recognition method for medical treatment, belongs to the technical field of artificial intelligence and medical treatment information, and mainly aims to simulate the dynamic change process of emotion by establishing a Neural ODEs framework and overcome the static property and discreteness of emotion modeling in a traditional method. Through a causal inference technology, emotional features are separated from individual-independent physiological differences, and the generalization ability across individuals is improved. A self-supervised learning method is utilized, the synergistic effect between the EEG and the eye movement signal is improved through cross-modal contrast learning, and the emotion recognition precision is enhanced. The calculation complexity is reduced through a dynamic sparse attention mechanism, and meanwhile, focusing is performed on a key time slice in emotion recognition. Through multi-task joint learning, the model learns multiple tasks such as emotion intensity regression and tested identity recognition during emotion classification, and the personalized emotion recognition capability is improved.

The invention belongs to the technical field of image processing, tracking and recognition, and relates to a multi-mode re-recognition method based on semantic-style decoupling distillation. The method depends on a multi-modal re-identification model which comprises a multi-modal feature extractor comprising a teacher branch module and a student branch module, a decoupling distillation module and a hierarchical self-supervised learning module, and comprises the following steps: constructing a mixed multi-modal feature extractor sharing a shallow layer and an independent deep layer to extract mixed features; performing dual supervision of semantic distillation and style distillation, modeling modal-invariant semantic information and modal-specific style information, and realizing effective decoupling of a feature space; a hierarchical self-supervised learning space is constructed, and in combination with intra-modal and cross-modal comparative learning, images under local damage and style disturbance conditions are scrambled; according to the method, recognition performance and reasoning efficiency are both considered, semantic features and modal specificity styles are effectively separated, semantic consistency, feature robustness and network learning efficiency are cooperatively improved, and modal specificity is also reserved.

The invention discloses a winter wheat LAI and SPAD estimation method based on a lightweight semi-supervised model, and relates to the technical field of agricultural remote sensing monitoring, and the method comprises the steps: obtaining multispectral image data of a winter wheat key growth period, and carrying out the preprocessing of the multispectral image data to generate a standardized multichannel vegetation index image; the method comprises the following steps: constructing a lightweight semi-supervised model MCVI-SANet, and carrying out self-supervised training on the MCVI-SANet by adopting a semi-supervised training strategy driven by VICReg; and inputting the multi-channel vegetation index image into the trained MCVI-SANet, and outputting quantitative estimation results of the LAI and SPAD of the winter wheat. Through combination of a saturation perception mechanism and semi-supervised learning, estimation deviation caused by dense canopy vegetation index saturation and data noise is effectively eliminated, and the estimation precision and generalization ability in a complex agricultural scene are improved while the lightweight deployment characteristic of the model is ensured.

The invention discloses a spectrum aliasing decoupling and concentration inversion method under the cross influence of multi-source environmental factors, belongs to the field of industrial process control and environment monitoring, and constructs an environment-spectrum collaborative fusion decoupling model for concentration prediction. The method specifically comprises the following steps: respectively collecting absorption spectrum signals of specified mixed gas at different temperatures, pressures and known concentrations, meanwhile, collecting environmental parameter data, constructing a multi-source data set, and carrying out denoising, dimension reduction and preprocessing on the multi-source data set; constructing a self-supervised feature extraction network for adaptive modulation of environmental parameters to realize deep fusion of spectrum and environmental information; the feature expression capability and generalization performance of the self-supervised feature extraction network are improved by using a self-supervised learning mechanism; and constructing a BPBO-GRNN self-adaptive concentration inversion optimization model for realizing inversion of mixed gas concentration and self-adaptive optimization of model parameters. According to the invention, high-precision concentration inversion and stable detection of the aliasing gas can be realized.

The invention discloses a deeply-forged face video frame-level positioning method and system based on weak supervised learning, and the method comprises the steps: firstly constructing a training set with a video as a unit, carrying out the data enhancement of a frame-level sample, and generating an enhanced view pair; secondly, splicing the enhanced view pair and inputting the spliced enhanced view pair into a depth forgery detection model to obtain and generate fusion enhanced frame-level features; then, intra-class contrast learning loss, time sequence consistency constraint loss and frame weight loss are constructed, and a deep forgery detection model is trained based on fusion-enhanced frame-level feature joint optimization. And finally, inputting a video to be detected into the deep counterfeiting detection model to output the frame-level confidence, judging whether the video is a forged video or not, and realizing frame-level counterfeiting positioning. According to the method, video-level detection and frame-level positioning are effectively realized, meanwhile, the influence of label noise in part of forged videos is relieved, and the generalization and robustness of the system are improved.

The invention provides an enterprise intelligent finance and taxation system fusing supervised learning and a block chain, and solves the core technical problems of insufficient data credibility, transparent contradiction between privacy protection and supervision, AI model training data island and the like of a traditional finance and taxation system. According to the system, an innovative technical fusion scheme is adopted, bank API, OCR recognition, voice input and other multi-source financial data are integrated through a multi-modal data fusion unit, and high-quality data fusion is achieved through confidence evaluation and an intelligent conflict resolution algorithm; an intelligent classification unit based on BERT deep learning integrates a pre-training model with a business rule engine and a gradient boosting decision tree, and accurate and automatic classification of financial transactions is achieved. A complete technical solution is provided for enterprise finance and taxation digital transformation, intelligent, automatic and credible processing of finance and taxation businesses is achieved on the premise that data safety and privacy protection are guaranteed, and the method has wide market application prospects.

The invention discloses a humanoid robot reinforcement learning gait control method and system, and belongs to the technical field of robot control. Comprising the following steps: constructing a model prediction control optimization problem based on a linear inverted pendulum model, and generating a robot mass center track and a foothold sequence; collecting state-action pair data of model prediction control, and training a neural network model by adopting supervised learning; designing a reinforcement learning strategy network, taking the output of the neural network model as a physical guidance reference, calculating a training reward based on the constructed composite reward function, training the strategy network in a high-concurrency simulation environment by adopting a near-end strategy optimization algorithm, and outputting a joint action instruction; and verifying the trained strategy and the joint action instruction output by the trained strategy in a plurality of simulation environments, and deploying the trained strategy and the joint action instruction to a real machine for dynamic gait control. According to the method, the stability and adaptability of gait control of the humanoid robot are improved through a method of combining model predictive control and reinforcement learning.

A dynamic adaptive learning method for mineral prediction includes: collecting a dataset including geological data and labels of the geological data; extracting features from the geological data, initializing parameters of a training model and optimizing the parameters to obtain training parameters; performing an associative training on the training model based on the training parameters and the labels in a dynamic adaptive learning framework to obtain a mineral prediction model, algorithms of the associative training including a variational expectation algorithm and a variational maximization algorithm, and the variational expectation algorithm including an unsupervised learning mode, a semi-supervised learning mode, and a fully supervised learning mode; and predicting, by using the mineral prediction model, a mineral to obtain a mineral prediction result. The method can break through limitations of the traditional machine learning technology, offering a more efficient, universal, and stable strategy for geophysical data analysis and mineral resource assessment.

The invention relates to the technical field of wires and cables, and particularly discloses a wire and cable test system based on sensor data acquisition, which comprises a data acquisition module, an intelligent analysis module and a function output module. The intelligent analysis module integrates technologies such as multi-modal signal blind source separation, mechanism-data hybrid drive deep learning, federated learning and digital twinborn linkage and self-supervised learning optimization, and forms a layer-by-layer progressive analysis system. Interference components are effectively eliminated through a signal separation technology, meanwhile, the adaptability of the model to different working conditions and different cable types is improved by means of fusion of mechanisms and data, model collaborative optimization under multi-site data privacy protection is realized through federated learning, and a self-supervised learning-driven digital twinborn evolution mechanism is combined, so that the multi-site data privacy protection model is optimized. The problems that a traditional analysis technology is insufficient in generalization ability, simulation precision is prone to drifting, and privacy risks exist in data sharing are solved, and the accuracy of fault recognition and the long-term adaptability of the system are remarkably improved.

In various examples, self-supervised learning may be used to pre-train an encoder network of a masked prediction model to reconstruct masked regions of an input representation of 3D detections such as LiDAR point cloud(s). Spatial and / or temporal masking may be applied to a projected representation of 3D detections (e.g., a two-dimensional (2D) projection image), and the masked prediction model (e.g., a masked auto-encoder or joint-embedding predictive architecture) may be used to reconstruct a representation of the masked regions (e.g., reflection characteristic(s) stored in corresponding pixels or cells of the projected representation, a latent representation of the reflection characteristic(s)) during iterations of self-supervised learning. As such, the pre-trained encoder network of the masked prediction model may be used as a foundation model and fine-tuned with a task-specific output head or its pre-trained weights may be used to initialize a task-specific model.

The invention provides a deadline constraint-based DAG application dynamic scheduling optimization method and system, and the method comprises the steps: converting an application deadline into an instant reward of each task scheduling through employing a DAG structured encoder, a Transform encoding network based on gating feature fusion, and a multi-action selection deep reinforcement learning task scheduling method based on a pointer network, in combination with a dynamic mask scheme, the mobility of a DAG application and the dynamic nature of edge resources are dealt with, then priority subtask selection and real-time decision of the scheduling position of the priority subtask selection are made, and the completion time and execution energy consumption of the application are reduced. In order to stabilize and accelerate DRL scheduler training, task encoder training and reinforcement learning training are decoupled, and a DAG encoder is pre-trained based on self-supervised learning.

The invention discloses a deep learning assisted acceleration fracturing construction parameter intelligent real-time optimization method, and belongs to the field of unconventional oil and gas field development, and the method comprises the steps: constructing a structured sample database covering geological attributes, engineering parameters and fracturing effect responses, and carrying out the unified preprocessing of multi-source data; constructing a multi-modal space-time collaborative prediction model, and combining a multi-expansion time permissible convolutional network, a three-dimensional residual network and a cross attention mechanism; supervised learning training is carried out based on a database, sparse regularization and learning rate scheduling are introduced, and the model precision and generalization ability are improved; a hierarchical collaborative optimization framework of outer-layer Bayesian search-inner-layer CMA-ES refinement is provided, and reservoir transformation volume maximization and construction feasibility are achieved under complex constraints; compared with an existing method, optimization parameters of the method include the cluster distance and the section distance and further include the displacement, the sand concentration, the fracturing fluid type and other construction parameters, and real-time optimization of the fracturing construction parameters can be achieved through the machine learning agent model.

The invention discloses a power distribution network transient characteristic prediction method based on supervised learning, and relates to the technical field of power distribution network state prediction, and the method comprises the steps: collecting historical operation data through a power distribution network monitoring system, carrying out the data preprocessing, and obtaining standardized multi-dimensional time series data; carrying out transient feature extraction, constructing a high-dimensional feature set, and carrying out feature dimension reduction according to a transient event tag to generate a feature subset; inputting the feature subset into a mixed supervised learning model of a gradient boosting decision tree GBDT and a long short-term memory network LSTM for joint training to obtain a transient feature prediction result; and calculating a root-mean-square error according to the transient characteristic prediction result and the real-time monitoring observation value of the power distribution network, and dynamically adjusting hyper-parameters of the supervised learning model based on a Bayesian optimization algorithm. According to the method, the detection accuracy can be improved, the calculation complexity can be reduced, and the discrimination capability and the time sequence prediction capability of the model are considered.

The invention provides a simulation test key factor screening-oriented method and system and a computer program product. The method comprises the following steps: generating a structured configuration file; constructing a supervised learning data set based on the structured configuration file; based on the supervised learning data set, training a machine learning classification model to obtain a current key factor set; and repeating the steps, judging whether the current key factor set is converged or not, and if the current key factor set is converged, stopping simulation and outputting the current key factor set of the last round as a final key factor. According to the technical scheme of the invention, a high-dimensional, nonlinear and high-coupling complex system can be automatically processed; key factors are objectively recognized through machine learning, a small-batch iteration verification mechanism is adopted, and the screening accuracy and efficiency are improved while the number of times of simulation is remarkably reduced.

The invention discloses an indoor environment automatic adjustment method based on self-supervised learning, and the method comprises the steps: collecting the multi-modal data of an indoor environment and a user behavior, completing the synchronization and standardization processing, and constructing a causal graph model which comprises an environment variable, a user behavior variable and an adjustment response variable; adjusting causal representation vectors are generated through reverse causal modeling, building structure parameters, user preferences and climate regionalization information are fused, and a unified cross-modal embedding space is constructed; and further training an adjustment strategy migration model based on a federal migration learning mechanism, and generating a personalized control instruction in combination with local terminal data. The method has the advantages of being high in causal reasoning ability, accurate in cross-modal fusion expression, high in control strategy adaptability and the like, and is suitable for application scenes such as intelligent buildings, energy-saving air conditioning systems and environment sensing type home furnishing.

The invention discloses an artificial intelligence denoising method for a speckle shearing interference image based on self-supervised learning. The method is a self-supervised image denoising method based on blind spot learning. According to the method, an improved self-supervised network architecture is adopted, pixel points of an image are input through a random mask and are replaced by neighborhood pixel values, and a blind spot training sample is constructed. The network only learns and predicts an original noise value of a masked pixel point in a training process, and does not depend on a clean image as a supervision signal, so that real self-supervised learning is realized. The de-noising method comprises the steps of constructing a data set meeting training requirements, performing de-noising model training by using a blind spot learning method and a self-supervised network, performing de-noising calculation on a speckle interferogram through a fully trained model, and finally obtaining a de-noised interference image. The method has the characteristics of simplicity and convenience in calculation and high processing speed, and can meet the requirement of large-data-volume image processing.

The invention relates to the technical field of fault diagnosis, in particular to a few-label self-supervised learning fault diagnosis method based on an interpretable neural network, and the method comprises the steps: collecting time domain data of a sensor of an aero-engine under different health conditions, carrying out the standardization processing, and dividing the time domain data into a pre-training set, a training set, a verification set and a test set; performing fast Fourier transform and data enhancement on the time domain data in the pre-training set to obtain frequency domain data and enhanced time domain data; constructing a pre-training framework, and performing pre-training to convergence based on the frequency domain data and the enhanced time domain data to obtain a pre-trained time encoder; constructing a fault diagnosis model based on the pre-trained time encoder, and performing iterative training to convergence by using the training set to obtain a trained fault diagnosis model; and performing fault diagnosis on the test set by using the trained fault diagnosis model, and performing visual interpretation on the diagnosis process of the fault diagnosis model by using a gradient weighting class activation mapping technology.

The invention relates to the technical field of automatic driving and intelligent control, in particular to a multi-transportation-equipment cooperative motion control method based on multi-stage mixed learning and a storage medium, and the method comprises the steps: generating expert demonstration data through employing a single-vehicle motion control algorithm based on an expert rule, performing initialization training on the strategy network through online iterative supervised learning to obtain a pre-training strategy model; the multi-vehicle cooperative motion control method comprises the following steps: selecting a multi-vehicle cooperative motion model, loading parameters of the model into an Actor strategy network of multi-agent reinforcement learning, performing interactive training on a plurality of agents in a simulation environment by adopting a centralized training and decentralized execution normal form, and performing online iterative optimization on the strategy based on a composite reward function and generalized advantage estimation to obtain a multi-vehicle cooperative motion control strategy. According to the method, the complementary advantages of imitation learning and reinforcement learning are exerted, the training efficiency, the strategy performance and the collaborative operation capability and robustness of the system in a complex scene are improved, and the method can be directly applied to collaborative scheduling and control of transportation equipment groups in scenes such as surface mines and ports.

The invention relates to the technical field of power utilization monitoring, and discloses a photovoltaic user power utilization abnormity monitoring method and system based on artificial intelligence. The photovoltaic user electricity consumption abnormity monitoring system based on artificial intelligence comprises a data acquisition module which is used for acquiring photovoltaic power generation data, electricity consumption data and environment data of a user; the data preprocessing and feature engineering module is used for cleaning, aligning and normalizing the original data acquired by the data acquisition module and constructing a feature data set for model training and reasoning; and the artificial intelligence analysis engine module comprises an unsupervised learning unit, a supervised learning unit and a deep learning unit. According to the invention, the false alarm rate and the missing report rate can be effectively reduced, the accurate diagnosis of the abnormal type can be realized, and the intelligent and accurate operation and maintenance requirements of power grid enterprises on the power utilization monitoring of photovoltaic users are met.