501 results about "Learning based" patented technology

Some embodiments of a method may include: decoding a motion feature by accessing a motion bitstream; predicting a predicted feature based on the motion feature and one or more reference point cloud frames; decoding a first feature representing an occupancy status of a child level voxel; predicting a second feature based on the first feature and the predicted feature; and decoding a tree voxel occupancy status of the child level voxel via the second feature.

Techniques for applying a generative artificial intelligence (AI) model to identify and correct anomalies in remediation records are disclosed. A system trains and applies a generative AI model to displayed datasets to predict remediation record anomalies. If the system detects the generation of a remediation record in a dataset to reconcile the displayed datasets, the system generates a generative AI prompt that includes the remediation record. The generative AI model generates an output that identifies anomalies in the remediation record and the datasets being reconciled. The generative AI model further generates recommendations for remediating errors in the remediation record.

The invention discloses an enterprise and policy service automatic matching method based on machine learning, and the method comprises the steps: carrying out the processing of enterprise multi-source data, constructing an enterprise portrait graph, and generating an enterprise graph embedding and structuring feature set; performing policy text analysis and condition recognition, constructing a policy condition graph and generating condition graph embedding representation; constructing a condition constraint field based on policy conditions, and generating a cross-graph alignment relationship and fusion features; integrating a multi-source feature input improved model to carry out joint modeling, and outputting a basic matching score; constructing a condition boundary manifold, and generating an anti-fact feature sample and a matching elasticity score; and based on the basic and elastic scores, generating a comprehensive score and outputting matching result information. According to the invention, by introducing graph structure perception alignment, conditional constraint guide interaction and a multi-channel scoring aggregation mechanism, high-precision, high-interpretability and intelligent reachability automatic matching between enterprises and policy services is realized.

The invention relates to the technical field of remote sensing data processing and earth surface parameter inversion, and discloses an earth surface matrix parameter hyperspectral data inversion method and system based on machine learning. Comprising the following steps: constructing a multi-source heterogeneous hyperspectral data set; performing feature screening on the preprocessed hyperspectral data set based on an adaptive band selection algorithm, constructing a dynamic weight matrix by calculating mutual information entropy and inter-class distance measurement between spectral bands to realize intelligent screening of key feature bands, and combining spectral derivative conversion and spectral index calculation to generate an enhanced feature vector; and a multi-task transfer learning neural network model is constructed, and an output layer realizes multi-parameter collaborative inversion based on a multi-task learning architecture. And performing preprocessing and feature enhancement operation which is the same as that of the training data on the hyperspectral image data of the to-be-inverted region, inputting the trained neural network model, and outputting a surface matrix parameter inversion result.

The invention discloses a digital twinning multi-agent reinforcement learning intelligent decision-making system and method with a secure memory playback mechanism, and the system comprises a digital twinning module which is used for constructing a virtual model and synchronizing the virtual model with a physical entity in real time; the multi-agent reinforcement learning module is used for carrying out strategy learning based on a constrained Markov decision process and balancing performance and safety through a Lagrange multiplier; the safe memory playback module is used for weighting and playing back the experience samples according to the risk and the timeliness so as to improve the learning safety; the reversible grey influence network module is used for causal modeling and reasoning and enhancing decision interpretability; the double-loop self-constraint control module ensures that a control action is always in a physical safety boundary through a barrier function and safety projection; and the convergence and stability criterion module is used for verifying strategy security convergence and system asymptotic stability. According to the method, the problems of strategy border crossing, virtual-real mismatching and the like in the high-risk manufacturing process are solved, and multi-target optimal control under the safety constraint is realized.

An object of a system according to an embodiment is to provide optimal learning support according to individual learning needs of learners.SOLUTION: A system according to an embodiment includes a learning history analysis unit, a customized content generation unit, a comprehension degree monitoring unit, and an advice providing unit. A learning history analysis part analyzes the learning history and interest of the learner. The customized content generation unit generates learning content on the basis of the result analyzed by the learning history analysis unit. The comprehension degree monitoring unit provides the learning content generated by the customized content generation unit and monitors the comprehension degree and progress of the learner. The advice providing unit provides advice based on a result of monitoring by the comprehension degree monitoring unit.SELECTED DRAWING: Figure 1

The invention relates to the technical field of data processing, in particular to a relational database intelligent query method based on machine learning, which comprises the following steps of: processing multi-modal flow data through time sequence alignment, generating a unified semantic representation vector, constructing a dynamic psychological state map, and modeling a psychological state evolution track by utilizing a neural common differential equation mechanism. After user query is received, historical dialogue nodes are retrieved from the graph, enhanced query intention representation is generated, the enhanced query intention representation is converted into an execution plan through a neural symbol inference engine, and a graph neural network is adopted to predict execution cost. And finally, a personalized analysis report is generated by combining a causal discovery algorithm, and system adaptive optimization is realized through feedback signals. According to the method, the problems of inconsistent time sequence semantics and strong context dependency of the multi-modal psychological data are effectively solved, and the query accuracy and the personalized level in a psychological dialogue scene are improved.

The invention discloses an educational resource recommendation method and system based on artificial intelligence. The method comprises the following steps: acquiring audio data, interaction data and task data acquired by a user terminal; performing feature extraction on the audio data, the interaction data and the task data to obtain an emotion feature vector, a learning rhythm vector and a content feature vector; inputting the emotion feature vector and the learning rhythm vector into a pre-constructed emotion recognition model to obtain a psychological state vector; the cognitive load is calculated based on the learning rhythm vector and the content feature vector, and then the cognitive load is corrected through the psychological state vector; matching a state interval of the corrected cognitive load according to a preset threshold interval; and according to the state interval, adjusting a difficulty coefficient of the recommended course, rearranging a course content sequence and an auxiliary learning prompt, generating structured data, and outputting the structured data as an intelligent auxiliary learning recommendation result. According to the invention, online learning interactivity and teaching quality in rural and remote areas are effectively improved.

In one implementation, geometry of a point cloud is encoded / decoded. On the encoder side, the encoder determines a first feature representing a voxel occupancy status of a current level and / or one or more finer levels of the point cloud, based on the voxel occupancy status of the current level and / or the finer levels; determines a second feature representing prediction of the voxel occupancy status of the current level and / or the finer levels of the point cloud; determines a third feature associated with the voxel occupancy status of the current level and / or the finer levels, based on the first feature and the second feature; and encodes the third feature. On the decoder side, the first feature is decoded from a bitstream, the second feature is determined similarly as the encoder side, and the third feature is determined based on the first feature and the second feature.

There is provided a system and method of automatic software testing. The method includes obtaining an input including software code of a software program and metadata, and feeding the input to a machine learning model to generate a test suite usable for testing the program. The test suite comprises a set of tests meeting a predefined condition. The test suite is generated by generating at least one question related to at least one of: expected intents of one or more sections of the software code, or tests for testing the sections, and presenting the at least one question to a user; upon receiving feedback from the user, analyzing the feedback with respect to the predefined condition, and determining whether to generate at least one new question; and, in response to an affirmative determination, repeating the above process with respect to the new question, until the predefined condition is met.

The invention relates to a wind noise modeling method and system based on machine learning and application, and belongs to the field of marine acoustics and environmental noise modeling, and the method comprises the steps of data preprocessing and feature extraction, hybrid network model building, hybrid network model training and verification. According to the method, a hybrid network model of multiple linear regression and a multi-layer perceptron is constructed based on a known physical mechanism of wind noise and two main noise generation mechanisms of surface turbulence and bubble oscillation, a linear relation and a non-linear relation are modeled respectively, outputs of the two models are integrated through a weighted fusion strategy, and a multi-layer perceptron model is constructed. Smooth transition modeling from a low-wind-speed linear relation to a high-wind-speed nonlinear relation is achieved.

The invention relates to the technical field of laboratory safety risk assessment, and discloses a laboratory safety risk dynamic assessment method based on machine learning, and the method comprises the steps: S1, collecting the multi-source real-time data of a laboratory environment and equipment; s2, carrying out preprocessing and time sequence synchronization on the multi-source real-time data; s3, extracting time sequence features from the time sequence data based on a sliding time window; s4, inputting the feature vector into a machine learning model with an online learning capability; s5, distributing according to the risk prediction result and the current data; and S6, when the risk level reaches a preset condition, triggering laboratory safety early warning and linkage control. Incremental updating is carried out on the machine learning model by inputting feature vectors in real time, adaptive iteration adjustment is carried out on a to-be-updated parameter set based on prediction error changes of a continuous time window, risk judgment is corrected in time along with environment changes, and the real-time performance, sensitivity and stability of model risk prediction are improved.

A system allows multiple users to interact with the system to perform data analysis. The system allows users to specify data analytics requests using high-level natural language requests. The system generates an execution plan based on natural language requests received from a particular user and executes the execution plan. The system detects a failure in executing the execution plan and determines whether to request help from another entity. The system may change the state of execution of the execution plan to a waiting state in which the system blocks execution until it receives an approval to proceed from an entity. The system receives a request to modify the execution plan from the entity and modifies the execution plan based on the request. The system iteratively performs the modification of the execution plan until an acceptable execution plan is generated.

The invention discloses an integrated current transformer fault diagnosis system and method based on machine learning, and relates to the technical field of fault diagnosis. Comprising a current transformer abnormity primary judgment module, a primary judgment abnormal current transformer state label judgment module, a disturbed current transformer disturbed data updating module and a fault source current transformer fault diagnosis module. According to the method, the feature vectors are constructed, and the multi-task gating neural network model is combined to carry out label probability determination, so that the body fault and the disturbed abnormity of the current transformer can be effectively distinguished, and corresponding diagnosis or data updating branches are automatically triggered for different fault types; under the complex working conditions of external electromagnetic interference, load fluctuation and the like, disturbed channel data are self-corrected in real time, so that the stability and the consistency of an overall data set are recovered, the misjudgment rate and the omission ratio are reduced, the robustness of transient disturbance and the fault positioning precision under a conjoined structure are improved, and the fault positioning efficiency is improved. And finally, reliable operation and long-term stability of the power grid measurement and protection system are ensured.

The invention relates to the technical field of data processing, in particular to a personalized learning path planning method and system. Comprising the following steps: acquiring a behavior data sequence arranged according to a time sequence, and extracting a repetitive mode in a learning behavior and a difference point deviating from a standard learning process to obtain a behavior difference index; dynamically adjusting an association structure between nodes in the knowledge graph, identifying key knowledge nodes, determining a missing concept set, and inserting missing concepts into a current learning path to generate a supplementary path draft; by simulating a plurality of alternative learning paths and calculating coherence scores of the alternative learning paths, screening and sorting to obtain a plurality of personalized learning path options; and integrating the behavior data newly generated by the learner through a feedback module, and outputting a final dynamic learning path. According to the method, the problems of insufficient dynamic adaptability and difficulty in effectively utilizing the behavior data of the learner in the existing learning path planning are solved, and dynamic and personalized learning path planning based on the behavior difference of the learner is realized.

The invention relates to the field of robot technology and artificial intelligence, and discloses a robot fine operation method and system based on a visual language model and semantic key point characterization, a closed-loop multi-body Agent system is constructed, GPT-4o and Ground DINO are combined to accurately understand and disambiguate a natural language instruction of a user, an innovative bridging layer is introduced, and the robot fine operation method and system based on visual language model and semantic key point characterization are obtained. Abstract decision information is converted into bottom execution parameters represented by three-dimensional semantic key points, the problem of decision transfer distortion is solved, meanwhile, a KMP algorithm is improved, and the stiffness and contact force of trajectory tracking are dynamically optimized by introducing a learning-based time-varying hybrid impedance / force control strategy, so that the accuracy of trajectory tracking is improved. According to the method, the generalization success rate of fine operation tasks of the robot and the stability of physical interaction are remarkably improved, seamless connection from high-level semantic understanding to low-level action generation is achieved, and an efficient and reliable technical scheme is provided for autonomous operation of the robot in a complex scene.

The invention discloses a learning accompanying system based on an AI intelligent agent, and relates to the technical field of education, the learning accompanying system comprises a knowledge point learning grid module and a learning path generation module, and the knowledge point learning grid module is connected with the learning path generation module; the knowledge point learning grid module is used for generating attribute information of knowledge points based on the basic learning information, the pre-constructed knowledge information and the correlation information, and constructing a knowledge graph corresponding to the knowledge point set based on the attribute information; mapping the knowledge graph in a knowledge point learning grid corresponding to the course data information to obtain a target knowledge point learning grid; the learning path generation module is used for generating a learning plan of the student in a target time period based on the knowledge point learning grid in the knowledge point learning grid module, and generating a learning path of the student based on the learning plan; and the knowledge point learning grid module is used for displaying the learning path generated by the learning path generation module to a student end through a knowledge point learning grid. The learning efficiency of students can be improved.

Aspects of the present disclosure provide techniques for machine learning based disambiguation. Embodiments include receiving a query via a user interface; generating an enriched query by rewording the query based on conversation history data associated with the query. Embodiments include retrieving relevant information from a data store based on using an embedding of the enriched query to perform a semantic search. Embodiments include providing the enriched query and the relevant information to a language processing machine learning model along with a prompt that instructs the language processing machine learning model to generate an answer to the enriched query based on the relevant information and to generate a disambiguation question if one or more conditions are met. Embodiments include receiving an output from the language processing machine learning model in response to the prompt. Embodiments include providing a response to the query via the user interface based on the output.

The invention discloses a self-adaptive optimization method and system for online decoding of a motor imagery brain-computer interface, and the method comprises the steps: carrying out the real-time self-adaption of an electroencephalogram data stream of a target user through a teacher-student model framework on the premise that the privacy protection of source domain training data does not need to be accessed; performing batch weight normalization during testing, decoupling normalization statistic updating and parameter optimization by stopping gradient operation, and stabilizing feature representation; a dynamic category specific entropy threshold mechanism is combined with online category frequency and batch confidence to adaptively screen a high-confidence sample for each category; a dynamic online reweighting strategy is designed, and weights are distributed according to the sample entropy and the category frequency to balance the optimization process; and decoupling contrast learning based on a fixed prototype is introduced, and feature space distribution is optimized. According to the method, the problems of statistic drift, poor fixed threshold adaptability, category imbalance sensitivity, insufficient feature optimization and the like are solved, and the adaptability, the stability and the robustness of cross-user motor imagery brain-computer interface online decoding are improved.

The invention relates to the technical field of computer technology and coal mine intelligent mining, in particular to a machine learning-based open-pit mine blind cannon automatic identification method and device. The method comprises the steps that video data transmitted by an unmanned aerial vehicle are obtained, the unmanned aerial vehicle is provided with a camera device, and the video data are obtained by the unmanned aerial vehicle through data collection for the blasting process of a target blasting area of the strip mine; acquiring a key frame set corresponding to the video data; explosive loading parameters corresponding to the blasting process of the target blasting area are obtained; acquiring image features of the key frame set and parameter features of the charging parameters; and identifying the image features and the parameter features by adopting an automatic open-pit mine blind shot identification model established based on a target machine learning algorithm, and obtaining an identification result of an unblasted blast hole corresponding to the target blasting area. According to the invention, the duration of the blind shot detection can be reduced, the accuracy of the blind shot detection can be improved, and the working efficiency of the blind shot detection can be improved.

The invention discloses a network school student personalized learning path recommendation system, and relates to the technical field of education, and the recommendation system comprises a data collection module which obtains the micro-expression and limb details of a student during learning based on a camera, collects the learning behavior data of the student, and judges the knowledge ability data of the student through image analysis and limb analysis; the student portrait construction module obtains the knowledge weakness direction of the current student based on the knowledge ability data of the student, and constructs a multi-dimensional student portrait; and the knowledge graph construction module is used for constructing an association graph of the subject knowledge system, and the association graph comprises a preposed dependency relationship and a difficulty level between knowledge points. According to the invention, learning is reinforced and learning rhythm is adjusted in real time through a recommendation algorithm layer, proper challenges are introduced into an anti-fragility mechanism to enhance knowledge mastering toughness, path output is coupled with real-time states of students, course design and teaching can be fed back, learning efficiency and achievement sense of students are improved, and technical barriers of network schools are enhanced.

The invention provides a DDR wafer test anomaly detection method and device based on machine learning, and the method comprises the steps: obtaining a time sequence eye pattern synchronously collected in a DDR wafer test process and time sequence waveform data related to total jitter, deterministic jitter and random jitter, and carrying out the clock edge phase segmentation alignment of differential time sequence sampling points in the time sequence waveform data, phase domain dense sampling data is constructed, adaptive sparse coding is completed in combination with DDR jitter physical priori, noise and normal process fluctuation related components are removed, defect sensitive sparse components are obtained, variational mode decomposition is performed, components related to process drift, normal process fluctuation and abrupt change abnormity are obtained, and the defect sensitive sparse components are subjected to sparse coding; and the abrupt change anomaly correlation component is extracted as target detection data, a preset machine learning model is input, an anomaly mode correlation result is generated, a DDR wafer test anomaly detection result is output based on the result, and a corresponding test setting item adjustment instruction is generated. According to the invention, the overall efficiency and the result reliability of the DDR wafer test can be improved.

The invention discloses a machine learning-based grain boundary twinning behavior prediction method, which comprises the following steps of: firstly, analyzing microscopic structure data of a deformed sample, extracting parameters related to grain boundaries to calculate 15 characteristic parameters related to grain boundary twinning behaviors, and marking real twinning behavior types of the grain boundaries so as to construct an original characteristic data set; then, after equalization and standardization processing is carried out on the data set, the data set is divided into a training set and a test set, the training set is used for optimizing hyper-parameters of the machine learning model and training the optimized machine learning model to obtain a prediction model, and the test set is used for verifying the accuracy of an evaluation model; and finally, substituting 15 characteristic parameters of an undeformed to-be-tested sample into the prediction model so as to predict the types of twinning behaviors possibly occurring at each grain boundary after the to-be-tested sample undergoes plastic deformation. The model constructed by the method can comprehensively capture the nonlinear relationship and interaction among multiple influence factors, the prediction accuracy of the twinning behavior at the grain boundary is high, and the generalization ability is high.

The invention discloses an electric power spot market energy storage charging and discharging decision-making system based on machine learning, and the system comprises a data collection module which is used for obtaining multi-source data of an electric power spot market, the multi-source data at least comprises power transaction data, weather related data, energy price data, supply and demand data, renewable energy output data, energy storage system parameters, energy structure characteristics and carbon emission related data; and the electricity price prediction module analyzes the multi-source data acquired by the data acquisition module on the basis of a deep learning algorithm in combination with an attention mechanism so as to realize electricity price prediction of three time scales, i.e., day-ahead, day-in-day and real-time, of the electric power spot market. The multi-time-scale electricity price prediction accuracy of the electric power spot market is not lower than 88%, the load prediction accuracy is not lower than 92%, and market price fluctuation and load change rules are accurately captured.

The invention relates to the technical field of artificial intelligence and social media public opinion monitoring, in particular to an image recognition method and system based on machine learning, and the method comprises the steps: carrying out the OCR text extraction and regional visual feature extraction of an input image, generating a text emotion embedding vector in combination with a preset brand emotion dictionary, and carrying out the recognition of the emotion embedding vector; and visual and text features are fused through a cross-modal adversarial encoder to obtain joint semantic embedding representation, and whether hidden negative public opinions are formed or not is judged through a brand deviation degree discriminator. According to the method, semantic antagonism image contents including derogatory characters, competitive product comparison or sensitive symbols and the like can be effectively identified, the detection rate of recessive negative public opinions is improved, and the method is suitable for real-time monitoring of a large-scale social platform.

The invention discloses a data quality evaluation and restoration method and system based on machine learning. The method comprises the following steps: firstly, preprocessing data, and constructing a structured generator network containing a parameterized adjacent matrix; in the training stage, the network outputs preliminary reconstruction data, and manifold constraint projection is utilized to find a logic correction target matrix meeting domain constraints; and constructing a potential consistency loop through gradient blocking, and calculating a consistency loss to drive the network to approach a compliance manifold. Meanwhile, an overall target integrating reconstruction errors, logic consistency and acyclic constraints is constructed, and an augmented Lagrangian method and a double-layer circulation strategy are adopted to jointly optimize parameters. And after the double convergence judgment is met, final inference is executed based on mask synthesis. According to the method, the logic rule is internalized into the generation capability, and the sparse causal structure is mined synchronously, so that high-quality data recovery with logic compliance, distribution consistency and interpretability is realized.

The application provides a meta-learning-based responsive recommendation method, system and device, and the method comprises the following steps: constructing a meta-learning-based responsive recommendation model, wherein the meta-learning-based responsive recommendation model comprises a meta-learner and an ID embedding representation generator of a heterogeneous information network; training the meta-learning-based responsive recommendation model based on obtained data to obtain a trained meta-learning-based responsive recommendation model and model optimization parameters; obtaining user-goods historical scoring data of a user to be recommended, and obtaining target recommended goods based on the scoring data, the trained recommendation model and the model optimization parameters and recommending the target recommended goods to the user. The meta-learning-based responsive recommendation method is adopted, the meta-learning and the ID embedding representation generator are introduced, and therefore the responsiveness problem of the interest change of an old user and the initial response problem of a new user and a new good are solved from the root, and the problems of low recommendation accuracy and low user satisfaction are caused.

The invention discloses an automatic garbage classification method and system based on machine learning, and relates to the technical field of environmental protection, and the method comprises the steps: carrying out the multi-physical field dynamic excitation and response data collection of garbage articles, obtaining multi-modal feature data, and carrying out the environment disturbance correction of the multi-modal feature data; inputting the corrected multi-modal feature data into a feature decoupling network constrained by a physical mechanism, and decoupling and outputting essential attribute feature vectors and representation attribute feature vectors; inputting the essential attribute feature vector into a classification decision unit, and outputting a classification result, a confidence score and an uncertain sample mark based on a multi-level classification decision of essential attributes; and for the samples indicated by the uncertain sample marks, starting a physical verification-oriented active knowledge acquisition mechanism, acquiring classification labels and updating a feature database. According to the invention, the accuracy and adaptive evolution capability of garbage classification in a complex real scene are improved.