1029results about How to "Improve learning effect" patented technology

The invention provides a digital factory operation virtual simulation teaching method and system, and relates to the technical field of smart factories, and the method comprises the steps: collecting factory operation data, carrying out the standardization processing and correlation analysis, constructing a multi-dimensional data model, carrying out the feature extraction and semantic mining of the hierarchical data of each dimension, and constructing a multi-level digital twin factory model. Carrying out dynamic modeling, constructing a personalized knowledge graph, generating a learning demand list, matching the learning demand list with a digital twin factory model, and generating a multi-dimensional simulation environment; in the multi-dimensional simulation environment, performing analysis and intention recognition on an operation instruction of the learner, converting the operation instruction into a virtual operation, calculating a normative score of the virtual operation, generating corresponding feedback information based on the normative score and the personalized knowledge graph, updating model parameters based on a response of the learner to the feedback information, and performing simulation on the learner according to the updated model parameters. And completing iteration of the model.

The invention discloses a course recommendation method based on a learning track and a knowledge graph, and particularly relates to the technical field of education course recommendation, and the method comprises the following steps: collecting and integrating learning track data of students, mapping the learning track data to the knowledge graph to generate a learning track-knowledge joint graph, and carrying out knowledge point mastering and learning rate analysis; obtaining a knowledge mastering value and a learning rate of each knowledge point; based on the knowledge mastering value, the system divides the knowledge points into strong items and weak items; for weak knowledge points, weak recommendation degrees are calculated in combination with knowledge mastering values and learning rates, and courses are preferentially recommended according to the recommendation degrees; for the strong knowledge points, the strong recommendation degree is calculated based on the learning rate, advanced courses are recommended, and the learning effect and personalized learning experience of students are improved; according to the method, strong and weak knowledge points of students can be accurately identified, so that learning recommendation with extremely high pertinence is provided, the students can more efficiently learn on a personalized learning path, and the learning result is improved.

The invention discloses a method for realizing high-efficiency low-consumption micro-aerobic hydrolytic acidification of petrochemical wastewater by regulating and controlling the aeration rate in combination with a space-time diagram neural network and reinforced learning, and relates to a method for realizing high-efficiency low-consumption micro-aerobic hydrolytic acidification of petrochemical wastewater by regulating and controlling the aeration rate. The method comprises the following steps of: 1, collecting and cleaning data; 2, constructing a graph data set; 3, training the ST-GNN model; 4, constructing a deep Q reinforcement learning model; 5, the trained ST-GNN model is embedded into an automatic control system of a sewage treatment plant, and the model outputs the optimal aeration rate of the current time step and predicts the micro-aerobic hydrolytic acidification effect through interaction of the current working condition and historical data; and adjusting operation parameters of aeration equipment according to the output of the model, and carrying out hydrolytic acidification treatment. The method is high in regulation and control efficiency and low in operation error, and can be applied to the field of digital and intelligent management of sewage treatment plants.

The invention discloses a semi-supervised medical image segmentation method based on eye movement guide mixed data enhancement. The method comprises the following steps: collecting fixation position information of a doctor when reading a medical image through eye movement tracking equipment; using a teacher-student network model and adopting a two-stage training mode to train the model; the method comprises the following steps: taking GazeMix as a data enhancement strategy in training, extracting a fixation area in a labeled or unlabeled image, and pasting the fixation area to the background of other unlabeled images to generate a mixed image data pair; in the first stage, a GazeMix data enhancement strategy is combined to pre-train a teacher network; in the second stage, a student network is trained, GazeMix generates diversified data, and meanwhile, a teacher network is pre-trained for pseudo tag generation; multi-scale gaze perception is adopted, and model perception information is extracted on different scales and used for perception loss calculation; and the optimizer iteratively optimizes the student network parameters, and updates the teacher network by using an index moving average method.

The invention discloses a medical image segmentation method fusing multi-modal graphic and text information, and the method comprises the steps: carrying out the preprocessing and coding of a metadata text of a patient through a pre-trained BERT model, extracting the feature representation, and carrying out the attention-guided data enhancement operation of a pathological image. And finally, constructing a medical image segmentation network composed of an image encoder, a text encoder and a decoder, carrying out pathological image segmentation based on the feature representation extracted in the step 1 and the pathological image after data enhancement, and visualizing a segmentation result. In the segmentation network, a multi-modal feature fusion module is designed to fuse information of two modals, the module adopts a Transform architecture, a cross-modal attention mechanism and a self-attention mechanism are introduced, and the effectiveness of information fusion is ensured. According to the method, a more accurate segmentation result is obtained, the generalization ability on new data is improved, and the common problem of data imbalance in the medical image is effectively solved.

The invention discloses a self-adaptive education method based on artificial intelligence, and relates to the technical field of education, and the method comprises the following components: intelligent emotion monitoring, learning performance evaluation, self-adaptive teaching strategy adjustment, personalized learning path planning and a feedback and optimization mechanism. According to the method, by introducing a learning performance evaluation and prediction module and a prediction and adaptive teaching strategy adjustment module, individual differences, including learning styles, interest preferences and ability levels, of students are fully considered, so that teaching strategies are intelligently recommended and adjusted, and personalized learning paths are dynamically generated; the personalized teaching mode effectively overcomes the defects of a traditional'one-cut 'teaching mode, the teaching effect is remarkably improved, each student can obtain the most suitable learning experience, and the learning enthusiasm and the learning effect of the students are greatly improved.

The invention discloses an old people chronic disease risk prediction method and system based on a time sequence knowledge graph, and belongs to the technical field of medical health information, and the method comprises the following steps: S1, obtaining a health data set of an old people group; s2, on the basis of an ESOA-XGBoost algorithm, performing feature selection and sorting on each piece of health data in the health data set so as to determine correlation among variables, and generating a health data feature set; s3, constructing and training a time sequence knowledge graph prediction model including an STKGR-PR model and a T i PNN model, and predicting a relationship among the target entity, other entities and time sequence information through the time sequence knowledge graph prediction model; s4, predicting the old chronic disease risk of the old people group according to the trained time sequence knowledge graph prediction model; through the method, an elderly chronic disease risk prediction result with a good prediction effect and high accuracy can be obtained.

The invention provides an AI intelligent interactive course adjustment method and system based on a large language model, and the method comprises the steps: obtaining original typing input rhythm data, including a keyboard event timestamp sequence, an event type and input contents, of a student in concept interpretation processes with different difficulties; pause time distribution, input speed change and error rate indexes are calculated according to the event timestamp sequence; according to the current concept understanding level of the student, dynamically adjusting the course difficulty gradient and the progress arrangement, if the understanding level of the student is high, increasing the course difficulty and the learning progress, and if the understanding level of the student is low, reducing the course difficulty and enhancing targeted practice and feedback; the typewriting input rhythm characteristics of the students are combined with other learning behavior data, a comprehensive learning effect evaluation model is constructed through multi-modal data fusion, the comprehensive learning effect evaluation model is used for evaluating mastering conditions of the students on different knowledge points, and weak links and dominant fields of the students are identified.

The invention relates to the technical field of welding material performance testing, and discloses an acoustic-optical-electric synergistic welding material fatigue performance testing method and system, and the method comprises the steps: synchronously collecting a first multi-mode signal data set of a welding material in a fatigue testing process; carrying out fusion processing to obtain a fusion feature vector; performing time sequence feature extraction to obtain time sequence comprehensive representation; constructing and training an initial fatigue performance multi-task learning model comprising a shared feature extractor and a task-specific sub-network based on time sequence comprehensive representation; implementing domain adaptation and transfer learning on the fatigue performance multi-task learning model to obtain a target fatigue performance multi-task learning model; acquiring a second multi-mode signal data set in real time and inputting the second multi-mode signal data set into the target fatigue performance multi-task learning model to obtain a welding material fatigue performance test result, so that acoustic, optical and electric multi-mode signals can be effectively integrated, and high-precision, multi-task and migratable welding material performance test is realized.

The invention relates to the technical field of battery capacity prediction, and discloses a golf cart battery capacity prediction method, device and equipment and a storage medium, and the method comprises the steps: carrying out the collection and preprocessing of historical charging and discharging data of a golf cart battery, and obtaining a time sequence feature data set; generating an incremental capacity curve, inputting the incremental capacity curve into a bidirectional long-short-term memory network, and training to obtain an initial capacity prediction model; taking the initial capacity prediction model as a first-layer model, and taking the metabolism grey model as a second-layer model for stacking and integrating to obtain a mixed prediction model; dynamically adjusting model parameters through a double-layer optimization algorithm to obtain a target capacity prediction model; and inputting real-time battery operation data into the target capacity prediction model to carry out capacity prediction and health state evaluation, and outputting a capacity attenuation trend chart and a residual service life estimation value, so that the precision of predicting the battery capacity of the golf cart is improved.

The invention relates to a cross-modal hash retrieval method based on graph convolutional network fusion, and belongs to the technical field of multimedia retrieval. According to the method, a modal fusion module based on a graph convolutional neural network is constructed, modal sharing expressions are learned, the sharing expressions combine pairwise losses and intra-modal and inter-modal identification losses to reduce inter-modal heterogeneity, the similarity relation between modals is fully learned, and feature alignment between different modal data is enhanced; according to the method, an effective learning target, namely a loss function, is constructed by adopting pairwise loss, triple loss and quantization loss functions, the high-order semantic similarity of the method among different modes is captured, the learning of the method is guided, and the learning ability of the method for the relationship between data is further enhanced.

The invention relates to a polyp image segmentation method based on pyramid vision Transform, and belongs to the technical field of digital medical treatment. The method comprises the following steps: capturing global context information through a pyramid vision Transform module, and obtaining feature maps with different resolutions from a plurality of extraction stages; detail information is extracted from the shallow feature map of the first stage through a cyclic cross attention module, and shallow features are obtained; a multi-scale feature fusion sensing module is used for carrying out fusion processing on the feature maps extracted in multiple stages, deep features are extracted, and the deep features and shallow features are fused and then used for image segmentation; and designing weighted binary cross entropy loss and weighted IoU loss to train the above process, and segmenting the polyp image after training is completed. According to the invention, through the pyramid vision Transform module, the cyclic cross attention module and the multi-scale feature fusion perception module, the global information learning ability, the detail information capturing ability and the segmentation performance are significantly improved.

The invention belongs to the technical field of mechanical arm grabbing, and discloses a visual sense-force sense-based mechanical arm instruction grabbing method, which comprises the following steps of: acquiring an RGB-D image of a scene, performing cutting processing on the RGB-D image through OpenCV, and extracting visual features of each object in the RGB-D image; a text command input by a user is coded through BERT, and language features are output; inputting the language features and the visual features into a CLIP model for fusion and alignment, and performing further alignment by adopting a Co-TRM structure to generate bimodal features; generating a point cloud image according to the depth map of the RGB-D image, and based on the point cloud image, combining visual features of an object, and generating a grabbing attitude through Graspnet; the problem that in the prior art, when grabbing is conducted based on vision and instructions, self-adaptive adjustment on grabbing force is not convenient is solved.

The invention discloses a lightweight space-time traffic flow prediction method based on GAT and Mama, and relates to the technical field of intelligent traffic systems. According to the method, the feature expression ability of the model is improved through multi-dimensional feature learning (time, date and space-time) of an embedded layer, rich features of input data can be deeply captured, and the learning ability of the model is enhanced; a graph attention module is used to adaptively pay attention to the relative importance between nodes, so that the graph structure relationship in the data can be more effectively captured and utilized, and the analysis accuracy of the model on the spatial data is improved; the GAT-Mama module optimizes the time sequence analysis and spatial data processing capability, and the model can more accurately capture the dynamic dependency relationship between time points and between spatial positions through a multi-layer graph attention mechanism and residual connection; the GAT-Mama layer structure supports flexible adjustment, a user can adjust the depth of the model according to specific task requirements so as to adapt to spatio-temporal data prediction tasks with different complexities, and good adaptability is achieved.

The invention discloses a course learning planning system based on a computer, and relates to the technical field of course learning planning, and the course learning planning system comprises a learning data acquisition module, a knowledge graph construction module, a learning index scoring module, a multi-index comprehensive evaluation module, a learning plan making module and a real-time progress feedback module. Wherein the modules are connected through electric signals; the learning data acquisition module is used for collecting learning data of students and determining evaluation indexes of the learning data. According to the course learning planning system based on the computer, by monitoring the learning progress and achievement of students, instant learning feedback is provided for the students, so that the students can quickly know the learning state of themselves, related learning resources and exercises are intelligently recommended according to the learning conditions of the students, the students are helped to consolidate knowledge and make up for deficiencies, and the learning efficiency is improved. Students can achieve a higher learning effect in a shorter time, and the learning efficiency is improved.

The invention relates to the technical field of intelligent education, and discloses an integrated English teaching method and system based on artificial intelligence. The method comprises the following steps: constructing a digital resource library; generating pre-class preview data based on the resource library and the initial cognitive level of the student, analyzing the pre-class preview data and updating the cognitive level; generating classroom courseware based on the resource library and the student updating cognitive level, and analyzing classroom learning data to update the cognitive level again; generating personalized after-class homework based on the resource library and the re-updated cognitive level of the student, and analyzing homework data to finally update the cognitive level; and forming a heavy and difficult comment report based on the resource library and the final cognitive level of the student. Through continuous data collection and analysis, dynamic adjustment of teaching content is realized, pre-class preview, classroom teaching and after-class review are closely combined to form a complete teaching closed loop, teaching pertinence and effectiveness are improved, personalized learning and precise teaching are realized, and the overall effect of English teaching is greatly improved.

The invention relates to a tidal reach tide level forecasting method and system based on a combined model. The method comprises the following steps: mining the average propagation time of upstream and downstream tide levels through a derivative dynamic time warping method; feature decomposition is conducted on the tide level multi-influence-factor data through set and empirical mode decomposition, and high-frequency component information and low-frequency component information are extracted; a combined model is constructed by combining a deep residual shrinkage network, a bidirectional long-short term memory network and an attention mechanism, and spatial-temporal features are mined. The tide level propagation time between upstream and downstream tide level stations is mined by using a derivative dynamic time warping method, and a more accurate time reference is provided for tide level forecasting; a set and empirical mode decomposition method is adopted to perform characteristic decomposition on tide level data, spatial characteristics and time characteristics are extracted through a combined model, and an attention mechanism is utilized to perform fusion, so that the mining and learning ability of the model on multi-scale nonlinear characteristics and non-stationary characteristics is improved, and the tide level forecasting precision is further improved. And the forecasting error in the storm surge period is reduced.

The invention relates to an AI online education intelligent question and answer information processing method, which comprises the following steps of S1, collecting teaching materials, and performing preprocessing and labeling to form a text data set with labels; s2, constructing a question and answer model based on XLNet; s3, introducing a specific context optimization question and answer model for a specific subject or topic to obtain an optimized question and answer model; s4, constructing an auxiliary understanding information knowledge graph by considering hierarchical design of age groups based on the labeled text data set; s5, inputting a query by the user, and obtaining an optimally matched answer based on the optimized question and answer model; according to the age group of the user and the best matching answer, auxiliary understanding information is obtained from the knowledge graph, and a complete answer is obtained; and S6, adjusting provided content and difficulty through user interaction data, and recommending related domain knowledge based on user behaviors and preferences. According to the method, the direct answers required by the user are provided, the supplementary background information is provided to enhance the understanding, and the requirements of the user are presented in a personalized manner according to the characteristics of the user.

The invention discloses a traditional Chinese medicine recommendation method based on knowledge driving and a residual attention network, and the method comprises the following steps: S1, a data collection and cleaning module: obtaining prescription text data, executing a standardized process for symptoms and traditional Chinese medicine terms in the prescription text data, and dividing a data set after the standardized process is executed into a training set, a verification set and a test set; s2, an entity pre-training module: extracting symptom semantic features by using a Word2vec training model to extract the features of symptom entities in the prescription and obtain overall context semantic representation, constructing a traditional Chinese medicine attribute knowledge graph, and fusing the natural attribute features of the traditional Chinese medicine as external knowledge into a recommendation model; s3, a multi-graph construction and entity feature learning module: according to a co-occurrence relationship between the symptoms and the traditional Chinese medicines, constructing a symptom-traditional Chinese medicine isomerism graph (SHHG), a symptom-symptom isomerism graph (SSIG) and a traditional Chinese medicine-traditional Chinese medicine isomerism graph (HHIG); respectively extracting symptom features, traditional Chinese medicine features and interaction features from a symptom-traditional Chinese medicine isomeric graph (SHHG), a symptom-symptom isocomposition (SSIG) and a traditional Chinese medicine-traditional Chinese medicine isocomposition (HHIG) by using a graph attention neural network, and enhancing entity features by using a residual structure; the feature fusion and traditional Chinese medicine recommendation module is used for fusing symptom features and traditional Chinese medicine features extracted from a symptom-traditional Chinese medicine isomerism graph (SHHG), a symptom-symptom isomerism graph (SSIG) and a traditional Chinese medicine-traditional Chinese medicine isomerism graph (HHIG) to obtain final symptom features and traditional Chinese medicine features, and expressing the symptom features by using MLP to obtain a traditional Chinese medicine recommendation result. And finally recommending a proper traditional Chinese medicine set according to the given symptom set.

The invention provides a high-efficiency intelligent teaching resource scheduling algorithm and an implementation method thereof, and the method comprises the steps: constructing a judgment matrix according to a learner capability difference evaluation result, cooperation efficiency analysis data, knowledge graph coverage rate statistics and learning style matching degree score, carrying out the calculation to obtain a group heterogeneity index, solving the weight of each index through a feature value method, and carrying out the calculation of the group heterogeneity index. Carrying out weighted summation to obtain a group complementarity comprehensive index; acquiring a historical learning data sequence of a learner, extracting time sequence features, combining a current individual progress deviation monitoring result, individual resource demand evaluation and individual learning content suitability analysis, constructing an individual development trajectory prediction model, and predicting a future individual learning performance curve; and aiming at the group complementarity comprehensive index and a future individual learning performance prediction result, constructing a multi-objective optimization model of resource allocation, setting a group complementarity objective function and an individual satisfaction objective function, and solving to obtain a resource allocation scheme for balancing group and individual benefits.

The invention discloses an industrial product appearance defect semantic segmentation method and system, and relates to the technical field of product defect detection, and the method comprises the steps: making a data set of an appearance image of a to-be-detected industrial product; performing data preprocessing on the data set to obtain a preprocessed data set, and dividing the preprocessed data set into a training set and a test set; constructing a semantic segmentation model, and performing multiple iterative training on the semantic segmentation model through the training set by using a training mode based on edge supervision and adopting a combined weighted network loss function until the network loss function reaches convergence to obtain a trained semantic segmentation model; inputting the test set into a trained semantic segmentation model for testing to obtain a final semantic segmentation model; and inputting a to-be-detected image into the final semantic segmentation model, and outputting an industrial product appearance defect semantic segmentation result. According to the invention, the precision and accuracy of image segmentation are effectively improved.

The invention relates to the technical field of intelligent teaching, in particular to an intelligent teaching system for traditional Chinese medicine clinical skill cultivation. The system comprises a virtual reality simulation module, an operation interaction module, an operation data analysis module, an adaptive learning feedback module and a teaching evaluation module. The virtual reality simulation module constructs a vivid traditional Chinese medicine skill training scene through three-dimensional modeling, ray tracing and physical simulation technologies, and the vivid traditional Chinese medicine skill training scene covers pulse feeling, acupuncture and moxibustion, massage and other operations. The operation interaction module collects user operation data and extracts features in combination with a variational auto-encoder. The operation data analysis module analyzes user operation deviation by using a graph neural network and a generative adversarial network, the adaptive learning feedback module generates a personalized learning strategy, and the teaching evaluation module evaluates a learning effect through fuzzy evaluation and analytic hierarchy process. According to the invention, intelligence, individuation and high efficiency of traditional Chinese medicine clinical skill cultivation are realized, the fidelity of teaching and the accuracy of feedback are improved, and the skill level and the training effect of learners are also improved.

The invention discloses a remote sensing image ground object segmentation method based on hierarchical feature extraction and decoding, which relates to the technical field of remote sensing image processing, and comprises the following steps: step 1, collecting and preprocessing a remote sensing image, and constructing a training sample set; 2, constructing an image segmentation network, wherein the image segmentation network comprises a hierarchical encoder, a receptive field module unit and a network decoder which are connected in sequence; 3, training and optimizing the image segmentation network by adopting the training sample set to obtain a remote sensing image ground object segmentation model; and 4, collecting a remote sensing image to be segmented, and inputting the remote sensing image to the remote sensing image ground object segmentation model to obtain a ground object segmentation result. According to the method, the advantages of the advanced visual basic model and the U-shaped network architecture are combined, so that rapid and accurate segmentation of the ground target is realized.

The invention discloses a multi-language translation method and system, and relates to the field of electrical digital data process.The method comprises the steps that cultural feature information and semantic structure information are obtained; splitting the source language text into a plurality of semantic units based on the semantic structure information; retrieving cultural connotation information of which the association degree with the semantic unit is greater than a preset threshold value; determining that the semantic unit is a culture sensitive semantic unit; extracting a target language expression mode based on the cultural connotation information; performing semantic combination on the target language expression mode and standard translation results of other semantic units except the culture sensitive semantic unit in the source language text to obtain a translation result; judging whether the semantic coherence of the translation result meets a preset condition or not; if the preset condition is met, outputting a translation result; and if the preset condition is not met, re-executing the step of semantic combination. The accuracy of the cultural connotation and the emotional color contained in the transmission source language is improved, and then the cultural adaptability of the translation result is improved.

The invention provides a multi-course fusion knowledge graph construction and real question analysis method and system. The method comprises the following steps: carrying out knowledge point alignment operation, carrying out integration operation on cross-course knowledge points, carrying out quantitative analysis on the knowledge points by utilizing a cosine similarity calculation method, and identifying and aligning synonymous knowledge points in different courses; performing knowledge point disambiguation operation, and processing the situation that the knowledge points have the same name and different meanings to obtain integrated knowledge points and an integrated knowledge graph; performing knowledge point standardization operation on the integrated knowledge points, and performing standardization processing on the integrated knowledge graph to obtain standardized knowledge points and a standardized knowledge graph; converting the normalized knowledge points, extracting to obtain key features, and processing according to the key features to obtain semantic feature sequence vectors; matching to obtain a matching result and applicable knowledge points; and verifying and evaluating the matching result, and mounting the question to the corresponding knowledge point. The technical problems that the knowledge point extraction result is one-sided and the result accuracy is not high are solved.

The invention discloses a federal forgetting learning method based on small sample knowledge distillation. The method comprises the following steps: initializing a global model by adopting a server and broadcasting the global model to each client; each client carries out local training on the received global model by using local data, and after the local training is completed, the global model is updated and sent back to the server; the server stores and aggregates the global models sent by all the clients, is used for updating the local global model of the server, and repeats the federal learning process from S1 to S3; a target client makes a forgetting request at a certain moment, federal learning is stopped, and at the moment, a server side uses a forgetting module to generate a forgetting model and takes the forgetting model as a student model; the server side finely adjusts and compares the language image pre-training model according to local small sample data, so that the language image pre-training model adapts to downstream data and serves as a teacher model; the server uses local small sample data to carry out recovery training through a knowledge distillation method, so that catastrophic forgetting caused by client data revocation is avoided, and the performance of a forgetting model is improved.

The invention discloses a management teaching information processing method and system based on digital twinning, which can construct a personalized knowledge graph according to a digital twinning learning model, and accurately identify knowledge blind spots and weak links existing in the learning process of students by analyzing a pre-repair relationship and learning dependence between knowledge points. By utilizing the information, the presentation sequence of the learning path and the content can be further optimized, so that the students can be ensured to master each knowledge point according to the most suitable learning sequence. And meanwhile, performing learning influence weight analysis on each personalized learning content, calculating the actual influence of the personalized learning content on the learning effect of the student, and preferentially arranging the most critical content for improving the learning effect of the student for learning according to the analysis results. Through the optimization and adjustment, the learning efficiency of the students can be improved, the overall learning effect can be effectively improved, and the students are helped to solve learning difficulties in a more targeted manner.

The invention relates to the technical field of education informatization, and discloses a digital teaching resource library intelligent management and application method and system. The method comprises the steps of constructing a digital resource library, constructing a resource application big data analysis model to calculate a resource quality index, a popularity index and an update index, performing intelligent resource sorting and elimination based on the indexes, analyzing the correlation between a user retrieval request and resources, and performing intelligent recommendation. According to the method, efficient management and accurate application of teaching resources are realized, the resource utilization rate and the teaching effect are improved, the storage space and the management cost are saved, and data support is provided for education decision making.

The invention discloses a small sample learning method and system based on data enhancement. Collecting electric power operation and maintenance text data from a plurality of data sources, preprocessing and labeling the data, and constructing an electric power field corpus; performing fine tuning on a predefined pre-training language model by using the power field corpus, training power field word vectors and entity vectors from the power field corpus, and fusing the power field word vectors and entity vectors into the pre-training language model; performing named entity recognition and multi-task learning of power operation and maintenance knowledge based on a pre-training language model, constructing a multi-task adversarial learning model in combination with an adversarial learning algorithm, training the multi-task adversarial learning model by adopting multiple data enhancement strategies, and performing data prediction through integrated learning and self-training by utilizing the multi-task adversarial learning model; and evaluating a model prediction result, and dynamically adjusting the weight of each data enhancement strategy based on an evaluation result. The small sample learning performance is improved.

The invention discloses a speech enhancement method and system based on a time-frequency graph convolutional network in the technical field of speech signal processing, and the method comprises the steps: obtaining to-be-enhanced noisy speech data, inputting the to-be-enhanced noisy speech data into an improved metric generative adversarial network (CMGAN), and outputting an enhanced speech time domain signal; the improvement method of the metric generative adversarial network CMGAN comprises the following steps: replacing an encoder module of the metric generative adversarial network CMGAN with a time-frequency graph convolution encoder module; in the time-frequency graph convolution encoder module, a time convolution network and a graph convolution network are used for respectively extracting a long-time dependency relationship and global frequency characteristic information of noise-containing voice data to be enhanced, and dense residual error connection is introduced to fuse multi-scale characteristic information at the same time. The speech enhancement performance is improved under the condition of less model parameter quantity and calculation quantity.