259results about How to "Avoid redundancy" patented technology

The invention provides a lightweight underwater image enhancement method based on adaptive feature fusion, and the method comprises the steps: decomposing an underwater image enhancement task into a strong prior enhancement task and a fine-grained enhancement task through employing a lightweight underwater image enhancement network based on adaptive feature fusion, so as to make full use of the multi-scale information in an image; the strong prior enhancement task is used for extracting global and low-layer features of the image; the fine-grained enhancement task is used for improving local details and color recovery of the image so as to improve the visual quality; the lightweight underwater image enhancement network comprises a multi-scale feature aggregation module and a global channel attention module, the multi-scale feature aggregation module is composed of an adaptive feature fusion module and a segmented convolution feed-forward network, and the lightweight underwater image enhancement network is used for combining global and local information of features and adaptively adjusting importance of each channel through information association between channels.

The invention discloses a holographic display digital human speech recognition enhancement method based on multi-modal interactive learning, and the method comprises the following steps: S1, collecting and preprocessing data, and generating a multi-modal feature matrix; s2, inputting the multi-modal feature matrix into a self-adaptive multi-modal interaction kernel to generate multi-modal interaction features; s3, inputting the multi-modal interaction features into an emotion convolution block to generate semantic-emotion mapping features; s4, inputting the semantic-emotion mapping features into a cross attention generator, and outputting multi-modal fusion features; s5, inputting the multi-modal fusion features into a multi-modal fusion-decomposition two-way network, and generating multi-modal features after decoupling optimization; s6, inputting the multi-modal features into a holographic-speech symbiosis optimization module to generate speech recognition and holographic display data; and S7, performing parameter optimization by applying self-supervised learning and comparative learning strategies to realize self-adaptive adjustment. According to the invention, the enhancement of holographic display digital human speech recognition is realized by using a multi-mode interactive learning method.

The invention particularly relates to a document abstracting method based on domain knowledge and a multi-granularity graph network, which comprises the following steps: S1, constructing a knowledge coding module, carrying out domain knowledge graph transfer learning, extracting triple structure features in combination with a capsule network, and generating a text entity coding module; s2, constructing a knowledge fusion module, converting a document text into a semantic vector, and adaptively fusing the semantic vector with external knowledge; s3, constructing a word-level semantic graph, and aggregating neighborhood information through a semantic graph attention mechanism to obtain word embedding representation containing context; s4, constructing a sentence-level semantic graph, performing self-attention calculation on the word-level semantic vector in the S3 to obtain semantic node representation of the sentence-level semantic vector, and performing feature aggregation on sentence-level nodes to obtain global semantic information of the document; and S5, constructing an output layer, and predicting according to the document feature vector in the S4 to obtain a final extraction type abstract result. The method has the advantages that redundant information in the document is removed, and ambiguity of text semantics is eliminated.

The invention belongs to the technical field of time series prediction, and more specifically relates to a time series data prediction method based on a deep integrated learning model and high and low frequency separation. The method comprises the following steps: collecting time sequence data in a system, and preprocessing the obtained data; vMD variational mode decomposition is carried out on original time sequence data, and a time sequence is decomposed into K mode components with limited bandwidth; combining a maximum information coefficient method and a reconstruction error analysis method to determine an optimal decomposition mode number K; dividing high and low frequency components for all decomposed modes by using a zero-crossing rate and a center frequency; appropriate prediction models are established for the high-frequency component and the low-frequency component respectively; and superposing all modal prediction results to obtain a final time sequence prediction result. According to the method, multiple deep learning models are combined, so that the prediction method has higher flexibility and adaptability, and proper models can be selected for components with different characteristics for prediction, thereby improving the overall performance.

The invention relates to the technical field of electric power engineering, in particular to a power transmission line monitoring method based on meteorological disaster early warning, which comprises the steps of risk assessment model establishment, potential risk area division, risk level division, real-time monitoring and remote monitoring and management. The data acquisition center carries out decoding, coding and primary processing on data and regularly checks the working state of a sensor by supporting multiple transmission protocols, and can access monitoring equipment under different communication protocols, so that on one hand, the redundancy and repetition of the equipment can be avoided, and on the other hand, the monitoring efficiency is improved; on the other hand, the building and laying cost of the monitoring system is reduced, comprehensive receiving, efficient transmission, safe storage and accurate analysis of meteorological data are effectively ensured, and a solid technical guarantee is provided for stable operation and efficient management of the real-time monitoring system of the power transmission line.

The invention relates to a relationship perception learning method of a time sequence knowledge graph based on an attention mechanism, which comprises the following steps of: firstly, acquiring a target relationship, a neighbor entity and an embedding vector of time sequence information of the neighbor entity through an embedding layer, and dynamically adjusting a weight according to the similarity of the target relationship and the neighbor relationship in a time dimension by utilizing the attention mechanism; therefore, the time sequence information of the neighbors is finely aggregated. Then, a fitness function is introduced to score negative samples, and the most challenging negative sample is selected to realize local optimization; in addition, a specially designed positive and negative sample processing mechanism effectively improves the time sequence discrimination capability of the relation perception embedding model on the negative sample, so that the modeling effect on the time sequence relation is enhanced.

The invention discloses a tobacco planting soil fertility evaluation method, and relates to the technical field of soil fertility evaluation methods, and the method comprises the following steps: determining a total data set of soil evaluation indexes, determining a minimum data set, and calculating the weight of each evaluation index in the minimum data set through an entropy weight method; a membership function is constructed, a soil fertility suitability index method is adopted to construct a soil fertility evaluation model, and a soil fertility suitability index SFI is obtained through calculation. The method has the advantages that the influence of various evaluation indexes on the soil fertility and the dynamic adjustment of the critical value and the optimal value of the membership function are comprehensively considered, the soil fertility evaluation model can be dynamically adjusted along with real-time monitoring data, and the evaluation result is more accurate. The soil fertility evaluation model can be used for evaluating the soil fertility of a to-be-detected area, and can also be used as a basis for improving soil.

The invention discloses an interpretable deep learning-based innate immune gene expression prediction method, which comprises the following steps of: 1, collecting and preprocessing a DNA (Deoxyribose Nucleic Acid) promoter sequence and epigenetic modification data, and dividing a preprocessed data set into a training set and an independent test set so as to verify the prediction performance of a model; 2, constructing a human innate immune gene expression prediction network based on residual connection, a convolutional neural network and an attention mechanism; 3, performing model training on a plurality of cell lines to obtain an optimal human innate immune gene expression prediction model, and evaluating the prediction effect of the model on the independent test set; and 4, carrying out post interpretability analysis on the model through an integral gradient method, and identifying a key motif which is most likely to influence gene expression. According to the method, DNA sequence information and epigenetic modification information are extracted more effectively, and a new tool is provided for deeply understanding a regulation mechanism of an innate immune gene and developing individualized medical treatment.

The invention discloses an illumination adaptive road surface detection method and system considering small target area identification, and relates to the technical field of intelligent perception. The method comprises the following steps: receiving real-time image data, building a horizon line detection network, and inputting the image into the network to obtain an upper half region image containing environmental elements and a lower half region image containing a road surface and obstacles; the day and night state of the driving scene is judged by using the upper half area image, so that the system automatically adjusts model parameters according to illumination conditions; performing semantic segmentation by using the lower half region image, and intercepting a small-resolution image block with road surface information amount according to a semantic mask; a multi-block fusion decision network is built, blocks are input into the network, and the network can adaptively distribute weights of features of the blocks and perform fusion decision on prediction probabilities of the blocks. According to the invention, the road surface detection is expanded to an all-weather scene, the method has higher practical application value, the identification difficulty of a small target road surface area is overcome, and the accuracy of road surface detection is improved.

The invention discloses a high-throughput analysis method and system based on automation, a medium and a product. The method comprises the following steps: collecting data of a plurality of samples in a preset number of pore plate containers; the abscissa is time, and the ordinate is a mass spectrum detection diagram of ion signal intensity; determining target product mass spectra under different reaction conditions; determining a target product mass spectrum peak area list; selecting the first percentage X in the target product mass spectrum peak area list to obtain a TOPX% target compound reaction condition list; based on preset TopX reaction condition sequence information and a TOPX% target compound reaction condition list, sequentially testing target compounds under different TOPX% reaction conditions to obtain TOPX data; determining an ultraviolet spectrogram according to the TOPX data; and determining the proportion of each target compound according to the area of each ultraviolet peak and the total area of all the ultraviolet peaks, and generating a target compound proportion pie chart. By implementing the method, the sample analysis efficiency is improved.

The invention provides a large model interpretable question answering method and system based on knowledge graph fusion, and the method comprises the steps: obtaining related knowledge of a question text in a knowledge graph, and taking the embedding of the related knowledge as static embedding; performing dynamic interactive exploration in the knowledge graph by utilizing the initial large model based on the problem text and static embedding to obtain a knowledge sub-graph, and fusing the knowledge sub-graph into the initial large model to obtain a large model in which external knowledge is introduced; inputting the question text into the large model for question-answer decision and outputting a question-answer result; determining a reasoning process based on attention distribution and an intermediate hidden state in a large model question and answer decision process; according to the method, related knowledge in the knowledge graph is obtained through static embedding and dynamic interactive retrieval, and the decision-making efficiency and accuracy of a large model are improved; reasoning is carried out through an attention mechanism, input data with high attention can be compared with entities and relations in the knowledge sub-graph, and the interpretability of the question-answering system and the credibility of the question-answering system on a large model are improved.

The invention proposes an entity extraction method and system based on a dynamic window attention mechanism, and the method comprises the steps: data collection, data preprocessing, and automatic labeling training, and during the automatic labeling training, based on the dynamic window attention mechanism, through improving the attention extraction weight of a TMN frame, the automatic labeling training is carried out. Trigger training, entity recognition model training and entity recognition model testing are carried out. From the perspective, the problem of key information omission or redundancy possibly caused by a fixed window is avoided by introducing a dynamic window attention mechanism, so that the model is more efficient when processing long sentences and complex sentence patterns, and the text information capture capability and the feature extraction effect of the model are remarkably improved. Besides, by combining the similarity matching optimization between the trigger and the sentence, the distinguishing capability of the model in a trigger classification task is remarkably improved, so that the distinguishing of a matched sample and an unmatched sample is more accurate.

The invention provides a flexible resource parameter identification method based on a KAN neural network, and relates to the technical field of power grid resource parameter identification, and the method comprises the following steps: obtaining historical operation data of power grid resources, and identifying flexible resources in the power grid resources through an analytic hierarchy process; according to the identified flexible resources, constructing a flexible resource digital model through a digital twinning technology, and extracting a sample data set according to the flexible resource digital model; based on the extracted sample data set, constructing and training a resource parameter identification model through a KAN neural network; and acquiring operation data of the flexible resources in real time, and identifying flexible resource parameters by using the trained resource parameter identification model. According to the method, the accuracy of identifying the flexible resource parameters by the model can be improved, more accurate decision support can be provided for power grid operators by identifying the flexible resource parameters, and more reasonable decisions can be made in the aspects of resource scheduling, energy distribution and the like.

The invention discloses an atlas digital analysis method and system based on a notarization file database, and the method comprises the steps: S1, obtaining and analyzing notarization file data in the notarization file database, and carrying out the preprocessing of the notarization file data; s2, constructing map nodes according to the extracted key information elements; s3, carrying out attribute assignment on nodes and relation edges in the graph structure; s4, storing the atlas structure to a notarization file atlas database; s5, receiving a query request of a user; s6, querying demand parameters based on the query conditions; s7, outputting a query result, and generating a graph structure containing a node association relationship; and S8, outputting an analysis result including potential correlation among the nodes, an event development trend and pattern recognition output. According to the invention, the problems of low data association degree and low query efficiency in a traditional archive management system are effectively solved.

The invention discloses an intelligent building engineering management system based on a BIM platform, and relates to the technical field of building engineering management, and the system comprises a BIM model database, a participant interface module, a real-time synchronization module, an automatic notification module, an authority management module and a block chain recording module. According to the intelligent building engineering management system based on the BIM platform, computing resources and storage capacity are flexibly adjusted according to project requirements, and the requirements of projects of different scales are met; the block chain recording module supports a multi-chain synchronization function, and different participants can record on independent chains; therefore, the security of the data is ensured, the expandability of the building engineering management system is improved, and the individual requirements of different participants are met; the automatic notification module adopts a plurality of channel notification modes, and supports a user-defined reminding mode and priority setting of a participant; therefore, information transmission is more flexible and diversified, and working habits and requirements of different participants are met.

The invention relates to the technical field of colorectal image analysis, in particular to a colorectal cancer diagnosis auxiliary method and system based on deep learning. The method comprises the following steps: acquiring colorectum endoscope image data, and performing region-of-interest positioning on the colorectum endoscope image data to obtain colorectum region-of-interest data; performing multi-stage image segmentation on the colorectal endoscope image data to obtain colorectal image multi-stage segmentation data; performing depth feature extraction on the first colorectal image segmentation data to obtain colorectal image depth feature data, and performing three-dimensional network construction on the second colorectal image segmentation data to obtain colorectal image three-dimensional network data; and carrying out cell relation feature extraction on the colorectal image three-dimensional network data to obtain colorectal image cell relation feature data so as to carry out colorectal cancer diagnosis auxiliary operation. According to the invention, the early diagnosis rate and diagnosis precision of colorectal cancer are improved.

The invention discloses a liver cancer post-transplantation muscle loss prediction method and device, and belongs to the technical field of biomedicine, and the method comprises the steps: constructing an unbalanced random forest model comprising a plurality of decision trees, independently predicting through the plurality of decision trees to obtain a plurality of high-risk or low-risk dichotomy prediction results, taking the proportion of the decision tree with the prediction result being high risk in all decision trees as the prediction probability of muscle loss after liver cancer liver transplantation finally output by the model; performing risk classification according to the prediction probability, and judging the postoperative muscle loss level of the patient as high risk, medium risk or low risk; constructing a decision tree model to layer prognosis of patients, and dividing the patients into a high-risk group, a medium-risk group and a low-risk group; and carrying out survival rate prediction in combination with liver transplantation standards and prognosis layering results of patients. According to the method, the muscle loss level after the liver transplantation can be accurately predicted, and a clinician can make a personalized treatment scheme and perform scientific management after the transplantation.

The invention provides a rainfall monitoring method and system based on unmanned aerial vehicle multi-mode noise reduction in the technical field of environment monitoring and unmanned aerial vehicle application, and the method comprises the steps: S1, collecting a visible light image and a long-wave infrared image through a multispectral vision module after an unmanned aerial vehicle takes off, and collecting a rainfall audio from an acoustic cabin through a microphone; s2, carrying out noise reduction processing on the visible light image, the long-wave infrared image and the rainfall audio; s3, extracting a raindrop size distribution histogram and a spatial density thermodynamic diagram based on the visible light image and the long-wave infrared image, and extracting acoustic MFCC features based on rainfall audio; s4, performing feature fusion operation based on the raindrop size distribution histogram, the visual density thermodynamic diagram and the acoustic MFCC features to obtain rainfall intensity; and S5, carrying out cumulant dynamic compensation based on the rainfall intensity to obtain the cumulative rainfall. The rainfall monitoring method has the advantages that the precision, robustness and practical level of rainfall monitoring are greatly improved.

The invention discloses a physical wind tunnel pressure measurement test optimization method based on CFD-AI and a storage medium. The method comprises the following steps: completing wind load measurement point arrangement after segmentation based on a parameterized modeling platform, and completing curved surface partitioning; establishing a CFD numerical wind tunnel calculation model, performing CFD full wind direction angle calculation, and extracting building surface measuring point wind pressure and local shape coefficients corresponding to all wind direction angles; in combination with the local shape coefficient and the three-dimensional building model, performing machine learning clustering analysis on the measuring points to form an optimized measuring point arrangement scheme; curved surface partitions are updated based on an optimized measuring point arrangement scheme and a Thiessen polygon, and a physical wind tunnel test is carried out; and integrating wind load analysis results of the physical wind tunnel and the CFD numerical wind tunnel, marking a wind pressure hyper-standard region, and calculating and outputting an overall shape coefficient in combination with a curved surface partition area and a local shape coefficient. The objective of the invention is to improve the problems of high pressure test cost, too long test data processing time and incapability of achieving engineering practical application of test efficiency and data accuracy in a physical wind tunnel test.

The invention discloses an asset pricing method based on deep interactive learning, and belongs to the technical field of data processing. The FCDIN specifically comprises the following steps: carrying out embedded representation learning on company characteristics; performing high-order feature interaction based on a graph neural network; and carrying out multi-order feature aggregation based on an attention mechanism and outputting a final estimation result of the excess income. According to the asset pricing method based on deep interactive learning provided by the invention, the stock market operation law is taken as the basis, the existing financial theory is taken as the guidance, and economic explanation is emphasized; by adopting the modeling method based on the graph neural network, the problem of redundancy generated by factor interaction constructed by a traditional method is effectively avoided, and the modeling efficiency is improved. The FCDIN enhances the capability of capturing potential pricing information, shows the powerful advantage of coping with a complex market, and plays a key auxiliary role in investor decision making and financial department supervision.