80results about How to "Reduce noise interference" patented technology

The invention discloses a method for generating a micromechanical property distribution diagram of a solid waste composite cement-based cementing material, and belongs to the technical field of performance prediction of solid waste composite cement-based cementing materials, and the method comprises the following steps: acquiring BSE, EDS and nanoindentation data of a sample; identifying indentation areas in the nanoindentation mark graph, and generating masks corresponding to the areas; performing statistics on the regional masks to obtain element content data of each indentation region; establishing a prediction model by adopting machine learning based on the regional element content and the elasticity data; performing super-pixel segmentation on the BSE image to match the scale of the indentation area; calculating element features of the super-pixel regions, and predicting the elastic modulus of each super-pixel region; and mapping the predicted elastic modulus to a corresponding region to generate an elastic modulus distribution diagram. According to the method, prediction of the two-dimensional space distribution of the internal elastic modulus of the solid waste composite cement-based cementing material can be realized, and data and visual support are provided for material heterogeneity research and multi-scale modeling.

The invention relates to a generative artificial intelligence context management technology, and discloses a knowledge tree-based structured memory system and method, a computer readable storage medium and electronic equipment. According to the system, structured memory with a father-son relationship is stored through a knowledge tree, a retrieval strategy is determined according to current input, related nodes or branches are recalled, and a memory context is generated for a model to call after deduplication, truncation, pruning, hierarchical summarization and priority retention processing are carried out under context budget constraint; and meanwhile, node addition, deletion, modification and combination, conflict marking, version management and cutting control are supported, so that the accuracy, consistency and long-term task stability of generated contents are improved. The knowledge tree construction module is used for acquiring external information and executing node generation, updating, deletion and branch maintenance, and can write back a knowledge tree after output; when conflicts exist, version management is executed, and cutting is carried out according to correlation, credibility, redundancy and the like.

A voice interaction method, system, device, and storage medium are disclosed. The method includes: acquiring historical voice interaction data of a target user, their viewing location, and an audio stream at that location; acquiring a knowledge graph of multiple exhibits within the area where the viewing location is located; determining the target user's voice interaction commands in the audio stream; associating the voice interaction commands with historical voice interaction data based on a preset contextual dialogue model to obtain contextual dialogue data; determining the target user's intent based on the voice interaction commands and contextual dialogue data; determining the explanation content based on the exhibit knowledge graph and the target user's intent, and generating a target display scene based on the explanation content; selecting a target virtual guide from a preset virtual guide library based on the explanation content, and displaying the target display scene; and having the target virtual guide explain the target display scene based on the explanation content. This application can improve the accuracy of voice interaction in VR exhibitions.

The embodiment of the invention provides an image detection method and computing equipment. The method comprises the following steps: segmenting a first image to be detected into a plurality of image blocks; performing frequency domain analysis on each image block to obtain each frequency domain analysis result corresponding to each image block; based on each frequency domain analysis result, determining a plurality of first image blocks meeting a preset screening condition from the plurality of image blocks, the preset screening condition at least comprising: the frequency domain analysis result indicates that the richness of the contained high-frequency features is the first N, and the high-frequency features correspond to an area in which the gray scale variation amplitude exceeds a specified threshold in the image blocks; determining image features corresponding to the first image based on the plurality of first image blocks through an extraction network; and determining a detection result at least indicating whether the first image is the generated image or not through a detection network at least based on the image features so as to realize accurate detection of the generated image.

The invention discloses an ontology recognition method and device oriented to a decision knowledge graph, and the method comprises the steps: carrying out the ontology knowledge extraction of text data of a decision-related field, and obtaining an ontology text set; the ontology text set comprises an attribute text set and a rule text set of each ontology; the attribute text set comprises various attribute texts; the rule text set comprises various rule texts; preprocessing the ontology text set to obtain a preprocessed text data set; performing ontology type identification processing on the text data set of each ontology in the preprocessed text data set to obtain a type identification result of each ontology; the type of the ontology comprises a fact type ontology, a rule type ontology and a decision type ontology.

The application relates to the technical field of system reliability analysis, in particular to a mixed Copula system reliability analysis method based on failure modes, which comprises the following steps: acquiring multi-failure mode degradation data, combining Bayesian inference to estimate parameters of a basic Copula function, rotating and transforming the basic Copula function to construct a mixed static Copula model, judging and optimizing the mixed static Copula model based on root mean square errors, extracting a time-varying correlation parameter sequence by using a sliding window, smoothing and denoising the time-varying correlation parameter sequence by using Kalman filtering, and constructing a mixed dynamic Copula model, and calculating the reliability of the system at different operation time points in combination with a failure mode limit state function. The application can represent the non-symmetrical tail correlation between the multiple failure modes and the time evolution law thereof, and improve the accuracy, stability and engineering applicability of system reliability analysis.

The application discloses a space-time convolution short-time traffic flow prediction method based on complementary ensemble empirical mode decomposition, and comprises the following steps: acquiring original traffic flow data and performing data preprocessing; and inputting the traffic flow data into a pre-constructed CEEMD-GAT-LSTM model to perform short-time traffic flow prediction. The prediction model comprises the following steps: performing signal decomposition on the traffic flow data by using CEEMD, fully mining the spatial features of the data by using GAT, and fully mining the time features of the data by using LSTM, so that the learning efficiency of the neural network is improved. The application can effectively improve the prediction accuracy of short-time traffic flow prediction and provide favorable reference value for the traffic department.

The invention relates to radar angle measurement, in particular to an anti-multipath radar angle measurement system and method based on comprehensive angle measurement, and the method comprises the steps: an angle measurement fusion module generates multi-source pitch angle candidate data through sum-difference angle measurement and sum-sum angle measurement; the track batch optimization module is used for performing batch processing on the multi-source pitch angle candidate data of the multiple trace points in a track batch stage, selecting an optimal pitch angle and updating the three-dimensional coordinates of each trace point; the track association optimization module is used for calculating the Euclidean distance between the three-dimensional coordinate corresponding to the multi-source pitch angle candidate data of each trace point and the historical track in the track tracking stage, selecting the optimal pitch angle and updating the three-dimensional coordinate of each trace point; the flight path smoothing processing module is used for smoothing the flight path height sequence and outputting the smoothed flight path height sequence so as to reduce noise interference and improve height estimation stability; the technical scheme provided by the invention can effectively overcome the defects that multipath interference is difficult to suppress effectively, the angle measurement precision is low and the track starting stability is poor.

The invention discloses a document-level relation extraction method and system based on knowledge enhancement and evidence guidance, and belongs to the technical field of natural language processing and information extraction. According to the invention, three core modules are mainly used for cooperative work: a document graph enhancement module is used for constructing a hierarchical heterogeneous graph and fusing co-reference analysis to enhance semantic representation; the knowledge enhancement module introduces an external knowledge base and adopts a confidence coefficient filtering mechanism to reduce knowledge noise; the evidence guidance reasoning module realizes multi-hop reasoning through axial attention and evidence supervision, and solves the technical problems of decentralized modeling of reasoning capability, large knowledge integration noise, insufficient evidence guidance and limited long-range dependence capture capability in the existing method. Experiments show that the method can effectively capture inter-sentence dependence, suppress knowledge noise and improve multi-hop reasoning stability, and can be widely applied to scenes such as knowledge graph construction, intelligent question and answer and information retrieval.

The application belongs to the field of artificial intelligence model compression and edge deployment in intelligent operation and maintenance and fault diagnosis of power equipment, and discloses a transformer cooperative distillation incremental learning method and system based on time sequence consistency, which comprises the following steps: a teacher model is used to screen a no-label sample set to obtain a pseudo-label sample set, the pseudo-label sample set is combined with an original label sample set to obtain a distillation training sample set; a multi-mechanism cooperative distillation training scheme containing soft and hard label joint distillation, time sequence consistency distillation and multi-task distillation is constructed, and a student model is subjected to distillation training through the multi-mechanism cooperative distillation training scheme; and a cooperative distillation incremental learning scheme in which a cloud end continuously updates a teacher model to adapt to new multi-source monitoring data and a student model after edge distillation generates a pseudo-label to expand the distillation training sample set is constructed. The application can be used for realizing high-precision and low-cost training and continuous updating of a student model in a resource-limited terminal or an online scene.

The invention relates to a mobile monitoring device for a machining machine tool. The mobile monitoring device comprises a mobile box body, and a monitoring assembly, a calculation and analysis assembly, a communication assembly and an interactive feedback assembly which are arranged in the mobile box body, the monitoring assembly comprises a first current sensor and a first vibration sensor; the communication control assembly comprises a controller, a vibration decomposition unit and a noise reduction module, the controller is connected with the noise reduction module, the noise reduction module is connected with the first current sensor and the vibration decomposition unit, and the vibration decomposition unit is connected with the first vibration sensor; the communication assembly comprises an access switch, and the access switch is connected with the controller; the interactive feedback assembly comprises an IO module, a current abnormity alarm lamp and a vibration abnormity alarm lamp, wherein the current abnormity alarm lamp and the vibration abnormity alarm lamp are connected with the IO module. The IO module is connected with the controller and the vibration decomposition unit. The device can operate independently of the machine tool, can synchronously collect current and vibration data, improves the machining judgment accuracy of the machine tool, and is high in compatibility with machine tools of different models.

This invention provides a method for predicting the health trend of hydropower units based on the TCN-BiLSTM-Attention model, relating to the field of hydropower generator sets. The method involves: S1: acquiring the original vibration signal of the hydropower generator set and denoising the original vibration signal using a TTAO-VMD-EWT joint denoising model; S2: obtaining multiple operating state parameters of the hydropower generator set and calculating the Pearson correlation coefficient, Spearman correlation coefficient, maximum information coefficient, and distance correlation coefficient between these parameters and the vibration signal; S3: calculating the fusion evaluation index of each operating state parameter and the vibration signal, selecting key features, and constructing a multi-dimensional feature vector together with the reconstructed vibration signal; S4: constructing a TCN-BiLSTM-Attention prediction model to predict and output the predicted trend of the hydropower generator set's vibration signal. This method improves prediction accuracy, increases prediction efficiency, and enhances the accuracy, stability, and timeliness of hydropower generator set vibration trend prediction.

The application relates to a laser radar odometer method and system based on a state space model and window attention, comprising the following steps: projecting original point cloud data and constructing an invalid point mask to filter invalid points; performing down-sampling and region aggregation to reduce the calculation amount; designing a CNN-SSM module to extract multi-scale features considering global and local information; gradually establishing cross-frame association based on a state space window attention fusion encoder; and finally converting the associated features into a pose relationship between adjacent point cloud frames. The application solves the problems of the traditional radar odometer based on deep learning, such as loss of details in global information modeling, decline of cross-frame association confidence of point clouds and high calculation cost caused by attention calculation dependence, and realizes the laser radar odometer with efficient, high real-time and high-precision pose estimation.

This invention discloses a drug target affinity prediction method that integrates PPI quality and uncertainty. The method constructs a drug molecule map and a multimodal protein structure representation, and extracts multi-source features by combining the local PPI sub-map of the target protein. By calculating the protein's low-frequency level, prediction uncertainty, and PPI quality, a PPI quality-aware gating factor is generated to adaptively adjust the PPI information injection intensity, and a residual enhancement strategy is used to preserve the original protein features. Subsequently, the drug representation and the enhanced protein representation are fused using adaptive gating, and the result is input into a prediction network to output the drug-target affinity. This method effectively integrates protein function and interaction information, improves the prediction stability of low-frequency proteins and the model's generalization ability, and provides an accurate and reliable computational tool for drug screening and candidate molecule selection.

The application discloses a kind of image recognition method and system under complex illumination environment, the method includes: obtaining the image to be identified needing to carry out image recognition, the illumination influence area is obtained by analyzing the image to be identified, and the illumination influence area is divided into a plurality of grid units according to pre-set rule by grid division;Respectively, randomly select pixel points from illumination influence area and non-illumination influence area, and obtain corresponding pixel block based on pre-set window size;The similarity weight between the pixel block of illumination influence area and non-illumination influence area is calculated respectively, to denoise the image to be identified, and the denoising identification image is input into pre-set image recognition model to obtain corresponding image recognition result.The application solves the problem of low image recognition efficiency in the prior art under complex illumination environment.

The application discloses a kind of knowledge embedding and retrieval method and system of multi-modal PDF document, specifically relates to knowledge embedding and retrieval field, the present application uses multi-modal big model identification picture, table and other non-text elements in PDF, generates its position coordinate, converts picture into structured literal description and stores source URL;Second, the original text, picture description and URL are integrated into Markdown format, then, adopt the strategy of gradual blocking: each picture information is individually used as text block, and the remaining pure text is blocked according to character length;Subsequently, all text blocks are vector embedded, and the type is stored as metadata into vector database;Finally, in the retrieval stage, relevant text blocks are returned based on vector similarity;In the generation stage, single mode or multi-modal model generates accurate answer using text content and picture URL.

This invention discloses an entity relationship recognition method and apparatus for decision knowledge graphs. The method includes: retrieving a set of decision text information from a decision knowledge text database; preprocessing the set of decision text information to obtain a preprocessed dataset; and performing entity relationship recognition processing on the preprocessed dataset to obtain an entity relationship information set.

This invention discloses an anisotropic sparse deconvolution enhancement method and system for ultrasound tumor image segmentation. The method includes: establishing a local convolution model for ultrasound RF images based on the anisotropic characteristics of the ultrasound xz imaging plane; constructing an axis-aligned elliptical symmetric anisotropic point spread function (PSF), whose lateral and axial spread scales are obtained through physical parameter conversion or data-driven methods; constructing an ultrasound sparse reconstruction objective function incorporating the anisotropic PSF, adding non-negativity constraints, introducing a weighted Hessian continuity term and an L1 sparse prior term in the xz plane direction, and optimizing the solution to obtain the sparse reconstruction result; using this result as input, employing an RL iterative deconvolution method based on the anisotropic PSF, and achieving image boundary sharpening and noise suppression through PSF flip kernel ratio iteration; inputting the enhanced image into a tumor segmentation network to complete training and inference, thereby achieving ultrasound tumor image segmentation.

This invention provides a magnetic detection device based on diamond NV centers and the Kerr effect. It achieves the sharing of light sources and optical paths between magnetic detection technologies based on the magneto-optical Kerr effect and those based on NV centers, combining the two technologies and greatly simplifying the device structure. This increases the intensity of the optical signal received by the detection module, reduces noise interference in the signal, and thus improves the accuracy of magnetic detection. It can simultaneously meet the requirements of rapid and high-resolution detection, and improve the overall detection speed while ensuring detection accuracy.

This invention provides a lithium carbonate price prediction method based on multimodal data collaborative driving, comprising the following steps: multimodal data source identification and data acquisition; multimodal data classification and standardization; personalized noise filtering and outlier correction of multimodal data; extraction of trend and correlation features from structured data; extraction of semantic and visual / speech features from unstructured data; extraction of key information and feature quantification from semi-structured data; weighted collaborative fusion and feature optimization of multimodal features; construction and training of a two-branch collaborative prediction model; model prediction and preliminary verification of prediction results; optimization and dynamic correction of prediction results; interpretability analysis and visualization of prediction results; and method effectiveness verification and continuous improvement. This method, based on multimodal data collaborative driving, addresses the pain points of existing lithium carbonate price prediction technologies, forming a comprehensive, high-precision, and highly practical prediction solution.

The present application relates to the technical field of image processing, in particular to a kind of cardiovascular medicine OCT image filtering enhancement method, the method comprises: by obtaining optical coherence tomography OCT image, and the classification distribution parameter and tissue distribution parameter of image, wherein classification distribution parameter is based on the light and dark change of original image and is obtained by classifying original image, and tissue distribution parameter is based on the tissue distribution of original image and is obtained by segmenting original image.Then based on the difference of classification distribution parameter and tissue distribution parameter, determine the noise influence factor of original image, and according to noise influence factor, original image is carried out non-local mean filtering, clear target image that inhibits speckle noise is obtained, finally, target image is enhanced, it is ensured that the OCT image after enhancement retains important structure details, and unnecessary noise interference is reduced.

The present application relates to a three-dimensional human body key point detection method based on an RGB-D camera in a crowd gathering scene, which comprises the following steps: obtaining an RGB image of a target human body to obtain two-dimensional pixel coordinates of human body key points through a deep learning-based 2D human body posture estimation algorithm, obtaining a depth image of the target human body to obtain depth values corresponding to the human body key points, optimizing the two-dimensional pixel coordinates through an adaptive mean filter, and obtaining three-dimensional coordinates of the human body key points in a camera coordinate system through coordinate transformation. The present application can quickly and accurately detect and obtain three-dimensional human body key point coordinates in a crowd gathering scene, provide information support for rescue work, and help robots operate and perform rescue tasks more accurately.

The application provides a driving auxiliary source and a power converter, and belongs to the technical field of power electronics. The driving auxiliary source is used for supplying power to a power circuit. The driving auxiliary source comprises: a flyback transformer unit comprising a primary winding and a plurality of secondary windings, the flyback transformer unit being used for outputting the voltage of the primary winding through the plurality of secondary windings after voltage transformation, the plurality of secondary windings comprising M first secondary windings and one second secondary winding, and the interference noise generated by each first switch tube in the power circuit being transmitted to the primary winding through the corresponding first secondary winding; and a flyback control unit connected to a branch in which the primary winding is located and used for controlling the voltage of the primary winding. The parasitic capacitance between the primary winding and at least part of the M first secondary windings is less than a first value, or the impedance on the branch in which the primary winding is located is greater than a second value, so that the ability of the driving auxiliary source to cope with the noise interference of the power circuit is improved, and the stability of the driving auxiliary source is ensured.

This invention relates to big data processing technology, and particularly to a method for detecting software that maliciously acquires computing resources based on big data. The method includes: acquiring the executable file of the target software and constructing graph data from this data; filtering instruction segments from the graph data and extracting context features from the filtered instruction segments using a Transformer encoder; using the context features as initial features for nodes and a graph attention network to aggregate node features to obtain static features; acquiring the protocol fingerprint and traffic statistics features of the target software and extracting dynamic features from the acquired features using a bidirectional LSTM network; fusing the static and dynamic features through an attention mechanism, and inputting the fused features into a random forest classifier to detect whether the target software is maliciously acquiring computing resources. This invention comprehensively captures both static and dynamic behavioral features, overcoming the limitations of traditional single-feature detection.

This invention relates to the field of cable defect identification technology, solving the technical problems of low accuracy in cable defect identification caused by gradient diffusion and feature degradation in existing deep networks, which lead to loss of edge details and difficulty in effectively extracting true weak thermal deformation features. Specifically, it relates to a method for identifying surface thermal deformation defects in extruded insulated low-voltage fire-resistant cables. The method acquires a visual image of the cable surface in the extrusion cooling state and a one-dimensional temporal physical signal, preprocesses the surface visual image to obtain a standard image, and uses a weighted gradient edge detection algorithm to construct templates in multiple directions to perform edge detection on the standard image. This invention reduces the probability of network parameter combinations getting trapped in local optima during model training, lowers false positive and false negative rates, improves the classification accuracy of cable surface thermal deformation defects, and meets the high-precision and high-robust defect detection requirements of extruded insulated low-voltage fire-resistant cables.

This invention relates to the field of medical technology, specifically to a method for monitoring anesthesia depth based on a neural network model. It includes the following steps: collecting physiological indicator data of patients under different degrees of anesthesia; preprocessing the physiological indicator data to obtain interference-free physiological indicator data; and transmitting the processed physiological indicator data to a data management system; constructing a neural network model; inputting the physiological indicator data into the neural network model through the data management system; and training the neural network model. This invention, by collecting physiological indicator data of patients under different degrees of anesthesia to establish a training dataset, and training the neural network model, enables the neural network to accurately predict the patient's anesthesia depth. This method of collecting and processing the training dataset provides sufficient data samples, allowing the neural network model to be trained on diverse data, thus improving the model's generalization ability.

The present application belongs to the technical field of soil compaction degree prediction, and particularly relates to a soil compaction quality prediction method, medium and terminal based on image recognition, comprising the following steps: S10, collecting data of soil compaction degree and soil surface compaction pictures of sand under different conditions; S20, preprocessing the collected pictures, including picture normalization, grayscale and binarization processing, and constructing a data set; S30, constructing an improved CNN neural network model based on the preprocessed data set; S40, importing the data set into the improved CNN neural network model for pre-training to obtain a pre-training model; S50, importing the collected pictures into the pre-training model, and performing freezing and fine-tuning on the pre-training model to obtain a sand compaction quality prediction model; and S60, importing the preprocessed surface compaction pictures of the sand to be detected into the prediction model to output a compaction degree prediction value. The present application has simple process and convenient operation, the obtained prediction model has strong robustness and generalization ability, and the prediction efficiency and accuracy of sand compaction quality are high.

This invention relates to a method, apparatus, and medium for rapid sorting of poultry meat percentage based on X-ray imaging. The method includes: Step S1: acquiring X-ray images of the poultry to be tested; Step S2: identifying the sternal region and skin boundary based on the X-ray image; Step S3: drawing a normal at the sternal apex, obtaining the intersection of the normal at the sternal apex and the skin boundary as the first surface point, and obtaining the initial bone-skin distance based on the distance from the sternal apex to the first surface point; Step S4: obtaining the angle between the X-ray machine's visual axis direction and the normal direction of the first surface point as the consistency difference angle, obtaining the sternal integrity ratio and sternal principal axis attitude angle based on the sternal region, and correcting the initial bone-skin distance based on the consistency difference angle, sternal integrity ratio, and sternal principal axis attitude angle to obtain the corrected bone-skin distance; Step S5: obtaining the meat percentage grading result based on the corrected bone-skin distance. Compared with the prior art, this invention can achieve poultry meat percentage sorting based on X-ray imaging.

This invention relates to a dynamic retrieval enhancement generation method based on critical path entropy increase trends and document selection. Addressing the issues of retrieval response lag and false triggering caused by single-point threshold triggering in existing technologies, as well as noise interference and resource waste caused by direct splicing of Top-K retrieval documents, this invention creatively proposes a critical path entropy increase trend triggering mechanism. It optimizes single-point entropy monitoring of all tokens to critical path token entropy increase trend monitoring, achieving on-demand retrieval triggering by dynamically determining uncertainty increments, thereby suppressing false triggering caused by noise fluctuations in non-critical locations and alleviating retrieval response lag. Furthermore, this invention proposes a document selection model based on direct preference optimization of DPO, optimizing the coarse-grained injection of Top-K documents into a fine-grained filtering and injection mechanism. By filtering out irrelevant and redundant documents, it reduces the invalid occupation of the context window, thereby solving the problems of reduced generation quality and wasted computational resources caused by noise interference.

The application discloses a kind of based on multi-modal multi-agent's document understanding and question and answer method and system, the method is first to the document and generates text paragraph and page image for pre-processing, then adopt retrieval enhancement generation framework from text and page image two channels retrieval and query relevant context, obtain text candidate set and image candidate set;Then utilize five kinds of functional agents to carry out preliminary fusion and form candidate conclusion, form cross-modal key information limit subsequent analysis range, carry out fine-grained review and analysis in text and image modality respectively, output with page number, paragraph, area and other location indication intra-modal conclusion, finally to multi-source result carries out consistency analysis and weighted fusion generation final answer.The application can simultaneously integrate text and visual clues, improve complex multi-modal reasoning ability, improve accuracy in document question and answer and the like task.