25results about How to "Valid reservation" patented technology

The invention is applied to the technical field of food processing, and discloses a preparation method of low-temperature extraction medicinal and edible freeze-dried powder based on natural plants, and the preparation method comprises the following steps: S1, raw material pretreatment, S2, ultralow-temperature pre-cooling, S3, high-voltage pulsed electric field treatment, S4, low-temperature extraction, S5, multi-stage filtration, S6, vacuum concentration, and S7, freeze drying. According to the preparation method of the natural plant-based low-temperature extracted medicinal and edible homologous freeze-dried powder, an ultralow-temperature pre-cooling technology is adopted, an extremely low-temperature environment is created for the natural plants, possible damage to active components in the natural plants caused by high temperature is prevented from the source, a high-voltage pulsed electric field treatment means is introduced, the permeability of cell membranes can be ingeniously and remarkably improved, and the content of the active components in the natural plants is increased. And when the barrier action of the cell membrane is weakened, the extraction process becomes more efficient, so that more active ingredients can be smoothly dissolved out, damage to the active ingredients in the processing process is avoided to the greatest extent, and complete retention of the active ingredients is ensured.

The invention discloses a brand new end-to-end-based residential power load prediction method, which comprises the steps of 1) performing feature screening and data preprocessing on a data set by using a Pearson's correlation coefficient method, including feature normalization and one-hot coding; 2) dividing the preprocessed data set into a training set, a test set and a verification set according to 8: 1: 1; 3) extracting features of training set data by adopting a brand new end-to-end network model, learning data distribution and change rules, and constructing a deep learning neural network model; 4) through an Adam algorithm, according to the marble loss function, carrying out back propagation to train model parameters; the training effect of the model parameters is judged according to the loss value of the verification set; and 5) predicting the short-term residential power load by using the optimal deep learning neural network model trained in the step S04, and verifying the prediction precision of the network model.The method has the advantages of high prediction speed, good generalization ability and high prediction result accuracy.

The embodiment of the application provides a method for converting a knowledge graph into a natural language large model training sample and related equipment, and belongs to the technical field of artificial intelligence. The method comprises the following steps: selecting a key anchor point from the knowledge graph based on a graph centrality measurement index; taking a key anchor point pair as a starting point and an ending point, extracting a symmetric element path connecting the two, and constructing a subgraph; generating multi-perspective paths for the same core entity through an anchor point switching mechanism; converting subgraph information into a (instruction, output) sample pair conforming to the instruction fine-tuning paradigm by using a structured information template, a path information template and a metadata enrichment template; and fine-tuning a large language model by using the generated corpus. By introducing the symmetric element path and the multi-dimensional instruction template, the embodiment of the application realizes semantic preservation and structured mapping of complex relationships in the knowledge graph, and effectively improves the knowledge understanding, reasoning and generalization ability of the large model in a specific field such as the power secondary equipment field.

The present invention discloses a hyperspectral image compression and reconstruction method, device and equipment based on an autoencoder, which comprises: obtaining a Houston image data set and performing preprocessing including random cropping to generate an image block of a preset size as an original hyperspectral image; inputting the original hyperspectral image into an autoencoder model including an encoder and a decoder and training based on a preset loss function to obtain a trained hyperspectral compression model, wherein the network structure of the encoder includes a thumbnail generation branch and a potential encoding branch, and the network structure of the decoder includes a thumbnail decoding branch and a potential representation decoding branch; inputting a hyperspectral image to be compressed into the hyperspectral compression model, encoding the hyperspectral image to be compressed by the encoder to obtain compressed data, and decoding the compressed data by the decoder to obtain a reconstructed hyperspectral image.

The utility model discloses an inflator for inflating product belongs to inflating device technical field, and it includes the cylinder, the inflator and the piston structure. Its innovation lies in setting up the oil absorption cotton structure, and this oil absorption cotton can be installed in two positions: one is on the piston structure, and specifically can be set in the positioning groove of piston or the annular groove specially, is located the rubber ring inside, two is the bottom of the cylinder. The piston structure includes the support disc with the positioning groove and the annular groove and the rubber ring with the inverted L type section. The oil absorption cotton can be annular or circular, and can be provided with tail strip to facilitate replacement. The utility model prolongs the service life of inflator, improves the inflating cleanliness through the effective adsorption and slow -release lubricating oil of oil absorption cotton, reduces the friction wear and oil spill, is especially suitable for the product such as inflating toy.

The invention provides a bamboo-based biomass foaming material and a preparation method thereof. The bamboo-based biomass foaming material is derived from bamboo cellulose; wherein the bamboo-based biomass foaming material is of a three-dimensional network structure, and the three-dimensional network structure is formed by stacking micro-scale polyhedral cell walls; in addition, pore structures are formed among at least part of the polyhedral cell walls. The three-dimensional network structure of the bamboo-based biomass foaming material is mainly composed of micro-scale polyhedral cell walls, pore structures are arranged among at least part of the polyhedral cell walls, and the bamboo-based biomass foaming material which is excellent in performance and environmentally friendly is obtained.

This invention belongs to the field of food processing technology and discloses a method for producing anthocyanin-enriched antioxidant jelly from black chokeberry. By weight, the raw materials include: 6.5-19.5 parts black chokeberry, 3.5-10.5 parts persimmon, 7-21 parts erythritol, 0.4-1.2 parts carrageenan, 0.4-1.2 parts konjac gum, and the remainder being drinking water. The method employs a persimmon compound astringency removal process to eliminate the astringency of the black chokeberry itself; uses erythritol, a natural sugar substitute, to replace sucrose as a sweetener, which reduces calories and avoids masking the natural flavor of anthocyanins; and utilizes a compound gum to form the jelly, combining the anthocyanins of black chokeberry with the jelly; thus developing a low-sugar, healthy, functional food to meet consumers' demand for healthy snacks.

The application discloses a multi-domain modeling and semantic embedding enhanced lightweight small target detection method. The multi-domain modeling and semantic embedding enhanced lightweight small target detection method comprises the following steps: acquiring a to-be-detected image; inputting the to-be-detected image into a trained lightweight detection model, so as to determine a backbone feature map of the to-be-detected image through a plurality of high-frequency residual enhancement spatial depth conversion convolution units and a plurality of spatial-frequency context enhancement layer aggregation units; fusing the backbone feature map through a feature pyramid fusion method to obtain a fused feature map; determining a neck feature map based on the fused feature through a plurality of frequency-guided semantic injection units; and detecting the neck feature map through a plurality of detection heads to obtain a detection result of the to-be-detected image, thereby improving the detection precision of small targets.

This invention provides a protective mobile unmanned surface vessel (USV) hyperspectral system for shallow sea pollution observation, belonging to the field of marine environmental monitoring technology. It includes an USV hull, hyperspectral observation equipment, a water sampling and detection device, and a controller. By installing a cabin and a hinged door on the USV hull, and housing the height-adjustable hyperspectral observation equipment, the system effectively protects the equipment when observation is needed. The door opens to extend the equipment from the cabin, and retracts it when observation is not required, then closes the door. The water sampling and detection device allows for timely and rapid sampling of polluted water, analysis of the samples, and output of results. This invention integrates hyperspectral observation and water sampling and detection, effectively protecting the hyperspectral observation equipment while simultaneously enabling sampling of polluted water, thus improving the effectiveness of pollution evidence collection.

The present invention discloses a pure bearing target motion analysis method and system for surface track planning; wherein the analysis method comprises: a preprocessing step, a target predicted position acquisition step, and a target predicted position correction value acquisition step; the present invention uses a target position prediction model based on a time convolutional network to obtain a target predicted position, and compared with a traditional positioning method, the target position prediction model has a higher prediction accuracy; the present invention uses a set empirical mode decomposition method to decompose an initial signal, and uses a target position prediction model to obtain a target predicted position, thereby not prone to problems of reduced solution accuracy or even divergence; the present invention constructs a motion state equation of a target, and on this basis uses a recursive least squares method to correct the target predicted position output by the target position prediction model, so that all observation information in the observation process is utilized, and the accuracy and stability of the target motion state prediction are further improved.

The application discloses a forgetting learning method based on elastic weight consolidation, which comprises the following steps: initializing model parameters through a training data set, obtaining a loss function through a sample, selecting an optimization algorithm to minimize the loss function until the model converges, receiving a deletion request, obtaining a to-be-deleted data set, calculating a Fisher information matrix of the data set, modifying the loss function in combination with the to-be-deleted data set, minimizing the loss function by using the optimization algorithm until a model of the deleted data set is output after the requirement is met. The application is applicable to an online learning scene, can effectively retain previously learned knowledge, can pre-optimize the loss function before deleting data, and can quickly adapt to new tasks.

This invention discloses a method for detecting minute defects in cigarette boxes based on a CDM-YOLOv8 network, comprising: Step 1, acquiring an image of the cigarette box surface and constructing a defect detection dataset; Step 2, performing feature extraction enhancement on the input image, extracting defect-related features through multi-branch convolution, deformable convolution, and spatial attention mechanisms; Step 3, dynamically fusing features at different scales, and performing frequency domain banding processing on the fused features during the downsampling stage, employing a differentiated downsampling strategy to preserve defect edge and texture information; Step 4, outputting the category and location information of the defects based on the detection head. This invention solves the problems of easy loss of minute defects in cigarette boxes during downsampling and easy missed detection in complex backgrounds. By enhancing feature representation capabilities and preserving high-frequency defect information while ensuring computational efficiency, it improves the detection accuracy of minute defects in cigarette boxes and reduces the missed detection rate.

The application relates to the technical field of target detection, in particular to a high-altitude electric power operation violation identification method, which discloses the following steps: collecting high-definition images and low-quality images of an electric power operation site by using a drone, and making an electric power site high-definition data set; constructing an image enhancement network based on a local information enhancement module and a global information enhancement module; building a violation identification model based on an improved YOLOv8; selecting a suitable optimizer and a loss function; training and optimizing the constructed model. The optimal model after training and optimization is converted into an RKNN model in the front end, and is deployed to the front end of the drone. Real-time detection is realized by relying on the camera in the front end, and whether the operation personnel violate the rules is judged by the judgment unit according to the detection result. The application provides a high-altitude electric power operation violation identification method, which considers the construction of an operation data set, the enhancement of low-quality images, and simultaneously proposes a violation identification network model based on an improved YOLOv8, so that the accuracy of detection is maximally improved.

This invention relates to a method and system for suppressing baseline drift in electrocardiogram (ECG) signals based on cascaded singular spectrum analysis (SSA). The method includes: acquiring ECG signal data affected by baseline drift, setting the number of layers i = 1; and extracting baseline drift noise n from the ECG signal data affected by baseline drift using SSA with a window length of 2. i With ECG signal components o i Its central electrical signal ECG i Obtained through a formula; calculate baseline drift noise n. i With electrocardiogram (ECG) signal i inner product IP i Determine if the inner product has reached its minimum value. If the inner product has reached its minimum value, output the ECG signal of the current layer. i As a final result of suppressing baseline drift, otherwise, the baseline drift noise n i Using ECG signal data affected by baseline drift and incrementing the layer number i by 1, repeat the above extraction and calculation operations until the inner product reaches its minimum value, then output the ECG signal of the current layer. i .

The present application relates to the technical field of intelligent analysis of flavonoids, and particularly relates to an intelligent analysis method for electrochemical recognition of flavonoids. The method comprises the following steps: obtaining a response signal matrix in time-frequency dimension, and performing frequency domain compression and nonlinear interaction mapping to obtain a one-dimensional nonlinear compressed current response sequence; introducing a variable window integral singular response recognition mechanism based on the one-dimensional nonlinear compressed current response sequence to calculate a singular response strength; determining a singular response occurrence point based on the singular response strength, and performing weighted fusion on a local window tensor; performing asynchronous reconstruction processing on the obtained singular weighted fusion tensor to obtain a characteristic representation of the flavonoid target after asynchronous reconstruction processing, and performing intelligent analysis on the flavonoids. The method solves the problems of low resolution, poor stability and repeatability of traditional electrochemical recognition analysis methods for flavonoids, and the inability to obtain characteristics of various target objects in flavonoids, thereby improving the analysis accuracy.

An embodiment of the present application provides a method for human body posture migration, an electronic device, and a computer storage medium, the method comprising: acquiring multiple pictures, different pictures among the multiple pictures presenting different angles of a target human body; performing segmentation processing on each of the multiple pictures to obtain multiple human body segmentation maps; generating a second target picture based on the multiple pictures, the multiple human body segmentation maps, and a first target picture, wherein the first target picture is used to determine a first posture, and the second target picture has the target human body presented in the first posture.

The application relates to the technical field of image fusion, in particular to an image decomposition fusion method and system with adaptive filtering parameters, which comprises the following steps: acquiring each source image to be fused; calculating the pixel intensity quartile skewness of each source image; calculating the Gaussian filtering standard deviation, the spatial domain standard deviation of co-occurrence filtering and the co-occurrence matrix value range Gaussian standard deviation corresponding to each source image based on the pixel intensity quartile skewness; for each source image, performing Gaussian filtering processing based on the Gaussian filtering standard deviation, performing co-occurrence filtering processing based on the spatial domain standard deviation of co-occurrence filtering and the co-occurrence matrix value range Gaussian standard deviation, and then performing difference operation to obtain a base layer, a feature layer and an edge layer; fusing the base layer, the feature layer and the edge layer of each source image respectively, and linearly superimposing three fusion results to obtain a final fusion image. The application can realize fine separation and effective fusion of source image features, and significantly improves the definition and detail retention capability of the fusion image.

The present application belongs to the field of data acquisition, and relates to a gearbox gear detection equipment detection data acquisition method and system. The method comprises the following steps: collecting gearbox vibration and synchronous speed signals, dividing the vibration signals into frames, and performing noise reduction processing on each frame; estimating the composite noise spectrum based on the synchronous speed signal and harmonic analysis, combining the time-frequency kurtosis to adaptively select a multi-window function to calculate the noisy power spectrum, using the transient characteristics and prior signal-to-noise ratio to determine the nonlinear subtraction factor, performing spectral subtraction to obtain the target power spectrum, comparing the deviation of the actual meshing frequency and the theoretical value to dynamically determine whether to reconstruct the phase spectrum; and reconstructing all processed data frames by overlapping addition to obtain the detection signal. The present application can comprehensively suppress harmonic and random noise, and conditionally reconstruct key phase information, thereby improving the recognition degree and diagnostic accuracy of early weak fault features of the gearbox.

This invention discloses a cross-domain generation method for ball screw pair fault data based on unsupervised conditional diffusion, belonging to the field of ball screw pair fault diagnosis. The method includes constructing a source domain dataset and a target domain dataset; constructing an unsupervised conditional diffusion model; extracting a training set based on the source and target domain datasets, using the training set as input to the unsupervised conditional diffusion model, and performing unsupervised training on the unsupervised conditional diffusion model using a weighted joint loss function to establish a bidirectional mapping between the data in the source and target domain datasets, obtaining a mapping model; acquiring the health state data to be enhanced; and generating enhanced fault state vibration data corresponding to the operating conditions of the health state data to be enhanced based on the mapping model. This invention can generate one-dimensional time-series vibration data of the corresponding fault state from one-dimensional time-series vibration data of an unknown operating condition in a healthy state.

A garment color generation system and method for human body images belong to the field of garment auxiliary design. In view of the problem of garment automatic coloring, a human body image dataset is first constructed, including original human body images, local gray human body images and corresponding human body analysis images; then a locally controllable garment color generation system is designed, including a color feature extraction module and a color generation adversarial network. The color feature extraction module extracts the color matching scheme from the reference material and generates the color feature map, realizing the local controllability of color rendering. The color generation adversarial network includes a generator with a "double encoder-single decoder" structure and a discriminator, and the generator fuses human body features and color features to automatically color the garment area in the human body image. The color generation system adopts the generator and discriminator in an adversarial manner for training, and is matched with various auxiliary loss functions, realizing high-quality human body image generation.

The invention provides a driver driving behavior detection method, and belongs to the technical field of behavior detection, and the method comprises the steps: obtaining a safety equipment image when a driver drives through a camera disposed in a vehicle unit, and carrying out the enhancement processing of the safety equipment image, and obtaining an enhanced driver driving image; performing face feature point detection on the driver by using a Retina Face algorithm, and analyzing the driving state of the driver by extracting eye features and mouth features of the driver; an improved Small-Goals-Yov8 model is constructed, and the weight of the improved Small-Goals-Yov8 model is utilized to carry out prediction; and according to the extracted driving state and the prediction result, alarming and reminding the non-standard driving behavior of the driver to complete the detection of the driving behavior of the driver. The problems that an existing driver driving behavior detection device is high in deployment difficulty, high in cost and difficult to maintain are solved.

This disclosure provides a model animation processing method, a model animation processing device, an electronic device, and a computer program product, belonging to the field of animation processing technology. The method includes: acquiring vertex animation resources of a model to be processed; the vertex animation resources at least include a geometric mesh model, animation texture data, and configuration parameter information of the model to be processed; remapping the data channels of the geometric mesh model and / or performing coordinate system chirality transformation to generate a target mesh model; the target mesh model includes vertex data in a channel-adapted format; and transforming the poses of the vertices in the target mesh model based on the animation texture data and configuration parameter information to reconstruct the vertex animation of the target mesh model. This disclosure can effectively preserve vertex data in a channel-adapted format and complete the vertex animation reconstruction of the target mesh model based on the animation texture data and configuration parameter information.

The utility model discloses a sorting system for removing shells in sea sand, and relates to the technical field of sea sand treatment. The sorting system comprises a pre-screening device, a wind power sorting device, a crushing sorting device and a first conveying assembly. The pre-screening device is used for receiving original sea sand containing sea sand and shells and screening the original sea sand into a first particle size part, a second particle size part, a third particle size part and a fourth particle size part of which the particle sizes are increased in sequence; the wind power sorting device is used for receiving the third particle size part and screening the third particle size part into a first screened-out part and a first remaining part of which the shell content is sequentially increased; the crushing and sorting device is used for receiving the second particle size part and screening the second particle size part into a second screened-out part and a second remaining part of which the shell content is sequentially increased; and the first conveying assembly is used for conveying the third particle size part to the wind power sorting device and conveying the second particle size part to the crushing sorting device. The method can effectively reduce the content of shells in the sea sand.

The application relates to the feed manufacturing field, and particularly discloses a granular feed ration based on a cotton byproduct combination and a preparation method thereof. The granular feed ration based on the cotton byproduct combination comprises cotton stalks, detoxified cottonseed meal, energy feed, mixed meal, a compound enzyme preparation, a gossypol detoxification synergist, a rumen-protected amino acid, a buffer, premix, salt, stone powder and calcium hydrogen phosphate. The cotton stalks are cotton straw subjected to silk rubbing treatment, and the silk rubbing length is 1-3 cm. The detoxified cottonseed meal is cottonseed meal subjected to microbial fermentation. The granular feed ration has the advantages of eliminating the toxicity risk of free gossypol in the cottonseed meal and significantly improving the palatability and digestibility of the cotton stalks.

This invention provides a method and system for suppressing seismic network noise in marine seismic data, relating to the field of seismic network noise suppression technology. The method includes acquiring marine seismic data and performing single-shot input processing to form initial single-shot seismic input data; locating network noise based on amplitude characteristics of the initial single-shot seismic input data to pinpoint the network noise; and suppressing the network noise to form suppressed single-shot seismic data. This method effectively suppresses network noise by applying median filtering and linear suppression processing to the seismic data.