26results about How to "Implement expansion" patented technology

The invention belongs to the technical field of power grid main equipment diagnosis, and provides a power grid main equipment fault diagnosis method and system based on voiceprint cloud edge collaboration, which adopts a new cloud edge collaboration method and divides the analysis of voiceprint monitoring data into two stages. According to the method, the exception detection model is deployed on the edge side, exception analysis of mass voiceprint data is achieved, concurrent requests of a large number of concurrent signals at the cloud side are avoided, and the timeliness of voiceprint monitoring and analysis is improved. In the cloud, a multi-modal defect identification method fusing voiceprint, visible light, infrared and other multi-source data is deployed, secondary classification of sound abnormal signals is realized, and the reliability of equipment operation, maintenance and management is improved.

The invention belongs to the technical field of transformers, and provides a transformer partial discharge defect voiceprint feature extraction method and system, and the technical scheme comprises the steps: obtaining the original voiceprint data of a transformer; performing noise reduction on the original voiceprint data of the transformer based on an improved spectral subtraction method to obtain noise-reduced voiceprint data, and performing data expansion on the noise-reduced voiceprint data to obtain data-expanded voiceprint data; based on the voiceprint data after data expansion, in combination with the fundamental frequency and frequency distribution characteristics of the transformer, feature extraction is carried out to obtain the features of the partial discharge defect of the transformer, the voiceprint feature distribution characteristics and the deep relation with the transformer fault are fully considered, and the problems that the time domain, frequency domain and time-frequency domain features of the power transformer are multiple in variety, and the power transformer fault is poor are solved. The extraction of effective features is improved, the extraction of redundant and invalid features is avoided, and the prediction precision of the partial discharge defect of the transformer is improved.

The invention provides an image segmentation model training method and device, equipment and a storage medium, and the method comprises the steps: carrying out the merging of a foreground image, mask information and a background image, obtaining a first annotation image, generating annotation information for an original image according to a target detector and a first segmentation model, obtaining a second annotation image, generating a high-confidence first training dataset and a low-confidence second training dataset according to the first annotation image and the second annotation image, training based on the first training dataset to obtain a target teacher model, and then segmenting the second training dataset through the target teacher model to obtain a third training dataset; and finally training a student model according to the third training data set to obtain a target image segmentation model. According to the method and the device, the utilization rate of the training data is effectively improved in a low-resource scene, and high-reliability labeling information is automatically added to the image.

The invention relates to a label generation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a video identifier and description data of a target video; obtaining classification reference data of the target video according to the video identifier; generating a candidate label set based on the description data and the classification reference data; and inputting the description data and the candidate label set into a preset classification model to obtain a classification label of the target video. According to the embodiment of the invention, the classification label of the target video can be automatically generated, furthermore, the classification label closer to the description data of the target video is selected from the expanded richer candidate label set, the label generation accuracy is improved, and the classification label generation efficiency is improved due to the fact that the classification label is generated based on the same standard. Errors caused by individual differences in manual labeling are avoided, and the consistency of the labels is improved.

The invention discloses a colorectal cancer pathological image semi-supervised semantic segmentation method for regulating and controlling a pseudo label, and relates to the field of medical image visual segmentation. The method comprises the following steps: firstly, performing image acquisition and marking on a target pathological region, and dividing the target pathological region into a training set, a verification set and a test set in proportion; in the consistency regularization process of training the teacher model, sorting and reducing the categories of the low-confidence pseudo labels according to the confidence scores; the confidence coefficient of the pseudo-labels is evaluated through the prediction score difference between the final model and the optimal model of the trained teacher network, and the pseudo-labels with the high confidence coefficient are refined; according to the number of categories in the pseudo tag, setting the triggering probability of each sub-data enhancement method, and generating cascaded pixel random change; and finally, constructing a semi-supervised semantic segmentation model for the colorectal cancer pathological image false label. The problem that the semi-supervised semantic segmentation task of the colorectal cancer pathological image is low in precision is solved.

The invention provides a small sample radiation source individual identification model training method and device and electronic equipment, and relates to the technical field of radiation source individual identification, and the method comprises the steps: obtaining an original signal sample, and carrying out the form conversion of the original signal sample, and obtaining a multi-domain signal sample; the multi-domain signal sample comprises same-direction-orthogonal component data, bispectrum data and Hilbert spectrum data; performing phase rotation on the multi-domain signal sample to obtain an enhanced signal sample; performing feature extraction on the enhanced signal sample, and performing feature fusion on the extracted features to obtain multi-domain embedded features; performing classification based on multi-domain embedded features to obtain a prediction result of an enhanced signal sample; and constructing multi-task loss based on the multi-domain embedded features, the prediction result and the sample label of the original signal sample, and performing model optimization based on the multi-task loss to obtain a trained radiation source individual identification model. According to the invention, radiation source individual identification in a small sample scene can be carried out, and the identification accuracy is improved.

The invention relates to a white balance parameter determination method and device, equipment, a storage medium and a program product. The method comprises the steps that a partition statistical data stats graph corresponding to a target original image is acquired, and the stats graph comprises a plurality of first stats points; according to the plurality of first stats points, generating a plurality of second stats points; and according to the plurality of first stats points and the plurality of second stats points, white balance parameters are determined, and the white balance parameters are used for carrying out image processing on the target original image. By adopting the method, the accuracy of white balance parameters can be improved.

The invention discloses a financial supervision and inspection problem text classification method and device, equipment and a storage medium. The method comprises the following steps: acquiring a financial supervision inspection question text; inputting the financial examination question text into the target classification model to obtain a risk result output by the target classification model; wherein the target classification model is obtained by pre-training on the basis of a BERT model, and a lexicon table of the BERT model is obtained by expanding a lexicon table corresponding to a SentencePiece word segmentation device. According to the scheme provided by the embodiment of the invention, on the basis of the Bert model, the word library table of the BERT model is expanded by introducing SentecePiece word segmentation, that is, the target classification model is obtained through easy-to-difficult training, so that the model fully learns more feature information in a financial supervision inspection problem text, and the purpose of improving the classification accuracy of the model is achieved.

The invention belongs to the technical field of image recognition, provides an electric power inspection evidence recognition method and system based on data enhancement and retraining, and aims to solve the problems of low accuracy of electric power marketing inspection image recognition, poor service scene applicability and the like, and adopts data enhancement to expand samples, YOLOv8 retraining optimization and network compression to improve the application range. Therefore, electric power inspection evidence identification requirements of multiple service scenes can be met. Firstly, in order to avoid low model identification accuracy caused by insufficient training sample quantity, a CutMix-based data enhancement algorithm is adopted to generate a simulation training sample; secondly, based on the expanded training sample set, carrying out applicability retraining on a YOLOv8 network identification model, and improving the accuracy of electric power inspection image identification; and finally, the retrained YOLOv8 network identification model is compressed by adopting a mode of combining structural design and knowledge distillation, so that the field identification requirement of the mobile terminal application is met, the network scale is effectively reduced, and the identification timeliness is improved.

The invention discloses a flow control method and system for an MAC address, and the method comprises the steps: defining the load level of the MAC address based on the real-time flow of the MAC address, and triggering the load upgrade of the MAC address according to the load level of the MAC address and the transmission speed of data. If the Linux operating system is associated with a plurality of users, the Linux operating system matches a corresponding load balance relationship based on the traffic load of the Linux operating system and the traffic loads of the plurality of traffic expansion spaces, and dynamically regulates and controls a traffic control path between the Linux operating system and the plurality of traffic expansion spaces according to the load balance relationship; if so, carrying out synchronous management and control based on MAC addresses corresponding to a plurality of users, defining the priority of each flow management and control path based on the use level of the user, and defining the data transmission speed of each user based on the priority of each flow management and control path and the importance level of the received data; therefore, the data transmission speed of multiple users can be managed and controlled, and the accurate control of the data traffic of the multiple users is realized.

The present application relates to a configuration parameter synchronization method, device, computer equipment and readable storage medium. The method comprises: obtaining a target device set; in the process of synchronizing configuration parameters to target devices in the target device set based on a configuration file, when a current target device that has completed configuration parameter synchronization is detected, the current target device is used as a newly added source device; the target devices in the target device set that have not started configuration parameter synchronization are divided to obtain a first processing device set corresponding to the current source device and a second processing device set corresponding to the newly added source device; based on the configuration file, the configuration parameters are continued to be synchronized to the target devices in the first processing device set, and the configuration parameter synchronization authority corresponding to the second processing device set is allocated to the newly added source device, so that the newly added source device synchronizes the configuration parameters to the target devices in the second processing device set based on the local configuration file. The use of this method can improve the efficiency of configuration parameter synchronization.

The invention relates to the technical field of network security, and discloses an unknown attack-based network defense method, which comprises the following steps of: dividing according to tuple information of a network data packet to obtain a network data stream; aggregating communication nodes of the network data packet to obtain a data communication channel; performing feature statistics and original byte extraction on the data stream to obtain a preprocessed network stream, and enhancing the preprocessed network stream to obtain an enhanced network stream; optimizing network parameters through a joint loss function to obtain an optimized feature vector; extracting feature vectors by freezing parameters of the triple network, and training a single classifier to obtain a trained single classifier; and based on the feature vector, judging a preset test sample to be benign or malicious, and when the test passes, obtaining a trained attack distinguishing model, and performing unknown attack detection. The invention further provides a network defense device and equipment based on the unknown attack and a storage medium. According to the method, the detection capability of unknown network attacks can be coped, and the security of network protection is improved.

The invention provides a construction method of a user experience knowledge base and a construction device of the user experience knowledge base. The method comprises the steps that user experience data are obtained, the user experience data are reaction data generated in the interaction process of a user and a product, and the user experience data comprise user feeling data, product performance data, product feature data and use scene data; according to the use scene data, classifying the multiple pieces of user experience data to obtain multiple data sets; according to the multiple data sets, a target user experience network is constructed, a user experience knowledge base is obtained, and the target user experience network is used for representing the influence probability of any one of the product performance data, the product feature data and the use scene data on the user experience data; and obtaining a target search condition, and searching in the user experience knowledge base according to the target search condition to obtain a target search result. According to the method, the problem that user experience analysis is subjective in the prior art is solved.

The present invention provides a soil monitoring data analysis method, device and equipment for mine ecological restoration, which relates to the field of data processing technology, including: obtaining soil monitoring data; inputting soil monitoring data into a pre-trained soil monitoring data analysis model, and outputting soil monitoring data analysis results; the training method of the pre-trained soil monitoring data analysis model includes: training multiple local models based on training data sets respectively and then summarizing them to a global model of a central server for parameter update, and multiple local models perform global iteration based on the updated parameters until the training converges to complete the training; wherein the step of obtaining the training data set includes data expansion using a generative adversarial network based on variational Bayesian sparse matrix decomposition. This method reduces the cost of data transmission and storage, avoids the centralization and transmission of data, effectively reduces the risk of data leakage, and ensures the comprehensive use of data.

The invention relates to model training, in particular to a community police information early warning model training system based on quantum safety protection, which comprises a multivariate data identification unit, a data processing unit, a data processing unit, a data processing unit, a data processing unit and a data processing unit, model training samples corresponding to the modal data are sent to the model training management unit; the model training management unit verifies the model training samples sent by the multivariate data identification unit, performs model training on models corresponding to various modal data, and optimizes the models according to model training quality and model operation efficiency scores provided by the model deployment unit; the model deployment unit is used for deploying the trained model in the operation environment and monitoring and evaluating the operation state and the operation efficiency of the model; according to the technical scheme provided by the invention, the defects of low accuracy and efficiency of community police information early warning caused by difficulty in effective model training can be effectively overcome.

The utility model discloses a pen holding device suitable for pens with different diameters, which comprises a soft sleeve body, a support part and a containing cavity, the soft sleeve body and the support part are integrally formed by elastic soft materials, the pen holding device is suitable for the pens with different diameters through the structure and the material property of the support part, and the problems that the pen holding device is relatively single and the pen holding device is inconvenient are solved. A single pen holding device can only be matched with a pen with a diameter of one specification; according to the pen holder, the supporting part comprises the supporting rib and the rib extrusion cavity, expansion and fixation of the pen holder after the pen holder enters the containing cavity are achieved through cooperation of the supporting rib and the rib extrusion cavity and the structure of the supporting rib, and the maximum diameter D2 and the minimum diameter D1 suitable for the pen holder are divided through the extrusion degree of the supporting rib; when the supporting part is in a completely natural state, the diameter of the pen holder is the minimum diameter allowing the pen holder to penetrate through the supporting part; and when the supporting part is in a complete extrusion state, the diameter of the pen holder is the maximum diameter allowing the pen holder to penetrate through the containing cavity.

The invention discloses a seismic response sample expansion method based on a non-linear kernel function and an evolutionary strategy, which realizes expansion of small sample data by establishing and sampling a multi-dimensional normal distribution model of building seismic response data, and introduces the non-linear kernel function to calculate non-linear relevancy among features in a data set. According to the method, complex feature association of data is more accurately captured by a distribution model, an evolutionary strategy method is adopted, a nonlinear covariance matrix of the distribution model is optimized by maximizing the similarity between an expansion sample and an original data set, and therefore stable solution in the data expansion process is ensured, and the problem that an existing sample expansion algorithm is unstable is solved.

The invention relates to the technical field of emery roll machining, and discloses multifunctional tool rest equipment of a rice milling emery roll machining machine tool, which comprises a bottom plate, a mandrel is fixedly mounted at the top of the bottom plate, a locking nut is in threaded connection with the top of the mandrel, and a locking oil cylinder sleeves the outer side of the mandrel through the locking nut; an electric shock plate is fixedly mounted on the side surface of the top of the locking oil cylinder; the knife rest assembly is rotated through the swing oil cylinder to achieve selection of knife sharpening and outer circular knife, and when the sliding block rotates to the position of the check block, after the sliding block makes contact with the limiting switch, the swing oil cylinder stops working; when the locking oil cylinder rotates to a designated position, after the electric shock plate makes contact with the proximity switch, the locking oil cylinder locks the tool rest assembly and stops working, and finally a corresponding tool is used for machining a product. Therefore, one-time clamping and one-time machining forming are achieved for machining of the emery roll product, the machining precision of the groove profile of the emery roll is greatly improved, the machining efficiency is also improved, the turnover and carrying period is also shortened, and the labor amount is also reduced.

The invention relates to a model training method and device, a mechanical arm control method, electronic equipment and a medium. The model training method comprises the steps that a pre-training alignment model is obtained through training based on an obtained training data set; wherein the training data set comprises first sample data; controlling a mechanical arm based on the pre-training alignment model, and collecting candidate sample data when the to-be-processed flexible cutting piece is flattened and aligned; after the paving and aligning operation is completed, screening the candidate sample data to obtain second sample data; adding the second sample data into the training data set to obtain a new training data set; and re-training the pre-training alignment model based on the new training data set to obtain a new pre-training alignment model, and returning to the step of controlling the mechanical arm based on the pre-training alignment model until a preset stop condition is met to obtain a trained alignment model. According to the method, the qualified training samples are automatically generated under the condition of less manual intervention, and the training data set acquisition efficiency is improved.

The embodiment of the invention provides an image generation model training method and device, an image generation method and device, equipment and a medium, and the method comprises the steps: obtaining any first image description in an initial sample set which is a sample set used for training a target image generation model; based on the first image description, through a target text generation model, obtaining a plurality of prediction descriptions; based on each prediction description, through a target image generation model, obtaining at least two first generation images corresponding to each prediction description; based on the first image description and the at least two first generated images, determining an expanded image-text pair for training a target image generation model; and training the target image generation model by using the first generated image and the first image description in the expanded image-text pair, so as to improve the quality of the image generated by the target image generation model obtained by training, and improve the stability of the capability of generating the image with better quality.

The present application relates to the technical field of printed matter detection, and relates to a printed matter online detection method and system based on machine vision, which comprises the following steps: acquiring a printed matter image library, classifying features of the printed matter image library to obtain a plurality of feature image libraries, training a pre-constructed discrimination model by using a training matrix set, a defect matrix set, a positive verification matrix set and a negative verification matrix set to obtain a defect discrimination model, constructing a generative adversarial network based on the pre-constructed VAE encoder and the defect discrimination model, discriminating a to-be-detected feature matrix based on a weight coefficient group and a plurality of completed adversarial networks to obtain a printing defect index, and confirming a plurality of printing defect images based on a plurality of printing defect indexes and a plurality of to-be-detected images to complete online detection of the printed matter. The present application can improve the accuracy and robustness of printed matter defect detection and improve the printed matter detection efficiency.

The invention provides an account detection model training method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a sample data set, and enabling samples of the sample data set to comprise a plurality of unlabeled accounts and a plurality of positive sample accounts; performing clustering processing on each sample in the sample data set to obtain a clustering result, the clustering result comprising a plurality of clusters; marking the unmarked accounts in each cluster to obtain a marking result of each cluster; marking the unmarked accounts in each cluster, wherein the step of marking the unmarked accounts in each cluster comprises the substeps of calculating the similarity between each unmarked account in each cluster and a positive sample account; according to the similarity corresponding to each unlabeled account, labeling each unlabeled account in each cluster; training a sub-account detection model corresponding to each cluster according to the labeling result of each cluster and the positive sample account in each cluster; and according to the clustering result, aggregating the sub-account detection models corresponding to each cluster to obtain a target account detection model.

The application discloses a kind of electric power data acquisition method, readable storage medium and device, belong to industrial internet of things and power system automation technical field;A kind of electric power data acquisition method, based on the industrial protocol characteristics of access equipment to identify the protocol type of access equipment, select the analysis template compatible with the protocol type of access equipment by pre-configured template library, finally using analysis template to the data stream of access equipment is parsed and processed, the original binary or byte stream data of access equipment is converted into the key-value pair data point with standard semantics, data acquisition is convenient, adapt to the access of multi-source heterogeneous equipment in power internet of things, greatly reduce the complexity of system development, deployment and maintenance, solve the problem that current electric power data acquisition needs to be separately developed special drive or communication service for different protocol equipment.

The invention provides an enterprise violation risk prediction model training method and a related device, and the method comprises the steps: obtaining enterprise contract data, inputting the enterprise contract data into a pre-trained enterprise contract data expansion model, and obtaining expanded contract data; combining the enterprise contract data and the expanded contract data to obtain a first contract sample set; performing feature extraction on the first contract sample set by adopting a pre-trained feature extraction model to obtain contract features of each contract sample in the first contract sample set; according to the risk type of the contract sample, correspondingly marking contract features, and combining all marked contract features to obtain a training feature set; training the classification model by adopting the training feature set to obtain an enterprise violation risk prediction model; according to the method, the enterprise violation risk prediction model for performing high-accuracy judgment on the enterprise contract risk can be obtained through training.

This invention belongs to the field of control system technology, specifically relating to a rapid switching device for chlorination furnaces in a chlorination production line. It is used for the rapid switching control of chlorination furnaces in at least two chlorination production lines. Each chlorination production line has two chlorination furnaces configured with one in operation and one on standby. The rapid switching device includes a standard cabinet integrating various control components, including circuit breakers, terminal blocks, 24V relays, 24V switching power supplies, redundant modules, and transfer switches. This invention allows the equipment to transmit signals to different control system loops, enabling the device to switch to different systems. The switching device uses a cross-power supply mode, which reduces system load and improves system safety and stability. It maximizes the utilization of chlorination furnace equipment in chlorination production, expands chlorination production lines, and is not limited to chlorination production, exhibiting significant compatibility with other production systems.

The present invention discloses a complex product intelligent design method based on case reasoning and reinforcement learning, which belongs to the complex product design technical solution, and the steps include: case characterization, structurally characterizing the case through framework theory, accurately describing the characteristics and module composition of the case; case matching, retrieving similar cases in the case library according to the needs, and obtaining relevant experience and solutions; case reconstruction, using a method based on reinforcement learning and weighted sequential cross reconstruction to expand the case library and generate more possible design solutions; case optimization, using a multi-attribute decision-making method to evaluate and optimize the expanded solution set. The present invention adopts the above-mentioned complex product intelligent design method based on case reasoning and reinforcement learning to meet the needs of the engineering design field for efficient and high-quality design solutions, quickly and diversely provide design solutions to designers, and achieve the effect of shortening the design cycle and reducing manufacturing costs.