17results about How to "Avoid training" patented technology

The invention discloses a neural radiation field optimization method and equipment based on energy loss uncertainty voting. The method comprises the following steps: acquiring a data set required for training and testing a neural radiation field; an NLL function used by ActiveNeRF training is changed into an energy loss function, and a more reasonable regular term is used; training the model by using the energy loss; building a multi-head attention network model; acquiring a data set for training the multi-head attention network model; training a multi-head attention network model; and the trained attention network model is used to replace the color value of the sampling point with large noise under the test pose, and the final rendering effect is improved. According to the method, data uncertainty is modeled through the Bayesian method, training is carried out through energy loss, and the problem that negative logarithm likelihood loss can generate overlarge variance regardless of whether a predicted mean value is correct or not, so that model training is damaged is solved. On the basis, the data uncertainty is further fused into a multi-head attention network module, and the final rendering quality is improved.

The invention discloses a skyline analysis method and system for urban landscape design, and relates to the field of urban planning and design, and the method comprises the steps: collecting urban landscape historical images of a target city, generating an image data set, and dividing the image data set into a training set and a test set; establishing an SAM image segmentation model, and training and testing the SAM image segmentation model; acquiring an urban landscape image of a target city, and inputting the urban landscape image into the tested SAM image segmentation model to obtain a segmented binary image; performing edge extraction on the binarized image to obtain skyline discrete points and calculating urban landscape evaluation system indexes; and comprehensively analyzing the indexes of the urban landscape evaluation system to obtain an analysis result of the skyline of the target city. According to the method, the city skyline can be accurately extracted, large-scale model training can be avoided, so that a large amount of cost is saved, a scientific reference basis is provided for city planning and design, and optimization and improvement of city landscapes are promoted.

The invention discloses a substation monitoring data anomaly detection method and system based on deep learning, and mainly relates to the technical field of power data processing and monitoring. Comprising the following steps: carrying out preprocessing and feature extraction on original data collected in a transformer substation monitoring system; after feature extraction is completed, the extracted features are analyzed and processed by adopting a deep learning algorithm, and abnormal points or abnormal modes in the data are identified; performing hyper-parameter optimization on the constructed deep learning algorithm model; and outputting an anomaly detection result in a visual mode. The beneficial effects of the invention are that the method can achieve the quick and accurate anomaly detection of the monitoring data of the transformer substation, and provides a powerful guarantee for the safe and stable operation of the transformer substation.

The invention relates to the field of gene engineering, and discloses a construction method and application of a GPX4S131A mutant endothelial cell line. According to the invention, the CRISPR / Cas9 technology is utilized to construct a gRNA vector containing targeted GPX4, ssODN is utilized to carry out targeted alanine (A) mutation on serine (S) of the 131 basic group of GPX4, and a stable GPX4S131A mutant endothelial cell ferroptosis model is constructed, so that a specific mechanism of endothelial cell ferroptosis is disclosed, a useful clue is provided for treating cardiovascular diseases caused by endothelial cell ferroptosis, and the application has a wide application prospect. The important application value is realized.

The application discloses a kind of secondary frequency control method, device and storage medium based on neural network, belong to microgrid control technical field, method includes: obtaining the rated angular frequency of distributed microgrid preset, and the active power of each distributed power generation unit;Active power is respectively input into the corresponding pre-trained neural network, and the frequency compensation of each distributed power generation unit is output, the frequency deviation caused by droop control is compensated, so that the angular frequency of distributed microgrid output recovers to the rated angular frequency preset;Corresponding pre-trained neural network refers to the neural network that each distributed power generation unit corresponds one training process and is added privacy protection processing, so that attacker cannot infer whether single sample is used for the training of neural network according to neural network output result.The application can improve the security and stability of microgrid, solve the problem that traditional secondary frequency control method exists privacy leakage risk and security risk.

The application discloses a kind of customized training plan generation methods for operation and maintenance personnel based on performance prism, which comprises the following steps: collecting multi-source heterogeneous demand data of operation and maintenance personnel on multiple platforms, and combining Carnot model and importance performance analysis model for fusion processing, extracting key technology theme through cluster analysis, drawing core training intention and decomposing into key measurement indicators, collecting employee daily operation and maintenance behavior data and calculating ability membership degree vector, combining post demand information, calculating target ability information to be enhanced, generating training content using intelligent workflow engine according to target ability information and key measurement indicators, generating hybrid training plan combining online and offline according to employee historical schedule, issuing the plan to terminal and setting task reminders, which can ensure that training is executed on time, improve training coverage and completion rate, and realize the intelligentization, customization and high efficiency of operation and maintenance personnel training from demand analysis, capability assessment, content generation to plan execution.

The embodiment of the invention provides a reliability detection and model automatic training method for a sealing structure of a wellhead. The method comprises the steps of obtaining a size data set of the sealing structure; the size data set comprises a plurality of size data; the size data represents information of a physical structure of the sealing structure; performing matching processing on the size data set and a data set in a preset model library to obtain multiple groups of matched data sets; determining an initial model corresponding to the matched data set based on a preset model library; based on a Bayesian optimization algorithm, processing the size data set and each initial model to obtain a reliability detection model; the reliability detection model is used for processing the size data of the sealing structure to obtain a reliability detection result of the sealing structure. The method is used for achieving the effect of accurately and effectively detecting the reliability of the sealing structure.

The invention discloses a long video question-answering method and system based on a visual language model and a causal reasoning tree. The method comprises the following steps: carrying out time sequence segmentation on an input long video; calling a visual language model to generate text description for each fragment; analyzing the text description into a causal unit; leaf nodes are constructed, then intermediate nodes and root nodes are constructed, and a hierarchical causal reasoning tree is formed to construct a lightweight index for each node; user questions are received; and executing a search strategy on the tree by the question and answer agent, and integrating information to generate a final answer. The system comprises three main modules including a video analysis module, a fruit tree construction module and a question and answer agent module, and the steps of the method are completed. According to the method, a training-free framework completely based on the pre-training model is adopted, fine tuning can be carried out, the effect is further improved, the problem that the information retrieval accuracy of a single visual language model in a long video understanding task is low is effectively solved, and the answer accuracy of problems of global and local contents is improved.

The invention provides a software vulnerability severity evaluation method based on course learning and ordered regression, belongs to the technical field of computers, and solves the technical problem that an existing method is difficult to capture a sequential relationship among severity levels. Comprising the following steps: S1, constructing a vulnerability data set, and extracting vulnerability description and source codes; s2, a training set, a verification set and a test set are divided according to the proportion of 8: 1: 1; s3, designing an automatic difficulty measurer; s4, fusing the vulnerability description and the source code into bimodal input through a mixed prompt template; s5, an early stop strategy is adopted to prevent overfitting, and an optimal model and a prompt template are returned; and S6, inputting the target vulnerability to the trained model for prediction. The method has the advantages that model training is gradually optimized through curriculum learning, dual-mode information and prompt fine tuning are combined, performance is remarkably improved, and the requirement for high-quality automatic vulnerability assessment is met.

The invention discloses a data expansion and exoskeleton joint end-to-end torque estimation method based on a diffusion model, and the method comprises the steps: carrying out the normalization processing of time series data from a multi-source sensor, carrying out the fragmentation according to a fixed length, and constructing a training sample with a motion class label; then, training a classifier-free conditional diffusion model by adopting a sample, and simultaneously learning conditional and unconditional denoising mapping relationships in a manner of randomly inactivating category conditions; in the generation stage, based on a classifier-free condition guidance mechanism, multi-modal time series data with specified motion category features are gradually generated from random noise; and finally, fusing the generated synthetic data with real acquired data to train a joint torque end-to-end prediction network, thereby realizing joint torque estimation of input sensor time sequence data. The method improves the prediction precision, generalization ability and stability of the end-to-end torque estimation model in a multi-action and few-sample scene, and has a good engineering application value.

The application discloses a hierarchical three-dimensional Gaussian semantic field construction method fusing a multi-modal large language model. The application comprises the following steps: firstly, generating an initial point cloud of a scene based on an obtained two-dimensional RGB image sequence, and then generating an initial three-dimensional Gaussian distribution set; then, respectively performing multi-level granularity segmentation to obtain original segmentation images corresponding to different granularity levels of each RGB image; for each granularity level, generating cross-view consistent segmentation images and pixel-level semantic images corresponding to different granularity levels of each RGB image; then, optimizing the three-dimensional Gaussian distribution set to obtain an optimal Gaussian distribution set containing semantic features of the current granularity level; and finally, constructing a hierarchical three-dimensional Gaussian semantic field containing different semantic granularities. The application realizes the construction of a three-dimensional Gaussian semantic field with high fidelity, multiple granularities and support for complex open vocabulary queries, has high robustness and real-time performance, and is suitable for fields such as scene understanding and virtual reality editing.

This application provides a data processing method, a data processing apparatus, an electronic device, a computer-readable storage medium, and a computer program product; the method includes: obtaining a first model state corresponding to a first checkpoint; the first model state is the model state output by a streaming processing engine after calling a large model to input first task processing data and performing the Nth model training; obtaining second task processing data of the streaming processing engine, where N is a positive integer; inputting the second task processing data and the first model state into a large model for training, and obtaining a second model state corresponding to a second checkpoint output by the large model; the second model state is the model state output after performing the N+1th model training on the large model.

The invention relates to an API time series data anomaly detection method and device, and relates to the technical field of computers, and the method comprises the steps: obtaining time series data of a target API, and generating a time series data first prediction value of a first target time period through a machine learning model and the time series data; when the difference between the first actual value and the first predicted value corresponding to the same unit time meets a preset difference range, acquiring abnormal reason data corresponding to the first actual value; decomposing the specified abnormal reason sub-data in the first target time period by using a time sequence decomposition method, and calculating a second predicted value of the specified abnormal reason sub-data in a second target time period; and collecting a second actual value of the specified abnormal reason subdata in a second target time period, calculating a difference value between the second actual value and the second predicted value corresponding to the same unit time, and determining target abnormal reason data of the target API according to the difference value. According to the method, the data processing pressure about the model can be reduced, and the problem checking time is shortened.

The invention discloses an image position identification method based on a twin width hash network. In the offline stage, firstly, a plurality of reference points are deployed in a target area, and 80%, 10% and 10% are taken to divide a training set, a verification set and a test set; then, constructing a Hash width network, and transversely increasing feature nodes through incremental learning so as to expand the width of the network; then, dividing positive and negative sample pairs, taking a width hash network as two branches of a twin network framework, and sharing weights and network parameters; and finally, keeping the similarity of the original samples to the greatest extent by shortening the Hash distance of similar features and shortening the Hash distance of dissimilar features. In the online stage, a query picture is input into the constructed model, a hash code with high semantic consistency with an original image is obtained, a most similar retrieval image is obtained through retrieval in a database, and the RP position corresponding to the retrieval image serves as a visual position recognition result. The invention provides an image position identification method based on a twin width Hash network by utilizing width learning transverse expansion nodes and fully considering intra-group correlation and inter-group exclusiveness, and the positioning precision is ensured while the system overhead is reduced.

This invention provides an efficient face style transfer method, apparatus, and device based on a diffusion model. The method includes: acquiring a face image to be stylized and a target style image; inputting the face image to be stylized and the target style image into a pre-trained style model for face stylization processing to obtain a final face style image; the pre-trained style model is constructed using a cross-attention mechanism based on a first basic style transfer model, a second basic style transfer model, a diffusion model, and a text prompting model; the first basic style transfer model is used to acquire style feature information of the target style image; the second basic style transfer model is used to acquire facial fusion information of the face image to be stylized and the target style image. By using a pre-trained model, processing efficiency is improved; and by combining the style transfer model, diffusion model, and text prompting model for processing, the realism and naturalness of the final face style image are improved.

The invention provides a rapid bandaging first-aid kit for head and face trauma, and belongs to the technical field of craniomaxillofacial trauma hemostasis. Comprising a binding belt, tightening belts are fixedly connected to the ends of the two sides of the binding belt, limiting buckles are fixedly connected to the ends of the tightening belts, first limiting grooves are formed in the sides, close to the tightening belts, of the binding belt and the tightening belts at equal intervals, ear hollowed-out grooves are formed in the binding belt, and the ear hollowed-out grooves are connected with the limiting buckles. A first connecting frame is arranged at the end of the tightening belt. By arranging the pressurizing hemostasis mechanism and the supporting and limiting mechanism, on-site first-aid requirements of hemostasis, fixation, eyesight protection, wound adhesion prevention and the like can be met at the same time, and specific details are shown below. The device can be rapidly and stably fixed to the head of the patient through cooperative use of the binding belt and the tightening belt, and the tightness of the binding belt and the tightening belt can be rapidly adjusted by adjusting the positions, formed in the first limiting grooves, of the ear hollowed-out grooves.