36results about How to "Expand the dataset" patented technology

The invention relates to a method for detecting quick-changing attack domain name based on host group characteristics, which mainly comprises the following steps of 1, capturing a network data package and extracting a DNS (domain name server) message characteristic; 2, detecting the quick-changing attack domain name; and 3, performing misjudgment detection, wherein detection of the quick-changing attack domain name comprises the steps of computing an IP (internet protocol) distribution program of the host group which corresponds to the domain name, assessing service availability, and detecting network wave, and is the core of the invention; and misjudgment detection gets rid of the normal large scale network domain name in the process of detection of the quick-changing attack domain name and a detection result when a local network is not good in the process of detection of online rate. According to the invention, set of the DNS message in a local area network is analyzed; the problem of the accuracy rate of analysis of the single DNS message is avoided based on the characteristics of IP degree of dispersion of the host group which corresponds to the domain name and online rate; and the scale that the domain name corresponds to the host group is considered when an IP distance is computed, so that the misjudgment of a large scale fine quick-changing network is avoided.

The embodiment of the present invention provides a method and device for enhancing network flow data based on a generative adversarial net. The method comprises the following steps: acquiring a data set of real network flow in a target scene; training the generative adversarial net model according to the data set; and obtaining final enhanced flow data based on the trained generative adversarial net model. The embodiment of the present invention can be applied to various scenes without the need of expert experience in flow data aspect, flow data enhancement is adaptively implemented, the dataset of the network flow is expanded, and the effect of optimizing network performance by using a machine learning method is improved.

The invention provides an object image augmentation method and device based on multiple modes, equipment and a storage medium, and relates to the technical field of machine learning image recognition. The method comprises the following steps: acquiring a three-dimensional point cloud model of a to-be-augmented object; segmenting the three-dimensional point cloud model to obtain a plurality of composition blocks of the to-be-augmented object; acquiring actual motion video data of the to-be-augmented object, and determining one or more motion axes of the to-be-augmented object according to the actual motion video data; identifying one or more motion blocks of the to-be-augmented object from the plurality of composition blocks according to one or more motion axes of the to-be-augmented object; and setting different motion states for each motion block of the to-be-augmented object to generate image augmentation data of the to-be-augmented object. According to the invention, the image of the three-dimensional object is widened, the data set for training the image recognition model is expanded, and the robustness of the image recognition model is improved.

A system and methods are provided in which an artificial intelligence inference module identifies targeted information in large-scale unlabeled data, wherein the artificial intelligence inference module autonomously learns hierarchical representations from large-scale unlabeled data and continually self-improves from self-labeled data points using a teacher model trained to detect known targets from combined inputs of a small hand labeled curated dataset prepared by a domain expert together with self-generated intermediate and global context features derived from the unlabeled dataset by unsupervised and self-supervised processes. The trained teacher model processes further unlabeled data to self-generate new weakly-supervised training samples that are self-refined and self-corrected, without human supervision, and then used as inputs to a noisy student model trained in a semi-supervised learning process on a combination of the teacher model training set and new weakly-supervised training samples. With each iteration, the noisy student model continually self-optimizes its learned parameters against a set of configurable validation criteria such that the learned parameters of the noisy student surpass and replace the learned parameter of the prior iteration teacher model, with these optimized learned parameters periodically used to update the artificial intelligence inference module.

The invention relates to the field of tunnel exploration, in particular to a tunnel face surrounding rock intelligent grading method and equipment based on deep learning. The method comprises the following steps: marking and preprocessing tunnel face surrounding rock photo samples, and establishing a face image database for training; and then, a surrounding rock grading prediction model based on deep learning is established, and the model is trained according to the tunnel face image database, so that a prediction model with more accurate identification is constructed. According to the method, the to-be-detected tunnel face picture is segmented by adopting image segmentation, each sub-image is predicted, and finally, comprehensive evaluation and prediction are performed according to the prediction result of each sub-image, so that the data on which the prediction result is based is more comprehensive, and efficient and accurate discrimination of the tunnel face surrounding rock is also realized.

A system and method for enhancing bitmap indexing representation of a dataset, which comprises a plurality of cases and features, each case characterized by one or more values of each feature. Currently, the bins vector for each case in the dataset, is a binary array, which is a bitmap indexing representation of each respective feature of the case. The system and method enhance the bitmap indexing by padding each bins vector. The padding is carried out by identifying all target bit locations with a ‘1’ value and replacing at least one ‘0’ bit adjacent to a target bit location with a non-zero numerical value, thereby creating a padded bitmap index. The padding factor may be based on any mathematical or statistical factor concerning population or subpopulation relevant to each of the features of the dataset.

The invention discloses a depth estimation method based on a light field EPI image. The steps include: 1. Refocusing the light field data to obtain light field data under different focusing parameters; 2. Obtaining the light field data from the refocused light field data. Extract sub-aperture images of horizontal and vertical viewing angles; 3. Extract horizontal and vertical light field EPI images from sub-aperture images; 4. Build a dual-branch depth estimation model based on light field EPI image association reasoning, and use the extracted EPI images in the horizontal and vertical directions are used for training; 5. Use the trained depth estimation model to estimate the depth of the light field data to be processed. The invention can make full use of the correlation between the central pixel of the EPI image and the neighborhood, and can use the light field refocusing principle to realize data enhancement, thereby effectively improving the accuracy of the depth estimation of the light field EPI image.

Embodiments of the present invention provide an image processing method, device, system and computer storage medium. The method includes: obtaining a generation confrontation network through training in the following manner, the generation confrontation network including a generation model and a discriminant model: inputting an input image into the generation model to obtain an output image, wherein the output image has a similarity with the input image Different styles; input the output image to the discriminant model to obtain the output value; according to the predefined loss function, train the generative model and the discriminant model until convergence; use the trained generative model to obtain the generated The input image of the model has different styles of the target image. Therefore, the embodiment of the present invention can obtain a generative adversarial network through training, and based on the generative model of the generative adversarial network, a target image with a different style from the input image can be obtained, so that the data set used for vehicle detection can be expanded, thereby ensuring vehicle detection. Effect.

The invention relates to the field of natural language processing, in particular to a method for answering multiple choice questions for reading comprehension based on data enhancement. The method is: using the sliding window method to cut the background material of the reading comprehension multiple-choice question; standardizing the background material, question stem and option data format of the reading comprehension multiple-choice question; Sentence set X; use Bi‑Attention to extract candidate sentences from the perspective of high-dimensional sentence vectors to obtain answer material sentence set X; combine the sentence sets X and Y obtained by deduplication S3 and S4 to obtain candidate sentence set Z; The EDA strategy for multiple-choice questions expands the candidate sentence set Z to obtain the final data-enhanced candidate sentence set; the final data-enhanced candidate sentence set is input to the BERT model for reading comprehension multiple-choice question answer prediction.

The embodiment of the present invention provides a method and device for enhancing network flow data based on a generative adversarial net. The method comprises the following steps: acquiring a data set of real network flow in a target scene; training the generative adversarial net model according to the data set; and obtaining final enhanced flow data based on the trained generative adversarial net model. The embodiment of the present invention can be applied to various scenes without the need of expert experience in flow data aspect, flow data enhancement is adaptively implemented, the dataset of the network flow is expanded, and the effect of optimizing network performance by using a machine learning method is improved.

The invention relates to a two-way prediction method of material microscopic image and performance based on deep learning, and proposes an algorithm combining CNN and DNN to process parallel prediction of multiple inputs. Using CNN to extract material microscopic image features, add one-dimensional feature vector represented by material composition and process in the first fully connected layer. Integrated image features, other features are DNN input, to achieve regression prediction or classification of material comprehensive features and performance. On the basis of a large number of images generated by GAN, the performance of the generated images is predicted using the previous prediction model. In order to increase the credibility of the experimental results, three different networks can be trained for prediction, and finally the intersection of the three is output as the target image. By combining the convolutional neural network to extract features and features such as components and processes, the fitting degree of the model and performance is greatly improved, avoiding model underfitting, and the prediction method of performance classification meets the actual needs of production.

The present disclosure provides a three-dimensional velocity geological modeling method with random layout of structure and wave velocity, determining a base point in a three-dimensional space, establishing an equation according to the base point to determine a plane layered model, complicating the inclined layer of the plane layered model, and constructing a three-dimensional space The fold layer model of the upper surface; based on the 3D surface fold layer model, combined with the fault plane of random reference points and the displacement of each point in the global coordinate system, a 3D fault fold model is established; based on the 3D fault fold model, the structure containing salt domes is constructed. The velocity model simulates the upward intrusion of salt domes in a geological body of a certain depth; according to the set layer type, according to the set velocity range, and the wave velocity difference range between each layer, random The wave velocity amplitude is used to realize three-dimensional velocity modeling; the present disclosure increases the amount of model data when the deep learning method is used for geophysical inversion, and improves the inversion effect of the deep learning method.