13results about How to "Effective characterization" patented technology

The invention provides a system efficiency evaluation method based on OODA ring closing, and the method comprises the steps: dividing an efficiency index system into three dimensions: a task, an OODA ring flow, and a killing chain, and constructing the overall dimension of the efficiency index system; establishing a multi-layer efficiency index system of task-OODA ring process-killing chain sub-chain-efficiency index by analyzing the OODA ring process and killing chain closing; and acquiring expert comprehensive weights of each node in the task layer, the OODA ring flow layer and the killing chain layer and each efficiency index in the efficiency index layer, and performing layer-by-layer upward recursion by adopting a weighted summation method according to the expert score and the expert comprehensive weight of each node or index in each layer, thereby determining a comprehensive efficiency value of the system, and completing efficiency evaluation of the cross-domain collaborative system. According to the method, the system efficiency index is constructed based on OODA ring closing, the richness and integrity of task requirements are ensured, and meanwhile, the finally obtained efficiency index can more comprehensively and effectively represent the capability of the system on the system level from the perspective of OODA ring closing.

The invention discloses a drought cause index screening method, and relates to the technical field of drought cause index screening, and the method comprises the steps: obtaining multi-scale drought data in time and space, and extracting the drought features of the multi-scale drought data; constructing a comprehensive drought index based on the drought characteristics; obtaining a data set based on the comprehensive drought index and the multi-scale drought data; analyzing the data set based on a drought evaluation model to obtain a loss value, inputting the loss value into an SHAP model to obtain an SHAP value, and screening drought cause indexes based on the SHAP value to obtain a screening result; the problems that in the process of obtaining the causal relationship between observation data and drought, an existing method neglects the influence of underlying surface factors on drought events, the relationship between agricultural and hydrological drought conditions and observation data cannot be mined, spatial features are neglected, and the spatial evolution features of the drought process are difficult to reflect can be solved.

The invention discloses a GIS equipment laser three-dimensional point cloud data denoising method, and relates to the field of data denoising, and the method comprises the steps: S1, obtaining, processing and analyzing GIS equipment laser three-dimensional point cloud data, the GIS point cloud data comprising X, Y and Z coordinate information of a Cartesian coordinate system of a three-dimensional object on a sampling curved surface and the sampling curved surface of the three-dimensional object; s2, constructing a de-noising mapping model, wherein the de-noising mapping model comprises a local region feature de-noising layer and an overlapping region feature de-noising layer; and S3, substituting the GIS equipment laser three-dimensional point cloud data into the denoising mapping model to obtain a target denoising point cloud and generate a three-dimensional image. According to the GIS equipment laser three-dimensional point cloud data denoising method provided by the invention, data of irrelevant equipment can be more accurately removed and subjected to noise reduction processing, and the complexity in the operation process is reduced.

Disclosed are a scene reconstruction method, device, storage medium and electronic device, wherein the method comprises: performing background segmentation on a first image sequence collected by a camera set on a movable device to obtain a second image sequence; performing sparse reconstruction of a point cloud using the second image sequence to obtain a first reconstructed point cloud and a first camera pose sequence of the camera; performing dynamic and static segmentation on the first image sequence to obtain a third image sequence corresponding to a static scene and a fourth image sequence corresponding to a dynamic scene; performing dense reconstruction of the point cloud using the first reconstructed point cloud, the first camera pose sequence and the third image sequence to obtain a second reconstructed point cloud; performing sparse reconstruction and dense reconstruction of the point cloud in sequence using the first camera pose sequence and the fourth image sequence to obtain a third reconstructed point cloud; and determining a scene reconstruction result corresponding to the first image sequence based on the second reconstructed point cloud and the third reconstructed point cloud. The present disclosure can reduce the implementation cost of scene reconstruction.

The present invention proposes a tutoring intention recognition method and a personalized tutoring method based on tutoring intention, including: S1. preprocessing user question data, and constructing a text representation for tutoring intention based on a constructed keyword list; S2. parsing the latent semantic vector of the user question data using a hierarchical neural network structure model; S3. based on the generated latent semantic vector, using a multi-task learning algorithm to perform tutoring intention recognition. The tutoring intention recognition provided by the present invention is based on multi-task learning and a hierarchical network model, and can effectively deal with the problem that the tutoring intention recognition method in the online tutoring scenario ignores the multi-task learning algorithm and does not fully consider the historical question and answer information.

The invention discloses an unstructured environment cognitive method based on semantic understanding and learning, belongs to the technical field of computer vision, relates to the field of cognitive understanding and semantic representation of a robot on unstructured landforms in extraterrestrial planet surface inspection and detection tasks, and aims to construct a simple and efficient waterfall type semantic segmentation backbone network model. The objective of the invention is to improve the accuracy and effectiveness of geomorphic segmentation of extraterrestrial satellites. The method comprises the following steps: establishing a learning-based binocular stereo matching model for geomorphic geometrical morphology, and parametrically describing geometrical characteristics; aiming at the landform semantic attributes, establishing a semantic segmentation network model based on learning, and classifying and determining the landform semantic attributes; a cascade stereo matching cost function is adopted, so that the matching efficiency is improved; and a waterfall type segmentation network framework is adopted as a semantic segmentation backbone network, so that the matching real-time performance is enhanced.

This application provides a product recommendation method, apparatus, device, medium, and program product, relating to the field of artificial intelligence. The method includes: determining the dynamic characteristics of a customer based on historical data of the customer's use of application software; determining the static characteristics of a customer based on the customer's attribute information; determining the static characteristics of a product based on the product's attribute information; determining the dynamic characteristics of a product based on the product's click and purchase records; pairing the customer and product based on their dynamic and static characteristics to obtain customer-product pairs; inputting the dynamic and static characteristics of the customer-product pairs into a pre-trained matching probability determination model to obtain the matching probability of the customer-product pairs; and recommending products to the customer based on the matching probability of each customer-product pair. This application accurately characterizes the features of customers and products through dynamic and static dual-dimensional information. Based on this, the matching results of customers and products are input into the model, resulting in more accurate and reliable matching probabilities.

The invention discloses an unmanned aerial vehicle sound recognition method and device, electronic equipment and a storage medium. The method is characterized by comprising the following steps: carrying out preprocessing and wavelet transformation on collected unmanned aerial vehicle original sound, and determining an unmanned aerial vehicle smooth signal; mel-frequency cepstral coefficient feature extraction is carried out on the unmanned aerial vehicle smooth signal, and sound signal features are determined; performing feature dimensionality reduction and combination on the sound signal features through a principal component analysis method and a linear discriminant analysis method, and determining model extraction features; and performing identification based on the model extraction features through a pre-trained unmanned aerial vehicle identification model, and determining target identification information. The unmanned aerial vehicle is identified and positioned, the accuracy and real-time performance of unmanned aerial vehicle sound identification are improved, and the accurate identification and classification of the unmanned aerial vehicle sound are improved.

The invention provides an abnormal traffic data detection method and system. The detection method comprises the following steps: acquiring real-time traffic data; and inputting the real-time traffic data into an abnormal traffic detection model to obtain target reconstruction data of the real-time traffic data, the abnormal traffic detection model comprising a coding layer, at least one time domain convolutional network layer, at least one attention mechanism layer and a decoding layer which are arranged in sequence, each time domain convolutional network layer of the at least one time domain convolutional network layer and each attention mechanism layer of the at least one attention mechanism layer are alternately stacked; whether the real-time traffic data is abnormal traffic data or not is determined based on a comparison result of the target reconstruction data and the threshold data, so that when a new category of abnormal traffic data appears at different times, the anomaly detection model can identify the abnormal traffic data, meanwhile, a good detection effect is achieved in the traffic data of a known category at any time, and in addition, the detection efficiency is improved. The calculation capability and memory of the abnormal traffic data detection model should be fixed or slowly increased along with the increase of the number of categories.

The present invention relates to the technical field of high voltage and insulation and discloses a cross-linking performance consistency characterization method for 500 kV cross-linked polyethylene cable insulation material. The characterization method includes the following steps: (1) preparing a standard sample: fully stirring and mixing low-density polyethylene and dicumyl peroxide at 63-67°C, and standing to fully diffuse the dicumyl peroxide into the low-density polyethylene; (2) testing, by using a torque rheometer, a cross-linking reaction kinetic curve of the standard sample and a sample to be tested; and (3) eliminating, by using a standard sample transformation method, a difference introduced due to different test places into the cross-linking reaction kinetic curves of the sample. By using the method, cross-linking reaction properties of the 500 kV cross-linked polyethylene cable insulation material are effectively characterized, thereby solving the problem of accurate comparison of results at different test places.

A monocular image-based three-dimensional lane line detection method, device and medium, two-dimensional semantic features are extracted from a monocular lane image, and three-dimensional perception features are obtained by using a pre-trained deep model; two-dimensional semantic features and three-dimensional perception features are fused, an initial lane query is enhanced, and a query representation for three-dimensional lane line prediction is obtained; the query representation is iteratively decoded layer by layer, the sampling offset in the decoding process is dynamically adjusted based on the uncertainty parameters obtained by decoding, and the two-dimensional semantic sampling values and three-dimensional perception sampling values obtained by sampling in the decoding process are adaptively weighted and fused to obtain a three-dimensional lane line prediction result; the detection network is trained and constrained based on geometric structure constraints, and the final three-dimensional lane line detection result is output. The present application improves the spatial perception ability, prediction stability and lane structure rationality of monocular three-dimensional lane line detection in complex road scenes without relying on additional depth sensors and depth labeling information.

The application discloses a land survey quality monitoring system for remote sensing image intelligent segmentation and ground object identification, relates to the technical field of remote sensing, and comprises an image identification module, a label comparison module and a monitoring module. Specifically, remote sensing images of land to be monitored are acquired through a remote sensing sensor, image regions are divided through structural complexity analysis, and the category probability vectors of the pixel positions of each region in the formed non-uniform region set are analyzed and acquired to construct a label map of the whole remote sensing image. Pixel-by-pixel category comparison is performed on the current label map and a reference label map to form a change mask map. Structural change regions are identified according to the change mask map. Through time sequence analysis, it is determined whether the corresponding candidate label inconsistent regions under different time phases are still structural change regions to acquire a judgment result. Based on the judgment result, an electronic map is updated.

The present invention proposes an epileptic EEG recognition method based on an enhanced deep TSK fuzzy classifier. In the TSK fuzzy classifier (ED‑TSK‑FC), the original EEG signal is used as input data, and deep feature learning of the epileptic EEG signal is performed through a one-dimensional convolutional neural network. The deep features of the hidden layer and the potential category information of the output layer can be obtained through layer-by-layer neural expression, and the deep features and the potential category information are merged into enhanced deep features. In addition, the enhanced deep features are used as training variables for the antecedent and consequent parts of the ED‑TSK‑FC fuzzy rules. In the antecedent part, a fuzzy clustering algorithm is used to fuzzily divide the enhanced deep feature space and obtain the corresponding antecedent parameters, and the ridge regression extreme learning algorithm is introduced in the consequent part to learn the parameters. The enhanced deep features make fuller use of the useful information of 1D‑CNN and improve the classification performance of ED‑TSK‑FC. Based on the high interpretability of fuzzy rules, ED‑TSK‑FC makes a good explanation of the enhanced deep features.