13 results about "Learning object" patented technology

A visual model-based intelligent personnel restriction method for mines prone to rockbursts, belonging to the field of coal mine safety monitoring and computer vision technology, comprises the following steps: 1. Acquiring and preprocessing real-time video stream data from mine roadways; 2. Extracting personnel identity features from the preprocessed video stream data based on a deep learning object detection model; 3. Performing cross-frame association and continuous tracking of detected personnel based on a multi-target dynamic tracking algorithm; 4. Extracting the foot tracking points of the tracked personnel and determining their entry / exit directions and counting personnel based on a preset polygonal target area; 5. Integrating personnel flow statistics and implementing graded early warning for personnel restriction at the working face. This invention, through the above method, can effectively reduce the risk of rockburst disasters and ensure the safety of underground workers and mine production.

This invention discloses a method for monitoring the number of trees in a region based on a cross-scale nested model. The method includes: regional partitioning and quadrat layout based on satellite remote sensing data; acquiring UAV imagery of the quadrats, automatically identifying and counting the number of trees within each quadrat using a deep learning object detection model, and generating quadrat labels; extracting the corresponding satellite multidimensional features of the quadrats and aggregating them to the quadrat scale; constructing and training a machine learning regression model using the quadrat feature vector as the independent variable and the quadrat label as the dependent variable; and applying the trained model to global satellite feature data to achieve spatial inversion and mapping of the number of trees in the region. This invention, through a two-layer nested architecture of UAV deep learning and satellite machine learning, achieves a scale conversion from high-precision quadrat calibration to high-efficiency regional inversion, solving the problems of high cost and low efficiency of traditional survey methods, as well as insufficient accuracy of single remote sensing methods.

This invention relates to an image data generation apparatus, an image data generation method, and a computer program. The image data generation apparatus includes: an object acquisition unit that acquires a learning object created as CG (Computer Graphics); a virtual space generation unit that generates a virtual space in which the learning object is arranged; a background setting unit that sets a background image captured in physical space as the background in the virtual space; and an image data generation unit that generates image data using a captured image obtained by capturing the learning object arranged in the virtual space.

The application relates to a pseudo-label generation method and a robot system for embodied robot self-learning. The method comprises the following steps: acquiring interactive multimedia data between an embodied robot and a to-be-learned object; determining state multimedia data from the interactive multimedia data; the state multimedia data reflects state changes of the to-be-learned object in the interaction process with the embodied robot; performing motion decomposition on the state multimedia data to obtain part multimedia data of key parts of the to-be-learned object, and generating part pseudo-labels about the to-be-learned object based on the part multimedia data; generating state pseudo-labels for reflecting the state changes of the to-be-learned object based on the state multimedia data; generating object pseudo-labels about the to-be-learned object based on the state pseudo-labels and the part pseudo-labels; and the object pseudo-labels are used for learning and training of the to-be-learned object by the embodied robot. The method can improve the quality of the pseudo-labels, and further improve the task success rate of the embodied robot.

This invention discloses a 3D object reconstruction method using a multimodal symmetric adversarial network, comprising: S210, using a symmetric learning network to learn the symmetry of the object from the voxel representation of the object's single-view depth image, generating coarse 3D voxels; then using a voxel encoding network and a planar encoding network to learn latent features from the coarse 3D voxels and voxel representations respectively; concatenating the latent features to obtain a latent vector; and finally using a decoding network to generate a target 3D voxel from the latent vector; S220, embedding the generated target 3D voxel and the real 3D voxel into the voxel encoding network, planar encoding network, and point cloud encoding network of a multimodal discriminator, respectively, to help the MSANet model generate more details under the multimodal discriminator loss that integrates voxel, point cloud, and planar losses. According to the technical solution of this invention, more accurate 3D structures can be predicted.

The application discloses an online education path optimization method and system based on Socrates learning condition four-tuple perception, which comprises the following steps: constructing a dialogue graph containing time, question and follow-up question relationship, and establishing a learning condition four-tuple extraction model to convert unstructured dialogue into structured information such as learning object, dimension, student original evidence and learning condition polarity; fusing emotion, cognitive and behavioral characteristics to generate a multi-modal unified learning condition state vector; calculating action utility based on a strategy action set, selecting the optimal teaching strategy, and performing path optimization when the trigger condition is met; constructing a knowledge point level vector through global learning condition aggregation, combining a multi-objective comprehensive function and a group iterative search algorithm to generate a personalized learning path, and adjusting the strategy parameter set in a closed loop. The application realizes closed-loop adaptive teaching of dialogue collection, state estimation, strategy selection, path optimization and re-dialogue, improves the accuracy of card point identification and the effectiveness of teaching intervention, and is suitable for online education scenarios.

The application discloses a content processing method, device, medium and equipment, comprising: obtaining delivery effect data, obtaining the identification of a target user and delivery effect slice data according to the delivery effect data; obtaining operation behavior data, obtaining first behavior data and second behavior data according to the operation behavior data and the identification of the target user; generating a first behavior strategy by analyzing the first behavior data; training a machine learning model according to the second behavior data and the delivery effect slice data to obtain a second behavior learning model, wherein the second behavior learning model represents a second behavior strategy; creating content based on the first behavior strategy, or adjusting content or adjusting the content delivery state based on the second behavior strategy. The application takes excellent operators as learning objects, analyzes their behavior patterns, and uses the behavior strategy obtained by learning analysis to effectively improve the content processing effect and the content delivery effect.

In learning the attribute information of the subject, the learning range can be flexibly changed. [Solution] The area of ​​interest reception unit 41 accepts the user's area of ​​interest setting. The feature data management unit 43 holds feature data that is determined according to the position of the object being photographed, serves as input to the learning model, and is subject to updating through learning. The feature data management unit 43 includes a hash function calculation unit 430 that outputs a hash value as input to position coordinates, and a table 431 that holds feature data linked to the hash value output by the hash function calculation unit 430. When a new learning area is set, the feature data held in the table 431 is changed to different data linked to the hash value output when the position coordinates included in the newly set learning area are input to the hash function calculation unit 430.

The application relates to a pseudo-label-based embodied robot self-learning method and an embodied robot system. The method comprises the following steps: generating a state pseudo-label and a component pseudo-label about a to-be-learned object based on interactive multimedia data between an embodied robot and the to-be-learned object; generating a cross-view pseudo-label about the to-be-learned object based on the state pseudo-label, the component pseudo-label and the interactive multimedia data; performing motion simulation on the to-be-learned object based on the interactive multimedia data to obtain simulation multimedia data of the to-be-learned object, and generating an enhanced pseudo-label about the to-be-learned object based on the simulation multimedia data; verifying the state pseudo-label, the component pseudo-label, the cross-view pseudo-label and the enhanced pseudo-label, and training the embodied robot based on the verified pseudo-labels. The method can improve the richness of the pseudo-labels, and further improve the success rate of interactive tasks of the embodied robot.

The application provides an adaptive learning system and method based on a knowledge graph under artificial intelligence vision, which extracts the knowledge correlation of a learning object between different tasks from multi-source behavior data, locates the corresponding knowledge nodes in a preset knowledge graph, and then generates the cognitive path of the learning object in the knowledge graph; according to the cognitive path, the understanding bias of the learning object when migrating between different knowledge nodes is screened out, and then all the understanding biases are converted into the cognitive shift degree of the learning object in the learning process; the learning robustness of the learning object when the knowledge structure changes is determined based on the interactive feedback data; the potential ability bias of the learning object is determined by the cognitive shift degree and the learning robustness; when the potential ability bias is greater than a preset ability threshold, the learning path weight in the knowledge graph is adaptively adjusted. By adopting the scheme, fine cognitive modeling of the knowledge migration process can be realized in a complex and changeable learning behavior environment.

This invention discloses an automatic counting method and system for mine water exploration and drainage drill rods based on static geometric calibration, belonging to the field of computer vision technology. The method includes: S1: In the static calibration stage, extracting the position information of the drill rod and drilling rig from real-time images of the work site using a deep learning object detection algorithm; S2: Obtaining the drilling rig's operating direction vector based on the position information, obtaining the boundary direction vector of the work area based on the drilling rig's operating direction vector, and obtaining area determination rules based on the boundary direction vector of the work area; S3: Obtaining counting rules based on the work area dwell time mechanism, obtaining valid counting rules based on the counting rules and the area determination rules, and obtaining the number of drill rod operations based on the valid counting rules. This invention solves the technical problem that existing technologies struggle to improve counting accuracy, leading to low operational safety.