97 results about "Learning object" patented technology

A computing system is disclosed for classifying rendered learning-object content and generating structured metadata representing competency and depth-of-knowledge attributes. The system detects rendered instructional content within a user interface and generates a cryptographic hash of the content, which is encrypted with session metadata to form a classification request. The request is transmitted to a remote categorization engine, where the content is processed using embedding models and inference classifiers to determine one or more competency labels, knowledge depth values, and confidence scores. The classification result is encrypted and returned to the client device for interface rendering. Classification records, including feedback interactions and associated metadata, are stored for use in model retraining.

The invention discloses a target-driven navigation method and device based on context awareness and imitation learning, and the method comprises the steps: recognizing an object instance of interest in an image based on a target detector DETR, and constructing an object graph; based on context perception graph reasoning, in the navigation process, dynamic context information such as images, actions and memories serves as guidance, object features are projected to hyperplanes of corresponding contexts by means of a TransH method at each time step, the object relation is dynamically learned, and an intelligent agent can better understand the complex environment. Based on visual representation of Transform, visual features and graph features are fused, and spatial semantic information of the environment is better captured. Based on generative adversarial imitation learning, a new dynamic reward function is designed, and an intelligent agent is helped to avoid a deadlock state in combination with environment rewards. Based on a standard asynchronous dominant actor-commentator algorithm, an effective navigation strategy is trained by using a new reward function, and the navigation success rate and efficiency of the intelligent agent in an unfamiliar environment are improved.

Disclosed is a system to generate an adversarial pattern. The system receives an input specifying data describing a target object, an objective indicating whether to reduce detectability of the target object or to induce a false detection of a target type, and context parameters. The system generates candidate adversarial patterns for the target object using an AI-based generative algorithm. Each candidate adversarial pattern represents a potential solution for achieving the objective under context parameters. The system simulates a representation of the target object with candidate adversarial pattern in a virtual environment that models a plurality of sensor modalities. The simulation may use machine learning object detection models. The system analyzes the target object and generates, for each target object, a performance metric for ranking the candidate adversarial pattern based on an effectiveness of the simulated representation. The candidate adversarial pattern with highest rank is generated as an optimized adversarial pattern.

The invention relates to a monocular 3D target detection method and system based on comparative learning. The method comprises the following steps: S1, performing feature extraction on a monocular image by using a backbone network to obtain a multi-scale feature map; the weight of the backbone network is obtained through a self-supervised training stage; s2, performing visual encoding by using a visual encoder to obtain an encoded visual feature; a depth predictor and a depth encoder are used in sequence to carry out depth coding on the sum to obtain coding depth features; s3, inputting the learnable object query, the coding visual features and the coding depth features into a visual-depth decoder to obtain a final query after learning; s4, mapping the final query into 3D information by adopting a detection head; and obtaining a 3D bounding box of the corresponding target. According to the method, the precision and robustness of 3D target detection are improved.

An information processing device acquires a learning image in which a subject for learning and a color chart appear. The information processing device calculates a correction coefficient for correcting a color appearing in the color chart in the learning image to a reference color as a reference. The information processing device generates learning data in which an image of a portion of the subject for learning in the learning image is associated with the correction coefficient. The information processing device generates a trained model that outputs a correction coefficient for correcting a color of an image in which a subject appears in response to an input of the image based on the learning data.

The invention relates to a self-learning method of a robot with a body based on a pseudo tag and a robot with a body system. The method comprises the steps of generating a state pseudo tag and a component pseudo tag about a to-be-learned object based on interactive multimedia data between a robot with a body and the to-be-learned object; generating a cross-view pseudo-tag about the to-be-learned object based on the state pseudo-tag, the component pseudo-tag 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 tag about the to-be-learned object based on the simulation multimedia data; and verifying the state false label, the component false label, the cross-view false label and the enhanced false label, and training the robot with the body based on the false labels passing the verification. By adopting the method, the richness of the pseudo labels can be improved, and the success rate of interaction tasks of the robot with the body is further improved.

The invention discloses a multi-task learning target tracking method and system based on domain self-adaption, and the method comprises the steps: taking a first frame image provided by a sample video sequence as the image data of a source domain and a target domain, employing a large and small target decision mechanism, carrying out the online selection of the scale of a model, and carrying out the feature extraction of the image data through a deep network; establishing a multi-task learning objective function fusing shallow and deep features; regarding a target tracking task as a field adaptive optimization problem under a multi-task learning framework, constructing a global target function fusing cross-domain sparse reconstruction constraint, multi-task loss and field adaptive loss, and obtaining a model after adaptive target tracking demand optimization; utilizing the optimized model to construct a likelihood function to obtain the probability density of the target position; determining a final tracking result of the target according to the probability density, the historical information and the predicted position of the linear motion model; according to the method, the accuracy and robustness of target tracking are effectively improved, and the method has relatively high application value and practicability.

This invention proposes a 3D semantic scene completion method based on hierarchical grouping and aggregation. The model proposes a novel dual-branch structure. The explicit constraint branch starts with the overall 3D scene features, focusing on regional aspects of the scene and aggregating explicitly similar features into grouped regional features. The implicit diffusion branch starts with the visible voxel query suggestions output by the query suggestion network, focusing on the details of objects in the scene and learning the implicit fine-grained features of the objects. A hierarchical grouping module is also proposed, which divides the 3D space into multiple sub-regions and performs similarity calculation and aggregation on the voxel features within each region, thereby generating a compact regional feature representation. This grouping method can focus on the local regions of specific objects in the scene, avoiding mutual interference from features of independently distributed objects in the distance, thus extracting more detailed and accurate semantic features.

Systems and methods for object detection can include obtaining one or more images and processing the one or more images with a machine-learned object detection model to generate one or more bounding boxes and one or more object classifications. The object detection model may perform atrous convolution, feature fusion, feature map generation, and prediction based on feature extraction.

The invention discloses a course recommendation method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a recommendation score of each course; sorting the courses according to the recommendation scores of the courses; and recommending the courses according to the sorting sequence of the courses. According to the technical scheme, the recommendation score of each course is determined; according to the method, the curriculums are sorted according to the recommendation scores of the curriculums, and finally, curriculum recommendation is performed according to the sorting order of the curriculums, so that when curriculum recommendation is performed on the object, the curriculum quality of the recommended curriculums can be ensured as much as possible, and the influence of the curriculum click rate on recommendation is reduced; and finally, the course learning quality of the learning object is ensured.

An object detection model and relationship prediction model are jointly trained with parameters that may be updated through a joint backbone. The offset detection model predicts object locations based on keypoint detection, such as a heatmap local peak, enabling disambiguation of objects. The relationship prediction model may predict a relationship between detected objects and be trained with a joint loss with the object detection model. The loss may include terms for object connectedness and model confidence, enabling training to focus first on highly-connected objects and later on lower-confidence items.

Machine learning device (2) which learns a correlation between shipping control information (X1n) obtained by checking an object during its shipping and operational alarm information (X2n) issued during the operation of the object, and which includes: - a condition monitoring unit (21) that monitors the shipping control information (X1n) and the operational alarm information (X2n) as data input from an environment (1), and - a learning unit (22) which generates a learning model based on the shipping control information (X1n) and operational alarm information (X2n) monitored by the condition monitoring unit (21), wherein the object includes a motor the environment (1) comprises an engine control device (11) that controls the engine during its shipment and outputs the shipping control information (X1n), and an engine control device (12) that gives an alarm during the operation of the engine and outputs the operating alarm information (X2n), The shipping control information (X1n) includes control element results associated with a motor model and motor inspection date, an insulation resistance value, an earth resistance value, a current value and / or a switching impulse voltage for the motor, and The operating alarm information (X2n) includes an overcurrent alarm, a noise alarm and / or an overload alarm for the motor.

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.

Systems and methods for generating performance metrics for autonomous vehicle systems are provided. The performance metrics include two complementary metrics that evaluate a machine-learning object prediction model relative to a number of potential trajectories of an autonomous vehicle. The performance metrics include an avoidance metric that quantifies a probability that a region occupied by a real-world or simulated object is reached by the autonomous vehicle, the region is not blocked by another object, and the region is not blocked by a prediction output by the machine-learning object prediction model. The performance metrics also include an availability metric that quantifies a probability that a simulated or real-world object is not located within a region, the region is not blocked by another simulated or real-world object, and the autonomous vehicle is unnecessarily blocked by the prediction output before the autonomous vehicle reaches the particular footprint.

The invention discloses a speech partner training method and device, a storage medium and a terminal, and the method comprises the steps: obtaining speech information of a user for a target speech theme, and inputting the speech information into an evaluation optimization large model; the speech information is evaluated from a preset dimension through an evaluation optimization large model, an evaluation result of the speech information is obtained, and the preset dimension comprises at least one of speech content, voice performance and body language; and optimizing the speech information based on the evaluation result to obtain a speech example corresponding to the speech information. When the speech information of the user is evaluated, not only is voice performance considered, but also multiple dimensions such as speech content and limb performance are covered, and more detailed and comprehensive evaluation of the speech information is realized; and an optimized speech example is generated after the evaluation result is obtained, so that a visual learning object can be provided for the user, and simulation and improvement of the user are facilitated.

The invention relates to an apparatus for generating shape data of an object and a method for generating shape data of an object. A computer device (1) is provided with: a first arithmetic unit (10) that outputs a numerical value obtained on the basis of coordinate values of object points indicating the positions of each part of the shape of an object; and a second calculation means (20) that, when a numerical value is input, outputs coordinate values of object points indicating the positions of the respective parts of the shape of the object and physical quantities at the respective object points such that coordinate values of learning object points indicating the shape of the learning object match the coordinate values of the object points output by the second calculation means. The second arithmetic unit learns the physical quantity output by the second arithmetic unit so as to satisfy an equation indicating the physical law that the physical quantity should satisfy, and the learned second arithmetic unit outputs the coordinate value of the object point and the physical quantity following the physical law on the basis of the input numerical value.

The application discloses an experience learning method and device for automatic driving of a vehicle, and comprises the following steps: obtaining sensor data through a vehicle perception system; obtaining surrounding vehicle motion data through the sensor data; analyzing the surrounding vehicle motion data to obtain an optimal learning object vehicle; taking target vehicle motion data corresponding to the optimal learning object vehicle as a training set to perform model training, and obtaining an abnormal driving behavior mode; updating a vehicle automatic driving model according to the abnormal driving behavior mode; and generating a real-time driving strategy based on the updated vehicle automatic driving model. The automatic driving vehicle can learn the behaviors of surrounding vehicles to improve its own behaviors, so that the automatic driving vehicle can learn abnormal events, and the adaptability and robustness of the automatic driving vehicle itself are improved.

A method may include receiving training data comprising a plurality of RGB-D images of an object at a plurality of time steps, and a plurality of robot actions associated with the object at the plurality of time steps; and optimizing, using the training data, a dynamics function to predict a future state of the object based on a current state of the object and a robot action. A state of the object is estimated as a plurality of particles comprising 3D Gaussians using particle filtering.

An object detection model and relationship prediction model are jointly trained with parameters that may be updated through a joint backbone. The offset detection model predicts object locations based on keypoint detection, such as a heatmap local peak, enabling disambiguation of objects. The relationship prediction model may predict a relationship between detected objects and be trained with a joint loss with the object detection model. The loss may include terms for object connectedness and model confidence, enabling training to focus first on highly-connected objects and later on lower-confidence items.

This invention relates to a method for reconstructing existing building information models based on image target detection and unmanned aerial vehicles (UAVs), comprising the following steps: acquiring images of the four facades of a target building taken by a UAV; employing a deep learning object detection model (YOLO V9) to obtain a detection map containing window detection boxes and center point markers, window position information, and window size information; determining the correspondence between the pixel length captured in the image and the actual length; performing edge detection processing on the detection map, and combining the correspondence to obtain the boundary position information of the walls and the actual coordinates of the windows based on the walls; performing parametric modeling of the building envelope based on the boundary position information of the walls, while simultaneously acquiring the building's floor information and the floor plan layout of each floor, thus completing the reconstruction of the entire building information model. Compared with existing technologies, this invention can quickly and easily identify the position and size of the building envelope, thereby facilitating modeling, and has a certain degree of automation and low cost.

Disclosed is a method for enhancing learning efficiency in digital or physical learning environments. The method being implemented using a Learning Object Sequencer (LO-SEQ) system. The method includes scheduling a learning object (LO) to be presented to a learner in at least one of a plurality of modalities. A very short priming object (vs-PO) is presented as a priming stimulus, wherein the vs-PO is semantically or conceptually related to the scheduled LO to be subsequently presented. The scheduled LO is subsequently presented after a predefined time period of presenting the vs-PO.

A model learning facility (1) comprises a fixed branch selection unit (16) that selects fixed branches as branches to be excluded from learning objects from a plurality of branches contained in a learning model; a computation graph modification unit (13) that modifies a computation graph to be used into one derived from a first computation graph utilizing the plurality of branches and a second computation graph utilizing learning object branches obtained by excluding the fixed branches from the plurality of branches; an inter-branch distance computation unit (11) that computes distances between branches, including distances between features generated by each of the plurality of branches, in a state where the computation graph to be used has been modified into the first computation graph; and a loss function computation unit (12).which calculates a total sum of losses based on a predetermined loss function and the distances between branches, a branch update unit (14) that updates weight parameters in the learning object branches based on the total sum of losses in a state in which the computation graph to be used has been modified to the second computation graph.

The invention discloses a multi-scale feature learning target detection method and device, and the method comprises the steps: obtaining a to-be-detected image, inputting the to-be-detected image into a trained target detection model, and obtaining a target detection result; according to the multi-scale feature learning target detection method and device, the target detection model is constructed through the multi-scale convolution extraction module, the pyramid feature fusion module and the detection result module, so that the target detection capability and the cross-scene rapid adaptation capability are greatly improved while real-time reasoning of the target detection model is realized; in the training process of the target detection model, multiple sub-data sets are used for training, and model parameters are averaged, so that the problem that the model parameters converge to a local optimal solution can be effectively solved, and an algorithm model with better target detection capability is obtained; in the incremental training stage, only a small number of parameters need to be trained, new target categories and application scenes can be rapidly adapted without changing the network structure, and the generalization ability and scene adaptability of the target detection model are greatly improved.

The invention provides an adaptive learning system and method based on a knowledge graph in an artificial intelligence vision field, and the method comprises the steps: extracting knowledge association of a learning object among different tasks from multi-source behavior data, positioning a corresponding knowledge node in a preset knowledge graph, and generating a cognitive path of the learning object in the knowledge graph; understanding deviations of the learning object during migration among different knowledge nodes are screened out according to the cognitive path, and then all the understanding deviations are converted into cognitive offset degrees of the learning object in the learning process; determining the learning robustness of the learning object when the knowledge structure changes based on the interaction feedback data; determining the potential ability deviation of the learning object for learning through the cognitive offset degree and the learning robustness; and when the potential capability deviation is greater than a preset capability threshold, adaptively adjusting a learning path weight in the knowledge graph. By adopting the scheme, refined cognitive modeling of the knowledge migration process can be realized in a complex and changeable learning behavior environment.

The invention provides a teaching information generation method and device, and relates to the technical fields of artificial intelligence, natural language processing, knowledge maps and the like. According to the specific implementation scheme, the method comprises the steps of updating an object portrait of a learning object based on current learning interaction data of the learning object and a knowledge graph to obtain an updated object portrait; in response to detecting that the updated object portrait does not conform to the risk control rule based on the learning interaction data, generating and sending first teaching content information of the new node based on the learning interaction data, the updated object portrait and the knowledge graph; acquiring next learning interaction data; and in response to the detection that the next learning interaction data does not meet the node learning target, taking the next learning interaction data as the current learning interaction data, taking the updated object portrait as the object portrait, updating the object portrait, and continuing to obtain the next learning interaction data. And the next learning interaction data is detected to meet the node learning target.

A model learning device (1) is provided with: a fixed branch selection unit (16) that selects, from among a plurality of branches included in a learning model, a fixed branch that is a branch excluded from a learning object; a calculation graph changing unit (13) that changes the used calculation graph to either a first calculation graph using a plurality of branches or a second calculation graph using a learning target branch obtained by excluding a fixed branch from the plurality of branches; an inter-branch distance calculation unit (11) that calculates an inter-branch distance including the distance between features generated by each of the plurality of branches in a state where the used calculation graph is changed to the first calculation graph; a loss function calculation unit (12) that calculates the sum of losses on the basis of a predetermined loss function and the inter-branch distance; and a branch update unit (14) that, in a state in which the used calculation graph is changed to the second calculation graph, updates the weight parameter within the learning target branch on the basis of the sum of the losses.

The present invention provides a server device, a learning assistance method, and a recording medium, which can immediately and easily confirm and effectively learn to what extent a sentence set by oneself as a learning object is searched by other users. When a user attribute of a summary object is set in a communication terminal, a user specifies a sentence and instructs "sentence search", a learning assistance server (10) searches the specified sentence with an encyclopedia, and determines whether the specified sentence is included in the top of a search ranking and whether the specified sentence is included in the top of an average search frequency ranking based on search history data of the summary object. When the specified sentence is included in the top of the search ranking, the server (10) displays a message (M1) notifying of the top of the search ranking in the summary object together with a search result of the specified sentence in the communication terminal (20), and when the specified sentence is included in the top of the average search frequency ranking, a message (M2) notifying of the top of the average search frequency ranking in the summary object is displayed.

A model learning device includes processing circuitry to select fixed branches, as branches to be excluded from learning objects, to modify a calculation graph to be used into one of a first calculation graph that uses the plurality of branches and a second calculation graph that uses learning object branches obtained by excluding the fixed branches from the plurality of branches, to calculate inter-branch distances, including distances between features respectively generated by each of the plurality of branches, in a state in which the calculation graph to be used has been modified to the first calculation graph, to calculate a sum total of losses based on a predetermined loss function and the inter-branch distances, and to update weight parameters in the learning object branches based on the sum total of losses in a state in which the calculation graph to be used has been modified to the second calculation graph.

A sorter device includes a feed system, a detection system including at least one launch device and at least one optical sorter, an ejector, and a computing device operably coupled to the detection system and the ejector. The computing device includes instructions thereon that, when executed by the at least one processor, cause the image processing system to generate image data such that the communication interface displays an output image based on the image data, causing the communication interface to receive a user input comprising tagged data of at least some pixels of an object defining the merchandise in the output image to generate training data, and training a machine learning object sorter model based on the training data. Related sorter apparatus and methods are also disclosed.