976 results about "Object based" patented technology

The invention provides a risk conduction prediction method and system based on combined deduction of a time sequence diagram and a large model, and relates to the technical field of artificial intelligence and knowledge engineering, and the method comprises the steps: extracting a prospective time sequence fact based on a hierarchical cue word and a structured constraint mechanism; extracting conflicts and generating a sequential relationship; the historical time sequence knowledge graph is updated based on the time sequence relation and a confidence coefficient weighted updating strategy; determining a central entity, and initiating a structured query to the updated historical time sequence knowledge graph by taking the central entity as a starting point to generate a context knowledge sub-graph; converting the context knowledge sub-graph into a natural language description with a logic relationship, injecting a risk hypothesis event, constructing a cue word as a new input of a large model, and outputting to obtain a structured JSON object containing a complete reasoning chain; and converting the structured JSON object based on a risk path extraction and visualization algorithm influencing weight attenuation to obtain risk early warning information and a visual conduction path diagram.

Apparatuses, systems, and techniques to use one or more neural networks to perform one or more tasks. In at least one embodiment, said one or more neural networks use one or more textual descriptions to generate one or more three-dimensional (3D) models of one or more first objects based, at least in part, on two or more images of one or more second objects from two or more viewpoints.

The invention discloses a hoisting posture prediction method and device, electronic equipment and a storage medium, and relates to the technical field of hoisting postures and the like. The hoisting posture prediction method comprises the steps that a three-dimensional model of a target object is constructed based on region division of the target object; extracting a key mode based on the three-dimensional model and constructing an attitude reduced-order model; obtaining a gravity parameter based on the current hoisting path; and solving the attitude reduced-order model based on the gravity parameter and a first constraint condition to obtain a hoisting prediction attitude. According to the hoisting attitude prediction method disclosed by the invention, the three-dimensional model of the target object considering the precision and the calculated amount is adaptively established by dividing the region of the target object, and the attitude in the hoisting process is predicted in real time by solving the attitude reduced-order model, so that real-time risk early warning and active protection are realized.

The invention provides a training-free text-image generation method based on a diffusion model, and relates to the technical field of computer graphic processing and artificial intelligence. The method comprises the following steps: extracting semantic phrases and layout information in an input text by utilizing a natural language model, inputting the input text, the semantic phrases and the layout information as additional conditions into a diffusion model, and extracting cross attention maps of different time steps; a positive and negative sample concept and a foreground and background concept based on an object are constructed, a new loss function is calculated on a cross attention map for semantic information and layout information, the loss function combines semantic loss, regional loss and original loss of a diffusion model and is used for updating a potential space image, and the image is generated through iterative denoising and a decoder. According to the method, additional training is not needed, image generation output based on the diffusion model better meets text requirements, and a better text and image alignment effect is achieved.

This disclosure describes systems, methods, and devices related to object detection in images. A device may input an image, representing an object, to a manual labeling learner system; identify, using the system, first coordinates of an upper left corner of a bounding box representing the object based on a heatmap indicative of a probability of the first coordinates representing the upper left corner; identify, using the system, second coordinates of a bottom right corner of the bounding box based on the first coordinates and a first distance regression map indicative of coordinate differences between the second coordinates and ground truth coordinates input to the machine learning model as training data; generate, using the system, adjustments to the first coordinates and the second coordinates based on a second regression map; and generate, using the system, the adjusted first and second coordinates, the bounding box.

Apparatuses, systems, and techniques are presented to introduce noise or variation into images. In at least one embodiment, one or more neural networks are used to determine noise to be added to one or more images of one or more objects based, at least in part, upon one or more features of the one or more objects.

The invention discloses an object three-dimensional reconstruction method, device and system based on deep learning. The reconstruction method comprises the following steps: acquiring a multi-view color image of an object through a controllable image acquisition device; reconstructing a sparse three-dimensional point cloud by using a motion recovery structure method and obtaining a camera pose; initializing parameters of the three-dimensional Gaussian sputtering model based on the sparse point cloud and performing training optimization; a target object semantic segmentation data set is constructed, and a low-rank adaptive technology is adopted to finely segment all models; generating prompts through an open vocabulary detection model at each view angle, obtaining an accurate segmentation mask, and optimizing a three-dimensional segmentation weight by adopting a joint loss function fusing color consistency loss and edge perception loss; and finally outputting the color three-dimensional point cloud of the target object. According to the method, the original image is segmented, so that the influence of the quality of the rendered image is avoided; the segmentation precision of the model in a specific scene is improved through field adaptive fine tuning; and the accuracy of the segmentation boundary is ensured by adopting a double-loss joint optimization mechanism.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as robot agent decision making, financial science and technology and medical health, and discloses an operation control method, device, equipment and medium based on an object flow sequence. The method comprises the following steps: exploring a mapping relation between an object flow sequence and an execution equipment action sequence in a simulation environment, generating a flow conditional action strategy, inputting a target object flow sequence to generate an initial execution equipment action sequence, tracking a real-time motion state of a target object to obtain a real-time object flow sequence, and comparing the real-time object flow sequence with the target object flow sequence. And dynamically adjusting the action sequence of the execution equipment based on the deviation. According to the method, the object flow and execution equipment action sequence mapping is constructed, and real-time object flow tracking and dynamic adjustment are combined, so that the influence of operator difference and environment uncertainty is reduced, and the operation accuracy and universality of the robot are improved.

An apparatus comprising an interface and a processor. The interface may be configured to receive pixel data. The processor may be configured to process the pixel data arranged as video frames, perform computer vision operations on the video frames to detect objects in the video frames, analyze characteristics of the objects detected, determine adaptive auto-exposure weightings in response to the characteristics of the objects detected, generate an auto-exposure weighting table based on the adaptive auto-exposure weightings and generate output video frames. Auto-exposure for the output video frames may be determined in response to the auto-exposure weighting table and the video frames. The auto-exposure weighting table may be generated for each of the video frames.

Various embodiments of the present disclosure provide prompt engineering and iterative, feedback-based generative techniques that improve traditional LLM technology, including extractive LLM techniques. The techniques may include generating, using a machine learning classification model, a resolution capability classification for an input data object that comprises an input question and an input document; generating using a large language model (LLM), an initial predictive output for the input data object based on an initial generative model prompt for the input data object; identifying a classification model output divergence based on a comparison between the resolution capability classification and the initial predictive output; and in response to the classification model output divergence: generating an augmented generative model prompt by modifying the initial generative model prompt with a representation of the resolution capability classification, and generating, using the LLM, an updated predictive output based on the augmented generative model prompt.

The invention discloses an unmanned simultaneous positioning and mapping method and device, a medium and equipment, and relates to the technical field of computers, and the method comprises the following steps: obtaining image data of the surrounding environment of unmanned equipment, carrying out semantic segmentation through employing an improved semantic segmentation model, and determining the semantic information of each pixel; acquiring multi-frame point cloud data, and performing distortion correction on the multi-frame point cloud data by performing pre-integration on the inertial measurement unit data; projecting each frame of point cloud data to the time-space synchronized image data, and determining a semantic tag of a three-dimensional point in each frame of point cloud data; removing three-dimensional points of the dynamic object according to the speed and the space overlapping degree; and optimizing a surrounding environment map and a pose map of the unmanned equipment by selecting a key frame and a loopback candidate frame. According to the method, the semantic segmentation technology and the laser radar inertial odometer are fused for positioning and mapping, so that the positioning and mapping precision in a dynamic similar environment is greatly improved.

A system and method for measuring the position of a moving object based on AI, which provides location and distance information of a moving object to a user using artificial intelligence-based image analysis and distance measurement. Accordingly, the system for measuring the position of an AI-based moving object includes a first camera that captures a first object, a second camera installed around the location where the first object has moved and captures the first object and a second object associated with the first object, and a rangefinder for measuring a first distance between the first object and a distance measurement reference position and a second distance between the second object and a distance measurement reference position; and an object monitoring device that calculates a position value of the first object and a position value of the second object using the first and the second distances measured by the rangefinder.

The invention provides a data processing method and a related device. The method comprises the steps of determining a first index value based on a first text and a second text; the first text is a session text of a first object and a second object generated by a first model, and the second text is a session text of a third object and the second object; the first index value is used for representing the session quality of the first object and the second object; determining a second index value based on the session response duration of the first object and the second object; the second index value is an index value used for representing the session response speed of the first object; determining an evaluation score for the first model based on the first index value and the second index value; and determining a text generation model matched with the first object based on the evaluation score. Through the method, the text generation effect of the text generation model corresponding to the first object can be improved.

The invention provides an information recommendation method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining a vector combination; performing dimension reduction based on the vector combination to obtain a first output vector; performing attention coding based on the first multi-modal feature vector to obtain a first weight coefficient set corresponding to the first multi-modal vector, and determining a second output vector representing the individual interest of the target object based on the first weight coefficient set; performing feature extraction on the first multi-modal feature vector to obtain a third output vector representing the group interest of the group to which the target object belongs; determining recommendation parameters based on the first output vector, the second output vector and the third output vector; and determining a target recommendation object for the target object from the plurality of candidate objects based on the plurality of recommendation parameters corresponding to the plurality of candidate objects. According to the method and the device, the target recommendation object can be determined from multiple dimensions, and the recommendation accuracy is improved.

Disclosed herein are system, method, and computer program product aspects for semantic search in a model-based prompt builder system. A system generates a search retriever object based on a search index comprising unstructured data. The search retriever object includes metadata specifying one or more details of a vector search operation to be performed on the search index. The system obtains search results by performing the vector search on the search index based on the one or more details of the vector search operation provided by the search retriever object and a search query. The system provides the search results to a prompt generator configured to use a model to generate a reply to a prompt request requiring the search results.

The invention provides a shader dynamic modification method, a graph rendering method and device and related equipment, and the method comprises the steps: obtaining creation parameters in a resource creation interface when it is detected that a graph processing application calls the resource creation interface, and the resource creation interface is used for creating a pipeline state object, the creation parameter comprises a plurality of shaders, and the plurality of shaders are expressed in the form of a first intermediate language code; under the condition that a to-be-modified first shader exists in the creation parameters, in response to a modification operation on the first shader, determining a modified second shader; a second pipeline state object is created according to the second shader, and the second pipeline state object is used for calling a graphic interface event by the graphic processing application and executing a graphic rendering task of the graphic interface event. According to the embodiment of the invention, the method can achieve the dynamic modification of the shader, and improves the modification efficiency and flexibility of the shader.

The invention discloses an object pose estimation method based on deep learning and synthetic data and related equipment, and belongs to the technical field of computer vision. The method comprises the following steps: generating an instance segmentation and pose estimation synthesis data set by utilizing simulation modeling software and an automatic script; a YOLO11-seg model is trained, and a data set used for training a domain adaptation model is constructed in an auxiliary mode; training a simulation-to-reality domain adaptation model based on the improved CycleGAN and using the model to enhance the fidelity of the RGB image in the pose estimation synthesis data set; and training a pose estimation model based on multi-modal feature fusion and an attention mechanism by using an enhanced synthetic data set, extracting real scene target foreground RoI data by using YOLO11-seg, inputting the pose estimation model, and outputting a 6D pose of an object. According to the method, the object pose in the disordered scene can be accurately estimated, the grabbing success rate of the robot is improved, the inter-domain difference between synthetic data and real data can be effectively reduced, the data labeling cost is reduced, and the method can be suitable for industrial scenes.

The invention is suitable for the technical field of data query, and provides an index query method and device, electronic equipment and a storage medium, and the index query method comprises the following steps: obtaining a first type of query language statement input by a user; performing grammar analysis on the first type of query language statement based on a predefined grammar rule to generate a corresponding analysis tree; traversing the analytic tree, identifying a query target in the first type of query language statement, and constructing a query semantic object based on the query target, the query target including one or more of an index and a physical table; and according to the query semantic object, generating a second type of query language statement corresponding to the first type of query language statement for an underlying data system to perform index query. According to the scheme, by introducing the query semantic object and supporting mixed recognition and processing of the index and the physical table, the problems that in an existing query mode, flexibility is insufficient, dynamic parameters cannot be expressed, and multi-source joint query cannot be supported are solved.

Embodiments of the present disclosure provide a method, device, and medium for training a large scale object foundation model. The method comprises obtaining a training dataset comprising a plurality of subsets for a plurality of object perception tasks, wherein a sample in the training dataset comprises an image with an object, a prompt indicating the object, and labeled object perception information of the image. The method further comprises generating, by the image encoder, an image feature based on the image. The method further comprises generating, by the text encoder or the visual prompt encoder, a prompt embedding based on the prompt. The method further comprises generating, by the object decoder, object perception information of the object based on the image feature and the prompt embedding. In addition, the method further comprises training the object processing model based on the generated object perception information and the labeled object perception information.

The invention provides a 3D modeling feature extraction method and system combined with natural language processing, and relates to the technical field of game development.The method comprises the steps that firstly, text description data containing morphological attributes, spatial relations and surface features of a target object is obtained, multi-level semantic analysis is conducted on the text description data, and a key semantic feature set is extracted; comprising global and local semantic vectors and dynamic context vectors, then generating intermediate representation data comprising geometric contour features, material distribution features and illumination response features of the target object based on the key semantic feature set, and executing three-dimensional topology reconstruction processing according to the intermediate representation data to generate initial 3D model data; and finally, performing multi-stage optimization processing on the initial 3D model data to obtain an optimized 3D model feature set containing geometric smoothness, texture continuity, illumination rendering and physical collision features, thereby improving 3D modeling efficiency and accuracy, and providing an efficient modeling scheme for game development and the like.

Disclosed are methods, systems, and computer program products that present, by a spatial computing system, an extended reality presentation to a user, wherein the extended reality presentation comprises virtual object(s) generated by a spatial computing system and transmitted to one or both eyes of the user and a physical environment that includes a first physical object and a second physical object and is perceived by the user via light reflected from the physical environment. The extended-reality representation is rendered for an object interaction between the first physical object and the first virtual object or the user. A physics-based effect on the first physical object by the object interaction is determined by using at least a stereoscopic model for the first physical object based at least in part upon the object interaction. The extended reality presentation into an undated extended reality presentation based at least in part upon the physics-based effect.

An object of initial unknown position on a map may be determined by traversing through moving and turning to establish motion trajectory to reduce its spatial uncertainty to a single location that would fit only to a certain map trajectory. An artificial neural network model learns from object motion on different map topologies may establish the object's end-to-end positioning from embedding map topologies and object motion. The proposed method includes learning potential motion patterns from the map and perform trajectory classification in the map's edge-space. Two different trajectory representations, namely angle representation and augmented angle representation (incorporates distance traversed) are considered and both a Graph Neural Network and an RNN are trained from the map for each representation to compare their performances. The results from the actual visual-inertial odometry have shown that the proposed approach is able to learn the map and localize the object based on its motion trajectories.

The invention provides a content generation method and device, equipment and a storage medium, and relates to the technical field of computers, in particular to the technical fields of deep learning, large models, agents and the like. According to the specific implementation scheme, a content generation request is received, and a task input object is determined based on the content generation request; determining a task flow based on the task input object, the task flow including a plurality of sub-tasks, the plurality of sub-tasks including at least two independent tasks and at least one dependent task; the execution of the independent task does not depend on the completion of other tasks; the execution of the dependent task depends on the completion of other tasks, and the other tasks are previous tasks of the dependent task; a dependency relationship exists between the previous task and the dependent task; based on the dependency relationship, performing concurrent scheduling and execution on a plurality of sub-tasks in the task process to generate an intermediate result; a content file is generated based on the intermediate result. The content generation efficiency can be improved.

The invention discloses an object group determination method and device, electronic equipment and a storage medium. The embodiment of the invention can be applied to artificial intelligence, and the method comprises the steps: obtaining preset bitmap information and object label information of at least one target object; determining a target bitmap element corresponding to the target object in the preset bitmap information; based on preset object tag information and object tag information of each target object, setting element states of target bitmap elements corresponding to each target object, and obtaining a plurality of set target bitmap elements corresponding to the preset object tag information; aggregating the plurality of set target bitmap elements corresponding to the preset object tag information to obtain object bitmap information; and determining an object group corresponding to the preset object tag information based on the element state of each bitmap element in the object bitmap information. In the embodiment of the invention, the whole bitmap information does not need to be traversed or other data structures do not need to be used. According to the scheme, the efficiency of confirming the object group can be improved.

In various examples, a technique for neural motion control includes generating a first trajectory associated with a first end effector of an articulated object based at least on a first reference trajectory and one or more transformations between one or more reference poses for one or more objects and one or more new poses for the one or more objects. The technique also includes generating a second trajectory associated with a second end effector of the articulated object based at least on a second reference trajectory and the one or more transformations. The technique further includes determining that a task is successfully completed via execution of the first trajectory and the second trajectory and updating one or more parameters of a machine learning model based at least on the first trajectory and the second trajectory to produce a trained machine learning model.

In a general aspect, orientation information is used to generate a unique code. In some aspects, orientation information is extracted from an object. The object includes multiple elements, and the orientation information indicates the relative spatial orientations of the respective elements. The orientation information can be extracted, for instance, by a scanner system that detects the elements. A unique code is generated for the object based on the orientation information. In some examples, the elements are diamond particles that each have one or more color centers, and the orientation information is extracted by detecting the color centers.

The invention relates to a method for boxing objects. The method comprises the steps that a plurality of candidate subspaces in a box body are determined based on the current state of the space in the box body; coding the plurality of candidate subspaces and the size of a first object to be loaded into the box body into a candidate subspace embedding sequence and a first object embedding sequence; performing attention processing on the candidate subspace embedding sequence and the first object embedding sequence to obtain a candidate subspace feature sequence subjected to attention processing and a first object feature sequence subjected to attention processing; and determining a position in the box body for placing the first object based on the attention processed candidate subspace feature sequence and the attention processed first object feature sequence.

The invention provides a data processing method and device based on artificial intelligence, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring an object grid model and a first texture parameter corresponding to the object grid model, and performing deformation processing on the object grid model based on a first weight parameter to obtain a first deformed object grid model; performing rendering processing based on the first deformation object grid model and the first texture parameter to obtain a first rendered object image, and performing image generation processing based on the object description text to obtain a generated object image conforming to the object description text; determining image semantic loss based on the first rendered object image and the generated object image, and updating the first weight parameter based on the image semantic loss to obtain a second weight parameter; and performing deformation processing on the object grid model based on the second weight parameter to obtain a second deformation object grid model. According to the invention, the modeling accuracy of the second deformation object grid model is improved.

A trajectory information processing method includes: generating an object geometry of a first object based on a body shape feature of the first object, the object geometry including a plurality of local geometries, and the local geometries surrounding at least one part of the first object; obtaining object trajectory information of a second object, and migrating the object trajectory information of the second object to the object geometry, to obtain object trajectory information of the object geometry; determining a plurality of collision points at which the local geometries collide during interaction, and determining collision occurrence positions of the plurality of collision points; performing position adjustment to obtain collision avoidance positions of the plurality of collision points; and correcting the object trajectory information of the object geometry based on the collision occurrence positions and the collision avoidance positions, to obtain object trajectory information of the first object.

A system may receive a request to generate an object. A system may generate, based on the request, a first portion of a prompt associated with a first layer of a hierarchy and a second portion of the prompt associated with a second layer of the hierarchy, where the second layer has a lower priority than the first layer. A system may generate the object based in part on providing the portions of the prompt as input to a machine learning model, where the object is formatted according to an object format and is internally consistent. To generate the object the machine learning model does not violate instructions associated with a layer of the hierarchy based on instructions associated with a layer of the hierarchy having a relatively lower priority.