60 results about "Virtual body" patented technology

The invention relates to a rotary inertial navigation digital twinning system and a construction method thereof. The rotary inertial navigation digital twinning system comprises a rotary inertial navigation digital twinning physical model layer, a rotary inertial navigation digital twinning geometric model layer, a multi-source information data acquisition layer, a decision control layer and a diagnosis and prediction analysis layer. Data information collection and transmission of a rotary inertial navigation system entity can be completed, association and interaction between a twin virtual body and the entity are achieved, iterative optimization of model parameters can be achieved through the decision control module, and finally prediction and evaluation of the overall operation state of the system and the performance of the digital twin inertial navigation system are achieved in the diagnosis and prediction analysis module.

The invention discloses an AI assessment method and system for the safety risk of aged furniture, and relates to the technical field of artificial intelligence assessment, and the method comprises the steps: placing a virtual body in a virtual three-dimensional environment, and positioning a mismatching risk point of the body of a user and to-be-assessed furniture through applying simulation disturbance; extracting biomechanical parameters under the risk point and determining a physical risk value; carrying out dynamic deduction through a physiological-psychological state mapping relation based on biomechanical parameters, and determining a psychological stress value; fusing the physical risk value and the psychological pressure value to generate a current safety risk assessment result; based on a virtual body, simulating an elderly weak physiological trajectory, and performing long-term safety risk prediction on furniture in the same virtual three-dimensional environment; according to the method, mechanical disturbance and typical instability working condition simulation are introduced into the virtual three-dimensional environment, so that the safety guarantee level and the prospective evaluation capability of the aged furniture under the real use condition are improved.

The invention discloses intelligent acupuncture and moxibustion equipment based on rosemary-rosemary reflection and a positioning method, relates to the field of intelligent positioning, and is used for solving the problem that the accuracy is reduced due to the fact that a traditional Chinese medicine bone degree division method and a user body type ratio are in a fuzzy relation and positioning of remaining acupuncture points cannot be accurately determined. Preprocessing the images of each partial region of the human body, synthesizing the image definition of each partial region image, the positioning distance difference between the virtual body position and the proportion size and a support vector machine model constructed by a virtual body position acupuncture point position model initial training set, and adjusting the model difference; weighted calculation is carried out through the distance difference between the electrode plate and the preset acupoint position and the preset current difference of the electrode plate, the weighted calculation is compared with the adjusting threshold value, the acupoint positioning accuracy is improved, the application scene of the intelligent acupuncture and moxibustion equipment is improved, and the personalized requirements of different users are met.

The invention discloses a transformer substation global digital twinborn fusion system, which comprises a data fusion module, a model fusion module and an artificial intelligence fusion module, and is characterized in that the data fusion module is used for collecting multi-source data of a transformer substation, preprocessing the data and performing data fusion on the preprocessed data; the model fusion module is used for constructing a bidirectional dynamic mapping model of a transformer substation physical entity and a digital virtual body, constructing a multi-field model and constructing a model increment updating mechanism, and the artificial intelligence fusion module is used for correcting the deviation of an AI model, performing simulation verification on the output of the AI model and generating a visual alarm. According to the method, the technical problems of incomplete data fusion, poor model fusion collaboration and insufficient AI and digital twinning fusion depth in the existing transformer substation digital twinning system are solved, real-time bidirectional accurate mapping of the transformer substation physical entity and the digital virtual body is realized, and the operation and maintenance efficiency and the decision-making precision are improved.

Embodiments of the present disclosure provide a method of controlling a robot, a method of evaluating a robot, a robot, a device of controlling a robot, and a non-volatile computer readable storage medium. The robot comprises a body assembly, upper limb assemblies and leg assemblies, and the method comprises the steps that in a simulation space, a virtual body corresponding to the robot and a virtual body corresponding to a to-be-transferred object are generated; determining a first expected trajectory of movement of a virtual body corresponding to the to-be-transferred object; on the basis of the first expected trajectory, a second expected trajectory of the movement is determined, and in the process that a virtual body corresponding to the robot moves along the second expected trajectory, virtual acting force is applied to the virtual body corresponding to the to-be-transferred object; based on the second expected trajectory, first control information used for controlling a virtual body corresponding to the robot in the simulation space is determined; and determining second control information for controlling the robot in the physical space based on the first control information.

The invention relates to an OST calibration system and an OST calibration method.The OST calibration system is used for calibrating OST-AR equipment, the OST-AR equipment comprises an AR display screen and a tracking camera which are correspondingly configured, and the OST calibration system comprises a three-dimensional target plate on which multiple sets of feature points are distributed; the industrial camera is used for simulating human eyes; the baffle is provided with a first position for shielding the three-dimensional target plate for the industrial camera and a second position for relatively avoiding the three-dimensional target plate; the industrial personal computer is used for acquiring virtual body target plate data and entity target plate data and correspondingly calculating to obtain calibration parameters of the OST-AR equipment, the virtual body target plate data is obtained by shooting an image target plate displayed by the AR display screen by the industrial camera when the baffle plate is at the first position, and the entity target plate data is obtained by shooting the image target plate displayed by the AR display screen when the baffle plate is at the second position. The entity target plate data is obtained by shooting the stereoscopic target plate through the AR display screen by the industrial camera and shooting the stereoscopic target plate through the tracking camera when the baffle plate is at the second position.

A method for determining a seat adjustment of a vehicle seat (110), comprising:- a computer-assisted determination of an ergonomically optimal adjustment of the vehicle seat (110) for each virtual body model (1-25) from a plurality of virtual body models (1-25), and- a retrievable storage of the ergonomically optimal adjustment for each of the virtual body models (1-25).The proposed solution also relates to a method for user-specific adjustment of a vehicle seat and a corresponding system.

The invention discloses a digital twinborn body and a digital twinborn method for a hydraulic test system of a turbine pump of a liquid rocket engine, and solves the technical problem of high production and test resource consumption caused by research and development of engine products. The basic architecture of the digital twinning body comprises a digital twinning engine, a physical entity and a digital virtual body, and dynamic unification of digital virtual body prediction performance and object actual measurement performance is realized through virtual-real interaction and model training and optimization; finally, the display effect that a digital virtual body completely replaces a liquid rocket engine turbine pump hydraulic test system entity can be achieved, and the contradiction between increasing turbine pump hydraulic test tasks and limited physical test resources is greatly relieved.

A method for determining a control policy model, the control policy model being used for controlling an end effector. The end effector comprises a central connector and a plurality of multi-joint operation components. The method comprising: acquiring a first control policy model installed on an end effector (S301); and using a plurality of action rounds to adjust the first control policy model installed on the end effector to determine a second control policy model installed on the end effector, in each action round among said plurality of action rounds, a learning task corresponding to each action round is determined based on information of the action round, a virtual body corresponding to the end effector executes the learning task corresponding to the action round in a virtual manner by using the first control policy model under adjustment, and a reward score corresponding to completion of the learning task corresponding to the action round and a reward score related to physical constraints during the execution of the learning task corresponding to the action round in a virtual manner are determined; and adjusting the first control policy model to increase the reward score for completing the learning task corresponding to the action round and the reward score related to physical constraints during the execution of the learning task corresponding to the action round in a virtual manner (S302).

An exemplary virtual IMU extraction system and method are disclosed for human activity recognition (HAR) or classifier system that can estimate inertial measurement units (IMU) of a person in video data extracted from public repositories of video data having weakly labeled video content. The exemplary virtual IMU extraction system and method of the human activity recognition (HAR) or classifier system employ an automated processing pipeline (also referred to herein as “IMUTube”) that integrates computer vision and signal processing operations to convert video data of human activity into virtual streams of IMU data that represents accelerometer, gyroscope, or other inertial measurement unit estimation that can measure acceleration, inertia, motion, orientation, force, velocity, etc. at a different location on the body. In other embodiments, the automated processing pipeline can be used to generate high-quality virtual accelerometer data from a camera sensor.

The invention discloses an interactive system based on a YOLO-CNN face emotional state model and multi-modal behavior response, and the system comprises six modules which are connected in sequence. The system obtains facial emotion features through a face emotion feature extraction module, a multi-modal fusion module fuses the features with voice and limb movement features to generate a fusion feature matrix, an emotion reasoning engine outputs an emotion reasoning result based on the matrix, and a closed-loop reinforcement learning optimization module optimizes a co-emotional response strategy in combination with historical and real-time interaction data. The virtual body interaction control module generates a control instruction, and the virtual body interaction execution module drives the virtual body to complete interaction and feed back data. The system improves the multi-modal information fusion depth and common situation strategy dynamic optimization capability, solves the problems of fusion limitation and strategy optimization lack closed loop in the prior art, adapts to the fields of education, medical treatment and the like, and enhances the human-computer interaction emotion suitability and stability.

The invention relates to an optical load real-installation digital twinning simulation system, which belongs to the technical field of digital twinning and comprises a satellite digital virtual body, an external interface module and an optical load full-digital virtual simulation platform, the simulation platform further comprises an ultra-high-line-frequency low-crosstalk comprehensive electronic module, a mechanism control module, an optical camera imaging simulation module and a focal plane data processing module. The system receives telemetry data and real shot images of an entity satellite, and performs instruction solution, mechanism motion simulation and full-link optical imaging simulation in a simulation platform to generate a virtual degraded image; performing online imaging quality comparison on the virtual degraded image and the real shot image through a focal plane data processing module, and identifying and correcting parameters of the digital twin model according to the online imaging quality comparison; and finally, the corrected model parameters are fed back to the entity satellite, so that the satellite images the ground object target again according to the plan. According to the invention, high-precision virtual-real twinning of the satellite camera is realized, so that the image quality of the satellite camera is higher.

The invention discloses a construction method of a coal flow monitoring and recognition system platform based on digital twinborn driving. The platform is composed of a real scene side, a communication bridge and a twinborn side. The real scene side builds a conveyor belt scene and completes calibration of a camera and a conveyor belt coordinate system, coal briquette / gangue output categories, confidence coefficients and coordinate information are detected in real time through an improved YOLOv8 model and converted into target poses under the conveyor belt coordinate system, and detection results are published through ROS-TCP. Constructing a mathematical model on the twinborn side based on a solid coal flow system; and after subscribing the live-action side message, generating a corresponding virtual body in a virtual scene according to a target type and a pose, thereby realizing dynamic visualization and consistency simulation of coal flow transportation, supporting start-stop and speed control of a conveyor belt, and feeding back and displaying an operation state and statistical data. The method can accurately position and visually track coal briquettes and gangues on the conveyor belt, is suitable for online monitoring and scheduling optimization of coal mines, coal dressing and related logistics production lines, can reduce manual intervention and misjudgment risks, and improves safety and production efficiency.

A method, a device (800), a medium for controlling the movement of a virtual body (107), including: a target determining step, in the first frame, based on the moving direction and position of the virtual body (107), selecting a virtual object (103) in a predetermined area as a virtual target (202); a dynamic adjusting step, calculating a horizontal moving direction (302a) of the virtual body (107), a direction of a connecting line between a vertical projection (107′a) of the virtual body (107) on the horizontal plane and a vertical projection of the virtual target on the horizontal plane, and an included angle (θ1) between the horizontal moving direction (302a) of the virtual body (107) and the direction of the connecting line in each frame, and controlling the horizontal moving direction (302a) of the virtual body (107) based on the included angle (θ1) (204).

The invention discloses an irrigation digital twinning system for combination of agriculture and clean energy, and belongs to the technical field of agricultural irrigation, the irrigation digital twinning system comprises a physical body, a twinning body and a digital twinning platform, and data mirroring, mapping reconstruction, information interaction and analogue simulation of a virtual body and the physical body are realized through data driving of the digital twinning platform; a simulation model and a twinborn body are constructed by taking a digital twinborn platform as a framework, taking the model as a substrate and taking data as driving. Agricultural, irrigation and clean energy power generation are combined by applying a digital twinborn technology, twinborn modeling is performed on a crop model, a power generation model and an irrigation model, and a digital twinborn model is established through a data management module, an optimization model module, a machine learning module and the like of a digital twinborn platform. And a system and a platform which have a full life cycle and integrate monitoring, optimization adjustment, analogue simulation, control and operation and maintenance are formed.

This technology provides a way to reduce the cognitive load on users during spatial and physical transitions. [Solution] The display is controlled to show a connected space, which is a virtual space connecting a first space to a second space, within the user's field of view. The display is controlled to show spatial images from the perspective of the virtual body, corresponding to the virtual body's position in the connected space and the virtual body's line of sight, in accordance with the user's actions to move the virtual body corresponding to the user through the connected space. Furthermore, as the virtual body moves through the connected space toward the second space, the display is controlled to represent the change in the virtual body's field of view from the field of view corresponding to the first form in the first space to the field of view corresponding to the second form in the second space using spatial images displayed on the display.

The invention discloses a pet digital twinning generation and interaction method and system based on multi-modal data and user definition, and a virtual pet with high-fidelity restoration and personalized creation functions is constructed through multi-modal data processing or user parameter input. The technology covers the following two core scenes. In the digital twinning mode, a highly restored virtual body (such as the appearance, behavior and emotional response of a pet 'Rifu') is generated based on pet pre-birth data (such as images, videos and voices), and the emotional accompanying requirement of an owner is met; the user-defined mode supports a user to create a special pet (such as a cat image and a small ball playing habit of'seven-seven ') through a preset template or natural language description, and the requirements of people with limited pet keeping conditions are met. The system realizes immersive pet accompanying experience of full-scene users through a dual-mode architecture, dynamic emotion response and virtual and real scene synthesis, and breaks through the application limitation of the traditional technology.

The invention relates to a method for generating and / or adapting a geometric meta-model for a molded part produced in a primary molding process for use as a simulation geometry, in which in a learning process step, a qualified part is produced and the qualified part process is characterized, and in order to determine the meta-model, in a geometry determination step, a geometric element model is generated and / or adapted for a molded part produced in a primary molding process for use as a simulation geometry. At least one of the learned features is approximated in an iterative manner in a simulation using an intermediate geometry until a sufficiently precise meta-model is achieved, in which a virtual body is used, which is at least one regular geometry body or consists of regular geometry bodies.

The invention discloses a virtual digital human action frame compensation method and device and terminal equipment, and the method comprises the steps: obtaining the current frame compensation data of each skeleton node in response to a current frame action rendering request of a virtual digital human, dividing a virtual body of the virtual digital human into a plurality of skeleton regions in advance, and carrying out the frame compensation of the skeleton regions; each skeleton region comprises at least one skeleton node; the current frame supplementary frame data comprises current frame sampling action data, skeleton region information and a historical motion curve; performing single-skeleton frame compensation calculation according to the current frame compensation data of each skeleton node, and correspondingly obtaining current frame single-skeleton matrix data; according to the current frame single-skeleton matrix data of all skeleton nodes, obtaining current frame full-skeleton matrix data; and according to the current frame full-skeleton matrix data, performing frame supplementing and rendering processing on the current frame action to obtain a rendered picture. According to the method, the problems of action delay and jamming of the virtual digital human and inconsistency between the action of the virtual digital human and the real action can be solved.

Provided is a technique that trains motor imagery to reinforce brain waves, and a guidance method for motor imagery displays virtual reality including a virtual body part corresponding to a user's real body part the user, detects a movement of the real body part through a motion sensor to track a motion, and visually displays the movement of the virtual body part through the virtual reality according to the tracked motion to induce an ownership feeling that makes the user mistake the virtual body part for the real body part.

The invention discloses an intelligent building structure construction method based on point cloud data and digital twinning, and the method comprises the steps: obtaining a building point cloud through three-dimensional laser scanning, carrying out the high-precision registration and preprocessing, carrying out the component feature extraction and parameterized reverse modeling through an RANSAC algorithm, and generating a high-fidelity BIM model; then, the model is deeply fused with GIS, finite element and Internet of Things data under a unified space-time reference, and a dynamically updated digital twinning scene is constructed. Finally, a virtual simulation platform is developed based on the scene, and real-time simulation, visualization and intelligent decision support of the construction progress and mechanical response are achieved. According to the method, the problems of insufficient precision and difficulty in multi-source data fusion of a traditional modeling method are solved, accurate mapping and interaction of a building structure from a physical entity to a digital virtual body are realized, and the intelligent level and decision scientificity of a construction process are remarkably improved.

A method for creating surgical simulation information by a computer includes creating a virtual body model corresponding to a body state of a patient for surgery, simulating a specific surgical process on the virtual body model to obtain virtual surgical data, dividing the virtual surgical data into minimum surgical operation units, each unit representing one specific operation, and creating cue sheet data composed of the minimum surgical operation units, wherein the cue sheet data represents the specific surgical process.

The present application relates to a kind of rotary inertial navigation digital twin systems and its construction method, including rotary inertial navigation digital twin physical model layer, rotary inertial navigation digital twin geometric model layer, multi-source information data acquisition layer, decision control layer, diagnosis and prediction analysis layer.Can complete the data information acquisition and transmission of rotary inertial navigation system entity, realize the association and interaction of twin virtual body and entity, can be realized using decision control module Iterative optimization of model parameters, finally in diagnosis and prediction analysis module realizes system overall operation state and the performance prediction and evaluation of digital twin inertial navigation system.

This application discloses a method for early warning processing of mechanical equipment, comprising: acquiring target working data of the target mechanical equipment within a preset time period; based on the construction objects and construction elements corresponding to each unit time period, performing predictive processing through virtual body models of machine groups corresponding to different construction objects to obtain a first benchmark value of the target mechanical equipment's early warning indicator for operation of the construction objects corresponding to each unit time period; obtaining a test statistic of the target mechanical equipment's operation of the construction objects corresponding to each unit time period based on the deviation between the first benchmark value and the first actual value of the target mechanical equipment's early warning indicator for operation of the construction objects corresponding to each unit time period; and, when the target test statistic is greater than or equal to a preset corresponding abnormal alarm threshold, executing an abnormal alarm prompt for the early warning indicator under the construction object corresponding to the target unit time period. This method enables rapid and effective abnormal early warning, improving the accuracy of early warnings.

The invention relates to the technical field of energy storage power stations, in particular to an energy storage power station fault protection method and system based on digital twinning. The scheme comprises the steps of obtaining a three-dimensional drawing of an energy storage power station, and forming a basic framework of a twin model according to the drawing; performing data entry and display according to the basic framework of the twin model; mapping the obtained voltage and current of the energy storage power supply to the operation state of the energy storage power station; according to preset battery charging and discharging historical data, a battery life estimated value is obtained and displayed; setting an optimal protection action setting value according to the battery life estimated value; and real-time judgment is carried out according to the optimal protection action setting value, and corresponding protection action data are stored in a twin system during protection action. According to the scheme, by constructing the virtual body and combining health analysis and fault monitoring, accurate analysis and judgment of the energy storage power station are achieved.

The present technology relates to an information processing device and an information processing method that make it possible to easily generate a virtual item to be attached to a moving virtual body in a virtual space. This information processing device comprises: an image acquisition unit that acquires image data of an autonomous moving body that takes a pose corresponding to an attached item; and an image processing unit that generates, on the basis of the image data, a virtual item that can be attached to a moving virtual body in a virtual space. The present technology can be applied to, for example, smartphones.

A method, a device (800), a medium for controlling the movement of a virtual body (107), including: a target determining step, in the first frame, based on the moving direction and position of the virtual body (107), selecting a virtual object (103) in a predetermined area as a virtual target (202); a dynamic adjusting step, calculating a horizontal moving direction (302a) of the virtual body (107), a direction of a connecting line between a vertical projection (107′a) of the virtual body (107) on the horizontal plane and a vertical projection of the virtual target on the horizontal plane, and an included angle (01) between the horizontal moving direction (302a) of the virtual body (107) and the direction of the connecting line in each frame, and controlling the horizontal moving direction (302a) of the virtual body (107) based on the included angle (01) (204).

The present application relates to a kind of hydraulic system fault prediction method of forging hydraulic press based on digital twin system, it includes: S1, the geometric parameter of the hydraulic system of forging hydraulic press is acquired, and digital twin model is constructed;S2, the digital twin model of the hydraulic system of forging hydraulic press is realized by using DNN depth neural network based on the order reduction, and the parameterized model of the hydraulic system of forging hydraulic press is established;S3, the order reduction of the digital twin model of forging hydraulic press is completed, and the fault diagnosis and prediction of hydraulic system are realized.The present application adopts multiscale physical model, realizes the data environment interaction of physical space and virtual body space, finally realizes the intelligent decision and maintenance of forging hydraulic press.The present application can realize the fault diagnosis, online monitoring and performance optimization of hydraulic system, reach predictive maintenance, and then realize the development of virtual verification to virtual-real interaction full closed-loop optimization driven by data, comply with the development needs of intelligent equipment, provide new platform for the design and development and performance upgrade of forging equipment.

To increase the degree of freedom in setting a virtual viewpoint in a system that generates a virtual space image including a real image. [Solution] A virtual space image generation system (1) comprising a virtual space configuration data storage unit (12), a plurality of photographing units (52) arranged to surround a subject, a virtual space generation unit (21) that generates a virtual space from the virtual space configuration data, a virtual body position determination unit (22) that determines the position of a virtual body in the virtual space according to predetermined criteria, a virtual viewpoint setting unit (23) that sets a virtual viewpoint in the virtual space, an image acquisition unit (24) that acquires an image of the subject using a first photographing unit that captures the subject at an angle of view closest to the angle of view at which the virtual viewpoint captures the virtual body, an image display processing unit (24) that displays the image of the subject at the position of the virtual body, facing the virtual viewpoint directly, and a virtual space image generation unit (27) that generates an image capturing the virtual space including the image of the subject from the virtual viewpoint.

Disclosed are a method and apparatus for converting data of a medical image for a virtual procedure simulation, according to an embodiment. The data conversion method may comprise the steps of: receiving medical images obtained by capturing the body parts of a procedure subject; on the basis of the medical images, generating a virtual three-dimensional body model including virtual body parts respectively corresponding to the body parts; generating position coordinate data corresponding to the position of each pixel included in each of the medical images; generating a position dataset related to the positions of the virtual body parts by mapping the position coordinate data to the virtual three-dimensional body model; and determining whether to generate a predefined procedure effect event on the basis of a position of a virtual procedure tool moving according to a user input and the position dataset related to the positions of the virtual body parts.