Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Virtual Reality Language Task Offloading Method Based on Deep Reinforcement Learning

A technology of virtual reality and reinforcement learning, applied in neural learning methods, services based on specific environments, communication between vehicles and infrastructure, etc., can solve the problems of limited energy consumption, difficult language communication simulation exercises, and a large number of virtual reality systems. Energy consumption and other issues to achieve the effect of solving energy constraints, improving convergence speed, and enhancing flexibility

Active Publication Date: 2021-06-04
HUNAN NORMAL UNIVERSITY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, in the mobile environment, the energy consumption of mobile terminals is often limited, and the calculation of the virtual reality system requires a lot of energy consumption. Therefore, most of the current virtual reality on the mobile terminal is a short-term application, and it is difficult to achieve long-term language communication simulation exercises.
The design of virtual reality system based on mobile environment is a huge technical challenge

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Virtual Reality Language Task Offloading Method Based on Deep Reinforcement Learning
  • A Virtual Reality Language Task Offloading Method Based on Deep Reinforcement Learning
  • A Virtual Reality Language Task Offloading Method Based on Deep Reinforcement Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be further described below in conjunction with specific embodiment and accompanying drawing:

[0054] Such as figure 1 As shown, a mobile virtual reality language communication simulation learning computing system based on deep reinforcement learning and mobile edge computing, the system consists of cloud computing layer, mobile edge computing layer and user layer, the cloud computing layer includes a cloud server; mobile edge The computing layer includes several mobile edge computing (MEC) devices installed on drones and unmanned vehicles to form a heterogeneous mobile edge network, where each mobile edge computing device includes an energy transmission module, a communication module and an MEC server;

[0055] The user layer includes several mobile virtual reality devices, where each mobile virtual reality device includes an energy harvesting module, a communication module, a processor, and a battery; the cloud server transmits data to the c...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a mobile virtual reality language communication simulation learning computing system and method. The invention constructs a mobile edge computing system with energy collection function, and then generates a task offloading decision of edge computing through a deep reinforcement learning method. The algorithm does not require any manually labeled training data, and learns from past task offloading experience, improving the task offloading action generated by DNN through reinforcement learning; by shrinking the local search method to improve the convergence speed of the algorithm, the trained DNN network can Real-time online and real-time task offloading decision-making; this method takes into account task offloading calculation and energy collection, and can solve the energy limitation problem of mobile terminals; this method uses mobile edge computing and cloud computing to solve virtual reality and augmented reality. The delay and energy consumption of large-scale computing in these emerging fields can enable users to realize simulated learning of virtual reality language communication in a mobile environment.

Description

technical field [0001] The invention belongs to the technical field of mobile virtual reality, and in particular relates to a virtual reality language task offloading method based on deep reinforcement learning. Background technique [0002] With the rapid development of artificial intelligence computing, natural language processing has made breakthroughs in the research of computer human-computer interaction, but language learning is based on scenes and environments, and the emerging virtual reality technology can provide an immersive experience for language learning. The learning and interactive environment is a new hotspot in future language communication simulation learning. [0003] However, virtual reality technology requires a large amount of image computing resources and extremely low communication delay, and often requires specialized virtual reality equipment and dedicated communication lines. Therefore, current virtual reality devices are dedicated virtual realit...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F3/01G06K9/62G06N3/04G06N3/08G06Q50/20H04L29/08H04W4/44
CPCH04W4/44H04L67/10G06N3/08G06F3/011G06Q50/205G06N3/045G06F18/23G06F18/24Y02D30/70
Inventor 江沸菠代建华刘帅蒋莉华董莉柳隽琰李睿恬
Owner HUNAN NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products