Behavior prediction method and device based on deep reinforcement learning

A technology of reinforcement learning and prediction methods, applied in the field of pattern recognition, can solve the problems of template outlier sample impact, discrimination ability impact, accuracy increase, etc., to achieve the effect of improving performance, suppressing background noise, and improving efficiency and effect

Active Publication Date: 2018-07-06
TSINGHUA UNIV
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The technology described in this patented describes how it can predict people's movements accurately without relying solely upon their physical attributes or contextual cues like speech patterns from other speakers. This helps improve understanding about complex social interactions between humans and makes them more efficient at making informed decisions.

Problems solved by technology

This patented technical problem addressed in this patents relates to improving how humans behave during interactions with computers (computerized systems). While analyzers have made significant progress towards understanding behaviors accurately, they often face issues due to variations between individuals over time. Current approaches involve learning patterns from incomplete data sources but these techniques may also result in poor results if used alone. Therefore, it would benefit us to provide new ways to improve behavior predictions without relying solely upon previous knowledge.

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
  • Behavior prediction method and device based on deep reinforcement learning
  • Behavior prediction method and device based on deep reinforcement learning
  • Behavior prediction method and device based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings, in which the same or similar reference numerals indicate the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to explain the present invention, but should not be construed as limiting the present invention.

[0035] Before introducing the behavior prediction method and device based on deep reinforcement learning in the embodiments of the present invention, first briefly introduce the behavior prediction and deep reinforcement learning fields involved in the embodiments of the present invention.

[0036] (1) Behavior prediction: It is very undesirable to use behavior prediction as a combination of behavior classification. The behavior recognition method in the related technology has an assumption that the time d

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 behavior prediction method and device based on deep reinforcement learning, wherein the method comprises the following steps of: extracting an action characteristic of humanskeleton information through a frame of a video image; encoding the action characteristics according to the human body mechanism information; screening the effective part of the human body behavior process through the deep reinforcement learning so as to predict the behavior of people. According to the method, a local image block is extracted at an important position of a human body, and an ordered arrangement of features of the image blocks is utilized, so that the structural information of the human body is effectively utilized in the prediction process, and the accuracy and the performanceof the behavior prediction are effectively improved.

Description

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

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
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap