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

Human artificial intelligence ethical method and robot that recognize and do not harm humans

A kind of artificial intelligence and category technology, applied in the human artificial intelligence ethical method and the field of robots, can solve problems such as not taking into account, reducing the ethical risk of artificial intelligence, not taking into account the correlation of input variables, etc.

Pending Publication Date: 2020-10-30
SOUTH CHINA NORMAL UNIVERSITY
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to address the flaws or insufficiencies of existing technologies and provide artificial intelligence ethical methods and robots that identify human beings that do not harm humans, so as to solve the problem of algorithmic bias detection and prevention in existing artificial intelligence ethics without taking into account the gap between input variables. The bias caused by correlation does not take into account the defects of the bias caused by the introduction of "impurity" input variables that have nothing to do with the prediction results. By deleting the input variables that cause bias and have no obvious impact on the prediction results, the algorithm bias can be reduced or even eliminated. Reducing the Ethical Risks of Artificial Intelligence

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
  • Human artificial intelligence ethical method and robot that recognize and do not harm humans
  • Human artificial intelligence ethical method and robot that recognize and do not harm humans

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0096] The technical solutions in the embodiments of the present invention will be described in detail below in conjunction with the embodiments of the present invention.

[0097] One, basic embodiment of the present invention

[0098] In the first aspect, the embodiment of the present invention provides an artificial intelligence method

[0099] Such as figure 1 As shown, the method includes: the first information type acquisition step; the first object category acquisition step; the second object category acquisition step; the first category classification accuracy calculation step; the jth subcategory classification accuracy calculation step; A step of calculating the classification accuracy rate of the first category; a step of calculating the accuracy rate of the classification test of the i-th subcategory j; a step of evaluating the correlation between the i-th first information type and the second object category; K kinds of first information type behaviors Evaluation...

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 relates to a human artificial intelligence ethical method and a robot that recognize and do not harm humans. The method comprises the following steps: a screening set initialization step; a step of starting an attempt; a third information type behavior evaluation step; a deletable judgment step; a step of executing control. According to the method, the system and the robot, the algorithm bias is reduced or even eliminated by deleting the input variables which cause the bias and have no obvious influence on the prediction result, so that the artificial intelligence ethical risk isreduced.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence ethical method and a robot for identifying human beings who do not harm human beings. Background technique [0002] In the process of realizing the present invention, the inventors found that there are at least the following problems in the prior art: the algorithmic bias detection and prevention in the existing artificial intelligence ethical risk prevention technology focus on the number of samples, such as the number of samples of ethnic B people Algorithmic bias caused by the difference in the number of samples from ethnic A people, but many experiments have shown that even if the sample size is controlled to be the same, this algorithmic bias cannot be completely eliminated. It can be seen that there are deeper reasons for the bias, and this reason is related to The solution is not available in the prior art. [0003] Therefore, th...

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
IPC IPC(8): G06K9/62G06N20/00
CPCG06N20/00G06F18/24G06F18/214
Inventor 朱定局
Owner SOUTH CHINA 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com