Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Cognitive moderator for cognitive instances

A technology that mediates processes and processors, applied in the field of cognitive computing, to solve problems such as undesired and unwanted

Active Publication Date: 2020-04-17
IBM CORP
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, learning by multiple agents can lead to undesired and unwanted dynamics because the learning creates non-stationary environments for other agents to learn

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
  • Cognitive moderator for cognitive instances
  • Cognitive moderator for cognitive instances
  • Cognitive moderator for cognitive instances

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The proposed method for generating improved responses to queries from two different cognitive engines may provide several advantages and technical effects:

[0016] By considering responses from two or more cognitive engines, a mediation unit enabled to access and weight different responses from different cognitive engines can be Designed and configured to generate improved responses to end-user queries. By using multiple cognitive engines, responses can have improved accuracy. Additionally, the proposed method and related system can integrate responses from multiple cognitive instances into ones that are more useful to the end user. A decision tree for a particular response can also be shown showing the pros and cons from different sources.

[0017] Furthermore, it is possible to use specialized cognitive instances / cognitive engines for queries or utilize parts thereof according to specific knowledge domains. Thus, instead of the end user having to decide which cogn...

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

A method includes receiving a first query by a computing device and assigning the first query to a plurality of cognitive engines, wherein each of the plurality of cognitive engines include differentcharacteristics for processing data. The method also includes, responsive to receiving a response from each of the plurality of cognitive engines for the first query, comparing the received responsesfrom the plurality of cognitive engines. The method also included responsive to determining a difference between a first response from a first cognitive engine and a second response from a second cognitive engine is above a predetermined threshold value, performing a response mediation process until the difference is below the predetermined threshold value.The method also includes selecting a first final response from the received responses for the first query and the second query and displaying the first final response to a user.

Description

technical field [0001] The present disclosure relates generally to cognitive computing, and more specifically, to methods for generating improved responses to queries addressed to two different cognitive engines. The invention also relates to a system for generating improved responses to queries from two different cognitive engines, and a computer program product. Background technique [0002] Currently, cognitive computing is partly a commodity service, where mobile or cloud computing providers produce and deliver end-user-facing devices that can recognize and interpret spoken language. Devices for end users can also act as personal assistants and knowledge navigators. Cognitive services from different providers use different data sources, different algorithms, and different tuning parameters, and can apply different self-learning methods over time. Additionally, the attributes of different providers may be specific to a particular group of users of the cognitive service,...

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 Applications(China)
IPC IPC(8): G06F16/2458G06N5/00G06N5/02G06N5/04G06N20/00
CPCG06N5/022G06N5/041G06N20/00G06N5/043G06F16/2471G06N5/01
Inventor A.乔瓦尼尼S.拉维扎T.U.沙伊德勒F.格拉夫
Owner IBM CORP
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
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