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

A perfect cognitive engine selection strategy from me through user feedback

A technology for selecting strategies and engines, applied in the field of translation engines, can solve problems such as inability to obtain results, delay in manual switching, inability to perform precise control, etc., and achieve an easy-to-use effect

Pending Publication Date: 2019-01-15
LANGOGO TECH CO LTD
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention proposes a self-improvement cognitive engine selection strategy through user feedback, which solves the problem of the inability to carry out precise control in the prior art, relying on the subjective judgment of a few people to obtain the most realistic results, and at the same time, there will be some problems in manual switching. the delay problem

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] The present invention provides a self-improvement cognitive engine selection strategy through user feedback, and the production method includes the following steps;

[0021] Step 1: Users can give feedback and score for each translation result;

[0022] Step 2: The server will collect the delayed data of each business;

[0023] Step 3: There is a list of supported engines for each language, and all engine failures have the same proportion;

[0024] Step 4: Adjust the proportion of the engine according to the results of daily user feedback;

[0025] Step 5: Adjust the proportion of the engine according to the delay data of the engine;

[0026] Step 6: The engine with the highest priority is selected for each business.

[0027] The steps 1 and 2 are data source processes, and the steps 3, 4, 5 and 6 are strategy optimization processes, and the results of each translation in the step 1 include recognition results, text translation results, and speech synthesis results ...

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 perfect cognitive engine selection strategy from me through user feedback, wherein the user can feedback and grade the result of each translation. The server will collect thedelay data of each service; for each language, there is a list of engines that are supported, and all engines have the same proportion of crashes; adjusting the proportion of engine according to theresult of daily user feedback; adjusting the proportion of the engine according to the delay data of the engine; selecting the engine with the highest priority for each business; at the translator device, the user may determine whether or not the user is aware of the result of the identification, the results of text translation and the results of TTS are fed back. The invention solves the problemthat the precise control can not be carried out and the most real result can not be obtained by relying on the subjective judgment of a few people, and at the same time, the manual switching will havecertain delay, and the engine switching strategy is automatically corrected through data analysis and user feedback, and the engine switching is carried out at an appropriate time, so as to be convenient for the user to use.

Description

technical field [0001] The invention relates to a self-improvement cognitive engine selection strategy through user feedback, in particular to a self-improvement cognitive engine selection strategy through user feedback, which belongs to the technical field of translation engines. Background technique [0002] Translation is the act of converting information in one language into information in another language on the basis of accuracy (letter) and smoothness (expression). Translation is the process of converting a relatively unfamiliar expression into a relatively familiar one. Its content includes language, text, graphics, symbols and video translations. Among them, in language A and language B, "translation" refers to the conversion of these two languages, that is, first convert a sentence in language A into language B, and then convert a sentence in language B into language A; "translation" is Refers to the process of switching between the two languages, converting lang...

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): G06F17/28
CPCG06F40/51G06F40/58
Inventor 张岩代同杰熊涛
Owner LANGOGO TECH CO LTD
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