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

Method and device for converting spoken languages to written languages

A written and spoken language technology, applied in the field of intelligent customer service, can solve problems such as irregular word usage, imprecise syntactic structure, inaccurate understanding of spoken language problems, etc., and achieve the effect of accurate conversion results and improved accuracy.

Active Publication Date: 2015-06-24
BEIJING SINOVOICE TECH CO LTD
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in practical applications, the questions raised by users are often colloquial questions, and colloquial questions often have problems such as irregular words and imprecise syntactic structures. Inaccurate understanding of the question, making it difficult to give the correct answer

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
  • Method and device for converting spoken languages to written languages
  • Method and device for converting spoken languages to written languages
  • Method and device for converting spoken languages to written languages

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0165] In a specific application, the process of converting a spoken sentence f into a written sentence e is to search for an optimal decoding result in the F╳A╳E space so that f can be converted into e with the greatest probability. Among them, F represents the spoken sentence set, E represents the written sentence set, A represents the vocabulary alignment parameter set between F and E, and ╳ represents the spatial operation, that is, to search for an optimal path in the three set spaces of F, A and E, That is, to search for an optimal decoding result.

[0166] Usually, the search for the optimal decoding result can be done by traversing through each written sentence e in the space E, and considering the possibility of each written sentence e, and finally determining a written sentence with the highest probability, which requires a lot of computing resources , taking up a lot of computing time.

[0167]In order to find an optimal decoding result within limited resources and...

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 embodiment of the invention provides a method and device for converting spoken languages to written languages, and a training method and device for translation models. The method for converting spoken languages to written languages specifically comprises the steps that searching and decoding are carried out on pre-processed spoken language statements according to converting probability parameters and alignment probability parameters in the translation models and language models, and corresponding optimal decoding results are obtained, wherein the translation models and the language models are obtained through training according to contrast corpuses comprising spoken language statements and written language statements; the optimal decoding results corresponding to the spoken language statements are output as the written language statements. By means of the method and device, an intelligent customer service system can accurately understand spoken problems proposed by users, and therefore the response accuracy rate of the intelligent customer service system can be improved.

Description

technical field [0001] The present invention relates to the technical field of intelligent customer service, in particular to a method and device for converting spoken language into written language, and a method and device for training translation models. Background technique [0002] The intelligent customer service system is an intelligent information system that uses natural language to interact with users. It can identify and understand questions raised by users, understand user intentions through semantic analysis, and communicate with users in a humanized way, thereby providing information consultation to users and related services. [0003] The existing intelligent customer service system processes and responds based on written language. Due to the norms of written language, the algorithm of the intelligent customer service system has a high accuracy rate in analyzing and understanding it. Therefore, the existing intelligent customer service systems are all Comprehe...

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): G06F17/28
Inventor 刘伟权杨立波李健张连毅武卫东
Owner BEIJING SINOVOICE TECH CO LTD
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