Method and system for automatically adjusting priority of speech input method vocabulary

A voice input and automatic adjustment technology, applied in the field of input methods, can solve the problem of difficulty in distinguishing short sentences and monophony, and achieve the effect of avoiding parsing errors

Inactive Publication Date: 2019-01-15
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is: to overcome the problem that the phonetic input method is difficult to distinguish short sentences and single sounds, and to propose a method and system for automatic adjustment of the lexicon priority of the phonetic input method

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 system for automatically adjusting priority of speech input method vocabulary
  • Method and system for automatically adjusting priority of speech input method vocabulary
  • Method and system for automatically adjusting priority of speech input method vocabulary

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0060] This embodiment takes android as the development platform, such as figure 1 As shown, the system first obtains the voice data and the attributes of the corresponding input box. The attributes of the input box include input type attributes and numeric data type attributes. The input type attributes include email address type, person name type, web page type, phone number type, number type, English character type and local character type, etc., in this embodiment, the local character type is taken as the Chinese character type. The attributes of the digital data type can include integer numbers, signed numbers, and floating-point numbers; the attribute settings of the input box during the specific development process are shown in Table 1 below.

[0061] Table 1 Properties of the input box

[0062]

[0063]

[0064] According to the priority mark of the attribute setting lexicon of input frame, priority mark comprises number priority mark, English character priority...

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 the field of input methods, the speech input method is difficult to distinguish the single tone of a short sentence, and a method for automatically adjusting the priority of the speech input method vocabulary is proposed. The system acquires the speech data and the attributes of the corresponding input box, sets the priority flag of the vocabulary according to the attributes of the input box, and selects the corresponding vocabulary according to the priority flag of the vocabulary to parse the speech data. When the voice data is inputted through the corresponding inputbox, the invention preferentially analyzes the voice data according to the attributes of the input box, avoids the parsing error caused when the voice input of short sentence or single tone is difficult to distinguish, and is suitable for adjusting the priority of the vocabulary of the voice input method.

Description

technical field [0001] The invention relates to the field of input methods, in particular to a voice input method. Background technique [0002] In smart terminals such as smart TVs and smart phones, input methods are indispensable, and voice input methods that convert people's natural language input into text input are also common. However, sometimes it is still difficult to analyze whether the input voice is a Chinese character (or other local language) or an English letter or a number. For example, the voice "yī" can correspond to the Chinese character "clothes" or the English letter " E" can also correspond to the number "1". The existing speech recognition technology for speech that is difficult to distinguish, the common practice is to match the query through the entire sentence including the context, such as "123456" or "your clothes are very Good-looking" can distinguish "1" from "clothes". This technology requires relatively long sentences to match accurately, but...

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): G06F3/16G06F3/023
CPCG06F3/0237G06F3/167
Inventor 章卫民
Owner SICHUAN CHANGHONG ELECTRIC 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
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