Unlock instant, AI-driven research and patent intelligence for your innovation.

Sentence Error Correction Method and System

An error correction method and error correction system technology, applied in the field of machine learning, natural language processing, and artificial intelligence, can solve the problems that modern Chinese cannot perform effective error correction and has no special error correction function, so as to speed up the processing speed and enhance User experience, effect of reducing load

Active Publication Date: 2015-09-02
义语智能科技(广州)有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the search engines represented by Google and Baidu also have some deficiencies: one, because the current Google and Baidu search engines are mainly based on text input, and the input and transformed formats are in the form of strings, so they have certain limitations. Due to the limitation of the system, it can only correct the errors of words, not suitable for the error correction of sentences
Second, the error correction of Chinese sentences by Google and Baidu search engines is based on a certain grammatical structure, which cannot effectively correct the lazy and disordered modern Chinese, for example, the original colloquial sentence
Third, Google and Baidu search engines do not have special error correction functions for a certain field

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
  • Sentence Error Correction Method and System
  • Sentence Error Correction Method and System
  • Sentence Error Correction Method and System

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0062] see figure 1As shown, the specific implementation of the sentence error correction method of the present invention includes the following steps:

[0063] S110: The user performs voice input through the microphone.

[0064] S120: Convert the input speech information into text-type first sentence information by using a speech recognizer.

[0065] In steps S110-S120, the first sentence information input by the user is completed by voice. In other embodiments, a text mode may also be used. Due to the use of voice, users can express meaning as they like, without any restrictions, and can even break away from grammar. At the same time, the voice mode also makes inputting sentence information faster and more convenient, and the user has a better experience. The first sentence information in the present invention can be Chinese, English or other languages, but in order to better illustrate the present invention, only the first sentence information in Chinese is taken as an ...

Embodiment 1

[0119] Step 1a: the user performs voice input through the microphone on the mobile communication terminal.

[0120] The user intended to input "I asked how to make scrambled eggs with tomatoes".

[0121] Step 1b: Convert the input voice information into text-type first sentence information through the built-in voice recognizer of the mobile communication terminal.

[0122] Due to the inaccurate pronunciation of the user, "tomato" was said to be "heart tomato", and the first sentence information in text form was converted by the speech recognizer, "I asked Xin tomato how to make scrambled eggs". Wherein, in a preferred embodiment of the present invention, the speech recognizer is set inside the mobile communication terminal. In other embodiments, the voice recognizer can also be set externally and communicated with the mobile communication terminal. Although the recognition capability of the external speech recognizer is relatively high, the time for the entire recognition, a...

Embodiment 2

[0142] Step 2a: The user performs voice input through the microphone on the mobile communication terminal.

[0143] The user intended to enter "what's the weather like tomorrow".

[0144] Step 2b: Convert the input voice information into text-type first sentence information through the built-in voice recognizer of the mobile communication terminal.

[0145] Due to the inaccurate pronunciation of the user, the tongue roll is not clear, and the "weather" is said to be "going to the sky", and the speech recognizer converts the first sentence information in text form "how will the sky go tomorrow".

[0146] Step 2c: The background of the mobile communication terminal acquires the first sentence information input by the user, and stores it in a memory.

[0147] Step 2d: Search the first sentence information "how to go tomorrow" in the first mapping table, and judge whether there is a matching result.

[0148] There is no matching result corresponding to the sentence information "...

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 particularly relates to statement error correction method and system. The method comprises the following steps: (a) acquiring first statement information input by a user and storing the information in a storage; (b) determining whether the input first statement information has a matching result in a first mapping table, and if not, executing step (c), and if so, executing step (f); (c) according to the criterion of maximal similarity, performing error correction on the first statement information and generating second statement information; (d) displaying the second statement information on a user interface; (e) after affirmation by the user, finding the second statement information in a function library, and if a matching result exists, executing step (f), and if a matching result does not exist, executing ending; and (f) after affirmation by the user, displaying a response result on the user interface. By the method provided by the invention, oral statements of users can be accurately identified, so that automatic error correction on statement information is realized; and information is dynamically added to a database, so that the content information of the database is timely and popular.

Description

technical field [0001] The invention relates to the technical fields of artificial intelligence, machine learning and natural language processing, in particular to a sentence error correction method and system thereof. Background technique [0002] With the continuous development of the Internet, users often conduct information inquiries through search systems to obtain relevant materials. At present, search engines represented by Google and Baidu have provided users with convenient query functions. Users only need to input keywords, phrases and key sentences to get accurate search results. If there are general small errors in the keywords, phrases and key sentences entered by the user, Google and Baidu search engines can correct them to a certain extent. Among them, Google and Baidu's Chinese error correction is based on words, for example, "Moonlight in the Lotus Pond" is the title of a song, and it is a proprietary phrase. Based on this, Google and Baidu search engines...

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 Patents(China)
IPC IPC(8): G06F17/30G06F17/27
Inventor 舒畅唐璐穆影英胡金荣王丽君黄莎莎张林刘文陈昱洁沈玉龙高迎刘畅廖益玄孙彦玲
Owner 义语智能科技(广州)有限公司