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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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 "...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 