Text correcting method and device and electronic device
A text and standard text technology, which is applied in the fields of electrical digital data processing, instruments, calculations, etc., can solve the problem that text cannot be recognized successfully, and achieve the effect of improving the text recognition rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0026] This specification proposes a text correction method, which uses a text correction model obtained by machine learning to correct the text, wherein the text correction model can use a seq2seq (Sequence-to-Sequence) model. The text that the seq2seq model can be used to correct includes but is not limited to: names of various objects (such as places, people, companies), and Query entries used for queries. Among them, for each standard text, it can correspond to a variety of non-standard texts. The standard text can be a predefined standard expression, and the non-standard text can be some character changes made on the basis of the standard expression. For example, a certain A standard text is: "Luck did better than Huan", and the non-standard text corresponding to this standard text can be: "Luck did better then Huan" or "Luck do better than Huan", etc. In actual text recognition scenarios, it is expected to recognize non-standard texts caused by rewriting or misspellings ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


