US 11,386,266 B2Granted

Text correction

AssigneeApple Inc.

InventorsDouglas R. Davidson, Bishal Barman, Vivek Kumar Rangarajan Sridhar

Life of this patent

Estimating the term…

Loading patent…

Abstract

The present disclosure generally relates to text correction and generating text correction models. In an example process for text correction, text input is received. In response to receiving the text input, a text string corresponding to the text input is displayed. The text string is represented by a token sequence. The process determines whether an end of the token sequence corresponds to a text boundary. In accordance with a determination that the end of the token sequence corresponds to a text boundary, the process determines, based on a context state of the token sequence, one or more textual errors at one or more tokens of the token sequence. An error indication for a portion of the text string corresponding to the one or more tokens is displayed.

Claims54

Dependent claims

A non-transitory computer-readable storage medium storing one or more programs configured to be executed by one or more processors of an electronic device with a display, the one or more programs including instructions for:

receiving text input;
in response to receiving the text input, displaying, on the display, a text string corresponding to the text input, wherein the text string is represented by a token sequence;
determining whether an end of the token sequence corresponds to a text boundary;
in accordance with a determination that the end of the token sequence corresponds to a text boundary:
identifying, based on a context state of the token sequence, a textual error of a first type at two or more tokens of the token sequence, wherein identifying the textual error of the first type includes:
determining, based on the context state of the token sequence, a sequence of labels to assign to the token sequence, wherein:
a first label of the sequence of labels defines a start of a segment of two or more tokens of the token sequence;
a second label of the sequence of labels defines an end of the segment of two or more tokens of the token sequence;
and
the first label and the second label indicate the first type of textual error and correspond to a first edit operation to perform on the segment of two or more tokens of the token sequence;
and
displaying, on the display, an error indication for a portion of the text string corresponding to the segment of two or more tokens;
and
applying the first edit operation and the second edit operation to the segment of two or more tokens to generate corrected text for the portion of the text string.

11 more elements

A method for text correction, comprising:

at an electronic device having one or more processors, memory, and a display:
receiving text input;
in response to receiving the text input, displaying, on the display, a text string corresponding to the text input, wherein the text string is represented by a token sequence;
determining whether an end of the token sequence corresponds to a text boundary;
and
in accordance with a determination that the end of the token sequence corresponds to a text boundary:
identifying, based on a context state of the token sequence, a textual error of a first type at two or more tokens of the token sequence, wherein identifying the textual error of the first type includes:
determining, based on the context state of the token sequence, a sequence of labels to assign to the token sequence, wherein:
a first label of the sequence of labels defines a start of a segment of two or more tokens of the token sequence;
a second label of the sequence of labels defines an end of the segment of two or more tokens of the token sequence;
and
the first label and the second label indicate the first type of textual error and correspond to a first edit operation to perform on the segment of two or more tokens of the token sequence;
and
displaying, on the display, an error indication for a portion of the text string corresponding to the segment of two or more tokens;
and
applying the first edit operation to the segment of two or more tokens to generate corrected text for the portion of the text string.

13 more elements

An electronic device, comprising:

a display;
one or more processors;
and
memory storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions for:
receiving text input;
in response to receiving the text input, displaying, on the display, a text string corresponding to the text input, wherein the text string is represented by a token sequence;
determining whether an end of the token sequence corresponds to a text boundary;
and
in accordance with a determination that the end of the token sequence corresponds to a text boundary:
identifying, based on a context state of the token sequence, a textual error of a first type at two or more tokens of the token sequence, wherein identifying the textual error of the first type includes:
determining, based on the context state of the token sequence, a sequence of labels to assign to the token sequence, wherein:
a first label of the sequence of labels defines a start of a segment of two or more tokens of the token sequence;
a second label of the sequence of labels defines an end of the segment of two or more tokens of the token sequence;
and
the first label and the second label indicate the first type of textual error and correspond to a first edit operation to perform on the segment of two or more tokens of the token sequence;
and
displaying, on the display, an error indication for a portion of the text string corresponding to the segment of two or more tokens;
and
applying the first edit operation to the segment of two or more tokens to generate corrected text for the portion of the text string.

16 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/114,673Filed 28 Aug 2018 · us provisional application
Priority: 1 Jun 2018
Published: US 2019/0370323 A15 Dec 2019
Granted: 12 Jul 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification7 codes

G06F 40/232
Natural language analysis: orthographic correction, e.g. spell checking or vowelisation
G06F 16/3347
Query execution: using vector based model
G06F 40/253
Natural language analysis: grammatical analysis; Style critique
G06F 40/284
Recognition of textual entities: lexical analysis, e.g. tokenisation or collocates