# US 2021/0209428 A1 · Translation Method and Apparatus and Electronic Device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0209428 A1
- Document ID: US20210209428A1
- Status: Published application
- Kind: A1
- Application number: 17/207,559
- Filed: 2021-03-19
- Published: 2021-07-08
- Earliest claimed: 2020-09-07
- Assignees: Baidu Online Network Technology (Beijing) Co., Ltd.
- Applicants: Baidu Online Network Technology (Beijing) Co., Ltd.
- Inventors: Shaoting YI; Yongjia YU
- Web page: https://patentgrep.com/patent/US20210209428A1

## CPC

- G06F 40/58: Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06V 30/153: {using recognition of characters or words}
- G06V 30/158: {using character size, text spacings or pitch estimation}
- G06V 30/18171: {Syntactic representation, e.g. using a grammatical approach}
- G06V 30/268: {Lexical context}
- G06V 30/413: Classification of content, e.g. text, photographs or tables
- G06N 20/00: Machine learning
- G06V 30/10: Character recognition
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A translation method includes acquiring an image, where the image includes a text to be translated; splitting the text to be translated in the image and acquiring a plurality of target objects, where each of the plurality of target objects includes a word or a phrase of the text to be translated; receiving an input operation for the plurality of target objects, acquiring an object to be translated among the plurality of target objects, and translating the object to be translated.

## Claims

### Claim 1

A translation method, comprising:
acquiring an image, wherein the image comprises text to be translated;
splitting the text to be translated in the image and acquiring a plurality of target objects, wherein each of the plurality of target objects comprises a word or a phrase of the text to be translated; and
receiving an input operation for the plurality of target objects, and acquiring an object to be translated among the plurality of target objects; and
translating the object to be translated.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the object to be translated comprises one target object or a plurality of target objects of which positions are discontinuous among the plurality of target objects, or a plurality of target objects of which positions are continuous among the plurality of target objects.

### Claim 3 (depends on 1)

The method according to claim 1, wherein splitting the text to be translated in the image and acquiring the plurality of target objects comprises,
performing a content identification on the image and acquiring a first identification result,
splitting words in the first identification result and acquiring the plurality of target objects, and
displaying a click box at a position where each of the plurality of target objects is located in the image, wherein each of the plurality of target objects further comprises a corresponding one of the click boxes; and
wherein receiving the input operation for the plurality of target objects and acquiring the object to be translated among the plurality of target objects comprises,
receiving an input operation for the click boxes of the plurality of target objects and acquiring the object to be translated among the plurality of target objects, wherein the object to be translated is a word or a phrase corresponding to a select one of the click boxes.

### Claim 4 (depends on 3)

The method according to claim 3, wherein splitting the words in the first identification result and acquiring the plurality of target objects comprises:
splitting the words in the first identification result by row and acquiring at least one row of words information; and
splitting each row of words information among the at least one row of words information according to a word-spacing, and acquiring the plurality of target objects.

### Claim 5 (depends on 3)

The method according to claim 3, wherein displaying the corresponding click box at the position where each of the plurality of target objects is located in the image comprises:
displaying a mask layer with preset transparency at the position where each of the plurality of target objects is located in the image; and
displaying the click box on the mask layer.

### Claim 6 (depends on 1)

The method according to claim 1, wherein translating the object to be translated comprises:
translating the object to be translated and acquiring a translation result;
acquiring a context of the object to be translated in the text to be translated, and extracting a plurality of knowledge points from a database;
determining priorities of the plurality of knowledge points based on historical query data of a user;
ranking the plurality of knowledge points according to the priorities, and acquiring top N knowledge points, wherein N is a positive integer; and
displaying the translation result and the N knowledge points.

### Claim 7 (depends on 1)

The method according to claim 1, wherein splitting the text to be translated in the image and acquiring the plurality of target objects comprises:
identifying the image by using an identification model and acquiring a second identification result;
when it is determined that the image is an image in a study scenario according to the second identification result, splitting the text to be translated in the image and acquiring the plurality of target objects.

### Claim 8

A translation apparatus, comprising: at least one processor; and
a memory in communication connection with the at least one processor; wherein,
the memory has stored thereon instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:
acquire an image, wherein the image comprises text to be translated;
split the text to be translated in the image and acquire a plurality of target objects, wherein each of the plurality of target objects comprises a word or a phrase of the text to be translated;
receive an input operation for the plurality of target objects, and acquire an object to be translated among the plurality of target objects, and
translate the object to be translated.

### Claim 9 (depends on 8)

The apparatus according to claim 8, wherein the object to be translated comprises one target object or a plurality of target objects of which positions are discontinuous among the plurality of target objects, or a plurality of target objects of which positions are continuous among the plurality of target objects.

### Claim 10 (depends on 8)

The apparatus according to claim 8, wherein the instructions are executed by the at least one processor to enable the at least one processor to:
perform content identification on the image and acquiring a first identification result;
split words in the first identification result and acquire the plurality of target objects; and
display a click box at a position where each of the plurality of target objects is located in the image, wherein each of the plurality of target objects further comprises a corresponding one of the click boxes;
wherein the instructions are executed by the at least one processor to enable the at least one processor to receive an input operation for click boxes of the plurality of target objects and acquire the object to be translated among the plurality of target objects, wherein the object to be translated is a word or a phrase corresponding to a select one of the click boxes.

### Claim 11 (depends on 10)

The apparatus according to claim 10, wherein the instructions are executed by the at least one processor to enable the at least one processor to:
split the words in the first identification result by row and acquire at least one row of words information; and
split each row of words information among the at least one row of words information according to a word-spacing, and acquire the plurality of target objects.

### Claim 12 (depends on 10)

The apparatus according to claim 10, wherein the instructions are executed by the at least one processor to enable the at least one processor to:
display a mask layer with preset transparency at the position where each of the plurality of target objects is located in the image; and display each click box on each of the mask layers.

### Claim 13 (depends on 8)

The apparatus according to claim 8, wherein the instructions are executed by the at least one processor to enable the at least one processor to:
translate the object to be translated and acquire a translation result;
acquire a context of the object to be translated in the text to be translated, and extract a plurality of knowledge points from a database;
determine priorities of the plurality of knowledge points based on historical query data of a user;
rank the plurality of knowledge points according to the priorities, and acquire top N knowledge points, wherein N is a positive integer; and
display the translation result and the N knowledge points.

### Claim 14 (depends on 8)

The apparatus according to claim 8, wherein the instructions are executed by the at least one processor to enable the at least one processor to:
identify the image by using an identification model and acquire a second identification result; and
when it is determined that the image is an image in a study scenario according to the second identification result, split the text to be translated in the image and acquire the plurality of target objects.
