# US 2016/0259760 A1 · Automated document translation

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

- Number: US 2016/0259760 A1
- Document ID: US20160259760A1
- Status: Published application
- Kind: A1
- Application number: 14/812,142
- Filed: 2015-07-29
- Published: 2016-09-08
- Earliest claimed: 2015-03-06
- Assignees: Translation Management Systems Ltd.
- Applicants: Translation Management Systems, Ltd
- Inventors: Vladimir Gusakov; Jean-Luc Dominique Sailard; Ivan Smolnikov; Artem Ukrainets
- Web page: https://patentgrep.com/patent/US20160259760A1

## 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 40/00: Handling natural language data (speech analysis or synthesis, speech recognition G10L)
- G06V 30/40: Document-oriented image-based pattern recognition
- H04N 1/00: Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N 1/00244: {with a server, e.g. an internet server (fax-servers or the like for store and forward H04N1/324)}
- G06V 2201/10: Recognition assisted with metadata
- H04N 2201/0094: Multifunctional device, i.e. a device capable of all of reading, reproducing, copying, facsimile transception, file transception
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Systems and methods for automated document translation. An example method comprises: scanning an image of an original document using a scanner of a multi-function device; performing, by a processor, optical character recognition of the image to retrieve a text of the original document, wherein the text comprises at least a portion expressed in a source natural language; responsive to receiving a user input specifying a translation method, producing a translated document by causing the portion of the text to be translated into a target natural language using the translation method, wherein the translation method is provided by one of: a machine translation or a human translation; and printing the translated document using a printer of the multi-function device.

## Claims

### Claim 1

A method comprising:
scanning an image of an original document using a scanner of a multi-function device;
performing, by a processor, optical character recognition of the image to retrieve a text of the original document, wherein the text comprises at least a portion expressed in a source natural language;
receiving a user input specifying a translation method selected from a machine translation and a human translation;
responsive to receiving the user input specifying the translation method, selecting the translation method from among the machine translation and the human translation;
producing a translated document by causing the portion of the text to be translated into a target natural language using the selected translation method; and
printing the translated document using a printer of the multi-function device.

### Claim 2 (depends on 1)

The method of claim 1, wherein performing optical character recognition of the image further comprises:
retrieving, from the original document, metadata comprising at least one of: a document structure of the original document or document formatting of the original document.

### Claim 3 (depends on 2)

The method of claim 2, wherein printing the translated document comprises:
formatting the translated document using the metadata.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
receiving a user input specifying the target natural language.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
identifying an account to be associated with a current translation job.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
verifying an entitlement of the account to order the current translation job.

### Claim 7 (depends on 5)

The method of claim 5, further comprising:
producing a billing record reflecting the current translation job.

### Claim 8

A method comprising:
scanning an image of an original document using a scanning device;
performing, by a processor, optical character recognition of the image to retrieve a text of the original document;
identifying, within the text, a first portion expressed in a source natural language, wherein the first portion matches a first stored translation record associating the first portion and a first translated text expressed in a target natural language;
translating the first portion into the target natural language using the first translated text;
receiving a user input specifying a translation method selected from a machine translation and a human translation;
responsive to receiving the user input specifying the translation method, selecting the translation method from among the machine translation and the human translation; and
responsive to failing to match a second portion of the text to a second stored translation record, causing the second portion of the text to be translated into the target natural language using the selected translation method.

### Claim 9 (depends on 8)

The method of claim 8, wherein performing optical character recognition of the image further comprises:
retrieving, from the original document, metadata comprising at least one of: a document structure of the original document or document formatting of the original document.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
producing a translated document comprising the translations of the first portion and the second portion; and
printing the translated document using a printer device, wherein printing the translated document comprises formatting the translated document using the metadata.

### Claim 11 (depends on 8)

The method of claim 8, further comprising:
receiving a user input specifying the target natural language.

### Claim 12 (depends on 8)

The method of claim 8, further comprising:
identifying an account to be associated with a current translation job.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
verifying an entitlement of the account to order the current translation job.

### Claim 14 (depends on 12)

The method of claim 12, further comprising:
producing a billing record reflecting the current translation job.

### Claim 15

A method comprising:
identifying an account to be associated with a current translation job;
scanning an image of an original document using a scanning device;
performing, by a processor, optical character recognition of the image to retrieve a text of the original document;
receiving a user input specifying a translation method selected from a machine translation and a human translation;
responsive to receiving the user input specifying the translation method, selecting the translation method from among the machine translation and the human translation; and
responsive to successfully verifying an entitlement of the account to order the current translation job comprising translation of at least a portion of the text of the original document to a target natural language, causing at least the portion of the text to be translated into the target natural language using the selected translation method.

### Claim 16 (depends on 15)

The method of claim 15, wherein performing optical character recognition of the image further comprises:
retrieving, from the original document, metadata comprising at least one of: a document structure of the original document or document formatting of the original document.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
producing a translated document comprising the translation of the portion; and
printing the translated document using a printer device, wherein printing the translated document comprises formatting the translated document using the metadata.

### Claim 18 (depends on 15)

The method of claim 15, further comprising:
receiving a user input specifying the target natural language.

### Claim 19 (depends on 15)

The method of claim 15, further comprising:
producing a billing record reflecting the current translation job.

### Claim 20 (depends on 15)

The method of claim 15, wherein the machine translation is performed using a translation memory database comprising a plurality of records, each record associating a first text fragment in the source natural language and a second text fragment in the target natural language.

### Claim 21

A computer-readable non-transitory storage medium comprising executable instructions that, when executed by a computer system, cause the computer system to perform operations comprising:
scanning an image of an original document using a scanner of a multi-function device;
performing, by a processor, optical character recognition of the image to retrieve a text of the original document, wherein the text comprises at least a portion expressed in a source natural language;
receiving a user input specifying a translation method selected from a machine translation and a human translation;
responsive to receiving the user input specifying the translation method, selecting the translation method from among the machine translation and the human translation;
producing a translated document by causing the portion of the text to be translated into a target natural language using the selected translation method; and
printing the translated document using a printer of the multi-function device.

### Claim 22

A computer-readable non-transitory storage medium comprising executable instructions that, when executed by a computer system, cause the computer system to perform operations comprising:
scanning an image of an original document using a scanning device;
performing, by a processor, optical character recognition of the image to retrieve a text of the original document;
identifying, within the text, a first portion expressed in a source natural language, wherein the first portion matches a first stored translation record associating the first portion and a first translated text expressed in a target natural language;
translating the first portion into the target natural language using the first translated text;
receiving a user input specifying a translation method selected from a machine translation and a human translation;
responsive to receiving the user input specifying the translation method, selecting the translation method from among the machine translation and the human translation; and
responsive to failing to match a second portion of the text to a second stored translation record, causing the second portion of the text to be translated into the target natural language using the selected translation method.

### Claim 23

A computer-readable non-transitory storage medium comprising executable instructions that, when executed by a computer system, cause the computer system to perform operations comprising:
identifying an account to be associated with a current translation job;
scanning an image of an original document using a scanning device;
performing, by a processor, optical character recognition of the image to retrieve a text of the original document;
receiving a user input specifying a translation method selected from a machine translation and a human translation;
responsive to receiving the user input specifying the translation method, selecting the translation method from among the machine translation and the human translation; and
responsive to successfully verifying an entitlement of the account to order the current translation job comprising translation of at least a portion of the text of the original document to a target natural language, causing at least the portion of the text to be translated into the target natural language using the selected translation method.
