公开(公告)号：EP4459511A1

公开(公告)日：2024-11-06

申请号：EP24172491.3

申请日：2024-04-25

申请人： Fossick LLC

发明人： BURKE, Anthony Jon ,  GOENS, Jeffrey

IPC分类号： G06N3/10 ,  G06N20/00 ,  G06F40/58 ,  G06N3/0455 ,  G06N3/0475

摘要： The output of a machine learning model may be customized for a particular application using context satisfying the requirements of that application. This may be done using a method comprising receiving an artificial intelligence request, retrieving a set of exemplars corresponding to the artificial intelligence request, generating an artificial intelligence prompt comprising the exemplars and a payload of the artificial intelligence request, and obtaining an artificial intelligence response by providing the artificial intelligence prompt to a trained machine learning model.

公开(公告)号：EP4414978A1

公开(公告)日：2024-08-14

申请号：EP24155089.6

申请日：2024-01-31

申请人： T-Mobile USA, Inc.

发明人： YOUNGE, Mark L.

IPC分类号： G10L17/00 ,  G10L21/02 ,  H04R25/00 ,  H04R1/10 ,  G06F40/58

CPC分类号： G10L17/00 ,  G06F40/58 ,  G10L21/0208 ,  H04R3/005 ,  H04R2499/1120130101 ,  H04R27/00

摘要： Methods and systems for enhanced peer-to-peer voice conversation are disclosed. According to an implementation, a first device worn by a first user may detect a voice signal in an environment. The voice signal may be associated with a second user. The first device may initiate a request for establishing a communication channel between the first device and a second device worn by the second user. Upon receiving an acknowledging signal from the second device, the first device may establish the communication channel between the first device and the second device though a Bluetooth connection, a Wi-Fi connection, a 5G connection, etc. The first device may receive a subsequent voice signal on the communication channel. The first device may amplify a strength of the subsequent voice signal on certain frequencies; perform noise cancellation in the subsequent voice signal; and play the subsequent voice signal to the first user.

公开(公告)号：EP4398143A1

公开(公告)日：2024-07-10

申请号：EP23305005.3

申请日：2023-01-03

申请人： Dassault Systèmes

发明人： CHAUMARTIN, Mr. Francois-Regis

IPC分类号： G06F40/247 ,  G06F16/33 ,  G06F16/36 ,  G06F40/51 ,  G06F40/58

CPC分类号： G06F40/247 ,  G06F40/58 ,  G06F16/3337 ,  G06F40/51

摘要： The disclosure notably relates to a computer-implemented method for translating a Natural Language Processing (NLP) system given in a source language into at least one target language. The NLP system is based on a lexicalized taxonomy and allows text annotation and classification. The method comprises providing a corpus in the source language. The taxonomy includes annotations allowing determination of the most frequent terms describing a given concept in the corpus. The method further comprises filtering the most frequent terms for each annotation. The method further comprises querying the corpus with the most frequent terms and extracting portions of sentences comprising these terms. The method further comprises tagging the terms in each extracted portion. The method further comprises translating the extracted portions in the at least one target language using a quality machine-translator, thereby obtaining a tagged translation for each portion. The method further comprises normalizing the translations.

公开(公告)号：EP4362011A1

公开(公告)日：2024-05-01

申请号：EP23178654.2

申请日：2023-06-12

申请人： Kudo, Inc.

发明人： Fantinuoli, Claudio

IPC分类号： G10L13/08 ,  G10L15/26 ,  G06F40/58 ,  G10L13/033 ,  G06F40/284

CPC分类号： G06F40/58 ,  G06F40/289 ,  G06F40/284 ,  G10L15/26 ,  G10L13/033 ,  G10L13/08

摘要： A method for providing automatic interpretation may include receiving, by a processor, audible speech from a speech source, generating, by the processor, in real-time, a speech transcript by applying an automatic speech recognition model on the speech, segmenting, by the processor, the speech transcript into speech segments based on a content of the speech by applying a segmenter model on the speech transcript, compressing, by the processor, the speech segments based on the content of the speech by applying a compressor model on the speech segments, generating, by the processor, a translation of the speech by applying a machine translation model on the compressed speech segments, and generating, by the processor, audible translated speech based on the translation of the speech by applying a text to speech model on the translation of the speech.

公开(公告)号：EP4354340A1

公开(公告)日：2024-04-17

申请号：EP23203068.4

申请日：2023-10-11

申请人： SDL Limited

发明人： McKnight Hardy, Matthew William ,  Vasilescu, Rares Ionut

IPC分类号： G06F40/51 ,  G06F40/58 ,  G06Q10/10 ,  G06Q50/00

CPC分类号： G06F40/58 ,  G06F40/51 ,  G06Q10/10 ,  G06Q10/105 ,  G06Q10/06398 ,  G06Q50/10

摘要： A method and system (300) for providing a translation decision assistant. A document is processed to determine a value (320) and document insights (325). The value (320) is a quantification of the impact of the content to the business. The insights (325) include language, personally identifiable information, and the domain of the work. These insights (325) and content value (320) are evaluated against prior job history to identify suitable resources for the translation job. A machine learning aggregation process (350) extracts resources including people, machine translation engines, terminology, and workflows. The machine learning aggregation process (350) from prior training selects resources from the various evaluations. A constraint filter (360) processes the resources with external constraints including hard constraints and soft constraints. Hard constraints include translator certification, languages, and permissions. Soft constraints include quality, availability, costs, and service levels. The constraint filter (360) outputs ranked resources by cost, quality, and time. A decision filter (380) step selects the best resources from the constraint filter output based on the job value and time, cost, and quality criteria and presents to a user (302) or allows a translation management system (390) to make automated allocation and routing decisions.

公开(公告)号：EP4339830A1

公开(公告)日：2024-03-20

申请号：EP22893156.4

申请日：2022-11-08

申请人： Samsung Electronics Co., Ltd.

发明人： HAN, Hyojung ,  YOON, Yoonjin ,  CHOI, Yoonjung ,  KIM, Sangha ,  AHN, Seokchan ,  YOO, Taehwan ,  LEE, Beomseok

IPC分类号： G06F40/58 ,  G06F40/51 ,  G06F40/263 ,  G06F40/211 ,  G06F16/34

摘要： An electronic device and a controlling method of an electronic device are disclosed. Specifically, the electronic device according to the disclosure includes a memory and a processor which obtains, based on a text sequence of a first language being obtained, a first translated text in which a first phrase is translated in a second language by inputting the first phrase from among a plurality of phrases included in the text sequence to a translation model, determine an extent of delay in translation of the first phrase by comparing an obtained time-point of the first phrase with an obtained time-point of the first translated text, identify one phrase from among the first phrase and a second phrase following the first phrase based on the extent of delay, obtain a summary text of the identified phrase by inputting the identified phrase to a summary model, obtain a second translated text in which the summary text is translated in the second language by inputting the summary text to the translation model, and output the second translated text after the first translated text is output.

公开(公告)号：EP4270240A1

公开(公告)日：2023-11-01

申请号：EP21909305.1

申请日：2021-12-20

申请人： Zhang, Longbu

发明人： XU, Rongjun ,  SHANG, Qiang ,  ZHANG, Longbu

IPC分类号： G06F40/58

摘要： A cloud translation calling method, comprising: receiving or obtaining content to be translated; calling the cloud translation service according to the cloud translation calling information; obtaining and/or displaying the results of cloud translation services; wherein, the cloud translation calling information is a cloud translation calling information provided by a third party; or the cloud translation calling information comprises basic information and additional information; or the cloud translation calling information includes information that can be used to call one or more cloud translation services. A cloud translation calling device, configured to call cloud translation service according to cloud translation calling information; or include a cloud translation module, which is configured to call the cloud translation service according to the cloud translation calling information. Further, using the cloud translation calling information provided by the third party to directly call the cloud translation service from the cloud translation provider, and call multiple cloud translation services at the same time. The present invention also includes a related method and server for providing cloud translation calling information, and a system for calling cloud translation.

公开(公告)号：EP4229539A1

公开(公告)日：2023-08-23

申请号：EP21879665.4

申请日：2021-08-27

申请人： Mitra, Bhawana

发明人： Mitra, Bhawana

IPC分类号： G06F40/47 ,  G06F40/58 ,  G06F40/263

公开(公告)号：EP4211631A1

公开(公告)日：2023-07-19

申请号：EP21791528.9

申请日：2021-09-13

申请人： Schadow, Gunther

发明人： Schadow, Gunther

IPC分类号： G06Q10/06 ,  G06Q10/10 ,  G06F9/48 ,  G06F9/50 ,  G06F40/58

公开(公告)号：EP4143672A1

公开(公告)日：2023-03-08

申请号：EP21718730.1

申请日：2021-03-23

申请人： Microsoft Technology Licensing, LLC

发明人： BORZA, Paul Valentin ,  WU, Dan ,  WANG, Xiao ,  PIO, Jonathan Drew ,  YUSUF, Maryam Ummi ,  BROWN, Jared

IPC分类号： G06F3/0482 ,  G06F3/0484 ,  H04L29/08 ,  G06F9/451 ,  G06F40/58