公开(公告)号：US12093660B2

公开(公告)日：2024-09-17

申请号：US18329204

申请日：2023-06-05

申请人： Zoom Video Communications, Inc.

发明人： Justin Bryce Betteridge ,  Connor Isaac Brinton ,  Samuel John Wenke

IPC分类号： G06F40/47 ,  G06F40/263 ,  G06F40/30 ,  G06F40/51

CPC分类号： G06F40/47 ,  G06F40/263 ,  G06F40/30 ,  G06F40/51

摘要： A server accesses a natural language query. The server facilitates a mapping of the natural language query to a vector using a query-to-vector engine. The server matches the vector to an intent representing a prediction associated with the natural language query. The server provides a response to the natural language query based on the intent.

公开(公告)号：US20240265213A1

公开(公告)日：2024-08-08

申请号：US18436347

申请日：2024-02-08

申请人： Rovi Guides, Inc.

发明人： Ajay Kumar Mishra ,  Jeffry Copps Robert Jose

IPC分类号： G06F40/58 ,  G06F16/2452 ,  G06F40/263 ,  G06F40/47 ,  G06F40/51

CPC分类号： G06F40/58 ,  G06F16/24522 ,  G06F40/263 ,  G06F40/47 ,  G06F40/51

摘要： Systems and methods for handling multilingual queries are provided. One example method includes receiving, at a computing device, an input, wherein the input comprises a multi-lingual query comprising at least a first source language and a second source language. The multi-lingual query is translated, word for word, into a destination language to produce a monolingual query, with the word order of the multilingual query and the word order of the monolingual query being the same. The monolingual query is processed using natural language processing to map the mono-lingual query to a natural language query in the destination language.

公开(公告)号：US12039286B2

公开(公告)日：2024-07-16

申请号：US17700123

申请日：2022-03-21

申请人： GOOGLE LLC

发明人： Markus Freitag ,  Isaac Caswell ,  Howard Scott Roy

IPC分类号： G06F40/51 ,  G06F40/166 ,  G06F40/253 ,  G06F40/58 ,  G10L13/00

CPC分类号： G06F40/51 ,  G06F40/166 ,  G06F40/253 ,  G06F40/58 ,  G10L13/00

摘要： Techniques are disclosed for training and/or utilizing an automatic post-editing model in correcting translation error(s) introduced by a neural machine translation model. The automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.

公开(公告)号：US12033173B2

公开(公告)日：2024-07-09

申请号：US17375838

申请日：2021-07-14

申请人： DENSO TEN Limited

发明人： Shinichi Tanaka ,  Shinichi Shiotsu ,  Haruki Shiraishi ,  Minoru Maehata ,  Miki Hitotsuya ,  Tomohiro Ikeda

IPC分类号： G06Q30/02 ,  G06F40/263 ,  G06F40/51 ,  G06Q30/0207 ,  G07B15/02

CPC分类号： G06Q30/0207 ,  G06F40/263 ,  G06F40/51 ,  G07B15/02

摘要： A taxi management device includes: an information acquisition unit that acquires first information including information specifying a use language of a first person and second information including information specifying an interpretable language of a second person; and a discount setting unit that performs discount setting of a fare of the second person at a time of ride-sharing of taxi by the first person and the second person based on the first information and the second information.

公开(公告)号：US12019999B2

公开(公告)日：2024-06-25

申请号：US17351872

申请日：2021-06-18

申请人： GOOGLE LLC

发明人： Wangqing Yuan ,  David Kogan ,  Vincent Lacey ,  Guanglei Wang ,  Shaun Post ,  Bryan Christopher Horling ,  Michael Anthony Schuler

IPC分类号： G06F40/51 ,  G06F40/211 ,  G06F40/289

CPC分类号： G06F40/51 ,  G06F40/211 ,  G06F40/289

摘要： Implementations relate to determining a well-formed phrase to suggest to a user to submit in lieu of a not well-formed phrase. The suggestion is rendered via an interface that is provided to a client device of the user. Those implementations relate to determining that a phrase is not well-formed, identifying alternate phrases that are related to the not well-formed phrase, and scoring the alternate phrases to select one or more of the alternate phrases to render via the interface. Some of those implementations are related to identifying that the phrase is not well-formed based on occurrences of the phrase in documents that are generated by a source with the language of the phrase as the primary language of the creator.

公开(公告)号：US20240135112A1

公开(公告)日：2024-04-25

申请号：US17832800

申请日：2022-06-05

申请人： Government of the United States as Represented by the Secretary of the Air Force

发明人： Jonathan W. LUU ,  Kevin P. FENTON ,  Steve SIMSKE

IPC分类号： G06F40/51 ,  G06F40/205 ,  G06V30/19 ,  G06V30/224

CPC分类号： G06F40/51 ,  G06F40/205 ,  G06V30/1916 ,  G06V30/224

摘要： An apparatus for automated safety data sheet (SDS) processing that translates the entire SDSs from numerous chemical vendors, and in various formats (.pdf, .doc, .txt, .jpg, .gif, .png, etc) to machine-encoded text by employing optical, RFID, and infrared scanning, reading and writing devices. The apparatus reads and assess documents as a human would; ensuring that the documents are compliant, ensuring reported values are within expected thresholds, and that there are no conflicts in hazardous material classification, and comparing to similar products for more environmentally friendly alternatives. The apparatus further employs a processor that computes meta-algorithms as trainable neural networks that allow the invention to “learn” and appropriately classify values and calculate statistical probabilities for output accuracy and precision.

公开(公告)号：US20240062020A1

公开(公告)日：2024-02-22

申请号：US17970305

申请日：2022-10-20

申请人： MICROSOFT TECHNOLOGY LICENSING, LLC

发明人： Pengcheng HE ,  Jianfeng GAO ,  Nanshan ZENG ,  Xuedong HUANG ,  Wei XIONG ,  Baolin PENG

IPC分类号： G06F40/56 ,  G06F40/284 ,  G06F40/51

CPC分类号： G06F40/56 ,  G06F40/284 ,  G06F40/51

摘要： Systems and methods are provided for training and using a novel unified language foundation model. An encoder-decoder natural language model is obtained and various training data is obtained and used for training. The training process integrates a combination of replaced token detection, corrupted span reconstruction, and disentangled attention methodologies to produce a unified encoder-decoder model. The trained model is trained for performing both natural language understanding (NLU) tasks and natural language generation (NLG) tasks. Attention applied to the model is applied discretely to segmented chunks of encoded data during processing to improve the efficiency of applying attention by the model.

公开(公告)号：US11907678B2

公开(公告)日：2024-02-20

申请号：US17093879

申请日：2020-11-10

申请人： International Business Machines Corporation

发明人： Fan Wang ,  Li Cao ,  Rui Wang ,  Lei Gao

IPC分类号： G06F40/45 ,  G06F40/51 ,  G10L15/26 ,  G06F40/30 ,  G06F40/284 ,  G06F40/58

CPC分类号： G06F40/58 ,  G06F40/284 ,  G06F40/30 ,  G06F40/45 ,  G06F40/51 ,  G10L15/26

摘要： A machine translation system, a ChatOps system, a method for a context-aware language machine identification, and computer program product. One embodiment of the machine translation system may include a density calculator. The density calculator may be adapted to calculate a part of speech (POS) density for a plurality of word tokens in an input text, calculate a knowledge density for the plurality of word tokens, and calculate an information density for the plurality of word tokens using the POS density and the knowledge density. In some embodiments, the machine translation system may further comprise a sememe attacher and a context translator.

公开(公告)号：US11842158B2

公开(公告)日：2023-12-12

申请号：US17174425

申请日：2021-02-12

申请人： SAP SE

发明人： Alexander Schreiber ,  Vladimir Shapiro ,  Joachim Sander

IPC分类号： G06F40/30 ,  G06F3/14 ,  G06N20/00 ,  G06F40/51

CPC分类号： G06F40/30 ,  G06F3/14 ,  G06F40/51 ,  G06N20/00

摘要： Implementations include receiving, by a semantic translation service of a ML platform, an output data set from a ML model, the output data set including a predicted value and a set of metrics, determining, by the semantic translation service, a numerical value based on at least two or more metrics in the set of metrics, selecting, by the semantic translation service, a semantic result by mapping the numerical value to a projection including two or more semantic values, and transmitting, by the ML platform, a prediction result at least partially including the semantic result for selective display to a user using one or more user interfaces (UIs).

公开(公告)号：US11829727B2

公开(公告)日：2023-11-28

申请号：US17239297

申请日：2021-04-23

申请人： salesforce.com, inc.

发明人： Jasdeep Singh ,  Nitish Shirish Keskar ,  Bryan McCann

IPC分类号： G06F40/00 ,  G06F40/58 ,  G06N20/00 ,  G06N3/08 ,  G06F40/51

CPC分类号： G06F40/58 ,  G06F40/51 ,  G06N3/08 ,  G06N20/00

摘要： Approaches for cross-lingual regularization for multilingual generalization include a method for training a natural language processing (NLP) deep learning module. The method includes accessing a first dataset having a first training data entry, the first training data entry including one or more natural language input text strings in a first language; translating at least one of the one or more natural language input text strings of the first training data entry from the first language to a second language; creating a second training data entry by starting with the first training data entry and substituting the at least one of the natural language input text strings in the first language with the translation of the at least one of the natural language input text strings in the second language; adding the second training data entry to a second dataset; and training the deep learning module using the second dataset.