公开(公告)号：US20240386218A1

公开(公告)日：2024-11-21

申请号：US18317703

申请日：2023-05-15

Applicant: International Business Machines Corporation

Inventor： Vishwajeet Kumar ,  Jaydeep Sen ,  Saneem Ahmed Chemmengath ,  Rudra V Murthy

IPC: G06F40/42 ,  G06F16/2452

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to building a unified question generation system across languages and modalities. The computer-implemented system can comprise a memory that can store computer executable components. The computer-implemented system can further comprise a processor that can execute the computer executable components stored in the memory, wherein the computer executable components can comprise a training component that can train a unified question generation model to generate questions in a language from a first modality in the language using training data comprising one or more second modalities in the language different from the first modality, wherein the first modality and the one or more second modalities can include at least one of one or more tables, one or more passages, or a combination of the one or more tables and the one or more passages.

公开(公告)号：US20240296296A1

公开(公告)日：2024-09-05

申请号：US18177467

申请日：2023-03-02

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Jin Shi ,  CHIH-YUAN LIN ,  Shu-Chih Chen ,  PEI-YI LIN ,  Chao Yuan Huang

IPC: G06F40/42 ,  G06F40/103 ,  G06F40/30

CPC classification number: G06F40/42 ,  G06F40/103 ,  G06F40/30

Abstract: Embodiments of the present disclosure relate to a method, system, and computer program product for translation of rich text. In some embodiments, a method is disclosed. According to the method, one or more candidate formats are determined for source rich text. A target format for the source rich text is selected from the one or more candidate formats based on one or more corresponding images obtained from rendering the source rich text in the one or more candidate formats. Based on the target format, a translation editing environment is provided for editing a translation of the source rich text. In other embodiments, a system and a computer program product are disclosed.

公开(公告)号：US20240265043A1

公开(公告)日：2024-08-08

申请号：US18430553

申请日：2024-02-01

Applicant: The Ark Project LLC

Inventor： Larry Ben Lytle ,  Larry Blanton Lytle ,  Narendran Muraleedharan ,  Bradley Hillstrom, Jr. ,  Joshua Banko ,  John Van Dyke ,  Spencer Beckwith ,  Rajbir Johar ,  David Lahtinen

IPC: G06F16/335 ,  G06F16/33 ,  G06F16/338 ,  G06F40/42

CPC classification number: G06F16/335 ,  G06F16/3344 ,  G06F16/3347 ,  G06F16/338 ,  G06F40/42

Abstract: Systems and methods are described for enabling a user to interact with an avatar representative of a target person. The avatar is configured to virtually embody audio, visual and behavioral characteristics of the target person and respond to the user's query based on the target person's life story. The user's query is presented in the form of audio based utterances. The target person's life story is processed in order to extract contextual, syntactic and semantic features related to the target person's audio, visual and linguistic characteristics.

公开(公告)号：US20240143943A1

公开(公告)日：2024-05-02

申请号：US18050191

申请日：2022-10-27

Applicant: Ford Global Technologies, LLC

Inventor： Saul Moreno ,  Aaron Lara

IPC: G06F40/42

CPC classification number: G06F40/42

Abstract: A system for distributing string length computation by a server computer coupled to a computer network. A server memory stores executable server instructions to receive a client request over the computer network at a server network endpoint, determine a pixel size of display text based on the string specification, and transmit a server response over the computer network. The client request includes a string specification with a display text, a font identifier, a font size, and a display resolution. The server response includes the pixel size of the display text.

公开(公告)号：US11889398B2

公开(公告)日：2024-01-30

申请号：US17865781

申请日：2022-07-15

Applicant: Kant AI Solutions LLC

Inventor： Gregory L. Rohde ,  Michael M. Kangior ,  Tyler S. Tappan

IPC: H04W4/90 ,  G06F40/30 ,  H04W76/50 ,  H04W4/021 ,  H04M3/51 ,  G06F40/42

CPC classification number: H04W4/90 ,  G06F40/30 ,  G06F40/42 ,  H04M3/5116 ,  H04W4/021 ,  H04W76/50

Abstract: A method and apparatus for providing emergency assistance includes receiving audio, visual, or text data about an ongoing emergency at a public safety answering point, comparing that data to a database of other emergencies with an artificial intelligence engine, recognizing patterns in aggregated and correlated data by the artificial intelligence engine, and generating appropriate audio, visual, and text output for a human operator to respond to the emergency. An AI engine receives audio data, visual data, and text data related to ongoing emergencies being received at public safety answering points and compares it with data from other emergencies. The AI engine identifies key words and patterns and generates appropriate messages for operators. The system continuously generates feedback to the AI engine to aid in machine learning. The feedback includes: “the message was correct; continue drawing this conclusion”; and “the message was wrong; do not continue drawing this conclusion.”

公开(公告)号：US11880361B2

公开(公告)日：2024-01-23

申请号：US16623993

申请日：2018-06-11

Applicant: ORANGE

Inventor： Julien Zimmermann ,  Emmanuel Bertin

IPC: G06F16/2452 ,  G06F16/242 ,  G06F40/42 ,  G06F40/58 ,  G16Y40/35 ,  H04L51/04

CPC classification number: G06F16/2452 ,  G06F16/243 ,  G06F40/42 ,  G06F40/58 ,  G16Y40/35 ,  H04L51/04

Abstract: A communication device associated with a transmitting entity and including: a first transmitting/receiving module capable of receiving, from the transmitting entity, a query formulated in a predetermined computer language or in a predetermined natural language; a translation module, activated if the query is formulated in the predetermined computer language, and configured to translate the query into the predetermined natural language; an extraction module configured to extract from the query formulated in the predetermined natural language at least one keyword representing the query; an identification module configured to identify, using the at least one keyword extracted, a target device supporting the predetermined natural language towards which to transmit the query; and a second transmitting/receiving module configured to transmit the query formulated in the natural language to the target device.

公开(公告)号：US11579826B2

公开(公告)日：2023-02-14

申请号：US17123898

申请日：2020-12-16

Applicant: BROTHER KOGYO KABUSHIKI KAISHA

Inventor： Ryoji Ban ,  Ryo Yasui ,  Satoki Nagao

IPC: G06F40/42 ,  G06F3/12 ,  G06F3/04845 ,  G06F40/166 ,  G06F3/0482

Abstract: A non-transitory computer-readable recording medium stores instructions executable by a controller of an information processing apparatus. The instructions cause the controller to perform operations. The operations include: displaying an edit screen, the edit screen being configured to receive a translation instruction, the edit screen including a text area and a print area, the print area being configured to place therein a target text string to be printed; upon receiving on the edit screen an operation for inputting the target text string, displaying the target text string in a first language in the text area; upon receiving on the edit screen the translation instruction for translating the target text string displayed in the text area from the first language into a second language, translating the target text string to obtain a translation data piece representing a translated text string in the second language.

公开(公告)号：US11568373B2

公开(公告)日：2023-01-31

申请号：US17363577

申请日：2021-06-30

Applicant: Giga Technologies

Inventor： Prasanna L. Narayan ,  Amarinder Bansal

IPC: G06Q20/08 ,  G06Q20/38 ,  G06Q40/02 ,  G06Q20/32 ,  G06Q20/10 ,  G06F40/42 ,  G06Q30/04 ,  G06Q30/00 ,  G06F9/54 ,  G06Q20/02

Abstract: A facility for facilitating payments from a client to a freelancer is described. The facility provides a mobile app enabling the freelancer to open an account and solicit payments by clients. In response, each client can use any of a variety of forms of electronic payments to pay into the account. The freelancer can use a debit card issued for the account to spend or withdraw payments made into the account, and can use the app to track requests for payment, payments, client activity, and spending and withdrawals from the account.

公开(公告)号：US20230029271A1

公开(公告)日：2023-01-26

申请号：US17382056

申请日：2021-07-21

Applicant: Karen Cahill

Inventor： Karen Cahill

IPC: G06F40/42 ,  G06F3/0488

Abstract: A two way communication assembly includes a display housing that is positionable on a support surface such that the display housing is visible to a pair of users. A pair of displays and a pair of qwerty keyboards is each integrated into opposite sides of the display housing. A translation unit is integrated into the display housing and the translation unit stores a database comprising a plurality of languages spoken around the world. The translation unit translates language between the qwerty keyboards to facilitate a patient who speaks a first language to communicate with a caregiver that speaks a second language. In this way the translation unit facilitates the caregiver to communicate with the patient.

公开(公告)号：US11551664B2

公开(公告)日：2023-01-10

申请号：US17737546

申请日：2022-05-05

Applicant: Deep Media Inc.

Inventor： Rijul Gupta ,  Emma Brown

IPC: G06F30/27 ,  G10L13/08 ,  G10L15/04 ,  G10L17/00 ,  G06F40/103 ,  G06T7/20 ,  G06F40/42

Abstract: A system and method for translating audio, and video when desired. The translations include synthetic media and data generated using AI systems. Through unique processors and generators executing a unique sequence of steps, the system and method produces more accurate translations that can account for various speech characteristics (e.g., emotion, pacing, idioms, sarcasm, jokes, tone, phonemes, etc.). These speech characteristics are identified in the input media and synthetically incorporated into the translated outputs to mirror the characteristics in the input media. Some embodiments further include systems and methods that manipulate the input video such that the speakers' faces and/or lips appear as if they are natively speaking the generated audio.