公开(公告)号：US12229525B2

公开(公告)日：2025-02-18

申请号：US18315654

申请日：2023-05-11

Applicant: AI21 LABS

Inventor： Barak Peleg ,  Dan Padnos ,  Amnon Morag ,  Gilad Lumbroso ,  Yoav Shoham ,  Ori Goshen ,  Barak Lenz ,  Or Dagan ,  Guy Einy

IPC: G06F40/30 ,  G06F3/0482 ,  G06F40/166 ,  G06F40/211 ,  G06F40/274 ,  G06F40/289 ,  G06F40/56 ,  G06F40/58 ,  G06F3/0486

Abstract: The presently disclosed embodiments may include a computer readable medium including instructions that when executed by one or more processing devices cause the one or more processing devices to perform a method. The method may include: identifying a location in an electronic document for at least one text insertion; automatically generating one or more text insertion options, based on a syntactic or semantic context of text in the electronic document before or after the identified location, and causing the one or more text insertion options to be displayed to the user; receiving, from a user, a selection of a text insertion option from among the one or more text insertion options; and causing the selected text insertion option to be included in the electronic document at a location that includes the identified location.

公开(公告)号：US20250053754A1

公开(公告)日：2025-02-13

申请号：US18925933

申请日：2024-10-24

Applicant: Casetext, Inc.

Inventor： Jake Heller ,  Pablo Arredondo ,  Walter DeFoor ,  Ryan Walker ,  Javed Qadrud-Din

IPC: G06F40/56 ,  G06F40/205

Abstract: A first set of text generation prompts may be determined based on an input document and a first text generation prompt template. The first text generation prompts may include an instruction to identify factual assertions in the input text. The prompt may be sent to a remote text generation modeling system, which may respond by identifying factual assertions in the input text. A second text generation prompt may be determined based on the factual assertions and a second text generation prompt template. The second text generation prompt may include an instruction to respond to the factual assertions. A response to the input text may be generated based on written responses provided by the remote text generation modeling system.

公开(公告)号：US20250045520A1

公开(公告)日：2025-02-06

申请号：US18923851

申请日：2024-10-23

Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED

Inventor： William TUNSTALL-PEDOE ,  Robert HEYWOOD ,  Seth WARREN ,  Paul BENN ,  Duncan REYNOLDS ,  Ayush SHAH ,  Luci KRNIC ,  Ziyi ZHU

IPC: G06F40/20 ,  G06F16/33 ,  G06F40/56

Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.

公开(公告)号：US12217013B2

公开(公告)日：2025-02-04

申请号：US17937616

申请日：2022-10-03

Applicant: UnitedHealth Group Incorporated

Inventor： Rajesh Sabapathy ,  Chirag Mittal ,  Gourav Awasthi ,  Aditya Teja Josyula

IPC: G06F40/56 ,  G06F40/247 ,  G06F40/30 ,  G06F40/35 ,  G06N5/022

Abstract: There is a need for more effective and efficient predictive natural language summarization. This need is addressed by applying hybrid extractive and abstractive summarization techniques in a unique processing pipeline to generate a cohesive and comprehensive summary of a multi-party interaction. A method for generating the summary of a multi-party interaction includes receiving a multi-party interaction transcript data object comprising a plurality of interaction utterances from at least two participants; using an extractive summarization model to identify a key sentence of the multi-party interaction transcript data object; identifying an interaction utterance from the multi-party interaction transcript data object that corresponds to the key sentence; generating a contextual summary for the multi-party interaction transcript data object based at least in part on the interaction utterance; and generating a reported contextual summary for the multi-party interaction transcript data object based at least in part on the contextual summary.

公开(公告)号：US12214284B2

公开(公告)日：2025-02-04

申请号：US18331365

申请日：2023-06-08

Applicant: SQUARE ENIX CO., LTD.

Inventor： Youichiro Miyake ,  Shinpei Sakata

IPC: A63F13/60 ,  A63F13/45 ,  A63F13/54 ,  A63F13/85 ,  G06F40/56

Abstract: A computer is caused to execute: acquiring the log; generating a natural sentence based on the acquired log; and generating story content to be appreciated by a user by arranging the generated natural sentence and one or a plurality of game-related contents that are related to the log.

公开(公告)号：US20250036888A1

公开(公告)日：2025-01-30

申请号：US18793988

申请日：2024-08-05

Applicant: Salesforce, Inc.

Inventor： Andrew R. Paley ,  Nathan Drew Nichols ,  Matthew Lloyd Trahan ,  Maia Jane Lewis Meza ,  Lawrence A. Birnbaum ,  Kristian J. Hammond

IPC: G06F40/56 ,  G06F16/36 ,  G06F40/106 ,  G06F40/166 ,  G06F40/169 ,  G06F40/174 ,  G06F40/20 ,  G06F40/295 ,  G06F40/30 ,  G06N5/02 ,  G06N5/025 ,  G06N5/043 ,  G06Q10/10

Abstract: Artificial intelligence (AI) technology can be used process natural language statements to facilitate the automated generation of narratives about data sets that achieve a desired communication goal without any need for a user to directly author computer code. This AI technology permits NLG systems to determine the appropriate content for inclusion in the narrative in a manner that will satisfy the desired communication goal.

公开(公告)号：US20250005304A1

公开(公告)日：2025-01-02

申请号：US18215517

申请日：2023-06-28

Applicant: JPMorgan Chase Bank, N.A.

Inventor： Ruibo SHI ,  Agathe LHÉRONDELLE ,  Denis KOCHEDYKOV

IPC: G06F40/56 ,  G06F40/35

Abstract: A method and a system for automatic generation of conversation samples for training machine learning-based dialogue managers by using conversation graphs are provided. The method includes: receiving a conversational flow that relates to a conversation; converting the conversational flow into a graphical representation of the conversation; using the graphical representation to determine a set of paths that relate to possible realizations of potential user interactions with respect to the conversation; and generating conversation samples that correspond to the set of paths.

公开(公告)号：US12175195B2

公开(公告)日：2024-12-24

申请号：US17382067

申请日：2021-07-21

Applicant: Pandemic Insights, Inc.

Inventor： Eric Klasson

IPC: G06F40/30 ,  G06F16/29 ,  G06F40/56 ,  G06N20/00 ,  G06Q10/105 ,  G06Q10/1093 ,  G16H10/60 ,  G16H10/65 ,  G16H15/00 ,  G16H40/20 ,  G16H40/67 ,  G16H50/20 ,  G16H50/30 ,  G16H50/70 ,  G16H50/80 ,  G16H80/00 ,  H04L51/222 ,  H04W4/02 ,  H04W4/021 ,  H04W4/029 ,  H04W12/03 ,  H04W12/033 ,  G16H10/20

Abstract: Provided is a process, including: obtaining, with a computer system, a next geolocation to be visited by a user or at which the user has arrived; obtaining, with the computer system, a geolocation-pathogen-risk score of the next geolocation; determining, with the computer system, a topic of message based on the geolocation-pathogen-risk score; determining, with the computer system, by a natural-language-text generation model, natural language text within the topic of the message; and causing, with the computer system, the natural language text of the message to be presented to the user.

公开(公告)号：US12164868B2

公开(公告)日：2024-12-10

申请号：US18648788

申请日：2024-04-29

Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED

Inventor： William Tunstall-Pedoe ,  Robert Heywood ,  Seth Warren ,  Paul Benn ,  Duncan Reynolds ,  Ayush Shah ,  Luci Krnic ,  Ziyi Zhu

IPC: G06F40/20 ,  G06F16/33 ,  G06F40/56

Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.

公开(公告)号：US12159119B2

公开(公告)日：2024-12-03

申请号：US18169707

申请日：2023-02-15

Applicant: Casetext, Inc.

Inventor： Jake Heller ,  Pablo Arredondo ,  Walter DeFoor ,  Ryan Walker ,  Javed Qadrud-Din

IPC: G06F40/56 ,  G06F40/205

Abstract: A first set of text generation prompts may be determined based on an input document and a first text generation prompt template. The first set of text generation prompts may include an instruction to identify factual assertions in the input text. The prompts may be sent to a remote text generation modeling system, which may respond by identifying factual assertions in the input text. A second set of text generation prompts may be determined based on the factual assertions and a second text generation prompt template. The second set of text generation prompts may include an instruction to respond to the factual assertions. A response to the input text may be generated based on written responses provided by the remote text generation modeling system.