公开(公告)号：US20250071157A1

公开(公告)日：2025-02-27

申请号：US18238414

申请日：2023-08-25

Applicant: Sony Interactive Entertainment America LLC ,  SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Brielle Powell ,  Celeste Bean ,  Victoria Walker ,  Olga Rudi ,  Steven Osman

IPC: H04L65/403 ,  G06F3/0482 ,  G06F40/169

Abstract: Systems and methods of intelligent reporting within online communities are provided. A current communication session associated with a plurality of user device may be monitored. The current communication session may include a stream of audio-visual content generated in real-time based on interactions between the user devices. A recording trigger may be detected within the current communication session. A recording of a portion of the stream of audio-visual content may be recorded in response to the detected trigger event. The recording may be analyzed to attribute one or more sub-portions within the recording to one or more of the user devices. At least one of the sub-portions attributed to an identified one of the user devices may be determined to meet a moderation event. A report regarding the identified user device may be generated that includes the at least one sub-portion that meets the moderation event.

公开(公告)号：US20250068978A1

公开(公告)日：2025-02-27

申请号：US18941229

申请日：2024-11-08

Applicant: State Farm Mutual Automobile Insurance Company

Inventor： Sambasiva R. Murakonda ,  Theodore Edward Dorner

IPC: G06N20/00 ,  G06F3/0482 ,  G06F3/04847 ,  G06F40/169 ,  G06N5/04

Abstract: A data pipeline tool provides a machine-learning design interface that a user can utilize (e.g., via an electronic device such as a personal computer, tablet, or smart phone) to design or configure data pipelines or workflows defining the manner in which ML models are developed, trained, tested, validated, or deployed. Once deployed, a designed ML model may generate predictive results based on input data fed to the ML model. The tool may present the predictive results via a GUI, and may enable a user to mark-up or otherwise interact with those predictive results. The tool may enable the user to share the results (which may include a mark-up or annotation provided by a user).

公开(公告)号：US12236263B2

公开(公告)日：2025-02-25

申请号：US15236148

申请日：2016-08-12

Applicant: Imagination Technologies Limited

Inventor： Stephen John Clohset ,  James Alexander McCombe ,  Luke Tilman Peterson

IPC: G06F9/48 ,  G06F9/50 ,  G06F40/169 ,  G06T15/00 ,  G06T15/06

Abstract: In some aspects, finer grained parallelism is achieved by segmenting programmatic workloads into smaller discretized portions, where a first element can be indicative both of a configuration or program to be executed, and a first data set to be used in such execution, while a second element can be indicative of a second data element or group. The discretized portions can cause program execute on distributed processors. Approaches to selecting processors, and allocating local memory associated with those processors are disclosed. In one example, discretized portions that share a program have an anti-affinity to cause dispersion, for initial execution assignment. Flags, such as programmer and compiler generated flags can be used in determining such allocations. Workloads can be grouped according to compatibility of memory usage requirements.

公开(公告)号：US12236184B2

公开(公告)日：2025-02-25

申请号：US17531479

申请日：2021-11-19

Applicant: Bluebeam, Inc.

Inventor： Jack Kutilek ,  Elliot Chenault

IPC: G06F40/169 ,  G06T11/60

Abstract: A method of computerized presentation of a legend of object symbols on a document. The method includes receiving a document having object symbols. Each object symbol includes a graphical representation, an object symbol type and an object type numerical value. The method includes generating one or more groups of object symbols of the one or more object symbols based upon the object symbol type of each of the object symbols. The method includes deriving a group cumulative quantity for each group of object symbols based upon the object type numerical value of each object symbol in each group of object symbols. The method includes generating a legend including a one or more legend entries corresponding to each of the one or more groups of object symbols. Each legend entry includes a group type symbol, the object symbol type, and a group cumulative quantity. The method includes displaying the legend.

公开(公告)号：US12236148B2

公开(公告)日：2025-02-25

申请号：US18464013

申请日：2023-09-08

Applicant: Snap Inc.

Inventor： Timothy Sehn

IPC: G06F3/14 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04883 ,  G06F3/0489 ,  G06F40/169 ,  G06T11/60 ,  G11B27/031 ,  G11B27/32 ,  H04L51/10 ,  H04L51/214 ,  H04L51/52 ,  H04L69/329

Abstract: A machine includes a processor and a memory connected to the processor. The memory stores instructions executed by the processor to receive a message and a message parameter indicative of a characteristic of the message, where the message includes a photograph or a video. A determination is made that the message parameter corresponds to a selected gallery, where the selected gallery includes a sequence of photographs or videos. The message is posted to the selected gallery in response to the determination. The selected gallery is supplied in response to a request.

公开(公告)号：US20250053728A1

公开(公告)日：2025-02-13

申请号：US18446812

申请日：2023-08-09

Applicant: Microsoft Technology Licensing, LLC

Inventor： David J. CONGER ,  Iman Abdullahi YUSUF ,  Fnu PRIMADONA ,  Eric ANDERSON

IPC: G06F40/169 ,  G06V30/10

Abstract: A device for generating archival notes for a user based on content a user has located electronically and viewed on a display device includes: a display for presenting information to a user, a user interface for receiving user input from the user; a processor; and a memory storing executable instructions which, when executed by the processor, cause the processor, alone or in combination with other processors, to perform the following: capturing information on the display; operating a prompt generator to structure a prompt for a generative Artificial Intelligence (AI) model, the prompt based on the information captured from the display and causing the AI model to generate a note based on the information captured; and storing the note in a user data structure for future reference by the user.

公开(公告)号：US12223944B2

公开(公告)日：2025-02-11

申请号：US17744440

申请日：2022-05-13

Applicant: GOOGLE LLC

Inventor： Martin Baeuml ,  Thushan Amarasiriwardena ,  Roberto Pieraccini ,  Gianluca Martini

IPC: G06F40/56 ,  G06F3/16 ,  G06F16/332 ,  G06F40/169 ,  G06T7/20 ,  G06V20/40 ,  G06V40/20 ,  G10L13/02 ,  G10L13/033 ,  G10L13/08 ,  G10L13/10 ,  G10L15/06 ,  G10L15/18 ,  G10L15/183 ,  G10L15/22 ,  G10L25/57 ,  H04N5/04

Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

公开(公告)号：US20250045306A1

公开(公告)日：2025-02-06

申请号：US18922970

申请日：2024-10-22

Applicant: Twilio Inc.

Inventor： Luke Percival de Oliveira ,  Umair Akeel ,  Alfredo Láinez Rodrigo ,  Nicolas Acosta Amador ,  Sahil Kumar ,  Liat Barda Dremer ,  Byeongung Ahn ,  Tyler Cole

IPC: G06F16/332 ,  G06F16/383 ,  G06F40/169 ,  G06F40/295 ,  G06N20/00 ,  G10L15/26

Abstract: Methods, systems, and computer programs are presented for searching the content of voice conversations. The conversations are translated into text and analysis of the conversation is performed to identify information in the conversation. The information identified includes turns taking data in the conversation and states identified within each state. A powerful user interface (UI) is provided to review the conversations and add annotations that tag the different turns. Additionally, parameter values are extracted from the text. A powerful search engine is provided with multiple search options, such as searching for text, searching by state within the conversation, searching by parameters extracted from the conversation, or a combination thereof.

公开(公告)号：US12216983B2

公开(公告)日：2025-02-04

申请号：US17594217

申请日：2020-09-29

Applicant: Google LLC

Inventor： Ajit Narayanan ,  Lei Shi

IPC: G06F40/117 ,  G06F16/34 ,  G06F40/137 ,  G06F40/169 ,  G06F40/205 ,  G06F40/30

Abstract: A method includes obtaining a text document, generating a first mark-up of the text document by a first natural language processing (NLP) model, and displaying the text document and the first mark-up. The method also includes receiving a user interaction with a portion of the first mark-up. The portion of the first mark-up of the text document may be associated with a portion of the text document. The method additionally includes, based on the user interaction with the portion of the first mark-up, selecting a second NLP model by which to process the portion of the text document, where the second NLP model is different from the first NLP model. The method further includes, based on selecting the second NLP model, generating a second mark-up of the text document by processing at least the portion thereof by the second NLP model, and displaying the text document and the second mark-up.

公开(公告)号：US12210830B2

公开(公告)日：2025-01-28

申请号：US17750240

申请日：2022-05-20

Applicant: Oracle International Corporation

Inventor： Thanh Tien Vu ,  Tuyen Quang Pham ,  Mark Edward Johnson ,  Thanh Long Duong ,  Ying Xu ,  Poorya Zaremoodi ,  Omid Mohamad Nezami ,  Budhaditya Saha ,  Cong Duy Vu Hoang

IPC: G06F40/30 ,  G06F40/169 ,  G06F40/284 ,  G06F40/295

Abstract: In some aspects, a computing device may receive, at a data processing system, a set of utterances for training or inferencing with a named entity recognizer to assign a label to each token piece from the set of utterances. The computing device may determine a length of each utterance in the set and when the length of the utterance exceeds a pre-determined threshold of token pieces: dividing the utterance into a plurality of overlapping chunks of token pieces; assigning a label together with a confidence score for each token piece in a chunk; determining a final label and an associated confidence score for each chunk of token pieces by merging two confidence scores; determining a final annotated label for the utterance based at least on the merging the two confidence scores; and storing the final annotated label in a memory.