-
公开(公告)号:US20240362406A1
公开(公告)日:2024-10-31
申请号:US18768208
申请日:2024-07-10
申请人: Canva Pty Ltd
IPC分类号: G06F40/166 , G06F40/10 , G06F40/205 , G06F40/279 , G06V30/10
CPC分类号: G06F40/166 , G06F40/205 , G06F40/279 , G06V30/10 , G06F40/10
摘要: Described herein is a computer implemented method. The method includes accessing, by a computer system including a processing unit, portable document format (PDF) data defining a plurality of glyphs, sorting the plurality of glyphs into one or more glyph sets, and calculating an expanded glyph bounding box for each glyph. Each glyph set is processed to determine one or more text areas, each text area being associated with one or more glyphs from the glyph set which have collectively overlapping expanded bounding boxes.
-
公开(公告)号:US12130868B2
公开(公告)日:2024-10-29
申请号:US17848721
申请日:2022-06-24
申请人: Heather Rose Walters
发明人: Heather Rose Walters
IPC分类号: G06F16/93 , G06F3/04842 , G06F16/951 , G06F40/166
CPC分类号: G06F16/93 , G06F3/04842 , G06F16/951 , G06F40/166
摘要: A platform to provide content to reader users and to gather content from writer users. The platform provides user interfaces to reader users displaying one or more titles accessible by the reader user, receives a user content input through the user interface identifying selection of a title, presents a first content block from the title to the reader user one or more buttons to indicate alternative storylines in the titles, and repeats until a final content block is accessed: receiving a button selection from the reader user through the user interface; and loading a next content block indicated by the button selection. The platform provides a title user interface to a writer user for a new title, receives title information for the new title, presents a writing user interface to the writer user, and repeats, until the receiving an input from the writer user indicating completion: receiving one or more user inputs containing a content block from the writer user through the user interface and text labels for one or more buttons associated with the content block; and generating tracking lines linking the content block to the buttons. The platform then associates the content blocks, buttons and tracking lines with the title and stores them in a database when the writer user indicates completion.
-
公开(公告)号:US20240354491A1
公开(公告)日:2024-10-24
申请号:US18476365
申请日:2023-09-28
申请人: YAHOO ASSETS LLC
IPC分类号: G06F40/166 , G06F40/20
CPC分类号: G06F40/166 , G06F40/20
摘要: Disclosed embodiments are directed toward a computer-implemented system and method for providing an email digest in association with an interface display of an electronic inbox. The disclosed digest includes non-native inbox functionality related to a summary data structure that includes an interactive portion, whereby upon generation of electronic prompts via a large language model (LLM), the digest can leverage functionality of the LLM to determine how electronic inbox content can be rendered for display.
-
公开(公告)号:US20240354179A1
公开(公告)日:2024-10-24
申请号:US18763661
申请日:2024-07-03
申请人: PagerDuty, Inc.
IPC分类号: G06F9/54 , G06F16/33 , G06F16/35 , G06F40/166 , G06F40/211 , G06F40/279 , G06F40/284 , G06F40/30
CPC分类号: G06F9/542 , G06F16/3347 , G06F16/353 , G06F40/211 , G06F40/279 , G06F40/284 , G06F40/30 , G06F40/166
摘要: A machine learning model is applied to extract keywords from an event associated with network operations. A keyword vector is constructed where each keyword extracted is represented as a unique dimension in the keyword vector. The keyword vector is compared against event category vectors associated with event categories to identify potential matches. A relevance score is calculated for each category based on the comparing. The event is classified into one or more categories based on the relevance scores exceeding a predetermined threshold. A user interface configured to visually display and obtain feedback regarding the classifying is generated. At least one of the event categories is updated based on a user feedback received via the user interface and machine learning retraining.
-
公开(公告)号:US12125487B2
公开(公告)日:2024-10-22
申请号:US17450551
申请日:2021-10-11
申请人: SoundHound, Inc.
发明人: Kiersten L. Bradley , Ethan Coeytaux , Ziming Yin
IPC分类号: G10L15/26 , G06F40/134 , G06F40/166 , G06F40/284 , G10L15/02 , G10L15/06 , G10L15/07
CPC分类号: G10L15/26 , G06F40/134 , G06F40/166 , G06F40/284 , G10L15/02 , G10L15/063 , G10L15/07 , G10L2015/0631
摘要: Methods and systems for enabling an efficient review of meeting content via a metadata-enriched, speaker-attributed and multiuser-editable transcript are disclosed. By incorporating speaker diarization and other metadata, the system can provide a structured and effective way to review and/or edit the transcript by one or more editors. One type of metadata can be image or video data to represent the meeting content. Furthermore, the present subject matter utilizes a multimodal diarization model to identify and label different speakers. The system can synchronize various sources of data, e.g., audio channel data, voice feature vectors, acoustic beamforming, image identification, and extrinsic data, to implement speaker diarization.
-
公开(公告)号:US12124490B2
公开(公告)日:2024-10-22
申请号:US17451832
申请日:2021-10-22
IPC分类号: G06F16/35 , G06F16/33 , G06F16/383 , G06F40/166 , G06Q30/018
CPC分类号: G06F16/35 , G06F16/3335 , G06F16/383 , G06F40/166 , G06Q30/018
摘要: Predicting potential policy violations in a given data source (such as a set of documents) so that a deeper analysis can be performed on the set of documents to gain additional insights into the potential policy violation(s) that may be contained therein. In some instances, this prediction is done by performing a random sampling operation on the set of documents and collecting the metadata from these documents in order to determine whether or not the set of documents that are randomly sampled include a policy violation that can be remediated.
-
公开(公告)号:US20240346946A1
公开(公告)日:2024-10-17
申请号:US18638162
申请日:2024-04-17
申请人: Acapedia, LLC
发明人: Alexander S. PASCIAK
IPC分类号: G09B7/06 , G06F40/166 , G06F40/40
CPC分类号: G09B7/06 , G06F40/166 , G06F40/40
摘要: Systems, devices, methods, and instructions for generation of content for an education application, including periodically web-scraping a repository of learning content, storing the learning content and corresponding information, language processing the learning content using a neural network architecture, using artificial intelligence or machine learning to summarize the learning content, and using artificial intelligence or machine learning to generate one or more questions and answers for the education application based on the learning content.
-
8.
公开(公告)号:US20240346238A1
公开(公告)日:2024-10-17
申请号:US18638075
申请日:2024-04-17
申请人: GONG.io Ltd.
发明人: Eyal BEN-DAVID , Inbal HOREV , Raz NUSSBAUM , Adi KOPILOV , Nadav Shai Oved SHALEV , Shlomi MEDALION
IPC分类号: G06F40/166 , G06F16/34
CPC分类号: G06F40/166 , G06F16/345
摘要: Techniques for efficiently generating a brief of a call summary is provided. The method includes ingesting at least one simplified transcript, wherein a simplified transcript is a summarization of a transcript of a call and includes a plurality of bullet points of at least one main subject; representing each bullet point of the plurality of bullet points of the simplified transcript as an embedded vector using an embedding technique; determining at least one grouping of the plurality of bullet points based on the embedded vector, wherein the grouping includes at least one bullet point; feeding the at least one grouping into a trained rephrasing model to generate a rephrased content for each of the at least one grouping; and generating a summarized brief based on the rephrased content of the at least one grouping, wherein the summarized brief is generated as natural language textual data below a predetermined length.
-
公开(公告)号:US20240346237A1
公开(公告)日:2024-10-17
申请号:US18637896
申请日:2024-04-17
发明人: Haruyoshi HINO
IPC分类号: G06F40/166 , G06F16/332 , G06F16/9538 , G06T11/00 , G06T13/80
CPC分类号: G06F40/166 , G06F16/3329 , G06F16/9538 , G06T11/00 , G06T13/80
摘要: Using communicative human language information inputted through the User Interface (UI), an LLM (Language Learning Model) acquires communicative human language information to include in the content. Simultaneously, using the communicative human language information inputted through the UI, the LLM acquires information for selecting visualization software capable of generating visual information to include in the content. Based on the acquired communicative human language information, the visualization software is selected. According to the communicative human language information inputted through the UI, the selected visualization software is operated based on the text information acquired from the LLM's output. Visual information for inclusion in the content is acquired, and content containing at least a part of the acquired communicative human language information and at least a part of the acquired visual information is generated and outputted.
-
公开(公告)号:US20240346235A1
公开(公告)日:2024-10-17
申请号:US18300813
申请日:2023-04-14
IPC分类号: G06F40/166 , G06F16/23 , G06F16/958 , G06F40/14 , G06F40/197 , G06F40/30
CPC分类号: G06F40/166 , G06F16/2365 , G06F16/986 , G06F40/14 , G06F40/197 , G06F40/30
摘要: Systems and techniques that facilitate context-aware edit management of webpage-based applications are provided. In various embodiments, a system can detect an edit made to a webpage. In various aspects, the system can determine whether a webpage-based application associated with the webpage is consistent with the edit, based on a registry that respectively maps outputs of the webpage-based application to source texts and corresponding semantic contexts of a pre-edit version of the webpage.
-
-
-
-
-
-
-
-
-