公开(公告)号：US12001792B2

公开(公告)日：2024-06-04

申请号：US17972411

申请日：2022-10-24

申请人： Google LLC

发明人： Vishnu Sivaji ,  Steven Joseph Saviano ,  Andrea Dulko

IPC分类号： G06F40/258 ,  G06F16/34 ,  G06F40/103 ,  G06F40/106 ,  G06F40/131 ,  G06F40/186 ,  G06N20/00 ,  G06F40/151 ,  G06F40/177

CPC分类号： G06F40/258 ,  G06F16/345 ,  G06F40/103 ,  G06F40/106 ,  G06F40/131 ,  G06F40/186 ,  G06N20/00 ,  G06F40/151 ,  G06F40/177

摘要： A method for generating presentation slides with distilled content including receiving one or more data files as source material for slide generation, obtaining content from the one or more data files for a slide of a slide presentation, identifying a layout template for the slide based on the content, and distilling the content into distilled content to generate a presentation visualization item based on the distilled content. The distilled content may include a subset of the content. The method may also include generating the slide based on the presentation visualization item and the layout template.

公开(公告)号：US12001486B2

公开(公告)日：2024-06-04

申请号：US16583372

申请日：2019-09-26

申请人： International Business Machines Corporation

发明人： Martin Oberhofer ,  Joerg Rehr ,  Ivan Matthew Milman ,  Sushain Pandit

IPC分类号： G06F40/106 ,  G06F16/906 ,  G06F16/907 ,  G06F18/21 ,  G06F18/214 ,  G06F40/258 ,  G06F40/279 ,  G06F40/284 ,  G06N20/00 ,  G06V30/19 ,  G06V30/412

CPC分类号： G06F16/906 ,  G06F16/907 ,  G06F18/2148 ,  G06F18/2178 ,  G06F40/106 ,  G06F40/258 ,  G06F40/279 ,  G06F40/284 ,  G06N20/00 ,  G06V30/19173 ,  G06V30/412

摘要： A method, system, and computer program product for identifying reference data values in a source data set. The method may include inputting a block of attribute values to a predefined machine learning model. The method may also include receiving an indication of a presentation layout of the block of the attribute values and an associated reference data extraction method. The method may also include determining a reading direction of the block of values. The method may also include identifying one or more inspection areas in the reading direction of the block of values. The method may also include determining sets of the one or more inspection areas that share a common presentation feature. The method may also include identifying tokens in an inspection area. The method may also include determining if the inspection area includes reference data values. The method may also include outputting the reference data values.

公开(公告)号：US11893337B2

公开(公告)日：2024-02-06

申请号：US17333953

申请日：2021-05-28

申请人： Vikas Balwant Joshi

发明人： Vikas Balwant Joshi

IPC分类号： G06F40/103 ,  G06F16/34 ,  G06F40/258

CPC分类号： G06F40/103 ,  G06F16/345 ,  G06F40/258

摘要： Disclosed is a method of generating a multi-level summary of an article. The method may comprise generating, by a computing device, a low-level summary from article-matter in an article. The method may also comprise generating, by the computing device, a mid-level summary based on the low-level summary and the article-matter. The method may also comprise generating, by the computing device, an upper-level summary based on the mid-level summary, the low-level summary, and the article-matter.

公开(公告)号：US20230360421A1

公开(公告)日：2023-11-09

申请号：US18215614

申请日：2023-06-28

申请人： Wells Fargo Bank, N.A.

发明人： Qun Luo ,  Andrew Mack

IPC分类号： G06V30/414 ,  G06F40/216 ,  G06N3/04 ,  G06F40/258 ,  G06V30/416 ,  G06F40/284 ,  G06F18/2411 ,  G06N3/09

CPC分类号： G06V30/414 ,  G06F40/216 ,  G06N3/04 ,  G06F40/258 ,  G06V30/416 ,  G06F40/284 ,  G06F18/2411 ,  G06N3/09

摘要： Disclosed are systems, methods, and computer readable media for natural language processing and text analytics of audit documentation for prioritization and selection. Text extraction and conversion techniques can analyze documents corresponding to an audit request to generate a dataset. A two-layer model can produce word embeddings to reconstruct linguistic contexts of words in the dataset. An embedding layer can map each word, and a classifier layer can generate a similarity score for each word. A three-layer model can determine weights of documents in the dataset. A ranking layer can obtain a document rank value for each document. An initial layer and successive layers can receive feature vectors and document rank values to assign weights to the documents. Based on the document weights and the audit request, the natural language processing and text analytics can determine an audit likelihood for each document to prioritize and select subsets of the documents.

公开(公告)号：US11803694B1

公开(公告)日：2023-10-31

申请号：US16273585

申请日：2019-02-12

申请人： West Corporation

发明人： Gretel Baumgartner ,  Nathaniel Brogan ,  Nickolas Heckman ,  Joshua M. Heizman ,  Benjamin P. Hencke ,  Sean Michael Kelly ,  Ronald Park ,  Howard A. Wood

IPC分类号： G06F40/14 ,  G06F40/10 ,  G06F40/16 ,  G06F40/103 ,  G06F40/131 ,  G06F40/134 ,  G06F40/258

CPC分类号： G06F40/14 ,  G06F40/10 ,  G06F40/103 ,  G06F40/131 ,  G06F40/134 ,  G06F40/16 ,  G06F40/258

摘要： Electronic documents may be large and have numerous pages, sections and areas of information that are useful to some individuals and not others. It is common for large documents to include some information that is intended for only certain recipients and other information that is intended for other recipients. One example may provide receiving a document including a number of pages, identifying a number of extraction attributes corresponding to various users identified in the document, querying the document for the extraction attributes, and creating a number of new documents corresponding to the extraction attributes.

公开(公告)号：US12056201B2

公开(公告)日：2024-08-06

申请号：US18305277

申请日：2023-04-21

申请人： Capital One Services, LLC

发明人： Elijah Taylor Moreau-Arnott

IPC分类号： G06F17/00 ,  G06F3/0483 ,  G06F16/23 ,  G06F16/955 ,  G06F40/205 ,  G06F40/258

CPC分类号： G06F16/9562 ,  G06F3/0483 ,  G06F16/2379 ,  G06F16/9558 ,  G06F40/205 ,  G06F40/258

摘要： A dynamic browser bookmark system configured to present a user's bookmarks in a hierarchical manner based on webpage contextual data is disclosed. The system may aggregate browser bookmarks associated with a user device. The system may determine a first webpage being viewed on the user device. The system may dynamically filter the browser bookmarks to determine a first plurality of browser bookmarks associated with the first webpage. The system may generate and transmit a graphical user interface including a hierarchical view of the browser bookmarks. The system may determine a second webpage being viewed on the user device and dynamically filter the aggregated browser bookmarks to determine a second plurality of browser bookmarks relevant to the second webpage, which may include a browser bookmark of the first plurality of browser bookmarks, and generate a second graphical user interface including a hierarchical view of the second plurality of browser bookmarks.

公开(公告)号：US12051257B2

公开(公告)日：2024-07-30

申请号：US18215614

申请日：2023-06-28

申请人： Wells Fargo Bank, N.A.

发明人： Qun Luo ,  Andrew Mack

IPC分类号： G06N3/09 ,  G06F18/2411 ,  G06F40/216 ,  G06F40/258 ,  G06F40/284 ,  G06N3/04 ,  G06N3/045 ,  G06V30/414 ,  G06V30/416

CPC分类号： G06V30/414 ,  G06F18/2411 ,  G06F40/216 ,  G06F40/258 ,  G06F40/284 ,  G06N3/04 ,  G06N3/045 ,  G06N3/09 ,  G06V30/416

摘要： Disclosed are systems, methods, and computer readable media for natural language processing and text analytics of audit documentation for prioritization and selection. Text extraction and conversion techniques can analyze documents corresponding to an audit request to generate a dataset. A two-layer model can produce word embeddings to reconstruct linguistic contexts of words in the dataset. An embedding layer can map each word, and a classifier layer can generate a similarity score for each word. A three-layer model can determine weights of documents in the dataset. A ranking layer can obtain a document rank value for each document. An initial layer and successive layers can receive feature vectors and document rank values to assign weights to the documents. Based on the document weights and the audit request, the natural language processing and text analytics can determine an audit likelihood for each document to prioritize and select subsets of the documents.

公开(公告)号：US20240062001A1

公开(公告)日：2024-02-22

申请号：US18497623

申请日：2023-10-30

申请人： Thomson Reuters Enterprise Centre GmbH

发明人： Richard Anthony Pito

IPC分类号： G06F40/279 ,  G06F3/0481 ,  G06F40/109 ,  G06F40/137 ,  G06F40/166 ,  G06F40/232 ,  G06F40/242 ,  G06F40/258 ,  G06F40/284 ,  G06F40/289 ,  G06V30/416

CPC分类号： G06F40/279 ,  G06F3/0481 ,  G06F40/109 ,  G06F40/137 ,  G06F40/166 ,  G06F40/232 ,  G06F40/242 ,  G06F40/258 ,  G06F40/284 ,  G06F40/289 ,  G06V30/416

摘要： The present disclosure is directed towards systems and methods for extracting structure and headers from a body of text. This computational extraction is based on the visual and logical similarities between portions of text. Boilerplate is removed from chunks of text making up potential headers and the cleaned result is compared against other potential headers and the remainder of the body of text.

公开(公告)号：US11765112B2

公开(公告)日：2023-09-19

申请号：US17364970

申请日：2021-07-01

申请人： VMware, Inc.

发明人： Arjun Kochhar ,  Suman Aluvala ,  Arvind Maan ,  Nitin Sethi ,  Ramesh Pilla ,  Shree Harsha Shedigumme

IPC分类号： H04L51/02 ,  H04L12/58 ,  H04L51/063 ,  H04L51/046 ,  G06Q10/107 ,  G06F40/216 ,  G06F40/258 ,  G06F40/268 ,  G06F40/56 ,  G06F16/9032

CPC分类号： H04L51/063 ,  G06F40/216 ,  G06F40/258 ,  G06F40/268 ,  G06Q10/107 ,  H04L51/046

摘要： Disclosed are various approaches for dynamically creating content to present to a user based on an identified intent, or other context, associated with a message (e.g., email). A message that is received from a message server can be analyzed to identify the message content within the message prior to distributing to the recipient client device. Trained intent identification models can be applied to the identified message content to determine an intent, or other type of context, associated with the message. Upon identifying the intent, the message header can be modified to include the intent prior to forwarding the message to the recipient client device. The client device can then display a user interface including the message and a user interface element corresponding to a third-party service. The user interface element can be dynamically generated to include an action component that upon selection, triggers an action associated with the intent.

公开(公告)号：US11727702B1

公开(公告)日：2023-08-15

申请号：US18098055

申请日：2023-01-17

申请人： Velocity EHS Inc.

发明人： Julia Penfield ,  Aatish Suman ,  Veeru Talreja ,  Misbah Zahid Khan

IPC分类号： G06V10/82 ,  G06V30/24 ,  G06F40/205 ,  G06F40/284 ,  G06F40/258 ,  G06F40/295 ,  G06V30/19 ,  G06V30/413

CPC分类号： G06V30/2528 ,  G06F40/205 ,  G06F40/258 ,  G06F40/284 ,  G06F40/295 ,  G06V10/82 ,  G06V30/19147 ,  G06V30/413

摘要： Systems and methods for automated indexing and extraction of information in digital documents are disclosed. A method may comprise selecting a page number of a digital document to identify a page containing targeted information; inputting an image of the page into a visual machine learning network (visual ML), wherein the visual ML is trained to recognize text associated with the targeted information in an image; identifying by the visual ML, a section of the image that contains the targeted information; inputting the page number, the digital document, and coordinates of the section into an extraction module; and extracting the targeted information by the extraction module from the section.