-
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
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
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.
-
4.
公开(公告)号:US20230360421A1
公开(公告)日:2023-11-09
申请号:US18215614
申请日:2023-06-28
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:US11580291B2
公开(公告)日:2023-02-14
申请号:US16922141
申请日:2020-07-07
申请人: RELATIVITY ODA LLC
发明人: Vladyslav Andrusenko
IPC分类号: G06F16/93 , G06F40/103 , G06F40/123 , G06F40/205 , G06F40/258
摘要: A computer-implemented method for resolving date ambiguities in electronic communication documents includes identifying, within the documents, date field values each associated with a different instance of a communication segment. The method also includes resolving a candidate date for each different communication segment instance, with each candidate date being associated with a respective priority level indicative of a level of certainty with which the candidate date was resolved, and determining a final date from among the candidate dates at least by comparing the respective priority levels. The method further includes determining, based on the final date, an ordered relationship between the electronic communication documents, and storing metadata indicating the ordered relationship between the electronic communication documents.
-
公开(公告)号:US20230035641A1
公开(公告)日:2023-02-02
申请号:US17840987
申请日:2022-06-15
发明人: Christopher Malon
IPC分类号: G06N3/08 , G06F40/166 , G06F40/40 , G06F40/258
摘要: A method for neural network training is provided. The method inputs a training set of textual claims, lists of evidence including gold evidence chains, and claim labels labelling the evidence with respect to the textual claims. The claim labels include refutes, supports, and not enough information (NEI). The method computes an initial set of document retrievals for each of the textual claims. The method also includes computing an initial set of page element retrievals including sentence retrievals from the initial set of document retrievals for each of the textual claims. The method creates, from the training set of textual claims, a Leave Out Training Set which includes input texts and target texts relating to the labels. The method trains a sequence-to-sequence neural network to generate new target texts from new input texts using the Leave Out Training Set.
-
公开(公告)号:US20230023325A1
公开(公告)日:2023-01-26
申请号:US17374075
申请日:2021-07-13
发明人: Jignesh K. Karia , Mukundan Sundararajan , Pankaj Satyanarayan Dayama , Neha Shah , Vishal Awal
IPC分类号: G06F40/258 , G06N20/20 , G06K9/62 , G06F40/205 , H04W4/14 , G06F40/295
摘要: Recommendation and approval of a header for a message includes generating a proposed header based on the name and/or brand of the entity and product and/or content of the message, classifying the proposed header using a machine learning model trained based on historical complaints on previously used headers related to the entity name and brand and product and/or content of the message and recommending the proposed header based on the classification. The training of the machine learning model may include learning a threshold wherein headers having a classification greater than the threshold are not recommended as having a high probability of being wrongly associated with the requesting entity and headers having a classification lower than the threshold are recommended as having a high probability of not being wrongly associated with the requesting entity.
-
公开(公告)号:US11494555B2
公开(公告)日:2022-11-08
申请号:US16675456
申请日:2019-11-06
发明人: Darrell Bellert
IPC分类号: G06F40/205 , G06V30/414 , G06V30/416 , G06F40/258 , G06V30/10 , G06N5/04
摘要: A method, non-transitory computer readable medium, and system for inferring certain texts as stylized section headings in an electronic document (ED). Stylized section headings are section headings that have unique styling distinct from the body of text below each stylized heading. In particular, the stylized section headings are identified based on styling information in the ED. Identifying stylized section headings includes grouping candidate headings based on identification of dominant styling, locating high level fragments, and repeatedly locating nested fragments from within higher level fragments. The ED may or may not include explicitly identified headings in the document.
-
公开(公告)号:US11409749B2
公开(公告)日:2022-08-09
申请号:US15808540
申请日:2017-11-09
IPC分类号: G06F16/33 , G06F16/2457 , G06N20/00 , G06F16/93 , G06F16/332 , G06F16/951 , G06F40/205 , G06F40/258
摘要: A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and/or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.
-
-
-
-
-
-
-
-
-