公开(公告)号：US12236194B2

公开(公告)日：2025-02-25

申请号：US18048064

申请日：2022-10-20

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Zhaoqi Wu ,  Yi Fang Chen ,  Zhi Wang ,  Yi Qun Zhang ,  Yan Du ,  Li Na Yuan

IPC: G06F40/295 ,  G06F40/216 ,  G06N3/08

Abstract: A method of this disclosure may include performing a named entity recognition on text information related to requirements for a wireframe by a first artificial intelligence (AI) model, so as to extract entities and relations of the entities from the text information. The method may further comprise inputting the extracted entities and relations to a second AI model to generate the wireframe, wherein the second AI model is trained so that a difference between resultant relations of the entities of the generated wireframe and the extracted relations of the entities from the first AI model is decreased.

公开(公告)号：US12231510B2

公开(公告)日：2025-02-18

申请号：US17329854

申请日：2021-05-25

Applicant: People.ai, Inc.

Inventor： Oleg Rogynskyy ,  Yury Markovsky ,  Yurii Brunets ,  Rajit Kurien Joseph

IPC: G06F16/21 ,  G06F7/14 ,  G06F9/54 ,  G06F11/30 ,  G06F11/34 ,  G06F16/11 ,  G06F16/17 ,  G06F16/178 ,  G06F16/215 ,  G06F16/22 ,  G06F16/23 ,  G06F16/245 ,  G06F16/2455 ,  G06F16/2457 ,  G06F16/2458 ,  G06F16/25 ,  G06F16/26 ,  G06F16/27 ,  G06F16/28 ,  G06F16/29 ,  G06F16/31 ,  G06F16/335 ,  G06F16/355 ,  G06F16/901 ,  G06F16/903 ,  G06F16/9035 ,  G06F16/906 ,  G06F16/9535 ,  G06F21/62 ,  G06F40/20 ,  G06F40/237 ,  G06F40/295 ,  G06N3/08 ,  G06N5/025 ,  G06N5/04 ,  G06N7/02 ,  G06Q10/04 ,  G06Q10/0631 ,  G06Q10/0639 ,  G06Q10/107 ,  G06Q10/109 ,  G06Q10/1091 ,  G06Q10/1093 ,  G06Q50/22 ,  G16H50/20 ,  H04L41/14 ,  H04L43/00 ,  H04L43/026 ,  H04L43/045 ,  H04L43/062 ,  H04L43/065 ,  H04L43/067 ,  H04L43/0876 ,  H04L51/046 ,  H04L51/212 ,  H04L51/234 ,  H04L51/42 ,  H04L61/45 ,  H04L67/125 ,  H04L67/30 ,  H04L67/303 ,  H04L67/306 ,  H04L67/50 ,  H04M3/436 ,  H04M15/00 ,  G06F40/205 ,  G06N20/00 ,  G06Q10/10 ,  G16H15/00 ,  G16H50/30 ,  H04L12/14 ,  H04L101/00 ,  H04L101/35 ,  H04L101/37 ,  H04M3/22 ,  H04M3/56

Abstract: The present disclosure relates to systems and methods for updating email addresses based on email generation patterns. The method includes accessing a plurality of electronic activities used to update a plurality of member node profiles. The method includes determining that the plurality of member node profiles is linked to a group node profile of a group entity. The methods includes identifying, for each of the plurality of member node profiles, a first field-value pair of the member node profile corresponding to an email address. The method includes determining, for each member node profile, a correlation between the email address, a second field-value pair corresponding to a first name and a third field-value pair corresponding to a last name. The method includes determining, based on the determined correlation, an electronic account identifier pattern. The method includes storing an association between the group node and the electronic account identifier pattern.

公开(公告)号：US12229513B2

公开(公告)日：2025-02-18

申请号：US18365504

申请日：2023-08-04

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ying Suresh Wang ,  Min Li ,  Mengyan Lu

IPC: G06F40/295 ,  G06F16/28 ,  G06F40/284 ,  G06N20/00

Abstract: A technical document scanner disclosed herein determines and categorizes various common issues among a large number of documents. An implementation of the technical document scanner is implemented using various computer process instructions including scanning a technical document to extract content, applying named entity recognition on the extracted content from the technical document to extract named entities, applying relation extraction on the named entities to extract relations between the named entities, and analyzing the relations between the entities to compose lists of high relevance entities for issue checking.

公开(公告)号：US12223951B2

公开(公告)日：2025-02-11

申请号：US17556585

申请日：2021-12-20

Applicant: Adeia Guides Inc.

Inventor： Jeffry Copps Robert Jose ,  Reda Harb

IPC: G10L15/18 ,  G06F40/295 ,  G10L15/22

Abstract: Systems and methods are provided for responding to a natural language query, e.g., a first natural language query. A first natural language understanding model is used to process the natural language query. A confidence level, e.g., a first confidence level, of the understanding of the natural language query is determined. In response to the confidence level being below a confidence level threshold, the natural language query is reprocessed using a reprocessing module. A response to the first natural language query is generated based on the processing of the natural language query by the first natural language understanding model and the reprocessing of the natural language query.

公开(公告)号：US12223269B2

公开(公告)日：2025-02-11

申请号：US17664031

申请日：2022-05-18

Applicant: Microsoft Technology Licensing, LLC

Inventor： Pengcheng He ,  Jianfeng Gao ,  Weizhu Chen

IPC: G06F40/284 ,  G06F40/295 ,  G06N3/08 ,  G06N5/04

Abstract: A method for training a language model comprises (a) receiving vectorized training data as input to a multitask pretraining problem; (b) generating modified vectorized training data based on the vectorized training data, according to an upstream data embedding; (c) emitting pretraining output based on the modified vectorized training data, according to a downstream data embedding equivalent to the upstream data embedding; and (d) adjusting the upstream data embedding and the downstream data embedding by computing, based on the pretraining output, a gradient of the upstream data embedding disentangled from a gradient of the downstream data embedding, thereby advancing the multitask pretraining problem toward a pretrained state.

公开(公告)号：US12223015B2

公开(公告)日：2025-02-11

申请号：US17651414

申请日：2022-02-16

Applicant: Google LLC

Inventor： Emmanouil Koukoumidis ,  Nikolaos Kofinas ,  Evan Huang ,  Kiran Bellare ,  Xiao Liu ,  Michael Lanning ,  Lukas Rutishauser

IPC: G06F40/295 ,  G06F18/20 ,  G06F18/21

Abstract: A computer-implemented method includes receiving a document insight request that requests document insights for a corpus of documents. The document insight request includes the corpus of documents, a set of entities contained within each document of the corpus of documents, and document insight request parameters that includes a confidence value threshold. The method also includes generating the document insights for the corpus of documents based on the confidence value threshold. Here, the document insights include an accuracy target and a user review rate target. The method also includes transmitting the document insights to the user device causing a graphical user interface to display the document insights on the user device.

公开(公告)号：US20250045509A1

公开(公告)日：2025-02-06

申请号：US18364537

申请日：2023-08-03

Applicant: Capital One Services, LLC

Inventor： Joshua EDWARDS ,  Benjamin ENG ,  Kok Leong SEOW

IPC: G06F40/166 ,  G06F40/295 ,  G06F40/30

Abstract: In some implementations, a device may obtain an audio input. The device may perform an audio-to-text operation to translate the audio input into a first text output. The device may detect that a first portion of the first text output is to be modified to include an entity name. The device may perform, using an identifier of a source of the audio input, a lookup operation to identify the entity name. The device may modify the first text output to obtain a second text output by replacing the first portion with the entity name.

公开(公告)号：US12217004B2

公开(公告)日：2025-02-04

申请号：US17351120

申请日：2021-06-17

Applicant: Ramp Business Corporation

Inventor： Calvin Jun-Gong Lee ,  Veeral Dilip Patel ,  Paul Alexander Meier ,  Karim Atiyeh ,  Ariel Petren Langer ,  Ori Ephraim Goldfield ,  Geoffrey Jacques Charles

IPC: G06F40/295 ,  G06N3/08 ,  G06N20/00 ,  G06Q30/0201 ,  G06Q40/02 ,  G06V30/414 ,  G06V30/416 ,  G06F40/205 ,  G06F40/211 ,  G06F40/279

Abstract: A system for stable and streamlined transaction approval includes a rule management server and an authorizer server. The rule management server is configured to receive a transaction rule that includes a list of named entities specified by a client. The rule management server stores past transaction data and analyzes patterns in the past data to determine a named entity identification rule. The authorizer server receives a transaction data payload related to a pending transaction associated with the client and identifies a noisy data field in the transaction data payload. The noisy data field includes a representation of a particular named entity and one or more irrelevant strings. The authorizer server parses the particular named entity based on the named entity identification rule and determines whether the particular named entity is one of the named entities in the list. The authorizer server conducts a transaction evaluation using the result.

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：US12210648B2

公开(公告)日：2025-01-28

申请号：US17830237

申请日：2022-06-01

Applicant: Microsoft Technology Licensing, LLC

Inventor： Sekhar Poornananda Chintalapati ,  Vinod Kumar Yelahanka Srinivas ,  Dattatraya Baban Rajpure ,  Pieter Kristian Brouwer ,  Gaurav Anil Yeole ,  Mihai Silviu Peicu

IPC: G06F21/62 ,  G06F16/174 ,  G06F40/284 ,  G06F40/295

Abstract: Methods and systems for detecting personally identifiable information in data associated with a cloud computing system are described. An example method includes ingesting the data associated with the cloud computing system to generate source data. The method includes processing the source data by: performing cell-based de-duplication to generate cell-based de-duplicated data, subjecting the cell-based de-duplicated data to regular expression classification to generate a first subset of initial results, tokenizing the cell-based de-duplicated data to generate tokenized data, and de-duplicating the tokenized data and subjecting de-duplicated tokenized data to a first named entity recognition classification to generate a second subset of the initial results. The method includes cross-referencing the cell-based de-duplicated data and the initial results and subjecting output of the cross-referencing to a second named entity recognition classification to generate final results. The method includes processing the final results to detect any personally identifiable information in the final results.