公开(公告)号：US12223264B2

公开(公告)日：2025-02-11

申请号：US18154601

申请日：2023-01-13

Applicant: Capital One Services, LLC

Inventor： Anindya Misra ,  Cindy Liu ,  Milovan Milovanovic

IPC: G06F40/20 ,  G06F16/34 ,  G06F16/36 ,  G06F16/901 ,  G06F40/30 ,  G06N3/048 ,  G06N20/00

Abstract: A method may include a obtaining a first data model instance comprising an identifier string and. a set of attributes associated with a set of attribute name strings. The method may include obtaining an ontology graph that includes a first label, a second label, and an association between them. The method may include using a prediction model to select the first label based on the first data model instance and determining the second label based on the relationship. The method may include determining a selected set of labels that includes the first label and the second label to associate with the first data model instance. The method may include associating the selected set of labels with the first data model instance in a dataset that includes a plurality of records, where each record is associated with a different data model instance.

公开(公告)号：US12222974B2

公开(公告)日：2025-02-11

申请号：US17853086

申请日：2022-06-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Oron Nir ,  Inbal Sagiv ,  Fardau Van Neerden

IPC: G06F16/36 ,  G06F16/35 ,  G06F18/2137 ,  G06F18/22 ,  G06F18/2323 ,  G06F40/30

Abstract: A method for automatically classifying terms of a first ontology into categories of a classification scheme defined with respect to a second ontology includes generating, for each term in the first ontology and each term in the second ontology, an embedding encoding the term and a description of the term. The method further includes adding the generated embeddings to a transformer model and computing, for each pair of the embeddings consisting of a first term from the first ontology and a second term from the second ontology, a similarity metric quantifying a similarity of the first term and the second term. The method still further provides for determining a matching scheme based on the similarity metric computed with respect to each pair of the embeddings, where the matching scheme associates term of the first ontology with one or more relevant categories of the classification scheme defined with respect to the second ontology. The method further provides for returning the one or more relevant categories of the classification scheme that are matched, by the determined matching scheme, to a term of the second ontology received as an input.

公开(公告)号：US12198075B2

公开(公告)日：2025-01-14

申请号：US17136216

申请日：2020-12-29

Applicant: FASOO.COM CO., LTD.

Inventor： Kyu Gon Cho ,  Jong Sin Choi ,  Bum Jong Lee

IPC: G06F16/00 ,  G06F16/36 ,  G06F40/169 ,  G06F40/216 ,  G06F40/242 ,  G06F40/279 ,  G06N5/022 ,  G06N5/048 ,  G06N20/00

Abstract: Disclosed are a method and device for calculating a correlation between notes using a database constructed on a basis of artificial intelligence, and supporting a service for the notes on a basis of the calculated correlation. A method by which a note providing device that interworks with a user terminal provides notes, includes: constructing a keyword DB by extracting a keyword from a note generated through the user terminal and reflecting a weight calculated through machine learning using the extracted keyword; and calculating a correlation score for each of a plurality of target notes correlated with a reference note using the keyword DB. Therefore, the method and device for providing the notes using the artificial intelligence-based correlation calculation can more accurately recommend the correlated notes by reflecting the interaction of the user.

公开(公告)号：US12197485B2

公开(公告)日：2025-01-14

申请号：US18138195

申请日：2023-04-24

Applicant: cortical.io AG

Inventor： Francisco De Sousa Webber

IPC: G06F16/00 ,  G06F16/33 ,  G06F16/36

Abstract: A method for using distributed representations of data items within a first set of data documents clustered in a first two-dimensional metric space to generate a cluster of distributed representations in a second two-dimensional metric space includes clustering in a first two-dimensional metric space, by a reference map generator, a set of data documents, generating a semantic map. A parser generates an enumeration of data items occurring in the set of data documents. A representation generator generates a distributed representation using occurrence information about each data item. A sparsifying module receives an identification of a maximum level of sparsity and reduces a total number of set bits within the distributed representation. The reference map generator clusters, in a second two-dimensional metric space, a set of SDRs retrieved from the SDR database and selected according to a second at least one criterion, generating a second semantic map.

公开(公告)号：US20240419743A1

公开(公告)日：2024-12-19

申请号：US18818512

申请日：2024-08-28

Applicant: eBay Inc.

Inventor： Neelakantan Sundaresan ,  Yongzheng Zhang ,  Catherine Baudin ,  Dan Shen ,  Shen Huang

IPC: G06F16/93 ,  G06F16/33 ,  G06F16/36 ,  G06F16/583 ,  G06F40/30 ,  G06Q10/00 ,  G06Q30/00

Abstract: Methods, apparatus, and systems to determine a niche market of items or services, the first phase of which identifies a gap between demand and supply for a set of items. Session logs may be evaluated to compare transactions involving a specific item to those of a larger group of items. The resultant information identifies areas of high demand, but with low availability. The niche market information may be provided as direct merchandising items for sellers. In one example, the method generates niche market item web pages in specific categories. Additional methods, apparatus, and systems are disclosed.

公开(公告)号：US20240419714A1

公开(公告)日：2024-12-19

申请号：US18695441

申请日：2022-09-26

Applicant: Siemens Aktiengesellschaft

Inventor： Swathi Shyam Sunder ,  Nataliia Rümmele ,  Tobias Aigner ,  Yogesh Kamath ,  Rani Joseph ,  Yogesh Borkhade ,  Prithvi Raj Ramakrishnaraja

IPC: G06F16/35 ,  G06F16/332 ,  G06F16/36

Abstract: A system and method for data management is provided. The method includes obtaining a dataset from a data source by a processing unit. The dataset includes a plurality of datapoints, and each of the datapoints belongs to a column among a plurality of columns. Further, an ontology label for at least one column in the dataset is predicted using a machine learning model. The predicted ontology label is associated with an ontology comprising a plurality of ontology labels. Further, a mapping between the dataset and the ontology is generated based on the relation between the predicted ontology label and the column. Furthermore, the datapoints are classified with respect to the ontology labels based on the mapping generated. The classified datasets are outputted on a user interface.

公开(公告)号：US12169524B2

公开(公告)日：2024-12-17

申请号：US18226156

申请日：2023-07-25

Applicant: Palantir Technologies Inc.

Inventor： Cenk Sezgin ,  Advaya Krishna ,  Adhish Ramkumar ,  Arthur Wu ,  Adam Wiles ,  Gregory Slonim ,  Harsh Pandey ,  Kushal Nigam ,  Michal Adamczyk

IPC: G06F7/00 ,  G06F16/23 ,  G06F16/242 ,  G06F16/2457 ,  G06F16/36 ,  G06F16/9032

Abstract: The present disclosure relates to methods and systems for querying data in a data repository. According to a first aspect, this disclosure describes a method of querying a database, comprising: receiving, at a computing device, a plurality of keywords; determining, by the computer device, a plurality of datasets relating to the keywords; identifying, by the computer device, metadata for the plurality of datasets indicating a relationship between the datasets by examining an ontology associated with the datasets; providing, by the computer device, one or more suggested database queries in natural language form, the one or more suggested database queries constructed based on the plurality of keywords and the metadata; receiving, by the computing device, a selection of the one or more suggested database queries; and constructing, by the computer device, an object view for the plurality of datasets based on the selected query and the metadata.

公开(公告)号：US12169514B2

公开(公告)日：2024-12-17

申请号：US18115466

申请日：2023-02-28

Applicant: Adeia Guides Inc.

Inventor： Murali Aravamudan ,  Rakesh Barve ,  Sashikumar Venkataraman ,  Vineet Agarwal ,  Abhijit Savarkar ,  Ganesh Ramamoorthy ,  Ahmed Nizam Mohaideen Pathurudeen ,  K China Srinivasulu Reddy

IPC: G06F16/30 ,  G06F16/24 ,  G06F16/332 ,  G06F16/335 ,  G06F16/36 ,  G06F16/9032

Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.

公开(公告)号：US20240411787A1

公开(公告)日：2024-12-12

申请号：US18632864

申请日：2024-04-11

Applicant: SAP SE

Inventor： Jan PORTISCH ,  Guilherme COSTA ,  Michael HLADIK

IPC: G06F16/332 ,  G06F16/21 ,  G06F16/36

Abstract: A method, a system and a computer program for providing data from a directed graph to a language model are provided. The method comprises defining a plurality of conditions and a plurality of patterns, wherein each of the conditions has at least one corresponding pattern. The method further comprises receiving a subset of the directed graph, wherein the subset of the directed graph includes a plurality of statements, wherein each of the statements includes a subject, an object and a predicate relating the subject to the object. The method further comprises for each of the statements in the subset of the directed graph, performing the following: when one of the conditions matches a respective statement and the pattern corresponding to the condition can be applied to the respective statement, computing a string from the respective statement using the pattern.

公开(公告)号：US12164404B2

公开(公告)日：2024-12-10

申请号：US17827122

申请日：2022-05-27

Applicant: Palantir Technologies Inc.

Inventor： Brandon Mac ,  Joseph Sayegh ,  Thomas Eckerle ,  Zachary Romanow

IPC: H03M7/30 ,  G06F11/30 ,  G06F16/36

Abstract: Computing systems methods, and non-transitory storage media are provided for obtaining information regarding an incident, generating a representation of the information, augmenting the representation with additional contextual information, determining a response to address the incident, and implementing the response or transmitting the determined response to a separate computing system that implements the response.