-
公开(公告)号：US11886233B2
公开(公告)日：2024-01-30
申请号：US17096767
申请日：2020-11-12
Inventor： Dong Hwan Kim , Sung Ju Hwang , Seanie Lee , Dong Bok Lee , Woo Tae Jeong , Han Su Kim , You Kyung Kwon , Hyun Ok Kim
Abstract: The present invention relates to a context-based QA generation architecture, and an object of the present invention is to generate diverse QA pairs from a single context. To achieve the object, the present invention includes a latent variable generating network including at least one encoder and an artificial neural network (Multi-Layer Perceptron: MLP) and configured to train the artificial neural network using a first context, a first question, and a first answer, and generate a second question latent variable and a second answer latent variable by applying the trained artificial neural network to a second context, an answer generating network configured to generate a second answer by decoding the second answer latent variable, and a question generating network configured to generate a second question based on a second context and the second answer.
-
公开(公告)号：US12159118B2
公开(公告)日：2024-12-03
申请号：US18544209
申请日：2023-12-18
Inventor： Dong Hwan Kim , Sung Ju Hwang , Seanie Lee , Dong Bok Lee , Woo Tae Jeong , Han Su Kim , You Kyung Kwon , Hyun Ok Kim
Abstract: The present invention relates to a context-based QA generation architecture, and an object of the present invention is to generate diverse QA pairs from a single context. To achieve the object, the present invention includes a latent variable generating network including at least one encoder and an artificial neural network (Multi-Layer Perceptron: MLP) and configured to train the artificial neural network using a first context, a first question, and a first answer, and generate a second question latent variable and a second answer latent variable by applying the trained artificial neural network to a second context, an answer generating network configured to generate a second answer by decoding the second answer latent variable, and a question generating network configured to generate a second question based on a second context and the second answer.
-
公开(公告)号：US20250068855A1
公开(公告)日：2025-02-27
申请号：US18942853
申请日：2024-11-11
Inventor： Dong Hwan Kim , Sung Ju Hwang , Seanie Lee , Dong Bok Lee , Woo Tae Jeong , Han Su Kim , You Kyung Kwon , Hyun Ok Kim
Abstract: The present invention relates to a context-based QA generation architecture for generating diverse QA pairs from a single context. The context-based QA generation architecture includes a latent variable generating network, an answer generating network and a question generating network. The latent variable generating network comprises multiple Bi-LSTM encoders encode the a first context, the a first question and the a first answer to generate a first context vector, a first question vector and a first answer vector, respectively, a first Multi-Layer Perceptron (MLP) generate a first question latent variable based on the first context vector and the first question vector, and a second MLP generate a first answer latent variable based on the first question latent variable and the first answer vector. The answer generating network and the question generating network are trained based on the first context, the first question latent variable and the first answer latent variable.
-
公开(公告)号：US12182184B2
公开(公告)日：2024-12-31
申请号：US18130164
申请日：2023-04-03
Applicant: 42Maru Inc.
Inventor： Dong Hwan Kim , Kibong Sung , You Kyung Kwon , SeongYeop Jeong
IPC: G06F16/00 , G06F16/332 , G06F16/903 , G06F18/214 , G06F18/22 , G06N3/045
Abstract: Disclosed herein is a search method performed by a server, including: receiving a user question from a user terminal; generating a user question vector for the user question; selecting similar question candidates based on a similarity to the user question vector; generating an answer to the user question based on the similar question candidates; and transmitting the answer to the user question to the user terminal.
-
公开(公告)号：US12259917B2
公开(公告)日：2025-03-25
申请号：US18071105
申请日：2022-11-29
Applicant: 42Maru Inc.
Inventor： Dong Hwan Kim , Hyun Wuk Son , Hyun Ok Kim , You Kyung Kwon , In Je Seong , Yong Sun Choi , Ha Kyeom Moon
IPC: G06F16/34 , G06F16/334 , G06F16/35
Abstract: A method of retrieving a document according to an embodiment of the present application includes: acquiring a user retrieval query; calculating a user inquiry vector in a unit of sentence from the user retrieval query and acquiring a first document candidate group based on similarity between the calculated user inquiry vector and an embedding vector of a document stored in a retrieval database; acquiring a second document candidate group based on similarity between a text included in the user retrieval query and a text of the document stored in the retrieval database; and determining a summarization target document based on the first document candidate group and the second document candidate group.
-
Patent Agency Ranking
公开(公告)号：US11620343B2
公开(公告)日：2023-04-04
申请号：US16699515
申请日：2019-11-29
Applicant: 42Maru Inc.
Inventor： Dong Hwan Kim , Kibong Sung , You Kyung Kwon , SeongYeop Jeong
IPC: G06N3/00 , G06F16/903 , G06K9/62 , G06N3/04
Abstract: Disclosed herein is a search method performed by a server, including: receiving a user question from a user terminal; generating a user question vector for the user question; selecting similar question candidates based on a similarity to the user question vector; generating an answer to the user question based on the similar question candidates; and transmitting the answer to the user question to the user terminal.
-
公开(公告)号：US20230237084A1
公开(公告)日：2023-07-27
申请号：US18130164
申请日：2023-04-03
Applicant: 42Maru Inc.
Inventor： Dong Hwan KIM , Kibong Sung , You Kyung Kwon , SeongYeop Jeong
IPC: G06F16/332 , G06F16/903 , G06F18/22 , G06F18/214 , G06N3/045
CPC classification number: G06F16/3329 , G06F16/90348 , G06F18/22 , G06F18/214 , G06N3/045
Abstract: Disclosed herein is a search method performed by a server, including: receiving a user question from a user terminal; generating a user question vector for the user question; selecting similar question candidates based on a similarity to the user question vector; generating an answer to the user question based on the similar question candidates; and transmitting the answer to the user question to the user terminal.
-
公开(公告)号：US20250086208A1
公开(公告)日：2025-03-13
申请号：US18962508
申请日：2024-11-27
Applicant: 42Maru Inc.
Inventor： Dong Hwan KIM , Ki Bong Sung , You Kyung Kwon , SeongYeop Jeong
IPC: G06F16/332 , G06F16/903 , G06F18/214 , G06F18/22 , G06N3/045
Abstract: Disclosed herein is a search method performed by an electronic device, including: receiving the plurality of similar question candidates selected by the server using a first similarity analysis model and question vectors corresponding to the plurality of similar question candidates from the server; selecting one or more similar questions from the plurality of similar question candidates by the electronic device using a second similarity analysis model; receiving the responses to the one or more similar questions from the server; and providing the one or more similar questions and the responses to the similar question together to the user.
-
公开(公告)号：US12033413B2
公开(公告)日：2024-07-09
申请号：US17502017
申请日：2021-10-14
Applicant: 42Maru Inc.
Inventor： Dong Hwan Kim , You Kyung Kwon , So Young Ko , Sook Jin Roe , Ki Beom Kwon , Da Hea Moon
IPC: G06K9/00 , G06F16/953 , G06F40/20 , G06V30/12 , G06V30/19 , G06V30/412 , G06V30/413 , G06V30/414 , G06V30/416
CPC classification number: G06V30/413 , G06F16/953 , G06F40/20 , G06V30/12 , G06V30/19093 , G06V30/412 , G06V30/414 , G06V30/416
Abstract: Provided are method and apparatus for data structuring of text. The apparatus for data structuring of text includes a data extraction unit configured to extract text and location information of the text from an image based on an optical character recognition (OCR) technique, a data processing unit configured to generate a text unit based on the text and the location information, a form classification unit configured to classify a form of the image based on the text, a labeling unit configured to label the text unit as first text, second text, and third text respectively corresponding to an item name, an item value, or others based on the classified form, a relationship identification unit configured to map and structure the second text corresponding to the first text, and a misrecognition correction unit configured to determine misrecognition of the first text and correct the first text determined to be misrecognized.
-
公开(公告)号：US20240168984A1
公开(公告)日：2024-05-23
申请号：US18071105
申请日：2022-11-29
Applicant: 42Maru Inc.
Inventor： Dong Hwan Kim , Hyun Wuk Son , Hyun Ok Kim , You Kyung Kwon , In Je Seong , Yong Sun Choi , Ha Kyeom Moon
CPC classification number: G06F16/345 , G06F16/3347 , G06F16/35
Abstract: A method of retrieving a document according to an embodiment of the present application includes: acquiring a user retrieval query; calculating a user inquiry vector in a unit of sentence from the user retrieval query and acquiring a first document candidate group based on similarity between the calculated user inquiry vector and an embedding vector of a document stored in a retrieval database; acquiring a second document candidate group based on similarity between a text included in the user retrieval query and a text of the document stored in the retrieval database; and determining a summarization target document based on the first document candidate group and the second document candidate group.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.021 seconds)
