公开(公告)号：US20230401391A1

公开(公告)日：2023-12-14

申请号：US18209790

申请日：2023-06-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Fan ZHANG ,  Mei TU ,  Song LIU

IPC: G06F40/47 ,  G06F40/284

CPC classification number: G06F40/47 ,  G06F40/284

Abstract: A method performed by an electronic device comprises acquiring information to be translated. The method includes determining, based on the information to be translated, a target domain adapter from a plurality of candidate domain adapters, the target domain adapter corresponding to the information to be translated, each candidate domain adapter from the plurality of candidate domain adapters corresponding to at least one domain. The method includes obtaining, based on the target domain adapter corresponding to the information to be translated, a translation result corresponding to the information to be translated.

公开(公告)号：US20230126826A1

公开(公告)日：2023-04-27

申请号：US17979384

申请日：2022-11-02

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Xiangfeng MENG ,  Xiaoyan QU ,  Song LIU

IPC: G06F40/20 ,  G06N3/04 ,  G06F40/166

Abstract: A text classification method includes acquiring a text to be classified, obtaining a feature representation of the text to be classified by performing feature extraction on the text to be classified, acquiring a tuple set of each current text class, the tuple set of each text class comprising a prototype of each respective text class and a distribution density of text data of each respective text class, and obtaining a text class of the text to be classified by classifying the text to be classified based on the feature representation of the text to be classified and the tuple set.

公开(公告)号：US20220083745A1

公开(公告)日：2022-03-17

申请号：US17533797

申请日：2021-11-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Wenbo YUAN ,  Yuxing ZHENG ,  Song LIU

IPC: G06F40/53 ,  G06F40/47 ,  G06F40/55 ,  G06F40/279

Abstract: Embodiments of the present disclosure provide a method, an apparatus and an electronic device for determining a word representation vector, and a computer-readable storage medium, which belong to a field of processing natural languages. The method includes obtaining a set of glyph units of a text; obtaining a context vector of the text based on the set of glyph units; and predicting next word of the text based on the context vector. The method for determining the word representation vector of the present disclosure can effectively obtain a corresponding set of glyph units even for hieroglyphics in which hyperbolic characters are prone to appear or languages evolved from the hieroglyphics, thereby improving an accuracy of determining the word representation vector.

公开(公告)号：US20220067115A1

公开(公告)日：2022-03-03

申请号：US17418013

申请日：2019-12-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yinhe ZHENG ,  Song LIU ,  Qing WANG ,  Yimeng ZHUANG ,  Tiancong PANG

IPC: G06F16/9535 ,  G06N5/02 ,  G06N5/04

Abstract: An electronic device is provided. The electronic device includes a memory storing instructions, and at least one processor configured to execute the instructions to collect information of a user based on user activities on the electronic device, analyze the collected information of the user for generating a personal knowledge graph of the user, provide personalization information to a content provider (CP) based on the personal knowledge graph, and receive at least one content which is provided from the CP.

公开(公告)号：US20220179888A1

公开(公告)日：2022-06-09

申请号：US17604609

申请日：2020-04-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Huadong WANG ,  Song LIU ,  Yuntao ZHANG

IPC: G06F16/332 ,  G06F16/335 ,  G06F16/338 ,  G06F40/35

Abstract: Embodiments of the present disclosure provide an information processing method, apparatus, electronic device, and computer readable storage medium, and relate to the field of natural language processing technologies. The method includes: obtaining attribute information currently corresponding to an information responding party based on current input of a user, and then determining the information to be responded corresponding to the current input of the user, and then generating and outputting a target response based on the attribute information currently corresponding to the information responding party and the information to be responded corresponding to the current input of the user. The embodiments of the present disclosure realize that the target response is outputted more accurately when an information responding party (for example, an intelligent chatbot) interacts with the user, so as to implement the dialogue with the user.

公开(公告)号：US20220310091A1

公开(公告)日：2022-09-29

申请号：US17616836

申请日：2020-06-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yinhe ZHENG ,  Song LIU ,  Qing WANG ,  Yimeng ZHUANG ,  Tiancong PANG

IPC: G10L15/22 ,  G10L15/00 ,  G06F3/0482

Abstract: A method and apparatus for interacting with an intelligent response system is provided. The method comprises: receiving a user input; identifying user intent based on content of the user input; and automatically interacting with an intelligent response system involved in the user intent to achieve the user intent. According to the method and apparatus, interacting with the corresponding intelligent response system is automatically performed only based on the user input reflecting the user intent to achieve the user intent without directly interacting with the intelligent response system by the user.

公开(公告)号：US20220310077A1

公开(公告)日：2022-09-29

申请号：US17592956

申请日：2022-02-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Mei TU ,  Fan ZHANG ,  Wangli CHAO ,  Xiaoyun XU ,  Song LIU ,  Shuo HU ,  Xue WEN ,  Liming SONG ,  Xiaoyan LOU

IPC: G10L15/187 ,  G10L15/22 ,  G10L15/00 ,  G10L15/02

Abstract: A speech recognition method, an apparatus, an electronic device, and a computer-readable storage medium are provided. The method includes acquiring a first speech recognition result of a speech; acquiring context information and pronunciation feature information about a target text unit in the first speech recognition result; and acquiring a second speech recognition result of the speech based on the context information and the pronunciation feature information.

公开(公告)号：US20210209356A1

公开(公告)日：2021-07-08

申请号：US17142566

申请日：2021-01-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Huadong WANG ,  Song LIU ,  Xiangfeng MENG

IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06F40/279

Abstract: A method for keyword extraction, an apparatus, an electronic device, and a computer-readable storage medium, which relate to the field of artificial intelligence are provided. The method includes collecting feature information corresponding to an image to be processed, the feature information including text representation information and image visual information and then extracting keywords from the image to be processed based on the feature information. The text representation information includes text content and text visual information corresponding to each text line in the image to be processed. The method for keyword extraction, apparatus, electronic device, and computer-readable storage medium provided in the embodiments of the disclosure may extract the keywords from an image to be processed.