公开(公告)号：WO2023085508A1

公开(公告)日：2023-05-19

申请号：PCT/KR2021/019243

申请日：2021-12-17

Applicant: 주식회사 심도컴퍼니

Inventor： 심도형

IPC: G06Q50/10 ,  G06F40/10 ,  G06N3/02

Abstract: 제품 또는 서비스에 대한 데이터를 입력 받아 카피라이팅 및 브랜드명을 생성하는 AI 기반 브랜드 생성 장치 및 방법이 개시된다. 일 실시예에 따른 AI 기반 브랜드 생성 장치는 서비스 종류 및 제품 종류 중 적어도 하나에 대한 입력 데이터를 입력 받아 유사한 단어로 구성된 유의어 클러스터를 생성하는 유사 단어 생성부; 단어 클러스터에 포함된 단어를 기초 연관된 단어로 구성된 연관어 클러스터를 생성하는 연관 단어 생성부; 입력 데이터와 함께 연관어 클러스터에 포함된 단어 각각을 사용하는 사람의 연령, 성별 및 지역 중 적어도 하나에 대한 메타 데이터를 생성하는 메타 데이터 생성부; 및 연관어 클러스터에 포함된 단어와 메타 데이터를 매칭하여 출력하며, 사용자 입력을 수신하는 인터페이스부를 포함할 수 있다.

公开(公告)号：WO2022125480A1

公开(公告)日：2022-06-16

申请号：PCT/US2021/062095

申请日：2021-12-07

Applicant: IKEGUCHI HOLDINGS DBA AKYRIAN SYSTEMS [US]/[US] ,  IKEGUCHI, Edward [US]/[US] ,  JACKSON, Peter, T. [US]/[US]

Inventor： IKEGUCHI, Edward ,  JACKSON, Peter, T.

IPC: G16H10/20 ,  G06F40/10 ,  G06Q10/10 ,  G16H10/60 ,  G16H15/00 ,  G16H50/70

Abstract: An improvement to a clinical trial study workflow system and method providing a method for electronic verification of a source for a source capture in a clinical trial workflow system, the method including opening an EMR system, logging into the EMR system on behalf of a user using securely stored credentials, automatically selecting correct navigation links of the EMR system and filling out the appropriate navigation forms to reach an EMIR page with desired information for a correct study subject's record and visit date, capturing one or more screenshots of one or more relevant pages containing the desired information for answering one or more questions on a case report form (CRF), and verifying that the one or more captured screenshots is of the correct study subject by using one or more data points for verification.

公开(公告)号：WO2022054079A1

公开(公告)日：2022-03-17

申请号：PCT/IN2021/050862

申请日：2021-09-06

Applicant: IQREATE INFOTECH PVT LTD

Inventor： RAKESH, Srivastava ,  KIRAN, Kumar ,  NITIN, Gupta

IPC: G06F16/35 ,  G06F40/10 ,  G06F40/279 ,  G06F40/30

Abstract: The invention relates to a system for contextual and positional parameterized record building. The system provides a mechanism to track any data record, information element or its parts to extract graphical/logical and contextual location in source documents and construct a data tree representation using a data representation module. The information extraction is enabled by a learning approach that incorporates graphical positional features into the model building process. A prediction architecture includes a gate network having a plurality of gates/neurons. Each gate/neuron is associated with an activation function based on a pre-built logic to perform a specific operation and operates on signals received at the gate/neuron. A record building module constructs one or more records based on candidate data values derived from the data tree representation using the prediction architecture. The candidate data values are wrapped in signals and fed to gates/neurons to construct the one or more records.

公开(公告)号：WO2021179956A1

公开(公告)日：2021-09-16

申请号：PCT/CN2021/078646

申请日：2021-03-02

Applicant: 华为技术有限公司

Inventor： 徐传飞 ,  刘刚毅 ,  潘邵武

IPC: G06F40/10

Abstract: 提供了一种翻译方法、相关装置、设备及计算机可读存储介质，涉及人工智能及自然语言处理，应用于协同系统，协同系统包括Q个设备；Q个设备之间建立有通信连接；第一设备获取待翻译文本(S200)；针对待翻译文本，第一设备确定Q个设备中每个设备各自需要翻译的目标分配结果；至少一个目标分配结果包括目标翻译语句和目标翻译语句对应的附加翻译语句(S202)；第一设备向Q个设备中每个设备分别发送各自需要翻译的目标分配结果(S204)；第一设备获取Q个设备各自对应的翻译结果，并根据Q个设备各自对应的翻译结果获取待翻译文本的目标翻译结果(S206)；输出目标翻译结果(S208)。

公开(公告)号：WO2021178750A1

公开(公告)日：2021-09-10

申请号：PCT/US2021/021014

申请日：2021-03-05

Applicant: BELMONT TECHNOLOGY INC.

Inventor： LAIGLE, Jean-Marie ,  COLLANTES, Carlos ,  HARE, Eric

IPC: G06F40/10 ,  G06F40/30 ,  G06F16/21

Abstract: A method for extracting information from documents includes accepting a document as input to a programmed computer. In the computer, text is processed to identify named entities in the text. In the computer, the identified named entities are disambiguated. In the computer, presence of concepts in the document is established using an artificial neural network trained using established relationships between predetermined named entities and predetermined concepts. In the computer, parts of the document where established concepts occur are classified. In the computer, the disambiguated entities are characterized according to attributes associated with the disambiguated entities. In the computer, the characterized entities are used to update a database comprising published information corresponding to the characterized entities and the established present concepts.

公开(公告)号：WO2021092099A1

公开(公告)日：2021-05-14

申请号：PCT/US2020/058999

申请日：2020-11-05

Applicant: EPACCA, INC.

Inventor： ROUSHAR, Joseph

IPC: G06F40/20 ,  G06F40/205 ,  G06F40/42 ,  G06F40/284 ,  G06F40/40 ,  G06F40/30 ,  G06F40/10

Abstract: A system and method for mechanistic causal reasoning are provided herein. The method includes receiving an input text from a user, the input text specified in a natural language. The method also includes building a knowledge graph that represents real world facts and associations in the form of contextually tagged and weighted knowledge propositions, in multiple knowledge domains (e.g., causality, taxonomy, meronomy, time, space, identity, language, symbols and mathematical formulas). The method also includes resolving ambiguity and determining actual intent of the user for the input text, from a plurality of interpretations of intent for sentences in natural language understanding, using the knowledge graph in conjunction with natural language understanding and logical inference. The method also includes generating a response to the input text, as to why and/or how unknown factors resulted in a known outcome, or what outcomes are likely given known causal factors.

公开(公告)号：WO2021089129A1

公开(公告)日：2021-05-14

申请号：PCT/EP2019/080286

申请日：2019-11-05

Applicant: NALANTIS NV ,  NALANTIS HOLDING LTD

Inventor： DEVOS, Geert ,  PLATTEAU, Frank

IPC: G06Q10/10 ,  G06F40/10

Abstract: Computer-implemented job matching is disclosed. Based on a combination of pattern matching and concept extraction from natural language information, a template is automatically amended with an abstract concept of a concept network. Concept extraction is based on an association of a natural language expression with an abstract concept of a concept network. Pattern matching is used to discriminate between relevant and irrelevant natural language expressions based on the context of a natural language expression. For each of multiple different combinations of a candidate and a job,a numerical matching value based on corresponding candidate and job templates is automatically calculated. An ordered list associated with the multiple different combinations is displayed via a visualization means, or sent to a user device for display via a visualization means. The list comprises an ordering based on the numerical matching values.

公开(公告)号：WO2021017458A1

公开(公告)日：2021-02-04

申请号：PCT/CN2020/076063

申请日：2020-02-20

Applicant: 浙江口碑网络技术有限公司

Inventor： 廖春安

IPC: G06F40/10

Abstract: 本申请公开了一种图像识别的辅助处理方法、装置及系统，涉及图像识别技术领域，可降低用户获取信息的路径与成本，可提高用户编辑识别信息的效率和准确性。其中方法包括：输出包含图像识别信息的至少一个输入框，其中，所述图像识别信息中各项子信息在各自对应的输入框内进行展示；接收信息编辑指令，发送被选择的输入框所对应的待填写项标识，以便在所述被选择的输入框内进行信息编辑的同时，在上传图像中突出展示与所述待填写项标识对应的字段信息。本申请适用于图像识别的辅助处理。

公开(公告)号：WO2021006538A1

公开(公告)日：2021-01-14

申请号：PCT/KR2020/008637

申请日：2020-07-02

Applicant: 주식회사 데커드에이아이피

Inventor： 박지원 ,  김혁 ,  이지연

IPC: H04L12/58 ,  G06F40/10 ,  G06Q50/30 ,  G06T13/00

Abstract: 본 발명은 메신저 서비스에 있어서 텍스트 메시지를 브이모지(V-moji)로 표현하여 새로운 사용자 경험을 제공할 수 있는 아바타 비주얼 변환 장치 및 메시지 변환 방법에 관한 것입니다. 구체적으로, 발신자 단말기에 텍스트를 입력하면, 비주얼 변환 장치가 그 의미를 분석하여 감정좌표를 설정하고 이를 이용해 아바타의 감정표현을 위한 애니메이션 코드를 생성합니다. 또한 TTS용 텍스트를 추출하여 보이스 데이터를 생성하고 각 음소에 대한 비즘 표현을 위한 비즘 코드를 생성합니다. 수신자 단말기는 보이스 데이터를 출력하면서, 비즘 코드 및 애니메이션 코드를 기준으로 아바타의 비주얼 영상을 제어합니다.

公开(公告)号：WO2020112409A1

公开(公告)日：2020-06-04

申请号：PCT/US2019/062001

申请日：2019-11-18

Applicant: T-MOBILE USA, INC.

Inventor： CHIANG, Hsin-Fu Henry

IPC: G06F40/20 ,  G06F40/10 ,  H04L12/58 ,  H04W4/12

Abstract: A first user equipment (UE) - during a real time text (RTT) communication session with a second UE - may be configured to transmit RTT content in "word mode" by buffering text characters in local memory as they are typed by a user, and holding off on transmitting the buffered text characters until the user types a word delimiter or a timer expires, whichever occurs first. In an example process, the first UE may detect character user input requesting to type a text character, and, in response, the first UE starts a timer and buffers the text character in local memory. The timer can be restarted for additional text characters that are typed before expiration of the timer, and those additional text characters are also buffered. The buffered text characters are transmitted upon detecting delimiter user input requesting to type a word delimiter or the expiration of the timer, whichever occurs first.