-
公开(公告)号：WO2019113578A1
公开(公告)日：2019-06-13
申请号：PCT/US2018/064731
申请日：2018-12-10
Applicant: WALMART APOLLO, LLC
Inventor： FERGUSON, David , BEYENE, Saba , HOWELL, Jay , PURMA, John
CPC classification number: G06K9/00456 , G06F17/2705 , G06F17/2785 , G06Q30/0282
Abstract: Systems, methods, and machine readable media are provided for classifying customer feedback. In exemplary embodiments, text is captured from at least one source relating to at least one product. The text is scanned and a score is produced for sentiment for the at least one product. The text is filtered into parts of speech and key words to produce filtered text. The filtered text is transformed into a term-document matrix. A risk score is calculated and prioritized based on the term-document matrix and the sentiment score. The product and the associated risk score are reported to a subject matter expert (SME), where a determination is made whether the product is reportable or non-reportable.
-
2.发明申请
公开(公告)号：WO2018185574A1
公开(公告)日：2018-10-11
申请号：PCT/IB2018/051349
申请日：2018-03-02
Applicant: LENDING SOLUTION S.R.L.
Inventor： MAFODDA, Salvatore , RUIZ GARCIA, Manuel Alejandro
CPC classification number: G06K9/00449 , G03B15/05 , G03B2215/0514 , G03B2215/0539 , G03B2215/0567 , G06K9/00456 , G06K9/00912 , G06K9/00979 , G06K9/2018 , G06K9/2027 , G06K9/22 , G07D7/01 , G07D7/12 , G07D7/2008 , G07D7/2016 , G07D7/206 , G07D7/2083
Abstract: The present invention relates to the context of the personal identification procedures, validation of identity documents, etc. In particular, the present invention proposes to offer a process and a semi-automatic and secure apparatus for recognition and validation of personal identities, identity documents or both at once.
-
公开(公告)号：WO2018183952A1
公开(公告)日：2018-10-04
申请号：PCT/US2018/025555
申请日：2018-03-30
Applicant: ALIBABA GROUP HOLDING LIMITED
Inventor： LIU, Yu , LIU, Ruitao
CPC classification number: G06F16/5838 , G06F16/583 , G06F16/951 , G06K9/00456 , G06K9/00684 , G06K9/4628 , G06K9/6267 , G06N3/08 , G06N3/084
Abstract: Methods, apparatuses and electronic devices for generating a feature vector, as well as searching methods, apparatuses and electronic devices are disclosed. The method for generating a feature vector includes: acquiring data information; extracting a semantic feature from the data information, to acquire semantic feature information; and acquiring a feature vector of the data information by using a preset function, with the semantic feature information as a parameter. The technical solution identifies picture information by recognizing semantics of image information and matching the semantics of the image information with natural language descriptions. Different from conventional image search schemes of existing search engines, this technical solution does not need to retrieve a text description of image information, but retrieves and identifies images based on the content of the image information. Therefore, results with higher accuracy may be returned compared with the existing text-based image search.
-
4.发明申请METHOD AND SYSTEM FOR GENERATING AND DISPLAYING STRUCTURED TOPICS OF A HEALTHCARE TREATMENT TAXONOMY IN DIFFERENT FORMATS 审中-公开用于生成和显示不同格式医疗处理分类结构主题的方法和系统
公开(公告)号：WO2017085552A1
公开(公告)日：2017-05-26
申请号：PCT/IB2016/001751
申请日：2016-11-15
Applicant: UCB BIOPHARMA SPRL
Inventor： HADDAD, Nassim , LIEUTENANT, Arnaud , FILAIRE, Thomas
IPC: G06F17/30
CPC classification number: G06F19/326 , G06F3/04847 , G06F17/30539 , G06F17/30696 , G06F17/30713 , G06F19/00 , G06K9/00456
Abstract: A computerized method for generating and displaying structured topics of a taxonomy in different formats is provided. The computerized method includes generating a categorized topic viewer graphical user interface allowing a user to select a textual model defining a corpus of documents to explore by delimiting a healthcare treatment product; generating in the categorized topic viewer graphical user interface, in response to an input of the user delimiting the healthcare treatment product, at least one of a plurality of tools; generating in a topic mapping graphical user interface an interactive map illustrating the number of documents for a first class for each corresponding country; generating in a trend generating graphical user interface at least one of a plurality of tools; and modifying each of the categorized topic viewer graphical user interface, the topic mapping graphical user interface and the trend generating graphical user interface in response to at least one input of the user into at least one taxonomy filter such that data displayed by each of the categorized topic viewer graphical user interface, the topic mapping graphical user interface and the trend generating graphical user interface display data related to a second class of the corpus of documents, the second class being a subcategory of the first class.
Abstract translation: 提供了用于以不同格式生成和显示分类标准的结构化主题的计算机化方法。 该计算机化方法包括：生成分类主题观看者图形用户界面，其允许用户通过界定保健治疗产品来选择定义要浏览的文档的语料库的文本模型; 在所述分类主题观看者图形用户界面中生成多个工具中的至少一个;响应于界定所述医疗保健治疗产品的所述用户的输入，生成多个工具中的至少一个; 在主题映射图形用户界面中生成交互式地图，该交互式地图示出每个对应国家的第一类文档的数量; 在趋势生成图形用户界面中生成多个工具中的至少一个; 以及响应于用户对至少一个分类过滤器的至少一个输入，修改每个分类的话题观看者图形用户界面，主题映射图形用户界面和趋势生成图形用户界面，使得由每个分类显示的数据 主题查看器图形用户界面，主题映射图形用户界面和趋势生成图形用户界面显示与第二类文档语料库相关的数据，第二类是第一类的子类别。
-
公开(公告)号：WO2017070011A1
公开(公告)日：2017-04-27
申请号：PCT/US2016/056962
申请日：2016-10-14
Applicant: GOOGLE INC.
Inventor： ALLEKOTTE, Kevin , GORDON, David Robert
IPC: G06F17/30
CPC classification number: G06F3/04842 , G06F3/0482 , G06F17/30247 , G06F17/30265 , G06K9/00456 , G06K9/344 , G06K2209/01 , G06T7/11 , G06T2207/10016
Abstract: Systems and methods of determining image captions are provided. In particular, metadata and image recognition data associated with an image can be obtained. The metadata and image recognition data can be used to generate one or more image tags associated with the image. One or more caption templates associated with the image can further be determined. Upon a selection of one or more of the image tags, an image caption can be generated using a caption template based at least in part on the user selection. The generated caption can be a sentence or phrase providing semantic and/or contextual information associated with the image.
Abstract translation: 提供了确定图像字幕的系统和方法。 具体而言，可以获得与图像相关联的元数据和图像识别数据。 元数据和图像识别数据可以用于生成与图像相关联的一个或多个图像标签。 可以进一步确定与图像相关联的一个或多个字幕模板。 在选择一个或多个图像标签之后，可以至少部分地基于用户选择使用标题模板来生成图像标题。 生成的标题可以是提供与图像相关联的语义和/或上下文信息的句子或短语。
-
Patent Agency Ranking
公开(公告)号：WO2017069741A1
公开(公告)日：2017-04-27
申请号：PCT/US2015/056447
申请日：2015-10-20
Applicant: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.
Inventor： MACHADO, Leonardo A. , THIELO, Marcelo R. , TRARBACH, Lisandro L.
CPC classification number: G06K9/00456 , G06K9/52 , G06K9/6282
Abstract: An example system includes a feature engine to determine a plurality of features of a document in a segment of an image. The system also includes a probability engine to determine a probability that the document is a particular document type based on the plurality of determined features. The system also includes a classify engine to classify the segment as the particular document type or a generic document type based on at least one of the determined probabilities.
Abstract translation: 示例系统包括用于确定图像的片段中的文档的多个特征的特征引擎。 该系统还包括基于多个确定的特征来确定文档是特定文档类型的概率的概率引擎。 该系统还包括分类引擎，用于基于所确定的概率中的至少一个将分段分类为特定文档类型或通用文档类型。
-
公开(公告)号：WO2017012642A1
公开(公告)日：2017-01-26
申请号：PCT/EP2015/066469
申请日：2015-07-17
Applicant: HEWLETT-PACKARD INDIGO B.V.
Inventor： ITAN, Liron , HAIK, Oren
IPC: B41F33/00
CPC classification number: G06K9/00483 , B41F33/0036 , G06F15/18 , G06K9/00456 , G06K9/40 , G06K9/4642 , G06K9/4652 , G06K9/4661 , G06K9/6259 , G06K9/6269 , G06K9/6282 , H04N1/04 , H04N2201/0081
Abstract: A method of detecting Moire artefacts in a digital image comprises calculating at least one parameter relating to at least one feature of the digital image. The at least one parameter is compared to at least one corresponding threshold, wherein the at least one threshold is determined by a machine learning process, based on a set of example images and reference parameters for the set of example images. It is determined whether the digital image contains Moire artefacts based on the results of the comparing.
Abstract translation: 一种在数字图像中检测莫尔伪影的方法包括计算与数字图像的至少一个特征相关的至少一个参数。 将至少一个参数与至少一个对应的阈值进行比较，其中基于用于该组示例图像的一组示例图像和参考参数，通过机器学习过程来确定该至少一个阈值。 基于比较的结果确定数字图像是否包含莫尔伪像。
-
公开(公告)号：WO2016047377A1
公开(公告)日：2016-03-31
申请号：PCT/JP2015/074470
申请日：2015-08-28
Applicant: 富士フイルム株式会社
Inventor： 山崎 善朗
IPC: G01N21/892 , B41J29/46 , G06T1/00
CPC classification number: G06K9/036 , B41J2/2142 , B41J2/2146 , B41J29/46 , G01N21/892 , G06K9/00456 , G06K9/4642 , G06K9/4652 , G06K9/6201 , G06K2009/6213 , G06T1/00 , G06T7/001 , G06T7/11 , G06T7/90 , G06T2207/10008 , G06T2207/10024 , G06T2207/20021 , G06T2207/30144 , H04N1/00005 , H04N1/4097 , H04N1/56
Abstract: 本発明は、確度の高い画像欠陥検出を一定時間内に行う画像記録装置、画像欠陥検出装置及び方法並びにプログラムを提供する。本発明の好ましい態様では、印刷元画像と印刷元画像に基づいて印刷された印刷画像とをそれぞれ対応する領域に分割し、分割された領域毎の画像特徴量を取得し、印刷元画像と印刷画像との分割された領域毎の差分の強度を抽出し、分割された領域毎の画像特徴量と差分の強度とから、印刷画像の分割された領域毎の欠陥を検出するために必要な時間を示す画像欠陥検出時間を算出し、分割された領域毎の画像特徴量と差分の強度とから、印刷画像の分割された領域毎の欠陥が存在する可能性を示す画像欠陥期待値を算出し、画像欠陥検出時間と画像欠陥期待値とから、印刷画像の分割された領域の画像欠陥を検出する順序を決定し、決定した順序で印刷画像の画像欠陥を検出する画像欠陥検出装置によって上記課題を解決する。
Abstract translation: 本发明提供一种图像记录装置，用于在给定的时间间隔内高度可靠地检测图像缺陷; 图像缺陷检测装置和方法; 和一个程序。 根据本发明的优选实施例，通过将打印原始图像和基于打印原始图像打印的打印图像分成相应区域的图像缺陷检测装置来解决问题; 获取每个分割区域的图像特征量，并且提取每个分割区域的打印原始图像和打印图像之间的差异强度; 根据每个分割区域的图像特征量差的强度，计算指示检测打印图像的每个分割区域中的缺陷所需的时间间隔的图像缺陷检测时间间隔; 根据每个分割区域的图像特征量差的强度，计算指示存在于打印图像的每个分割区域中的缺陷的可能性的图像缺陷期望值; 根据图像缺陷检测时间间隔和图像缺陷期望值，确定检测印刷图像的分割区域中的图像缺陷的顺序; 并以确定的顺序检测打印图像的分割区域中的图像缺陷。
-
9.发明申请
公开(公告)号：WO2016036044A1
公开(公告)日：2016-03-10
申请号：PCT/KR2015/008901
申请日：2015-08-26
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： KIM, Mi Su , JUNG, In Hyung , CHOE, Jeong In , CHOI, Chang Hyun , BAEK, Jong Wu , SEO, Jeong Wook
CPC classification number: G06F3/04883 , G06F3/03545 , G06K9/00456 , G06K9/00463 , G06K9/2081 , G06K9/3241 , G06K2009/363
Abstract: A method of processing image data of an electronic device is provided. The method includes dividing the image data into at least one segment corresponding to a feature of at least part of the image data, determining a category corresponding to the at least one segment, and displaying the at least one segment in a converted form based on the category.
Abstract translation: 提供一种处理电子设备的图像数据的方法。 该方法包括将图像数据划分成对应于图像数据的至少一部分的特征的至少一个片段，确定与至少一个片段对应的类别，并且基于转换形式显示所述至少一个片段 类别。
-
公开(公告)号：WO2016018458A1
公开(公告)日：2016-02-04
申请号：PCT/US2015/012431
申请日：2015-01-22
Applicant: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.
Inventor： BISWAL, Bibhu, Prasad , KOOTHUR, Sibin, Jos , PRABHU, Sandeep, Matti
CPC classification number: G06K9/00456 , G06K7/1413 , G06K9/00463 , G06K9/00469 , G06K19/06028 , G06T1/0028 , H04N1/32251
Abstract: Examples disclosed herein relate to selection of machine-readable link type. Examples include acquisition of an electronic document, selection of a machine-readable link type for evaluation, and a decision of whether at least one characteristic of the document satisfies at least one evaluation metric for use of the selected type of machine-readable link.
Abstract translation: 本文公开的示例涉及机器可读链接类型的选择。 示例包括获取电子文档，选择用于评估的机器可读链接类型，以及决定文档的至少一个特征是否满足使用所选类型的机器可读链接的至少一个评估度量。
-
-
-
-
-
-
-
-
-
Search Results
141
records
(took 0.024 seconds)
