专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11610418B2 Identifying versions of a form 有权
公开(公告)号：US11610418B2
公开(公告)日：2023-03-21
申请号：US16923441
申请日：2020-07-08
申请人： DST Technologies, Inc.
发明人： Ramesh Sridharan
IPC分类号： G06V30/418 , G06K9/62 , G06V10/26 , G06V30/24 , G06V30/412
摘要： Disclosed are a method and apparatus for identifying versions of a form. In an example, clients of a medical company fill out many forms, and many of these forms have multiple versions. The medical company operates in 10 states, and each state has a different version of a client intake form, as well as of an insurance identification form. In order to automatically extract information from a particular filled out form, it may be helpful to identify a particular form template, as well as the version of the form template, of which the filled out form is an instance. A computer system evaluates images of filled out forms, and identifies various form templates and versions of form templates based on the images.

2. 发明授权

US11182640B2 Analyzing content of digital images 有权
公开(公告)号：US11182640B2
公开(公告)日：2021-11-23
申请号：US16530778
申请日：2019-08-02
申请人： DST Technologies, Inc.
发明人： Huguens Jean , Yoriyasu Yano , Hui Peng Hu , Kuang Chen
IPC分类号： G06K9/46 , G06F16/583 , G06K9/00
摘要： Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.

3. 发明申请

US20150199386A1 System and Method for Candidate Sorting and Clustering 审中-公开
标题翻译：候选排序和聚类的系统和方法
公开(公告)号：US20150199386A1
公开(公告)日：2015-07-16
申请号：US14560584
申请日：2014-12-04
申请人： DST Technolgies, Inc.
发明人： Kevin W. Stokes
IPC分类号： G06F17/30 , G06F7/24
CPC分类号： G06F16/5866 , G06F7/24 , G06F16/35 , G06F16/51 , G06F16/56 , G06F16/5838 , G06K9/00483 , G06K9/4642
摘要： A system for organizing a plurality of candidates based on the relative similarity of a first candidate with respect to the remaining plurality of candidates is disclosed. The system includes a controller in communication with a storage device configured to receive and accessibly store a generated plurality of candidate images. The controller operable to analyze each of the plurality of candidate images to determined a numeric thumbnail based on a number of identified features in each of a plurality of grid elements of an array and a sum total number of all identified features in the array, calculate a similarity score between one of the plurality of determined numeric thumbnails and each of the remaining plurality of determined numeric thumbnails; and generate a logical group image order as a function of the highest similarity score between the one of the plurality of determined numeric thumbnails and each of the remaining plurality of determined numeric thumbnails.
摘要翻译：公开了一种用于基于第一候选者相对于其余多个候选者的相对相似度来组织多个候选的系统。该系统包括与被配置为接收和可访问地存储所生成的多个候选图像的存储设备通信的控制器。所述控制器可操作以分析所述多个候选图像中的每一个以基于阵列的多个网格元素中的每一个中的所识别的特征的数量和所述阵列中所有识别的特征的总和数来确定数字缩略图，所述多个确定的数字缩略图中的一个和剩余的多个确定的数字缩略图中的每一个之间的相似性分数; 并且生成作为所述多个确定的数字缩略图中的一个和剩余多个确定的数字缩略图中的每一个之间的最高相似度得分的函数的逻辑组图像顺序。

4. 发明授权

US08929687B2 System and method for candidate sorting and clustering 有权
标题翻译：候选排序和聚类的系统和方法
公开(公告)号：US08929687B2
公开(公告)日：2015-01-06
申请号：US13220397
申请日：2011-08-29
申请人： Kevin W. Stokes
发明人： Kevin W. Stokes
IPC分类号： G06K9/00 , G06F17/30 , G06K9/46
CPC分类号： G06F17/30268 , G06F7/24 , G06F17/30256 , G06F17/30271 , G06F17/3028 , G06F17/30705 , G06K9/00483 , G06K9/4642
摘要： A system for organizing a plurality of candidates based on the relative similarity of a first candidate with respect to the remaining plurality of candidates is disclosed. The system includes a controller in communication with a storage device configured to receive and accessibly store a generated plurality of candidate images. The controller operable to analyze each of the plurality of candidate images to determined a numeric thumbnail based on a number of identified features in each of a plurality of grid elements of an array and a sum total number of all identified features in the array, calculate a similarity score between one of the plurality of determined numeric thumbnails and each of the remaining plurality of determined numeric thumbnails; and generate a logical group image order as a function of the highest similarity score between the one of the plurality of determined numeric thumbnails and each of the remaining plurality of determined numeric thumbnails.
摘要翻译：公开了一种用于基于第一候选者相对于其余多个候选者的相对相似度来组织多个候选的系统。该系统包括与被配置为接收和可访问地存储所生成的多个候选图像的存储设备通信的控制器。所述控制器可操作以分析所述多个候选图像中的每一个以基于阵列的多个网格元素中的每一个中的所识别的特征的数量和所述阵列中所有识别的特征的总和数来确定数字缩略图，所述多个确定的数字缩略图中的一个和剩余的多个确定的数字缩略图中的每一个之间的相似性分数; 并且生成作为所述多个确定的数字缩略图中的一个和剩余多个确定的数字缩略图中的每一个之间的最高相似度得分的函数的逻辑组图像顺序。

5. 发明申请

US20140149440A1 User Generated Context Sensitive Information Presentation 审中-公开
标题翻译：用户生成的上下文敏感信息表示
公开(公告)号：US20140149440A1
公开(公告)日：2014-05-29
申请号：US13686773
申请日：2012-11-27
申请人： DST TECHNOLOGIES, INC.
发明人： Stephen J. Mason , Deni Esposito , Chin Hsu , Paul Martin Ives , Linh Hua
IPC分类号： G06F17/30
CPC分类号： G06Q10/0631
摘要： In order to increase the efficiency of the worker and ultimately decrease the cost of the worker performing work-related tasks, a method and a system for presenting information relevant to user activity of a user at a computing device is provided. A database including data records that each include information relevant to at least one user activity and at least one identifier identifying the at least one user activity is provided. Activities of a user are monitored and compared to the data records of the database. When a monitored activity matches an identifier of one of the data records, the information corresponding to the matched data record is presented to the user.
摘要翻译：为了提高工作人员的效率并最终降低执行工作相关任务的工作人员的成本，提供了一种用于在计算设备处呈现与用户的活动相关的信息的方法和系统。提供包括数据记录的数据库，每个数据记录包括与至少一个用户活动相关的信息和至少一个标识该至少一个用户活动的标识符。监视用户的活动并与数据库的数据记录进行比较。当被监视的活动与数据记录之一的标识符匹配时，将与匹配的数据记录相对应的信息呈现给用户。

6. 发明授权

US09411547B1 Compensation for print shift in standardized forms to facilitate extraction of data therefrom 有权
标题翻译：对标准化形式的打印移位进行补偿，以便于从中提取数据
公开(公告)号：US09411547B1
公开(公告)日：2016-08-09
申请号：US14811069
申请日：2015-07-28
申请人： DST Technologies, Inc.
发明人： Keith Bessinger , John Kirchmeier
IPC分类号： G06F3/12 , H04N1/00
CPC分类号： G06F17/243
摘要： A method comprising receiving a candidate image, including a first field, a second field, a first data element, and a second data element. The processor receives a definition of first and second form zones. The processor evaluates the first data element to determine a first measure of a similarity and the second data element to determine a second measure of a similarity. The processor computes a similarity value indicative of an overall similarity, iteratively compares the overall similarity to a previous iteration, modifies the positions of the form zones, and repeats the evaluating and computing based on the modified positions until the computed similarity value meets a threshold.
摘要翻译：一种方法，包括接收候选图像，包括第一场，第二场，第一数据元和第二数据元。处理器接收第一和第二表格区域的定义。处理器评估第一数据元素以确定相似性的第一度量，而第二数据元素确定相似性的第二量度。处理器计算指示总体相似度的相似度值，迭代地将总体相似度与先前迭代进行比较，修改形式区域的位置，并基于修改的位置重复评估和计算，直到计算出的相似度值达到阈值。

7. 发明申请

US20140355890A1 CANDIDATE IDENTIFICATION BY IMAGE FINGERPRINTING AND MODEL MATCHING 有权
标题翻译：通过图像指纹和模型匹配进行候选标识
公开(公告)号：US20140355890A1
公开(公告)日：2014-12-04
申请号：US14452701
申请日：2014-08-06
申请人： DST Technologies, Inc.
发明人： Joshua O. Highley
IPC分类号： G06K9/00
CPC分类号： G06K9/00483 , G06K9/00449 , G06K9/00463 , G06K9/00859 , G06K9/3208 , G06K9/6206 , G06K9/72
摘要： Candidate identification utilizing fingerprint identification is disclosed. The method includes receiving a candidate image comprising a plurality of constituent elements arranged in a content pattern, compensating for rotation variation in the content pattern of the received candidate, analyzing each of the plurality of constituent elements comprising the content pattern of the received candidate image to define a bounded area about each of the plurality of constituent elements, building a candidate fingerprint representative of the content pattern wherein the candidate fingerprint is based on the defined bounded area, comparing the candidate fingerprint to a plurality of fingerprints wherein each of the plurality of fingerprints represents one of a plurality of exemplars, identifying one of the plurality of fingerprints that corresponds to the candidate fingerprint, and evaluating the candidate and one or more identified exemplars to determine the best match there between, wherein the identified exemplar corresponds to the one of the plurality of fingerprints.
摘要翻译：公开了使用指纹识别的候选标识。该方法包括接收包括以内容模式排列的多个组成元素的候选图像，补偿接收候选的内容模式中的旋转变化，分析包括接收的候选图像的内容模式的多个构成元素中的每一个，定义关于所述多个构成元素中的每一个的有界区域，构建代表所述内容模式的候选指纹，其中所述候选指纹基于所述限定的有界区域，将所述候选指纹与多个指纹进行比较，其中所述多个指纹表示多个样本中的一个，识别与候选指纹相对应的多个指纹之一，以及评估候选和一个或多个识别的样本以确定其间的最佳匹配，其中所识别的样本对应于多个指纹 s。

8. 发明授权

US08832853B2 Managed virtual point to point communication service having verified directory, secure transmission and controlled delivery 有权
标题翻译：具有验证目录，安全传输和受控传递的托管虚拟点对点通信服务
公开(公告)号：US08832853B2
公开(公告)日：2014-09-09
申请号：US12632477
申请日：2009-12-07
申请人： Peter E. Clark , Paul M. Ives , Michael V. Gentry
发明人： Peter E. Clark , Paul M. Ives , Michael V. Gentry
IPC分类号： H04L12/58 , H04L9/32
CPC分类号： H04L63/10 , H04L9/32 , H04L51/12 , H04L51/22 , H04L51/34 , H04L2209/56 , H04L2209/60 , H04L2209/80
摘要： A system for providing a managed virtual point to point communication service having a verified directory and providing secure transmission and controlled delivery of electronic document images may include a memory, an interface, and a processor. The memory may store a verified directory of users. The interface may communicate with devices of sending and receiving users in the verified directory. The processor may be operative to receive a request to deliver an electronic document image from a sending user to a receiving user. The processor may provide secure access to the electronic document image to the receiving user. The processor may provide a delivery confirmation to the sending device of the sending user upon determining that the electronic document image was securely accessed by the receiving user. The delivery confirmation may indicate that the electronic document image was securely transmitted to the receiving user.
摘要翻译：一种用于提供具有经过验证的目录并提供电子文档图像的安全传输和控制传送的被管理虚拟点对点通信服务的系统可以包括存储器，接口和处理器。内存可以存储经过验证的用户目录。该接口可以与已验证目录中的发送和接收用户的设备进行通信。处理器可操作以接收将电子文档图像从发送用户传送到接收用户的请求。处理器可以向接收用户提供对电子文档图像的安全访问。当确定电子文档图像被接收用户安全访问时，处理器可以向发送用户的发送设备提供传送确认。传送确认可以指示电子文档图像被安全地传送到接收用户。

9. 发明申请

US20130051607A1 Candidate Identification by Image Fingerprinting and Model Matching 有权
标题翻译：通过图像指纹和模型匹配的候选识别
公开(公告)号：US20130051607A1
公开(公告)日：2013-02-28
申请号：US13220387
申请日：2011-08-29
申请人： Joshua O. Highley
发明人： Joshua O. Highley
IPC分类号： G06K9/00
CPC分类号： G06K9/00483 , G06K9/00449 , G06K9/00463 , G06K9/00859 , G06K9/3208 , G06K9/6206 , G06K9/72
摘要： Candidate identification utilizing fingerprint identification is disclosed. The method includes receiving a candidate image comprising a plurality of constituent elements arranged in a content pattern, compensating for rotation variation in the content pattern of the received candidate, analyzing each of the plurality of constituent elements comprising the content pattern of the received candidate image to define a bounded area about each of the plurality of constituent elements, building a candidate fingerprint representative of the content pattern wherein the candidate fingerprint is based on the defined bounded area, comparing the candidate fingerprint to a plurality of fingerprints wherein each of the plurality of fingerprints represents one of a plurality of exemplars, identifying one of the plurality of fingerprints that corresponds to the candidate fingerprint, and evaluating the candidate and one or more identified exemplars to determine the best match there between, wherein the identified exemplar corresponds to the one of the plurality of fingerprints.
摘要翻译：公开了使用指纹识别的候选标识。该方法包括接收包括以内容模式排列的多个组成元素的候选图像，补偿接收候选的内容模式中的旋转变化，分析包括接收的候选图像的内容模式的多个构成元素中的每一个，定义关于所述多个构成元素中的每一个的有界区域，构建代表所述内容模式的候选指纹，其中所述候选指纹基于所述限定的有界区域，将所述候选指纹与多个指纹进行比较，其中所述多个指纹表示多个样本中的一个，识别与候选指纹相对应的多个指纹之一，以及评估候选和一个或多个识别的样本以确定其间的最佳匹配，其中所识别的样本对应于多个指纹 s。

10. 发明授权

US11238275B2 Computer vision image feature identification via multi-label few-shot model 有权
公开(公告)号：US11238275B2
公开(公告)日：2022-02-01
申请号：US16678982
申请日：2019-11-08
申请人： DST Technologies, Inc.
发明人： Hui Peng Hu , Ramesh Sridharan
IPC分类号： G06K9/00 , G06F17/16 , G06N3/04 , G06N20/00 , G06K9/62
摘要： A technique making use of a few-shot model to determine graphical features present in an image based on a small set of examples with known graphical features. Where a support set including a number of images that each have a known combination of graphical features, the image recognition can identify unknown combinations of those graphical features in any number of query images. In an embodiment of the present disclosure examples of a filled-out form are used to interpret any number of additional filled out versions of the form.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式