-
1.发明授权Handwritten word recognition using nearest neighbor techniques that allow adaptive learning 失效使用允许自适应学习的最近邻技术的手写字识别公开(公告)号：US07697760B2
公开(公告)日：2010-04-13
申请号：US11972913
申请日：2008-01-11
CPC分类号： G06K9/00852
摘要： A handwritten word is transcribed into a list of possibly correct transcriptions of the handwritten word. The list contains a number of text words, and this list is compared with previously stored set of lists of text words. Based on a metric, one or more nearest neighbor lists are selected from the set. A decision is made, according to a number of combination rules, as to which text word in the nearest neighbor lists or the recently transcribed list is the best transcription of the handwritten word. This best transcription is selected as the appropriate text word transcription of the handwritten word. The selected word is compared to a true transcription of the selected word Machine learning techniques are used when the selected and true transcriptions differ. The machine learning techniques create or update rules that are used to determine which text word of the nearest neighbor lists or the recently transcribed list is the correct transcription of the handwritten word.
摘要翻译： 手写词被转录成手写词的可能正确转录的列表。 该列表包含多个文本字，并将该列表与之前存储的文本列表集进行比较。 基于度量，从集合中选择一个或多个最近邻居列表。 根据多个组合规则，决定最近邻居列表中的哪个文本字或最近转录的列表是手写词的最佳转录。 这个最好的录音被选为手写词的适当的文字转录。 将所选择的词与所选择的词的真实转录进行比较当所选择的和真实的转录不同时，使用机器学习技术。 机器学习技术创建或更新用于确定最近邻居列表的文本字或最近转录的列表是手写字的正确转录的规则。
-
公开(公告)号：US07627596B2
公开(公告)日：2009-12-01
申请号：US10079741
申请日：2002-02-19
申请人： Thomas Yu-Kiu Kwok , James Randal Moulic , Kenneth Blair Ocheltree , Michael Peter Perrone , John Ferdinand Pitrelli , Eugene Henry Ratzlaff , Gregory Fraser Russell , Jayashree Subrahmonia
发明人： Thomas Yu-Kiu Kwok , James Randal Moulic , Kenneth Blair Ocheltree , Michael Peter Perrone , John Ferdinand Pitrelli , Eugene Henry Ratzlaff , Gregory Fraser Russell , Jayashree Subrahmonia
IPC分类号： G06F17/00
CPC分类号： G06K9/00872 , Y10S707/99943
摘要： The techniques in the present invention allow both text and handwritten queries, and the queries can be single-word or multiword. Generally, each handwritten word in a handwritten document is converted to a document stack of words, where each document stack contains a list of text words and a word score of some type for each text word in the list. The query is also converted to one or more stacks of words. A measure is determined from each query and document stack. Documents that meet search criteria in the query are then selected based on the query and the values of the measures. The present invention also performs multiple recognitions, with multiple recognizers, on a handwritten document to create multiple recognized transcriptions of the document. The multiple transcriptions are used for document retrieval. In another embodiment, a single transcription is created from the multiple transcriptions, and the single transcription is used for document retrieval.
-
3.发明授权Handwritten word recognition using nearest neighbor techniques that allow adaptive learning 失效使用允许自适应学习的最近邻技术的手写字识别公开(公告)号：US07343041B2
公开(公告)日：2008-03-11
申请号：US10079763
申请日：2002-02-19
CPC分类号： G06K9/00852
摘要： A handwritten word is transcribed into a list of possibly correct transcriptions of the handwritten word. The list contains a number of text words, and this list is compared with previously stored set of lists of text words. Based on a metric, one or more nearest neighbor lists are selected from the set. A decision is made, according to a number of combination rules, as to which text word in the nearest neighbor lists or the recently transcribed list is the best transcription of the handwritten word. This best transcription is selected as the appropriate text word transcription of the handwritten word. The selected word is compared to a true transcription of the selected word. Machine learning techniques are used when the selected and true transcriptions differ. The machine learning techniques create or update rules that are used to determine which text word of the nearest neighbor lists or the recently transcribed list is the correct transcription of the handwritten word.
摘要翻译： 手写词被转录成手写词的可能正确转录的列表。 该列表包含多个文本字，并将该列表与之前存储的文本列表集进行比较。 基于度量，从集合中选择一个或多个最近邻居列表。 根据多个组合规则，决定最近邻居列表中的哪个文本字或最近转录的列表是手写词的最佳转录。 这个最好的录音被选为手写词的适当的文字转录。 将所选择的词与所选词的真实转录进行比较。 当选择和真实转录不同时，使用机器学习技术。 机器学习技术创建或更新用于确定最近邻居列表的文本字或最近转录的列表是手写字的正确转录的规则。
-
公开(公告)号：US20090228311A1
公开(公告)日：2009-09-10
申请号：US12042424
申请日：2008-03-05
申请人： Trieu C. Chieu , Manikandan Dharamarajan , Thomas Yu-Kiu Kwok , Linh Hue Lam , Thao Ngoc Nguyen , Kakan Roy , Amit Jaysukhlal Shah
发明人： Trieu C. Chieu , Manikandan Dharamarajan , Thomas Yu-Kiu Kwok , Linh Hue Lam , Thao Ngoc Nguyen , Kakan Roy , Amit Jaysukhlal Shah
IPC分类号： G06Q10/00
CPC分类号： G06F17/2288 , G06F17/30011 , G06Q10/063 , G06Q10/10 , G06Q90/20
摘要： Access to documents by parties can be controlled as follows. First, access can be controlled in accordance with access counters associated with the parties, where the documents have one or more versions. Second, access can be controlled in accordance with access levels associated with the parties. The access level of each party is one of a first access level, a second access level, a third access level, or a fourth access level. The first, second, third, and fourth access levels are ordered from the first access level to the fourth access level such that the first access level provides a greatest degree of access to the documents and the fourth access level provides a least degree of access to the documents. Third, access can be controlled in accordance with placement of organizations within a hierarchy of organizations, where the parties are organized over the organizations.
摘要翻译： 各方可以控制文件的访问权限如下。 首先，可以根据与各方相关联的访问计数器来控制访问，其中文档具有一个或多个版本。 第二，可以根据与各方相关的访问级别来控制访问。 每个方的访问级别是第一访问级别，第二访问级别，第三访问级别或第四访问级别之一。 第一，第二，第三和第四访问级别从第一访问级别排序到第四访问级别，使得第一访问级别提供对文档的最大程度的访问，并且第四访问级别提供对 文件。 第三，可以根据组织层次结构中的组织的安置来控制访问，各方在组织中组织各方。
-
5.发明申请SYSTEMS AND METHODS TO EXTRACT DATA AUTOMATICALLY FROM A COMPOSITE ELECTRONIC DOCUMENT 失效从复合电子文档自动提取数据的系统和方法公开(公告)号：US20080235227A1
公开(公告)日：2008-09-25
申请号：US12132845
申请日：2008-06-04
申请人： Thomas Yu-Kiu Kwok , Thao Ngoc Nguyen , Kakan Roy
发明人： Thomas Yu-Kiu Kwok , Thao Ngoc Nguyen , Kakan Roy
CPC分类号： G06Q10/10
摘要： A system and method for automatically extracting contract data from electronic contracts includes an administrator module configured to provide templates for inputting document patterns and a list of contract data tags for each of a plurality of contract document types. A parser is configured to convert an electronic contract document into a contract text document and reformat the contract text document to provide a pattern for the text contract document. A pattern recognition engine is configured to determine a list of contract document types in the electronic contract by comparing and matching patterns of all known contract document types with the pattern of the contract text document. A contract data extraction engine is configured to extract contract data for each contract document type on the list.
摘要翻译： 用于从电子合同自动提取合同数据的系统和方法包括：管理员模块，被配置为提供用于输入文档模式的模板和用于多个合同文档类型中的每一个的合同数据标签的列表。 解析器被配置为将电子合同文档转换成合同文本文档并重新格式化合同文本文档以提供文本合同文档的模式。 模式识别引擎被配置为通过将所有已知合同文档类型的模式与合同文本文档的模式进行比较和匹配来确定电子合同中的合同文档类型的列表。 合同数据提取引擎被配置为提取列表中每个合同文档类型的合同数据。
-
公开(公告)号：US20120197942A1
公开(公告)日：2012-08-02
申请号：US13443392
申请日：2012-04-10
申请人： Trieu C. Chieu , Manikandan Dharamarajan , Thomas Yu-Kiu Kwok , Linh Hue Lam , Thao Ngoc Nguyen , Kakan Roy , Amit Jaysukhial Shah
发明人： Trieu C. Chieu , Manikandan Dharamarajan , Thomas Yu-Kiu Kwok , Linh Hue Lam , Thao Ngoc Nguyen , Kakan Roy , Amit Jaysukhial Shah
IPC分类号： G06F17/30
CPC分类号： G06F17/2288 , G06F17/30011 , G06Q10/063 , G06Q10/10 , G06Q90/20
摘要： Illustrative embodiments disclose a computer process controlling access to one or more documents by one or more parties, the parties organized over one or more organizations. In response to a party associated with a first organization attempting to access documents, determining an access level associated with the party as a first access level, a second access level, a third access level, or a fourth access level. The first, second, third and fourth access levels are ordered from the first access level to the fourth access level such that the first access level provides a greatest degree of access to the documents and the fourth access level provides a least degree of access to the documents. In response to determining the access level associated with the party, permitting the party to access the documents, or preventing the party from accessing the documents, according to the access level associated with the party.
摘要翻译： 示例性实施例公开了一个控制对一个或多个文档的访问的计算机过程，所述一个或多个参与者组织在一个或多个组织上。 响应于与尝试访问文档的第一组织相关联的一方，将与该方相关联的访问级别确定为第一访问级别，第二访问级别，第三访问级别或第四访问级别。 第一，第二，第三和第四访问级别从第一访问级别排序到第四访问级别，使得第一访问级别提供对文档的最大程度的访问，并且第四访问级别提供对 文件。 响应于确定与该方相关联的访问级别，允许该方访问该文档，或者根据与该方相关联的访问级别来阻止该方访问该文档。
-
7.发明授权Systems and methods to extract data automatically from a composite electronic document 失效从复合电子文档自动提取数据的系统和方法公开(公告)号：US08140468B2
公开(公告)日：2012-03-20
申请号：US12132845
申请日：2008-06-04
申请人： Thomas Yu-Kiu Kwok , Thao Ngoc Nguyen , Kakan Roy
发明人： Thomas Yu-Kiu Kwok , Thao Ngoc Nguyen , Kakan Roy
CPC分类号： G06Q10/10
摘要： A system and method for automatically extracting contract data from electronic contracts includes an administrator module configured to provide templates for inputting document patterns and a list of contract data tags for each of a plurality of contract document types. A parser is configured to convert an electronic contract document into a contract text document and reformat the contract text document to provide a pattern for the text contract document. A pattern recognition engine is configured to determine a list of contract document types in the electronic contract by comparing and matching patterns of all known contract document types with the pattern of the contract text document. A contract data extraction engine is configured to extract contract data for each contract document type on the list.
摘要翻译： 用于从电子合同自动提取合同数据的系统和方法包括：管理员模块，被配置为提供用于输入文档模式的模板和用于多个合同文档类型中的每一个的合同数据标签的列表。 解析器被配置为将电子合同文档转换成合同文本文档并重新格式化合同文本文档以提供文本合同文档的模式。 模式识别引擎被配置为通过将所有已知合同文档类型的模式与合同文本文档的模式进行比较和匹配来确定电子合同中的合同文档类型的列表。 合同数据提取引擎被配置为提取列表中每个合同文档类型的合同数据。
-
8.发明申请SYSTEMS AND METHODS TO ASSOCIATE INVOICE DATA WITH A CORRESPONDING ORIGINAL INVOICE COPY IN A STACK OF INVOICES 失效将发票数据与相关原始发票复制在一起的发票中的系统和方法公开(公告)号：US20090067013A1
公开(公告)日：2009-03-12
申请号：US11852591
申请日：2007-09-10
申请人： GRAEME NEVILLE DIXON , Thomas Yu-Kiu Kwok , Jim A. Laredo , Sridhar Maradugu , Thao Ngoc Nguyen , Brian L. White
发明人： GRAEME NEVILLE DIXON , Thomas Yu-Kiu Kwok , Jim A. Laredo , Sridhar Maradugu , Thao Ngoc Nguyen , Brian L. White
IPC分类号： H04N1/04
CPC分类号： G06F17/30011 , G06F17/30722 , H04N1/32128 , H04N2201/3225 , H04N2201/3243
摘要： A system and method for associating documents includes providing a plurality of scanned documents of different types and identifying a document type for each scanned document by comparing a determined pattern for each scanned document to known document patterns. Metadata values are extracted from each scanned document using metadata labels, and each scanned document is identified by using extracted metadata values. A stored electronic record is associated with each scanned document by employing the extracted metadata values such that a relationship between the stored electronic record and the associated scanned document is determined and stored.
摘要翻译： 用于关联文档的系统和方法包括提供不同类型的多个扫描文档，并通过将每个扫描文档的确定图案与已知文档图案进行比较来识别每个扫描文档的文档类型。 使用元数据标签从每个扫描的文档中提取元数据值，并通过使用提取的元数据值来标识每个扫描的文档。 存储的电子记录通过采用所提取的元数据值与每个扫描的文档相关联，使得确定并存储所存储的电子记录与相关联的扫描文档之间的关系。
-
9.发明申请Systems and methods to extract data automatically from a composite electronic document 审中-公开从复合电子文档自动提取数据的系统和方法公开(公告)号：US20070300295A1
公开(公告)日：2007-12-27
申请号：US11472868
申请日：2006-06-22
申请人： Thomas Yu-Kiu Kwok , Thao Ngoc Nguyen , Kakan Roy
发明人： Thomas Yu-Kiu Kwok , Thao Ngoc Nguyen , Kakan Roy
IPC分类号： H04L9/32
CPC分类号： G06Q10/10
摘要： A system and method for automatically extracting contract data from electronic contracts includes an administrator module configured to provide templates for inputting document patterns and a list of contract data tags for each of a plurality of contract document types. A parser is configured to convert an electronic contract document into a contract text document and reformat the contract text document to provide a pattern for the text contract document. A pattern recognition engine is configured to determine a list of contract document types in the electronic contract by comparing and matching patterns of all known contract document types with the pattern of the contract text document. A contract data extraction engine is configured to extract contract data for each contract document type on the list.
摘要翻译： 用于从电子合同自动提取合同数据的系统和方法包括：管理员模块，被配置为提供用于输入文档模式的模板和用于多个合同文档类型中的每一个的合同数据标签的列表。 解析器被配置为将电子合同文档转换成合同文本文档并重新格式化合同文本文档以提供文本合同文档的模式。 模式识别引擎被配置为通过将所有已知合同文档类型的模式与合同文本文档的模式进行比较和匹配来确定电子合同中的合同文档类型的列表。 合同数据提取引擎被配置为提取列表中每个合同文档类型的合同数据。
-
公开(公告)号：US06397256B1
公开(公告)日：2002-05-28
申请号：US09238254
申请日：1999-01-27
IPC分类号： G06F1516
CPC分类号： H04L29/06 , G06F17/30873 , G06F2216/15 , G06F2221/2101 , H04L67/22 , H04L69/329
摘要： A system for monitoring Internet usage, in accordance with the present invention, includes an Internet access unit for accessing the Internet, the Internet access unit including a browser for navigating on the Internet. A transmission device is included for transmitting browser activity and providing browser activity information to be transmitted to a monitoring unit. The monitoring unit is remotely disposed from the Internet access unit and coupled to the transmission device, the monitoring unit including a display for viewing and recording Internet activity of the Internet access unit.
摘要翻译： 根据本发明的用于监控因特网使用的系统包括用于访问因特网的因特网接入单元，所述因特网接入单元包括用于在互联网上导航的浏览器。 包括发送装置用于发送浏览器活动并提供要发送到监视单元的浏览器活动信息。 监视单元从互联网接入单元远程设置并耦合到传输设备，监视单元包括用于观看和记录因特网接入单元的因特网活动的显示器。
-
-
-
-
-
-
-
-
-
搜索结果
23 条记录 (耗时 0.019 秒)
