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

US06684202B1 Computer-based system and method for finding rules of law in text 有权
标题翻译：基于计算机的系统和方法，用于在文本中查找法律规则
公开(公告)号：US06684202B1
公开(公告)日：2004-01-27
申请号：US09583867
申请日：2000-05-31
申请人： Timothy L. Humphrey , X. Allan Lu , James S. Wiltshire, Jr. , John T. Morelock , Spiro G. Collias , Salahuddin Ahmed
发明人： Timothy L. Humphrey , X. Allan Lu , James S. Wiltshire, Jr. , John T. Morelock , Spiro G. Collias , Salahuddin Ahmed
IPC分类号： G06N504
CPC分类号： G06F17/2715 , G06F17/2765 , Y10S707/99932 , Y10S707/99935
摘要： A system and method for binary classification of text units such as sentences, paragraphs and documents as either a rule of law (ROL) or not a rule of law (˜ROL). During a training phase of the system and method of the present invention, an initialized knowledge base and labeled or pre-classified sentences are used to build a trained knowledge base. The trained knowledge base contains an equation, a threshold, and a plurality of statistical values called Z values. When inputting text documents for classification, a Z value is generated for each term or token in the input text. The Z values are input to the equation which calculates a score for each sentence. Each calculated score is then compared to the threshold to classify each sentence as either ROL or ˜ROL.
摘要翻译：一种用于文本单元的二进制分类的系统和方法，例如句法，段落和文件作为法治（ROL）或不是法治（〜ROL）。在本发明的系统和方法的训练阶段，一个初始化的知识库和标记或预先分类的句子被用来建立一个训练有素的知识库。训练有素的知识库包含方程式，阈值和多个称为Z值的统计值。当输入用于分类的文本文档时，为输入文本中的每个项或令牌生成Z值。将Z值输入到计算每个句子的分数的方程式中。然后将每个计算得分与阈值进行比较，将每个句子分类为ROL或〜ROL。

2. 发明授权

US06502081B1 System and method for classifying legal concepts using legal topic scheme 有权
标题翻译：使用法律主题方案对法律概念进行分类的制度和方法
公开(公告)号：US06502081B1
公开(公告)日：2002-12-31
申请号：US09633266
申请日：2000-08-04
申请人： James S. Wiltshire, Jr. , John T. Morelock , Timothy L. Humphrey , X. Allan Lu , James M. Peck , Salahuddin Ahmed
发明人： James S. Wiltshire, Jr. , John T. Morelock , Timothy L. Humphrey , X. Allan Lu , James M. Peck , Salahuddin Ahmed
IPC分类号： G06F1518
CPC分类号： G06F17/30707 , G06N5/025 , G06Q10/10 , G09B7/00
摘要： An economic, scalable machine learning system and process perform document (concept) classification with high accuracy using large topic schemes, including large hierarchical topic schemes. One or more highly relevant classification topics is suggested for a-given document (concept) to be classified. The invention includes training and concept classification processes. The invention also provides methods that may be used as part of the training and/or concept classification processes, including: a method of scoring the relevance of features in training concepts, a method of ranking concepts based on relevance score, and a method of voting on topics associated with an input concept. In a preferred embodiment, the invention is applied to the legal (case law) domain, classifying legal concepts (rules of law) according to a proprietary legal topic classification scheme (a hierarchical scheme of areas of law).
摘要翻译：经济，可扩展的机器学习系统和过程使用大型主题方案（包括大型分层主题方案）以高精度执行文档（概念）分类。对于要分类的给定文件（概念），建议一个或多个高度相关的分类主题。本发明包括训练和概念分类过程。本发明还提供了可以用作训练和/或概念分类过程的一部分的方法，包括：评估训练概念中特征的相关性的方法，基于相关性得分对概念进行排名的方法和投票方法关于与输入概念相关的主题。在一个优选实施例中，本发明适用于法律（判例法）领域，根据专有法律主题分类方案（法律领域的分级方案）对法律概念（法治）进行分类。

3. 发明授权

US5410475A Short case name generating method and apparatus 失效
标题翻译：短案例名称生成方法和装置
公开(公告)号：US5410475A
公开(公告)日：1995-04-25
申请号：US47659
申请日：1993-04-19
申请人： X. Allan Lu , Timothy M. Klein
发明人： X. Allan Lu , Timothy M. Klein
IPC分类号： G06F17/27 , G06F15/21 , G06F15/401
CPC分类号： G06F17/278
摘要： A short case name generator transforms the long case name of a lawsuit into a short case name format. The text of the long case name is converted to low-level tokens using dictionaries and heuristic rules. Selected tokens are eliminated and other selected tokens are consolidated into higher level tokens. Each of a sequence of stages receives the output tokens from the preceding stage and produce tokens at a higher level of abstraction. Ultimately, the highest level tokens are produced. Selected high-level tokens are deleted and the surviving tokens are broken down to their component tokens, selected ones of which are also deleted. Next, the surviving tokens are converted back into the text they represent. Editing rules are then applied to that text which results in the short case name format.
摘要翻译：短案例名称生成器将长诉讼名称转换为短案名称格式。使用字典和启发式规则将长例名称的文本转换为低级令牌。删除所选的令牌，并将其他选定的令牌合并到更高级别的令牌中。每个阶段中的每一个接收来自前一阶段的输出令牌，并在较高抽象层次产生令牌。最终产生了最高级别的令牌。选定的高级令牌被删除，幸存的令牌被分解成它们的组件令牌，选定的令牌也被删除。接下来，幸存的令牌被转换成他们所代表的文本。然后将编辑规则应用于导致短名称格式的文本。

4. 发明授权

US5771378A Associative text search and retrieval system having a table indicating word position in phrases 失效
标题翻译：关联文本搜索和检索系统具有指示短语中的词位置的表
公开(公告)号：US5771378A
公开(公告)日：1998-06-23
申请号：US473824
申请日：1995-06-07
申请人： John Holt , David James Miller , X. Allan Lu , Ray Daley , Minh Doan , Richard G. Graham , Catherine Leininger , Darin W. McBeath , Thomas Pease , Stephen M. Sever , Dale Waddell , Franz Weckesser
发明人： John Holt , David James Miller , X. Allan Lu , Ray Daley , Minh Doan , Richard G. Graham , Catherine Leininger , Darin W. McBeath , Thomas Pease , Stephen M. Sever , Dale Waddell , Franz Weckesser
IPC分类号： G06F17/27 , G06F17/30 , G06F17/21
CPC分类号： G06F17/30622 , G06F17/274 , G06F17/30687 , Y10S707/99933 , Y10S707/99935 , Y10S707/99936
摘要： An associative text search and retrieval system uses one or more front end processors to interacting with a network having one or more user terminals connected thereto to allow a user to provide information to the system and receive information from the system. The system also includes storage for a plurality of text documents, and at least one processor, coupled to the front end processors and the document storage. The processor(s) search the text documents according to a search request provided by the user and provide to the front end processor a predetermined number of retrieved documents containing at least one term of the search request. The retrieved documents have higher ranks than documents not provided to the front end processor. The ranks are calculated using a formula that varies according to the square of the frequency in each of the text documents of each of the search terms.
摘要翻译：关联文本搜索和检索系统使用一个或多个前端处理器与具有连接到其上的一个或多个用户终端的网络进行交互，以允许用户向系统提供信息并从系统接收信息。该系统还包括用于多个文本文档的存储，以及耦合到前端处理器和文档存储器的至少一个处理器。处理器根据用户提供的搜索请求搜索文本文档，并向前端处理器提供包含搜索请求的至少一个项的预定数量的检索文档。检索到的文档的排名高于未提供给前端处理器的文档。使用根据每个搜索词的每个文本文档中的频率的平方而变化的公式来计算排名。

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