公开(公告)号：WO01093102A1

公开(公告)日：2001-12-06

申请号：PCT/US2001/015127

申请日：2001-05-10

IPC: G06F17/27 ,  G06F17/30

CPC classification number: G06F17/2775 ,  G06F17/2715 ,  G06F17/279 ,  G06F17/30616 ,  Y10S707/99932 ,  Y10S707/99935 ,  Y10S707/99945 ,  Y10S707/99954

Abstract: A method and apparatus is disclosed for making predictions about entities represented in documents and for information analysis of text documents or the like, from a large number of such documents. Predictive models (80) are executed responsive to variables (70) derived from canonical documents (60) to determine documents containing desired attributes or characteristics. The canonical documents are derived from standardized documents (30), which in turn are derived from original documents.

Abstract translation: 公开了一种方法和装置，用于从大量这样的文档中对文档中表示的实体进行预测，以及对文本文档等的信息分析。 响应于从规范文档（60）导出的变量（70）来执行预测模型（80）以确定包含期望属性或特征的文档。 标准文件来源于标准化文件（30），而这些文件反过来源于原始文件。

公开(公告)号：WO01004812A3

公开(公告)日：2001-11-15

申请号：PCT/US2000/018422

申请日：2000-07-05

IPC: G06F17/21 ,  G06F17/27 ,  G06F17/28 ,  G06Q10/08 ,  G06Q10/10 ,  G06F17/60

CPC classification number: G06F17/279 ,  G06F17/2745 ,  G06F17/2775 ,  G06F17/2881 ,  G06Q10/087 ,  G06Q10/10 ,  Y10S707/917 ,  Y10S707/955 ,  Y10S707/962 ,  Y10S707/967 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99943 ,  Y10S707/99944

Abstract: An object-based, semantic representation (277) for documents as information containers, using a controlled taxonomy, facilitates the extraction of meaning from such information containers to provide high-level, automated document interpretation. The high-level functions that are enabled include automated filtering of an information container in accordance with the controlled taxonomy and a set of conditions, to produce a result having only those information objects that are applicable under the specified set of conditions. These functions further include automated combination of information objects which comprise the information containers, to build a composite information container that reflects combined meaning of the associated documents, and automated handling of references from one information container to another.

Abstract translation: 本发明涉及用于诸如信息容器之类的文档的对象的语义表示（277），借助受控分类来促进从这些信息容器提取含义，以便 提供文档的高级自动解释。 授权的高级功能包括根据所订购的分类法和一组条件对信息容器进行自动过滤，以便根据指定的一组条件只保留适用的信息对象。 这些功能还包括包括信息容器的信息对象的自动组合，以便构建反映相关文档的组合信息的复合信息容器，以及信息容器的自动参考操作。 信息给另一个人。

公开(公告)号：WO01006408A1

公开(公告)日：2001-01-25

申请号：PCT/US2000/004505

申请日：2000-02-22

IPC: G06F17/27

CPC classification number: G06F17/279 ,  G06F17/2715 ,  G06F17/274 ,  G06F17/2755 ,  G06F17/2775

Abstract: A summary of an input document is generated by extracting at least one sentence from the document and parsing the extracted sentences into components, such as in a parse tree (110). Sentence reduction processing is performed to mark components which can be removed from the parse trees (135). Sentence reduction can include context importance processing, probabilistic processing, and linguistic knowledge based processing, probabilistic processing includes identifying sentence combination operations and establishing rules for applying the sentence combination operations to mark the parse trees to merge at least two sentences (140). Sentence combination processing also provides a paste operation to operate on the marked components to effect the indicated removal and combination of sentence components, thereby generating summary sentences for the input document.

Abstract translation: 通过从文档中提取至少一个句子并将提取的句子解析成诸如解析树（110）中的组件来生成输入文档的摘要。 执行句子缩减处理以标记可从解析树（135）中移除的分量。 句子减少可以包括语境重要性处理，概率处理和基于语言知识的处理，概率处理包括识别语句组合操作和建立用于应用语句组合操作来标记解析树以合并至少两个句子的规则（140）。 句子组合处理还提供了对标记的组件进行操作的粘贴操作以实现所指示的删除和组合句子组件，从而为输入文档生成摘要句子。

公开(公告)号：WO00070491A2

公开(公告)日：2000-11-23

申请号：PCT/US2000/013398

申请日：2000-05-16

IPC: G06F17/27 ,  G06Q10/00 ,  G06F17/00

CPC classification number: G06F17/2775 ,  G06F17/2715 ,  G06Q10/109

Abstract: Waiting prior to engaging an automated service, for enhancement thereof, is disclosed. In one embodiment, a computer-implemented method first determines an automated service to be performed. The method waits a predetermined time between a minimum time and a maximum time, before performing the automated service. In one embodiment, the method determines the predetermined time by performing a statistical regression as to the predetermined time that should be waited based on a length of a received text.

Abstract translation: 在进行自动化服务之前等待进行增强。 在一个实施例中，计算机实现的方法首先确定要执行的自动服务。 在执行自动服务之前，该方法在最小时间和最大时间之间等待预定时间。 在一个实施例中，该方法通过根据接收到的文本的长度执行关于应当等待的预定时间的统计回归来确定预定时间。

公开(公告)号：WO00062194A2

公开(公告)日：2000-10-19

申请号：PCT/US2000/009733

申请日：2000-04-12

IPC: G06F17/27 ,  G06F17/30 ,  G06F17/20

CPC classification number: G06F17/277 ,  G06F17/2705 ,  G06F17/2775 ,  G06F17/2785 ,  G06F17/30616

Abstract: A "domain-general" method for topical segmentation of a document input includes the steps of: extracting one or more selected terms from a document; linking occurrences of the extracted terms based upon the proximity of similar terms; and assigning weighted scores to paragraphs of the document input corresponding to the linked occurrences. In accordance with the present invention, the values of the assigned scores depend upon the type of the selected terms, e.g., common noun, proper noun, pronominal, and the position of the linked occurrences with respect to the paragraphs, e.g., front, during, rear, etc. Upon zero-sum normalization, the assigned scores represent the boundaries of the topical segments of the document input.

Abstract translation: 用于文档输入的局部分割的“一般”方法包括以下步骤：从文档中提取一个或多个所选项; 基于类似术语的接近度连接提取的术语的出现; 并将加权分数分配给对应于链接事件的文档输入的段落。 根据本发明，所分配的分数的值取决于所选择的术语的类型，例如，常用名词，专有名词，代词，以及相对于段落的链接事件的位置，例如在前面，在 ，后部等。在零和标准化时，分配的分数表示文档输入的主题段的边界。

公开(公告)号：WO0055786A2

公开(公告)日：2000-09-21

申请号：PCT/US0006647

申请日：2000-03-15

Applicant: SNAP ON TECH INC ,  BELLEFEUILLE JEAN DE

Inventor： DE BELLEFEUILLE JEAN

IPC: G06F17/24 ,  G06F17/27 ,  G06F17/28 ,  G06Q99/00 ,  G06F17/60

CPC classification number: G06F17/24 ,  G06F17/2775 ,  G06F17/2827 ,  G06Q99/00

Abstract: A multilingual software application for controlling vehicle servicing equipment includes a plurality of dynamic link libraries corresponding to supported national languages. The multilingual application is configured to receive input selecting one of the supported national languages, load the corresponding dynamic link library, and redisplay during run-time operating instructions for the vehicle servicing equipment in the selected national language. An international language management system is provided to develop, maintain, and synchronize the dynamic link libraries based on processing resource files from which the dynamic link libraries are compiled.

Abstract translation: 用于控制车辆维修设备的多语言软件应用包括与支持的本国语言相对应的多个动态链接库。 多语言应用被配置为接收输入，选择所支持的本国语言之一，加载相应的动态链接库，并且在所选国家语言的车辆维修设备的运行时操作指令期间重新显示。 提供了一种国际语言管理系统，用于开发，维护和同步动态链接库，基于处理从其中编译动态链接库的资源文件。

公开(公告)号：WO00014727A1

公开(公告)日：2000-03-16

申请号：PCT/US1999/020445

申请日：1999-09-08

IPC: G06F17/30 ,  G06F3/16 ,  G06F13/00 ,  G06F17/27 ,  G06F17/28 ,  G10L15/00 ,  G10L15/06 ,  G10L15/18 ,  G10L15/22 ,  G10L15/26 ,  G10L15/28 ,  H04L29/06

CPC classification number: G06F17/2785 ,  G06F3/167 ,  G06F17/27 ,  G06F17/2775 ,  G10L15/18 ,  G10L15/19 ,  G10L15/22 ,  H04L29/06

Abstract: A system and method for interacting with a computer using utterances, speech processing and natural language processing. The system comprises a speech processor for searching a first grammar file for a matching phrase for the utterance, and for searching a second grammar file for the matching phrase if the matching phrase is not found in the first grammar file. The system also includes a natural language processor for searching a database for a matching entry for the matching phrase; and an application interface for performing an action associated with the matching entry if the matching entry is found in the database. The system utilizes context-specific grammars, thereby enhancing speech recognition and natural language processing efficiency. Additionally, the system adaptively and interactively "learns" words and phrases, and their associated meanings.

Abstract translation: 一种使用话语，语音处理和自然语言处理与计算机交互的系统和方法。 该系统包括语音处理器，用于搜索第一语法文件以获得用于话语的匹配短语，并且用于在第一语法文件中找不到匹配短语时搜索匹配短语的第二语法文件。 该系统还包括一个自然语言处理器，用于搜索数据库中匹配词组的匹配项; 以及用于在数据库中找到匹配条目时执行与匹配条目相关联的动作的应用接口。 该系统利用上下文特定的语法，从而增强语音识别和自然语言处理效率。 此外，系统自适应地和交互地“学习”单词和短语及其相关联的含义。

公开(公告)号：WO00007094A2

公开(公告)日：2000-02-10

申请号：PCT/US1999/017431

申请日：1999-07-30

IPC: G06F17/22 ,  G06F17/27 ,  G06F17/30 ,  G06F7/00

CPC classification number: G06F17/30985 ,  G06F17/2211 ,  G06F17/27 ,  G06F17/2775 ,  Y10S707/99934

Abstract: A method and apparatus are disclosed for comparing an input or query file to a set of files to detect similarities between the query file and the set of files, and digitally shredding files that match, to some degree, the query file and doing so from within the comparison feature. Using a comparison program, the query file is compared with each non-query file in a data processing system, ranging from a stand-alone computer to an enterprise computing network. A list of non-query files having some degree of similarity with the query file is compiled and presented to the user via a user interface within the comparison program. Certain or all non-query files can then be deleted by marking the names of those non-query files in the list. The comparison program can be of the type using either clustering or coalescing, or both, known hashing techniques, or other comparison algorithms.

Abstract translation: 一种用于将输入或查询文件与一组文件进行比较以检测查询文件和该组文件之间的相似性并且数字地将这些文件 对应于查询文件的一定程度，这个过程是从比较函数本身执行的。 查询文件通过比较程序与计算机系统的每个其他文件进行比较，计算机系统可以包括独立计算机或企业计算机网络。 建立与查询文件具有一些相似性的文件列表，并通过比较程序中的用户界面将其呈现给用户。 然后可以通过在列表中指定这些文件的名称来销毁查询文件以外的一些或全部文件。 比较程序可以是使用聚类或合并或两者都知道的散列技术或其他比较算法的程序。

公开(公告)号：WO99062001A1

公开(公告)日：1999-12-02

申请号：PCT/US1999/011856

申请日：1999-05-28

IPC: G06F17/21 ,  G06F17/27 ,  G06F17/28

CPC classification number: G06F17/277 ,  G06F17/271 ,  G06F17/2715 ,  G06F17/2755 ,  G06F17/2775 ,  G06F17/2863

Abstract: The present invention provides a facility for selecting from a sequence of natural language characters combinations of characters that may be words. The facility uses probability indications for each of a plurality of words as a function of adjacent characters.

Abstract translation: 本发明提供了一种用于从自然语言字符序列中选择可以是单词的字符组合的设施。 该设施使用作为相邻字符的函数的多个单词中的每一个的概率指示。

公开(公告)号：WO1997010589A1

公开(公告)日：1997-03-20

申请号：PCT/US1996014743

申请日：1996-09-12

Applicant: AT & T CORP.

Inventor： AT & T CORP. ,  GORIN, Allen, Louis ,  PARKER, Barry, Allen ,  SCHERER, James, B. ,  WILPON, Jay, Gordon

IPC: G10L09/00

CPC classification number: G06F17/2765 ,  G06F17/2715 ,  G06F17/2775 ,  G06Q30/06 ,  G10L15/1822

Abstract: The automated call routing system and method which operates on a call routing objective of a calling expressed in natural speech of the calling party. The system incorporates a speech recognition function, as to which a calling party's natural-speech call routing objective provides an input (15), and which is trained to recognize a plurality of meaningful phrases (10), each such phrase being related to a specific call routing objective. Upon recognition of one or more of such meaningful phrases in a calling party's input speech, an interpretation function (20) then acts on such calling party's routing objective, request to either implement the calling party's requested routing objective, or to enter into a dialog (25), with the calling party to obtain additional information from which a sufficient confidence level can be attained to implement that routing objective.

Abstract translation: 在呼叫方的自然语音中表达的呼叫的呼叫路由目标上操作的自动呼叫路由系统和方法。 该系统包括语音识别功能，主叫方的自然语音呼叫路由目标提供输入（15），并且被训练以识别多个有意义的短语（10），每个这样的短语与特定的 呼叫路由目标。 当在主叫方的输入语音中识别出一个或多个这样有意义的短语时，解释功能（20）然后作用于该主叫方的路由目标，请求实现主叫方所请求的路由目的，或者进入对话（ 25），主叫方获得额外的信息，从而可以获得足够的置信水平来实现该路由目标。