公开(公告)号：US09684721B2

公开(公告)日：2017-06-20

申请号：US14629398

申请日：2015-02-23

申请人： WOLFRAM ALPHA LLC

发明人： Stephen Wolfram

IPC分类号： G06F9/44 ,  G06F7/00 ,  G06F17/00 ,  G10L15/00 ,  G06F17/30 ,  G06F17/21 ,  G06F3/01 ,  G10L15/22 ,  G06F19/00

CPC分类号： G06F17/30864 ,  G06F3/01 ,  G06F8/30 ,  G06F17/215 ,  G06F19/707 ,  G10L15/22

摘要： In a method for determining an answer to a query expressed in an imprecise syntax, a formula for computing an answer to the query is determined. An answer is calculated using the formula, and the answer is then presented to the user.

公开(公告)号：US09229927B2

公开(公告)日：2016-01-05

申请号：US14462282

申请日：2014-08-18

申请人： WOLFRAM ALPHA LLC

发明人： Stephen Wolfram ,  Peter Overmann

IPC分类号： G06F17/27 ,  G06F17/28 ,  G06F17/24 ,  G06F17/30

CPC分类号： G06F17/28 ,  G06F17/246 ,  G06F17/2705 ,  G06F17/2881 ,  G06F17/30654

摘要： In a method of creating a natural language (NL) macro, a first term/phrase and a second term/phrase in an imprecise syntax are obtained, and an association between the first and the second terms/phrases is created. The association is stored as an NL macro. In a method of using an NL macro in an NL query, it is determined that an original NL query includes an NL macro, and the NL macro is replaced with its corresponding NL value to form a revised NL query. The revised NL query is processed to generate one or more answers.

摘要翻译： 在创建自然语言（NL）宏的方法中，获得不准确语法中的第一项/短语和第二项/短语，并且创建第一和第二术语/短语之间的关联。 该关联存储为NL宏。 在NL查询中使用NL宏的方法中，确定原始NL查询包括NL宏，并且将NL宏替换为其对应的NL值以形成修订的NL查询。 处理修订的NL查询以生成一个或多个答案。

公开(公告)号：US08589869B2

公开(公告)日：2013-11-19

申请号：US11852044

申请日：2007-09-07

申请人： Stephen Wolfram

发明人： Stephen Wolfram

IPC分类号： G06F9/44 ,  G06F7/00 ,  G06F17/00

CPC分类号： G06F17/30864 ,  G06F3/01 ,  G06F8/30 ,  G06F17/215 ,  G06F19/707 ,  G10L15/22

摘要： In a method to help a user determine a formula, (e.g., a fact, rule, or principle expressed in scientific, mathematical, technical, etc. symbols), a user may input an indication of the formula in an imprecise syntax. The inputted indication may be in ASCII text, for example, and may include technical shorthand, technical abbreviations, pseudocode, etc. In response, one or more formulas corresponding to the user's input are determined. Optionally, other outputs related to the determined formula(s) may be generated. In one implementation, software programming code corresponding to the formula is generated. Then, the formula(s) and the output(s) are presented to the user.

摘要翻译： 在帮助用户确定公式（例如，以科学，数学，技术等等表示的事实，规则或原则）符号的方法中，用户可以以不精确的语法输入公式的指示。 例如，输入的指示可以是ASCII文本，并且可以包括技术简写，技术缩写，伪代码等。作为响应，确定与用户输入相对应的一个或多个公式。 可选地，可以生成与所确定的公式相关的其他输出。 在一个实现中，生成与该公式相对应的软件编程代码。 然后，公式和输出被呈现给用户。

公开(公告)号：US08484015B1

公开(公告)日：2013-07-09

申请号：US12780651

申请日：2010-05-14

申请人： Stephen Wolfram ,  Christopher Williamson ,  Oyvind Tafjord

发明人： Stephen Wolfram ,  Christopher Williamson ,  Oyvind Tafjord

IPC分类号： G06F17/27 ,  G06F17/21 ,  G06F17/20 ,  G06F17/30

CPC分类号： G06F17/30693 ,  G06F17/30654

摘要： An answer engine determines an entity related to a query from a user in a system designed for computation, search, or other activities involving the processing of queries. The system determines whether an entity page for the entity is stored in an answers database and, if so, retrieves and displays the stored entity page. If there is no stored entity page for the entity, the answer engine generates and displays an answer to the query and may optionally store the answer as an entity page. Additionally, the answer engine may pre-generate and store entity pages according to algorithmic variation of received queries and/or according to information received from external sources.

摘要翻译： 答案引擎在用于计算，搜索或涉及处理查询的其他活动的系统中确定与来自用户的查询相关的实体。 系统确定实体的实体页面是否存储在答案数据库中，如果是，则检索并显示存储的实体页面。 如果实体没有存储的实体页面，则答案引擎生成并显示对查询的答案，并且可以可选地将答案存储为实体页面。 此外，应答引擎可以根据接收到的查询的算法变化和/或根据从外部源接收的信息来预生成和存储实体页面。

公开(公告)号：US10606563B2

公开(公告)日：2020-03-31

申请号：US16370336

申请日：2019-03-29

申请人： Wolfram Alpha LLC

发明人： Stephen Wolfram ,  Theodore W. Gray

IPC分类号： G06F17/28 ,  G06F8/30

摘要： A method facilitates development of instructions in a precise syntax, such as built-in functions of a computational system such as a spreadsheet application, using natural language (NL) input. A user may enter NL input in a workspace. An NL processing system may process the NL input to generate instruction(s) in a precise syntax that corresponds to the NL input. The instruction(s) in the precise syntax then may be included in the workspace.

公开(公告)号：US10191968B2

公开(公告)日：2019-01-29

申请号：US15168237

申请日：2016-05-30

申请人： Wolfram Alpha LLC

发明人： Stephen Wolfram ,  Taliesin Sebastian Beynon

IPC分类号： G06F17/30

摘要： A compatibility of a computational analysis and a data set is automatically determined by comparing data set attribute data with attribute data of the computational analysis. Other computational analyses may also be evaluated for compatibility with the data set. Compatible analyses may be performed on the data set, and selected views of the results may be presented. Selection of the analyses to be performed, the views, and/or the contents and format of the views may be determined based result data attributes and computational analysis attribute data as well as other considerations, such as resources required and multiplicity. As computational analysis attributes are based on a set of rules or statements determined from heuristics of respective computational analyses, evaluation of the compatibility between various analyses and the data set is accordingly determined based on the heuristic-based rules or statements. Computational analyses may include visualizations and heavyweight computational analyses.

公开(公告)号：US10176268B2

公开(公告)日：2019-01-08

申请号：US15676636

申请日：2017-08-14

申请人： Wolfram Alpha LLC

发明人： Stephen Wolfram ,  Wiktor Macura ,  Michael Pilat

IPC分类号： G06F7/00 ,  G06F17/30

摘要： Content data items in a first electronic file that correspond to entities in a database comprising categorized entities are identified. Modified content data items of a second electronic file are generated, the modified content data items indicating how the content data items are to be interpreted by a natural language query answering system. Information in the second electronic file indicating how the content data items are to be interpreted by the natural language query answering system are modified in response to user input. The second electronic file is used by the natural language query answering system to facilitate analysis of a natural language query regarding content in the first electronic file. Results of the analysis using the natural language query answering system are output.

公开(公告)号：US09734252B2

公开(公告)日：2017-08-15

申请号：US13608817

申请日：2012-09-10

申请人： Stephen Wolfram ,  Wiktor Macura ,  Michael Pilat

发明人： Stephen Wolfram ,  Wiktor Macura ,  Michael Pilat

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30873 ,  G06F17/30684

摘要： A natural language query answering system includes an external data pre-processor configured to i) analyze a first data set, the first data set received via a communication network, to identify data in the first data set that corresponds to entities in a database comprising categorized entities, and ii) generate a second data set corresponding to the first data set and based on the analysis of the first data set, wherein the second data set includes information indicating how data in the second data set is to be interpreted by the natural language query answering system. The natural language query answering system is configured to retrieve data and/or process data from the second data set in response to natural language queries.

公开(公告)号：US09069814B2

公开(公告)日：2015-06-30

申请号：US13560507

申请日：2012-07-27

申请人： Stephen Wolfram ,  Theodore W. Gray

发明人： Stephen Wolfram ,  Theodore W. Gray

IPC分类号： G06F17/30

CPC分类号： G06F17/30401 ,  G06F17/30389 ,  G06F17/30404 ,  G06F17/30654 ,  G06F17/30657 ,  G06F17/30964 ,  G06F17/30976

摘要： A user interface application is created to prompt a user for information and to generate a query to be submitted to a natural language (NL) query answering system. A first user is prompted to submit an NL query, and the NL query is received. The user interface application is generated using the NL query and so that the user interface application is configured to prompt the first user or a second user to provide information, receive the information, generate a computer-generated query based on the NL query and the received information, provide the computer-generated query to the NL query answering system, receive answer information from the NL query answering system in response to the computer-generated query, and cause at least some of the answer information to be displayed on a display device.

摘要翻译： 创建用户界面应用程序以提示用户信息并生成要提交给自然语言（NL）查询应答系统的查询。 系统提示第一个用户提交NL查询，并收到NL查询。 使用NL查询生成用户界面应用程序，并且使得用户界面应用程序被配置为提示第一用户或第二用户提供信息，接收信息，基于NL查询和接收的生成计算机生成的查询 信息，向NL查询应答系统提供计算机生成的查询，响应于计算机生成的查询从NL查询应答系统接收应答信息，并使至少一些应答信息显示在显示设备上。

公开(公告)号：US20140229497A1

公开(公告)日：2014-08-14

申请号：US13763568

申请日：2013-02-08

申请人： WOLFRAM ALPHA LLC

发明人： Stephen Wolfram ,  Taliesin Sebastian Beynon

IPC分类号： G06F17/30

CPC分类号： G06F17/30598 ,  G06F17/30569 ,  G06F17/30572

摘要： A compatibility of a computational analysis and a data set is automatically determined by comparing data set attribute data with attribute data of the computational analysis. Other computational analyses may also be evaluated for compatibility with the data set. Compatible analyses may be performed on the data set, and selected views of the results may be presented. Selection of the analyses to be performed, the views, and/or the contents and format of the views may be determined based result data attributes and computational analysis attribute data as well as other considerations, such as resources required and multiplicity. As computational analysis attributes are based on a set of rules or statements determined from heuristics of respective computational analyses, evaluation of the compatibility between various analyses and the data set is accordingly determined based on the heuristic-based rules or statements. Computational analyses may include visualizations and heavyweight computational analyses.

摘要翻译： 通过将数据集属性数据与计算分析的属性数据进行比较，自动确定计算分析与数据集的兼容性。 还可以评估其他计算分析与数据集的兼容性。 可以对数据集执行兼容分析，并且可以呈现所选择的结果视图。 可以基于结果数据属性和计算分析属性数据以及诸如所需资源和多样性的其他考虑来确定要执行的分析的选择，视图和/或内容和格式。 由于计算分析属性基于从各自的计算分析的启发式确定的一组规则或语句，因此根据基于启发式的规则或语句来确定各种分析与数据集之间的兼容性的评估。 计算分析可能包括可视化和重量级计算分析。