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. 发明申请

WO2017218370A1 SYSTEMS AND METHODS FOR BUILDING STATE SPECIFIC MULTI-TURN CONTEXTUAL LANGUAGE UNDERSTANDING SYSTEMS 审中-公开
标题翻译：用于构建状态特定的多转向语境语义理解系统的系统和方法
公开(公告)号：WO2017218370A1
公开(公告)日：2017-12-21
申请号：PCT/US2017/036926
申请日：2017-06-12
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： SARIKAYA, Ruhi , KIM, Young-Bum , ROCHETTE, Alexandre
IPC分类号： G06F17/27
CPC分类号： G06F17/279 , G06F17/2775 , G06F17/28 , G06F17/2881 , G10L15/063 , G10L15/1815 , G10L15/1822 , G10L15/22
摘要： Systems and methods for building a dialog-state specific multi-turn contextual language understanding system are provided. More specifically, the systems and methods infer or are configured to infer a state-specific schema and/or state-specific rules from a formed single-shot language understanding model and/or a single-shot rule set. As such, the systems and methods only require the information necessary to form a single-shot language understanding model and/or a single-shot rule set from a builder to form or build the dialog-state specific multi-turn contextual language understanding system. Accordingly, the systems and methods for building a dialog-state specific multi-turn contextual language understanding system reduce the expertise, time, and resources necessary to build a dialog-state specific multi-turn contextual language understanding system for an application when compared to systems and methods that require further input from the builder than necessary to build a single-shot language understanding system.
摘要翻译：
提供了用于构建对话状态特定的多回转语境语言理解系统的系统和方法。更具体地说，所述系统和方法推断或被配置为从形成的单发语言理解模型和/或单发规则集推断出状态特定模式和/或状态特定规则。因此，系统和方法仅需要形成构建器的单镜头语言理解模型和/或单镜头规则集所需的信息，以形成或构建对话状态特定的多轮上下文语言理解系统。因此，与系统相比，用于构建对话状态特定多回转语境语言理解系统的系统和方法减少了为应用程序构建对话状态特定多回转语境语言理解系统所需的专业知识，时间和资源以及需要构建者进一步输入才能构建单镜头语言理解系统的方法。

2. 发明申请

WO2017127316A1 CONFIGURABLE GENERIC LANGUAGE UNDERSTANDING MODELS 审中-公开
标题翻译：可配置的通用语言理解模型
公开(公告)号：WO2017127316A1
公开(公告)日：2017-07-27
申请号：PCT/US2017/013584
申请日：2017-01-14
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： SARIKAYA, Ruhi , CELIKYILMAZ, Asli , KIM, Young-Bum , FEIZOLLAHI, Zhaleh , RAMESH, Nikhil , SUZUKI, Hisami , ROCHETTE, Alexandre
IPC分类号： G10L15/22 , G06F17/27
CPC分类号： G06F17/289 , G06F17/2785 , G06F17/30294 , G06N99/005 , G10L15/22
摘要： Examples of the present disclosure describe systems and methods of configuring generic language understanding models. In aspects, one or more previously configured schemas for various applications may be identified and collected. A generic schema may be generated using the collected schemas. The collected schemas may be programmatically mapped to the generic schema. The generic schema may be used to train on ore more models. An interface may be provided to allow browsing the models. The interface may include a configuration mechanism that provides for selecting on or more of the models. The selected models may be bundled programmatically, such that the information and instructions needed to implement the models are configured programmatically. The bundled models may then be provided to a requestor.
摘要翻译：本公开的示例描述了配置通用语言理解模型的系统和方法。在各方面中，可以识别并收集用于各种应用的一个或多个先前配置的模式。通用模式可以使用收集到的模式生成。收集到的模式可以以编程方式映射到通用模式。通用模式可以用来训练更多的模型。可以提供界面以允许浏览模型。界面可以包括提供用于选择一个或多个模型的配置机制。所选模型可以以编程方式捆绑在一起，以便实现模型所需的信息和指令以编程方式进行配置。捆绑的模型然后可以被提供给请求者。

3. 发明申请

WO2017040436A1 DISTRIBUTED SERVER SYSTEM FOR LANGUAGE UNDERSTANDING 审中-公开
标题翻译：用于语言理解的分布式服务器系统
公开(公告)号：WO2017040436A1
公开(公告)日：2017-03-09
申请号：PCT/US2016/049337
申请日：2016-08-30
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： LIU, Xiaohu , SARIKAYA, Ruhi
IPC分类号： G06F17/27
CPC分类号： G06F17/28 , G06F17/274 , G06F17/278 , G06F17/2785 , G10L15/22 , G10L15/30
摘要： Systems and methods for training and using a natural language understanding system are provided. More specifically, the systems and methods train a natural language understanding system utilizing a distributed network of feature extractors on features servers. Further, the systems and methods for using the natural language understanding system utilize a distributed network of features extractor on features servers. Accordingly, the systems and methods provide for a more accurate natural langue understanding system, a more reliable natural langue understanding system, and a more efficient natural langue understanding system. Further, the systems and methods provide for natural language understanding systems with better development (including update ability), productivity, and scalability.
摘要翻译：提供了用于培训和使用自然语言理解系统的系统和方法。更具体地，系统和方法利用特征服务器上的特征提取器的分布式网络训练自然语言理解系统。此外，使用自然语言理解系统的系统和方法利用特征提取器的分布式网络在特征服务器上。因此，系统和方法提供了更为准确的天然ue ue理解系统，更可靠的天然ue ue理解系统，以及更有效的天然ue ue理解系统。此外，系统和方法为自然语言理解系统提供了更好的发展（包括更新能力），生产力和可扩展性。

4. 发明申请

WO2016179126A1 BUILDING MULTIMODAL COLLABORATIVE DIALOGS WITH TASK FRAMES 审中-公开
标题翻译：建立与任务框架的多模式协同对话
公开(公告)号：WO2016179126A1
公开(公告)日：2016-11-10
申请号：PCT/US2016/030486
申请日：2016-05-03
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： BIKKULA, Ravi , PANIC, Danko , CROOK, Paul , KHAN, Omar Zia , SARIKAYA, Ruhi , SUZUKI, Hisami
IPC分类号： H04L29/08 , G06F3/038 , G06F17/20
CPC分类号： G06F9/5011 , G06F3/038 , G06F9/4881
摘要： Methods and systems are provided for collaborative completion of tasks using task frames. Upon receiving a request to perform a task, a system utilizes task frames in completing the requested task. A task frame is a data structure that contains the parameters and status signals that represent a particular task and captures the combined system's understanding of a current state of the task. Input is received at a client device and sent to a server, where the input is processed. Based on the processed input, a task frame is retrieved and filled. The filled task frame is sent to the client device, where the client device performs actions based on the task frame and updates the task frame parameters and the state of the task. The updated task frame is returned to the server. The shared task frame provides improvements to the overall task completion process.
摘要翻译：提供了使用任务框架协同完成任务的方法和系统。在接收到执行任务的请求时，系统利用任务帧来完成所请求的任务。任务框架是包含表示特定任务的参数和状态信号的数据结构，并且捕获组合系统对当前任务状态的理解。在客户端设备接收到输入，并发送到服务器，处理输入。基于处理的输入，检索并填充任务帧。填充的任务帧被发送到客户端设备，其中客户端设备基于任务帧执行动作，并更新任务帧参数和任务的状态。更新的任务帧返回到服务器。共享任务框架提供了整个任务完成过程的改进。

5. 发明申请

WO2016176234A1 CONTEXT CARRYOVER IN LANGUAGE UNDERSTANDING SYSTEMS OR METHODS 审中-公开
标题翻译：语言学习理解系统或方法
公开(公告)号：WO2016176234A1
公开(公告)日：2016-11-03
申请号：PCT/US2016/029410
申请日：2016-04-27
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： BOIES, Daniel , SARIKAYA, Ruhi , FEIZOLLAHI, Zhaleh , XU, Puyang
IPC分类号： G06Q10/00 , G06F17/20
CPC分类号： G06Q10/00 , G06F17/2785
摘要： Systems and methods for determining a user intent or goal for contextual language understanding by utilizing information from one or more previous user natural language inputs and one or more previous system generated responses to the user natural language inputs are provided. More specifically, the systems and methods utilize a common schema for determining features from the responses and natural language inputs and provide carryover tracking between responses and the natural language inputs. Accordingly, the systems and methods for contextual language understanding provide for a more accurate, a more reliable, and a more efficient context carryover and goal tracking system when compared to systems and methods that do not utilized the responses in determining the user goal/intent.
摘要翻译：提供了通过利用来自一个或多个先前用户自然语言输入的信息和一个或多个先前系统生成的对用户自然语言输入的响应来确定用于语境语言理解的用户意图或目标的系统和方法。更具体地说，系统和方法利用通用模式来从响应和自然语言输入中确定特征，并提供响应与自然语言输入之间的进位跟踪。因此，与在确定用户目标/意图时没有使用响应的系统和方法相比，用于语境语言理解的系统和方法提供更准确，更可靠和更有效的上下文携带和目标跟踪系统。

6. 发明申请

WO2018045202A1 AUTOMATING NATURAL LANGUAGE TASK/DIALOG AUTHORING BY LEVERAGING EXISTING CONTENT 审中-公开
标题翻译：通过利用现有内容来自动完成自然语言任务/对话
公开(公告)号：WO2018045202A1
公开(公告)日：2018-03-08
申请号：PCT/US2017/049675
申请日：2017-08-31
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： SARIKAYA, Ruhi , RADOSTEV, Vasiliy
IPC分类号： G06F17/27 , G06Q10/00 , G06F17/30
CPC分类号： G10L15/22 , G06F16/00 , G06F16/90332 , G06F17/2247 , G06F17/243 , G06F17/2705 , G06F17/2785 , G06F17/279 , G06Q10/02 , G06Q10/30 , G10L15/1822 , G10L15/183 , Y02W90/20
摘要： Systems and methods for augmenting existing CU system to be used with content, such as a website. The content may be parsed to determine on or more actions that may be performed by a user who uses the content. These actions may then be compared to tasks of CU systems to identify potential matches. When a match is found, the CU system may be updated to include information.
摘要翻译：用于增强现有CU系统以与内容（例如网站）一起使用的系统和方法。内容可以被解析以确定可以由使用该内容的用户执行的一个或多个动作。然后可以将这些行动与CU系统的任务进行比较以识别潜在的匹配。当找到匹配项时，CU系统可能会更新以包含信息。

7. 发明申请

WO2018039049A1 MULTI-TURN CROSS-DOMAIN NATURAL LANGUAGE UNDERSTANDING SYSTEMS, BUILDING PLATFORMS, AND METHODS 审中-公开
标题翻译：多转向跨领域自然语言理解系统，构建平台和方法
公开(公告)号：WO2018039049A1
公开(公告)日：2018-03-01
申请号：PCT/US2017/047463
申请日：2017-08-18
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： SARIKAYA, Ruhi , KIM, Young-Bum , ROCHETTE, Alexandre
IPC分类号： G10L15/06 , G10L15/22
摘要： Multi-turn cross-domain natural language understanding (NLU) systems and platforms for building the multi-turn cross-domain NLU system are provided. Further, methods for using and building the multi-turn cross-domain NLU system are provided. More specifically, the multi-turn cross-domain NLU system supports multi-turn bot/agent/application scenarios for new domains without having to select a task definition and/or define a new schema during the building of the NLU system. Accordingly, the platform for building the multi-turn cross-domain NLU system that does not require the builder to select a task and/or build a schema for a selected task provides an easy to use, cost effective, and efficient service for building a NLU system. Further, the multi-turn cross-domain NLU system provides a more versatile NLU system than previously utilized NLU systems that were trained for and limited to a selected task and/or domain.
摘要翻译：提供了多圈跨领域自然语言理解（NLU）系统和平台，用于构建多圈跨域NLU系统。此外，提供了用于使用和构建多圈跨域NLU系统的方法。更具体地说，多转跨域NLU系统支持新域的多回合机器人/代理/应用场景，而无需在NLU系统的构建期间选择任务定义和/或定义新模式。因此，用于构建不需要构建器为选择的任务选择任务和/或构建模式的多圈跨域NLU系统的平台提供了易于使用，成本有效且高效的服务，用于构建 NLU系统。此外，多圈跨域NLU系统提供了比先前使用的NLU系统更多功能的NLU系统，NLU系统已经被训练并限于所选任务和/或域。

8. 发明申请

WO2017151400A1 INTERPRETING AND RESOLVING CONDITIONAL NATURAL LANGUAGE QUERIES 审中-公开
标题翻译：解读和解决有条件的自然语言问题
公开(公告)号：WO2017151400A1
公开(公告)日：2017-09-08
申请号：PCT/US2017/019225
申请日：2017-02-24
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： SARIKAYA, Ruhi
IPC分类号： G06F17/27 , G10L15/18
CPC分类号： G06F16/24522 , G06F16/24565 , G06F17/279 , G06N5/02 , G06Q10/1093
摘要： Techniques to interpret and resolve natural language queries that contain conditions are presented. The domains, intents, and slots for the condition portion and the action portion may be identified. The identified domain, intents, and slots may be delivered to another device or application for further processing.
摘要翻译：介绍解释和解决包含条件的自然语言查询的技术。可以识别条件部分和动作部分的域，意图和时隙。所标识的域，意图和插槽可以被传送到另一设备或应用程序以供进一步处理。

9. 发明申请

WO2016133696A1 TRAINING SYSTEMS AND METHODS FOR SEQUENCE TAGGERS 审中-公开
标题翻译：训练系统和序列标签的方法
公开(公告)号：WO2016133696A1
公开(公告)日：2016-08-25
申请号：PCT/US2016/016245
申请日：2016-02-03
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： JEONG, Minwoo , KIM, Young-Bum , SARIKAYA, Ruhi
IPC分类号： G06N7/00 , G06F17/27
CPC分类号： G06N99/005 , G06F17/2705 , G06F17/2785 , G06F17/30864 , G06N7/005
摘要： Systems and methods for or training a sequence tagger, such as conditional random field model. More specifically, the systems and methods train a sequence tagger utilizing partially labeled data from crowd-sourced data for a specific application and partially labeled data from search logs. Further, the systems and methods disclosed herein train a sequence tagger utilizing only partially labeled by utilizing a constrained lattice where each input value within the constrained lattice can have multiple candidate tags with confidence scores. Accordingly, the systems and methods provide for a more accurate sequence tagging system, a more reliable sequence tagging system, and a more efficient sequence tagging system in comparison to sequence taggers trained utilizing at least some fully-labeled training data.
摘要翻译：用于或训练序列标签的系统和方法，如条件随机场模型。更具体地说，系统和方法使用来自针对特定应用的来自人群的数据的部分标记的数据和来自搜索日志的部分标记的数据来训练序列标签器。此外，本文公开的系统和方法通过利用受约束的格点仅利用部分标记的序列标签器来训练序列标签器，其中约束格点内的每个输入值可以具有具有置信度分数的多个候选标签。因此，与使用至少一些完全标记的训练数据训练的序列标签相比，系统和方法提供了更准确的序列标签系统，更可靠的序列标签系统和更有效的序列标签系统。

10. 发明申请

WO2016109307A2 DISCRIMINATING AMBIGUOUS EXPRESSIONS TO ENHANCE USER EXPERIENCE 审中-公开
标题翻译：辨别不良表现以增强用户体验
公开(公告)号：WO2016109307A2
公开(公告)日：2016-07-07
申请号：PCT/US2015/067238
申请日：2015-12-22
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： ROBICHAUD, Jean-Philippe , SARIKAYA, Ruhi
IPC分类号： G06F17/30 , G06F17/27
CPC分类号： G06F17/278 , G06F17/279 , G06F17/30646 , G06F17/30654 , G06F17/30657 , G06F17/30663 , G06F17/30666 , G06F17/30684 , G06F17/30693 , G10L15/22
摘要： Methods and systems are provided for discriminating ambiguous expressions to enhance user experience. For example, a natural language expression may be received by a speech recognition component. The natural language expression may include at least one of words, terms, and phrases of text. A dialog hypothesis set from the natural language expression may be created by using contextual information. In some cases, the dialog hypothesis set has at least two dialog hypotheses. A plurality of dialog responses may be generated for the dialog hypothesis set. The dialog hypothesis set may be ranked based on an analysis of the plurality of the dialog responses. An action may be performed based on ranking the dialog hypothesis set.
摘要翻译：提供方法和系统用于区分不明确的表达以增强用户体验。例如，语音识别组件可以接收自然语言表达。自然语言表达可以包括文本的单词，术语和短语中的至少一个。可以通过使用上下文信息来创建从自然语言表达式设置的对话假设。在某些情况下，对话假设集至少有两个对话假设。可以为对话假设组生成多个对话响应。对话假设集合可以基于对多个对话响应的分析进行排名。可以基于对话假设集合的排序来执行动作。

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