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

US20220284171A1 HIERARCHICAL STRUCTURE LEARNING WITH CONTEXT ATTENTION FROM MULTI-TURN NATURAL LANGUAGE CONVERSATIONS 有权
公开(公告)号：US20220284171A1
公开(公告)日：2022-09-08
申请号：US17693414
申请日：2022-03-14
申请人： SRIVATSAN LAXMAN , SUPRIYA RAO , SRIKHAR PADMANABHAN
发明人： SRIVATSAN LAXMAN , SUPRIYA RAO , SRIKHAR PADMANABHAN
IPC分类号： G06F40/117 , G06F40/242 , G06F40/268 , G06F40/205 , G06F40/35 , G06F40/284 , G06N3/04
摘要： A computerized method for implementing a neural architecture for hierarchical sequence labelling comprising: providing a neural architecture comprising a set of labelling layers, wherein the neural architecture uses a multi-pass approach on the set of labelling layers, receiving an input sentence; parsing the input sentence; embedding the input sentence into a corresponding character vector and a corresponding word vector to generate a feature vector; passing the feature vector through the neural architecture; and performing a multi-layer labelling procedure on the feature vector with the neural architecture comprising: augmenting a set of corresponding bits of the feature vector, wherein the feature vector is passed through the set of labelling layers of neural architecture.

2. 发明申请

US20140058793A1 FORECASTING A NUMBER OF IMPRESSIONS OF A PROSPECTIVE ADVERTISEMENT LISTING 审中-公开
标题翻译：预测前瞻性广告列表的数量
公开(公告)号：US20140058793A1
公开(公告)日：2014-02-27
申请号：US13590192
申请日：2012-08-21
申请人： Abhirup Nath , Shibnath Mukherjee , Prateek Jain , Navin Goyal , Srivatsan Laxman
发明人： Abhirup Nath , Shibnath Mukherjee , Prateek Jain , Navin Goyal , Srivatsan Laxman
IPC分类号： G06Q30/02
CPC分类号： G06Q30/02 , G06Q30/08
摘要： Technologies pertaining to advertisement impression forecasting are described herein. An advertiser sets forth a proposed bid value for a prospective advertisement listing with respect to a keyword for a defined range of time. A number of auctions for the keyword in which the prospective advertisement listing will participate is estimated. A generative model that models auctions for the keyword is sampled to simulate auctions for the keyword, wherein the number of simulated auctions is equivalent to the number of auctions for the keyword in which the prospective advertisement listing is estimated to participate. For each simulated auction, a determination is made regarding whether the prospective advertisement listing wins the auction based upon the proposed bid value set forth by the advertiser. A number of simulated auctions won by the prospective advertiser is output as a forecasted number of impressions for the advertisement over the defined range of time.
摘要翻译：本文描述了与广告印象预测有关的技术。广告客户针对所定义的时间范围内的关键字提出针对预期广告列表的提议出价值。估计有望刊登广告的关键字的一些拍卖。为关键字建模拍卖的生成模型被抽样以模拟关键字的拍卖，其中模拟拍卖的数量等于预期广告列表估计参与的关键字的拍卖数量。对于每个模拟拍卖，确定根据广告商提出的提议的出价值，潜在广告列表是否赢得拍卖。预期广告客户获得的许多模拟拍卖会作为广告在指定时间范围内的预测曝光次数输出。

3. 发明申请

US20060195444A1 System and method for mining of temporal data 有权
标题翻译：时间数据挖掘的系统和方法
公开(公告)号：US20060195444A1
公开(公告)日：2006-08-31
申请号：US11068498
申请日：2005-02-28
申请人： P. S. Sastry , Srivatsan Laxman , K. P. Unnikrishnan
发明人： P. S. Sastry , Srivatsan Laxman , K. P. Unnikrishnan
IPC分类号： G06F17/30
CPC分类号： G06F17/30539 , G06F17/30548
摘要： A method, system, and apparatus for temporal data mining is disclosed. The method includes receiving as input a temporal data series comprising events with start times and end times, a set of allowed dwelling times, and a threshold frequency. The method also includes finding all frequent principal episodes of a particular length in the temporal data series having dwelling times within the allowed dwelling times. The method includes steps executed in successive passes through the temporal data series. The steps include incrementing the particular length to generate an increased length, combining frequent principal episodes to create combined episodes of the increased length, creating a set of candidate episodes from the combined episodes by removing combined episodes which have non-frequent sub-episodes, identifying one or more occurrences of a candidate episode in the temporal data series, incrementing a count for each identified occurrence, determining frequent principal episodes of the increased length, and setting the particular length to the increased length.
摘要翻译：公开了一种用于时间数据挖掘的方法，系统和装置。该方法包括作为输入接收包括具有开始时间和结束时间的事件的时间数据序列，一组允许的住宅时间和阈值频率。该方法还包括在允许住宅时间内具有住宅时间的时间数据序列中找到特定长度的所有频繁主发生。该方法包括在连续通过时间数据序列中执行的步骤。这些步骤包括增加特定长度以产生增加的长度，组合频繁的主要发作以产生增加的长度的组合的剧集，通过去除具有非频繁子剧集的识别的组合剧集从组合的剧集中创建一组候选剧集在时间数据序列中出现一个或多个候选事件，增加每个识别的事件的计数，确定增加长度的频繁主发生，并将特定长度设置为增加的长度。

4. 发明申请

US20060195423A1 System and method for temporal data mining 有权
标题翻译：时间数据挖掘的系统和方法
公开(公告)号：US20060195423A1
公开(公告)日：2006-08-31
申请号：US11068505
申请日：2005-02-28
申请人： P.S. Sastry , Srivatsan Laxman , K. P. Unnikrishnan
发明人： P.S. Sastry , Srivatsan Laxman , K. P. Unnikrishnan
IPC分类号： G06F17/30
CPC分类号： G06F17/30551 , G06F17/30539
摘要： A method, system, and apparatus for temporal data mining is disclosed. The method includes receiving as input a temporal data series comprising time-stamped events, and a threshold frequency. An aspect of this technology is the defining of appropriate frequency counts for non-overlapping and non-interleaved episodes. Two frequency measures and embodiments for obtaining frequent episodes are described. The method includes finding all frequent episodes of a particular length in the temporal data series. The method includes steps executed in successive passes through the temporal data series. The steps include incrementing the particular length to generate an increased length, combining frequent episodes to create combined episodes of the increased length, creating a set of candidate episodes from the combined episodes by removing combined episodes which have non-frequent sub-episodes, identifying one or more occurrences of a candidate episode in the temporal data series, incrementing a count for each identified occurrence, determining frequent episodes of the increased length, and setting the particular length to the increased length.
摘要翻译：公开了一种用于时间数据挖掘的方法，系统和装置。该方法包括作为输入接收包括时间戳事件和阈值频率的时间数据序列。该技术的一个方面是定义非重叠和非交错事件的适当频率计数。描述了用于获得频繁发作的两个频率测量和实施例。该方法包括在时间数据序列中查找特定长度的所有频发。该方法包括在连续通过时间数据序列中执行的步骤。这些步骤包括增加特定长度以产生增加的长度，组合频繁剧集以产生增加长度的组合剧集，通过去除具有非频繁子剧集的组合剧集，从组合剧集中创建一组候选剧集，识别一个或更多次出现在时间数据序列中的候选事件，增加每个识别出现的计数，确定增加的长度的频繁发作，以及将特定长度设置为增加的长度。

5. 发明授权

US08126891B2 Future data event prediction using a generative model 有权
标题翻译：使用生成模型的未来数据事件预测
公开(公告)号：US08126891B2
公开(公告)日：2012-02-28
申请号：US12255556
申请日：2008-10-21
申请人： Srivatsan Laxman , Vikram Tankasali , Ryen White
发明人： Srivatsan Laxman , Vikram Tankasali , Ryen White
IPC分类号： G06F15/18 , G06F17/30
CPC分类号： G06N99/005
摘要： The prediction of future data events using a generative model is disclosed. One disclosed embodiment comprises a method of predicting a search engine switch, by first tracking a sequence of events in a user search. Next, a search engine switch based upon the sequence of events tracked is predicted. Then, in response to predicting a search engine switch and prior to the user requesting a search engine switch, an action is taken toward changing a user experience.
摘要翻译：公开了使用生成模型对未来数据事件的预测。一个公开的实施例包括通过首先跟踪用户搜索中的事件序列来预测搜索引擎切换的方法。接下来，预测基于跟踪的事件的顺序的搜索引擎切换。然后，响应于预测搜索引擎切换，并且在用户请求搜索引擎切换之前，采取行动来改变用户体验。

6. 发明申请

US20100299305A1 PROGRAMMING ELEMENT MODIFICATION RECOMMENDATION 审中-公开
标题翻译：编程元素修改建议
公开(公告)号：US20100299305A1
公开(公告)日：2010-11-25
申请号：US12471006
申请日：2009-05-22
申请人： Srivatsan Laxman , Prasad G. Naldurg , Nachiappan Nagappan , Jacek A. Czerwonka
发明人： Srivatsan Laxman , Prasad G. Naldurg , Nachiappan Nagappan , Jacek A. Czerwonka
IPC分类号： G06F9/44 , G06F17/30
CPC分类号： G06F8/71
摘要： Techniques described herein help determine dependencies and associations between CPEs in a computing system. These techniques track previous check-ins over a period of time in order to learn the dependencies and associations between CPEs. The previous check-ins are performed by a plurality of different computer programmers. In some embodiments, in response to receiving an indication that a CPE has either already been modified or is about to be modified by a computer programmer, the techniques provide the computer programmer with a recommendation indicating CPEs that are associated with the CPE being modified. This recommendation is based on the dependencies and associations determined from the previous check-ins performed by the plurality of different computer programmers.
摘要翻译：本文描述的技术有助于确定计算系统中CPE之间的依赖关系和关联。这些技术在一段时间内跟踪以前的签入，以便了解CPE之间的依赖关系和关联。先前的签入由多个不同的计算机程序员执行。在一些实施例中，响应于接收到CPE已经被修改或即将被计算机程序员修改的指示，该技术向计算机程序员提供指示与被修改的CPE相关联的CPE的建议。该建议基于由多个不同的计算机程序员执行的先前签入确定的依赖关系和关联。

7. 发明申请

US20100100517A1 FUTURE DATA EVENT PREDICTION USING A GENERATIVE MODEL 有权
标题翻译：使用生成模型的未来数据事件预测
公开(公告)号：US20100100517A1
公开(公告)日：2010-04-22
申请号：US12255556
申请日：2008-10-21
申请人： Srivatsan Laxman , Vikram Tankasali , Ryen White
发明人： Srivatsan Laxman , Vikram Tankasali , Ryen White
IPC分类号： G06N5/02
CPC分类号： G06N99/005
摘要： The prediction of future data events using a generative model is disclosed. One disclosed embodiment comprises a method of predicting a search engine switch, by first tracking a sequence of events in a user search. Next, a search engine switch based upon the sequence of events tracked is predicted. Then, in response to predicting a search engine switch and prior to the user requesting a search engine switch, an action is taken toward changing a user experience.
摘要翻译：公开了使用生成模型对未来数据事件的预测。一个公开的实施例包括通过首先跟踪用户搜索中的事件序列来预测搜索引擎切换的方法。接下来，预测基于跟踪的事件的顺序的搜索引擎切换。然后，响应于预测搜索引擎切换，并且在用户请求搜索引擎切换之前，采取行动来改变用户体验。

8. 发明申请

US20080177680A1 RESILIENT CLASSIFICATION OF DATA 有权
标题翻译：数据的灵活分类
公开(公告)号：US20080177680A1
公开(公告)日：2008-07-24
申请号：US11625249
申请日：2007-01-19
申请人： Srivatsan Laxman , Ramarathnam Venkatesan
发明人： Srivatsan Laxman , Ramarathnam Venkatesan
IPC分类号： G06F15/18
CPC分类号： G06N99/005 , G06K9/6256 , G06K9/6269 , G06K9/6292
摘要： A classification system is described for resilient classification of data. In various embodiments, the classification system divides a full set of the training data into a positive subset and a negative subset. The positive subset contains all training data with a positive classification value and the negative subset contains all training data with a negative classification value. The classification system constructs several subsets of the training data wherein each subset contains data randomly selected from both the positive subset and the negative subset. The classification system then creates at least two classifiers based on each of the randomly created subsets of the training data.
摘要翻译：描述了对数据进行弹性分类的分类系统。在各种实施例中，分类系统将整套训练数据划分为正子集和负子集。正子集包含具有正分类值的所有训练数据，负子集包含具有负分类值的所有训练数据。分类系统构建训练数据的几个子集，其中每个子集包含从正子集和负子集两者随机选择的数据。分类系统然后基于训练数据的随机创建的子集中的每一个创建至少两个分类器。

9. 发明申请

US20200134018A1 MIXED-INITIATIVE DIALOG AUTOMATION WITH GOAL ORIENTATION 审中-公开
公开(公告)号：US20200134018A1
公开(公告)日：2020-04-30
申请号：US16170034
申请日：2018-10-25
申请人： SRIVATSAN LAXMAN , DEVANG SAVITA RAM MOHAN , SUPRIYA RAO
发明人： SRIVATSAN LAXMAN , DEVANG SAVITA RAM MOHAN , SUPRIYA RAO
IPC分类号： G06F17/27 , G06N3/08
摘要： In one aspect, method useful for goal-oriented dialog automation comprising incudes the step of receiving an input message. The method includes the step of implementing an entity tagging operation on the input message. The method includes the step of tagging the message context of the input message to generate a tagged message context. The method includes the step of implementing semantic frame extraction from the tagged message context. The method includes the step of implementing an entity interpretation on the extracted frame. The method includes the step of accessing a database to determine a business schedule and a client profile. The business schedule and the client profile are related to the input message. The method includes the step of implementing a retrieval engine. The retrieval engine obtains one or more response templates. The method includes the step of generating a ranked list of candidate templates from the output of the retrieval engine. Based on the output of the entity interpretation, the business schedule and the client profile, and the ranked list of candidate templates, implementing a candidate eliminator. Based on the output of the candidate eliminator, providing a set of recommended responses. Each recommend response is associated with a confidence score.

10. 发明授权

US10853579B2 Mixed-initiative dialog automation with goal orientation 有权
公开(公告)号：US10853579B2
公开(公告)日：2020-12-01
申请号：US16170034
申请日：2018-10-25
申请人： Srivatsan Laxman , Devang Savita Ram Mohan , Supriya Rao
发明人： Srivatsan Laxman , Devang Savita Ram Mohan , Supriya Rao
IPC分类号： G06F40/30 , G06N3/08
摘要： In one aspect, method useful for goal-oriented dialog automation comprising includes the step of receiving an input message. The method includes the step of implementing an entity tagging operation on the input message. The method includes the step of tagging the message context of the input message to generate a tagged message context. The method includes the step of implementing semantic frame extraction from the tagged message context. The method includes the step of implementing an entity interpretation on the extracted frame. The method includes the step of accessing a database to determine a business schedule and a client profile. The business schedule and the client profile are related to the input message. The method includes the step of implementing a retrieval engine. The retrieval engine obtains one or more response templates. The method includes the step of generating a ranked list of candidate templates from the output of the retrieval engine. Based on the output of the entity interpretation, the business schedule and the client profile, and the ranked list of candidate templates, implementing a candidate eliminator. Based on the output of the candidate eliminator, providing a set of recommended responses. Each recommend response is associated with a confidence score.

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