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

WO2012172561A1 ENTERPRISE INFORMATION FUSION 审中-公开
标题翻译：企业信息融合
公开(公告)号：WO2012172561A1
公开(公告)日：2012-12-20
申请号：PCT/IN2012/000118
申请日：2012-02-20
申请人： TATA CONSULTANCY SERVICES LIMITED , SHROFF, Gautam , AGARWAL, Puneet , DEY, Lipika
发明人： SHROFF, Gautam , AGARWAL, Puneet , DEY, Lipika
IPC分类号： G06Q10/06
CPC分类号： G06Q10/06
摘要： Systems and methods related to enterprise information fusion are described. The method comprises obtaining event information corresponding to at least one event, wherein the at least one event includes at least one of an incident and a customer feedback. Based on the event information, information corresponding to at least one entity associated with at least one operation of an enterprise is retrieved, from a plurality of entity information sources. An impact of the at least one event on the at least one entity is determined. Based on the determination of the impact, a risk associated with the at least one event on the at least one operation of the enterprise is evaluated. An alert is generated, based on the evaluation, where the alert is indicative of the risk.
摘要翻译：描述与企业信息融合相关的系统和方法。所述方法包括获得与至少一个事件相对应的事件信息，其中所述至少一个事件包括事件和客户反馈中的至少一个。基于事件信息，从多个实体信息源检索与至少一个与企业的至少一个操作相关联的实体对应的信息。确定至少一个事件对至少一个实体的影响。基于影响的确定，评估与企业的至少一个操作中的至少一个事件相关联的风险。根据评估产生警报，其中警报指示风险。

2. 发明申请

WO2013005227A1 SYSTEM AND METHOD FOR INFORMATION FUSION 审中-公开
标题翻译：信息融合的系统和方法
公开(公告)号：WO2013005227A1
公开(公告)日：2013-01-10
申请号：PCT/IN2012/000117
申请日：2012-02-20
申请人： TATA CONSULTANCY SERVICES LIMITED , SHROFF, Gautam , AGARWAL, Puneet , SHARMA, Saurabh , BHAT, Shefali
发明人： SHROFF, Gautam , AGARWAL, Puneet , SHARMA, Saurabh , BHAT, Shefali
IPC分类号： G06N5/02
CPC分类号： G06N5/02
摘要： Methods and systems for information fusion are described herein. In one implementation, the method includes posting a fact on a layered memory structure (126) and indexing the posted fact to a group, such that facts with a similar property measure are indexed to same group. Further, one or more knowledge modules (122) are applied on the posted fact and one or more input facts indexed to the group. Based on the application of the one or more knowledge modules (122) an output fact is provided and it is determined whether the output fact is a deduced fact based on a probability estimate.
摘要翻译：本文描述了用于信息融合的方法和系统。在一个实现中，该方法包括在分层存储器结构（126）上发布事实并将发布的事实索引到组，使得具有相似属性度量的事实被索引到同一组。此外，将一个或多个知识模块（122）应用于已发布的事实以及索引到该组的一个或多个输入事实。基于一个或多个知识模块（122）的应用，提供输出事实，并且基于概率估计确定输出事实是否是推导的事实。

3. 发明申请

WO2020261234A1 SYSTEM AND METHOD FOR SEQUENCE LABELING USING HIERARCHICAL CAPSULE BASED NEURAL NETWORK 审中-公开
公开(公告)号：WO2020261234A1
公开(公告)日：2020-12-30
申请号：PCT/IB2020/056101
申请日：2020-06-27
申请人： TATA CONSULTANCY SERVICES LIMITED
发明人： SRIVASTAVA, Saurabh , AGARWAL, Puneet , SHROFF, Gautam , VIG, Lovekesh
IPC分类号： G06F17/28 , G06F17/27
摘要： This disclosure relates generally to sequence labeling and more particularly to method and system for sequence labeling. The method includes employing a hierarchical capsule based neural network for sequence labeling, which includes a sentence encoding layer (having word embedding layer, feature extraction layer and multiple capsule layer) and a document encoding layer, Bi-LSTMs, a fully connected layer and a conditional random fields (CRF) layer. The word embedding Layer obtains fixed-size vector representation of words of sentences associated with a dialogue or an abstract, then the feature extraction layer encodes the sentences, the Capsule layer extracts high-level features from the sentence. Ah the sentence encodings are then stacked up together and are passed through another Bi-LSTM layer to derive the contextual information from sentences. A fully connected layer calculates likelihood scores. The CRF layer obtains optimized label sequence based on the likelihood scores.

4. 发明申请

WO2018069817A1 SYSTEM AND METHOD FOR PREDICTING REPEAT BEHAVIOR OF CUSTOMERS 审中-公开
标题翻译：系统和方法预测客户的重复行为
公开(公告)号：WO2018069817A1
公开(公告)日：2018-04-19
申请号：PCT/IB2017/056227
申请日：2017-10-09
申请人： TATA CONSULTANCY SERVICES LIMITED
发明人： AGARWAL, Puneet , KAZMI, Auon Haidar , SHROFF, Gautam
IPC分类号： G06E1/00
摘要： System and method for predicting repeat behaviour of customers are disclosed. In an embodiment, the method includes abstracting a customer interaction data associated with interactions of the customer with respect a target entity into a common data format (CDF) to obtain an abstracted customer interaction data. Based on at least a portion of the abstracted customer interaction data, a set of features corresponding to the target entity are extracted. The set of features characterizes customer interaction with respect to the target entity. Based on the set of features, a prediction model is predicted to predict repeat behaviour probability of the customer with respect to the target entity.
摘要翻译：公开了用于预测顾客的重复行为的系统和方法。在一个实施例中，该方法包括将与客户关于目标实体的交互相关联的客户交互数据提取为公共数据格式（CDF）以获得抽象的客户交互数据。基于抽象的客户交互数据的至少一部分，提取对应于目标实体的一组特征。这组功能描述了客户与目标实体之间的交互。基于这组特征，预测预测模型以预测客户相对于目标实体的重复行为概率。

5. 发明申请

WO2017093953A1 METHOD AND SYSTEM FOR PURCHASE BEHAVIOR PREDICTION OF CUSTOMERS 审中-公开
标题翻译：客户购买行为预测的方法和系统
公开(公告)号：WO2017093953A1
公开(公告)日：2017-06-08
申请号：PCT/IB2016/057292
申请日：2016-12-02
申请人： TATA CONSULTANCY SERVICES LIMITED
发明人： MALHOTRA, Pankaj , ANAND, Gaurangi , KAZMI, Auon Haidar , VIG, Lovekesh , AGARWAL, Puneet , SHROFF, Gautam
IPC分类号： G06F15/18 , G06Q30/06
CPC分类号： G06Q30/06 , G06Q30/02
摘要： A method and a system to enable customer behavior prediction are disclosed. Temporal and aggregate features with respect to purchases made by a customer are extracted from purchase history of customers. Further, temporal and aggregate models are generated corresponding to the features extracted, wherein the temporal and aggregate models are data of a first type and data of a second type respectively. Further, a Mixture of Experts (ME) is used to process the temporal and aggregate models that are of different types of data, to build a combined model, and purchase behavior of the customer is identified based on the combined model.
摘要翻译：公开了一种用于实现顾客行为预测的方法和系统。关于客户购买的时间和集合特征是从客户的购买历史中提取的。进一步地，对应于提取的特征生成时间和聚合模型，其中时间和聚合模型分别是第一类型的数据和第二类型的数据。此外，专家混合（ME）用于处理具有不同类型数据的时间和聚合模型，构建组合模型，并基于组合模型识别客户的购买行为。

6. 发明申请

WO2013171758A2 SYSTEM AND METHOD FOR CREATING STRUCTURED EVENT OBJECTS 审中-公开
标题翻译：用于创建结构化事件对象的系统和方法
公开(公告)号：WO2013171758A2
公开(公告)日：2013-11-21
申请号：PCT/IN2013/000192
申请日：2013-03-22
申请人： TATA CONSULTANCY SERVICES LIMITED
发明人： AGARWAL, Puneet , VAITHIYANATHAN, Rajgopal , SHROFF, Gautam
IPC分类号： H04L29/06
CPC分类号： G06F17/30607 , G06F17/3053 , G06F17/30705 , G06F17/30864 , G06Q10/10 , G06Q50/01 , H04L51/12 , H04L51/32 , H04L67/02
摘要： The present invention envisages a system and method for converting a voluminous stream of unstructured short text messages into event-objects of specific event type that may be of potential interest to users at far away locations. The method of structuring involves detecting long tail of events in spite of their sparsity. This is followed by extracting and correlating detected short text messages that describe same event type to create structured event objects.
摘要翻译：本发明设想一种用于将非结构化短文本消息的大量流转换成特定事件类型的事件对象的系统和方法，该事件对象可能在远处位置处的用户潜在地受益。结构化的方法涉及检测事件的长尾，尽管它们的稀疏性。之后，提取和关联检测到的描述相同事件类型的短文本消息，以创建结构化事件对象。

7. 发明申请

WO2017216647A1 HEALTH MONITORING AND PROGNOSTICS OF A SYSTEM 审中-公开
标题翻译：一个系统的健康监测和预测
公开(公告)号：WO2017216647A1
公开(公告)日：2017-12-21
申请号：PCT/IB2017/051621
申请日：2017-03-21
申请人： TATA CONSULTANCY SERVICES LIMITED
发明人： MALHOTRA, Pankaj , TV, Vishnu , RAMAKRISHNAN, Anusha , ANAND, Gaurangi , VIG, Lovekesh , AGARWAL, Puneet , SHROFF, Gautam
IPC分类号： G06F17/15
CPC分类号： G06K9/6247 , G05B23/0243 , G06K9/00523 , G06K9/00563
摘要： The present disclosure relates to sequence to sequence mapper based systems and methods for health monitoring and prognostics of a system via a health index (HI). The sequence to sequence mapper learns to reconstruct normal time series behavior, and thereafter uses reconstruction error to estimate the HI. The HI is used for generating health behavior trend, detection of anomalous behavior, and remaining useful life (RUL) pertaining to a monitored system. The present disclosure does not rely on domain knowledge, as in the prior art, when estimating the health index. The HI of the monitored system can be determined irrespective of the predictability of the time series data generated from the monitored system. Likewise, the present disclosure is relevant to time series data of varying nature: predictable, unpredictable, periodic, aperiodic, and quasi-periodic time series; short time series and long time series; and univariate and multivariate time series.
摘要翻译：本公开涉及用于经由健康指数（HI）对系统进行健康监测和预测的基于序列映射器的系统和方法。序列映射器学习重构正常的时间序列行为，然后使用重构误差来估计HI。 HI用于产生健康行为趋势，检测异常行为和与监测系统有关的剩余使用寿命（RUL）。当在估计健康指数时，本公开不像在现有技术中那样依赖于领域知识。无论监测系统产生的时间序列数据的可预测性如何，都可以确定被监测系统的HI。同样地，本公开涉及具有不同性质的时间序列数据：可预测的，不可预知的，周期性的，非周期性的和准周期性的时间序列; 短时间序列和长时间序列; 和单变量和多变量时间序列。

8. 发明申请

WO2009094654A1 SYSTEMS AND METHODS FOR CONFIGURATION AND FINE GRAIN POLICY DRIVEN WEB CONTENT DETECTION AND REWRITE 审中-公开
标题翻译：用于配置和精细粒度驱动网络内容检测和清晰度的系统和方法
公开(公告)号：WO2009094654A1
公开(公告)日：2009-07-30
申请号：PCT/US2009/032042
申请日：2009-01-26
申请人： CITRIX SYSTEMS, INC. , AGARWAL, Puneet , THIRUNARAYANAN, Srinivasan , ADHYA, Saibal, Kumar , CHOUDHARY, Akshat , KORRAPATTI, Vamsi , KHEMANI, Prakash , MIRANI, Rajiv , REDDY, Anoop
发明人： AGARWAL, Puneet , THIRUNARAYANAN, Srinivasan , ADHYA, Saibal, Kumar , CHOUDHARY, Akshat , KORRAPATTI, Vamsi , KHEMANI, Prakash , MIRANI, Rajiv , REDDY, Anoop
IPC分类号： H04L29/06
CPC分类号： H04L63/0272 , H04L29/08846 , H04L63/0281 , H04L63/105 , H04L63/166 , H04L63/20 , H04L67/02 , H04L67/14 , H04L67/2814
摘要： The present disclosure provides solutions that may enable an enterprise providing services to a number of clients to determine whether to establish a client based SSL VPN session or a clientless SSL VPN session with a client based on an information associated with the client. An intermediary establishing SSL VPN sessions between clients and servers may receive a request from a client to access a server. The intermediary may identify a session policy based on the request. The session policy may indicate whether to establish a client based SSL VPN session or clientless SSL VPN session with the server. The intermediary may determine, responsive to the policy, to establish a clientless or client based SSL VPN session between the client and the server.
摘要翻译：本公开提供了可以使得能够向多个客户端提供服务的企业基于与客户端相关联的信息来确定是否建立与客户端的基于客户端的SSL VPN会话或客户端SSL VPN会话的解决方案。在客户端和服务器之间建立SSL VPN会话的中间件可以接收客户端访问服务器的请求。中介可以根据请求识别会话策略。会话策略可以指示是否与服务器建立基于客户端的SSL VPN会话或客户端SSL VPN会话。中介可以根据策略确定在客户端和服务器之间建立基于客户端或客户端的SSL VPN会话。

9. 发明申请

WO2007046830A3 SEARCH OVER STRUCTURED DATA 审中-公开
公开(公告)号：WO2007046830A3
公开(公告)日：2007-04-26
申请号：PCT/US2005/045447
申请日：2005-12-13
申请人： GOOGLE INC. , REDDY, Bindu , BRUNSMAN, Jonathan , MOSBERGER, Ning , BHAYA, Gaurav, Ravindra , SIRAJUDDIN, Sarah , KALE, David , KOZENSKI, Jennifer, L. , SUNDARARAJAN, Arvind , AGARWAL, Puneet
发明人： REDDY, Bindu , BRUNSMAN, Jonathan , MOSBERGER, Ning , BHAYA, Gaurav, Ravindra , SIRAJUDDIN, Sarah , KALE, David , KOZENSKI, Jennifer, L. , SUNDARARAJAN, Arvind , AGARWAL, Puneet
IPC分类号： G06F7/00 , G06F17/30
摘要： A user can refine a search over structured data by specifying that a label or an attribute value be used to further filter the results of a query.

10. 发明申请

WO2016113718A1 SYSTEM AND METHOD TO DIAGNOSE AND PREDICT DIFFERENT SYSTEMIC DISORDERS AND MENTAL STATES 审中-公开
标题翻译：诊断和预测不同系统疾病和精神状态的系统和方法
公开(公告)号：WO2016113718A1
公开(公告)日：2016-07-21
申请号：PCT/IB2016/050228
申请日：2016-01-18
申请人： AGARWAL, Puneet , PANWAR, Siddharth
发明人： AGARWAL, Puneet , PANWAR, Siddharth , JOSHI, Shiv Dutt , GUPTA, Anubha
IPC分类号： A61B5/0476 , G06T7/00
CPC分类号： A61B5/0476 , A61B5/165 , A61B5/7239 , A61B5/7257 , G06K9/00496
摘要： The present invention relates a novel system and method to diagnose and predict systemic disorders including brain disorders and mental states in early stage and more accurately. More particularly, this invention relates to a novel method of EEG recording and processing through which multiple output data streams are taken together from a system like brain and the structure of their correlation matrix is studied through its eigenvector, eigendirection and eigenspaces and other signal processing techniques including compression sensing, wavelet transform, fast fourier transform etc.
摘要翻译：本发明涉及一种用于早期诊断和预测全身性疾病，包括脑部疾病和精神状态的新型系统和方法。更具体地说，本发明涉及一种脑电图记录和处理的新方法，通过该方法，多个输出数据流从诸如大脑的系统中取出，并且通过其特征向量，特征向量和特征等信号处理技术来研究其相关矩阵的结构包括压缩感知，小波变换，快速傅里叶变换等。

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