专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明专利

CA2893495C SYSTEM AND METHOD FOR INTERACTIVELY VISUALIZING RULES AND EXCEPTIONS 未知
公开(公告)号：CA2893495C
公开(公告)日：2019-04-23
申请号：CA2893495
申请日：2015-05-29
申请人： TATA CONSULTANCY SERVICES LTD
发明人： SHARMA GEETIKA , SHROFF GAUTAM , PANDEY ADITEYA , AGARWAL PUNEET
IPC分类号： G06F17/00 , G06F3/0481 , G16B45/00
摘要： The present disclosure discloses system and method for providing perceptually efficient visualization of rules and exceptions mined from dataset. Further, parsing is performed on data-attributes associated with the rules. The data-attributes may comprise antecedents, consequents, ranges of the antecedents, syntax and statistics of the rules and exceptions. The visualization scheme of present disclosure present an overview first, allows semantic zooming, and then shows details on demand. Further, data attributes of the rules are mapped with visual attributes of graphical elements such as shape, color, opacity to create the perceptually efficient visualization of the rules and exceptions. Initially, the visualization shows main rule highlighting the exceptions associated and properties of the exceptions. Further, a semantic zoom slider is provided for allowing a user to navigate through different exception levels of the exception. Further, an interface is provided for obtaining additional information associated with the rules and the exceptions.

42. 发明专利

CA3017655A1 TECHNIQUES FOR CORRECTING LINGUISTIC TRAINING BIAS IN TRAINING DATA 未知
公开(公告)号：CA3017655A1
公开(公告)日：2019-03-18
申请号：CA3017655
申请日：2018-09-18
申请人： TATA CONSULTANCY SERVICES LTD
发明人： AGARWAL PUNEET , PATIDAR MAYUR , VIG LOVEKESH , SHROFF GAUTAM
IPC分类号： G06N20/00 , G06F16/903 , G06F17/27
摘要： In automated assistant systems, a deep-learning model in form of a long short-term memory (LSTM) classifier is used for mapping questions to classes, with each class having a manually curated answer. A team of experts manually create the training data used to train this classifier. Relying on human curation often results in such linguistic training biases creeping into training data, since every individual has a specific style of writing natural language and uses some words in specific context only. Deep models end up learning these biases, instead of the core concept words of the target classes. In order to correct these biases, meaningful sentences are automatically generated using a generative model, and then used for training a classification model. For example, a variational autoencoder (VAE) is used as the generative model for generating novel sentences and a language model (LM) is utilized for selecting sentences based on likelihood.

43. 发明专利

CA2960505C SYSTEM AND METHOD FOR VISUAL BAYESIAN DATA FUSION 未知
公开(公告)号：CA2960505C
公开(公告)日：2018-12-11
申请号：CA2960505
申请日：2017-03-09
申请人： TATA CONSULTANCY SERVICES LTD
发明人： SHARMA GEETIKA , SINGH KARAMJIT , GUPTA GARIMA , SHROFF GAUTAM , AGARWAL PUNEET , PANDEY ADITEYA , PANERI KAUSHAL ASHOKBHAI , SEHGAL GUNJAN
IPC分类号： G06F7/00
摘要： System and method for visual Bayesian data fusion are disclosed. In an example, a plurality of datasets associated with a topic are obtained from a data lake. Each of the plurality of datasets include information corresponding to various attributes of the topic. Further, the plurality of datasets are joined to obtain a joined dataset. Furthermore, distribution associated with a target attribute is predicted using Bayesian modeling by selecting a plurality of attributes (k) based on mutual information with the target attribute in the joined dataset, learning a minimum spanning tree based Bayesian structure using the selected attributes and the target attribute, learning conditional probabilistic tables at each node of the minimum spanning tree based Bayesian structure; and predicting the distribution associated with the target attribute by querying the conditional probabilistic tables, thereby facilitating visual Bayesian data fusion.

44. 发明专利

AU2016201330B2 MULTI-SENSOR DATA SUMMARIZATION 未知
公开(公告)号：AU2016201330B2
公开(公告)日：2018-05-10
申请号：AU2016201330
申请日：2016-03-01
申请人： TATA CONSULTANCY SERVICES LTD
发明人： SRINIVASAN ASHWIN , AGARWAL PUNEET , SHROFF GAUTAM , SAIKIA SARMIMALA
IPC分类号： G06F17/15
摘要： A system 200 and method for summarizing multi-sensor data are provided. In an embodiment, the method includes computing a plurality of histograms from sensor data associated with a plurality of sensors. The respective histograms of each sensor are clustered into a first plurality of sensor-clusters, and a first set of rules is extracted therefrom. First set of rules defines patterns of histograms of a set of sensors occurring frequently over a time-period. Two or more sensor-clusters from amongst the first plurality of sensor-clusters are merged selectively to obtain a second plurality of sensor-clusters. Second set of rules are extracted from the second plurality of sensor-clusters, and a set of correlated sensors are identified therefrom based on the second set of rules. Third set of rules are extracted from the set of correlated sensors, where the third set of rules summarizes the multi-sensor data to represent prominent co-occurring sensor behaviors. 2592327v2 104a 104b 104c 104d 202 NETWORK PROCESSOR UNIT

45. 发明专利

AU2016201425B2 Systems and methods for predictive reliability mining 未知
公开(公告)号：AU2016201425B2
公开(公告)日：2018-01-18
申请号：AU2016201425
申请日：2016-03-04
申请人： TATA CONSULTANCY SERVICES LTD
发明人： SINGH KARAMJIT , SHROFF GAUTAM , AGARWAL PUNEET
IPC分类号： G06F17/00
摘要： SYSTEMS AND METHODS FOR PREDICTIVE RELIABILITY MINING Systems and methods for predictive reliability mining are provided that enable predicting of unexpected emerging failures in future without waiting for actual failures to start occurring in significant numbers. Sets of discriminative Diagnostic Trouble Codes (DTCs) from connected machines in a population are identified (202) before failure of the associated parts. A temporal conditional dependence model based on the temporal dependence between the failure of the parts from past failure data and the identified sets of discriminative DTCs is generated (204). Future failures are predicted (206) based on the generated temporal conditional dependence and root cause analysis of the predicted future failures is performed (208) for predictive reliability mining. The probability of failure is computed based on both occurrence and non-occurrence of DTCs. The root cause analysis enables identifying a subset of the population when an early warning is generated and also when an early warning is not generated.

46. 发明专利

AU2016259280A1 MULTI-SENSOR VISUAL ANALYTICS 未知
公开(公告)号：AU2016259280A1
公开(公告)日：2017-06-01
申请号：AU2016259280
申请日：2016-11-14
申请人： TATA CONSULTANCY SERVICES LTD
发明人： SHARMA GEETIKA , SHROFF GAUTAM , AGARWAL PUNEET , PANDEY ADITEYA , SEHGAL GUNJAN , PANERI KAUSHAL ASHOKBHAI , SINGH BRIJENDRA
IPC分类号： G06F15/18 , G06K7/00 , G06Q10/06
摘要： A system and method for multi-sensor visual analytics are provided. The method includes acquiring sensor data associated with a plurality of sensors for a plurality of days of operation. A plurality of multi-dimensional histograms, including two-dimensional and three-dimensional histograms, having operational profiles of the plurality of sensors are computed from the sensor data. The plurality of multi-dimensional histograms are monitored, and a plurality of multi sensor patterns are obtained from the plurality of histograms. The plurality of multi-sensor patterns are indicative of one or more properties of a plurality of sensor-clusters of the plurality of sensors. One or more visual analytical tasks are performed by processing the plurality of multi-sensor patterns using at least one machine-learning model. The one or more visual models are rendered based on the processing of the multi-sensor patterns. ACQUIRE SENSOR DATA ASSOCIATED WITH A 702 PLURALITY OF SENSORS FOR A PLURALITY OF DAYS OF COMPUTE A PLURALITY OF MULTI-DIMENSIONAL 704 HISTOGRAMS ASSOCIATED WITH THE PLURALITY OF SENSORS FROM THE SENSOR DATA MONITOR THE PLURALITY OF MULTI-DIMENSIONAL 706 HISTOGRAMS AND OBTAINING A PLURALITY OF MULTI-SENSOR PATTERNS FROM THE PLURALITY OF MULTI-DIMENSIONAL HISTOGRAMS PERFORM ONE OR MORE VISUAL ANALYTICAL TASKS 708 BY PROCESSING THE PLURALITY OF MULTI-SENSOR PATTERNS USING AT LEAST ONE MACHINE-LEARNING RENDER ONE OR MORE VISUAL MODELS BASED ON 710 THE PROCESSING OF THE MULTI-SENSOR PATTERNS

47. 发明专利

AU2016201425A1 Systems and methods for predictive reliability mining 未知
公开(公告)号：AU2016201425A1
公开(公告)日：2017-05-04
申请号：AU2016201425
申请日：2016-03-04
申请人： TATA CONSULTANCY SERVICES LTD
发明人： SINGH KARAMJIT , SHROFF GAUTAM , AGARWAL PUNEET
IPC分类号： G06F17/00
摘要： SYSTEMS AND METHODS FOR PREDICTIVE RELIABILITY MINING Systems and methods for predictive reliability mining are provided that enable predicting of unexpected emerging failures in future without waiting for actual failures to start occurring in significant numbers. Sets of discriminative Diagnostic Trouble Codes (DTCs) from connected machines in a population are identified (202) before failure of the associated parts. A temporal conditional dependence model based on the temporal dependence between the failure of the parts from past failure data and the identified sets of discriminative DTCs is generated (204). Future failures are predicted (206) based on the generated temporal conditional dependence and root cause analysis of the predicted future failures is performed (208) for predictive reliability mining. The probability of failure is computed based on both occurrence and non-occurrence of DTCs. The root cause analysis enables identifying a subset of the population when an early warning is generated and also when an early warning is not generated.

48. 发明专利

MX2016003107A RECAPITULACION DE DATOS DE MULTIPLES SENSORES. 未知
公开(公告)号：MX2016003107A
公开(公告)日：2017-04-17
申请号：MX2016003107
申请日：2016-03-09
申请人： TATA CONSULTANCY SERVICES LTD
发明人： AGARWAL PUNEET , SHROFF GAUTAM , SARMIMALA SAIKIA , SRINIVASAN ASHWIN
IPC分类号： G06F19/00 , G06F15/04 , G06F17/18
摘要： Se proporcionan un sistema 200 y un procedimiento para recapitular datos de múltiples sensores. En una realización, el procedimiento incluye calcular una pluralidad de histogramas a partir de datos de sensores asociados a una pluralidad de sensores. Los respectivos histogramas de cada sensor son agrupados en una primera pluralidad de agrupaciones de sensores, y se extrae de los mismos un primer conjunto de reglas. El primer conjunto de reglas define patrones de histogramas de un conjunto de sensores que aparecen frecuentemente durante un periodo de tiempo. Dos o más agrupaciones de sensores, entre la primera pluralidad de agrupaciones de sensores, se funden selectivamente para obtener una segunda pluralidad de agrupaciones de sensores. El segundo conjunto de reglas se extraen a partir de la segunda pluralidad de agrupaciones de sensores, y un conjunto de sensores correlacionados son identificados a partir de las mismas, en base al segundo conjunto de reglas. El tercer conjunto de reglas se extraen del conjunto de sensores correlacionados, donde el tercer conjunto de reglas recapitula los datos de múltiples sensores para representar prominentes comportamientos concurrentes de sensores.

49. 发明专利

CA2923908A1 METHODS AND SYSTEMS FOR SEARCHING LOGICAL PATTERNS 未知
公开(公告)号：CA2923908A1
公开(公告)日：2016-12-19
申请号：CA2923908
申请日：2016-03-16
申请人： TATA CONSULTANCY SERVICES LTD
发明人： HASSAN EHTESHAM , YADAV MOHIT , AGARWAL PUNEET , SHROFF GAUTAM , SRINIVASAN ASHWIN
IPC分类号： G06F17/30 , G06F17/00
摘要： Methods and systems for searching logical patterns in voluminous multi sensor data from the industrial internet is provided. The method retrieves instances of patterns in time-series data where patterns are specified logically, using a sequence of symbols. The logical symbols used are a subset of the qualitative abstractions specifically, the concepts of steady, increasing, decreasing. Patterns can include symbol-sequences for multiple sensors, approximate duration as well as slope values for each symbol. To facilitate efficient querying, each sensor time-series is pre-processed into a sequence of logical symbols. Each position in the resulting compressed sequence is registered across a TRIE-based index structure corresponding to the multiple logical patterns it may belong to. Logical multi-sensor patterns are efficiently retrieved and ranked using such a structure. This method of indexing and searching provides an efficient mechanism for exploratory analysis of voluminous multi-sensor data.

50. 发明专利

MX2014013314A RESOLUCION DE ENTIDAD DE DOCUMENTOS. 未知
公开(公告)号：MX2014013314A
公开(公告)日：2016-03-15
申请号：MX2014013314
申请日：2014-11-03
申请人： TATA CONSULTANCY SERVICES LTD
发明人： AGARWAL PUNEET , SHROFF GAUTAM , MALHOTRA PANKAJ
IPC分类号： G06F17/30 , G06F40/00
摘要： La presente materia objeto se refiere a resolución de entidad, y en particular, se refiere a proporcionar un resolución de entidad a partir de documentos. El método comprende obtener la pluralidad de documentos a partir de al menos una fuente de datos. La pluralidad de documentos se agrupa en bloques en al menos un cubo basándose en la similitud textual y las referencias entre documentos entre la pluralidad de documentos. Además, en cada cubo, puede crearse un documento fusionado para cada entidad basándose en una técnica de coincidencia-fusión interactiva. La técnica de coincidencia-fusión interactiva identifica, a partir de la pluralidad de documentos, al menos un par de documentos coincidente y fusiona el al menos un par de documentos coincidente para crear el documento fusionado para cada entidad. Los documentos fusionados pueden fusionarse para generar un documento de entidad resuelta para cada entidad basándose en una técnica de agrupación de grafos. A publicar con fig. 2.

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