公开(公告)号：US20210125207A1

公开(公告)日：2021-04-29

申请号：US16788317

申请日：2020-02-12

Applicant: SOMNATH BANERJEE ,  RIMO DAS ,  HARSHINDER CHADHA ,  KURIEN JACOB

Inventor： SOMNATH BANERJEE ,  RIMO DAS ,  HARSHINDER CHADHA ,  KURIEN JACOB

IPC: G06Q30/02 ,  G06Q50/12 ,  G06Q10/04 ,  G06F16/25 ,  G06N20/00

Abstract: In one aspect, a computerized method for implementing multi-layered market forecast framework for hotel revenue management by continuously learning market dynamics includes the step of collecting a set of data from various relevant providers, wherein the set of data comprises market data, events information relevant to a market, and market pricing. The method includes the step of implementing an extract, transform, load (ETL) operations on the set of data, wherein the ETL comprises the ingestion of the multi-textured data into big data storage for use on demand basis. The method includes the step of implementing one or more specified data cleaning operations on the set of data. The method includes the step of implementing one or more specified feature engineering operations on the cleaned data. The method includes the step of generating an Average daily rate (ADR) training data set. The method includes the step of generating an occupancy training data set. The method includes the step of building an ADR model using the ADR training data. The method includes the step of building the occupancy model using the occupancy training data. The method includes the step of, with the ADR model and the occupancy model, generating a prediction data set. The method includes the step of, with the prediction data set, generating a forecast for a specified set of rates for a specific hotel. The method includes the step of, with the accuracy trackers, evaluating the multi-layered market forecaster and update the multi-layered market forecaster model to ensure its accuracy.

公开(公告)号：US20100306144A1

公开(公告)日：2010-12-02

申请号：US12476821

申请日：2009-06-02

Applicant: Martin B. Scholz ,  Somnath Banerjee

Inventor： Martin B. Scholz ,  Somnath Banerjee

IPC: G06F15/18

CPC classification number: G06N20/00 ,  G06F16/353

Abstract: An exemplary embodiment of the present invention provides a computer implemented method for classifying information. The method may include accessing a plurality of information sources to identify example information items for each of a plurality of classification categories. Each of the example information items may be analyzed to generate a training corpus for each information source for each of the classification categories. The training corpus for each of the information sources may be combined to generate a training set for each of the classification categories, wherein the training set may be configured to allow the generation of a classification function.

Abstract translation: 本发明的示例性实施例提供了一种用于对信息进行分类的计算机实现方法。 该方法可以包括访问多个信息源以识别多个分类类别中的每一个的示例信息项。 可以分析每个示例信息项以为每个分类类别的每个信息源生成训练语料库。 每个信息源的训练语料库可以被组合以产生每个分类类别的训练集合，其中训练集合可以被配置为允许生成分类功能。

公开(公告)号：US08447766B2

公开(公告)日：2013-05-21

申请号：US12766942

申请日：2010-04-26

Applicant: Somnath Banerjee ,  Soumen Chakrabarti ,  Ganesh Ramakrishnan

Inventor： Somnath Banerjee ,  Soumen Chakrabarti ,  Ganesh Ramakrishnan

IPC: G06F17/30 ,  G06F7/00

CPC classification number: G06F17/30675

Abstract: Disclosed is a method of querying a collection of electronic documents, comprising defining a query for retrieving a numerical answer, said query comprising one or more search terms and a tolerance for said numerical answer; defining a set of document portions from said collection, each document portion in said set being extracted from an electronic document and comprising at least one term relevant to at least one of the one or more search terms and a numerical value associated with the at least one term; ordering the associated numerical values contained in said set; defining a plurality of results groups, each results group comprising an interval of ordered numerical values, each interval having a range not exceeding the tolerance; ranking the results groups; and returning at least the interval of the highest ranked results group as a response to said query A computer program product for executing this method on a computer processor and a server are also disclosed.

Abstract translation: 公开了一种查询电子文档集合的方法，包括定义用于检索数字答案的查询，所述查询包括一个或多个搜索项和对所述数字答案的容差; 从所述集合定义一组文档部分，所述集合中的每个文档部分从电子文档中提取，并且包括与所述一个或多个搜索项中的至少一个相关联的至少一个术语和与所述至少一个相关联的数值 术语; 对包含在所述组中的相关数值进行排序; 定义多个结果组，每个结果组包括有序数值的间隔，每个间隔的范围不超过公差; 排名结果组; 并且至少返回最高排名的结果组的间隔作为对所述查询的响应还公开了一种用于在计算机处理器和服务器上执行该方法的计算机程序产品。

公开(公告)号：US08024765B2

公开(公告)日：2011-09-20

申请号：US11611900

申请日：2006-12-18

Applicant: Krishnan Ramanathan ,  Ajay Gupta ,  Shekhar Ramachandra Borgaonkar ,  Arnaud Francois Paul Salomon ,  Chakradhar Dandu ,  Somnath Banerjee

Inventor： Krishnan Ramanathan ,  Ajay Gupta ,  Shekhar Ramachandra Borgaonkar ,  Arnaud Francois Paul Salomon ,  Chakradhar Dandu ,  Somnath Banerjee

IPC: H04N7/173 ,  H04N7/10 ,  H04N7/16

CPC classification number: H04N5/44508 ,  H04N21/235 ,  H04N21/4104 ,  H04N21/4113 ,  H04N21/4126 ,  H04N21/435 ,  H04N21/4622 ,  H04N21/47 ,  H04N21/47214 ,  H04N21/478 ,  H04N21/482 ,  H04N21/488 ,  H04N21/84

Abstract: A method for communicating media program information is provided. The method includes receiving a content-augmented broadcast signal at a conventional broadcast receiver, the content-augmented broadcast signal having a program content and a program cookie relating to the program content, demodulating the content-augmented broadcast signal, rendering the program content, recovering the program cookie from the demodulated content-augmented broadcast signal at substantially the same time the program content is rendered, determining whether the program cookie comprises information relating to a current media program a user is currently watching or listening to, or to an advertisement of a future media program, and sending the program cookie to an electronic device.

Abstract translation: 提供了一种用于传送媒体节目信息的方法。 该方法包括在常规广播接收机处接收内容增强广播信号，内容增强广播信号具有节目内容和节目内容相关的节目内容，解调内容增强广播信号，呈现节目内容，恢复 在解码的内容增强广播信号的基本上同时呈现节目内容的节目cookie，确定节目cookie是否包括与用户当前正在观看或收听的当前媒体节目相关的信息，或者确定节目内容的广告 将来的媒体程序，并将程序cookie发送到电子设备。

公开(公告)号：US5305417A

公开(公告)日：1994-04-19

申请号：US37771

申请日：1993-03-26

Applicant: Habib N. Najm ,  Mehrdad M. Moslehi ,  Somnath Banerjee ,  Lino A. Velo

Inventor： Habib N. Najm ,  Mehrdad M. Moslehi ,  Somnath Banerjee ,  Lino A. Velo

IPC: G01J5/10 ,  C30B25/10 ,  G01J5/08 ,  G05D23/19 ,  G05D23/27 ,  H01L21/66 ,  G01J5/06

CPC classification number: B24B37/013 ,  C30B25/10 ,  G05D23/27 ,  H01L22/26 ,  H01L22/12

Abstract: In a RTP reactor where wafer temperature is measured by a pyrometer assembly (32), a pyrometer assembly (50) is further provided to measure the temperature of the quartz window (30) that is situated between the wafer pyrometer assembly (32) and the wafer (16) that is being processed. During the calibration procedure (100, 120) where a thermocouple wafer is used, the measurements from the wafer pyrometer assembly (32) and the window pyrometer assembly (50) are calibrated, and pyrometer measurements and thermocouple measurements are collected and compiled into calibration tables. During actual RTP reactor operation, the data from the calibration tables and current wafer and window pyrometer measurements are used to compute corrected wafer temperature(s). The corrected wafer temperature(s) is/are then used to control the intensities of the heating lamps according to the wafer processing heating schedule.

Abstract translation: 在通过高温计组件（32）测量晶片温度的RTP反应器中，还提供高温计组件（50）以测量位于晶片高温计组件（32）和晶片高温计组件（32）之间的石英窗口（30）的温度， 正在处理的晶片（16）。 在使用热电偶晶片的校准过程（100,120）期间，对来自晶片高温计组件（32）和窗口高温计组件（50）的测量进行校准，并将高温计测量和热电偶测量值收集并编译成校准表 。 在实际的RTP电抗器操作期间，使用来自校准表和当前晶圆和窗口高温计测量的数据来计算校正的晶片温度。 然后使用校正的晶片温度来根据晶片加工时间表来控制加热灯的强度。

公开(公告)号：US20100281044A1

公开(公告)日：2010-11-04

申请号：US12495825

申请日：2009-07-01

Applicant: Ajay GUPTA ,  Somnath Banerjee ,  Krishnan Ramanathan

Inventor： Ajay GUPTA ,  Somnath Banerjee ,  Krishnan Ramanathan

IPC: G06F17/30 ,  G06F15/16

CPC classification number: G06Q30/02 ,  G06F16/9024 ,  G06Q30/0224

Abstract: Presented is a computer implemented method and system for creating a profiled social network. The method includes mapping at least one identity to each node in the plurality of nodes, defining a profile for each node in the plurality of nodes, identifying a relationship between the at least two nodes in the plurality of nodes, defining a profile for the relationship between the at least two nodes in the plurality of nodes, and forming a collection of profiles defined for all relationships between the plurality of nodes.

Abstract translation: 提出了一种用于创建分析社交网络的计算机实现方法和系统。 该方法包括将至少一个身份映射到多个节点中的每个节点，为多个节点中的每个节点定义简档，识别多个节点中的至少两个节点之间的关系，定义关系的简档 在所述多个节点中的所述至少两个节点之间，并且形成为所述多个节点之间的所有关系定义的简档集合。

公开(公告)号：US20090307029A1

公开(公告)日：2009-12-10

申请号：US12177155

申请日：2008-07-22

Applicant: Krishnan Ramanathan ,  Ajay Gupta ,  Somnath Banerjee

Inventor： Krishnan Ramanathan ,  Ajay Gupta ,  Somnath Banerjee

IPC: G06Q30/00 ,  G06Q10/00 ,  H04L9/00

CPC classification number: G06Q30/00 ,  G06Q10/00 ,  G06Q20/0855 ,  G06Q20/3674 ,  G06Q30/0277 ,  G06Q30/06

Abstract: A system and method for method for implementing a discounted printing is disclosed. In one embodiment, a method for implementing discounted printing includes creating a sponsored document including a digital signature using a cryptographic protocol provided in an application by an enterprise, sending the sponsored document including the digital signature to a client computing system including a sponsored printer for printing by the enterprise, dynamically verifying the digital signature by a trusted service provider upon the enterprise sending the sponsored document to the sponsored printer, and printing the sponsored document by the sponsored printer upon a successful verification of the digital signature. The method may also include crediting an end user associated with the sponsored printer by an amount that substantially subsidizes cost associated with the printing of the sponsored document.

Abstract translation: 公开了一种用于实现打折打印的方法的系统和方法。 在一个实施例中，用于实现打折打印的方法包括使用在企业的应用程序中提供的加密协议来创建包括数字签名的赞助文档，将包括数字签名的赞助文档发送到客户端计算系统，该客户端计算系统包括用于打印的赞助打印机 由企业在企业将赞助文件发送给赞助的打印机时由可信服务提供商动态地验证数字签名，以及在成功验证数字签名时由赞助的打印机打印赞助的文档。 该方法还可以包括将与赞助的打印机相关联的最终用户的贷记量基本上补贴与赞助文档的打印相关联的成本。

公开(公告)号：US20210110445A1

公开(公告)日：2021-04-15

申请号：US17029036

申请日：2020-09-23

Applicant: SOMNATH BANERJEE ,  RIMO DAS ,  KURIEN JACOB ,  HARSHINDER CHADHA

Inventor： SOMNATH BANERJEE ,  RIMO DAS ,  KURIEN JACOB ,  HARSHINDER CHADHA

IPC: G06Q30/02 ,  G06F16/25 ,  G06N20/00

Abstract: In one aspect, a computerized method for implementing a multi-layered system for heterogeneous pricing decisions by continuously learning market and hotel dynamics includes the step of collecting a set of data from relevant providers. The set of data from relevant providers comprises hotel data, competitor data, market data, and market pricing data. The method includes the step of implementing an ETL operation on the set of data from relevant providers. The ETL operation comprises an ingestion of the multi-textured data into a big data storage for use on an on-demand basis. The method includes the step of implementing one or more specified data cleaning operations on the dataset to generate a cleaned data set. The method includes the step of implementing one or more specified feature engineering operations on the cleaned data set. The method includes the step of generating an evaluation set and prediction set. The method includes the step of generating training and test dataset from the evaluation set. The method includes the step of building a price-sensitive demand model using the training data. The method utilizes a machine-learning gradient boosting framework and Expectation-Maximization algorithm to build the price-sensitive demand model. The method includes the step of measuring the accuracy of the model using the test data. The method includes the step of optimizing a price for a specified set of dates for a specific hotel using the prediction dataset. The method includes the step of providing a price-sensitive demand model.

公开(公告)号：US08051012B2

公开(公告)日：2011-11-01

申请号：US12177155

申请日：2008-07-22

Applicant: Krishnan Ramanathan ,  Ajay Gupta ,  Somnath Banerjee

Inventor： Krishnan Ramanathan ,  Ajay Gupta ,  Somnath Banerjee

IPC: G06Q20/00

CPC classification number: G06Q30/00 ,  G06Q10/00 ,  G06Q20/0855 ,  G06Q20/3674 ,  G06Q30/0277 ,  G06Q30/06

Abstract: A system and method for method for implementing a discounted printing is disclosed. In one embodiment, a method for implementing discounted printing includes creating a sponsored document including a digital signature using a cryptographic protocol provided in an application by an enterprise, sending the sponsored document including the digital signature to a client computing system including a sponsored printer for printing by the enterprise, dynamically verifying the digital signature by a trusted service provider upon the enterprise sending the sponsored document to the sponsored printer, and printing the sponsored document by the sponsored printer upon a successful verification of the digital signature. The method may also include crediting an end user associated with the sponsored printer by an amount that substantially subsidizes cost associated with the printing of the sponsored document.

Abstract translation: 公开了一种用于实现打折打印的方法的系统和方法。 在一个实施例中，用于实现打折打印的方法包括使用在企业的应用程序中提供的加密协议来创建包括数字签名的赞助文档，将包括数字签名的赞助文档发送到客户端计算系统，该客户端计算系统包括用于打印的赞助打印机 由企业在企业将赞助文件发送给赞助的打印机时由可信服务提供商动态地验证数字签名，以及在成功验证数字签名时由赞助的打印机打印赞助的文档。 该方法还可以包括将与赞助的打印机相关联的最终用户的贷记量基本上补贴与赞助文档的打印相关联的成本。

公开(公告)号：US20110264670A1

公开(公告)日：2011-10-27

申请号：US12766942

申请日：2010-04-26

Applicant: Somnath BANERJEE ,  Soumen Chakrabarti ,  Ganesh Ramakrishnan

Inventor： Somnath BANERJEE ,  Soumen Chakrabarti ,  Ganesh Ramakrishnan

IPC: G06F17/30

CPC classification number: G06F17/30675

Abstract: Disclosed is a method of querying a collection of electronic documents, comprising defining a query for retrieving a numerical answer, said query comprising one or more search terms and a tolerance for said numerical answer; defining a set of document portions from said collection, each document portion in said set being extracted from an electronic document and comprising at least one term relevant to at least one of the one or more search terms and a numerical value associated with the at least one term; ordering the associated numerical values contained in said set; defining a plurality of results groups, each results group comprising an interval of ordered numerical values, each interval having a range not exceeding the tolerance; ranking the results groups; and returning at least the interval of the highest ranked results group as a response to said query A computer program product for executing this method on a computer processor and a server are also disclosed.

Abstract translation: 公开了一种查询电子文档集合的方法，包括定义用于检索数字答案的查询，所述查询包括一个或多个搜索项和对所述数字答案的容限; 从所述集合定义一组文档部分，所述集合中的每个文档部分从电子文档中提取，并且包括与所述一个或多个搜索项中的至少一个相关联的至少一个术语和与所述至少一个相关联的数值 术语; 对包含在所述组中的相关数值进行排序; 定义多个结果组，每个结果组包括有序数值的间隔，每个间隔的范围不超过公差; 排名结果组; 并且至少返回最高排名的结果组的间隔作为对所述查询的响应还公开了一种用于在计算机处理器和服务器上执行该方法的计算机程序产品。