公开(公告)号：US20140052606A1

公开(公告)日：2014-02-20

申请号：US13968277

申请日：2013-08-15

Applicant: Infosys Limited

Inventor： Bintu G. Vasudevan ,  Anju G. Parvathy ,  Abhishek Kumar ,  Rajesh Balakrishnan

IPC: G06Q40/02

CPC classification number: G06Q40/025

Abstract: A system for facilitating prediction of a loan recovery decision pertaining to a customer of a financial institution is provided. The system comprises one or more databases comprising customer interaction data, customer profile data, and economic data. The system further comprises a Behavioral History Sequence (BHS) module configured to generate behavioral history sequence data associated with the customer. The BHS module generates the BHS data by sanitizing the customer interaction data and classifying the sanitized customer interaction data into predefined categories. The system further comprises a prediction module that is configured to predict payment behavior of the customer based on the BHS data, the customer profile data, and the economic data. The prediction module is further configured to predict the loan recovery decision pertaining to the customer, wherein the predicted loan recovery decision is based on the predicted payment behavior of the customer.

Abstract translation: 提供了一种用于促进关于金融机构的客户的贷款恢复决定的预测的系统。 该系统包括一个或多个数据库，其包括客户交互数据，客户简档数据和经济数据。 该系统还包括行为历史序列（BHS）模块，其被配置为生成与客户相关联的行为历史序列数据。 BHS模块通过消毒客户交互数据并将消毒的客户交互数据分类为预定类别来生成BHS数据。 该系统还包括预测模块，其被配置为基于BHS数据，客户简档数据和经济数据预测顾客的支付行为。 预测模块还被配置为预测与客户有关的贷款恢复决定，其中预测的贷款恢复决定基于客户的预测的支付行为。

公开(公告)号：US20140164417A1

公开(公告)日：2014-06-12

申请号：US13946832

申请日：2013-07-19

Applicant: Infosys Limited

Inventor： Rajesh Balakrishnan ,  Bintu G. Vasudevan ,  Amar Viswanathan ,  Prasanna Venkatesh Raghunathan ,  Umadas Ravindran

IPC: G06F17/30

CPC classification number: G06F16/345

Abstract: A method, non-transitory computer readable medium, and opinion manager device that analyzes user opinions in data includes identifying one or more items of text in data that match one or more of the terms in a database for one or more domain specific concepts. At least the identified one or more items of text in the data for each of the one or more domain specific concepts with the identified one or more terms that match are analyzed based on stored concept analysis rules. One or more reports are provided based on the analysis.

Abstract translation: 分析数据中的用户意见的方法，非暂时性计算机可读介质和意见管理器设备包括识别与数据库中的一个或多个术语匹配的数据中的一个或多个文本的一个或多个项目，用于一个或多个域特定概念。 基于存储的概念分析规则，分析至少所识别的一个或多个具有所标识的一个或多个匹配项的一个或多个域特定概念中的每一个文本的文本项目。 基于分析提供一个或多个报告。

公开(公告)号：US10049096B2

公开(公告)日：2018-08-14

申请号：US15165630

申请日：2016-05-26

Applicant: Infosys Limited

Inventor： Krishnamurty Sai Deepak ,  Ganesh Kumar Nunnagoppula ,  Ann Matthew ,  Harikrishna G. N Rai ,  P. Radha Krishna ,  Rajesh Balakrishnan ,  Shreyas Bettadapura Guruprasad ,  Bintu G. Vasudevan

IPC: G06K9/00 ,  G06F17/24 ,  G06T11/60 ,  G06K9/20 ,  G06K9/62

Abstract: Methods and systems for template creation for a data extraction tool. A first template is selected from a plurality of documents provided by a user. An OCR engine annotates the first template and at least one data region in the first template corresponding to a set of parameters required in a target template is identified by selecting a geometrical region on the first template. At least one interim template is created based on the identification, and the plurality of documents are analyzed using the interim template to extract data values in the data region. The documents are converted to a format compliant with the target template based on the analysis.

公开(公告)号：US20160371246A1

公开(公告)日：2016-12-22

申请号：US15165630

申请日：2016-05-26

Applicant: Infosys Limited

Inventor： Krishnamurty Sai Deepak ,  Ganesh Kumar Nunnagoppula ,  Ann Matthew ,  Harikrishna G. N Rai ,  P. Radha Krishna ,  Rajesh Balakrishnan ,  Shreyas Bettadapura Guruprasad ,  Bintu G. Vasudevan

IPC: G06F17/24 ,  G06K9/18 ,  G06F3/0482 ,  G06F17/27 ,  G06F17/21

CPC classification number: G06F17/248 ,  G06F17/241 ,  G06F17/243 ,  G06K9/2054 ,  G06K9/6253 ,  G06T11/60

Abstract: Methods and systems for template creation for a data extraction tool. A first template is selected from a plurality of documents provided by a user. An OCR engine annotates the first template and at least one data region in the first template corresponding to a set of parameters required in a target template is identified by selecting a geometrical region on the first template. At least one interim template is created based on the identification, and the plurality of documents are analyzed using the interim template to extract data values in the data region. The documents are converted to a format compliant with the target template based on the analysis.

Abstract translation: 用于数据提取工具的模板创建的方法和系统。 从用户提供的多个文档中选择第一模板。 OCR引擎注释第一模板，并且通过选择第一模板上的几何区域来识别对应于目标模板中所需的一组参数的第一模板中的至少一个数据区域。 基于标识创建至少一个临时模板，并且使用临时模板分析多个文档以提取数据区域中的数据值。 基于分析，将文档转换为符合目标模板的格式。