公开(公告)号：US10949807B2

公开(公告)日：2021-03-16

申请号：US15674379

申请日：2017-08-10

Applicant: ServiceNow, Inc.

Inventor： Baskar Jayaraman ,  Debashish Chatterjee ,  Kannan Govindarajan ,  Aniruddha Thakur

IPC: G06N20/00 ,  G06Q10/10 ,  G06F40/174 ,  G06N5/04 ,  H04L29/08

Abstract: Systems and methods for using a mathematical model based on historical information to automatically schedule and monitor work flows are disclosed. Prediction methods that use some variables to predict unknown or future values of other variables may assist in reducing manual intervention when addressing incident reports or other task-based work items. For example, work items that are expected to conform to a supervised model built from historical customer information. Given a collection of records in a training set, each record contains a set of attributes with one of the attributes being the class. If a model can be found for the class attribute as a function of the values of the other attributes, then previously unseen records may be assigned a class as accurately as possible based on the model. A test data set is used to determine model accuracy prior to allowing general use of the model.

公开(公告)号：US20170262753A1

公开(公告)日：2017-09-14

申请号：US15444030

申请日：2017-02-27

Applicant: ServiceNow, Inc.

Inventor： Baskar Jayaraman ,  Debashish Chatterjee ,  Kanaan Govindarajan ,  Ganesh Rajan

IPC: G06N5/02

CPC classification number: G06N5/02

Abstract: The present invention envisages a system and method for automating the generation of business decision analytic models. The system uses a plurality of predictor variables stored in a plurality of data sets, to automatically create a business decision analytic model. The system includes a processor configured to process the data sets and determine the total number of records present in each of the data sets and the number of columns containing only numerical values. The processor selects a column containing only numerical values, from a dataset under consideration, and counts the number of unique numerical values in the selected column, and the total number of records present in the selected column. The two counts are compared and the selected column is transformed using a non-linear transformation to obtain a column of transformed values. The transformed values and corresponding time stamps are utilized for the purpose of model generation.

公开(公告)号：US10671926B2

公开(公告)日：2020-06-02

申请号：US15405041

申请日：2017-01-12

Applicant: SERVICENOW, INC.

Inventor： Baskar Jayaraman ,  Debashish Chatterjee ,  Kannan Govindarajan ,  Ganesh Rajan

IPC: G06N5/02 ,  G06F16/22 ,  G06N20/00

Abstract: A computer implemented system for automating the generation of an analytic model includes a processor configured to process a plurality of data sets. Each data set includes values for a plurality of variables. A time-stamping module is configured to derive values for a plurality of elapsed-time variables for each data set, and the plurality of variables and plurality of elapsed-time variables are included in a plurality of model variables. A model generator is configured to create a plurality of comparison analytic models each based on a different subset of model variables. Each comparison analytic model is configured to operate on new data sets associated with current opportunities, and to output a likelihood of successfully closing each current opportunity. A model testing module is configured to select an operational analytic model from among the comparison analytic models based on a quality metric.

公开(公告)号：US20180322462A1

公开(公告)日：2018-11-08

申请号：US15674379

申请日：2017-08-10

Applicant: ServiceNow, Inc.

Inventor： Baskar Jayaraman ,  Debashish Chatterjee ,  Kannan Govindarajan ,  Aniruddha Thakur

IPC: G06Q10/10 ,  G06N99/00 ,  G06N5/04 ,  H04L29/08

CPC classification number: G06Q10/103 ,  G06F17/243

Abstract: Systems and methods for using a mathematical model based on historical information to automatically schedule and monitor work flows are disclosed. Prediction methods that use some variables to predict unknown or future values of other variables may assist in reducing manual intervention when addressing incident reports or other task-based work items. For example, work items that are expected to conform to a supervised model built from historical customer information. Given a collection of records in a training set, each record contains a set of attributes with one of the attributes being the class. If a model can be found for the class attribute as a function of the values of the other attributes, then previously unseen records may be assigned a class as accurately as possible based on the model. A test data set is used to determine model accuracy prior to allowing general use of the model.

公开(公告)号：US10719767B2

公开(公告)日：2020-07-21

申请号：US15444030

申请日：2017-02-27

Applicant: ServiceNow, Inc.

Inventor： Baskar Jayaraman ,  Debashish Chatterjee ,  Kanaan Govindarajan ,  Ganesh Rajan

IPC: G06N5/02

Abstract: The present invention envisages a system and method for automating the generation of business decision analytic models. The system uses a plurality of predictor variables stored in a plurality of data sets, to automatically create a business decision analytic model. The system includes a processor configured to process the data sets and determine the total number of records present in each of the data sets and the number of columns containing only numerical values. The processor selects a column containing only numerical values, from a dataset under consideration, and counts the number of unique numerical values in the selected column, and the total number of records present in the selected column. The two counts are compared and the selected column is transformed using a non-linear transformation to obtain a column of transformed values. The transformed values and corresponding time stamps are utilized for the purpose of model generation.

公开(公告)号：US10706359B2

公开(公告)日：2020-07-07

申请号：US15405076

申请日：2017-01-12

Applicant: SERVICENOW INC.

Inventor： Baskar Jayaraman ,  Debashish Chatterjee ,  Kannan Govindarajan ,  Ganesh Rajan

IPC: G06N5/02 ,  G06F16/22 ,  G06N20/00

Abstract: A computer implemented system for automating the generation of an analytic model includes a processor configured to process a plurality of data sets. Each data set includes values for a plurality of variables. A time-stamping module is configured to derive values for a plurality of elapsed-time variables for each data set, and the plurality of variables and plurality of elapsed-time variables are included in a plurality of model variables. A model generator is configured to create a plurality of comparison analytic models each based on a different subset of model variables. Each comparison analytic model is configured to operate on new data sets associated with current leads, and to output a likelihood of successfully closing an associated transaction. A model testing module is configured to select an operational analytic model from among the comparison analytic models based on a quality metric.