公开(公告)号：US11163747B2

公开(公告)日：2021-11-02

申请号：US15588088

申请日：2017-05-05

Applicant: ServiceNow, Inc.

Inventor： Shayan Shahand ,  Aida Rikovic Tabak ,  Robert Ninness ,  Abhijith Thette Nagarajan ,  Prabhakaran Subramani Thandayuthapani

IPC: G06F16/23 ,  G06Q30/00 ,  G06Q30/02 ,  G06F11/30 ,  G06Q10/06 ,  G06F17/18 ,  G06Q10/04 ,  G06N20/00

Abstract: Time series data is generated and forecasted with a selected forecasting mechanism. Time series data to forecast including a plurality of data points is received. A count of the plurality of data points is determined to meet a threshold. Responsive to that determination, a plurality of test forecasts are generated with respective forecasting mechanisms of a plurality of forecasting mechanisms using a first subset of the plurality of data points. Errors are then determined for the respective forecasting mechanisms, such as based on comparisons of corresponding ones of the plurality of test forecasts and a second subset of the plurality of data points. One of the plurality of forecasting mechanisms is selected based on the errors. An output forecast is then generated with the selected forecasting mechanism using the first and second subsets of the plurality of data points.

公开(公告)号：US11238082B2

公开(公告)日：2022-02-01

申请号：US15729250

申请日：2017-10-10

Applicant: ServiceNow, Inc.

Inventor： Dileeshvar Radhakrishnan ,  Robert Ninness ,  Seth Stafford ,  Aida Rikovic Tabak ,  Shayan Shahand ,  Sumana Ravikrishnan ,  Abhijith Nagarajan ,  Prabhakaran Subramani Thandayuthapani ,  Marta Penzo ,  Ciprian Mocanu

IPC: G06F16/35 ,  G06F3/0482 ,  G06F40/103 ,  G06F40/174 ,  G06F40/205 ,  G06F40/247 ,  G06F40/284

Abstract: Systems, methods, and media are presented to analyze unstructured text. Unstructured data is retrieved from a user inputs or records. The user inputs include an incident report or a problem report. Text words in the unstructured data are identified. A number of occurrences of each text word is counted. The text words are displayed in a word cloud by displaying each of the text words with a size corresponding to the number of occurrences of the respective text word. A larger number of occurrences results in a larger size of the respective text word when displayed. At least one trendline for occurrences for a corresponding text word is also displayed.

公开(公告)号：US20190102455A1

公开(公告)日：2019-04-04

申请号：US15729250

申请日：2017-10-10

Applicant: ServiceNow, Inc.

Inventor： Dileeshvar Radhakrishnan ,  Robert Ninness ,  Seth Stafford ,  Aida Rikovic Tabak ,  Shayan Shahand ,  Sumana Ravikrishnan ,  Abhijith Nagarajan ,  Prabhakaran Subramani Thandayuthapani ,  Marta Penzo ,  Ciprian Mocanu

IPC: G06F17/30 ,  G06F17/27 ,  G06F3/0482

Abstract: Systems, methods, and media are presented to analyze unstructured text. Unstructured data is retrieved from a user inputs or records. The user inputs include an incident report or a problem report. Text words in the unstructured data are identified. A number of occurrences of each text word is counted. The text words are displayed in a word cloud by displaying each of the text words with a size corresponding to the number of occurrences of the respective text word. A larger number of occurrences results in a larger size of the respective text word when displayed. At least one trendline for occurrences for a corresponding text word is also displayed.

公开(公告)号：US20180322400A1

公开(公告)日：2018-11-08

申请号：US15588088

申请日：2017-05-05

Applicant: ServiceNow, Inc.

Inventor： Shayan Shahand ,  Aida Rikovic Tabak ,  Robert Ninness ,  Abhijith Thette Nagarajan ,  Prabhakaran Subramani Thandayuthapani

IPC: G06N5/04 ,  G06F17/30

CPC classification number: G06N5/04 ,  G06F17/30002

Abstract: Time series data is generated and forecasted with a selected forecasting mechanism. Time series data to forecast including a plurality of data points is received. A count of the plurality of data points is determined to meet a threshold. Responsive to that determination, a plurality of test forecasts are generated with respective forecasting mechanisms of a plurality of forecasting mechanisms using a first subset of the plurality of data points. Errors are then determined for the respective forecasting mechanisms, such as based on comparisons of corresponding ones of the plurality of test forecasts and a second subset of the plurality of data points. One of the plurality of forecasting mechanisms is selected based on the errors. An output forecast is then generated with the selected forecasting mechanism using the first and second subsets of the plurality of data points.