Model building architecture and smart routing of work items

Patent metadata

Field	Value
Publication number	US-10949807-B2
Application number	US-201715674379-A
Country	US
Kind code	B2
Filing date	Aug 10, 2017
Priority date	May 4, 2017
Publication date	Mar 16, 2021
Grant date	Mar 16, 2021

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.

First claim

What is claimed is:

1. A cloud-based computer system, comprising:
a memory partition; and
one or more network interfaces communicatively coupled to one or more processing units and to the memory partition;
wherein the memory partition comprises computer instructions that when executed by the one or more processing units cause the cloud-based computer system to provide at least one customer instance and a shared machine learning service,
wherein the at least one customer instance is communicatively coupled, via the one or more network interfaces, to a remotely executing client application and the at least one computer instance is configured to:
receive information defining one or more parameters regarding historical data pertaining to one or more completed incident reports; and
provide at least a portion of the obtained information to the shared machine learning service; and

wherein the shared machine learning service is configured to:
receive historical data from the at least one customer instance representing respective attributes of a set of resolved historical incident reports, the historical data comprising both structured and unstructured data values;
process the structured data values to create a first mathematical representation of attributes defined by the structured data;
parse the unstructured data to create generated structured data;
process the generated structured data to create a second mathematical representation of terms; and
analyze the first mathematical representation and the second mathematical representation to create a model sufficient to determine one or more attributes of a newly created incident report;

wherein the at least one computer instance is configured to apply the model to natural language text of the newly created incident report to automatically complete one or more incomplete input fields in the newly created incident report with the one or more attributes.

2. The cloud-based computer system of claim 1 , wherein the shared machine learning service is configured to include a machine learning scheduler configured to receive respective requests from at least two customer instances and invoke at least two machine learning trainer instances configured to execute independently and concurrently.

3. The cloud-based computer system of claim 1 , wherein each machine learning trainer instance of the at least two machine learning trainer instances purges the historical data after creation of a first model and prior to obtaining additional historical data for a second model.

4. The cloud-based computer system of claim 1 , wherein the shared machine learning service is configured to retrain the model based on one or more changes to previously predicted attributes of incident reports.

5. The cloud-based computer system of claim 1 , wherein the shared machine learning service is configured to:
partition the historical data to create at least a preparation dataset and a separate test dataset prior to creating the model;
create the model using the preparation dataset; and
test the model using the test dataset.

6. The cloud-based computer system of claim 1 , wherein the shared machine learning service is configured to publish the model to the at least one customer instance.

7. The cloud-based computer system of claim 6 , wherein the shared machine learning service is configured to schedule a machine learning trainer instance based on a geographical location associated with the at least one customer instance.

8. The cloud-based computer system of claim 1 , wherein the shared machine learning service is configured to be idempotent.

9. The cloud-based computer system of claim 1 , wherein the shared machine learning service is configured to provide restartable training and prediction functions.

10. The cloud-based computer system of claim 1 , wherein the shared machine learning service and the at least one customer instance are configured for full instance redundancy.

11. The cloud-based computer system of claim 1 , wherein the shared machine learning service is configured to provide a training feature utilizing a first portion of cloud infrastructure and a prediction feature utilizing a second portion of the cloud infrastructure, wherein the first portion and second portion maintain independence from each other.

12. A method of creating a model based on historical incident report data, the method comprising:
receiving a request, at a shared machine learning service executing in a cloud-based architecture, to schedule creation of the model for a first customer instance;
invoking a machine learning training instance associated with the shared machine learning service;
providing historical data obtained from the first customer instance to the machine learning training instance, the historical data representing respective attributes of a set of resolved historical incident reports, the historical data comprising both structured and unstructured data values;
processing the structured data values to create a first mathematical representation of attributes defined by the structured data;
parse the unstructured data to create generated structured data;
process the generated structured data to create a second mathematical representation of terms; and
analyze the first mathematical representation and the second mathematical representation to create the model sufficient to determine one or more attributes of a newly created incident report;
wherein the first customer instance is configured to apply the model to natural language text of the newly created incident report to automatically complete one or more incomplete input fields in the newly created incident report with the one or more attributes.

13. The method of claim 12 , wherein the historical data comprises data obtained from the first customer instance over a defined time frame.

14. The method of claim 12 , wherein parsing the unstructured data to create generated structured data comprises removing junk characters or redundant information from the unstructured data.

15. The method of claim 12 , wherein parsing the unstructured data to create generated structured data comprises adjusting different references to a common item in the unstructured data to a consistent reference to the common item.

Assignees

• Servicenow Inc

Inventors

• Jayaraman Baskar
• Chatterjee Debashish
• Govindarajan Kannan
• Thakur Aniruddha

Classifications

• G06Q10/103 Primary

  Workflow collaboration or project management · CPC title

• H04L67/10

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title

• G06F40/174

  Form filling; Merging · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06N20/00

  Machine learning · CPC title