Intelligent automation of self service product identification and delivery

Patent metadata

Field	Value
Publication number	US-11514458-B2
Application number	US-201916601445-A
Country	US
Kind code	B2
Filing date	Oct 14, 2019
Priority date	Oct 14, 2019
Publication date	Nov 29, 2022
Grant date	Nov 29, 2022

Abstract

Embodiments for implementing intelligent automation of opportunity transaction workflows by a processor. One or more tasks identified in an existing transaction opportunity workflow suitable for automation may be automated in a current transaction opportunity workflow. The automated tasks may be scheduled and executed in the current transaction opportunity workflow. The automated tasks in the current transaction opportunity workflow may be monitored.

First claim

The invention claimed is:

1. A method for implementing intelligent automation of opportunity transaction workflows by a processor, comprising:
receiving data representative of product information and historical transaction opportunity data relating to one or more transaction opportunities for an entity;
training, in a machine learning operation, a classifier to identify those of a plurality of tasks associated with a workflow of the one or more transaction opportunities suitable for automation, wherein the training of the classifier includes performing a pattern mining operation on the data to extract sequence patterns of performed tasks to learn and classify those of the plurality of tasks capable of being automated, and wherein the learning and classifying those of the plurality of tasks capable of being automated includes assigning a confidence score to each of a plurality of sub-tasks of each of the plurality of tasks, the confidence score representative of a plurality of features indicative of whether each of the plurality of sub-tasks is capable of automation;
automating, in a current transaction opportunity workflow, those of the plurality of tasks identified in an existing transaction opportunity workflow suitable for automation;
monitoring the plurality of tasks automated in the current transaction opportunity workflow, inclusive of monitoring a win probability of the one or more transaction opportunities based on a performance of the plurality of tasks automated in the current transaction opportunity workflow, wherein the monitoring generates feedback data utilized to iteratively enhance accuracy of the machine learning operation;
identifying one or more anomalies during execution of the plurality of tasks automated in the current transaction opportunity workflow, wherein the identifying of the one or more anomalies includes determining those of the plurality of sub-tasks which require human action to complete and are incapable of being automated, and wherein the identifying of the one or more anomalies includes detecting a decrease in the win probability based on the performance of the plurality of tasks; and
triggering a notification upon identification of the one or more anomalies describing the human action requisite to perform those of the plurality of sub-tasks, wherein subsequent to identifying the human action is complete, automation of executing a remainder of the plurality of sub-tasks of those of the plurality of tasks in the current transaction opportunity workflow is recommenced.

2. The method of claim 1 , wherein learning and classifying those of the plurality of tasks capable of being automated for the current transaction opportunity workflow includes determining those of the plurality of tasks in an identified transaction opportunity.

3. The method of claim 1 , further including automatically replicating those of the plurality of tasks in the current transaction opportunity workflow.

4. The method of claim 1 , further including scheduling and executing those of the plurality of tasks automated in the current transaction opportunity workflow.

5. The method of claim 1 , further including testing and evaluating performance of those of the plurality of tasks automated in the current transaction opportunity workflow, wherein an interactive graphical user interface (“GUI”) enables a user to assist with testing and evaluating.

6. A system for intelligent automation of opportunity transaction workflows, comprising:
one or more computers with executable instructions that when executed cause the system to:
receive data representative of product information and historical transaction opportunity data relating to one or more transaction opportunities for an entity;
train, in a machine learning operation, a classifier to identify those of a plurality of tasks associated with a workflow of the one or more transaction opportunities suitable for automation, wherein the training of the classifier includes performing a pattern mining operation on the data to extract sequence patterns of performed tasks to learn and classify those of the plurality of tasks capable of being automated, and wherein the learning and classifying those of the plurality of tasks capable of being automated includes assigning a confidence score to each of a plurality of sub-tasks of each of the plurality of tasks, the confidence score representative of a plurality of features indicative of whether each of the plurality of sub-tasks is capable of automation;
automate, in a current transaction opportunity workflow, those of the plurality of tasks identified in an existing transaction opportunity workflow suitable for automation;
monitor the plurality of tasks automated in the current transaction opportunity workflow, inclusive of monitoring a win probability of the one or more transaction opportunities based on a performance of the plurality of tasks automated in the current transaction opportunity workflow, wherein the monitoring generates feedback data utilized to iteratively enhance accuracy of the machine learning operation;
identify one or more anomalies during execution of the plurality of tasks automated in the current transaction opportunity workflow, wherein the identifying of the one or more anomalies includes determining those of the plurality of sub-tasks which require human action to complete and are incapable of being automated, and wherein the identifying of the one or more anomalies includes detecting a decrease in the win probability based on the performance of the plurality of tasks; and
trigger a notification upon identification of the one or more anomalies describing the human action requisite to perform those of the plurality of sub-tasks, wherein subsequent to identifying the human action is complete, automation of executing a remainder of the plurality of sub-tasks of those of the plurality of tasks in the current transaction opportunity workflow is recommenced.

7. The system of claim 6 , wherein learning and classifying those of the plurality of tasks capable of being automated for the current transaction opportunity workflow includes determining those of the plurality of tasks in an identified transaction opportunity.

8. The system of claim 6 , wherein the executable instructions automatically replicate those of the plurality of tasks in the current transaction opportunity workflow.

9. The system of claim 6 , wherein the executable instructions schedule and execute those of the plurality of tasks automated in the current transaction opportunity workflow.

10. The system of claim 6 , wherein the executable instructions test and evaluate performance of those of the plurality of tasks automated in the current transaction opportunity workflow, wherein an interactive graphical user interface (“GUI”) enables a user to assist with testing and evaluating.

11. A computer program product for intelligent automation of opportunity transaction workflows by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that receives data representative of product information and historical transaction opportunity data relating to one or more transaction opportunities for an entity;
an executable portion that trains, in a machine learning operation, a classifier to identify those of a plurality of tasks associated with a workflow of the one or more transaction opportunities suitable for automation, wherein the training of the classifier includes performing a pattern mining operation on the data to extract sequence patterns of perform

Assignees

• IBM

Inventors

• Chen Bei
• Botea Adi
• Daly Elizabeth
• Alkan Oznur
• Vejsbjerg Inge
• Mattetti Massimiliano

Classifications

• G06Q20/405 Primary

  Establishing or using transaction specific rules · CPC title

• G06Q20/386

  using messaging services or messaging apps (using mobile network messaging services for payment, e.g. SMS G06Q20/3255) · CPC title

• G06Q20/12

  specially adapted for electronic shopping systems · CPC title

• G06Q10/06316 Primary

  Sequencing of tasks or work · CPC title

• G06Q20/105

  involving programming of a portable memory device, e.g. IC cards, "electronic purses" · CPC title