Automation discovery platform

Patent metadata

Field	Value
Publication number	US-12498945-B2
Application number	US-202318368407-A
Country	US
Kind code	B2
Filing date	Sep 14, 2023
Priority date	Sep 14, 2023
Publication date	Dec 16, 2025
Grant date	Dec 16, 2025

Abstract

In various embodiments, a process for providing an automation discovery platform includes obtaining training data indicating conversation utterances and labels that are associated with the conversation utterances, where each of the labels of at least a subset of the labels corresponds to a virtual agent automation topic. The process includes obtaining a language machine learning model, where the language machine learning model has been trained to a first trained state using unlabeled data. The process includes updating the language machine learning model from the first trained state to a second trained state by applying the training data to the language machine learning model, where updating the language machine learning model includes generating an automation discovery model configured to provide outputs corresponding to virtual agent automation opportunities.

First claim

What is claimed is:

1 . A method, comprising:
obtaining training data indicating conversation utterances and labels that are associated with the conversation utterances, wherein each of the labels of at least a subset of the labels corresponds to a virtual agent automation topic; obtaining a language machine learning model, wherein the language machine learning model has been trained to a first trained state using unlabeled data; updating the language machine learning model from the first trained state to a second trained state by applying the training data to the language machine learning model, wherein updating the language machine learning model includes generating an automation discovery model configured to provide outputs corresponding to virtual agent automation opportunities; providing an incident description of an incident record to the automation discovery model; and suggesting a virtual agent automation opportunity based on a result of the automation discovery model in response to the incident description.

2 . The method of claim 1 , wherein the training data indicating the conversation utterances and the labels that are associated with the conversation utterances include at least one of: an application log, a chat conversation, an incident table, or a human resources (HR) case table.

3 . The method of claim 1 , wherein the training data is user-specific and includes data different from the unlabeled data with which the language machine learning model is trained.

4 . The method of claim 1 , wherein at least one of the virtual agent automation opportunities includes utilization of a machine learning based tool.

5 . The method of claim 4 , further comprising determining a quantitative assessment of using the machine learning based tool, wherein suggesting the virtual agent automation opportunity includes providing the quantitative assessment.

6 . The method of claim 5 , wherein:
at least one of the virtual agent automation opportunities includes at least one use case specific to a user; and the quantitative assessment of using the machine learning based tool includes potential time savings associated with the at least one use case.

7 . The method of claim 1 , wherein each of the labels corresponds to a natural language intent.

8 . The method of claim 1 , further comprising performing language detection on the training data.

9 . The method of claim 1 , further comprising generating another automation discovery model, wherein the automation discovery model is associated with a first virtual agent automation opportunity and the other automation discovery model is associated with a second virtual agent automation opportunity.

10 . The method of claim 1 , further comprising identifying at least one cluster of data from a set of unclassified data, wherein the unclassified data are unclassified with respect to the outputs corresponding to the virtual agent automation opportunities.

11 . The method of claim 10 , further comprising determining analytical information associated with the at least one cluster and providing the at least one cluster of data and the analytical information.

12 . The method of claim 10 , further comprising adding another virtual agent automation topic based at least on the at least one cluster of data.

13 . The method of claim 1 , further comprising pre-processing the training data by at least one of: cleaning the training data, applying de-duplication to the training data, measuring at least one statistic with respect to the training data, or removing small punctuation in the training data.

14 . The method of claim 1 , wherein at least one of the virtual agent automation opportunities is included in a discovery report.

15 . The method of claim 14 , wherein the discovery report includes a plurality of virtual agent automation opportunities.

16 . The method of claim 14 , wherein the discovery report is provided in a graphical user interface.

17 . A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
obtaining training data indicating conversation utterances and labels that are associated with the conversation utterances, wherein each of the labels of at least a subset of the labels corresponds to a virtual agent automation topic; obtaining a language machine learning model, wherein the language machine learning model has been trained to a first trained state using unlabeled data; updating the language machine learning model from the first trained state to a second trained state by applying the training data to the language machine learning model, wherein updating the language machine learning model includes generating an automation discovery model configured to provide outputs corresponding to virtual agent automation opportunities; and identifying at least one cluster of data from a set of unclassified data, wherein the unclassified data are unclassified with respect to the outputs corresponding to the virtual agent automation opportunities.

18 . The computer program product of claim 17 , further comprising:
determining analytical information associated with the at least one cluster and providing the at least one cluster of data and the analytical information.

19 . The computer program product of claim 17 , further comprising:
providing an incident description of an incident record to the automation discovery model; and suggesting a virtual agent automation opportunity based on a result of the automation discovery model in response to the incident description.

20 . A method comprising:
providing, to an automation discovery model, an incident description of an incident record, wherein a language machine learning model was trained to a first trained state using unlabeled data, wherein the language machine learning model was updated from the first trained state to a second trained state by applying labeled data to the language machine learning model, wherein data of the labeled data relate to conversation utterances, wherein labels of the labeled data relate to virtual agent automation topics associated with the conversation utterances, and wherein updating the language machine learning model includes generating the automation discovery model configured to provide outputs corresponding to virtual agent automation opportunities; and receiving, from the automation discovery model, a suggestion of a virtual agent automation opportunity based on a result of the automation discovery model in response to the incident description.

21 . The method of claim 20 , wherein the labeled data includes data different from the unlabeled data.

22 . The method of claim 20 , wherein at least one of the virtual agent automation opportunities includes utilization of a machine learning based tool, and wherein suggesting the virtual agent automation opportunity includes providing a quantitative assessment of using the machine learning based tool.

Assignees

• Servicenow Inc

Inventors

• Ryan Patrick
• Mahalingam Aparna
• Narendula Rammohan
• Nivarthi Phani

Classifications

• G06F40/40

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F9/453 Primary

  Help systems · CPC title