Contextual communication and service interface

Patent metadata

Field	Value
Publication number	US-10740568-B2
Application number	US-201815879259-A
Country	US
Kind code	B2
Filing date	Jan 24, 2018
Priority date	Jan 24, 2018
Publication date	Aug 11, 2020
Grant date	Aug 11, 2020

Abstract

An example embodiment may involve obtaining an incident record relating to a user. The embodiment may also involve generating and providing, for display on a graphical user interface, a single window including a dialog region, an incident record region, and a suggestion region. The embodiment may also involve determining candidate messages by incorporating components of the incident record into predetermined message templates. The embodiment may also involve determining a scoring for the candidate messages based on a relevance to a conversation between the user and an agent. The embodiment may also involve based on the scoring, selecting one or more of the candidate messages to include in a set of suggested messages displayed in the suggestion region. The embodiment may also involve receiving input from the agent selecting one of the suggested messages, and then responsively displaying the selected suggested message as part of the conversation in the dialog region.

First claim

What is claimed is:

1. A system disposed within a computational instance of a remote network management platform that remotely manages a managed network, the system comprising:
a database containing representations of incident records relating to users associated with the managed network; and
a computing device configured to:
obtain, from the database, an incident record relating to a user;
generate and provide, for display on a graphical user interface, a single window of the graphical user interface, the single window including:
a dialog region including: a first location for displaying a conversation between the user and an agent, and a second location for entering a message to be added to the conversation,
an incident record region including the incident record, wherein components of the incident record contain at least one of an identifier of the user, an incident status, and an incident description, and
a suggestion region for displaying a set of suggested messages for use by the agent to add to the conversation;

determine a plurality of candidate messages by incorporating the components of the incident record into predetermined message templates, wherein the predetermined message templates include sentence fragments and define fields in which to incorporate the components;
determine a confidence scoring for the plurality of candidate messages based on a relevance to messages from the conversation, wherein the confidence scoring is based at least in part on feedback from one or more previous conversations associated with the user;
based on the confidence scoring, select one or more of the plurality of candidate messages to include in the set of suggested messages displayed in the suggestion region;
receive, by way of the graphical user interface, input from the agent selecting one of the set of suggested messages to be added to the conversation; and
in response to receiving the input, provide, for display on the graphical user interface, the selected suggested message as part of the conversation in the first location of the dialog region.

2. The system of claim 1 , wherein the computing device is further configured to:
obtain, from the database, a past incident record and a past conversation related to the past incident record;
make a comparison of the incident record and the past incident record; and
in response to the comparison indicating that at least one component of the incident record is identical to a corresponding component of the past incident record, determine one or more candidate messages of the plurality of candidate messages based on one or more messages from the past conversation.

3. The system of claim 1 , wherein the feedback comprises a historical data set of previous inputs received from agents, wherein the computing device is further configured to:
store the previous inputs, the previous inputs indicating agent feedback related to past suggested messages; and
determine the confidence scoring for the plurality of candidate messages further based on the historical data set of the previous inputs.

4. The system of claim 1 , wherein the feedback comprises a historical data set of previous messages received from users, wherein the computing device is further configured to:
store the previous messages, the previous messages indicating user feedback related to past suggested messages; and
determine the confidence scoring for the plurality of candidate messages further based on the historical data set of the previous messages.

5. The system of claim 1 , wherein selecting one or more of the plurality of candidate messages to include in the set of suggested messages displayed in the suggestion region based on the confidence scoring comprises:
selecting one or more of the plurality of candidate messages to include in the set of suggested messages displayed in the suggestion region based on the selected one or more candidate messages having confidence scores that meet or exceed a predefined threshold confidence score.

6. The system of claim 1 , wherein the computing device is further configured to:
before providing the selected suggested message for display on the graphical user interface as part of the conversation in the first location of the dialog region, receive, by way of the graphical user interface, input from the agent making a modification to the selected suggested message, wherein providing the selected suggested message for display on the graphical user interface as part of the conversation in the first location of the dialog region is performed further in response to receiving the input modifying the selected suggested message and comprises providing the modified selected suggested message for display on the graphical user interface as part of the conversation in the first location of the dialog region.

7. The system of claim 6 , wherein the computing device is further configured to:
based on the input from the agent modifying the selected suggested message, determine a new message template that includes the modification to the selected suggested message.

8. The system of claim 6 , wherein the computing device is further configured to:
based on the input from the agent modifying the selected suggested message, update a predetermined message template corresponding to the selected suggested message to include the modification to the selected suggested message.

9. The system of claim 1 , wherein the computing device is further configured to:
provide for display, on the graphical user interface, in the incident record region, selectable graphical user interface elements corresponding to the components of the incident record;
receive, by way of the graphical user interface, input from the agent selecting one or more of the graphical user interface elements; and
in response to receiving the input selecting one or more of the graphical user interface elements, provide for display, on the graphical user interface, in the second location of the dialog region, components of the incident record corresponding to the selected one or more graphical user interface elements as part of a message to be added to the conversation.

10. The system of claim 9 , wherein the input from the agent selecting one or more of the graphical user interface elements comprises a click-and-drag input moving the selected one or more of the graphical user interface elements from the incident record region to the second location of the dialog region.

11. The system of claim 1 , wherein the computing device is further configured to:
while the conversation between the agent and the user is ongoing:
perform natural language processing on one or more of the messages from the conversation; and
based on the natural language processing, update the incident record based on contextual information derived from the one or more messages.

12. The system of claim 11 , wherein the components of the incident record further contain an incident priority level, wherein the natural language processing includes a sentiment analysis, and wherein updating the incident record comprises updating the incident priority level based on the sentiment analysis.

13. The system of claim 1 , wherein determining the confidence scoring for the plurality of candidate messages comprises determining an individual confidence scoring for each candidate message of the plurality of candidate messages.

14. A computer-implemented method comprising:
obtaining, from a database containing representations of incident records relating to users associated with a managed network remotely managed by a remote network management platform, an incident record rela

Assignees

• Servicenow Inc

Inventors

• Azmoon Troy

Classifications

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q30/016

  After-sales · CPC title

• H04M3/5133

  Operator terminal details · CPC title

• G06Q10/20

  Administration of product repair or maintenance · CPC title