Virtual Agent - How do you read/report against input(s) within a conversation message record?

[Adam Beutnagel]

Looking for any direction or information with folks if you have been successful with my inquiry below. 

How do you read/report against input(s) within a conversation message record? I could not find any ServiceNow documentation to answer my question.

The data stored under (sys_cs_message) is not very read friendly to quickly find what you are looking for.

For Example, we want to know the # of times a specific input was used and break down of the values selected within a given topic. 

Example #2 List results of query strings used on a KB search within the topic.

I found a previous topic that was similar, has anyone been successful with this so far? Are you using tools such as a JSON Parser Online? 

[Brandon Barret1 · Accepted solution]

So first, let me make sure I understand what you are trying to do: create a report based on navigation patterns and string/other variable inputs from the user during conversations in Virtual Agent? That's actually a really interesting question. 

Doing a bit of digging, the Virtual Agent Dashboard comes up, and notes "administrators can monitor user engagement with the virtual agent to understand topic usage." This is great, but the functionality seems aimed at topic choices, unique users, and monthly users per channel. You've probably read over this, and want something a bit more specific based on navigation and user input, if I understand correctly. 

Next, I found Virtual Agent Scripts, which allows you to store user input in variables:

https://docs.servicenow.com/bundle/newyork-performance-analytics-and-reporting/page/administer/virtu...

Okay, this seems to be getting closer but is still mainly aimed at topic control and analytics related to topic choices.

Next, I read over the Virtual Agent Plugin docs, which once activated, gives you a wider array of choices with which to manipulate data, but still nothing in the realm of what you want to do. Your question seems like one that should be simple to answer...yet I am not seeing it.

I have no experience doing this, but I guess I don't see any reason why you couldn't store the input as variables via script and use maybe a JSON parser to get and analyze variable results and create lists/reports. The path to getting those values can be ugly, however:

https://community.servicenow.com/community?id=community_question&sys_id=6415be76dbe7ef409540e15b8a96...

This is a very interesting question, and hopefully it has an easy answer. I hope you find it. 

Cheers

[Adam Beutnagel]

Thanks Brandon for responding to my post; I'm hoping in future releases they can build or integrate such capability. The OOTB PA for Virtual Agent Overview is limited with the data it can provide. 

In some workflows we are creating a record for every interaction that can give us some of the data our customers are looking for. 

[pawlak_poz1]

Wow 3 months already and still no additional answer. In my case my very first question was whether VA could learn itself. E.G. Learn new utterances basing on cusotmer selections. I think I know the answer but OK - it's just the beginning. So if we don't have an automated way of doing it is there a way to walkthrough the conversations and at least manually collect the new ones. IU am wondering @Adam Beutnagel whether you've had some good luck with @Brandon Barrett - CloudPires answer.

Especially with the part about variables usage?

Cheers!

[NAKUL A R2]

Recently attend a PEAK session on VA and got to know VA cannot learn itself.

No Machine learning capability so far added in VA