Category and Category Summary

Category and Category Summary

Overview

Understanding Category and Category summary

You can create separate email addresses and SMS campaigns for each queue and have the system route workitems based on the campaign they came into and this will do a good job. However this will not modify the routing of workitems that contain spam or were sent to the incorrect campaign

Categories use AI to route text based work items to the correct location on the first try. When workitems are routed to the correct location without any human intervention this increases user productivity and lowers queue and response times. For example if billing inquiries are automatically routed to the billing department there is no need for a technical support representative to read the message and then forward it on to the billing department. Spam workitems can be discarded without a user ever reading them.

In order to have the system route workitems based on the content you need to set up Categories and Category summaries

Category

A Category can be thought of as a classification. In other words everything in the category should be similar enough to be grouped together. Some examples could be spam, Tech Support, Billing etc Each work item that gets routed based on the Category should be able to be treated the same way. All spam can be discarded. All Tech support inquiries can be routed to the same tech support queue. All billing inquiries can be routed to the same billing queue. If you have 2 Tech Support queues (one for Windows and one for Apple products) then you will more than likely want to have 2 categories (Windows Tech Support and Apple Tech Support). The important thing is to create enough categories to meet your needs but not to create too many categories that get routed in the same way.

The Category you create needs to have a Name and a Description. The Name should be able to be easily understood by other Administrators and Users who will see this name when they classify the workitems they receive.

Category Summary

Category Summary is where you will upload examples of the text that will be used to train the AI (artificial intelligence). The AI will learn to distinguish and classify text within the work item based on the examples you provide. You will need to upload at least 200 examples for the AI to begin to learn. The more examples you provide should provide better results In addition to the examples you upload the system can continue to learn from real world work items that are received by your organization. When a user receives a workitem he can select a classification before setting the workitem disposition. The new examples can be used to continue to train the AI to make the classification of workitems more and more accurate over time.

Information
  • The Category you create needs to have a Name and a Description. The Name should be able to be easily understood by other Administrators.
Categories

In the Categories section you add all the categories you want the system to compare against.

for example. Tech support, Sales, Spam and None.

When a workitem is received the system will analyze the text in the workitem in order to classify the workitem into one of these 4 categories.

NOTE the AI can only match to the categories you have created and trained. There is no “None of the above” option. This is why it is important to create and train a “None” option so the system has a way to classify a workitem that does not match any of the other categories

  • To add a category select the plus symbol to the right of the Categories header. This will open a pop up window window will open with the list of categories that you have previously created choose one or more and select “OK”. This will add the Category to the list.
  • To remove a category, select the category you want to remove from the list. With the category highlighted select the garbage can symbol to the right of the Categories header. This will delete the Category from the list

Category Summary

In order to train the Category Summary you need to upload examples so the AI can learn. To upload examples you will need to create a CSV file. the CSV file needs to contain 2 columns. Column A needs to contain the Category Identifier of the Category that you wish to be trained Column B needs to contain the example text that will be used to train the AI

NOTE: To find the Category Identifier go to Category and select a category from the list view. Select edit to go to the detail view. On the detail view there is a field called “Identifier”. In that field you will find a string of letters and numbers. That is the category identifier

  • To upload the CSV file select the plus symbol to the right of the Category Summary header.This will open a pop up window that says “Add Examples” and has a field called “uploaded File” To the right of Uploaded File you will see a file icon. Select the file icon and a window will open. In this window navigate to the location of the CSV file on your computer or shared drive.choose the CSV file and select “OK”. This will bring you back to the “Add Examples” window. Select OK and the file will upload.
  • If all the Categories you have added in the Categories have at least 200 examples than you can select the “Start Training” button at the bottom left of the page. Training will take at least a few hours but time will vary based on the number of examples you have provided.
  • Once the Category Summary is trained you can begin to route workitems based on the Predict Category results in the Campaign workflow. (see article Setting up Categories in the Campaign workflow)

Click Here to Download Linked File

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.