Skip to main content

AI Similarity

This page enables to perform configurations based on which similar Incident, Problem, Change, and Suggested KB can be identified and displayed while creating tickets.

Also, the similarity score can be configured that decides and displays the list of similar requests, problems, changes, and knowledge while creating a ticket. It consists of two tabs:

  • AI Similarity Configurations: Enables the selection of modules and embedding models to determine how similar tickets are identified. It also allows configuring the minimum similarity score and the number of results to be displayed.
  • Embedding Parameters Configurations: Defines the fields whose input will be embedded for similarity matching. By default, Subject and Description are pre-selected. The available modules depend on the selections made in the AI Similarity Configurations tab. For example, if the Request and Problem modules are selected, they will also appear in the Embedding Parameters Configurations tab.

AI Similarity Configurations​

To configure AI Similarity,

  1. Enable the functionality. By default, it is disabled.

Once enabled the following parameters will be available.

  1. Enter the below details:
  • Module: Select the module for whom you want to view the similar tickets.
  • Embedding Model: Select the embedding model from the dropdown. The option appears only of configured in the AI models tab.
  • Min. Similarity Score: It is the minimum vector score that should match while identifying the similar items. The value must be from 0.00 to 1.
  • Maximum Number of Result: Enter the maximum number of results to appear. For example, if 10 is set, the system will search and display the top 10 similar tickets by comparing the vector embedding of user input and available data vectors.
  1. Once done, click Update, and the following features will appear.
  • Refresh: Click to refresh the embeddings.
  • Regenerate Embeddings: Click to regenerate the embeddings based on the configurations done. It is recommended to generate the embeddings whenever any changes are done in the configurations. Once generated its logs will appear in the View Embedding logs.

  • View Embedding Logs: Logs display the status of the embeddings generated along with their details like module, user, embedding model, status, Embedding Generation Date, and Remarks. If failed, the reason will be displayed in the remarks column.

Embedding Parameters Configurations​

This tab allows you to select fields for each module to identify similar tickets and knowledge base (KB) articles. By default, Subject and Description are pre-selected fields for all modules and cannot be removed. In addition to these, you can choose Custom Fields for embedding.

note
  • Embedding will be applied only to the selected fields.
  • The available modules depend on the selections made in the AI Similarity Configurations tab.

Once done, click Update.

Now, when you create a ticket (Request, Problem, or Change), based on configurations, you will find the Similar items on the right-hand side of the page as shown below.

Also, on the Details page of the ticket you can view the "Similar Tickets" and perform the required bulk operations on them.