---
sourceDocument: Australia IT Operations Management
sourceDocumentLink: https://www.servicenow.com/docs/r/australia/it-operations-management

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia IT Operations Management

ft:clusterId :

    - itom

bundleId :

    - itom

workflow :

    - Technology


---

# Similarity solutions

# Similarity solutions {#ariaid-title1}

Release version: Australia  
Updated March 12, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read
Summarize  
![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI  
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.  

## Summary of Similarity solutions

Similarity solutions in ServiceNow use Machine Learning (ML) to compare text between resolved and open alert records.
This comparison helps you identify and reuse resolution approaches from similar past alerts, improving efficiency in handling new incidents.
Show full answer Show less  

## Training a similarity solution

To train a similarity solution, you compile a collection of words from key alert fields---such as **Short Description** , **Description** , **Source** , **Type** , **Resource** , and **Metric Name**---from resolved alerts. ML uses this collection to find matches with open alerts, suggesting resolutions based on similar past cases.

* Your filter must return at least one record to proceed with training; ideally, you should use between 30,000 and 300,000 authentic and relevant records.
* If you exceed 300,000 records, only the most recent 300,000 are used.
* Keep training data current by avoiding hard-coded dates; instead, use relative date filters like the last 3, 6, or 12 months to ensure ongoing relevance.
* Training can be repeated as needed until the solution meets your similarity accuracy requirements.

## Fields to include

Select fields that contain meaningful words and phrases to help identify similar records. Ensure these fields are relevant to the current state of the records---for example, do not select fields like **Close note** if you are comparing open incident records, as those fields will not be populated.

## Similarity score and threshold

The system generates a similarity score from 0 to 100 indicating how closely two alert records match. You can set a threshold score to control which records are considered similar enough to suggest resolution reuse. Use the **Show training progress** feature to review example matches and their scores, then adjust the threshold accordingly to balance precision and recall.

## Training progress and duration

Training duration depends on the volume and complexity of your data; for example, 100,000 records with several hundred classes may take about five hours. During training, the system performs these steps:

* **Fetching files:** Downloads training records and sends them to the nearest training service.
* **Preparing data:** Removes duplicate records from the training set.
* **Training:** The training service builds the ML model.
* **Uploading:** The trained model is uploaded back into the system as attachments.

You can monitor this process through the **Show training progress** option on the Solutions page to understand the current training status and outcomes.  
Similarity solutions enable you to use Machine Learning (ML) to compare the text in a
resolved alert record to an open alert record to reuse its resolution approach.

## Training a similarity solution {#word-collection-similarity-solution__section_pcm_pt4_qhb}

To train a similarity solution, you collect words to compile a collection. Machine
Learning (ML) uses the collection to compare text in the Short Description,
Description, Source, Type,
Resource, and Metric Name fields in a resolved
alert. ML checks whether the words in the set match words in an open alert. The resolved alert,
which is similar to an open alert, provides an example to show how the open alert can be
resolved.  
To train a solution, the filter must return at least one record. If your filter returns no records, update it.  
Note:  
The preferred number of records for training a solution is between 30,000 records and 300,000. If you submit more than 300,000 records, the most recent 300,000 records are used to train the solution. Use only authentic records from the database.  
* Ensure that the records you train are not too old and that they are relevant to your business needs. Keep the words in the collection current.
* Do not use hard-coded dates as filters because these filters are not updated when you retrain solutions unless you update them manually before every retraining. Instead, use relative date filters, for example, the last 3 months, last 6 months, or last 12 months.
* Perform training as needed until it provides an acceptable similarity solution. This practice provides you time to review and update your solution definition.
{#word-collection-similarity-solution__ul_wnv_wzl_shb}

For more information on similarity solution concept, see [Create and train a similarity solution](https://www.servicenow.com/docs/access?context=create-similarity-solution&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).

## Fields to include in the solution {#word-collection-similarity-solution__section_j1n_d54_qhb}

Record the fields that are likely to contain words and phrases that help the system identify
similar records for your solution.

The similarity fields that you select should be a subset of your input field selections. For
example, if you select fields from incident records that are in Open state, do not select
Close note as a similarity field. Because open records do not include
Close note fields, the text cannot be similar.

The similarity fields are available to users when they create records.

## About the similarity score {#word-collection-similarity-solution__section_s2n_vfp_qhb}

The similarity score is a measure from 0-100 of the degree of similarity between two alert
records. Alert records that have a similarity score higher than the threshold that you specify
is returned by the solution.

Review similarity examples and their scores using the Show training progress feature to determine whether to either increase or decrease the solution
threshold. You can change the threshold value in the Threshold for Similarity Score field.

## View training solution progress {#word-collection-similarity-solution__section_ohz_yl5_qhb}

Training times
vary based on the number of records and classes within the training set. The more records and
classes you use, the longer the training can take. For example, a data set containing 100,000
records and several hundred classes can take around five hours to complete.
To show the training solution progress, the ML solution automatically performs the following activities when you select Show training progress on the Solutions page. For more information, see [View solution training progress](https://www.servicenow.com/docs/access?context=view-training-progress&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).  
{#word-collection-similarity-solution__table_jgn_fy2_nhb__entry__2}

| Activity | Description |
|-|-|
| Fetching files for training. | The system downloads the training records and sends them to the nearest training service. |
| Preparing the data. | The system removes duplicate records from the training set. |
| Training the solution. | The training service trains the solution. |
| Uploading the trained solution. | The training service uploads the solution as attachment records. |
[Table 1. Solution training activities]

{#word-collection-similarity-solution__table_jgn_fy2_nhb}