Similarity solutions
Summarize
Summary of Similarity solutions
Similarity solutions in ServiceNow enable you to leverage Machine Learning (ML) to compare text fields in resolved alert records with those in open alert records. This comparison helps identify similar past alerts to reuse their resolution approaches, improving efficiency in incident management.
Show less
Training a similarity solution
To train a similarity solution, you compile a collection of words from key text fields such as Short Description, Description, Source, Type, Resource, and Metric Name from resolved alerts. The ML model uses this to find matches to open alerts, suggesting how to resolve them.
- Training requires a filter that returns at least one record; ideally between 30,000 and 300,000 recent and relevant authentic records from your database.
- If more than 300,000 records are submitted, only the most recent 300,000 are used.
- Use relative date filters (e.g., last 3, 6, or 12 months) to keep training data current and avoid hard-coded dates that do not automatically update.
- Iterative training is recommended to refine and achieve an effective similarity solution.
Fields to include in the solution
Choose fields likely to contain meaningful text for similarity comparison. Ensure these fields are relevant and available in the record state you are analyzing (e.g., do not select fields like Close note for open incidents where that field is empty). The selected similarity fields influence the accuracy of identifying matching records.
Similarity score and threshold
The similarity score ranges from 0 to 100, indicating how closely two alert records match. The solution returns records with scores above a configurable threshold, which you can adjust to balance precision and recall. Use the Show training progress feature to review example scores and fine-tune the threshold.
Training progress and performance
Training duration depends on the number of records and classes involved; for example, training on 100,000 records with several hundred classes can take about five hours.
The system performs these steps during training:
- Fetching files for training: Downloads training records and sends them to the nearest training service.
- Preparing the data: Removes duplicate records from the training set.
- Training the solution: The ML service processes the data to build the solution.
- Uploading the trained solution: The trained model is uploaded as attachment records for use.
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
To train a similarity solution, you collect words to compile a collection that Machine Learning (ML) can use to compare text in the Short Description, Description, Source, Type, Resource, and Metric Name fields in a resolved alert to see 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.
- 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.
Fields to include in the solution
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
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
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.| 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. |