- Spirent moves all users to Office 365 for user collaboration in 1 week, and with seamless user adoption.
Unstructured data driven intelligence
The calibration engine is architected to leverage the out-of-the-box artificial intelligence models to either customize, extend or “train” them to accurately detect company-defined or other proprietary data. The module gets you closer to your business, by refining its artificial intelligence to identify and classify your unique data sets.
Artificial intelligence calibration
A.I. training is at the center of the calibration module, utilized to build out entities that are relevant to your business and to customize each of the artificial intelligence models to meet your unique company-specific unstructured data classification needs.
- Pre-trained A.I. models available to be customized for unique and custom requirements
- A self-guided process directs the user to provide the required information to train the individual A.I. model
- Samples from the repository are utilized for training the A.I. models
- A.I. models can be trained as often as required or desired
- Newly trained versions of the A.I. models can be selected to deploy as needed
"DryvIQ was the only solution that addressed our needs."
The support I got from DryvIQ was phenomenal, it blew away all expectations.
Includes a sample content repository
Platform administrators can upload sample (test) content to be leveraged by the calibration module to train and test different A.I. models to achieve maximum accuracy:
- Two modes of population — user uploaded files or items found during scan (disputed items)
- Ability to organize samples of content and files
- Content within the repository can be leveraged across all A.I. models
- Upload only one copy of a file if it is needed to train different A.I. models
A.I. model accuracy evaluation
Designed to evaluate and compare the overall accuracy of multiple, customized A.I. models
- Ability to test trained A.I. models using test samples from the A.I. sample repository
- Depicts how a sample (test) file will be classified by the A.I. model(s)
- Match accuracy is displayed for each file tested and classified
- Used to decide on which version of the A.I. model(s) to leverage based upon sample data results