Jump to: navigation, search

Journey Optimization Platform Release Notes

Journey Optimization Platform was renamed to AI Core Services in release

AI Core Services is part of 9.x starting in
Release Date Release Type Restrictions AIX Linux Solaris Windows
03/05/18 Restricted X

Helpful Links

What's New

This is a restricted release for this component. For availability of this release, contact your Genesys representative. This release includes the following new features and enhancements:

  • Predictive Routing now supports datasets of up to 250 columns for predictor data generation, model training, and analysis. (PRR-2077, PRR-1563)
  • Model training speed has been considerably improved. (PRR-1221)
  • Predictive Routing now provides progress indicators when loading predictor data and generating predictors. The progress indicators show the percent complete and the number of data rows already loaded. (PRR-2075, PRR-1747)
  • You can now view an entire Agent or Customer Profile record from the Agents and Customers Details tabs or an entire record on the Datasets Details tab. Click a single record to open a new window containing a table with all the related key-value pairs. (PRR-2057, PRR-1966)
  • The maximum supported cardinality for the Group By functionality in the Lift Estimation report has been increased to 20. All features with cardinalities between 1 and 20 are now available in the Group By selection menu. (PRR-2034)
  • You can now enter a maximum value of 500 simulations in the Lift Estimation analysis report settings. This prevents you from entering numbers too large to efficiently analyze and which can lead to an out-of-memory situation. The Number of Simulations field accepts any value larger than 0 and less than or equal to 500. (PRR-1970)
  • Memory handling when appending data to a dataset has been improved. Previously, appending data a few times in a row could lead to an out of memory state. (PRR-1964)
  • Predictive Routing now provides a text search field for use when selecting attributes for analysis. (PRR-1834)
  • When a dataset is loaded, the system checks the first 1000 rows of each column to determine data types automatically. Predictive Routing now assigns the boolean type to columns with 0 and 1 values. Previously, values in such columns were identified as numeric. (PRR-1791)
  • You can now enable Predictive Routing to look up updated values for certain agent attributes based on customer or interaction attributes during a scoring request. For instance, you can look up agent performance by Virtual Queue, making it possible to evaluate the agent’s previous performance handling interactions from that queue. This avoids comparing agent performance for a specific queue against other agents who handle interactions from a different mixture of Virtual Queues.
    The Agent Profile schema encodes such information as a dictionary. Currently only one-dimensional dictionaries are supported. They can have up to 200 key-value pairs, where the key is a string and the value is one of the following types: int, float or boolean. (PRR-1643)

Resolved Issues

This release contains the following resolved issues:

Scoring requests now correctly return scores for all valid agents even if some agents have errors. Previously, if any agent included in the scoring request had an error, the scoring request failed for all agents. (PRR-2100)

Upgrade Notes

No special procedure is required to upgrade to release

This page was last edited on March 29, 2018, at 14:53.
blog comments powered by Disqus