Jump to: navigation, search

9.0.006.05

Journey Optimization Platform Release Notes

Important
Journey Optimization Platform was renamed to AI Core Services in release 9.0.009.01.


This is the first 9.x release of AI Core Services.
Release Date Release Type Restrictions AIX Linux Solaris Windows
09/26/17 General Under Shipping Control X

Helpful Links

Releases Info

Product Documentation

Genesys Products


What's New

For availability of this release, contact your Genesys representative. This release contains the following new features and enhancements:

  • This release provides improved navigation around the web interface and includes the new Genesys branding:
    • To open the Settings menu, click the cog wheel icon in the top menu.
    • If your environment includes other Analytics applications in addition to Predictive Matching, you can switch between them by clicking the current application name in the top menu bar to open a drop-down menu with the available applications.
  • This release includes context sensitive Help. To open the Help from the interface, click the ? icon on the top menu bar.
  • You can now update and retrain models that have not yet been activated. You can also make changes to activated models by cloning them, editing the parameters, then activating the new model in place of the old one.
  • Predictive Routing now supports HTTPS.
  • Predictive Routing now supports TLS 1.2 encryption. Support for TLS 1.1 has been discontinued.

The following new features were added in previous Restricted releases:

  • Agent and Customer profile schemas now include an is_indexed flag. Mark a field as indexed to have Predictive Routing create indexes in the database for this field, which speeds up queries on this field.
  • Predictive Routing now has more flexibility when building predictors based on incomplete data. Previously, if you tried to create a predictor using agent or/and customer profiles that were not yet configured, you could not save or update your predictor until you corrected the issue. Now, although Predictive Matching generates an error message to notify you about the issue, it completes the creation or updating of the predictor.
  • Predictive Routing now offers a script that identifies misconfigurations, prints them out, and, when possible, fixes them. For example, it can identify and automatically build missing indexes in MongoDB collections. To run this script, open a command window and enter the following:
    $ cd /opt/tango/solariat_bottle/src/solariat_bottle
    $ python prr/configuration_checker.py --mode=prod
  • Scoring requests and responses are now logged into the database for reporting purposes. For every interaction, Predictive Routing now records the actual interaction result and contrasts it with the predicted outcome. This helps demonstrate how well the prediction models are working.
    Note: To make use of this scoring request change, you must modify your strategy subroutines by adding a true/false field to the log_request content.
  • The predictor_models API endpoint now returns the list of local models and scoring request results, with an indication logged for each agent showing whether the model used for scoring was local or global.
  • Predictive Routing now provides full API access to all Predictive Routing-related functionality, including the following:
    • Creation, updating, deletion, and modification of datasets, predictors, and models.
    • Dataset and Predictor schema management.
    • Predictor data purging and generation.
    • Dataset synchronization.
    • Improved logging and reporting for the scoring API.
    • Creation, updating, and deletion of accounts.
    • Agent profile and customer profile updates.
  • Predictive Routing now supports strategies created in Composer and processed by Orchestration Server (ORS). These strategies utilize common URS subroutines to store scores returned from the scoring server and to set callback functions in URS.
  • Schema modification has been extended to enable manual creation of fields not included in an imported dataset. This extended functionality also enables discovery of additional fields by uploading further data and thereby extending the schema.
  • Extended datasets functionality now includes built-in analysis capabilities to make data exploration and feature analysis more straightforward without requiring customers to first build a predictive model.
  • Customer profile data can now be loaded to the platform by means of a REST-API and joined at run time for scoring. This simplifies the integration requirements for deploying Predictive Routing, requiring less modification to existing routing strategies or run time CRM integrations.
  • Predictive Routing now enables logging of routing decisions, required for accurate A/B testing, to JOP rather than Genesys Info Mart. This simplifies Predictive Routing deployment, by removing the need to make changes to Interaction Concentrator and Genesys Info Mart to support Predictive Matching.
  • Improvements to the analytics and reporting functionality:
    • Reports can now indicate whether a predictive score was generated, enabling A/B testing.
    • The range of visualization on the Reporting Dashboard page has been improved.
    • Predictive Routing can now perform analysis and data discovery on factors driving the KPI that is being optimized.
  • You can now upload data sets in CVS format, enabling you to have Predictive Routing analyze the data, define predictors based on it, and report on it. You can use these data sets for model training and testing, and you can calculate statistics for correlation and cardinality from them.
  • Self-service predictor management and model creation. Note the following properties of predictors and models:
  • You can have multiple models built from one related data set.
  • You can only use a predictor to optimize a single metric (that is, a column in the data set); each model under the same predictor optimizes the same metric.
  • You can use a subset of features from the data set to define a predictor.
  • A predictor can be based on a subset of data (such as a time range, or a subset created by filtering data set column values).
  • Once you define a predictor, you can append new data to its underlying data set.
  • A predictor can use any source of data matching the source data set schema to retrain and update models.


Resolved Issues

This release contains the following resolved issues:

The Predictive Routing Settings menu now opens on the Datasets tab by default. It no longer displays the Channels tab, since Channels do not apply to Predictive Routing. (PRR-1003)

Parsing of CSV source files has been improved. If a file contains a corrupted row, this row is now skipped. Previously, the existence of a corrupted row caused a parsing error and the none of the file was uploaded. (PRR-987)


Upgrade Notes

No special procedure is required to upgrade to release 9.0.006.05.

This page was last edited on March 29, 2018, at 14:56.
Comments or questions about this documentation? Contact us for support!