Difference between revisions of "PE-GPR/HIW"
m (Text replacement - "\|Platforms?=([^\|]*)PureEngage([\|]*)" to "|Platform=$1GenesysEngage-onpremises$2") |
(Published) |
||
| (One intermediate revision by one other user not shown) | |||
| Line 1: | Line 1: | ||
{{HIW | {{HIW | ||
| − | |||
| − | |||
|DisplayName=How Predictive Routing works | |DisplayName=How Predictive Routing works | ||
|TocName=How Predictive Routing works | |TocName=How Predictive Routing works | ||
|Context=Learn how Predictive Routing scores agents to find the best match between agent and interaction for the KPI you want to optimize. | |Context=Learn how Predictive Routing scores agents to find the best match between agent and interaction for the KPI you want to optimize. | ||
|ComingSoon=No | |ComingSoon=No | ||
| − | |Platform=GenesysEngage- | + | |Platform=GenesysEngage-cloud |
|Application=GPR Core Platform | |Application=GPR Core Platform | ||
|featurename=Predictive Routing | |featurename=Predictive Routing | ||
|ShortDescription=Predictive Routing uses Machine Learning to match agents and interactions so as to optimize your most important KPIs. | |ShortDescription=Predictive Routing uses Machine Learning to match agents and interactions so as to optimize your most important KPIs. | ||
| − | |overviewtext=Your environment provides a rich source of historical data about your agents, customers, interactions, and interaction outcomes. Predictive Routing (GPR) ingests this data in a systematic way, then uses it to score your agents for each interaction. Agent scores indicate how well each agent should be able to resolve the customer's need in a way that optimizes whichever metric you are trying to improve. The machine learning component ensures that GPR continuously improves scoring accuracy based on outcome data from previous interaction-agent matchups. | + | |overviewtext=Your environment provides a rich source of historical data about your agents, customers, interactions, and interaction outcomes. Predictive Routing (GPR) ingests this data in a systematic way, then uses it to score your agents for each interaction. Agent scores indicate how well each agent should be able to resolve the customer's need in a way that optimizes whichever metric you are trying to improve. The machine learning component ensures that GPR continuously improves scoring accuracy based on outcome data from previous interaction-agent matchups. For a high-level view, take a look at the following overview video: |
| − | |featureoverview=Predictive Routing (GPR) consists of three components: | + | |
| − | + | {{Video|id=312195823|Description=Predictive Routing overview}} | |
| − | + | ||
| + | There's more detailed information about how to deploy and use Predictive Routing here: | ||
| + | |||
| + | *{{Link-AnywhereElse|product=PE-GPR|version=9.0.0|manual=Deployment|display text=Predictive Routing Deployment & Operations Guide}} | ||
| + | *{{Link-AnywhereElse|product=PE-GPR|version=9.0.0|manual=Help|display text=Predictive Routing help topics}} | ||
| + | |featureoverview=Predictive Routing (GPR) consists of three components: | ||
| + | |||
| + | * The GPR Core Platform - a set of services deployed in the Genesys Multicloud environment | ||
| + | * Data Loader - deployed in a Docker container | ||
| + | * The URS Strategy Subroutines - integrated into your routing solution | ||
| + | |||
| + | Data Loader uploads your data to the Core Platform. The Core Platform enables you to view your GPR account and access reports showing feature coverage, KPI outcomes, and model accuracy. It also scores agents and provides the GPR API. The URS Strategy Subroutines submit interaction details to the Core Platform, which scores agents scored for their historical ability to handle such an interaction, and then route the interaction based on the scoring response. | ||
}} | }} | ||
Latest revision as of 09:37, August 31, 2021
Learn how Predictive Routing scores agents to find the best match between agent and interaction for the KPI you want to optimize.
What Predictive Routing does[edit source]
Your environment provides a rich source of historical data about your agents, customers, interactions, and interaction outcomes. Predictive Routing (GPR) ingests this data in a systematic way, then uses it to score your agents for each interaction. Agent scores indicate how well each agent should be able to resolve the customer's need in a way that optimizes whichever metric you are trying to improve. The machine learning component ensures that GPR continuously improves scoring accuracy based on outcome data from previous interaction-agent matchups. For a high-level view, take a look at the following overview video:
There's more detailed information about how to deploy and use Predictive Routing here:
How Predictive Routing works[edit source]
Predictive Routing (GPR) consists of three components:
- The GPR Core Platform - a set of services deployed in the Genesys Multicloud environment
- Data Loader - deployed in a Docker container
- The URS Strategy Subroutines - integrated into your routing solution
Data Loader uploads your data to the Core Platform. The Core Platform enables you to view your GPR account and access reports showing feature coverage, KPI outcomes, and model accuracy. It also scores agents and provides the GPR API. The URS Strategy Subroutines submit interaction details to the Core Platform, which scores agents scored for their historical ability to handle such an interaction, and then route the interaction based on the scoring response.