System and method for intelligent sales engagement
A system for automatically automatic workflow triggering using real-time analytics, comprising an analytics server that receives and analyzes interaction information and a workflow server that produces workflow events based on the analysis, sends workflow events to handlers for processing, retrieves workflow-related data, and produces workflow reports for review, and a method for automatically automatic workflow triggering using real-time analytics.
1. A system for machine-learning-assisted sales engagement, comprising:
a network-connected computing device comprising a memory and a processor;
a directed graph module comprising a first plurality of programming instructions stored in the memory and operating on the processor of the network-connected computing device, wherein the first plurality of programming instructions, when operating on the processor, causes the network-connected computing device to:
monitor and capture sales related data, the sales related data comprising a plurality of interaction events between a business and its customers arising out of the sales process;
construct a directed event graph of events from the data, wherein the vertices of the directed event graph represent the plurality of interaction events, and wherein the edges of the directed event graph represent transitions between the events;
receive probabilities of transition between the plurality of interaction events from a machine learning module; and
construct a directed state graph representing a reverse-engineered sales process from the directed event graph and the probabilities of transition, wherein the vertices of the directed state graph represent states of interaction between the business and its customers, and wherein the edges of the directed graph represent transitions between the states; and
the machine learning module comprising a second plurality of programming instructions stored in the memory of, and operating on the processor of, the network-connected computing device wherein the second plurality of programming instructions, when operating on the processor, causes the network-connected computing device to:
process the directed event graph through one or more machine learning models to determine probabilities of transition between each pair of interaction events in the directed event graph; and
send the probabilities of transition to the directed graph module;
receiving one or more performance metrics;
processing the directed state graph through one or more machine learning models to determine an optimal path through the directed state graph for each performance metric;
sending the determined optimal path for each performance metric to an optimization module; and
the optimization module comprising a third plurality of programming instructions stored in the memory of, and operating on the processor of, the network-connected computing device wherein the third plurality of programming instructions, when operating on the processor, cause the network-connected computing device to:
choose one or more performance metrics for evaluation;
send each performance metric to the machine learning module;
receive the determined optimal path through the directed state graph for each performance metric from the machine-learning model;
create a new sales process from the determined optimal paths from each of the performance metrics.
2. A method for machine-learning-assisted sales engagement, comprising:
using a directed graph module operating on a network-connected computing device comprising a memory and a processor to:
monitor and capture sales related data, the sales related data comprising a plurality of interaction events between a business and its customers arising out of the sales process;
construct a directed event graph of events from the data, wherein the vertices of the directed event graph represent the plurality of interaction events, and wherein the edges of the directed event graph represent transitions between the events;
receive probabilities of transition between the plurality of interaction events from a machine learning module operating on the computing device; and
construct a directed state graph representing a reverse-engineered sales process from the directed event graph and the probabilities of transition, wherein the vertices of the directed state graph represent states of interaction between the business and its customers, and wherein the edges of the directed graph represent transitions between the states; and
using the machine learning module to:
process the directed event graph through one or more machine learning models to determine probabilities of transition between each pair of interaction events in the directed event graph; and
send the probabilities of transition to the directed graph module;
receiving one or more performance metrics;
processing the directed state graph through one or more machine learning models to determine an optimal path through the directed state graph for each performance metric;
sending the determined optimal path for each performance metric to an optimization module operating on the computing device; and
using the optimization module to:
choose one or more performance metrics for evaluation;
send each performance metric to the machine learning module;
receive the determined optimal path through the directed state graph for each performance metric from the machine-learning model; and
create a new sales process from the determined optimal paths from each of the performance metrics.