公开(公告)号：US11568305B2

公开(公告)日：2023-01-31

申请号：US16379110

申请日：2019-04-09

Applicant: Genesys Telecommunications Laboratories, Inc.

Inventor： Sapna Negi ,  Maciej Dabrowski ,  Aravind Ganapathiraju ,  Emir Munoz ,  Veera Elluru Raghavendra ,  Felix Immanuel Wyss

IPC: G06Q20/00 ,  G06N20/00 ,  G06F21/60 ,  G06N3/04 ,  G06N3/08 ,  G06Q30/06

Abstract: A system and method are presented for customer journey event representation learning and outcome prediction using neural sequence models. A plurality of events are input into a module where each event has a schema comprising characteristics of the events and their modalities (web clicks, calls, emails, chats, etc.). The events of different modalities can be captured using different schemas and therefore embodiments described herein are schema-agnostic. Each event is represented as a vector of some number of numbers by the module with a plurality of vectors being generated in total for each customer visit. The vectors are then used in sequence learning to predict real-time next best actions or outcome probabilities in a customer journey using machine learning algorithms such as recurrent neural networks.

公开(公告)号：US20200327444A1

公开(公告)日：2020-10-15

申请号：US16379110

申请日：2019-04-09

Applicant: Genesys Telecommunications Laboratories, Inc.

Inventor： Sapna Negi ,  Maciej Dabrowski ,  Aravind Ganapathiraju ,  Emir Munoz ,  Veera Elluru Raghavendra ,  Felix Immanuel Wyss

IPC: G06N20/00 ,  G06F21/60 ,  G06N3/08 ,  G06N3/04 ,  G06Q30/06

Abstract: A system and method are presented for customer journey event representation learning and outcome prediction using neural sequence models. A plurality of events are input into a module where each event has a schema comprising characteristics of the events and their modalities (web clicks, calls, emails, chats, etc.). The events of different modalities can be captured using different schemas and therefore embodiments described herein are schema-agnostic. Each event is represented as a vector of some number of numbers by the module with a plurality of vectors being generated in total for each customer visit. The vectors are then used in sequence learning to predict real-time next best actions or outcome probabilities in a customer journey using machine learning algorithms such as recurrent neural networks.

公开(公告)号：US11553317B2

公开(公告)日：2023-01-10

申请号：US16352022

申请日：2019-03-13

Applicant: Genesys Telecommunications Laboratories, Inc.

Inventor： Joseph Smyth ,  Ismael Rivera ,  Maciej Dabrowski

IPC: H04W4/21 ,  H04L67/02 ,  G06N20/00

Abstract: A system and method that pre-configure a telecommunication path between two users across a network. A server communicates an Application Programming Interface (API) to a website of an entity which, when accessed by a first user at a remote terminal, loads the API into the user terminal, captures data representative of the interaction of the first user with the website in real time, and communicates the data across the network to the server. The server compares the data with stored attributes of second users to identify a matching second user. The data is analyzed and used to predict a successful outcome between the two users. The server selects a network address of the matched second user, and, upon initiation of a telecommunication with the entity by the first user, routes the telecommunication to the network address and communicates the data to a second terminal of the matched second user.