公开(公告)号：CO2025004356A2

公开(公告)日：2025-04-28

申请号：CO2025004356

申请日：2025-04-03

Applicant: GENESYS CLOUD SERVICES INC

Inventor： MAZOR IGAL

IPC: G06N20/20

Abstract: RESUMEN Un sistema y método de entrenamiento de un modelo basado en aprendizaje automático (ML) mediante al menos un procesador puede incluir recibir un conjunto de datos inicial, que incluye una pluralidad de muestras de datos anotadas; basado en el conjunto de datos inicial, entrenar al menos un modelo de primer nivel basado en ML para realizar una tarea de primer nivel; basado en el entrenamiento del al menos un modelo de primer nivel basado en ML, calcular al menos una característica, que represente, para cada muestra de datos, un valor de contribución en un entrenamiento de un modelo de segundo nivel basado en ML para realizar una tarea de segundo nivel; omitir un subconjunto de muestras de datos del conjunto de datos inicial basado en la al menos una característica, para obtener un conjunto de datos objetivo; y entrenar el modelo de segundo nivel basado en ML, para realizar la tarea de segundo nivel, basado en el conjunto de datos objetivo.

公开(公告)号：AU2020268901B2

公开(公告)日：2025-01-23

申请号：AU2020268901

申请日：2020-05-02

Applicant: GENESYS CLOUD SERVICES INC

Inventor： BATCHA MOHAMED UVAIZ ANWAR ,  BALARAMAN PRASANTH ,  DURAIRAJ ASMITHA ,  ANANDADOSS PRAVEEN KUMAR ,  SUBRAMANIAN RAJESHKUMAR ,  THAZHEKKADEN TONY ,  GANESAN KESAVAN

IPC: H04M3/51 ,  H04M3/42 ,  H04M3/58 ,  H04M7/00

Abstract: A system and method are presented for providing a contextual summary of an interaction between a first party and a second party over a media channel in an interaction transfer to a third party. A request is received to transfer an interaction to the third party, the request being triggered from the interaction. A text transcript of the interaction is obtained. The text transcript is processed to obtain the contextual summary and metadata, which is provided to the third party for handling the interaction with the interaction transfer. The contextual summary is provided by a contextual summarizer, which comprises a custom plurality of application programming interfaces (APIs). The plurality of APIs comprises at least one of: a text summarizer API, a churn predictor API, a sentiment analysis API, a next best action API, and an interaction reference detector API.

公开(公告)号：AU2021415468A1

公开(公告)日：2023-07-13

申请号：AU2021415468

申请日：2021-10-11

Applicant: GENESYS CLOUD SERVICES INC

Inventor： WYSS FELIX IMMANUEL

IPC: G06F40/35 ,  G06F40/279 ,  H04W4/70

Abstract: A method for conducting an automated dialogue between an inbound automated voice resource and an outbound automated voice resource during a voice communication session according to one embodiment includes receiving at the inbound automated voice resource an initiation of the voice communication session from the outbound automated voice resource; transmitting, by the inbound automated voice resource, a speech communication to the outbound automated voice resource during the voice communication session, wherein a digital watermark is embedded in the speech communication; identifying, by the outbound automated voice resource, the digital watermark in response to analyzing the speech communication; converting, by the outbound automated voice resource, an outbound automated voice resource communication language from speech to machine language in response to determining that the inbound automated voice resource interprets machine language based on the digital watermark; transmitting, by the outbound automated voice resource, a machine language communication to the inbound automated voice resource; converting, by the inbound automated voice resource, an inbound automated voice resource communication language from speech to machine language in response to determining that the outbound automated voice resource interprets machine language based on the machine language communication; and completing the automated dialogue between the inbound automated voice resource and the outbound automated voice resource using machine language.

公开(公告)号：CO2025000184A2

公开(公告)日：2025-04-07

申请号：CO2025000184

申请日：2025-01-10

Applicant: GENESYS CLOUD SERVICES INC

Inventor： FICO CHARLES D ,  BRINTON STEFAN ,  SLAPPEY CHAD ,  WADE HANNA

IPC: G06F12/0873 ,  G06F3/06 ,  G06F9/455 ,  G06F9/46 ,  G06F12/0866 ,  G06F16/215

Abstract: RESUMEN Un método para almacenamiento en caché configurable, deduplicación, y manejo de límites de velocidad de solicitudes de datos de interfaz de usuario de acuerdo con una modalidad incluye recibir una solicitud de datos iniciada por un elemento de interfaz de usuario de una interfaz de usuario, determinar si una caché de deduplicación incluye una entrada de deduplicación asociada con la solicitud de datos, determinar si una caché principal incluye una entrada de caché asociada con la solicitud de datos en respuesta a la determinación de que la caché de deduplicación no incluye la entrada de deduplicación, determinar si la solicitud de datos está asociada con un grupo limitado por velocidad de puntos finales de interfaz de programación de aplicaciones en respuesta a determinar que la caché principal no incluye la entrada de caché o determinar que la entrada de caché ha caducado, y realizar la solicitud de datos a un sistema en modo administrador después de que haya transcurrido un período de reintento de servidor predefinido asociado con el grupo limitado por velocidad en respuesta a determinar que la solicitud de datos está asociada con el grupo de velocidad limitada.

公开(公告)号：NZ771887A

公开(公告)日：2024-11-29

申请号：NZ77188718

申请日：2018-11-21

Applicant: GENESYS CLOUD SERVICES INC

Inventor： ANANDADOSS PRAVEEN KUMAR ,  SUBRAMANIAN RAJESHKUMAR ,  SIVAKUMAR VENKATESH

IPC: H04M3/51 ,  H04L65/403 ,  H04M1/725 ,  H04M3/523

Abstract: A system and method are presented for omni-channel notification and selection. A first party selects a first channel from a plurality of channels based on an estimated wait time for interaction with another party in a contact center or enterprise setting. The plurality of channels may comprise any means of interaction, such as chat, phone call, SMS, video, etc. While waiting in queue for the preferred first channel, the first party is presented with estimated wait times, which are dynamically updated, for other channels. Based on the first party’s preferences and the presented estimated wait times for the other channels, the first party may elect to change interaction channels from the first channel to a second channel. The first party may then be moved to a different queue corresponding to the second interaction channel.

公开(公告)号：CO2024012841A2

公开(公告)日：2024-10-10

申请号：CO2024012841

申请日：2024-09-23

Applicant: GENESYS CLOUD SERVICES INC

Inventor： SUNDARAM RAMASUBRAMANIAN ,  GEORGE BASIL

IPC: G06F40/279

Abstract: Un método para extraer temas tratados en conversaciones que incluye: recibir datos conversacionales; y usar un algoritmo de extracción de temas para extraer temas a partir de los datos conversacionales. El algoritmo de extracción de temas incluye identificar temas candidatos en cada una de las conversaciones. El algoritmo de extracción de temas incluye además identificar los temas de las conversaciones a través de: compilar una lista de temas candidatos; podar la lista de temas candidatos descartando ciertos temas candidatos de acuerdo con un factor de conversación cruzada que factoriza el uso en todas las conversaciones; e identificar como temas los temas candidatos que quedan en la lista podada de temas candidatos. El algoritmo de extracción de temas incluye además determinar grupos de temas agrupando los temas de acuerdo con un grado de similitud semántica entre los temas; y asociar una lista de enunciados con los grupos de temas.

公开(公告)号：AU2021415468A9

公开(公告)日：2024-07-25

申请号：AU2021415468

申请日：2021-10-11

Applicant: GENESYS CLOUD SERVICES INC

Inventor： WYSS FELIX IMMANUEL

IPC: G06F40/35 ,  G06F40/279 ,  H04W4/70

Abstract: A method for conducting an automated dialogue between an inbound automated voice resource and an outbound automated voice resource during a voice communication session according to one embodiment includes receiving at the inbound automated voice resource an initiation of the voice communication session from the outbound automated voice resource; transmitting, by the inbound automated voice resource, a speech communication to the outbound automated voice resource during the voice communication session, wherein a digital watermark is embedded in the speech communication; identifying, by the outbound automated voice resource, the digital watermark in response to analyzing the speech communication; converting, by the outbound automated voice resource, an outbound automated voice resource communication language from speech to machine language in response to determining that the inbound automated voice resource interprets machine language based on the digital watermark; transmitting, by the outbound automated voice resource, a machine language communication to the inbound automated voice resource; converting, by the inbound automated voice resource, an inbound automated voice resource communication language from speech to machine language in response to determining that the outbound automated voice resource interprets machine language based on the machine language communication; and completing the automated dialogue between the inbound automated voice resource and the outbound automated voice resource using machine language.

公开(公告)号：AU2023358622A1

公开(公告)日：2025-03-20

申请号：AU2023358622

申请日：2023-10-10

Applicant: GENESYS CLOUD SERVICES INC

Inventor： MAZOR IGAL

IPC: G06N20/20

Abstract: A system and method of training a machine-learning (ML) based model by at least one processor may include receiving an initial dataset, including a plurality of annotated data samples; based on the initial dataset, training at least one ML-based first-level model to perform a first-level task; based on training the at least one ML-based first-level model, calculating at least one characteristic, representing, for each data sample, a value of contribution into a training of a ML-based second-level model to perform a second-level task; omitting a subset of data samples from the initial dataset based on the at least one characteristic, to obtain a target dataset; and training ML-based second-level model, to perform the second-level task, based on the target dataset.

公开(公告)号：AU2020257179B2

公开(公告)日：2025-01-02

申请号：AU2020257179

申请日：2020-04-15

Applicant: GENESYS CLOUD SERVICES INC

Inventor： DUMAINE ALEXANDER G

IPC: H04L67/02 ,  H04L67/14 ,  H04L67/75

Abstract: A system and method are presented for analyzing network performance of a web application. A user interface in a cloud-based collaboration platform provides a notification when the user's location is having network connectivity issues to the collaboration platform. Connectivity issues may be determined through aggregation of measurements of network quality and performance (e.g. XMLHttpRequest requests, Websockets, and WebRTC) and alerting the user when issues arise. Data may be pushed back to an analytics ingestion system for aggregate-of-aggregate analytics and alerting as well as viewing network performance across a plurality of users and organizations.

公开(公告)号：AU2021394754A9

公开(公告)日：2024-09-26

申请号：AU2021394754

申请日：2021-12-08

Applicant: GENESYS CLOUD SERVICES INC

Inventor： TER WEI ,  ROSOY GEIR ,  HAMEED MOHAMED ,  WICAKSONO BAYU ,  HUMPHREYS TRAVIS ,  ROBINSON BRIAN

IPC: H04M3/50

Abstract: A system for estimating a wait time to connect a customer to an agent according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the system to receive incoming interaction data from the customer indicative of a request to estimate the wait time, retrieve historical data indicative of interaction information for one or more interactions that have already been serviced in response to receipt of the request, and generate a wait time estimation based on the historical data.