公开(公告)号：US20230281399A1

公开(公告)日：2023-09-07

申请号：US17653426

申请日：2022-03-03

Applicant: INTUIT INC.

Inventor： Prarit LAMBA ,  Clifford GREEN ,  Tomer TAL ,  Andrew MATTARELLA-MICKE

IPC: G06F40/58 ,  G06F40/56 ,  G06K9/62

CPC classification number: G06F40/58 ,  G06F40/56 ,  G06K9/6257

Abstract: Embodiments disclosed herein provide language-agnostic routing prediction models. The routing prediction models input text queries in any language and generate a routing prediction for the text queries. For a language that may have sparse training text data, the models, which are machine learning models, are trained using a machine translation to a prevalent language (e.g., English) to the language having sparse training text data -with the original text corpus and the translated text corpus being an input to multi-language embedding layers. The trained machine learning model makes routing predictions for text queries for the language having sparse training text data.

公开(公告)号：US20230385087A1

公开(公告)日：2023-11-30

申请号：US17804828

申请日：2022-05-31

Applicant: INTUIT INC.

Inventor： Tomer TAL ,  Prarit LAMBA ,  Clifford Green ,  Xiaoyu ZENG ,  Neo YUCHEN ,  Andrew MATTARELLA-MICKE

IPC: G06F9/451 ,  G06N20/00 ,  G06F11/34 ,  G06F3/04842

CPC classification number: G06F9/453 ,  G06N20/00 ,  G06F11/3438 ,  G06F3/04842

Abstract: A processor may obtain historic clickstream data indicating a plurality of interactions with a user interface (UI) by a plurality of users. The processor may select at least one user for real-time monitoring by processing, using a machine learning (ML) model, the historic clickstream data and at least one user feature and predicting, from the processing, that the at least one user will utilize a UI resource. The processor may monitor ongoing clickstream data of the selected at least one user and configure the UI resource according to the ongoing clickstream data.

公开(公告)号：US20220012643A1

公开(公告)日：2022-01-13

申请号：US16927655

申请日：2020-07-13

Applicant: INTUIT INC.

Inventor： Shanshan TUO ,  Neo YUCHEN ,  Divya BEERAM ,  Valentin VRZHESHCH ,  Tomer TAL ,  Nhung HO

IPC: G06N20/20 ,  G06N3/04 ,  G06F16/9535 ,  G06K9/62

Abstract: Aspects of the present disclosure provide techniques for training a machine learning model. Embodiments include receiving a historical support record comprising time-stamped actions, a support initiation time, and an account indication. Embodiments include determining features of the historical support record based at least on differences between times of the time-stamped actions and the support initiation time. Embodiments include determining a label for the features based on the account indication. Embodiments include training an ensemble model, using training data comprising the features and the label, to determine an indication of an account in response to input features, wherein the ensemble model comprises a plurality of tree-based models and a ranking model.

公开(公告)号：US20240169994A1

公开(公告)日：2024-05-23

申请号：US18426488

申请日：2024-01-30

Applicant: INTUIT INC.

Inventor： Shanshan TUO ,  Divya BEERAM ,  Meng CHEN ,  Neo YUCHEN ,  Wan Yu ZHANG ,  Nivethitha KUMAR ,  Kavita SUNDAR ,  Tomer TAL

IPC: G10L17/04 ,  G06F21/32 ,  G06N20/20 ,  G10L17/18 ,  G10L17/26 ,  G10L21/0208

CPC classification number: G10L17/04 ,  G06F21/32 ,  G06N20/20 ,  G10L17/18 ,  G10L17/26 ,  G10L21/0208

Abstract: Certain embodiments of the present disclosure provide techniques training a user detection model to identify a user of a software application based on voice recognition. The method generally includes receiving a data set including a plurality of voice interactions with users of a software application. For each respective recording in the data set, a spectrogram representation is generated based on the respective recording. A plurality of voice recognition models are trained. Each of the plurality of voice recognition models is trained based on the spectrogram representation for each of the plurality of voice recordings in the data set. The plurality of voice recognition models are deployed to an interactive voice response system.

公开(公告)号：US20220270611A1

公开(公告)日：2022-08-25

申请号：US17183006

申请日：2021-02-23

Applicant: INTUIT INC.

Inventor： Shanshan TUO ,  Divya BEERAM ,  Meng CHEN ,  Neo YUCHEN ,  Wan Yu ZHANG ,  Nivethitha KUMAR ,  Kavita SUNDAR ,  Tomer TAL

IPC: G10L17/04 ,  G06F21/32 ,  G10L17/26 ,  G10L17/18 ,  G10L21/0208 ,  G06N20/20

Abstract: Certain embodiments of the present disclosure provide techniques training a user detection model to identify a user of a software application based on voice recognition. The method generally includes receiving a data set including a plurality of voice interactions with users of a software application. For each respective recording in the data set, a spectrogram representation is generated based on the respective recording. A plurality of voice recognition models are trained. Each of the plurality of voice recognition models is trained based on the spectrogram representation for each of the plurality of voice recordings in the data set. The plurality of voice recognition models are deployed to an interactive voice response system.