公开(公告)号：US20240256581A1

公开(公告)日：2024-08-01

申请号：US18160449

申请日：2023-01-27

Applicant: Salesforce, Inc.

Inventor： Feifei Jiang ,  Aron Kale ,  Anuprit Kale ,  Sitaram Asur ,  Na Cheng ,  Zachary Alexander ,  Victor Yee ,  Fermin Ordaz

IPC: G06F16/332 ,  G06F16/33 ,  G06F40/263

CPC classification number: G06F16/3329 ,  G06F16/3347 ,  G06F40/263

Abstract: Embodiments described herein provide ______.

公开(公告)号：US11836450B2

公开(公告)日：2023-12-05

申请号：US17099083

申请日：2020-11-16

Applicant: Salesforce, Inc.

Inventor： Anuprit Kale ,  Weiping Peng ,  Na Cheng ,  Rick Lindstrom ,  Zachary Alexander

IPC: G06F40/289 ,  G06F16/33 ,  G06F16/31 ,  G06F16/332 ,  G06F40/30

CPC classification number: G06F40/289 ,  G06F16/31 ,  G06F16/3329 ,  G06F16/3344 ,  G06F16/3347 ,  G06F40/30

Abstract: Described herein are systems, apparatus, methods and computer program products for machine learning intent classification. In various embodiments, historical utterances provided by users may be utilized for bot training. Context and personally identifiable information may be removed from the utterances. The utterances may be associated with vectors. The utterances and vectors may be used to determine recommendations.

公开(公告)号：US20240143945A1

公开(公告)日：2024-05-02

申请号：US18161767

申请日：2023-01-30

Applicant: Salesforce, Inc.

Inventor： Shubham Mehrotra ,  Zachary Alexander ,  Shilpa Bhagavath ,  Gurkirat Singh ,  Shashank Harinath ,  Anuprit Kale

IPC: G06F40/47 ,  G06F40/30 ,  G06F40/51

CPC classification number: G06F40/47 ,  G06F40/30 ,  G06F40/51

Abstract: Embodiments described herein provide a cross-lingual intent classification model that predicts in multiple languages without the need of training data in all the multiple languages. For example, data requirement for training can be reduced to just one utterance per intent label. Specifically, when an utterance is fed to the intent classification model, the model checks whether the utterance is similar to any of the example utterances provided for each intent. If any such utterance(s) are found, the model returns the specified intent, otherwise, it returns out of domain (OOD).