WO2022066695A1 - Systèmes et procédés pour générer des réponses conversationnelles dynamiques par l'intermédiaire de sorties agrégées de modèles d'apprentissage machine - Google Patents

Systèmes et procédés pour générer des réponses conversationnelles dynamiques par l'intermédiaire de sorties agrégées de modèles d'apprentissage machine Download PDF

Info

Publication number
WO2022066695A1
WO2022066695A1 PCT/US2021/051438 US2021051438W WO2022066695A1 WO 2022066695 A1 WO2022066695 A1 WO 2022066695A1 US 2021051438 W US2021051438 W US 2021051438W WO 2022066695 A1 WO2022066695 A1 WO 2022066695A1
Authority
WO
WIPO (PCT)
Prior art keywords
machine learning
output
learning model
user
input
Prior art date
Application number
PCT/US2021/051438
Other languages
English (en)
Inventor
Minh Le
Original Assignee
Capital One Services, Llc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US17/029,997 external-priority patent/US11621930B2/en
Priority claimed from US17/030,059 external-priority patent/US11694038B2/en
Application filed by Capital One Services, Llc filed Critical Capital One Services, Llc
Priority to EP21873310.3A priority Critical patent/EP4217886A1/fr
Priority to CA3196711A priority patent/CA3196711A1/fr
Publication of WO2022066695A1 publication Critical patent/WO2022066695A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G06F40/35—Discourse or dialogue representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions

Abstract

L'invention concerne des procédés et des systèmes pour générer des réponses conversationnelles dynamiques. Par exemple, des réponses conversationnelles dynamiques peuvent permettre un échange interactif avec des utilisateurs. Par conséquent, les procédés et les systèmes utilisent des procédés spécialisés pour enrichir des données qui peuvent être indicatives de l'intention de l'utilisateur avant le traitement de ces données par le biais du modèle d'apprentissage machine, ainsi qu'une architecture spécialisée pour les modèles d'apprentissage machine qui tirent profit du format d'interface utilisateur.
PCT/US2021/051438 2020-09-23 2021-09-22 Systèmes et procédés pour générer des réponses conversationnelles dynamiques par l'intermédiaire de sorties agrégées de modèles d'apprentissage machine WO2022066695A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21873310.3A EP4217886A1 (fr) 2020-09-23 2021-09-22 Systèmes et procédés pour générer des réponses conversationnelles dynamiques par l'intermédiaire de sorties agrégées de modèles d'apprentissage machine
CA3196711A CA3196711A1 (fr) 2020-09-23 2021-09-22 Systemes et procedes pour generer des reponses conversationnelles dynamiques par l'intermediaire de sorties agregees de modeles d'apprentissage machine

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US17/029,997 2020-09-23
US17/029,997 US11621930B2 (en) 2020-09-23 2020-09-23 Systems and methods for generating dynamic conversational responses using trained machine learning models
US17/030,059 2020-09-23
US17/030,059 US11694038B2 (en) 2020-09-23 2020-09-23 Systems and methods for generating dynamic conversational responses through aggregated outputs of machine learning models

Publications (1)

Publication Number Publication Date
WO2022066695A1 true WO2022066695A1 (fr) 2022-03-31

Family

ID=80845767

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2021/051438 WO2022066695A1 (fr) 2020-09-23 2021-09-22 Systèmes et procédés pour générer des réponses conversationnelles dynamiques par l'intermédiaire de sorties agrégées de modèles d'apprentissage machine

Country Status (3)

Country Link
EP (1) EP4217886A1 (fr)
CA (1) CA3196711A1 (fr)
WO (1) WO2022066695A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115292491A (zh) * 2022-08-04 2022-11-04 四川大学 基于ctmsn-ehi的任务型多轮对话信息处理方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030191753A1 (en) * 2002-04-08 2003-10-09 Michael Hoch Filtering contents using a learning mechanism
WO2016195912A1 (fr) * 2015-05-31 2016-12-08 Microsoft Technology Licensing, Llc Génération sensible au contexte de réponses de conversation
US20170293695A1 (en) * 2016-04-12 2017-10-12 Ebay Inc. Optimizing similar item recommendations in a semi-structured environment
US20170357635A1 (en) * 2016-06-08 2017-12-14 Rovi Guides, Inc. Systems and methods for determining context switching in conversation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030191753A1 (en) * 2002-04-08 2003-10-09 Michael Hoch Filtering contents using a learning mechanism
WO2016195912A1 (fr) * 2015-05-31 2016-12-08 Microsoft Technology Licensing, Llc Génération sensible au contexte de réponses de conversation
US20170293695A1 (en) * 2016-04-12 2017-10-12 Ebay Inc. Optimizing similar item recommendations in a semi-structured environment
US20170357635A1 (en) * 2016-06-08 2017-12-14 Rovi Guides, Inc. Systems and methods for determining context switching in conversation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
YANG ZHIMING; WANG LAIQI; WANG YONG: "Multi-Intent Text Classification Using Dual Channel Convolutional Neural Network", 2019 34RD YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION (YAC), IEEE, 6 June 2019 (2019-06-06), pages 397 - 402, XP033589697, DOI: 10.1109/YAC.2019.8787650 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115292491A (zh) * 2022-08-04 2022-11-04 四川大学 基于ctmsn-ehi的任务型多轮对话信息处理方法

Also Published As

Publication number Publication date
EP4217886A1 (fr) 2023-08-02
CA3196711A1 (fr) 2022-03-31

Similar Documents

Publication Publication Date Title
US11621930B2 (en) Systems and methods for generating dynamic conversational responses using trained machine learning models
US20170032242A1 (en) Predicting likelihoods of conditions being satisfied using recurrent neural networks
US11677693B2 (en) Systems and methods for generating dynamic conversational responses using ensemble prediction based on a plurality of machine learning models
CN111191791A (zh) 机器学习模型的应用方法、训练方法、装置、设备及介质
US20240029436A1 (en) Action classification in video clips using attention-based neural networks
US11423436B2 (en) Interpretable click-through rate prediction through hierarchical attention
US11973725B2 (en) Systems and methods generating conversational responses using machine learning models
US11811708B2 (en) Systems and methods for generating dynamic conversational responses using cluster-level collaborative filtering matrices
US11790183B2 (en) Systems and methods for generating dynamic conversational responses based on historical and dynamically updated information
US20230351119A1 (en) Systems and methods for generating dynamic conversational responses through aggregated outputs of machine learning models
US20230108855A1 (en) Systems and methods for generating training data for sequential conversational responses
GB2600817A (en) Systems and methods for generating dynamic interface options using machine learning models
US20240144278A1 (en) Systems and methods for fraud monitoring
US20240046922A1 (en) Systems and methods for dynamically updating machine learning models that provide conversational responses
WO2022066695A1 (fr) Systèmes et procédés pour générer des réponses conversationnelles dynamiques par l'intermédiaire de sorties agrégées de modèles d'apprentissage machine
US20240015168A1 (en) Methods and systems for cyber threat detection using artificial intelligence models in data-sparse environments
US11836168B1 (en) Systems and methods for generating dynamic human-like conversational responses using a modular architecture featuring layered data models in non-serial arrangements with gated neural networks
US11977515B1 (en) Real time analysis of interactive content
US20230419046A1 (en) Systems and methods for generating real-time dynamic conversational responses during conversational interactions using machine learning models
CN113762584A (zh) 数据处理方法、装置、计算机设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21873310

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 3196711

Country of ref document: CA

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021873310

Country of ref document: EP

Effective date: 20230424