WO2026060133A1 - Moteur de réapplication de décision de système de messagerie - Google Patents

Moteur de réapplication de décision de système de messagerie

Info

Publication number
WO2026060133A1
WO2026060133A1 PCT/US2025/045964 US2025045964W WO2026060133A1 WO 2026060133 A1 WO2026060133 A1 WO 2026060133A1 US 2025045964 W US2025045964 W US 2025045964W WO 2026060133 A1 WO2026060133 A1 WO 2026060133A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
message
messages
actions
data fields
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
PCT/US2025/045964
Other languages
English (en)
Inventor
Pranit Nitin KALANTRI
Gaurav Gupta
Mike ASHCROFT
Siva HOSKERI
Shruti Nair
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of New York Mellon Corp
Original Assignee
Bank of New York Mellon Corp
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
Application filed by Bank of New York Mellon Corp filed Critical Bank of New York Mellon Corp
Publication of WO2026060133A1 publication Critical patent/WO2026060133A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/06—Message adaptation to terminal or network requirements
    • H04L51/063—Content adaptation, e.g. replacement of unsuitable content
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/21—Monitoring or handling of messages
    • H04L51/216—Handling conversation history, e.g. grouping of messages in sessions or threads
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/42—Mailbox-related aspects, e.g. synchronisation of mailboxes

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Probability & Statistics with Applications (AREA)
  • Algebra (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Est proposé un procédé comprenant la réception d'un message qui est destiné à un ou plusieurs destinataires et qui comprend une pluralité de champs de données, un premier ensemble de champs de données de la pluralité de champs de données comprenant des données non structurées. Le procédé consiste à analyser les données non structurées dans au moins une partie du premier ensemble de champs de données pour obtenir des données analysées et à traiter, avec un grand modèle de langage, les données analysées pour déterminer une interprétation des données et un score de confiance dans cette interprétation. Le procédé détermine, sur la base de l'interprétation et du score de confiance, une ou plusieurs actions à prendre avec le message et/ou les données non structurées dans la ou les parties du premier ensemble de champs de données, effectue la ou les actions, et envoie le message au ou aux destinataires.
PCT/US2025/045964 2024-09-12 2025-09-11 Moteur de réapplication de décision de système de messagerie Pending WO2026060133A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
IN202411069127 2024-09-12
IN202411069127 2024-09-12
IN202411072847 2024-09-26
IN202411072847 2024-09-26

Publications (1)

Publication Number Publication Date
WO2026060133A1 true WO2026060133A1 (fr) 2026-03-19

Family

ID=99101113

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2025/045964 Pending WO2026060133A1 (fr) 2024-09-12 2025-09-11 Moteur de réapplication de décision de système de messagerie

Country Status (1)

Country Link
WO (1) WO2026060133A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019060468A1 (fr) * 2017-09-20 2019-03-28 Conversica, Inc. Systèmes et procédés de traitement et de classification en langage naturel
KR20210116223A (ko) * 2020-03-13 2021-09-27 주식회사 솔루게이트 인공지능 기반의 가상상담 서비스 장치 및 방법
US20220383126A1 (en) * 2021-05-19 2022-12-01 Microsoft Technology Licensing, Llc Low-Rank Adaptation of Neural Network Models
US20230074406A1 (en) * 2021-09-07 2023-03-09 Google Llc Using large language model(s) in generating automated assistant response(s
US20230259705A1 (en) * 2021-08-24 2023-08-17 Unlikely Artificial Intelligence Limited Computer implemented methods for the automated analysis or use of data, including use of a large language model

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019060468A1 (fr) * 2017-09-20 2019-03-28 Conversica, Inc. Systèmes et procédés de traitement et de classification en langage naturel
KR20210116223A (ko) * 2020-03-13 2021-09-27 주식회사 솔루게이트 인공지능 기반의 가상상담 서비스 장치 및 방법
US20220383126A1 (en) * 2021-05-19 2022-12-01 Microsoft Technology Licensing, Llc Low-Rank Adaptation of Neural Network Models
US20230259705A1 (en) * 2021-08-24 2023-08-17 Unlikely Artificial Intelligence Limited Computer implemented methods for the automated analysis or use of data, including use of a large language model
US20230074406A1 (en) * 2021-09-07 2023-03-09 Google Llc Using large language model(s) in generating automated assistant response(s

Similar Documents

Publication Publication Date Title
US12106055B2 (en) Techniques for providing explanations for text classification
US11663409B2 (en) Systems and methods for training machine learning models using active learning
CN114547072A (zh) 自然语言查询转换sql方法、系统、设备及存储介质
CN114117048A (zh) 一种文本分类的方法、装置、计算机设备及存储介质
CN117114063A (zh) 用于训练生成式大语言模型和用于处理图像任务的方法
US20250045517A1 (en) Copywriting generation method, electronic device, and storage medium
KR20210125449A (ko) 업계 텍스트를 증분하는 방법, 관련 장치 및 매체에 저장된 컴퓨터 프로그램
US20220198153A1 (en) Model training
US12099817B2 (en) Intelligent industry compliance reviewer
CN116502807B (zh) 基于科技知识图谱的产业链分析应用方法和装置
CN113434683A (zh) 文本分类方法、装置、介质及电子设备
US20240185339A1 (en) Enabling Electronic Loan Documents
CN118733633A (zh) 一种实体搜索方法、大语言模型的微调方法、装置和设备
CN115146070A (zh) 键值生成方法、知识图谱生成方法、装置、设备及介质
CN120410458A (zh) 基于ai模型的材料评审处理平台
WO2025260927A1 (fr) Procédé et appareil d'extraction d'informations
CN118363577B (zh) 一种基于自然语言处理技术创建rpa流程的方法、系统及电子设备
WO2026060133A1 (fr) Moteur de réapplication de décision de système de messagerie
CN117131855B (zh) 基于智能数字孪生的元宇宙空间活动数据分析方法及系统
CN119692460A (zh) 基于人工智能的信息解析方法、装置、计算机设备及介质
CN113344405B (zh) 基于知识图谱生成信息的方法、装置、设备、介质和产品
CN116756281A (zh) 知识问答方法、装置、设备和介质
CN116048463A (zh) 基于标签管理的需求项内容智能推荐方法及装置
CN120705025B (zh) 数据处理方法、任务处理方法
US12541342B1 (en) Platform for automated infrastructure-as-code generation and deployment using multi-agent architecture