公开(公告)号：US20150242961A1

公开(公告)日：2015-08-27

申请号：US14189530

申请日：2014-02-25

Applicant: SRI International

Inventor： Sasha Caskey ,  Zor Gorelov ,  Dror Oren ,  William Mark

IPC: G06Q40/00

CPC classification number: G06Q40/12

Abstract: Example systems and methods of providing enriched financial transaction records are described. In one implementation, a method identifies a financial transaction record that describes a financial transaction associated with a financial institution. The method accesses metadata that has a relationship to the financial transaction and is not structured as a financial transaction record. The metadata is associated with the financial transaction record.

Abstract translation: 描述了提供丰富的金融交易记录的示例系统和方法。 在一个实施中，一种方法识别描述与金融机构相关联的金融交易的金融交易记录。 该方法访问与金融交易有关系的元数据，并不构成财务交易记录。 元数据与金融交易记录相关联。

公开(公告)号：US20170160813A1

公开(公告)日：2017-06-08

申请号：US15332494

申请日：2016-10-24

Applicant: SRI International

Inventor： Ajay Divakaran ,  Amir Tamrakar ,  Girish Acharya ,  William Mark ,  Greg Ho ,  Jihua Huang ,  David Salter ,  Edgar Kalns ,  Michael Wessel ,  Min Yin ,  James Carpenter ,  Brent Mombourquette ,  Kenneth Nitz ,  Elizabeth Shriberg ,  Eric Law ,  Michael Frandsen ,  Hyong-Gyun Kim ,  Cory Albright ,  Andreas Tsiartas

IPC: G06F3/01 ,  G06F3/00 ,  G06F3/16 ,  G06N99/00 ,  G10L25/63 ,  G10L15/22 ,  G10L15/06 ,  G10L15/02 ,  G06K9/00 ,  G10L15/18

CPC classification number: G06F3/017 ,  G06F3/0304 ,  G06F3/167 ,  G06K9/00221 ,  G06K9/00335 ,  G06N3/006 ,  G06N5/022 ,  G06N7/005 ,  G06N20/00 ,  G10L15/1815 ,  G10L15/1822 ,  G10L15/22 ,  G10L25/63 ,  G10L2015/228

Abstract: Methods, computing devices, and computer-program products are provided for implementing a virtual personal assistant. In various implementations, a virtual personal assistant can be configured to receive sensory input, including at least two different types of information. The virtual personal assistant can further be configured to determine semantic information from the sensory input, and to identify a context-specific framework. The virtual personal assistant can further be configured to determine a current intent. Determining the current intent can include using the semantic information and the context-specific framework. The virtual personal assistant can further be configured to determine a current input state. Determining the current input state can include using the semantic information and one or more behavioral models. The behavioral models can include one or more interpretations of previously-provided semantic information. The virtual personal assistant can further be configured to determine an action using the current intent and the current input state.

公开(公告)号：US20150134449A1

公开(公告)日：2015-05-14

申请号：US14079365

申请日：2013-11-13

Applicant: SRI International

Inventor： Zor Gorelov ,  Sasha Caskey ,  Dror Oren ,  William Mark

IPC: G06Q30/02

CPC classification number: G06Q30/0255

Abstract: Example financial conversation management systems and methods are described. In one implementation, a method receives a request from a user and identifies financial data associated with the user. The method determines an answer to the request from the user and infers a user intent based on the financial data associated with the user. An offer is selected for the user based on the user intent.

Abstract translation: 描述了财务会话管理系统和方法的示例。 在一个实现中，方法从用户接收请求并识别与用户相关联的财务数据。 该方法确定来自用户的请求的答案，并且基于与用户相关联的财务数据推断用户意图。 基于用户意图为用户选择报价。

公开(公告)号：US12282606B2

公开(公告)日：2025-04-22

申请号：US17107958

申请日：2020-12-01

Applicant: SRI International

Inventor： Ajay Divakaran ,  Amir Tamrakar ,  Girish Acharya ,  William Mark ,  Greg Ho ,  Jihua Huang ,  David Salter ,  Edgar Kalns ,  Michael Wessel ,  Min Yin ,  James Carpenter ,  Brent Mombourquette ,  Kenneth Nitz ,  Elizabeth Shriberg ,  Eric Law ,  Michael Frandsen ,  Hyong-Gyun Kim ,  Cory Albright ,  Andreas Tsiartas

IPC: G06F3/03 ,  G06F3/01 ,  G06F3/16 ,  G06N3/006 ,  G06N5/022 ,  G06N20/00 ,  G06N20/10 ,  G06V40/16 ,  G06V40/20 ,  G10L15/18 ,  G10L15/22 ,  G10L25/63 ,  G06N7/01

Abstract: Methods, computing devices, and computer-program products are provided for implementing a virtual personal assistant. In various implementations, a virtual personal assistant can be configured to receive sensory input, including at least two different types of information. The virtual personal assistant can further be configured to determine semantic information from the sensory input, and to identify a context-specific framework. The virtual personal assistant can further be configured to determine a current intent. Determining the current intent can include using the semantic information and the context-specific framework. The virtual personal assistant can further be configured to determine a current input state. Determining the current input state can include using the semantic information and one or more behavioral models. The behavioral models can include one or more interpretations of previously-provided semantic information. The virtual personal assistant can further be configured to determine an action using the current intent and the current input state.

公开(公告)号：US20210081056A1

公开(公告)日：2021-03-18

申请号：US17107958

申请日：2020-12-01

Applicant: SRI International

Inventor： Ajay Divakaran ,  Amir Tamrakar ,  Girish Acharya ,  William Mark ,  Greg Ho ,  Jihua Huang ,  David Salter ,  Edgar Kalns ,  Michael Wessel ,  Min Yin ,  James Carpenter ,  Brent Mombourquette ,  Kenneth Nitz ,  Elizabeth Shriberg ,  Eric Law ,  Michael Frandsen ,  Hyong-Gyun Kim ,  Cory Albright ,  Andreas Tsiartas

IPC: G06F3/01 ,  G06K9/00 ,  G06F3/16 ,  G10L15/18 ,  G10L25/63 ,  G10L15/22 ,  G06N20/00 ,  G06F3/03 ,  G06N5/02 ,  G06N3/00 ,  G06N20/10

Abstract: Methods, computing devices, and computer-program products are provided for implementing a virtual personal assistant. In various implementations, a virtual personal assistant can be configured to receive sensory input, including at least two different types of information. The virtual personal assistant can further be configured to determine semantic information from the sensory input, and to identify a context-specific framework. The virtual personal assistant can further be configured to determine a current intent. Determining the current intent can include using the semantic information and the context-specific framework. The virtual personal assistant can further be configured to determine a current input state. Determining the current input state can include using the semantic information and one or more behavioral models. The behavioral models can include one or more interpretations of previously-provided semantic information. The virtual personal assistant can further be configured to determine an action using the current intent and the current input state.

公开(公告)号：US10884503B2

公开(公告)日：2021-01-05

申请号：US15332494

申请日：2016-10-24

Applicant: SRI International

Inventor： Ajay Divakaran ,  Amir Tamrakar ,  Girish Acharya ,  William Mark ,  Greg Ho ,  Jihua Huang ,  David Salter ,  Edgar Kalns ,  Michael Wessel ,  Min Yin ,  James Carpenter ,  Brent Mombourquette ,  Kenneth Nitz ,  Elizabeth Shriberg ,  Eric Law ,  Michael Frandsen ,  Hyong-Gyun Kim ,  Cory Albright ,  Andreas Tsiartas

IPC: G06F3/03 ,  G06F3/01 ,  G06K9/00 ,  G06F3/16 ,  G10L15/18 ,  G10L25/63 ,  G10L15/22 ,  G06N20/00 ,  G06N5/02 ,  G06N3/00 ,  G06N7/00

Abstract: Methods, computing devices, and computer-program products are provided for implementing a virtual personal assistant. In various implementations, a virtual personal assistant can be configured to receive sensory input, including at least two different types of information. The virtual personal assistant can further be configured to determine semantic information from the sensory input, and to identify a context-specific framework. The virtual personal assistant can further be configured to determine a current intent. Determining the current intent can include using the semantic information and the context-specific framework. The virtual personal assistant can further be configured to determine a current input state. Determining the current input state can include using the semantic information and one or more behavioral models. The behavioral models can include one or more interpretations of previously-provided semantic information. The virtual personal assistant can further be configured to determine an action using the current intent and the current input state.