公开(公告)号：US10198433B2

公开(公告)日：2019-02-05

申请号：US15077814

申请日：2016-03-22

Applicant: Facebook, Inc.

Inventor： Jason E Weston ,  Antoine Bordes ,  Alexandre Lebrun ,  Martin Jean Raison

IPC: G06F17/27 ,  G06F3/0482 ,  G06F3/0484 ,  G06F17/30

Abstract: Techniques to predictively respond to user requests using natural language processing are described. In one embodiment, an apparatus may comprise a client communication component operative to receive a user service request from a user client; an interaction processing component operative to submit the user service request to a memory-based natural language processing component; generate a series of user interaction exchanges with the user client based on output from the memory-based natural language processing component, wherein the series of user interaction exchanges are represented in a memory component of the memory-based natural language processing component; and receive one or more operator instructions for the performance of the user service request from the memory-based natural language processing component; and a user interface component operative to display the one or more operator instructions in an operator console. Other embodiments are described and claimed.

公开(公告)号：US10978052B2

公开(公告)日：2021-04-13

申请号：US14686770

申请日：2015-04-14

Applicant: Facebook, Inc.

Inventor： Alexandre Lebrun

IPC: G10L15/18 ,  G06F40/35 ,  G10L15/06

Abstract: An email-like user interface displays a list of user logs determined based on user-specified list criteria to user logs received in a natural language (NL) training environment. The list comprise a subset of the received user logs in order to minimize the number of actions required to configure and train the NL configuration system in a semi-supervised manner, thereby improving the quality and accuracy of NL configuration system. To determine a list of user logs relevant for training the user logs can be filtered, sorted, grouped and searched within the email-like user interface. A training interface to a network of instances that comprises a plurality of NL configuration systems leverages a crowd-sourcing community of developers in order to efficiently create a customizable NL configuration system.

公开(公告)号：USD804493S1

公开(公告)日：2017-12-05

申请号：US29550163

申请日：2015-12-30

Applicant: Facebook, Inc.

Designer： Robert Franklin Daniel ,  Yoram Talmor ,  Alexandre Lebrun ,  Laurent Nicolas Landowski ,  Deniz Demir ,  Jeremy Harrison Goldberg ,  Willy Blandin

CPC classification number: H04L51/046 ,  H04L51/32

公开(公告)号：US20170187666A1

公开(公告)日：2017-06-29

申请号：US14981443

申请日：2015-12-28

Applicant: Facebook, Inc.

Inventor： Matthew Logan Schmid ,  Roee Vulkan ,  Laurent Nicolas Landowski ,  Alexandre Lebrun ,  Allan Grinshtein

IPC: H04L12/58 ,  H04L29/08

Abstract: Systems, methods, and non-transitory computer-readable media can acquire an incoming message via a communication system. Access to a preconfigured message template can be provided. A command to generate an outgoing message based on the preconfigured message template can be acquired. The outgoing message generated based on the preconfigured message template can be transmitted via the communication system. The outgoing message can be transmitted as a response to the incoming message.

公开(公告)号：US10762300B1

公开(公告)日：2020-09-01

申请号：US16227673

申请日：2018-12-20

Applicant: Facebook, Inc.

Inventor： Jason E Weston ,  Antoine Bordes ,  Alexandre Lebrun ,  Martin Jean Raison

IPC: G06F40/35 ,  G06F3/0484 ,  G06F3/0482 ,  G06F16/332

Abstract: Techniques to predictively respond to user requests using natural language processing are described. In one embodiment, an apparatus may comprise a client communication component operative to receive a user service request from a user client; an interaction processing component operative to submit the user service request to a memory-based natural language processing component; generate a series of user interaction exchanges with the user client based on output from the memory-based natural language processing component, wherein the series of user interaction exchanges are represented in a memory component of the memory-based natural language processing component; and receive one or more operator instructions for the performance of the user service request from the memory-based natural language processing component; and a user interface component operative to display the one or more operator instructions in an operator console. Other embodiments are described and claimed.

公开(公告)号：US10686738B2

公开(公告)日：2020-06-16

申请号：US14809078

申请日：2015-07-24

Applicant: Facebook, Inc.

Inventor： Robert Franklin Daniel ,  Yoram Talmor ,  Alexandre Lebrun ,  Laurent Nicolas Landowski ,  Deniz Demir ,  Jeremy Harrison Goldberg ,  Willy Blandin

IPC: H04L12/58

Abstract: The present disclosure relates to systems, methods, and devices for providing personal assistant service via messaging. In particular, one or more embodiments receive a request for personal assistant service in an electronic message from a user, assign the request to an agent, determine an intent of the request, and configure an agent user interface to include one or more options in accordance with the determined intent of the request.

公开(公告)号：US20170293681A1

公开(公告)日：2017-10-12

申请号：US15380112

申请日：2016-12-15

Applicant: Facebook, Inc.

Inventor： Willy Blandin ,  Alexandre Lebrun

IPC: G06F17/30 ,  G06N3/00 ,  G06N99/00 ,  H04L12/58

Abstract: Techniques to response to user requests using natural-language machine learning based on example conversations are described. In one embodiment, an apparatus may comprise a bot application interface component operative to receive an example-interaction repository, the example-interaction repository comprising a plurality of example user-to-bot interactions; and an interaction processing component operative to submit the example-interaction repository to a natural-language machine learning component; receive a sequence model from the natural-language machine learning component in response to submitting the example-interaction repository; and perform a user-to-bot conversation based on the sequence model. Other embodiments are described and claimed.

公开(公告)号：US10686745B2

公开(公告)日：2020-06-16

申请号：US14981443

申请日：2015-12-28

Applicant: Facebook, Inc.

Inventor： Matthew Logan Schmid ,  Roee Vulkan ,  Laurent Nicolas Landowski ,  Alexandre Lebrun ,  Allan Grinshtein

IPC: H04L12/58 ,  H04L29/08

Abstract: Systems, methods, and non-transitory computer-readable media can acquire an incoming message via a communication system. Access to a preconfigured message template can be provided. A command to generate an outgoing message based on the preconfigured message template can be acquired. The outgoing message generated based on the preconfigured message template can be transmitted via the communication system. The outgoing message can be transmitted as a response to the incoming message.

公开(公告)号：US20150302850A1

公开(公告)日：2015-10-22

申请号：US14686770

申请日：2015-04-14

Applicant: Facebook, Inc.

Inventor： Alexandre Lebrun

IPC: G10L15/06 ,  G06F3/16 ,  G10L15/18

CPC classification number: G10L15/18 ,  G06F17/279 ,  G10L15/063

Abstract: An email-like user interface displays a list of user logs determined based on user-specified list criteria to user logs received in a natural language (NL) training environment. The list comprise a subset of the received user logs in order to minimize the number of actions required to configure and train the NL configuration system in a semi-supervised manner, thereby improving the quality and accuracy of NL configuration system. To determine a list of user logs relevant for training the user logs can be filtered, sorted, grouped and searched within the email-like user interface. A training interface to a network of instances that comprises a plurality of NL configuration systems leverages a crowd-sourcing community of developers in order to efficiently create a customizable NL configuration system.

Abstract translation: 类似电子邮件的用户界面显示根据用户指定的列表条件确定的用户日志列表，以用于以自然语言（NL）培训环境接收的用户日志。 该列表包括接收的用户日志的子集，以便以半监督方式最小化配置和训练NL配置系统所需的动作数量，从而提高NL配置系统的质量和准确性。 要确定与培训相关的用户日志列表，可以在类似电子邮件的用户界面中对用户日志进行过滤，排序，分组和搜索。 包括多个NL配置系统的实例网络的训练接口利用开发者的群众来源社区，以便有效地创建可定制的NL配置系统。

公开(公告)号：US20150301795A1

公开(公告)日：2015-10-22

申请号：US14686771

申请日：2015-04-14

Applicant: Facebook, Inc.

Inventor： Alexandre Lebrun

IPC: G06F3/16 ,  G06F17/28

CPC classification number: G10L15/18 ,  G06F17/279 ,  G10L15/063

Abstract: A crowdsourcing based community platform includes a natural language configuration system that predicts a user's desired function call based on a natural language input (speech or text). The system provides a collaboration platform to configure and optimize quickly natural language systems to leverage the work and data of other developers, thus minimizing the time and data required to improve the quality and accuracy of one single system and providing a network effect to reach quickly critical mass of data. An application developer can provide training data for training a model specific to the developer's application. The developer can also obtain training data by forking one or more other applications so that the training data provided for the forked applications is used to train the model for the developer's application.

Abstract translation: 基于众包的社区平台包括基于自然语言输入（语音或文本）预测用户期望的功能呼叫的自然语言配置系统。 该系统提供协作平台，以配置和优化快速自然语言系统，以利用其他开发人员的工作和数据，从而最大限度地减少提高单个系统的质量和准确性所需的时间和数据，并提供网络效应以达到快速关键 大量数据。 应用程序开发人员可以提供培训数据，用于培训专门针对开发人员应用程序的模型。 开发人员还可以通过划分一个或多个其他应用程序来获取培训数据，以便为分叉应用程序提供的培训数据用于培训开发人员应用程序的模型。