知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.014 seconds)

    Methods and systems for performing end-to-end spoken language analysis
    2.
    发明授权
    Methods and systems for performing end-to-end spoken language analysis 有权

    公开(公告)号：US11107462B1

    公开(公告)日：2021-08-31

    申请号：US16175086

    申请日：2018-10-30

    Applicant: Facebook, Inc.

    Inventor： Christian Fuegen ,  Yongquiang Wang ,  Anuj Kumar ,  Baiyang Liu ,  Dmitrii Serdiuk

    IPC: G10L15/22 ,  G10L15/18 ,  G10L15/16

    Abstract: Exemplary embodiments relate to improvements in spoken language understanding (SLU) systems. Conventionally, SLU systems include an automatic speech recognition (ASR) component configured to receive an input of audio data and to generate a textual representation of the audio data. Conventional SLU systems also include a natural language understanding (NLU) component configured to receive a text-based transcript and perform language-based tasks such as domain classification, intent determination, and slot-filling. However, these two components are typically trained separately based on different metrics. In real-world situations, errors in the ASR component propagate to the NLU component, which degrades the performance of the overall system. Exemplary embodiments described herein perform SLU in an end-to-end manner that infers semantic meaning directly from audio features without an intermediate text representation. This may allow for more a more accurate translation performed in a more resource-efficient manner (particularly in terms of processing resources).

    Generating Personalized Content Summaries for Users
    3.
    发明申请
    Generating Personalized Content Summaries for Users 审中-公开

    公开(公告)号：US20190325084A1

    公开(公告)日：2019-10-24

    申请号：US15967290

    申请日：2018-04-30

    Applicant: Facebook, Inc.

    Inventor： Fuchun Peng ,  Fei Sha ,  Kun Han ,  Wenhai Yang ,  Anuj Kumar ,  Michael Robert Hanson ,  Benoit F. Dumoulin

    IPC: G06F17/30 ,  H04L29/08 ,  G06Q50/00 ,  G06F15/18

    Abstract: In one embodiment, a method includes receiving a user request for a summarization of a particular type of content objects from a client system associated with a first user, determining one or more modalities associated with the user request, selecting a plurality of content objects of the particular type based on a user profile of the first user, wherein the user profile comprises one or more confidence scores associated with one or more subjects associated with the first user, respectively, and wherein the plurality of content objects are selected based on the one or more confidence scores, generating a summary of each content object based on the user profile and the determined modalities, and sending, to the client system in response to the user request, instructions for presenting the summaries of the plurality of content objects, wherein the summaries are presented via one or more of the determined modalities.

    Systems and methods for distributing intent models
    4.
    发明授权
    Systems and methods for distributing intent models 有权

    公开(公告)号：US10452782B1

    公开(公告)日：2019-10-22

    申请号：US15900703

    申请日：2018-02-20

    Applicant: Facebook, Inc.

    Inventor： Anuj Kumar ,  Benoit F. Dumoulin

    IPC: G06F17/27 ,  G06Q30/06 ,  G06N20/00

    Abstract: Systems, methods, and non-transitory computer-readable media can receive, from a first entity, training data for training an intent model associated with a first intent of a plurality of intents. A first intent model associated with the first intent is generated based on the training data. The first intent model is made available in an intent marketplace for access by a second entity.

    Techniques for database versioning
    5.
    发明授权
    Techniques for database versioning 有权

    公开(公告)号：US11086845B1

    公开(公告)日：2021-08-10

    申请号：US16236369

    申请日：2018-12-29

    Applicant: Facebook, Inc.

    Inventor： Rushin Shah ,  Anuj Kumar ,  Ted Li ,  Wei Chen ,  Shusen Liu

    IPC: G06F16/23 ,  G06F16/22 ,  G06F16/21 ,  G06N20/00

    Abstract: Techniques for database versioning are described. In one embodiment, an apparatus may comprise a database change management component operative to compare a developer table to a reference table to determine a database change set, wherein both the developer table and the reference table are based on a target table; a database conflict management component operative to compare the database change set to the target table to determine a conflicting change set; and a user interface component operative to display the conflicting change set where the conflicting change set comprises one or more conflicting changes; and indicate a conflict-free change set where the conflicting change set is empty. Other embodiments are described and claimed.

    Building Customized User Profiles Based on Conversational Data
    7.
    发明申请
    Building Customized User Profiles Based on Conversational Data 审中-公开

    公开(公告)号：US20190327330A1

    公开(公告)日：2019-10-24

    申请号：US15967239

    申请日：2018-04-30

    Applicant: Facebook, Inc.

    Inventor： Vivek Natarajan ,  Wenhai Yang ,  Honglei Liu ,  Anuj Kumar

    IPC: H04L29/08 ,  G06Q50/00 ,  H04L12/58 ,  G06F17/30 ,  G06F15/18

    Abstract: In one embodiment, a method includes accessing a plurality of content objects associated with a first user from an online social network, accessing a baseline profile, wherein the baseline profile is based on ontology data from one or more information graphs, accessing conversational data associated with the first user, determining one or more subjects associated with the first user based on the plurality of content objects and conversational data associated with the first user, and generating a customized user profile for the first user based on the baseline profile, wherein the user profile comprises one or more confidence scores associated with the respective one or more subjects associated with the first user, wherein the one or more confidence scores are calculated based on the plurality of content objects associated with the first user and the conversational data associated with the first user.

    INTENT ARBITRATION FOR A VIRTUAL ASSISTANT
    8.
    发明申请
    INTENT ARBITRATION FOR A VIRTUAL ASSISTANT 审中-公开

    公开(公告)号：US20190205386A1

    公开(公告)日：2019-07-04

    申请号：US16211414

    申请日：2018-12-06

    Applicant: Facebook, Inc.

    Inventor： Anuj Kumar ,  Benoit Dumoulin ,  Wenhai Yang ,  Rajen Subba

    IPC: G06F17/27 ,  G06F9/451 ,  G06N5/04 ,  G06N20/00

    CPC classification number: G06F17/2785 ,  G06F9/453 ,  G06N5/043 ,  G06N5/046 ,  G06N20/00

    Abstract: A user interacts with a virtual digital assistant with the intent that it provides assistance with a task. The user sends messages to the virtual digital assistant that include content obtained via user input at a client device. An intent determination model is applied to the content to identify the user's intent. The virtual digital assistant identifies agents that are capable of servicing the intent are identified and retrieves contextual data relating to the message from a data store. An intent arbitration model is used to select one of the agents which is activated to provide assistance with the task. The contextual information may include global metrics of agent performance and/or information regarding the user's preferences.

Patent Agency Ranking