中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

31 records (took 0.023 seconds)

    A DRIVER MONITORING AND RESPONSE SYSTEM
    1.
    发明申请
    A DRIVER MONITORING AND RESPONSE SYSTEM 有权

    公开(公告)号：US20210129748A1

    公开(公告)日：2021-05-06

    申请号：US16472760

    申请日：2017-12-19

    Applicant: SRI International ,  Toyota Motor Corporation

    Inventor： Amir Tamrakar ,  Girish Acharya ,  Makoto Okabe ,  John James Bymes

    IPC: B60Q9/00 ,  G06K9/00 ,  G06F3/16 ,  A61B5/18 ,  A61B5/16 ,  A61B5/11 ,  A61B5/00

    Abstract: An evaluation engine has two or more modules to assist a driver of a vehicle. A driver drowsiness module analyzes monitored features of the driver to recognize two or more levels of drowsiness of the driver of the vehicle. The driver drowsiness module evaluates drowsiness of the driver based on observed body language and facial analysis of the driver. The driver drowsiness module is configured to analyze live multi-modal sensor inputs from sensors against at least one of i) a trained artificial intelligence model and ii) a rules based model while the driver is driving the vehicle to produce an output comprising a driver drowsiness-level estimation. A driver assistance module provides one or more positive assistance mechanisms to the driver to return the driver to be at or above the designated level of drowsiness.

    Techniques for user-centric document summarization
    5.
    发明授权
    Techniques for user-centric document summarization 有权

    公开(公告)号：US10984027B2

    公开(公告)日：2021-04-20

    申请号：US16088745

    申请日：2016-11-11

    Applicant: SRI International

    Inventor： Girish Acharya ,  John Niekrasz ,  John Byrnes ,  Chih-Hung Yeh

    IPC: G06F16/33 ,  G06F16/9535 ,  G06F16/34 ,  G06F40/20 ,  G06F40/205 ,  G06F40/258

    Abstract: Disclosed techniques can generate content object summaries. Content of a content object can be parsed into a set of word groups. For each word group, at least one topic to which the word group pertains can be identified and it can be determined, via a user model, at least one weight of the plurality of weights corresponding to the topic(s). For each word group, a score can be determined for the word group based on the weight(s). A subset of the set of word groups can be selected based on the scores for the word group. A summary of the content object can be generated that includes the subset but that does not include one or more other word groups in the set of word groups that are not in the subset. At least part of the summary of the content object can be output.

    SELECTING OPTIMAL IMAGE FROM MOBILE DEVICE CAPTURES
    6.
    发明申请
    SELECTING OPTIMAL IMAGE FROM MOBILE DEVICE CAPTURES 审中-公开

    公开(公告)号：US20190356844A1

    公开(公告)日：2019-11-21

    申请号：US16530774

    申请日：2019-08-02

    Applicant: SRI International

    Inventor： David Chao Zhang ,  John Benjamin Southall ,  Michael Anthony Isnardi ,  Michael Raymond Piacentino ,  David Christopher Berends ,  Girish Acharya ,  Douglas A. Bercow ,  Aaron Spaulding ,  Sek Chai

    IPC: H04N5/232 ,  G06T7/11 ,  A61B5/00 ,  G06K9/62 ,  G06T5/20 ,  G06K9/00 ,  H04N5/235 ,  G06K9/03 ,  G06T7/00

    Abstract: Embodiments of the disclosed technologies include a method of capturing, using a mobile device, a best-focused image of a skin surface of a subject, the method including: setting a camera of the mobile device to a fixed focal length; capturing, using the camera, a current image of a plurality of images of the skin surface, the plurality of images having a sequence and including a first previous image captured, using the camera, previously to the current image and a second previous image captured, using the camera, previously to the first previous image; producing a modified image from the current image; transforming the modified image, using a Laplacian pyramid, to produce a plurality of first luminance values from the modified image and a plurality of second luminance values from the plurality of first luminance values; averaging a plurality of first squared values, each including a square of a corresponding first luminance value of the plurality of first luminance values, to produce a first energy value; averaging a plurality of second squared values, each including a square of a corresponding second luminance value of the plurality of second luminance values, to produce a second energy value; calculating a first ratio of the first energy value to the second energy value; calculating, as an average first energy value of the first previous image, an average of the first energy value, a corresponding first energy value of the first previous image, and a corresponding first energy value of the second previous image; calculating, as an average first ratio of the first previous image, an average of the first ratio, a corresponding first ratio of the first previous image, and a corresponding first ratio of the second previous image; determining that the first previous image is one of a plurality of valid images, where each valid image of the plurality of valid images is an image of the plurality of images and has: a corresponding average first energy value above an energy threshold value; and a corresponding average first ratio approximately equal to 1.0; determining that a first valid image of the plurality of valid images is the best-focused image, where the first valid image has a corresponding average first energy value that is greater than the corresponding average first energy values of: a previous valid image captured immediately before the first valid image; and a subsequent valid image captured immediately after the first valid image; and performing an action associated with the best-focused image.

    MULTI-LINGUAL VIRTUAL PERSONAL ASSISTANT
    8.
    发明申请
    MULTI-LINGUAL VIRTUAL PERSONAL ASSISTANT 审中-公开

    公开(公告)号：US20190332680A1

    公开(公告)日：2019-10-31

    申请号：US16509428

    申请日：2019-07-11

    Applicant: SRI International

    Inventor： Wen Wang ,  Dimitra Vergyri ,  Girish Acharya

    IPC: G06F17/28 ,  G06F16/9032 ,  G10L15/07 ,  G10L15/22 ,  G10L15/18 ,  G06F17/27

    Abstract: Provided are systems, computer-implemented methods, and computer-program products for a multi-lingual device, capable of receiving verbal input in multiple languages, and further capable of providing conversational responses in multiple languages. In various implementations, the multi-lingual device includes an automatic speech recognition engine capable of receiving verbal input in a first natural language and providing a textual representation of the input and a confidence value for the recognition. The multi-lingual device can also include a machine translation engine, capable of translating textual input from the first natural language into a second natural language. The machine translation engine can output a confidence value for the translation. The multi-lingual device can further include natural language processing, capable of translating from the second natural language to a computer-based language. Input in the computer-based language can be processed, and the multi-lingual device can take an action based on the result of the processing.

    VIRTUAL HEALTH ASSISTANT FOR PROMOTION OF WELL-BEING AND INDEPENDENT LIVING
    9.
    发明申请
    VIRTUAL HEALTH ASSISTANT FOR PROMOTION OF WELL-BEING AND INDEPENDENT LIVING 审中-公开

    公开(公告)号：US20190108841A1

    公开(公告)日：2019-04-11

    申请号：US16088737

    申请日：2017-06-03

    Applicant: SRI International

    Inventor： Dimitra Vergyri ,  Diego Castan Lavilla ,  Girish Acharya ,  David Sahner ,  Elizabeth Shriberg ,  Joseph B Rogers ,  Bruce H Knoth

    IPC: G10L17/00 ,  A61B5/117 ,  A61B5/00 ,  G10L17/06 ,  G10L25/78

    Abstract: An electronic device for providing health information or assistance includes an input configured to receive at least one type of signal selected from sound signals, verbal signals, non-verbal signals, and combinations thereof, a communication module configured to send information related to the at least one user and his/her environment to a remote device, including the sound signals, non-verbal signals, and verbal signals, the remote device being configured to analyze a condition of the at least one user and communicate condition signals to the electronic device, a processing module configured to receive the condition signals and to cause the electronic device to engage in a passive monitoring mode or an active engagement and monitoring mode, the active engagement and monitoring mode including, but not limited to, verbal communication with the at least one user, and an output configured to engage the at least one user in verbal communication.

Patent Agency Ranking