-
公开(公告)号：US11663851B2
公开(公告)日：2023-05-30
申请号：US16790672
申请日：2020-02-13
发明人： Justin David Weisz , Abhishek Bhandwaldar , Maryam Ashoori , Arunima Chaudhary , Benjamin Hoover
CPC分类号： G06V40/168 , G06N5/02 , G06V10/761 , G06V20/46 , G06V40/20 , G08B21/24 , G10L25/51
摘要： An implicit bias monitoring system is provided. The system receives sensor data including video and audio that are captured during an interaction between a first individual and a second individual. The system determines a set of attributes associated with the interaction based on the received sensor data, the set of attributes comprising at least one of race and gender of the second individual. The system detects an implicit bias based on a combination of the determined set of attributes and a bias profile. The system generates an alert based on the detected implicit bias.
-
公开(公告)号：US20210256832A1
公开(公告)日：2021-08-19
申请号：US16790672
申请日：2020-02-13
发明人： Justin David Weisz , Abhishek Bhandwaldar , Maryam Ashoori , Arunima Chaudhary , Benjamin Hoover
摘要： An implicit bias monitoring system is provided. The system receives sensor data including video and audio that are captured during an interaction between a first individual and a second individual. The system determines a set of attributes associated with the interaction based on the received sensor data, the set of attributes comprising at least one of race and gender of the second individual. The system detects an implicit bias based on a combination of the determined set of attributes and a bias profile. The system generates an alert based on the detected implicit bias.
-
公开(公告)号：US10922365B2
公开(公告)日：2021-02-16
申请号：US14856194
申请日：2015-09-16
IPC分类号： G06F16/9535 , G06Q10/10 , G06Q10/06 , G06Q50/00
摘要： Methods and systems for matching users include measuring a biometric state of a first user. The biometric state of the first user is matched to a set of biometric states of respective other users. The set of biometric states is limited in accordance with user preferences including how recently each biometric state was measured. A real-time connection is formed with a second user from the limited set of biometric states having a best match.
-
公开(公告)号：US10693827B2
公开(公告)日：2020-06-23
申请号：US16172949
申请日：2018-10-29
发明人： Maryam Ashoori , Justin David Weisz
IPC分类号： G06F15/16 , H04L12/58 , H04L29/08 , H04L29/06 , G06F40/253 , G06F40/263
摘要： A method for checking against transmitting a message to an unintended recipient, includes developing, using a processor on a computer, a training model of a linguistic profile of messages previously transmitted electronically by a user to a recipient, by iteratively computing a composite feature vector over a set of all messages previously transmitted electronically to the recipient, the iterations for developing the training model continuing until summed proportional changes across all features falls below a first preset threshold value.
-
公开(公告)号：US10665066B2
公开(公告)日：2020-05-26
申请号：US16007226
申请日：2018-06-13
IPC分类号： G08B3/00 , G08B5/36 , G06F3/14 , G06F1/16 , G06F3/01 , A41D1/00 , H04W4/50 , H04W4/02 , G06F3/16
摘要： A system includes, but is not limited to, a hardware controller for adjusting a dynamically modifiable display on a garment; and an environmental dominant hue sensor that detects a real-time dominant hue of an environment in which the garment is located, where the hardware controller adjusts the dynamically modifiable display based on a real-time detected dominant hue of the environment in which the garment is located in order to increase a color contrast between the dynamically modifiable display and the real-time detected dominant hue of the environment in which the garment is located.
-
公开(公告)号：US10580435B2
公开(公告)日：2020-03-03
申请号：US15822854
申请日：2017-11-27
摘要： Monitoring and analysis of a user's speech to detect symptoms of a mental health disorder by continuously monitoring a user's speech in real-time to generate audio data based, transcribing the audio data to text and analyzing the text of the audio data to determine a sentiment of the audio data is disclosed. A trained machine learning model may be applied to correlate the text and the determined sentiment to clinical information associated with symptoms of a mental health disorder to determine whether the symptoms are a symptom event. The initial determination may be transmitted to a second device to determine (and/or verify) whether or not the symptom event was falsely recognized. The trained machine learning model may be updated based on a response from the second device.
-
公开(公告)号：US10393355B2
公开(公告)日：2019-08-27
申请号：US15447340
申请日：2017-03-02
摘要： A cognitive illumination system is provided. The cognitive illumination system includes a light source communicatively coupled to a servomechanism, wherein the servomechanism is configured to manipulate the light source in space, a tracking assembly configured to capture and track objects in the space and a processor communicatively coupled to the light source, the servomechanism and the tracking assembly. The processor is configured to receive information about the captured and tracked objects from the tracking assembly, determine a task being undertaken in the space therefrom, develop a lighting plan for the task which is executable by the light source and the servomechanism and control the light source and the servomechanism according to the lighting plan.
-
公开(公告)号：US20180366143A1
公开(公告)日：2018-12-20
申请号：US15626782
申请日：2017-06-19
CPC分类号： G10L25/66 , G06N99/005 , G10L15/02 , G10L15/063 , G10L15/1815 , G10L2015/0635 , G16H50/20
摘要： Monitoring and analysis of a user's speech to detect symptoms of a mental health disorder by continuously monitoring a user's speech in real-time to generate audio data based, transcribing the audio data to text and analyzing the text of the audio data to determine a sentiment of the audio data is disclosed. A trained machine learning model may be applied to correlate the text and the determined sentiment to clinical information associated with symptoms of a mental health disorder to determine whether the symptoms are a symptom event. The initial determination may be transmitted to a second device to determine (and/or verify) whether or not the symptom event was falsely recognized. The trained machine learning model may be updated based on a response from the second device
-
公开(公告)号：US20180315093A1
公开(公告)日：2018-11-01
申请号：US15583221
申请日：2017-05-01
发明人： Maryam Ashoori , Benjamin D. Briggs , Lawrence A. Clevenger , Leigh Anne H. Clevenger , Michael Rizzolo
摘要： A computer implemented method and system for identifying advertisements targeted to individuals based on analysis of audio recordings. The method includes recording audio input from at least one media transmission, analyzing the recorded media audio to identify content of the at least one media transmission, recording audio input from at least one individual, analyzing the recorded individual audio to classify the at least one individual into at least one segment, analyzing the recorded individual audio to identify at least one sentiment related to the identified media content, analyzing the at least one sentiment in context with the identified media content and identifying at least one advertisement targeted to the at least one segment based on the contextual analysis.
-
公开(公告)号：US10042874B2
公开(公告)日：2018-08-07
申请号：US14618278
申请日：2015-02-10
发明人： Maryam Ashoori , Jin Li
CPC分类号： G06F16/2246 , B60K2370/11 , G06F9/451 , G06F16/248 , G06F16/282 , G06F16/86
摘要： A method for generating a scalable visualization of a hierarchical data structure is provided. The method may include mapping at least one component within a plurality of components to the hierarchical data structure. The method may also include mapping at least one sub-component within a plurality of sub-components to the at least one mapped component. The method may further include mapping at least one variant within a plurality of variants to the hierarchical data structure as an accordion user interface widget. Additionally, the method may include mapping at least one variant component within a plurality of variant components to the at least one mapped variant as an accordion user interface widget. The method may also include mapping at least one variant sub-component within a plurality of variant sub-components to the at least one mapped variant component as an accordion user interface widget.
-
-
-
-
-
-
-
-
-
搜索结果
67 条记录 (耗时 0.028 秒)
