-
公开(公告)号：US20210090233A1
公开(公告)日：2021-03-25
申请号：US16582899
申请日：2019-09-25
发明人： Su Liu , Manjunath Ravi , Kai Liu , Shunguo Yan
IPC分类号： G06T7/00 , G06K9/00 , G06F16/583 , G06F16/51
摘要： According to one embodiment, a computer-implemented method includes collecting data corresponding to an image of one or more objects captured by a user on an image capture device, wherein the data comprises biometric data, emotion data, image quality data, and context data. In addition, the computer-implement method includes determining an image quality (IQ) value based on the image quality data, determining an emotion (E) value based on at least one of the biometric data and the emotion data, and determining a relationship (R) value between the one or more objects and the user based on the context data. The computer-implement method includes calculating an Overall Emotional Image Quality Score (OEIQS) for the image based on the IQ value, the E value, and the R value, and categorizing the image into at least one of a plurality of predefined categories.
-
公开(公告)号：US10915572B2
公开(公告)日：2021-02-09
申请号：US16205880
申请日：2018-11-30
IPC分类号： G06F16/583 , G06F16/51 , G06F16/901
摘要： To augment an image caption, a caption graph containing entity nodes corresponding to entities contained in the image and relationship edges between entity nodes corresponding to relationships between entities as illustrated in the image is generated. In addition, a contextual graph containing one or more of entity nodes corresponding to entities contained in the image and described in text associated with the image, textual entity nodes corresponding to textual entities described in text associated with the image and textual relationship edges between entity node pairs, textual entity node pairs and entity node and textual entity node pairs is generated. The textual relationship edges correspond to relationships described in the text associated with the image between entity pairs, textual entity pairs or entity and textual entity pairs. From the contextual graph, an augmented caption graph containing entity nodes, relationship edges, textual entities and textual relationship edges is generated.
-
公开(公告)号：US20210030225A1
公开(公告)日：2021-02-04
申请号：US16530312
申请日：2019-08-02
发明人： Michal Broz , Steven D. Clay , Shunguo Yan , Gabriel Cody Terrell
摘要： Provided is a method, computer program product, and system for leveraging spatial scanning data of an environment collected by a robotic vacuum to generate recommendations for improving environmental conditions. A robotic vacuum may collect cleanliness data relative to an environment. The robotic vacuum may store the cleanliness data over a plurality of cleaning cycles. The robotic vacuum may analyze the cleanliness data over the plurality of cleaning cycles to identify one or more cleanliness trends. The robotic vacuum may generate a recommendation for improving an environmental condition relative to the environment based on the identified one or more cleanliness trends. The robotic vacuum may provide the recommendation to a user.
-
公开(公告)号：US10318094B2
公开(公告)日：2019-06-11
申请号：US14668943
申请日：2015-03-25
IPC分类号： G06F17/27 , G06F9/451 , G06F3/0481 , G06F3/0484
摘要： A method of providing guidance in connection with a technological task includes determining, from an interaction of an end user with a computer system, a current context and task of the end user, identifying a change in a cognitive state of the end user, where the change in the cognitive state is associated with performance of the task using the computer system, searching a plurality of user experiences corresponding to the change in the cognitive state of the end user and the user's current context, selecting at least one of the user experiences according to a selection parameter for determining a selected user experience, and injecting the selected user experience into the current context of the end user via an output device of the computer system.
-
公开(公告)号：US20190095833A1
公开(公告)日：2019-03-28
申请号：US16196505
申请日：2018-11-20
摘要： Balancing a workload based on commitments to projects includes monitoring messages in a collaboration system, the messages representing correspondences between users of the collaboration system, selecting a number of the users associated with the collaboration system to form a group of users, retrieving the messages from each of the users in the group of users, analyzing data associated with the messages to determine which of the messages relate to at least one project, and executing, based on a threshold, at least one action to optimize a workload for at least one user in the group of users for the at least one project.
-
公开(公告)号：US10169188B2
公开(公告)日：2019-01-01
申请号：US14944369
申请日：2015-11-18
发明人： Rahul R. Belekar , Ankur Gupta , Shunguo Yan
IPC分类号： G06F3/14 , G06F11/36 , G06F3/0481 , G06F3/0484 , G06F9/451
摘要： From an element hierarchy of a User Interface (UI), a UI element that is selected for inclusion in the UI at runtime is determined. A category of the UI element is determined. A subset of a set of accessibility compliance rules is associated with the UI element. The subset of accessibility compliance rules corresponds to the category of the UI element. The UI element is analyzed to determine that the UI element fails to satisfy an accessibility compliance rule in the subset of accessibility compliance rules. Responsive to the analyzing, in an accessibility compliance report, a violation information is output describing the UI element and the accessibility compliance rule from the subset of accessibility compliance rules.
-
公开(公告)号：US10168890B2
公开(公告)日：2019-01-01
申请号：US14710677
申请日：2015-05-13
IPC分类号： G06F17/00 , G06F3/0488 , G06F17/24 , G06F17/21 , G06F3/0484 , G06F17/22
摘要： Embodiments of the present invention provide a method, system and computer program product for document content re-ordering for assistive technology processing. In an embodiment of the invention, a method for document content re-ordering for assistive technology processing is provided. The method includes sensing in a computer display a drawing of a path across different portions of displayed content in the computer display. Thereafter, a sequence of the different portions of the displayed content can be identified from the path. As such, meta-data indicative of the sequence can be generated in the memory of the computer and the content can be annotated with the generated meta-data. Finally, the portions of the content can be processed with assistive technology in an order dictated by the sequence.
-
公开(公告)号：US10108587B2
公开(公告)日：2018-10-23
申请号：US14833238
申请日：2015-08-24
发明人： John C. Emmons , Denise M. Genty , Su Liu , Shunguo Yan
摘要： For dynamically changing a rendering of content, the content including a textual character is received at a mobile device. An encoding of the textual character uses a first code point according to a character encoding standard. The mobile device's presence at a geographical location is detected. The mobile device is associated with a user. A variant selection rule is selected at the device. The variant selection rule specifies a location based condition to select a variant corresponding to the textual character. A variant is selected at the device according to the variant selection rule, a variant mapping corresponding to the first code point. The variant mapping includes the variant. The encoding of the textual character is replaced at the device with an encoding of the variant in the rendering of the content.
-
公开(公告)号：US10083015B2
公开(公告)日：2018-09-25
申请号：US15379842
申请日：2016-12-15
发明人： Shunguo Yan
摘要： An approach is provided that identifies interface changing events in the binary executable of an application. The approach generates code modules that are directed at evaluating accessibility requirements pertaining to the identified interface changing events. A modified binary of the application is created with the modified binary including the binary executable and the generated code modules. The modified binary is then executed. When one of the interface changing events is encountered, one of the generated code modules is executed and this code module returns a set of accessibility data that pertains to the interface changing event.
-
公开(公告)号：US20180089214A1
公开(公告)日：2018-03-29
申请号：US15813185
申请日：2017-11-15
发明人： Michal Broz , Steven D. Clay , John C. Sanchez , Richard S. Schwerdtfeger , Lisa Seeman , Shunguo Yan
CPC分类号： G06F16/90324 , A61B5/168 , A61B5/4088 , G06F16/907 , G06Q30/00 , G06Q30/0601
摘要： A method for generating and presenting accessibility resolution models to accessibility problems is provided. The method may include detecting user behavior patterns associated with users. The method may further include generating user groups and subgroups based on the detected user behavior patterns. Additionally, the method may include identifying accessibility problems based on the detected user behavior patterns and the generated user groups and subgroups. The method may also include generating accessibility profiles based on the detected user behavior patterns, the generated user groups and subgroups, and the identified accessibility problems. The method may further include determining correlations between the generated accessibility profiles and business loss indicators. The method may also include generating and presenting accessibility resolution models to the identified accessibility problems based on the detected user behavior patterns, the generated user groups and subgroups, and the determined correlations between the generated accessibility profiles and business loss indicators.
-
-
-
-
-
-
-
-
-
搜索结果
115 条记录 (耗时 0.029 秒)
