Abstract: One embodiment provides an apparatus for displaying an image comprising: a first optical substrate comprising at least one waveguide layer configured to propagate light in a first direction, wherein the at least one waveguide layer of the first optical substrate comprises at least one grating lamina configured to extract the light from the first substrate along the first direction; and a second optical substrate comprising at least one waveguide layer configured to propagate the light in a second direction, wherein the at least one waveguide layer of the second optical substrate comprises at least one grating lamina configured to extract light from the second substrate along the second direction; wherein the at least one grating lamina of at least one of the first and second optical substrates comprises an SBG in a passive mode.

Abstract: Disclosed embodiments provide a computer-implemented technique for selection and/or modification of surgical simulation scenarios based on patient similarity cohort identification. Prior to undergoing surgery, medical information of a patient, including genomic, physiological, and/or environmental data, is used to identify a patient cohort. The patient cohort represents a statistically significant sample size of similar patients, and complications that may have arose during similar surgical procedures to the procedure planned for the patient. Relevant scenarios are identified based on the patient cohort. These scenarios are then input to a surgical simulation system. The surgical simulation system may be implemented by virtual reality, augmented reality, and/or physical workpieces used for surgical practice and training.

Abstract: Disclosed embodiments provide a computer-implemented technique for selection and/or modification of surgical simulation scenarios based on patient similarity cohort identification. Prior to undergoing surgery, medical information of a patient, including genomic, physiological, and/or environmental data, is used to identify a patient cohort. The patient cohort represents a statistically significant sample size of similar patients, and complications that may have arose during similar surgical procedures to the procedure planned for the patient. Relevant scenarios are identified based on the patient cohort. These scenarios are then input to a surgical simulation system. The surgical simulation system may be implemented by virtual reality, augmented reality, and/or physical workpieces used for surgical practice and training.

Abstract: Techniques are described with respect to managing device maintenance. An associated method includes constructing a machine learning knowledge model associated with a plurality of devices in a client ecosystem based upon at least one course of device evaluation. The method further includes collecting, from a plurality of device sensors, device sensor data associated with each of the plurality of devices and collecting, from a plurality of environmental sensors, environmental sensor data associated with each of the plurality of devices. The method further includes analyzing, via the machine learning knowledge model, the device sensor data in view of the environmental sensor data to determine a failure risk value for each of the plurality of devices. Responsive to the failure risk value for any device among the plurality of devices exceeding a predefined failure risk threshold, the method further includes facilitating activation of the device for a designated duration of time.

Abstract: The context in which a user generates a search query is analyzed to generate an improved search query. Search query context may be determined with reference to a user profile or content collected from Internet of Things (IoT) or non-IoT devices located proximate the user. Content may be collected when the search query is generated or at a time before the search query is generated. Content collected for context analysis includes visual display content (screen capture), audio content, and data content.

Abstract: Using natural language analysis of content at URLs accessed by a user, content metadata is generated. From the content metadata and from activity information associated with a set of URLs accessed by the user, a class model is generated that represents a probability that content referenced by a URL will distract the user. Using the class model to analyze content referenced by a received URL, a probability is forecasted that the content referenced by the received URL will distract the user.

Abstract: Approaches presented herein enable evaluating a multimedia item to be posted to a website (e.g., social networking site, forum, blog, etc.) to determine whether a censoring action needs to be performed on the multimedia item prior to posting the multimedia item. Specifically, in response to a request to post a multimedia item to a website, the multimedia item is analyzed to determine a context of the multimedia item. The context may be derived from specific elements depicted in the multimedia item. Also, an entity (e.g., a person, logo, trademark, brand) may be identified. The preferences related to the entity are retrieved. The context is compared against the preferences of the entity to determine whether a variance exists. When a variance is determined, a censoring action related to the multimedia item may be performed prior to posting the multimedia item.

Abstract: Techniques are described with respect to adjusting image capture parameters. An associated method includes constructing an image capture learning model based upon data collection. The method further includes receiving, via at least one lens of an image capture device, at least one captured image from a client and parsing the at least one captured image to identify a plurality of discrete objects. The method further includes assigning a relevancy score to each of the plurality of discrete objects in the at least one captured image based upon analysis of a plurality of contextual inputs in view of the image capture learning model and determining at least one captured image modification option. Each of the at least one captured image modification option includes at least one photographic adjustment to the plurality of discrete objects in the at least one captured image based upon assigned relevancy score.

Abstract: Aspects of the present invention provide an approach for dynamically adapting an Internet of Things (IOT) device in an existing intelligent system. In an embodiment, in response to a new IOT device being added to an intelligent system, a replacement score is determined for each existing IOT device in the system. The replacement score for a given existing IOT device can indicate: (i) an amount of overlapping capabilities between the existing IOT device and the new IOT device, (ii) an amount of additional capabilities of the new IOT device over the existing IOT device, (iii) an amount of performance improvement of the new IOT device over the existing IOT device, and/or the like. In response to the replacement score for an existing IOT device exceeding a predefined threshold, a proposed reconfiguration of the existing intelligent system is generated.

Abstract: Disclosed embodiments provide techniques for expanding user-chatbot conversations to include other relevant users. In some embodiments, the users are deemed to potentially be interested in learning information regarding the conversation topic. In other embodiments, the users are deemed to be potentially able to provide additional information regarding the conversation topic. In embodiments, a submitted question to a chatbot in a conversation on a messaging platform is received. The topic of the submitted question is identified. A probability that one or more additional users would benefit from an answer to the submitted question is determined. One or more additional users are invited to the conversation based on the determined probability that one or more additional users would benefit from an answer to, and/or provide information regarding, the submitted question.

Abstract: Systems and methods for dynamic contribution mapping of digital works are disclosed. In embodiments, a computer-implemented method, comprises: capturing, by a computing device, an IP address of a user signing into a content management system through a user computer device; determining, by the computing device, that the IP address of the user does or does not match existing user profile data in a user profile database; determining, by the computing device, that the user is modifying a portion of a digital work; determining, by the computing device, an engagement context of the user's modification of the digital work using natural language processing; determining, by the computing device, an engagement type of the user based on the engagement context; and mapping, by the computing device, the user profile data of the user and the engagement type with the portion of the digital work.

Abstract: Disclosed embodiments provide techniques for automatically suggesting members of a social media system as recipients for sharing an item of social media content. Computerized analysis of the social media content includes image analysis, audio analysis, and language analysis for classifying the content. Profiles of participants within a social media system are examined to determine candidates for sharing. A subset of participants having profiles with metadata deemed relevant to the analyzed social media content is obtained. For each participant in the subset, an interaction score is computed, indicative of the amount of interaction between the participant and the sender of the content has occurred previously. The subset is ranked based on the interaction score. Participants having an interaction score above a predetermined threshold are deemed to be candidates for sharing the item of social media content, and are presented to a user on an electronic display.

Abstract: Techniques are described with respect to adjusting image capture parameters. An associated method includes constructing an image capture learning model based upon data collection. The method further includes receiving, via at least one lens of an image capture device, at least one captured image from a client and parsing the at least one captured image to identify a plurality of discrete objects. The method further includes assigning a relevancy score to each of the plurality of discrete objects in the at least one captured image based upon analysis of a plurality of contextual inputs in view of the image capture learning model and determining at least one captured image modification option. Each of the at least one captured image modification option includes at least one photographic adjustment to the plurality of discrete objects in the at least one captured image based upon assigned relevancy score.

Abstract: Methods, systems, and computer program products for internet of things (IoT) network context dependent communication responses are provided. Aspects include receiving, by a processor, a communication request for a user, obtaining IoT network contextual data for one or more IoT network devices, determining a user context based at least in part on the IoT network contextual data, and generating a response to the communication request based on the user context.

Abstract: Embodiments of the invention include computer-implemented methods, computer program products and systems for live video anomaly detection. The embodiments include detecting live stream data, determining an activity from the live stream data, and receiving contextual data associated with the live stream data. The embodiments also include prompting a user to redirect the live stream data from a first channel based on the activity and the contextual data, and redirecting, responsive to the prompt, the live stream data to a different channel and simultaneously maintaining the live stream data on the first channel.

Abstract: A mobile device, computer program product for a mobile device and a computer-implemented method of operating a mobile device is disclosed. The mobile device includes a sensor, an animal database and a processor. The sensor receives data regarding an animal proximate the mobile device. The processor compares the data to the animal database to determine a type of animal at the mobile device, and performs an action on the mobile device based on the type of animal in order to manipulate a behavior of the animal.

Abstract: A method, computer program product, and system includes a processor(s) obtaining a hashtag and analyzing the hashtag to identify components comprising the hashtag. The processor(s) generate sub-hashtags, where each of the sub-hashtags includes at least one component. The processor(s) obtain, over an Internet connection, via a user interface of a social media platform displayed on a first computing resource, an entry by a user comprising text and the hashtag. The processor(s) obtains from a second computing resource, a request from a second user to access the entry that includes parameters of the second user on the platform. The processor(s) determine that a sub-hashtag is most relevant to the second user. The processor(s) configure instructions to display a customized entry, where the customized entry includes the text and the relevant sub-hashtag for the second user. The processor(s) instruct the second computing resource to display the customized entry in its user interface.

Abstract: In an aspect of the present disclosure, a method for providing an alternate modality of input for filling a form field in response to a failure of voice recognition is disclosed including prompting the user for information corresponding to a field of a form, generating speech data by capturing a spoken response of the user to the prompt using at least one input device, attempting to convert the speech data to text, determining that the attempted conversion has failed, evaluating the failure using at least one speech rule, selecting, based on the evaluation, an alternate input modality to be used for receiving the information corresponding to the field of the form, receiving the information corresponding to the field of the form from the alternate input modality, and injecting the received information into the field of the form.

Abstract: Embodiments for phased collaborative editing by a processor. A region tag of phased input may be assigned to one or more document regions of a collaborative document along with a list of users enabled to input data to the one or more document regions according to the region tag. A concealed region of the one or more document regions may be revealed to one or more users in the list of users upon content input by a user matching content of the concealed region.

Abstract: Techniques are described with respect to managing device maintenance. An associated method includes constructing a machine learning knowledge model associated with a plurality of devices in a client ecosystem based upon at least one course of device evaluation. The method further includes collecting, from a plurality of device sensors, device sensor data associated with each of the plurality of devices and collecting, from a plurality of environmental sensors, environmental sensor data associated with each of the plurality of devices. The method further includes analyzing, via the machine learning knowledge model, the device sensor data in view of the environmental sensor data to determine a failure risk value for each of the plurality of devices. Responsive to the failure risk value for any device among the plurality of devices exceeding a predefined failure risk threshold, the method further includes facilitating activation of the device for a designated duration of time.