Abstract: The present disclosure relates to devices, systems and methods providing evaluation and feedback to an operator of a device providing neuromodulation treatment, such as modulation of renal nerves of a human patient. In one embodiment, for example, a system monitors parameters or values generated before treatment. Feedback provided to an operator is based on the monitored values and relates to an assessment of various electrical properties associated with an electrode carried by a catheter. The electrode measures an electrical property of biological material making contact with the electrode while deploying the electrode, the electrical property being dependent on a ratio of a wall-interface area to a fluid-interface area.

Abstract: Described herein are mechanisms to allow users to access functionality of applications in a suite of applications. In a first aspect, when a query relating to functionality of an application is received from a user, an index containing both top-level and sub-level functionality is searched. Results are ranked using a trained machine learning model using both context describing user interactions and the search results. A subset of the ranked results are presented to the user as options. In a second aspect the index can comprise entries describing functionality from other applications so that results presented to the user can include cross-application functionality. In a third aspect, the index can be searched using the context prior to receiving a query and adjusting the user interface based on the results. In a fourth aspect, the system can recommend other applications and/or devices that are better suited to a user's intent.

Abstract: A method and system for providing one or more suggested application features to a user of an application may include receiving an indication of a user action in a document, accessing contextual document data associated with the document, providing at least one of information about the user action or the contextual document data as input to a machine-learning (ML) model to predict a desired intent for the document, obtaining the predicted desired intent as an output from the ML model, identifying based on the predicted desired intent one or more application features that fulfil the desired intent, and providing data about the one or more application features for display.

Abstract: A method and system for intelligently organizing one or more groups of relevant files may include retrieving a user data signal including user-specific data, analyzing the user data signal to identify a parameter relating to file relevance, identifying one or more relevant files in a storage medium based on the parameter at least one of a user category property, a lifecycle stage property, a relevant activity property, or an activity level property of one or more files in the storage medium, organizing the one or more relevant file into the one or more groups of relevant files, and providing for display data relating to the one or more groups of relevant files.

Abstract: The present disclosure relates to devices, systems and methods providing evaluation and feedback to an operator of a device providing neuromodulation treatment, such as modulation of renal nerves of a human patient. In one embodiment, for example, a system monitors parameters or values generated before treatment. Feedback provided to an operator is based on the monitored values and relates to an assessment of various electrical properties associated with an electrode carried by a catheter. The electrode measures an electrical property of biological material making contact with the electrode while deploying the electrode, the electrical property being dependent on a ratio of a wall-interface area to a fluid-interface area.

Abstract: A method of training a submodule and preventing capture of an AI module is disclosed. Input data received from an input interface is transmitted through a blocker module to an AI module, which computes a first output data by executing a first model. A submodule in the AI system trained using methods steps processes the input data to identify an attack vector from the input data. The submodule executes the first model and at least a second model. The first model and the second model have a first and second set of network parameters and hyper-parameters respectively. The identification information of the attack vector is sent to the information gain module.

Abstract: A method and system for intelligently organizing one or more groups of relevant files may include retrieving a user data signal including user-specific data, analyzing the user data signal to identify a parameter relating to file relevance, identifying one or more relevant files in a storage medium based on the parameter at least one of a user category property, a lifecycle stage property, a relevant activity property, or an activity level property of one or more files in the storage medium, organizing the one or more relevant file into the one or more groups of relevant files, and providing for display data relating to the one or more groups of relevant files.

Abstract: A method and system for intelligently organizing one or more groups of relevant files may include retrieving a user data signal including user-specific data, analyzing the user data signal to identify a parameter relating to file relevance, identifying one or more relevant files in a storage medium based on the parameter at least one of a user category property, a lifecycle stage property, a relevant activity property, or an activity level property of one or more files in the storage medium, organizing the one or more relevant file into the one or more groups of relevant files, and providing for display data relating to the one or more groups of relevant files.

Abstract: A method of training a submodule and preventing capture of an AI module is disclosed. Input data is received from at least one user through an input interface. It is transmitted through a blocker module to an AI module which computes a first output data by executing a first model based on the input data. Input data is pre-processed by a submodule to obtain at least one subset of the input data. This submodule is trained using methods steps. The input data and the at least one subset of the input data are processed by the submodule to identify an attack vector from the input data. The identification information of the attack vector is sent to the information gain module.

Abstract: A method of training a submodule and preventing capture of an AI module is disclosed. Input data is received from at least one user through an input interface. It is transmitted through a blocker module to an AI module, which computes a first output data by executing a first model based on the input data. Input data is pre-processed by a submodule to obtain at least one subset of the input data. This submodule is trained using methods steps. The input data and the at least one subset of the input data are processed by the submodule to identify an attack vector from the input data. The identification information of the attack vector is sent to the information gain module.

Abstract: A computer-assisted medical device is configured and used to endoluminally navigate to a location in the gastrointestinal system and there treat certain body lumen wall areas while avoiding other body lumen wall areas. Embodiments ablate the inner mucosal layer and sub-mucosal nerve plexus of the stomach, duodenum and jejunum to effect treatment of insulin resistance and metabolic disorders, such as Type II diabetes (T2D), polycystic ovarian syndrome (PCOS), non-alcoholic steatohepatitis (NASH), non-alcoholic fatty liver disease (NAFLD), congestive heart failure (CHF) and obstructive sleep apnea (OSA). Various sensors are used to assist a clinical operator to navigate from the mouth through the pyloric sphincter and into and through the duodenum and/or jejunum. Various sensors are used to map and identify portions of the duodenum and/or jejunum. Various lumen wall ablation devices and methods are described. Various post-treatment assessments are described.

Abstract: A computer-assisted medical device is configured and used to endoluminally navigate to a location in the gastrointestinal system and there treat certain body lumen wall areas while avoiding other body lumen wall areas. Embodiments ablate the inner mucosal layer and sub-mucosal nerve plexus of the stomach, duodenum and jejunum to effect treatment of insulin resistance and metabolic disorders, such as Type II diabetes (T2D), polycystic ovarian syndrome (PCOS), non-alcoholic steatohepatitis (NASH), non-alcoholic fatty liver disease (NAFLD), congestive heart failure (CHF) and obstructive sleep apnea (OSA). Various sensors are used to assist a clinical operator to navigate from the mouth through the pyloric sphincter and into and through the duodenum and/or jejunum. Various sensors are used to map and identify portions of the duodenum and/or jejunum. Various lumen wall ablation devices and methods are described. Various post-treatment assessments are described.

Abstract: A method and system for intelligently identifying relevant application features includes receiving a request to identify the relevant application features for a file, the relevant application features being application features offered by an application associated with the file, retrieving a file usage signal, the file usage signal being a signal stored with the file and including data about user actions performed in the file over one or more sessions, providing the file usage signal as an input to a machine-learning (ML) model to identify the relevant application features based on the file usage signal, receiving from the ML model the identified relevant application features, determining a manner by which the identified relevant application features should be presented for display, and providing data relating to at least one of the identified relevant application features or the manner by which the identified relevant application should be presented to the application.

Abstract: A method and system for one or more application command recommendations may include receiving a search query, the search query being an in-application assistance query, accessing contextual data associated with the search query, providing at least one of the search query and the contextual data as input to a multilingual machine-learning (ML) model to identify one or more application command recommendations, obtaining the one or more application command recommendations as an output from the multilingual ML model, and providing data about the output to the application for display. The multilingual ML model uses a multilingual encoder to provide command recommendations for a plurality of languages.

Abstract: Described herein are mechanisms to allow users to access functionality of applications in a suite of applications. In a first aspect, when a query relating to functionality of an application is received from a user, an index containing both top-level and sub-level functionality is searched. Results are ranked using a trained machine learning model using both context describing user interactions and the search results. A subset of the ranked results are presented to the user as options. In a second aspect the index can comprise entries describing functionality from other applications so that results presented to the user can include cross-application functionality. In a third aspect, the index can be searched using the context prior to receiving a query and adjusting the user interface based on the results. In a fourth aspect, the system can recommend other applications and/or devices that are better suited to a user's intent.

Abstract: Systems and methods of controlled grasping and energy delivery include a computer-assisted device. The computer-assisted device includes an end effector and one or more processors. The end effector includes a first jaw, a second jaw, and a plurality of electrodes for delivering energy. The one or more processors are configured to grasp a material using the first jaw and the second jaw, determine characteristics of the grasp, determine characteristics of the material, and control one or more of the grasp or energy delivery by the plurality of electrodes based on the determined characteristics of the grasp and the determined characteristics of the material. According to some embodiments, the characteristics of the material include one or more of thermal, dielectric, or stiffness of the material. In some embodiments, the characteristics of the grasp include one or more of applied pressure, jaw angle, jaw separation, force, torque, or wrist articulation.

Abstract: An AI system includes an input interface configured to receive input data from at least one user, and a blocker module configured (i) to detect the received input data is an attack input data, (ii) to manipulate output data of the blocker module, and (iii) to send the output data from the blocker module to the at least one user. The AI system further includes an AI module configured to process the input data received by the blocker module and to generate output data corresponding to the input data. The AI system also includes a blocker notification module configured to transmit a notification to the owner of the AI system on detecting an attack input data, and an output interface configured to send the generated output data to the at least one user.

Abstract: Described herein are mechanisms to allow users to access functionality of applications in a suite of applications. In a first aspect, when a query relating to functionality of an application is received from a user, an index containing both top-level and sub-level functionality is searched. Results are ranked using a trained machine learning model using both context describing user interactions and the search results. A subset of the ranked results are presented to the user as options. In a second aspect the index can comprise entries describing functionality from other applications so that results presented to the user can include cross-application functionality. In a third aspect, the index can be searched using the context prior to receiving a query and adjusting the user interface based on the results. In a fourth aspect, the system can recommend other applications and/or devices that are better suited to a user's intent.

Abstract: A method and system for providing one or more suggested application features to a user of an application may include receiving an indication of a user action in a document, accessing contextual document data associated with the document, providing at least one of information about the user action or the contextual document data as input to a machine-learning (ML) model to predict a desired intent for the document, obtaining the predicted desired intent as an output from the ML model, identifying based on the predicted desired intent one or more application features that fulfil the desired intent, and providing data about the one or more application features for display.

Abstract: A method and system for intelligently organizing one or more groups of relevant files may include retrieving a user data signal including user-specific data, analyzing the user data signal to identify a parameter relating to file relevance, identifying one or more relevant files in a storage medium based on the parameter at least one of a user category property, a lifecycle stage property, a relevant activity property, or an activity level property of one or more files in the storage medium, organizing the one or more relevant file into the one or more groups of relevant files, and providing for display data relating to the one or more groups of relevant files.