Abstract: Example embodiments relate to expanding textual content using transfer learning and iterative inference. An example method includes receiving, by a computing device, a snippet of text that contains one or more terms expressed using succinct representations. The method also includes performing an iterative expansion, by the computing device, using the snippet of text as an input snippet of text. The iterative expansion includes receiving, by the computing device, the input snippet of text. The iterative expansion also includes determining, by the computing device using a machine-learned model, a set of intermediate expanded snippets. Each of the intermediate expanded snippets has an associated score based on the machine-learned model.

Abstract: Determining whether, upon cessation of a second automated assistant session that interrupted and supplanted a prior first automated assistant session: (1) to automatically resume the prior first automated assistant session, or (2) to transition to an alternative automated assistant state in which the prior first session is not automatically resumed. Implementations further relate to selectively causing, based on the determining and upon cessation of the second automated assistant session, either the automatic resumption of the prior first automated assistant session that was interrupted, or the transition to the state in which the first session is not automatically resumed.

Abstract: Embodiments of the present invention provide computer-implemented methods, computer program products and computer systems. Embodiments of the present invention can monitor user activity for one or more user interactions performed while connected to a Virtual Private Network. Embodiments of the present invention can then identify potential risks associated with a user and respective user interactions. Embodiments of the present invention can then, in response to determining a respective user interaction of the one or more interactions is suspicious, generate a real time risk score for the respective user interaction. Embodiments of the present invention can then, in response to the generate real time risk score exceeding a threshold level of risk for the respective user interaction, initiate a secondary authentication protocol.

Abstract: Embodiments of the present invention provide computer-implemented methods, computer program products and computer systems. Embodiments of the present invention can capture one or more interactions with an existing user interface displayed within a display screen. Embodiments of the present invention can then, in response to reaching a threshold level of interactions, dynamically generate an alternate user interface comprising one or more alternate interaction methods. Embodiments of the present invention can then overlay the alternate user interface over the existing user interface.

Abstract: Embodiments of the present invention provide computer-implemented methods, computer program products and computer systems. Embodiments of the present invention can monitor user activity for one or more user interactions performed while connected to a Virtual Private Network. Embodiments of the present invention can then identify potential risks associated with a user and respective user interactions. Embodiments of the present invention can then, in response to determining a respective user interaction of the one or more interactions is suspicious, generate a real time risk score for the respective user interaction. Embodiments of the present invention can then, in response to the generate real time risk score exceeding a threshold level of risk for the respective user interaction, initiate a secondary authentication protocol.

Abstract: Identifying and reducing package delivery risks can include receiving, at a computer, package delivery data for a package to be delivered. Package delivery factors can be determined which include package fragility. Product information and product reviews can be analyzed based on the factors, and the analyzing can include using natural language processing to evaluate the product information and product reviews to identify language related to the factors. The factors can be weighted based on the analysis of the product information and the product reviews based on a probability of risk of damage to the package. A package risk score is calculated based on the analysis and the weighting. A best delivery practice for the package is generated based on the package risk score, and the package risk score and best delivery practice is communicated to a device of a delivery person.

Abstract: Aspects for resolving failed user-interface functionality are described. One or more processors are configured for detecting a first user input having a first input magnitude at user-selectable elements displayed on a local device user-interface, determining that the local device user-interface is not responsive to the first user input; detecting a second user input having a second input magnitude that is greater than the first input magnitude at the user-selectable elements, wherein the first user input and the second user input are by the user; determining that the local device user-interface is not responsive to the second user input; transmitting first data corresponding to a user-interface offload prompt to a mobile device associated with the user, wherein the mobile device is within a predetermined proximity of the local device user-interface; and receiving second data corresponding to a plurality of mobile device user inputs from the mobile device.

Abstract: Aspects for resolving failed user-interface functionality are described. One or more processors are configured for detecting a first user input having a first input magnitude at user-selectable elements displayed on a local device user-interface, determining that the local device user-interface is not responsive to the first user input; detecting a second user input having a second input magnitude that is greater than the first input magnitude at the user-selectable elements, wherein the first user input and the second user input are by the user; determining that the local device user-interface is not responsive to the second user input; transmitting first data corresponding to a user-interface offload prompt to a mobile device associated with the user, wherein the mobile device is within a predetermined proximity of the local device user-interface; and receiving second data corresponding to a plurality of mobile device user inputs from the mobile device.

Abstract: Aspects of the present disclosure relate to wireless communication management. A set of sensor data can be collected by a first device paired to a second device using a wireless communication (WC) protocol. The set of sensor data can be analyzed to determine whether a rule for adjusting a WC activation threshold is satisfied, the WC activation threshold defining a distance at which the first device and second device are permitted to transfer data to each other. The WC activation threshold can be adjusted in response to determining that the rule for adjusting the WC activation threshold is satisfied.