Abstract: Large language models (LLMs) are able to provide robust results based on specified formatting and organization. Traditionally, however, users must form detailed queries to obtain desired results in a desired format. Accordingly, although LLMs are designed to receive natural language input, users often lack the skill, knowledge, or patience to utilize LLMs to their full potential. Ambient information and user history associated with device screenshots are leveraged to provide proactive artificial-intelligence (AI) assistance and query resolution in an LLM environment. In particular, screenshots associated with a computer display are continuously captured and analyzed to detect activity triggers for plugins, for example. In response to detecting an activity trigger, local context associated with one or more prior screenshots is collected. The collected context is then used to inform the plugin for performing the task, thereby reducing the burden placed on the user to input the required information.

Abstract: A technique uses a machine-trained model to generate a response based on a prompt which expresses current input information and abstract token information. The abstract token information summarizes a full dialogue history of a dialogue, and is generated by the model itself. The technique reduces the size of the prompt by incorporating the abstract summary information in lieu of the full dialogue history. A training system trains the machine-trained model by successively improving the predictive accuracy of the machine-trained model, while rewarding the machine-trained model based on an extent to which the machine-trained model compresses instances of abstract token information.

Abstract: A technique uses an encoder system to produce an index of target item embeddings. Each target item embedding is input-agnostic and universal in the sense that different expressions of a target concept, produced using different combinations of input modes, map to the same target item embedding in the index. The encoder system throttles the amount of computations it performs based on the assessed capabilities of an execution platform. A retrieval system processes a multimodal input query by first generating a candidate set of target item embeddings in the index that match the input query, and then using a filtering operation to identify those target item embeddings that are most likely to match the input query. The encoder system and the retrieval system rely on language-based components having weights that are held constant during a training operation. Other weights of these systems are updated during the training operation.

Abstract: The systems and methods may use machine learning models to process device data of user devices and determine device usage behaviors for the users of the user devices based on the device data. The systems and methods may provide relatable insights for the device usage behaviors in a user-friendly manner. The systems and methods may provide actional recommendations that users may take in response to the insights provided to promote healthy device usage behaviors or to prevent or reduce the device usage behavior. The systems and methods may also provide recommendations with access to information or other content related to the device usage behavior.

Abstract: Systems, methods, and software are disclosed herein that provide a computer-based user experience that allows a user to consume information about physical and digital activities undertaken by one or more users. In an implementation, a software application on a computing device communicates with an online service to obtain activity information indicative of such activities, as well as activity topics produced by the service. The application groups the activities into activity groups based at least on the topics produced for the activities, and displays the activity groups in a user interface to the application.

Abstract: A technique is described herein for automatically logging journeys taken by a user, and then automatically classifying the purposes of the journeys. In one implementation, the technique obtains journey data from one or more movement-sensing devices as a user travels from a starting location to an ending location in a vehicle. The technique generates a set of features based on the journey data, and then uses a machine-trainable model (such as a neural network) to make its classification based on the features. The machine-trainable model accepts at least one feature that is based on statistical information regarding at least one aspect of prior journeys that the user has taken. Overall, the technique provides a resource-efficient solution that rapidly provides personalized results to individual respective users. In some implementations, the technique performs its personalization without sharing journey data with a remote server.

Abstract: The systems and methods may use machine learning models to process device data of user devices and determine device usage behaviors for the users of the user devices based on the device data. The systems and methods may provide relatable insights for the device usage behaviors in a user-friendly manner. The systems and methods may provide actional recommendations that users may take in response to the insights provided to promote healthy device usage behaviors or to prevent or reduce the device usage behavior. The systems and methods may also provide recommendations with access to information or other content related to the device usage behavior.

Abstract: Systems and methods for identifying flagged content. One computer-based system includes an electronic processor configured to receive one or more websites, each website including a label identifying a flagged category and content, analyze one or more words included in the content of each of the one or more websites, and associate at least one of the one or more words included in the content of each of the one or more websites with the flagged category. The electronic processor is configured to perform, using the at least one of the one or more words, a query within a search engine to obtain one or more second websites, label each of the one or more second websites with the label identifying the flagged category, and update a model with the one or more websites, the one or more second websites, the one or more words, and the associated labels.

Abstract: Embodiments described herein are directed to a graphical user interface (GUI) for efficiently managing and organizing data items. The GUI utilizes machine learning-based clustering techniques that cluster data items into different clusters. The GUI displays each cluster as a user-selectable UI element. Each UI element displays keywords that are representative of the associated data items. The GUI enables the user to merge clusters together by interacting with the UI elements. For instance, the user may drag and drop one UI element over another UI element to combine the associated clusters. The GUI also enables a user to selectively associate certain Web pages of one cluster with another cluster. For instance, the GUI enables the user to move a keyword from one UI element to another UI element. The data items associated with that keyword are moved to the cluster represented by the other UI element.

Abstract: A technique is described herein for automatically logging journeys taken by a user, and then automatically classifying the purposes of the journeys. In one implementation, the technique obtains journey data from one or more movement-sensing devices as a user travels from a starting location to an ending location in a vehicle. The technique generates a set of features based on the journey data, and then uses a machine-trainable model (such as a neural network) to make its classification based on the features. The machine-trainable model accepts at least one feature that is based on statistical information regarding at least one aspect of prior journeys that the user has taken. Overall, the technique provides a resource-efficient solution that rapidly provides personalized results to individual respective users. In some implementations, the technique performs its personalization without sharing journey data with a remote server.