Abstract: Provided is a cloud-edge collaboration forecasting system and method for aluminum oxide production indexes. The forecasting system performs forecasting algorithm selection, parameter configuration and model training on indexes and variables of the aluminum oxide production process at a cloud model training server, performs evaluation and parameter correction on the trained model to obtain an optimal training model, and pre-processes the data in the aluminum oxide production process at an aluminum oxide production index forecasting computer at an edge end. The trained model parameters are imported from the cloud, and further the trained forecasting model is used for forecasting aluminum oxide production indexes for different production processes.

Abstract: According to implementations of the present disclosure, there is provided a solution for auto-formatting of a data table. A computer-implemented method comprises obtaining values of at least one attribute for a plurality of cells in a data table, the values of the at least one attribute indicating at least one of a semantic meaning of data filled in the cells or a structure of the data table, the cells being arranged in rows and columns in the data table; extracting a feature representation of the values of the at least one attribute In using a first learning network; and determining respective formats for the cells based on the feature representation using at least the first learning network. In this way, it is possible to implement automatic mapping from attribute settings of cells to cell formats by using a learning network, thereby achieving auto-formatting of the data table.

Abstract: A computer-implemented method is disclosed for use with a portable electronic device having a display. The method enables switching between electronic inboxes that can be accessed from the electronic device. In some configurations, the method includes, while the device is displaying emails in a first inbox, detecting user selection of a first icon. The method further includes, in response to user selection of the first icon, displaying a set of inbox selection icons; and, in response to user selection of one of the inbox selection icons, displaying emails in a second inbox corresponding to the inbox selection icon selected by the user.

Abstract: Systems and methods herein describe receiving a target location from a computing device, using a machine learning model: determining a first access point and a second access point associated with the target location, causing presentation of the first access point as a first selectable user interface element and the second access point as a second selectable user interface within a graphical user interface on the computing device, receiving a first selection of the first selectable user interface element from the computing device; and in response to receiving the first selection, and initiating a trip request based on the refined map coordinates of the first access point.

Abstract: Certain aspects of the present disclosure provide techniques for processing and presenting analyte data. Some example aspects may describe techniques for generating and providing a user interface view of a user's performance report for display. Some example aspects may describe techniques for providing one or more user interface views for display on one or more widgets.

Abstract: The present disclosure relates to chatbot systems, and more particularly, to batching techniques for handling unbalanced training data when training a model such that bias is removed from the trained machine learning model when performing inference. In an embodiment, a plurality of raw utterances is obtained. A bias eliminating distribution is determined and a subset of the plurality of raw utterances is batched according to the bias-reducing distribution. The resulting unbiased training data may be input into a prediction model for training the prediction model. The trained prediction model may be obtained and utilized to predict unbiased results from new inputs received by the trained prediction model.

Abstract: Disclosed are examples of systems, methods and techniques related to delivering a service widget that collects data and provides a service. A service widget is provided in response to a widget delivery request received from a user browser. The delivered service widget enables the user browser to request item-related services from an enterprise. A request for the item-related services is received by an enterprise from the delivered service widget. Provision of the service is enabled upon confirmation that an authentication token fetched from the client backend system is valid for the client backend system, the services request may be delivered to an enterprise server. The enterprise, in response to an analysis of the information related to the item available for purchase, may indicate that the item available for purchase meets a purchase threshold of the enterprise and provide an evaluation result including parameters of the item-related services.

Abstract: The disclosed technology involves autonomously identifying goals and sub-goals from a user utterance and generating responses to the user based on the goals and sub-goals.

Abstract: Embodiments described herein provide systems and methods for learning representation from unlabeled videos. Specifically, a method may comprise generating a set of strongly-augmented samples and a set of weakly-augmented samples from the unlabeled video samples; generating a set of predictive logits by inputting the set of strongly-augmented samples into a student model and a first teacher model; generating a set of artificial labels by inputting the set of weakly-augmented samples to a second teacher model that operates in parallel to the first teacher model, wherein the second teacher model shares one or more model parameters with the first teacher model; computing a loss objective based on the set of predictive logits and the set of artificial labels; updating student model parameters based on the loss objective via backpropagation; and updating the shared parameters for the first teacher model and the second teacher model based on the updated student model parameters.

Abstract: An approach is provided in which a method, system, and program product analyze, while training a machine learning model, a set of first data transformation operators in a first data preparation pipeline that generates a plurality of constructed features from a set of training data. The method, system, and program product create a plurality of second data preparation pipelines from the first data preparation pipeline, wherein the set of first data transformation operators are converted to a set of second data transformation operators and each assigned to one of the plurality of second data preparation pipelines. The method, system, and program product deploy the plurality of second data preparation pipelines to a runtime system.

Abstract: Disclosed is a device which includes a data manager, a learner, and a predictor. The data manager generates output data based on time-series data, receives device prediction results corresponding to the output data from the prediction devices, and calculates device errors based on the difference between device prediction results and time-series data. The learner may adjust a parameter group of a prediction model for generating device weights, based on device prediction results and device errors. The predictor generates the ensemble result of first and second device prediction results based on device weights.

Abstract: Implementations relate to an automated assistant that can automate repeatedly performed procedures. The automation can involve communicating with different users, organizations, and/or other automated assistants. The automated assistant, with prior permission from respective user(s), can detect repeated performance of a particular series of manually initiated computational actions. Based on this determination, the automated assistant can determine automated assistant computational action(s) that can be performed by the automated assistant in order to reduce latency in performing a procedure, reduce quantity and/or size of transmissions in performing the procedure, and/or reduce an amount of client device resources required for performing the procedure. Such actions can include communicating with an additional automated assistant that may be associated with another user and/or organization.

Abstract: An operation method based on a chip having an operation array is provided, including: obtaining a neural network model including D neural network layers, each neural network layer being used for operating M*N neurons; determining, from M*N*D neurons of the D neural network layers, K neurons to be operated corresponding to each operation clock cycle, and inputting the K neurons to K rows of operation units of an operation array; and performing an operation on the inputted K neurons in the each operation clock cycle by using the operation array. The M*N*D neurons are mapped to K dimensions and then allocated to the K rows of operation units. The operation array is used for operating the neural network model in a full-load operation mode.

Abstract: A method for partially publishing edits to a document is described. A first document including a first cell and a second cell is displayed on first user account on a first computing device and on a second user account. A second document including a linked version of the first cell and a linked version of the second cell is displayed. An edit of the first cell is received from the first user account and an edit of the second cell is received. In response to receiving an indication from the first user account that the edit of the first cell is to be published, the edit of the first cell is made to the linked version of the first cell, while the linked version of the second cell is unchanged so that the content of the linked version of the second cell no longer matches that of the second cell.

Abstract: Systems, devices, media, and methods are presented for dynamic presentation and management of messages within a graphical user interface by presenting content icons, monitoring consumption status of the presented content represented by the content icons, transferring a content item from a first set of content to a second set of content, and causing presentation of the content item as part of the second set of content.

Abstract: Techniques for coordinating movements of various objects in an electronic document are disclosed. A first-type object remains stationary so that it becomes outside a content boundary of the electronic document, as the content boundary is pulled inside an edge of a window displaying the electronic document. A second-type object remains stationary until the content boundary reaches the edge of the window and then moves along with the scrolled electronic document as the content boundary is pulled inside the edge of the window. A third-type object and a fourth-type object may show different movement behaviors.

Abstract: A page element display method and an electronic device are provided. The method includes: The electronic device displays a first interface, where the first interface includes a first page element; the electronic device detects a first operation performed by a user on the first page element; the electronic device adjusts a size of the first page element in response to the first operation; and the electronic device automatically displays a second interface after adjusting the size of the first page element.

Abstract: A computer system can perform a semi-supervised machine learning processes to cluster a plurality of entities within a population based on their features and associated labels. The computer system can generate visualization data representing the clusters of entities and associated labels for displaying on a user interface. A user can review the clustering of entities and use the user interface to add or modify the labels associated with a particular entity or set of entities. The computer system can use the user's feedback to update the labels and then re-determine the clustering of entities using the semi-supervised machine learning process with the updated labels as input. As such, the computer system can use the user's feedback to improve the accuracy of the machine learning model without requiring a larger amount of labeled input data.

Abstract: In some implementations, a system may identify one or more account identifiers associated with a user account and corresponding to one or more account types. The system may determine an action to perform if account information associated with the user account or with a particular account identifier satisfies a condition. The system may transmit, to a user device, user interface (UI) data associated with an icon-based UI element. The UI data indicates a rectangular-shaped element, of the icon-based UI element, associated with the particular account identifier, and an interactable icon, of the icon-based UI element, positioned within a bottom portion of the rectangular-shaped element. The interactable icon is representative of the action. The system may include receiving, from the user device, interaction data indicating an interaction, by a user of the user device, with the interactable icon. The system may perform the action based on receiving the interaction data.

Abstract: An electronic device includes a device housing supporting a user interface, one or more touch sensors, and at least one image capture device. One or more processors cause, in response to the user interface receiving user input initiating an image capture operation, the at least one image capture device to capture a first plurality of images when the one or more touch sensors detect a multi-handed touch input and a second plurality of images when the one or more touch sensors detect a single-handed touch input.