Abstract: A system for automated processing of electronic loan applications including user interfaces, visual presentation of data, automated loan documentation processing, financial analysis, loan scoring, real time risk adjustment, and underwriter approval processes is described. The system provides computer control for receiving electronic loan requests, automatically analysis and data verification, scoring loans, assessing risk, optimizing loan offers, generating dashboards with status information and tile displays of loan application data, real time adjusting of risk, displaying of optimized loan offers and underwriting of loan applications. More specifically, the dashboard includes a progress indicator of the progress of an electronic loan request to a complete loan application and finally to an approval or rejection.

Abstract: Predicting a state of a mold after molding upon injection molding. A machine learning device includes: an input data acquiring unit that acquires input data including any molding condition including at least a type of resin, a type of additive, a blending ratio of the additive, and a temperature of the resin in molding any article molded by any injection molding machine, and state information indicating a wear amount of a mold before molding at the molding conditions; a label acquiring unit that acquires label data indicating state information of the mold after molding at the molding conditions included in the input data; and a learning unit that executes supervised learning using the input data acquired by the input data acquiring unit and the label data acquired by the label acquiring unit, and generates a learned model.

Abstract: We describe a system that performs prognostic-surveillance operations based on an inferential model that dynamically adapts to evolving operational characteristics of a monitored asset. During a surveillance mode, the system receives a set of time-series signals gathered from sensors in the monitored asset. Next, the system uses an inferential model to generate estimated values for the set of time-series signals, and then performs a pairwise differencing operation between actual values and the estimated values for the set of time-series signals to produce residuals. Next, the system performs a sequential probability ratio test (SPRT) on the residuals to produce SPRT alarms. When a tripping frequency of the SPRT alarms exceeds a threshold value, which is indicative of an incipient anomaly in the monitored asset, the system triggers an alert. While the prognostic-surveillance system is operating in the surveillance mode, the system incrementally updates the inferential model based on the time-series signals.

Abstract: A computer mouse assembly having a slidable user wrist support controllably extendable upwardly and selectively set to a user-defined height above a main mouse body to support the wrist of a user during use of the mouse.

Abstract: Embodiments of the present disclosure present devices, methods, and computer readable medium for techniques for creating machine learning models. Application developers can select a machine learning template from a plurality of templates appropriate for the type of data used in their application. Templates can include multiple templates for classification of images, text, sound, motion, and tabular data. A graphical user interface allows for intuitive selection of training data, validation data, and integration of the trained model into the application. The techniques further display a numerical score for both the training accuracy and validation accuracy using the test data. The application provides a live mode that allows for execution of the machine learning model on a mobile device to allow for testing the model from data from one or more of the sensors (i.e., camera or microphone) on the mobile device.

Abstract: There is provided an information processing system that includes a communication unit that acquires act information indicating occurrence of a first act from a first user to a second user, an accumulation unit that accumulates at least a user who has performed the act, a user influenced by the act, and a type of the act in units of acts in order of occurrence of the acts, and a control unit that performs control, when a second act determined to have influenced the first act is found from among acts that are accumulated in the accumulation unit and from which the first user has received influence in past, to record the first act and the second act in association with each other in the accumulation unit.

Abstract: The invention provides a comprehensive data transformation system, method and computer program product structured for transformation of data structures to maintain data attribute equivalency in diagnostic databases. In some embodiments, the present invention is configured to determine a first source data structure based on at least received user information. The source data structure is typically comprises a comprising a first coding type. In addition, the present invention is configured to determine one or more source attributes associated with the first source data structure. Moreover, the present invention is configured for transforming the first source data structure to a first target data structure of a second coding type such that one or more target attributes associated with the first target data structure are equivalent to the one or more source attributes.

Abstract: A method for dynamically scoring aspects of a data object includes receiving a first data object indicating and determining a first sum of a product of a first value and a first weight value plus a product of a second value and a second weight value and generating a first score based on a result of the first sum. The method also includes determining a second sum of a product of a third value and a third weight value plus a product of a fourth value and a fourth weight value and generating a second score based on a result of the second sum. The method also includes determining a first data object score for the first data object based on, at least, the first score, the second score, and a fifth value.

Abstract: A search apparatus causes a first learning process using a first sample size and a first hyperparameter value to be executed, and causes a second learning process using the first sample size and a second hyperparameter value to be executed. When a third learning process using a second sample size larger than the first sample size and the first hyperparameter value has not been executed, the search apparatus calculates total resources associated with the first sample size based on resources used by the first and second learning processes. If the total resources exceed a threshold, the search apparatus allows the third learning process to be executed. If the total resources are equal to or less than the threshold, the search apparatus withholds the execution of the third learning process, and allows a fourth learning process using the first sample size or smaller and a third hyperparameter value to be executed.

Abstract: Methods, systems, and computer-readable media for offline evaluation of machine learning models with noise reduction are disclosed. A trigger computation system generates a plurality of experimental requests. The experimental requests do not represent unmodified requests received from clients in a production environment. At least one parameter value varies for individual ones of the experimental requests. The trigger computation system provides the experimental requests to a first machine learning model and a second machine learning model. The first machine learning model and the second machine learning model produce a set of results based at least in part on the experimental requests. The trigger computation system determines a reduced set of results for which the first machine learning model and the second machine learning model differ. An evaluation of the first machine learning model or the second machine learning model is performed using the reduced set of results.

Abstract: A flexible wireless charging mouse pad includes an anti-slip cushion layer, a double-sided adhesive layer, and a coil. The anti-slip cushion layer has a topside with a single-ring groove, and the single-ring groove has an inner bottom groove wall. The double-sided adhesive layer is adhered to the topside. The coil has multiple surrounding rings arranged side by side with one another to form a coil module, and the coil module of the coil inside the single-ring groove is stacked and connected between the double-sided adhesive layer and the inner bottom groove wall and adhered by the double-sided adhesive layer, so as to achieve a wireless charging effect by the mouse pad in the condition of having only one single-ring groove on the flexible board layer, further to achieve the effects of reducing manufacturing difficulty, lowering manufacturing cost, and improving market competitiveness.

Abstract: Systems and methods are provided for improved graphical user interfaces. The system enables multiple separate applications, each of which may typically be in their own separate window or tab, to be interacted within a single window, such as a tab of a web browser application. The main window includes smaller sub-windows that can correspond to a distinct application with its own graphical user interface. A large sub-window within the main window is opened for the primary application where the user is currently interacting with a graphical user interface of the primary application. The user then is able to switch between applications (all within the same main window) and applications that are no longer being used can be minimized in smaller sub-windows off to the side of the primary sub-window. The system enables a user to drag and drop an item from one sub-window to another sub-window. Some of the interactions between the windows and data transformations are stored and can be visually presented in a graph.

Abstract: In some examples, an electronic device includes a tip pressure sensor to capture tip pressure data based on a writing surface. In some examples, the electronic device includes a processor to produce a classification of the writing surface based on the tip pressure data via a machine learning model. In some examples, the electronic device may include a haptic device to control haptic feedback based on the classification.

Abstract: Example stylus holders for an electronic device are disclosed herein. In an example, the stylus holder is coupled to an outer housing of the electronic device. In addition, the stylus holder includes a sleeve that is to transition between: an extended position, in which the sleeve is projected out of the aperture of the outer housing; and a retracted position, in which the sleeve is retracted into the aperture of the outer housing from the extended position. Further, the stylus holder includes a biasing member disposed within the outer housing and coupled to the sleeve. The biasing member is to bias the sleeve toward the retracted position when the sleeve is in the extended position.

Abstract: An example digital pen holder can include a fastener to attach a digital pen to the digital pen holder, an integrated pen tip storage, and an integrated pen tip extractor.

Abstract: An electronic pen cartridge includes a pen tip that is configured to protrude outside of an electronic pen electronic pen casing through an opening of the electronic pen casing, an electronic circuit that transfers signals to a position detecting sensor, and a first connector that is joined to a second connector disposed in the electronic pen casing. The first connector includes plural terminals insulated from each other, and each of the terminals is electrically connected to the electronic circuit. The first connector and the second connector are joined through insertion of a fitting protrusion of a first one of the first connector and the second connector into a fitting recess of a second one of the first connector and the second connector in an axis center direction of the electronic pen casing, and circular annular conductor contacts are included in the first connector or the second connector.

Abstract: A system for organizing, displaying, and interacting with information on a display device includes a computer processor and a memory device. The memory device stores at least one piece of computer code executable by the computers processor and data used by the computer code. A display device is structured to display a graphical interface to a user based on the computer code executed by the computer processor. Input devices are structured to receive information from the user based on one or more images of the graphical interface displayed on the display device. The computer code includes a main display module for providing a main display area of the graphical interface, and for organizing digital objects in a plurality of layers. The layers include a base layer corresponding to a base-surface of the main display area, and a fixed layer corresponding to a fixed-surface of the main display area.

Abstract: A method for quickly starting an application service, and a terminal. The method includes acquiring, by a terminal, event trigger information; starting, by the terminal, the application service software after determining that the event trigger information meets a preset quick startup condition; and acquiring, by the terminal, a voice instruction input by a user, and running the application service software according to the voice instruction. According to the method provided in the embodiments of the present disclosure, application service software is started by using event trigger information, so that a background of a terminal starts to perform recording only after the application service software is started, and background recording is stopped after the terminal provides an application service for a user, preventing a recording device in the background of the terminal from being always in a recording state, and further reducing power consumption of the terminal.

Abstract: Provided is a non-transitory storage medium that stores a computer readable program for a computer of a medical information processing device configured to output and/or input medical information, the program causing the computer to perform acquiring locale information in environment information of the medical information processing device and presuming a character encoding of the medical information based on the locale information acquired in the acquiring.

Abstract: A method for controlling a mouse pointer on at least two displays is provided. A virtual display layout defines a mutual relative positioning of display areas relating to the at least two displays. The method comprises creating the virtual display area and tracking a position of the mouse pointer within it. Upon the mouse pointer being positioned within an area of any of the display areas, the mouse pointer is displayed. Upon the mouse pointer being positioned outside the area of any of the display areas, but within the virtual display area, a first marker is displayed on a side border of the display in a direction the mouse pointer is positioned within the virtual display area, and a second marker is displayed on at least one other side border of another display in a direction the mouse pointer is positioned within the virtual display area.