Abstract: Embodiments described herein relate to training, by a computing system, a gamma mixture hurdle model. The model may characterize a functional relationship between: output data specifying food flows between zones, and input variables representing food production and food consumption in the zones. The training involves: (i) using binary logistic regression to estimate whether corresponding food flows exist between zone pairs, and (ii) for pairs in which corresponding food flows exist, using a gamma mixture model to estimate amounts of the corresponding food flows. Based on the gamma mixture hurdle model, the computing system can estimate, where each zone includes a respective set of regions: (i) whether corresponding food sub-flows exist between region pairs, and (ii) for pairs in which the corresponding food sub-flows are estimated to exist, potentials of the corresponding food sub-flows. The computing system can also determine, using a linear programming framework, values for the corresponding food sub-flows.

Abstract: A method, computer system, and computer program product for explaining time series machine learning model are provided. The embodiment may include determining a first order difference in time series input data and historical training data. The embodiment may also include performing perturbation of time series input data based on the determined first order difference and the determined historical training data. The embodiment may further include computing closeness of the determined first order difference in the historical training data to the determined first order difference in the time series input data. The embodiment may also include generating a uniform random sample of first value input to a time series machine learning model. The embodiment may further include determining values of other inputs to the time series machine learning model based on the generated random sample and a random sample from the historical training data first order differences.

Abstract: The present disclosure provides a point autoencoder including an encoder receiving a 3D point cloud and extracting a global feature and a decoder reconstructing the 3D point cloud from the global feature; a dual autoencoder including the point autoencoder; and a method for dimensional transformation of a point cloud using the dual autoencoder. According to the present disclosure, it is possible to extract features from an input point cloud using a Bias-Induced Decoding (BID) layer, perform reconstruction of a 3D point cloud from the corresponding feature information, and reconstruct a 3D point cloud by using only high-dimensional global features as an input. Also, the present disclosure reduces the amount of storage space used and reduces computational complexity than the conventional structure employing a fully connected layer.

Abstract: A screenshot method includes that a terminal responds to a non-stylus operation by entering a screenshot waiting state. When the terminal establishes a connection to the stylus, the terminal detects an operation of the stylus on a touchscreen of the terminal. If an operation of drawing a closed figure with the stylus is detected, the terminal takes a screenshot of interface content in the closed figure drawn with the stylus.

Abstract: A computer-implemented method for determining a denoised named entity recognition (NER)-model and denoised relation extraction (RE)-model. A computer-implemented method for propagating an input dataset into a graph database representation, a computing unit and a computer program product, is also provided.

Abstract: A method for operating an electronic device is provided. Aspects include configuring a touch slop corresponding to a reference for performing a scroll in response to detection of a first touch event and acquiring touch information corresponding to a current touch point every predetermined time while the first touch event is maintained. Based on a determination that a touch movement distance exceeds the touch slop, based on the acquired touch information, aspects include initiating a scroll for a first screen displayed on the display module. Aspects further include identifying scroll data comprising at least one of a movement speed, a movement distance, and deceleration of the first touch event, based on the touch information acquired while the scroll is performed and determining whether to end the scroll, based on the scroll data to control a state of the scroll for the first screen.

Abstract: Systems, methods, and other embodiments associated with decision tree machine learning native to a graph database are described. In one embodiment, a method includes receiving an objective property value of a training graph for a graph-native decision tree to be trained to predict; determining feasible ranges of values from the training graph; automatically generating a graph query language grammar for graph-native decision trees based on the feasible ranges; progressively evolving output decision trees in a graph query language from the graph query language grammar to generate a final decision tree that accurately predicts the objective property value; and storing the final decision tree for subsequent execution against a target graph.

Abstract: Some embodiments of the invention provide a method for implementing a temporal convolution network (TCN) that includes several layers of machine-trained processing nodes. While processing one set of inputs that is provided to the TCN at a particular time, some of the processing nodes of the TCN use intermediate values computed by the processing nodes for other sets of inputs that were provided to the TCN at earlier times. To speed up the operation of the TCN and improve its efficiency, the method of some embodiments stores intermediate values computed by the TCN processing nodes for earlier sets of TCN inputs, so that these values can later be used for processing later set of TCN inputs.

Abstract: A portable electronic device having a touch screen with a floating soft trigger icon for enabling various functions of the electronic device, such as bar code reading, capturing RFID data, capturing video and images, calling applications, and/or placing phone calls. The floating trigger icon is displayed on the touch screen to enable easy identification and access of the trigger icon. The trigger icon may be selected via application of various unique control gestures to configure the electronic device. Based on the selected mode or function of the device, the trigger icon may alter its appearance to facilitate use of the device. The operation and functionality of the trigger icon may be programmed to customize operation of the device.

Abstract: One or more computing devices, systems, and/or methods for debiasing training data based upon information seeking behaviors are provided. Users associated with a set of training data are segmented into information seeking behavior groups corresponding to varying degrees of information seeking behaviors of the users. Biases for the information seeking behavior groups may be estimated based upon information seeking behaviors of users within the information seeking behavior groups. The training set of data is debiased using the biases to generate a debiased training set of data. A model may be trained to perform a task based upon the debiased training set of data.

Abstract: A computer-implemented method stratified elusion includes selecting hypothetical cutoff ranks when a stopping point is reached, calculating for each respective cutoff rank a recall value, elusion value, and remaining count; and displaying each respective cutoff rank, recall value, elusion value, and remaining count. A stratified elusion system includes a processor and a memory storing instructions that, when executed, cause the system to select cutoff ranks when a stopping point is reached, calculate for each respective cutoff rank a recall value, elusion value, and remaining count; and display each respective cutoff rank, recall value, elusion value, and remaining count.

Abstract: A risk-prediction-preparation module to generate a risk-prediction-model, is provided herein. The risk-prediction-preparation module includes accessing a data-storage of transactions to operate a group-by operation on transactions related to data-points, according to a logical-entity into entities. Then, clustering entities of a clean-financial dataset into clusters. Selecting data-points of: (a) entities from the clusters to a first dataset and (b) a preconfigured amount of entities randomly to a second dataset. Selecting all entities that have at least one ‘fraudulent’ data-points in at least one related data-point to add all the entities to the first dataset and the second dataset. Using vectorized and scaled extracted features for training a first machine-learning-model of fraud detection on the first dataset and training a second machine-learning-model of fraud detection on the second dataset to collect results.

Abstract: A computing device with a touch-sensitive display displays a menu for a touch-sensitive keyboard, the menu including a plurality of keyboard settings. In response to a first input in the menu, adjusting a first setting of a plurality of keyboard settings for a first application. In response to a second input in the menu, adjusting a second setting of the plurality of keyboard settings for a second application distinct from the first application.

Abstract: An icon displaying method and an electronic device are provided. The method is performed by the electronic device. The electronic device includes a device body and a stylus detachably connected to the device body. The method includes: obtaining a first working state of the stylus, where the first working state includes at least one of remaining power, a font color, or a font size of the stylus; and displaying an icon corresponding to the stylus based on the first working state.

Abstract: The technology disclosed herein enables automatic obscuration of a portion of a view shared during a screen sharing session. In a particular embodiment, a method includes receiving a view displayed by a first user system to a first user. The method further includes identifying a portion of the view not to be shared and obscuring the portion of the view to generate a shared view. Also, the method includes transmitting the shared view to a second user system over a real-time screen sharing session, wherein the second user system displays the shared view to a second user.

Abstract: Embodiments are disclosed for a method. The method includes receiving feedback decision rules for multiple predictions by a trained machine learning model. generating a feedback rule set based on the feedback decision rules. The method further includes generating an updated training dataset based on an original training dataset and an updated feedback rule set. The updated feedback rule set resolves one or more conflicts of the feedback rule set, and the updated training dataset is configured to train the machine learning model to move a decision boundary. Generating the updated training dataset includes generating multiple updated training instances by applying one of the feedback decision rules to a training instance of the original training dataset.

Abstract: A contextual menu system may be configured to perform operations that include: identifying a media category based on a user profile, the user profile comprising user profile data; causing display of a GUI that includes a content menu, the content menu comprising at least a display of a set of media items associated with the media category identified based on the user profile data, the set of media items comprising at least a first media item; accessing the user profile data of the user profile, the user profile data including a browser history associated with the user profile; identifying the first media item among the browser history; and removing the content menu within the GUI in response to the identifying the first media item among the browser history.

Abstract: A system, method implemented on a computer system, and computer program product for generating an expression. A graphical representation of the expression comprising criteria blocks and logical operator blocks is displayed on a user interface. Each of the criteria blocks includes criteria information defining a criteria, an edit block control element, and a delete block control element. A user interface to receive changes to the criteria information for a selected criteria block is displayed in response to selecting the edit block control element for the selected criteria block. The selected criteria block is deleted from the expression in response to selecting the delete block control element for the selected criteria block. A building block may be used to define criteria for criteria blocks in several expressions. Criteria for expressions defined using a building block are changed automatically in response to changes to the building block.

Abstract: Embedded sensors and onboard or off-board processing in an aligner case can detect aligner material and/or quality. Material detection can be used for counterfeit detection, or to trigger material specific events. Quality detection can include detection of common aligner failures or defects. A case for a dental appliance may include a tray for supporting the dental appliance, a cover coupled to the tray, and at least one sensor to detect a deformation of the dental appliance. A case for a dental appliance may include a tray for housing the dental appliance, a cover coupled to the tray, and at least one sensor configured to detect a change in material of the dental appliance.

Abstract: In some aspects described herein, a computer-based system that is capable of constructing digital documents is provided. In some implementations, a machine learning system is provided that learns certain terms within a document. The terms may be, for example, part of a document that forms a legally-binding contract between two entities. In one implementation of the machine learning system, the machine learning system interoperates within a user interface to show predictions of certain terms within the document to the user. Further, the machine learning system may capture user answers relating to certain terms and provide feedback into the system that learns during operation of the system, improving user interactions, accuracy and reducing the number of user interactions.