G06Q10/00

Action selection by reinforcement learning and numerical optimization

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a method comprises, at each of one or more time steps: generating a respective action score for each action in a set of possible actions, wherein the set of possible actions comprises: (i) a plurality of atomistic actions, and (ii) one or more optimization actions, wherein each optimization action is associated with a respective objective function that measures performance of the agent on a corresponding auxiliary task; selecting an action from the set of possible actions in accordance with the action scores, wherein the selected action is an optimization action; in response to selecting the optimization action, performing a numerical optimization to identify a sequence of one or more atomistic actions that are predicted to optimize the objective function.

DETERMINING RESTROOM OCCUPANCY
20230008566 · 2023-01-12 ·

Techniques for determining bathroom occupancy are disclosed herein. In this regard, one or more sensors may determine whether a plumbing fixture is in use. When a plumbing fixture is in use, the one or more sensors may trigger a visual cue that indicates that the plumbing fixture is in use. Additionally, the one or more sensors may send (e.g., transmit) information indicating that the plumbing fixture is in use to one or more computing devices. The information may include a start time of the fixture's usage, an end time of the fixture's usage, a duration of the fixture's usage, etc. The computing device may analyze the information from a plurality of fixtures associated with a location and present the analysis to a user, for example, via a dashboard.

Systems and methods for digital shelf display

The present disclosure provides methods and systems for quantifying item performance in a digital shelf. A method for quantifying item performance in a digital shelf may comprise: calculating a value associated with a shelf share of the given item; determining a set of factors for calculating a score indicative of the item performance on the digital shelf, wherein the set of factors includes the shelf share; generating, using a trained machine learning algorithm, the score based on the set of factors; and displaying the score within a graphical user interface (GUI) on an electronic device.

DETERMINING UTILITY INFRASTRUCTURE AND CONNECTIVITY INTERRUPTIONS

An approach for determining an infrastructure service interruption is disclosed. The approach relies on utilizing UAVs (unmanned aerial vehicle) to map electronic signals (e.g., Wi-Fi, etc.) that emanates from building structures (e.g., residential, commercial, etc.). Electronic signals having a certain frequency or multiple frequencies may be used. Essentially, the approach can detect power/signal loss by comparing differences in Wi-Fi signal maps pre and post event (e.g., severe thunderstorm, etc.). The 24/7 event monitoring is carried out by using UAVs and the UAVs can operate on a regular or event driven schedule vs. continuously operating multiple fixed data collection units.

Information processing apparatus and non-transitory computer readable medium
11574260 · 2023-02-07 · ·

An information processing apparatus includes a processor configured to: acquire a document; determine a route on which the document is to be processed in a workflow; determine a first process that is a final process for processing the document on the route among processes in which information is allowed to be input for a first item included in the document; and display the first item in a manner in accordance with the first process.

Generating search commands based on cell selection within data tables

A search interface is displayed in a table format that includes one or more columns, each column including data items of an event attribute, the data items being of a set of events, and a plurality of rows forming cells with the one or more columns, each cell including one or more of the data items of the event attribute of a corresponding column. Based on a user selecting one or more of the cells, a list of options if displayed corresponding to the selection, and one or more commands are added to a search query that corresponds to the set of events, the one or more commands being based on at least an option that is selected from the list of options and the event attribute for each of the one or more of the data items of each of the selected one or more cells.

Generating search commands based on cell selection within data tables

A search interface is displayed in a table format that includes one or more columns, each column including data items of an event attribute, the data items being of a set of events, and a plurality of rows forming cells with the one or more columns, each cell including one or more of the data items of the event attribute of a corresponding column. Based on a user selecting one or more of the cells, a list of options if displayed corresponding to the selection, and one or more commands are added to a search query that corresponds to the set of events, the one or more commands being based on at least an option that is selected from the list of options and the event attribute for each of the one or more of the data items of each of the selected one or more cells.

Collaborative media object generation and presentation in improved collaborative workspace

In the present disclosure, a collaborative workspace fosters content creation between users in a synchronous and/or asynchronous manner by enabling automatic generation and management of collaborative media objects that automatically combine content from a plurality of users into a single media object. This is extremely beneficial in technical scenarios where users are creating projects, assignments, presentations, etc., by removing the need for users to manually stitch together and combine content to create a final product. For example, the collaborative workspace is adapted for a video discussion application/service, where users create one or more video clips (e.g., video feeds, live video feeds) in response to a posted topic. In at least one instance, a collaborative workspace for a video discussion application/service may be integrated to display within another type of application/service. However, the present disclosure is extensible to work with any type of application/service and any content type.

Radio transmitter device for use in method and system for monitoring, controlling and optimizing flow of products
11593779 · 2023-02-28 · ·

A liquid product distribution network includes a liquid product distribution monitoring and reporting apparatus for operation in association with a tap handle flow monitoring and reporting apparatus. The liquid product distribution monitoring and reporting apparatus includes a radio transmitter device and sensing circuitry for sensing and communicating physical properties associating with the keg. A tap handle flow monitoring and reporting apparatus senses flow of a liquid through a tap includes a tap handle radio transmitter device for fitting within and protected by a tap handle and a low-energy consumption tap handle radio/processing module. A mobile communications device with geographic position sensing device and/or said tap handle flow monitoring and reporting apparatus passively and without user interaction within the liquid product distribution network, without using network uplink/gateway circuit devices for sensing and reporting fluid storage, flow, and financial operations relating to the distribution of said liquid product throughout the liquid product distribution network.

Collecting data from different sources
11593444 · 2023-02-28 · ·

A system for collecting data from different sources is described. In one example embodiment, the system obtains content-related data from a plurality of source computer systems, automatically identifies, based on the content-related data, content items having respective popularity values greater than a predetermined threshold value as popular content items, and automatically generates a list of popular content items based on the popular content items.