Abstract: In an electric power supply-demand adjustment system for performing electric power supply-demand adjustment by causing, by using a computer including a processor and memory, customers to control power consumption in accordance with an instruction issued by an aggregator, the processor, on the basis of demand response (DR) event information stored in the memory and including a scheduled event regarding the electric power supply-demand adjustment, and customer profile information stored in the memory and indicating a feature of a time-shiftable process performed by the customers consuming electric power, obtains a combination of processes shifted within an acceptable range, in which combination a power reduction amount fulfills a requested adjustment amount, to generate, for each of the customers, DR request information including a request for supply-demand adjustment of a power adjustment amount determined by the scheduled DR event, and determines a width of the shift to carry out electric power supply-demand

Abstract: Provided herein are systems and methods for matching and assigning drivers and various logistical agencies to food delivery tasks. The systems and methods increase the efficiency and effectiveness of delivering excess and/or unwanted food from donors to recipients who are in need of food. The systems and methods increase the efficiency and effectiveness by automatically matching each food delivery task to a driver who is able to pick up food from a donor and drop-off food at a recipient.

Abstract: Systems, computer program products, and methods are described herein for detecting attrition in a distributed network using artificial intelligence. Some embodiments are directed to a system including a first artificial intelligence engine configured to determine indicators of relationships between users and entities and a second artificial intelligence engine configured to determine statuses of relationships between the users and the entities. The system may determine, using the first artificial intelligence engine, and based on data associated with interactions between a user and an entity, a plurality of indicators of a relationship between the user and the entity. The system may determine, based on the plurality of indicators, based on the data associated with the interactions between the user and the entity, and using the second artificial intelligence engine, a status of the relationship between the user and the entity.

Abstract: Techniques for predicting marketing outcomes using contrastive learning are disclosed, including: obtaining historical marketing messages; obtaining historical open rates associated respectively with the historical marketing messages; based on the historical marketing messages, generating latent space representations associated respectively with the historical marketing messages; based on the latent space representations and respective contents of the historical marketing messages, training a first machine learning model to map contents of marketing messages to corresponding latent space representations of the marketing messages; based at least on the latent space representations and the historical open rates, training a second machine learning model to map latent space representations of marketing messages to predicted open rates of the marketing messages.

Abstract: A method for conducting an oilfield operation includes obtaining a plan for conducting an oilfield operation, the plan including a planned value for a metric, receiving data collected while performing one or more oilfield activities using the plan, at least a portion of the data representing an actual value for the metric, determining that one or more deviations from the plan occurred based on a difference between the actual value and the planned value, identifying one or more unplanned events of the one or more oilfield activities that are not in the plan that caused the one or more deviations, calculating a contribution to the difference between the actual value and the planned value caused by the one or more unplanned events, and modifying the plan to account for the one or more unplanned events.

Abstract: Methods and apparatuses are described in which unstructured computer text is analyzed for extraction of actionable insights in a computing environment. A server executes a machine learning classification model on text messages exchanged between users to classify each text message according to a disposition and a theme. The server analyzes the classified messages to generate candidate work items, each associated with software applications and skills requirements. The server filters the candidate items to remove extraneous items based upon a work item backlog or a prioritization. The server determines team members to assign to each remaining candidate item by comparing the software applications and the skills requirements for the work item to a profile for each team member. The server creates a task for each remaining candidate item, the task including the assigned team members. The server generates a notification for each task for transmission to the assigned team members.

Abstract: Systems and methods for providing an individualized map highlighting undiscovered areas of a locale. In particular, systems and methods are provided for providing a map that visually differentiates areas a user has visited from areas a user has yet to explore. In some implementations, generalized maps are displayed with highlighted and lowlighted areas representing unexplored and explored areas of the map. A generalized map can show popular tourist destinations or other features of each area. In some examples, specific map details of a particular area are revealed when a user selects the particular map area. In some examples, unexplored areas are revealed when a user elects to visit the unexplored area.

Abstract: A brand protection tool for managing risk to a brand is disclosed. The brand protection tool may provide a survey to a user. The survey may include a plurality of questions related to intellectual property. Based at least in part on the survey responses, the brand protection tool may determine a risk score, a protection score, and a net protection score. The brand protection tool may automatically generate a report including the net protection score and a visualization including a representation of the risk score and protection score. The brand protection tool may provide the report to a user or downstream system.

Abstract: A computer system, computer-implemented method and non-transitory computer-readable medium to predict transaction activity for a cyclical time period. A predictive transaction model is developed for individual user accounts, where the transaction model incorporates a cyclical data structure representation to detect and analyze transactions.

Abstract: A method and system for updating a graphical user interface (GUI) based on self-identified user intents.

Abstract: Embodiments described herein generate a first set of prompts, the first set of prompts configured to prompt a vehicle owner for a first set of answers used to learn preferred vehicle renter characteristics; receive the first set of answers; generate, based upon the first set of answers, a second set of prompts, the second set of prompts configured to prompt the owner for a second set of answers used to learn additional preferred vehicle renter characteristics; receive the second set of answers; predict user preference value(s) of a profile of the owner based upon the second set of answers, wherein the user preference value(s) define criteria for sharing a vehicle associated with the profile with vehicle renters who satisfy the criteria; apply the criteria to potential vehicle renters; and cause an indication of the vehicle to be displayed only to the potential vehicle renters who satisfy the criteria.

Abstract: A system selecting a process key factor in a commercial chemical process, includes: a data extraction unit that extracts tag data in units of a set period; an outlier discrimination unit that discriminates and aggregates outliers by tag by using an outlier extraction reference master; an outlier processing unit that generates an input mart draft excluding the outliers; a derived variable generation unit that generates derived variables for each tag, and generates an advanced input mart having the derived variable added thereto; a yield calculation unit that backs up the result of calculation of a yield by realizing a target value via exclusion and correction of the outliers; and a key factor extraction unit that extracts a yield key factor by calculating importance of each tag, and backs up importance data for each tag.

Abstract: A charging prediction system includes vehicles, a charging station, and a control device including one or more processors and one or more memories. The one or more processors are configured to execute a process. The process includes accumulating, in a storage device, record data that is actual data on a charged vehicle ratio for a first remaining traveling distance of each of the vehicles traveling along a specific traveling road. The process includes deriving, based on the record data, a predicted value of the charged vehicle ratio for each vehicle in a predetermined group including ones of the vehicles currently traveling along the specific traveling road. The process includes deriving a predicted waiting period that is a predicted value of a waiting period to a start of charging at the charging station based on the predicted values of the charged vehicle ratios.

Abstract: Various embodiments monitor compliance with standards for conducting rounds within corrections facilities and assist in maintaining safe corrections facilities by identifying predictable rounds patterns and encouraging inmate monitoring through unpredictable rounds timing. Some embodiments generate scores indicative of randomness in conducting rounds by individuals, groups, and even an entire staff of corrections officers.

Abstract: In one embodiment, a method comprises receiving, at a server comprising at least one processor, a transportation request from a computing device of a passenger, the transportation request specifying a pickup location; and determining, by the server, a surge pricing multiplier and a surge pricing cap for the transportation request based on the pickup location, the surge pricing cap representing a maximum amount of a fare for the transportation request that is subject to a surge pricing surcharge.

Abstract: An online concierge system uses a model to predict a user's interaction with an item, based on a user embedding for the user and an item embedding for the item. For the model to account for more recent interactions by users with items without retraining the model, the online concierge system generates updated item embeddings and updated user embeddings that account for the recent interactions by users with items. The online concierge system compares performance of the model using the updated item embeddings and the updated user embeddings relative to performance of the model using the existing item embeddings and user embeddings. If the performance of the model decreases, the online concierge system adjusts the updated user embeddings and the updated item embeddings based on the change in performance of the model. The adjusted updated user embeddings and adjusted updated item embeddings are stored for use by the model.

Abstract: A high-demand product processing system may include a seller device associated with a prospective seller, and a high-demand product marketplace server to store historical product data for a given product. The historical product data may include historical product prices and quantities at different times. The server may operate a web crawler to crawl e-commerce websites for current product data for the given product. The current product data may include current product prices and quantities at each of the e-commerce websites. The server may operate a machine learning algorithm to predict whether the given product will be a high-demand product based upon the historical product data and the current product data, and when so, generate an offer-to-purchase the high-demand product, communicate the offer-to-purchase to the seller device, and operate a marketplace to sell the high-demand product at a sales price higher than an offer price associated with the offer-to-purchase.

Abstract: The disclosure relates to the technical field of power system management, and in particular to a large-scale electric vehicle cluster coordinated charging optimization method based on greedy repair genetic algorithm.

Abstract: A method including: receiving a single usage value for a plurality of physical computing resources over a period of time; receiving a cost for the plurality of physical computing resources; and determining, using one or more processors, a normalized usage rate cost of the plurality of physical computing resources over the period of time by normalizing the cost for the plurality of physical computing resources for a unit of the single usage value.

Abstract: The present disclosure relates to systems, non-transitory computer readable media, and methods that intelligently provide dynamic transportation modes and corresponding user interfaces to client devices within multi-pickup-location area geofences to satisfy dynamic limitations corresponding to certain alternate location options. For instance, the disclosed systems can provide a transportation option corresponding to a first pickup location for display via the requestor device. Based on determining that the requestor device is associated with a location within a geofence of a multi-pickup-location area, the disclosed systems can provide a selectable mode option for initiating an alternate location transportation mode that includes modifying the pickup location for a transportation request to a second pickup location.