Abstract: A charging system can include a housing. The housing can include an inner surface configured to contact a finger of a user when the housing is worn by the user. The housing also can include an internal power source configured to be wirelessly charged by a removable power source that is removably coupled to the housing. The housing further can include a component configured to draw energy from the internal power source. The charging system also can include a first LED activated in response to a first activity at the removable power source. The charging system further can include a second LED activated in response to a second activity at the removable power source. The second LED can be different from the first LED. The second activity can be different from the first activity. Other embodiments are disclosed.

Abstract: A computer implemented including: collecting, via one or more sensors, a first set of operator data associated with a first group of vehicle operators during a first time period; determining, for each vehicle operator of the first group of vehicle operators and using one or more trained machine learning models based at least in part upon the first set of operator data, a first set of telematics inferences, the one or more trained machine learning models being trained using training data sets comprising sensor data associated with a second group of vehicle operators to predict telematics inferences; collecting, via the one or more sensors, a second set of operator data associated with the first group of vehicle operators during a second time period; determining, for each vehicle operator of the first group of vehicle operators and based on the second set of operator data, a second set of telematics inferences; determining, for each vehicle operator of the first group of vehicle operators, one or more match eva

Abstract: Method, system, device, and non-transitory computer-readable medium for managing vehicle operator profiles based on telematics inferences via a telematics marketplace. In some examples, a computer-implemented method includes: collecting a plurality of personal data sets continually; collecting a plurality of sensor data sets continually via one or more tensing modules; for each vehicle operator of the plurality of vehicle operators: generating and continually updating an operator profile including the personal data set: determining and continually updating one or more telematics inferences using a universal predictive model based at least in part upon the sensor data set, the universal predictive model having weights and biases hidden to marketplace participants; generating and continually updating a data profile including the one or more telematics inferences; and listing and continually updating the data profile onto a telematics marketplace to be accessible by a plurality of marketplace participants.

Abstract: A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising: detecting one or more mobile devices in a vehicle on a trip; collecting telematics data from the one or more mobile devices during the trip; determining one or more user interactions with the one or more mobile devices during the trip; determining respective positions of the one or more mobile devices in the vehicle during the trip; and determining if a user of the one or more mobile devices having at least one of the one or more user interactions during the trip is a driver or a passenger of the vehicle for the trip.

Abstract: A computer-implemented method of generating a scenic route including: receiving, by one or more processors, a user request from a user for directions from an origin location to a destination location; identifying, by the one or more processors, one or more route segments of one or more routes between the origin location and the destination location based on at least telemetry data and point of interest (POI) data; determining, by the one or more processors, one or more respective scenic views proximate to the one or more respective scenic points; receiving, by the one or more processors, a selection of at least one of the one or more respective scenic views; and transmitting, by the one or more processors, navigation directions to the user for at least one route of the one or more routes. Other embodiments are described.

Abstract: A method includes receiving one or more position values of a route of a vehicular trip. The method can also include receiving two or more images depicting what is potentially visible at one or more locations associated with the one or more position values, wherein each of the two or more images is associated with a respective position value of the one or more position values. The method can further include visually rendering, on a display device, a map and the two or more images in chronological order along the route of the vehicular trip.

Abstract: An online concierge shopping system fulfills orders using workers who pick items at a warehouse to complete an order and workers to deliver the orders to a customer's location. To optimize the staffing of workers for each task, the system uses a trained model to predict the number of workers needed to achieve an optimal outcome based on an input set of contextual information. The system also schedules specific workers to various shifts using the predicted number of workers needed and then searching a feasibility space for an optimal solution. The trained model may be updated based on performance observations.

Abstract: A computer-implemented method including predicting, using a trained computing model, one or more item categories for a user, the trained computing model being trained based on at least one of image data, personal possession data, claim data, or reimbursement data. The method also can include generating a plurality of predesignated policy levels for the user based at least on the one or more item categories, as predicted, wherein the plurality of predesignated policy levels cover one or more insured item categories. The method additionally can include receiving a selection by the user of a predesignated policy level from among the plurality of predesignated policy levels. The method further can include receiving a claim from the user. The method additionally can include generating one or more reimbursement controls for the one or more insured item categories based at least on the claim and the predesignated policy level.

Abstract: An online system includes an interface which facilitates communication between customers and pickers who are servicing the user's order. The customer may request a modification to their order through the interface. The online system performs an inference task in conjunction with the model serving system or the interface system to continuously monitor conversations between users and pickers to infer whether a customer requested to modify their order to maintain an updated order and an updated in-store transaction estimate for the order. The online system determines if the order has been updated to account for the requested changes. If the order has not been updated, the online system automatically updates the customer's order and computes an updated in-store transaction estimate based on the changes made.

Abstract: A smart ring includes a housing. The smart ring also can include a power source disposed within or at the housing. The power source can be configured to receive energy. The smart ring can further include a controller disposed within or at the housing. The power source also can be configured to power the controller. The controller can be configured to estimate a charging status for the power source. The controller also can be configured to generate information to indicate the charging status. Other embodiments are disclosed.

Abstract: A computer-implemented method for training a virtual character, the method can include receiving, from a user, a selection of the virtual character. The method can also include generating one or more virtual occurrences. The method can further include determining one or more outcomes associated with the one or more virtual occurrences. The method can additionally include initiating a virtual trip. The method can also include receiving telematics data associated with a real-life trip of a real-life vehicle operated by the user. The method can further include determining one or more real-life skills of the user indicative of how proficient the user operated the real-life vehicle upon encountering one or more real-life obstacles. The method can additionally include determining one or more skill points associated with the one or more real-life skills, and training the virtual character by at least updating one or more virtual ratings. Other embodiments are described.

Abstract: An online system receives information describing a set of items requested by a user and an indication via a chat interface that a particular item needs replacement. The online system generates one or more prompts configured to request a machine learned language model to identify the particular item that needs replacement and to identify one or more replacement items for the particular item. The online system receives a set of item identifiers from the machine learned language model and selects a replacement item from a database based on the set of item identifiers. The online system may also receive an order and a communication history associated with a user including a message with a request to modify the a. The online uses the machine-learning language model to map the request type to the set of API requests for updating the order to reflect the request from the user.

Abstract: Systems and methods are provided for providing recommendations of safe driving routes that are tailored to the driving habits of particular drivers. A machine learning model (e.g., an artificial neural network) may be trained using data indicative of insurance claim severity, road conditions, and/or vehicle telematics data associated with vehicle-related incidents, such as vehicle collisions. The machine learning model may be trained to identify road types and conditions that are predictive of claim frequency and severity. Any given driving route(s) may be provided to the trained machine learning model, and a risk value may be computed for the route(s). By further applying a personalized driver profile to the calculations of risk, personalized risk values may be computed for the route(s), and a safest route may be recommended to a driver.

Abstract: Method and system for generating virtual maps. For example, the method includes determining first real-world driving characteristics based upon first real-world telematics data of a first real-world user, determining first real-world geolocation characteristics based upon first real-world geolocation data of the first real-world user, generating a first virtual map based upon the first real-world driving characteristics and the first real-world geolocation characteristics, presenting the first virtual map in a virtual game, determining second real-world driving characteristics based upon second real-world telematics data of a second real-world user, determining second real-world geolocation characteristics based upon second real-world geolocation data of the second real-world user, generating a second virtual map based upon the second real-world driving characteristics and the second real-world geolocation characteristics, and presenting the second virtual map in the virtual game.

Abstract: A smart ring includes a body. The body includes a first part including at least a part of a sensor unit. The body also can include a second part including at least a part of an output unit and removably connected to the first part of the body. The body can further include a first pair of removable portions. The first pair of removable portions can include a first removable portion connected to the first part of the body. The first pair of removable portions also can include a second removable portion connected to the second part of the body. The first removable portion can be removable from the body. The second removable portion can be removable from the body. Other embodiments are disclosed.

Abstract: A system for displaying information via a smart ring device can include a smart ring device. The smart ring device also can include a processor disposed within a ring band. The processor can be configured to collect data to identify one or more conditions. The one or more conditions can include one or more of a biometric of a user of the smart ring device, a state of the user of the smart ring device, or a condition of an environment of the user of the smart ring device. The smart ring device further can include a display at a surface of the ring band. The processor can be configured to cause the display to present the information indicative of the one or more conditions. The processor also can be configured to determine whether a termination condition has been met for the one or more conditions.

Abstract: An online concierge shopping system fulfills orders using workers who pick items at a warehouse to complete an order and workers to deliver the orders to a customer's location. To optimize the staffing of workers for each task, the system uses a trained model to predict the number of workers needed to achieve an optimal outcome based on an input set of contextual information. The system also schedules specific workers to various shifts using the predicted number of workers needed and then searching a feasibility space for an optimal solution. The trained model may be updated based on performance observations.

Abstract: A computer system for providing reimbursement controls to insurance policies is provided. The computer system may include a processor in communication with a memory device.

Abstract: The present disclosure is directed to apparatuses, systems and methods for automatically classifying digital images of occupants inside a vehicle. More particularly, the present disclosure is directed to apparatuses, systems and methods for automatically classifying digital images of occupants inside a vehicle by comparing current image data to previously classified image data.

Abstract: An online system generates text-based representations of various types of data for processing using a large language model. The online system extracts location data from a map of a source location and converts the location data into a text-based representation of the location data. The online system receives a set of item identifiers from a client device of a user and generates an LLM prompt based on the set of item identifiers and the text-based representations of the location data. The online system receives a response from the LLM and parses the response for a text-based description of related items. The online system maps the text-based description of the related items to item identifiers and transmits a notification to the client device that includes item data associated with the related items.