Blueowl, LLC

Michael Sungjun Kim

Kenneth Jason Sanchez

A smart waste bin for waste management is provided. The smart waste bin may include a plurality of cameras, a deposit container, a plurality of waste receptacles, and a computing device including at least one processor in communication with at least one memory device. The processor may be configured to: (i) receive image data of items inserted into the deposit container by a user, the image data captured by a camera of the plurality of cameras, (ii) receive user data associated with the user, (iii) classify the one or more items based upon the image data, (iv) sort the one or more items into the corresponding waste receptacle of the plurality of waste receptacles based upon the classification, (v) determine an assigned value of the one or more items based upon the classification, and (vi) compensate the user based upon the assigned value of the one or more items.

Systems and methods for waste management using recurrent convolution neural network with stereo video input

A user's credit score is determined based at least in part upon collected telematics data and user data associated with the user. A credit score prediction model is created using training datasets of historical data including demographics data, driver profile data, and established credit scores. The credit score prediction model is then used to predict credit scores for users without formal credit scores. A user's credit score is predicted based at least in part upon a driver profile built using telematics data, among other factors.

Systems and methods for generating a credit score based at least in part upon telematics data

A computer system for creating driving tournaments for users including a processor in communication with a memory device is provided. The processor may be programmed to: i) receive user data associated with a plurality of users, ii) generate, based at least in part upon the received user data, a driving profile including driving characteristics of each user, iii) match users based at least in part upon the driving profiles of the users, wherein a match occurs when driving characteristics of the driving profiles are substantially similar, iv) create a driving tournament for the matched one or more users, v) receive current vehicle telematics data and current mobile device data associated with the matched one or more users, and vi) determine, after the predetermined time period has ended, a winner of the driving tournament.

Systems and methods for tournament-based telematics insurance pricing

A system serializing and deserializing models configured to (i) store a first model, wherein the first model includes a plurality of functionalities; (ii) generate a human-readable document based on the first model, wherein the human-readable document describes the first model; (iii) generate a second model based on the human-readable document, wherein the second model includes the plurality of functionalities; and (iv) perform at least one execution of the second model.

Systems and methods for automatically serializing and deserializing models

A smart contract computing device may be provided. A processor may be configured to: (1) receive a plurality of deposits from a plurality of user computing devices; (2) store the plurality of deposits in a blockchain structure including, for each user computing device, a user identifier and a current amount; (3) receive, from at least one user computing device of the plurality of user computing devices, a proposal message for a decentralized insurance policy, the proposal message including a price amount, a coverage amount, a payout condition, and a specified data source; (4) receive, from at least one user computing device of the plurality of user computing devices, a response message for the decentralized insurance policy; and/or (5) generate, in response to receiving the response message, a smart contract in the blockchain structure including at least one buyer user identifier, at least one seller user identifier, the coverage amount, the payout condition, and the specified data source.

Systems and methods for implementing a decentralized insurance platform using smart contracts and multiple data sources

A system serializing and deserializing models configured to (i) store a first model, wherein the first model includes a plurality of functionalities; (ii) generate a human-readable document based on the first model, wherein the human-readable document describes the first model; (iii) generate a second model based on the human-readable document, wherein the second model includes the plurality of functionalities; (iv) train the second model; (v) generate a new human-readable document based on the trained second model; and (vi) generate an updated second model based on the new human-readable document.

Growing community of inventors

Fairfax, CA, United States of America

Michael Sungjun Kim