State Farm Mutual Automobile Insurance Company

Hartford Fire Insurance Compnay

State Farm Insurance

Jufeng James Peng

Brian Mark Fields

Steve Roberson

Jibo He

Steve Cielocha

Bryan Allen Plummer

Parker Andrew Brown

Scott T Christensen

Gregory L Hayward

David James Dosher

William Messner

Julian Coltea

Mark O'Flaherty

Jason Freeck

James Maxwell McWilliams

Pat J Johnson

Duane Lee Marzinzik

Benjamin F Bowne

Nick U Christopulos

Matthew Eric Riley, Sr

J Lynn Wilson

David W Thurber

Nicholas R Baker

Bryan T Wilkerson

Lynn M Wilson

Gregory Patrick Larsson

Michael F Kosednar

Anne S Gouin

Nick Baker

Eric Riley

Todd Wilkerson

Dave Thurber

Sunish Menon

Dustin Charles Schneider

Scott Thomas Christensen

Nick Christopoulos

Lynn Wilson

A method for electronically mining intellectual property using an associative discovery process may include determining a set of documents containing keywords and/or phrases associated with an industry trend of interest. The method may also include determining a feedback score for each document in the set, determining an optimal weighing scheme for the determined keywords and/or phrases using a statistical learning model and the feedback scores, ranking all documents in the set of documents according to the optimal weighing scheme, and providing results of the associative discovery process to a user.

Systems and methods for electronically mining intellectual property

According to some embodiments, a server may access a data store containing electronic records, each electronic record representing a risk association for an entity in connection with a plurality of relationships, and each electronic record may contain a set of record characteristic values. The server may automatically designate a first sub-set of the set of record characteristic values as fixed effect variables and a second sub-set as random effect variables. A data analytics mixed effect predictive model may then generate, based on the fixed and random effect variables, a future performance estimation value for the risk association of each entity in connection with its plurality of relationships. An indication associated with the future performance estimation value for the risk association of at least one entity in connection with its plurality of relationships may then be transmitted to generate an interactive user interface display.

Performance estimation system utilizing a data analytics predictive model

A method for electronically mining intellectual property using an associative discovery process may include determining a set of documents containing keywords and/or phrases associated with an industry trend of interest and, for each document, assigning a weight. The method may also include selecting a subset of the documents based at least upon the assigned weights, and determining a feedback score for each document in the subset. The method may further include determining an optimal weighing scheme for the determined keywords and/or phrases using a statistical learning model and the feedback scores, ranking all documents in the set of documents according to the optimal weighing scheme, and providing results of the associative discovery process to a user.

Methods and systems for improving vehicular safety by utilizing a driving tip model are provided. According to embodiments, an analysis server can analyze telematics data associated with operation of one or more vehicles to identify driving tips that may be aimed to mitigate certain risks or warn of various conditions. The analysis server can provide the driving tips to the vehicles and, in response, receive updated telematics data from the vehicles that reflects operation data for the vehicles subsequent to receiving the driving tips. The analysis server can analyze the updated telematics data to associate certain driving tips with certain telematics data and identify effective driving tips and delivery techniques. The analysis server can update the driving tip model accordingly.

Systems and methods for updating a driving tip model using telematics data

In a computer-implemented method, data about potential vehicle operator impairment is retrieved. The data is generated by monitoring a vehicle operator, the environment ahead of the vehicle, and/or force in one or more directions. A number of impairment scores are generated by analyzing the data about potential vehicle operator impairment. A specific time period during which the vehicle operator tends to be most impaired is determined based on the impairment scores. Recommendations to reduce operator impairment of the vehicle operator are identified and communicated to the vehicle operator.

System and method for monitoring and reducing vehicle operator impairment

The method, system, and computer-readable medium facilitates monitoring one or more eyes of a vehicle operator during a driving session to generate a plurality of gaze location logs with gaze location values. The gaze location value may be generated by determining a location of the vehicle operator's gaze, determining which area of the vehicle is associated with the gaze location, and assigning the gaze location value based on the area of the vehicle associated with the gaze location. The gaze location logs may be analyzed to determine the duration of the vehicle operator's gaze at each area of the vehicle. Based on the duration of the vehicle operators gaze, one or more recommendations to improve vehicle operator performance may be identified and communicated to the vehicle operator.

Systems and methodologies for real-time driver gaze location determination and analysis utilizing computer vision technology

A system and method for determining a vehicle insurance premium for a period of time based at least in part on collected vehicle operation data, the system comprising: a mobile device, comprising: one or more sensors associated with the mobile device and configured to automatically collect vehicle operation data during a data collection session; a processor; a non-transitory storage medium; a display; a transmitter; and a set of computer readable instructions stored in the non-transitory storage medium and when executed by the processor configured to allow the mobile device to collect vehicle operation data and transmit the collected vehicle operation data; and a remote processing computer, comprising: a server that receives collected vehicle operation data; a database that stores collected vehicle operation data; and a rating engine that determines a vehicle insurance premium based at least in part on collected vehicle operation data.

Systems and methods using a mobile device to collect data for insurance premiums

A method includes receiving data about potential impairment of a vehicle operator, wherein the data about potential impairment is generated by: (i) monitoring the vehicle operator with a first optical sensor, and (ii) monitoring an environment ahead of a vehicle operated by the vehicle operator with a second optical sensor. The computer-implemented method further includes assigning a plurality of scores based on the data about potential impairment, wherein each of the plurality of scores corresponds to a respective impairment indicator, and determining an impairment score for the vehicle operator by performing a mathematical operation on the plurality of scores, the impairment score summarizing a level of impairment of the vehicle operator.

System and method to adjust insurance rate based on real-time data about potential vehicle operator impairment

In a computer-implemented method, data about potential vehicle operator impairment is retrieved. The data is generated by monitoring a vehicle operator, the environment ahead of the vehicle, and/or force in one or more directions. For each of a plurality of trips, an impairment score is generated by analyzing the data about potential vehicle operator impairment, and determining whether the vehicle operator was impaired during the trip by comparing the impairment score to a threshold value. A specific time period during which the vehicle operator tends to be most impaired is determined based on the determinations of whether the vehicle operator was impaired. Recommendations to reduce operator impairment of the vehicle operator are identified and communicated to the vehicle operator.

A data analysis method and computer system electronically mines potential intellectual property related to enterprise business needs. The method and system may utilize various text mining techniques to perform associative discovery, where existing enterprise documents or data are harvested and correlated with the latest industry trends in order to inspire new insights and stimulate the discovery of new or potential intellectual property. In one aspect, an area of interest may be identified. After which, identifiers associated with the area of interest, e.g., keywords and/or linking terms, may be determined. An enterprise database may be searched using the identifiers. The documents flagged by the search may be ranked with respect to their relevance to the area of interest based upon which and/or how many identifiers are contained within each respective document. The identification of highly relevant documents associated with an area of interest may lead to discovery of intellectual property.

In a computer-implemented method, data about potential vehicle operator impairment is retrieved. The data is generated by monitoring a vehicle operator with a first sensor, monitoring the environment ahead of the vehicle with a second sensor, and monitoring force in one or more directions with a third sensor. A plurality of scores is assigned. Each of the plurality of scores corresponds to a respective impairment indicator, and wherein each of the plurality of scores is based on the data about potential operator impairment. An impairment score is generated by performing a mathematical operation on the plurality of scores. It is determined whether the vehicle operator is impaired by comparing the impairment score to a threshold value. Recommendations to reduce operator impairment of the vehicle operator are identified by analyzing the data about potential vehicle operator impairment.

The method, system, and computer-readable medium facilitates monitoring one or more eyes of a vehicle operator during a driving session to generate a plurality of gaze location logs with gaze location values and timestamps. The gaze location value may be generated by determining a focal point of the vehicle operator's gaze, determining which of a plurality of areas of the vehicle is associated with the focal point, and assigning the gaze location value based on the area of the vehicle associated with the focal point. The gaze location logs may be analyzed to determine the duration of the vehicle operator's gaze at each area of the vehicle. Based on the duration of the vehicle operators gaze, recommendations to improve vehicle operator performance may be determined and communicated to the vehicle operator.

Growing community of inventors

Normal, IL, United States of America

Jufeng James Peng