“Automobile Monitoring Systems and Methods for Risk Determination” in Patent Application Approval Process (USPTO 20210256616)

2021 SEP 08 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent application by the inventors Christopulos, Nicholas U. (Bloomington, IL, US); Donahue, Erik (Normal, IL, US); Goldfarb, Meghan Sims (Bloomington, IL, US); Hayward, Gregory L. (Bloomington, IL, US), filed on September 20, 2018, was made available online on August 19, 2021, according to news reporting originating from Washington, D.C., by NewsRx correspondents.

This patent application is assigned to State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “As computer and computer networking technology has become less expensive and more widespread, more and more devices have started to incorporate digital “smart” functionalities. For example, controls and sensors capable of interfacing with a network may now be incorporated into devices such as vehicles, telephones (e.g., smartphones), tablets, wearables, and roadway infrastructure and portions of traffic monitoring systems. Furthermore, it is possible for one or more vehicle and/or central controllers to interface with the smart devices or sensors.

“However, conventional systems may not be able to automatically detect and characterize various conditions or damage/injuries associated with a vehicle or the vehicle’s occupants or occupants of other vehicles, and/or pedestrians. Additionally, conventional systems may not be able to detect or sufficiently identify and describe damage that is hidden from human view, and that typically has to be characterized by explicit human physical exploration, extent and range of electrical malfunctions, etc.”

In addition to the background information obtained for this patent application, NewsRx journalists also obtained the inventors’ summary information for this patent application: “The present disclosure generally relates to systems and methods for detecting damage, loss, injury, and/or other conditions associated with a vehicle and/or its occupants, and/or the occupants of other vehicles, and/or pedestrians using an automobile computer system and/or automobile monitoring system. Also, machine learning methods facilitate determining risk levels, as well as automobile insurance pricing and underwriting. Embodiments of exemplary systems and computer-implemented methods are summarized below. The methods and systems summarized below may include additional, less, or alternate components, functionality, and/or actions, including those discussed elsewhere herein.

“In one aspect, the present embodiments may relate to determining an automobile-based risk level via one or more processors, training a neural network (or other artificial intelligence or machine learning algorithm, program, module, or model) to identify risk factors within electronic claim features, receiving information corresponding to (i) an automobile, and/or (ii) an automobile operator, analyzing the information using the trained neural network (or other artificial intelligence or trained machine learning algorithm, program, module, or model) to generate one or more risk indicators, determining, by analyzing the risk indicators, a risk level corresponding to the automobile, and/or displaying, to a user, an insurance quotation based upon analyzing the risk indicators. The automobile may be a smart, autonomous, or semi-autonomous vehicle, and have sensors, software, and electronic components that direct autonomous or semi-autonomous vehicle features or technologies-each of which may have a various levels of risk, or lack thereof, that may be analyzed and determined by the present embodiments. Systems and methods may automatically generate risk models for various types of vehicle insurance types and loss types, such as by the application of artificial intelligence and machine learning methods as disclosed herein, to provide more granular risk models, leading to more accurate commercial offerings, and more appropriate matching premium price to actual risk.

“In another aspect, a computer-implemented method of determining an automobile-based risk level via one or more processors may include training, via one or more processors, a neural network (or other artificial intelligence or machine learning algorithm, program, module, or model) to identify risk factors within electronic vehicle claim records. The neural network may include a plurality of layers, and an input layer from among the plurality of layers may include a plurality of input parameters-with each corresponding to a different claim attribute. The method may include, via one or more processors, receiving information corresponding to (i) an automobile, and/or (ii) an automobile operator; and analyzing the information using the trained neural network (or other artificial intelligence or trained machine learning algorithm, program, module, or model). Analyzing the information may include generating, within the plurality of layers, one or more risk indicators corresponding to the information. The method may also include determining a risk level corresponding to the vehicle. The method may include additional, less, or alternate actions, including those discussed elsewhere herein.

“In another aspect, a computing system may include one or more processors, and one or more memories storing instructions. When the instructions are executed by the one or more processors, they may cause the computing system to provide a first application to a user of a client computing device. The first application, when executing on the client computing device, may cause the client computing device to obtain a set of information from an input device of the client computing device, and transmit, via a communication network interface of the client computing device, the set of information to a remote computing system. The instructions may cause the computing system to receive, at the remote computing system, the set of information and process, at the remote computing system, the set of information. The instructions may cause the computing system to identify, by the remote computing system, one or more risk indications, at least in part, by applying the set of information to a trained neural network (or other artificial intelligence or trained machine learning algorithm, program, module, or model) and generate, by the remote computing system analyzing the one or more risk indications, a quotation, such as quote for auto or homeowners insurance. The instructions may cause the computing system to (i) display the quotation to the user, and (ii) provide the quotation as input to a second application. The system may include additional, less, or alternate functionality, including that discussed elsewhere herein.

“Advantages will become more apparent to those skilled in the art from the following description of the preferred embodiments which have been shown and described by way of illustration. As will be realized, the present embodiments may be capable of other and different embodiments, and their details are capable of modification in various respects. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive.

“The Figures depict preferred embodiments for purposes of illustration only. One skilled in the art will readily recognize from the following discussion that alternative embodiments of the systems and methods illustrated herein may be employed without departing from the principles of the invention described herein.”

The claims supplied by the inventors are:

“1. A computer-implemented method of determining an automobile-based risk level via one or more processors, the method comprising, via one or more processors, servers, sensors, and/or transceivers: training, via the one or more processors and/or servers, a neural network to identify risk factors within electronic automobile claim records, the neural network including a plurality of layers, an input layer of the plurality of layers including a plurality of input parameters each corresponding to a different claim attribute, and an output layer of the plurality of layers configured to output labels and weights; receiving information corresponding to at least one of (i) an automobile, (ii) an automobile operator, or (iii) vehicle operation factors; analyzing, via the one or more processors and/or servers, the information using the trained neural network; identifying one or more risk factors of the risk factors applicable to the information; generating a risk indicator for each of the one or more risk factors using the trained neural network, wherein each risk indicator includes a label and a weight output from the output layer of the trained neural network; and determining, via the one or more processors and/or servers, a risk level corresponding to one or both of (i) the automobile, and (ii) an occupant of the automobile based upon the one or more risk indicators; wherein training a neural network to identify risk factors within electronic automobile claim records comprises: processing at least one of a historical set of electronic automobile claim records using natural language processing; and training the neural network using the processed historical set of electronic automobile claim records.

“2. The computer-implemented method of claim 1, wherein training a neural network to identify risk factors within electronic automobile claim records includes, via one or more processors: extracting textual content from one or both of (i) audio recordings, and (ii) images.

“3. (canceled)

“4. The computer-implemented method of claim 1, wherein training a neural network to identify risk factors within electronic automobile claim records includes, via one or more processors: analyzing, with respect to each automobile claim in a historical set of electronic automobile claim records, one or more of (i) a make, (ii) a model, and (iii) a year, associated with each automobile claim.

“5. The computer-implemented method of claim 1, wherein training a neural network to identify risk factors within electronic automobile claim records includes, via one or more processors: analyzing, with respect to each automobile claim in a historical set of electronic automobile claim records, one or both of (i) payments made under the claim, and (ii) a category corresponding to the type of claim.

“6. The computer-implemented method of claim 1, wherein generating, within the plurality of layers, one or more risk indicators corresponding to the information includes, via one or more processors: selecting, from a set of risk indicators stored in an electronic database, at least one risk indicator.

“7. The computer-implemented method of claim 1, wherein generating, within the plurality of layers, one or more risk indicators corresponding to the information includes, via one or more processors: generating, based upon the information, one or more risk indicators, and storing, in an electronic database, the one or more risk indicators.

“8. The computer-implemented method of claim 1, wherein determining a risk level corresponding to the automobile includes, via one or more processors: retrieving for each risk indicator among the one or more risk indicators, a set of weights, wherein each of the set of weights corresponds to a respective one of the one or more risk indicators; and calculating, based upon the set of weights, the risk level corresponding to the automobile.

“9. The computer-implemented method of claim 1, wherein determining a risk level corresponding to the automobile includes, via one or more processors: determining a geographic location of the automobile; and calculating, based upon the geographic location of the automobile, the risk level corresponding to the automobile.

“10. The computer-implemented method of claim 9, wherein calculating, based upon the geographic location of the automobile, the risk level corresponding to the automobile includes, via one or more processors: determining seasonal information, based upon the geographic location of the automobile.

“11. A computing system comprising: one or more processor; and one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to provide a first application to a user of a client computing device, wherein the first application, when executing on the client computing device, causes the client computing device to obtain a set of information from an input device of the client computing device, and transmit, via a communication network interface of the client computing device, the set of information to a remote computing system; receive, at the remote computing system, the set of information; process, at the remote computing system, the set of information; identify, by the remote computing system, one or more risk indications at least in part by applying the set of information to a trained neural network; generate, by the remote computing system analyzing the one or more risk indications, a quotation; and one or both of (i) cause, by the remote computing system, the quotation to be displayed to the user, and (ii) cause, by the remote computing system, the quotation to be provided as input to a second application.

“12. The computing system of claim 11, wherein the instructions further cause the one or more processors to one or both of: (i) cause, by the remote computing system, one or more audio recording in the set of information to be converted to text, and (ii) cause, by the remote computing system, one or more image in the set of information to be converted to text.

“13. The computing system of claim 11, wherein the instructions further cause the one or more processors to one or both of: (i) cause, by the remote computing system, one or more text pattern matchers to be applied to one or more strings in the set of information, to produce an indication of a pattern match, and (ii) cause, by the remote computing system, one or more natural language processors to be applied to one or more strings in the set of information, to produce an indication of a semantic relationship among a plurality of objects in the one or more strings.

“14. The computing system of claim 11, wherein the instructions further cause the one or more processors to one or both of: (i) cause, by the remote computing system, customer data corresponding to the user to be retrieved from an electronic database, and (ii) cause, by the remote computing system, automobile data corresponding to an automobile of the user to be retrieved from an electronic database.

“15. The computing system of claim 11, wherein the set of information comprises an application for an automobile insurance policy.

“16. The computing system of claim 11, wherein the set of information comprises a claim filed under an automobile insurance policy.

“17. The computing system of claim 11, wherein the instructions further cause the one or more processors to: retrieve, by the one or more processors, for each risk indicator among the one or more risk indicators, a set of weights, wherein each of the set of weights corresponds to a respective one of the one or more risk indicators; and calculate, based upon the set of weights, the risk level corresponding to the automobile.

“18. The computing system of claim 11, wherein the instructions further cause the one or more processors to: identify a confidence factor with respect to each of the one or more risk indications.

“19. A non-transitory computer readable medium containing program instructions that when executed, cause a computer to: train a neural network to identify risk factors within electronic automobile claim records, wherein the neural network includes a plurality of layers, and wherein an input layer of the plurality of layers includes a plurality of input parameters each corresponding to a different claim attribute and an output layer of the plurality of layers configured to output labels and weights; receive information corresponding to at least one of (i) an automobile, (ii) an automobile operator, or (iii) vehicle operation factors; analyze the information using the trained neural network; identify one or more risk factors of the risk factors applicable to the information; generate a risk indicator for each of the one or more risk factors using the trained neural network, wherein each risk indicator includes a label and a weight output from the output layer of the trained neural network; and determine a risk level corresponding to one or both of (ii) the automobile, and (ii) an occupant of the automobile based upon the one or more risk indicators, wherein to train a neural network to identify risk factors within electronic automobile claim records, the program instructions that when executed, cause the computer to: process at least one of a historical set of electronic automobile claim records using natural language processing; and train the neural network using the processed historical set of electronic automobile claim records.

“20. The non-transitory computer readable medium of claim 19 containing further program instructions that when executed, cause the computer to: generate, based upon analyzing the one or more risk indicators, a quotation; and one or both of (i) cause the quotation to be displayed to a user, and (ii) cause the quotation to be provided as input to a second application.”

URL and more information on this patent application, see: Christopulos, Nicholas U.; Donahue, Erik; Goldfarb, Meghan Sims; Hayward, Gregory L. Automobile Monitoring Systems and Methods for Risk Determination. Filed September 20, 2018 and posted August 19, 2021. Patent URL: https://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PG01&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.html&r=1&f=G&l=50&s1=%2220210256616%22.PGNR.&OS=DN/20210256616&RS=DN/20210256616

(Our reports deliver fact-based news of research and discoveries from around the world.)