Researchers Submit Patent Application, “Systems And Methods For Generating A Smart Contract For A Parametric Event Using Machine Learning Algorithms”, for Approval (USPTO 20230351380): Patent Application

2023 NOV 16 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Washington, D.C., NewsRx journalists report that a patent application by the inventors Amancha, Steve (Tempe, AZ, US); Cote, Kerry Lynne (Mesa, AZ, US); Crossland, Heath (Phoenix, AZ, US); Doak-Wigginton, Kimberly (Congerville, IL, US); Frazier, Darnell (Gilbert, AZ, US); Goumandakoye, Zaki (Emeryville, CA, US); Kloeppel, Kimberly Christine (Mesa, AZ, US); LeFebre, EllaKate (Mesa, AZ, US); Rahman, Moinur (Alpharetta, GA, US); Skyten, Erik (Harriman, TN, US); Trayer, Jerome Scott (Mesa, AZ, US), filed on April 14, 2023, was made available online on November 2, 2023.

No assignee for this patent application has been made.

News editors obtained the following quote from the background information supplied by the inventors: “Conventionally, when an operator of a vehicle suffers vehicle loss (e.g., theft of items inside the vehicle, a vehicle collision, a major collision resulting in a vehicle beyond repair, etc.), the operator manually contacts (e.g., via a phone call) an insurer entity of the vehicle to first report the loss, which may be referred to as First Notice of Loss (FNOL). The operator (and/or passengers, witnesses to the loss, etc.) may provide the insurer entity with details of the vehicle loss, such as the time and location of the vehicle loss, parties involved, etc., for the insurer entity to act (e.g., initiate a claims process).

“Generally speaking, the insurer entity may rely on reporting from the operator to initiate the FNOL process, and thus may be considered to employ a reactive approach for assisting the operator. The operator may also contact other entities, such as emergency response entities, tow servicing entities, taxi or ride-share service entities, vehicle repair service entities, vehicle salvage entities, rental car entities, etc. depending on the severity of the vehicle loss. Various entities may also contact each other. For example, an insurer may rely on a vehicle repair entity to assess repair costs for damage incurred in a collision, and these entities may need to agree on damages calculations and a payment amount to settle an insurance claim.

“In some situations, loss information reported by the operator to a particular entity may not be accurate, such as when the operator’s cognition is impaired during an accident, when the operator is suffering from emotion distress caused by an accident, when the operator forgets details by waiting too long to report the accident, or when the operator does not properly document the accident (e.g., with pictures) to name a few scenarios, and thus such loss information may be considered highly subjective, and in some cases, entirely inaccurate. Various entities may need to verify such information, such as by manually inspecting the vehicle involved in the loss, contacting parties involved in the loss or any witnesses, etc.

“Accordingly, to assist the operator, various entities may need to exchange and/or verify information relating to the loss, e.g., where the loss occurred, severity of the loss, facts to determine which party was at fault, etc. This exchange and/or verification of information may be cumbersome and time consuming. Delays for various reasons (e.g., the operator delays reporting of the vehicle loss, verifying the operator’s account of the vehicle loss, etc.) may further delay assistance for the operator.”

As a supplement to the background information on this patent application, NewsRx correspondents also obtained the inventors’ summary information for this patent application: “The disclosed embodiments generally relate to determining vehicle loss based upon vehicle sensor data received from the sensors installed on, or within, the vehicle to initiate an “Instantaneous” Notice of Loss (INOL) for proactively assisting an operator of the vehicle, prior to receiving any notice from the operator of the occurrence of the loss. The vehicle sensor data can be interpreted to be the “ground truth” of the vehicle loss, and thus need not be necessarily verified with manual inspections of the vehicle, for example. Advantageously, for example, an insurer of the vehicle may instantaneously determine that a vehicle loss occurred based upon the received vehicle sensor data, prior to receiving any report of loss information (e.g., phone call from the operator, pictures documenting the loss, police report, etc.) from the operator of the vehicle. In this way, the insurer of the vehicle may employ a proactive approach to initiate processes on behalf of the operator, such as initiating INOL rather than waiting for the operator to initiate FNOL, anticipating that the operator may need assistance, and contacting appropriate entities (e.g., emergency medical technicians (EMTs), police, towing services, taxi or ride-share services, repair shops, body shops, salvage vendors, etc.) that the operator has authorized the insurer to contact in advance if the operator was to experience vehicle loss.

“To employ the proactive approach, a blockchain-based solution is described herein. A large dataset of vehicle sensor data from numerous vehicles may be analyzed to determine one or more parametric events. For example, analysis of the large dataset of vehicle sensor data from numerous vehicles may indicate that a broken window of vehicles correlates to a parametric event of theft of item(s) in vehicles. As another example, analysis of vehicle sensor data may indicate that isolated damage of vehicles (e.g., the front but not the back) correlates to a parametric event of a relatively small collision (e.g., the vehicles drove into trees, mailboxes, etc.), whereas extensive damage of vehicles (e.g., body of vehicles severely damaged) correlates to a parametric event of a relatively large collision (e.g., the vehicles suffered total loss beyond repair). For each parametric event determined from the large dataset of vehicle sensor data, a corresponding smart contract is generated for deployment onto a shared leger (i.e., the blockchain), to define action(s) (e.g., initiating an INOL process, contacting an emergency response entity, towing service entity, taxi or ride-share services entity, vehicle repair service entity, vehicle salvage entity, etc.) when the parametric event involving a vehicle actually occurs.

“The blockchain operated by a group of network entities according to a set of consensus rules manages and resolves vehicle loss according to the generated smart contracts. Evidence regarding the vehicle loss (i.e., vehicle sensor data) and in some cases, any supplementation information (e.g., weather data indicating weather conditions at the moment of the vehicle loss, image data indicating photographic evidence of the vehicle loss) is sent to the blockchain by one or more entities (e.g., sensors installed on or within the vehicle, supplemental sources), which are routed to any of the smart contracts described above that are deployed on the blockchain. Upon execution of these smart contracts, assistance may be provided to the operator of the vehicle prior to receiving any report of loss information from the operator of the vehicle.

“In some embodiments, a computer-implemented method for generating one or more smart contracts for deployment onto a blockchain may be provided. The method may be implemented via one or more local or remote processors, transceivers, sensors, servers, memory units, and/or other electronic or electrical components. The method may include: (1) receiving, at one or more processors, vehicle sensor data generated from sensors mounted on or within one or more vehicles; (2) analyzing, by the one or more processors, the vehicle sensor data to determine one or more parametric events, wherein each of the parametric events is associated with a corresponding severity of loss; (3) generating, by the one or more processors and for each of the one or more parametric events, a corresponding smart contract that is configured to automatically execute on the blockchain when a transaction received from a computing device indicates that a parametric event corresponding to the smart contract has occurred; and/or (4) deploying, by the one or more processors, the smart contract at a particular address on the blockchain. The method may include additional, less, or alternate functionality, including that discussed elsewhere herein.

“In other embodiments, a computer system for generating one or more smart contracts for deployment onto a blockchain may be provided. The computing system may include one or more processors and associated transceivers, and a non-transitory program memory coupled to the one or more processors and storing executable instructions that, when executed by the one or more processors, cause the computer system to: (1) receive vehicle sensor data generated from sensors mounted on or within one or more vehicles; (2) analyze the vehicle sensor data to determine one or more parametric events, wherein each of the parametric events is associated with a corresponding severity of loss; (3) generate, for each of the one or more parametric events, a corresponding smart contract that is configured to automatically execute on the blockchain when a transaction received from a computing device indicates that a parametric event corresponding to the smart contract has occurred; and/or (4) deploy the smart contract at a particular address on the blockchain. The computing system may include additional, less, or alternate functionality, including that discussed elsewhere herein.

“In yet other embodiments, generating one or more smart contracts for deployment onto a blockchain may be provided. The executable instructions, when executed by one or more processors of a computer system, cause the computer system to: (1) receive vehicle sensor data generated from sensors mounted on or within one or more vehicles; (2) analyze the vehicle sensor data to determine one or more parametric events, wherein each of the parametric events is associated with a corresponding severity of loss; (3) generate, for each of the one or more parametric events, a corresponding smart contract that is configured to automatically execute on the blockchain when a transaction received from a computing device indicates that a parametric event corresponding to the smart contract has occurred; and/or (4) deploy the smart contract at a particular address on the blockchain. The executable instructions may include additional, less, or alternate functionality, including that discussed elsewhere herein.

“Advantages will become more apparent to those of ordinary skill 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 the present embodiments for purposes of illustration only. One skilled in the art will readily recognize from the following discussion that alternate embodiments of the structures 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 for generating one or more smart contracts for deployment onto a blockchain, the method comprising: receiving, at one or more processors, vehicle sensor data and/or electronic device data generated from sensors mounted on or within (a) a vehicle, and/or (b) an electronic device located within the vehicle; determining a parametric event associated with a vehicle collision or severity thereof from analysis of the vehicle sensor data and/or electronic device data by inputting, by the one or more processors, the vehicle sensor data and/or electronic device data into a trained machine learning model that is trained to identify vehicle collisions, severity of loss, severity of vehicle damage, and/or other vehicle-related events or factors; generating, by the one or more processors and for the parametric event, a corresponding smart contract that is configured to (i) receive a transaction and/or other data from one or more computing devices, and/or (ii) automatically execute on the blockchain; and deploying, by the one or more processors, the smart contract at a particular address on the blockchain.

“2. The computer-implemented method of claim 1, wherein the smart contract is configured to automatically execute on the blockchain when the transaction and/or vehicle sensor data or electronic device data indicates that the parametric event (a) associated with the vehicle collision or severity thereof, and/or (b) corresponding to the smart contract has occurred.

“3. The computer-implemented method of claim 1, wherein the trained machine learning model is trained using historical vehicle collision data.

“4. The computer-implemented method of claim 3, wherein the trained machine learning model is trained to identify vehicle-related events or factors, the vehicle-related events or factors including identifying one or more of: a vehicle collision has occurred; an amount of vehicle damage; an estimated severity of the vehicle collision; an estimated severity of personal injuries; an estimated cost to repair the vehicle or vehicle parts; an estimated cost to replace the vehicle or vehicle parts; that a tow vehicle is needed to tow a damaged vehicle; that a taxi or ride-share service is needed to transport an operator of the damaged vehicle; that an ambulance is needed at the scene of the vehicle collision; parts needed to repair the damaged vehicle; and/or a nearby repair shop or body shop with the parts and expertise necessary to repair the vehicle.

“5. The computer-implemented method of claim 3, wherein the trained machine learning model identifies one or more of the following vehicle-related events or factors as the parametric event from the vehicle sensor data and/or electronic device data input: a vehicle collision has occurred; an amount of vehicle damage; an estimated severity of the vehicle collision; an estimated severity of personal injuries; an estimated cost to repair the vehicle or vehicle parts; an estimated cost to replace the vehicle or vehicle parts; that a tow vehicle is needed to tow a damaged vehicle; that a taxi or ride-share service is needed to transport an operator of the damaged vehicle; that an ambulance is needed at the scene of the vehicle collision; parts needed to repair the damaged vehicle; and/or a nearby repair shop or body shop with the parts and expertise necessary to repair the vehicle.

“6. The computer-implemented method of claim 1, wherein training the trained machine learning model includes one or more of: (i) Bayesian program learning; (ii) voice recognition and synthesis; (iii) image and/or object recognition; (iv) optical character recognition; (v) natural language processing; (vi) semantic analysis; and/or (vii) automatic reasoning.

“7. The computer-implemented method of claim 1, wherein generating the smart contract includes generating the smart contract to define an action including any one of: (i) initiating an instantaneous notice of loss (INOL); (ii) communicating with an insurer entity; (iii) communicating with an emergency response entity; (iv) communicating with a towing service entity; (v) communicating with a taxi or ride-share service entity; (vi) communicating with a vehicle repair service entity; or (vii) communicating with a vehicle salvage entity.

“8. A computer system for generating one or more smart contracts for deployment onto a blockchain, the computer system comprising: one or more processors; a non-transitory program memory coupled to the one or more processors and storing executable instructions that, when executed by the one or more processors, cause the computer system to: receive vehicle sensor data and/or electronic device data generated from sensors mounted on or within (i) a vehicle, and/or (ii) an electronic device located within the vehicle; determine a parametric event associated with a vehicle collision or severity thereof from analysis of the vehicle sensor data and/or electronic device data by inputting the vehicle sensor data and/or electronic device data into a trained machine learning model that is trained to identify a vehicle collision, a severity of the vehicle collision, and/or other vehicle-related events or factors; generate, for the parametric event, a corresponding smart contract that is configured to automatically execute on the blockchain when a transaction or other data is received from one or more computing devices, and/or configured to receive or store the transaction or other data that is received from the one or more computing devices; and deploy the smart contract at a particular address on the blockchain.

“9. The computer system of claim 8, wherein the smart contract is configured to automatically execute on the blockchain when the transaction and/or vehicle sensor data or electronic device data indicates that the parametric event (a) associated with the vehicle collision or severity thereof, and/or (b) corresponding to the smart contract has occurred.

“10. The computer system of claim 8, wherein the trained machine learning model is trained using historical vehicle collision data.

“11. The computer system of claim 10, wherein the trained machine learning model is trained to identify vehicle-related events or factors, the vehicle-related events or factors including identifying one or more of: a vehicle collision has occurred; an amount of vehicle damage; an estimated severity of the vehicle collision; an estimated severity of personal injuries; an estimated cost to repair the vehicle or vehicle parts; an estimated cost to replace the vehicle or vehicle parts; that a tow vehicle is needed to tow a damaged vehicle; that a taxi or ride-share service is needed to transport an operator of the damaged vehicle; that an ambulance is needed at the scene of the vehicle collision; parts needed to repair the damaged vehicle; and/or a nearby repair shop or body shop with the parts and expertise necessary to repair the vehicle.

“12. The computer system of claim 11, wherein the trained machine learning model identifies one or more of the following vehicle-related events or factors as the parametric event from the vehicle sensor data and/or electronic device data input: a vehicle collision has occurred; an amount of vehicle damage; an estimated severity of the vehicle collision; an estimated severity of personal injuries; an estimated cost to repair the vehicle or vehicle parts; an estimated cost to replace the vehicle or vehicle parts; that a tow vehicle is needed to tow a damaged vehicle; that a taxi or ride-share service is needed to transport an operator of the damaged vehicle; that an ambulance is needed at the scene of the vehicle collision; parts needed to repair the damaged vehicle; and/or a nearby repair shop or body shop with the parts and expertise necessary to repair the vehicle.

“13. The computer system of claim 8, wherein training the trained machine learning model includes one or more of: (i) Bayesian program learning; (ii) voice recognition and synthesis; (iii) image and/or object recognition; (iv) optical character recognition; (v) natural language processing; (vi) semantic analysis; and/or (vii) automatic reasoning.

“14. The computer system of claim 12, wherein the executable instructions, when executed by the one or more processors, cause the computer system to generate the smart contract to define an action including any one of: (i) initiating an instantaneous notice of loss (INOL); (ii) communicating with an insurer entity; (iii) communicating with an emergency response entity; (iv) communicating with a towing service entity; (v) communicating with a taxi or ride-share service entity; (vi) communicating with a vehicle repair service entity; or (vii) communicating with a vehicle salvage entity.”

There are additional claims. Please visit full patent to read further.

For additional information on this patent application, see: Amancha, Steve; Cote, Kerry Lynne; Crossland, Heath; Doak-Wigginton, Kimberly; Frazier, Darnell; Goumandakoye, Zaki; Kloeppel, Kimberly Christine; LeFebre, EllaKate; Rahman, Moinur; Skyten, Erik; Trayer, Jerome Scott. Systems And Methods For Generating A Smart Contract For A Parametric Event Using Machine Learning Algorithms. U.S. Patent Application Number 20230351380, filed April 14, 2023 and posted November 2, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(20230351380)&db=US-PGPUB&type=ids

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