Patent Issued for System and method for generating mobility profile (USPTO 11963259): State Farm Mutual Automobile Insurance Company

2024 MAY 07 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Gaudin, Kristopher Keith (Bloomington, IL, US), Herbert, Cameron John (Bloomington, IL, US), McCloskey, Connor Warren (Bloomington, IL, US), filed on August 22, 2022, was published online on April 16, 2024.

The assignee for this patent, patent number 11963259, is State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “Consumers have been reluctant, historically, to share large amounts of data with companies, even for the purpose of receiving enhanced service. The type of data users have been willing to share has varied over time, and generally, users’ hesitance to share personal information and location/movement data has remained constant. The historical lack of quality user data has blunted the effectiveness of campaigns intended to appeal to prospective customers looking for a more connected and personalized banking and insurance experience. However, new research has shown that younger users are appreciably more willing to share all types of data with companies, particularly in exchange for improved and/or personalized service.

“User data collected may create a better understanding of each consumer, including by allowing multiple users to be distinguished in a way that may not be possible with traditional data collection practices, where only limited information may be known about each respective user. Newfound user willingness, combined with the application of data modeling algorithms across and among many categories of user data, may provide companies with unprecedented insights into their users’ behaviors, preferences, and the risks attendant to those customers. By having a deeper understanding of user behavior, it may be possible for companies to offer rewards to customers who act to decrease risks. Therefore, there is a need for methods and systems for generating user mobility profiles, to provide a more personalized experience to users and to allow service providers to apply findings from the data for the benefit of the user by dynamically learning a user’s preferences and opportunities to reduce risk, along with individual user information to help the user navigate life more effectively, efficiently, and intuitively.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “In one aspect, a computer-implemented method of generating a user mobility profile includes (i) receiving, in a remote computing device, mobility data associated with the user; (ii) storing, in an electronic database, the mobility data associated with the user; (iii) analyzing, using a trained machine learning model, a portion of the mobility data to produce an output corresponding to the portion of the mobility data; (iv) generating, based on the output, information corresponding to the user; (v) transmitting the generated information to a display device of the user; and (vi) displaying, in the display device, the generated information.

“In another aspect, computing system includes one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to: (i) receive, in a remote computing device, mobility data associated with a user; (ii) store, in an electronic database, the mobility data associated with the user; (iii) analyze, using a trained machine learning model, a portion of the mobility data to produce an output corresponding to the portion of the mobility data; (iv) generate, based on the output, information corresponding to the user; (v) transmit the generated information to a display device of the user; and (vi) display, in the display device, the generated information.

“In yet another aspect, a non-transitory computer readable medium includes program instructions that when executed, cause a computer to (i) receive, in a remote computing device, mobility data associated with a user; (ii) store, in an electronic database, the mobility data associated with the user; (iii) analyze, using a trained machine learning model, a portion of the mobility data to produce an output corresponding to the portion of the mobility data; (iv) generate, based on the output, information corresponding to the user; (v) transmit the generated information to a display device of the user; and (vi) display, in the display device, the generated information.”

The claims supplied by the inventors are:

“1. A computer-implemented method of generating a user mobility profile, comprising: receiving, in a remote computing device, mobility data associated with the user; storing, in an electronic database, the mobility data associated with the user; analyzing, using a machine learning model trained on historical insurance claim and purchasing data, a portion of the mobility data to produce an output corresponding to the portion of the mobility data; generating, based on the output, information corresponding to the user; transmitting the generated information to a display device of the user; displaying, in the display device, the generated information; generating the trained machine learning model by training a neural network, wherein the neural network includes a plurality of input neurons configured to accept, respectively, one or more portions of the mobility data, and to generate, based on the one or more portions of the mobility data, one or more outputs corresponding to one or both of (i) a risk profile, and (ii) an ambient similarity score; identifying, based on the ambient similarity score, a set of similar users wherein each respective one of the set of users is associated with the ambient similarity score; generating, by analyzing at least the set of similar users, a smart suggestion; and transmitting, to the user, the smart suggestion.

“2. The method of claim 1, wherein displaying the generated information corresponding to the user includes displaying a notification including one or both of (i) a smart recommendation, and (ii) a safe route.

“3. The method of claim 1, wherein analyzing, using the trained machine learning model, the portion of the mobility data to produce the output corresponding to the portion of the mobility data includes analyzing both traditional data and non-traditional data.

“4. The method of claim 1, wherein receiving the mobility data associated with the user includes receiving one or both of (i) location data corresponding to the user, and (ii) consumer history data corresponding to the user.

“5. The method of claim 4 wherein the consumer history data corresponding to the user is retrieved from a third-party credit reporting bureau.

“6. The method of claim 1, wherein receiving the mobility data associated with the user includes receiving one or both of (i) internet use data, and (ii) mobility accounts and applications data.

“7. The method of claim 1, wherein the mobility data is first mobility data and the risk profile is a first risk profile, further comprising: repeating the method using a second mobility data as input to obtain a second risk profile; comparing the first risk profile and the second risk profile to determine a risk mitigation; and transmitting, based on the risk mitigation, a reward to the user.

“8. A computing system comprising: one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to: receive, in a remote computing device, mobility data associated with a user; store, in an electronic database, the mobility data associated with the user; analyze, using a machine learning model trained on historical insurance claim and purchasing data, a portion of the mobility data to produce an output corresponding to the portion of the mobility data; generate, based on the output, information corresponding to the user; transmit the generated information to a display device of the user; display, in the display device, the generated information; generate the trained machine learning model by training a neural network including a plurality of input neurons configured to accept, respectively, one or more portions of the mobility data; generate, based on the one or more portions of the mobility data, one or more outputs that correspond to one or both of (i) a risk profile, and (ii) an ambient similarity score; identify, based on the ambient similarity score, a set of similar users wherein each respective one of the set of users is associated with the ambient similarity score; generate, by analyzing at least the set of similar users, a smart suggestion; and transmit, to the user, the smart suggestion.

“9. The system of claim 8, wherein the information corresponding to the user includes one or both of (i) a smart recommendation, and (ii) a safe route.

“10. The system of claim 8, wherein the instructions further cause the one or more processors to analyze both traditional data and non-traditional data.

“11. The system of claim 8, wherein the instructions further cause the one or more processors to receive one or both of (i) location data corresponding to the user, and (ii) consumer history data corresponding to the user.

“12. The system of claim 11, wherein the consumer history data includes data from a third party credit reporting bureau.

“13. The system of claim 8, wherein the instructions further cause the one or more processors to receive one or both of (i) internet use data, and (ii) mobility accounts and applications data.

“14. The system of claim 8, wherein the mobility data is first mobility data and the risk profile is a first risk profile, and the instructions further cause the one or more processors to: repeat, using a second mobility data as input to obtain a second risk profile, compare the first risk profile and the second risk profile to determine a risk mitigation, and transmit, based on the risk mitigation, a reward to the user.

“15. A non-transitory computer readable medium containing program instructions that when executed, cause a computer to: receive, in a remote computing device, mobility data associated with a user; store, in an electronic database, the mobility data associated with the user; analyze, using a machine learning model trained on historical insurance claim and purchasing data, a portion of the mobility data to produce an output corresponding to the portion of the mobility data; generate, based on the output, information corresponding to the user; transmit the generated information to a display device of the user; display, in the display device, the generated information; generate the trained machine learning model by training a neural network including a plurality of input neurons configured to accept, respectively, one or more portions of the mobility data; generate, based on the one or more portions of the mobility data, one or more outputs that correspond to one or both of (i) a risk profile, and (ii) an ambient similarity score; identify, based on the ambient similarity score, a set of similar users wherein each respective one of the set of users is associated with the ambient similarity score; generate, by analyzing at least the set of similar users, a smart suggestion; and transmit, to the user, the smart suggestion.”

For more information, see this patent: Gaudin, Kristopher Keith. System and method for generating mobility profile. U.S. Patent Number 11963259, filed August 22, 2022, and published online on April 16, 2024. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11963259)&db=USPAT&type=ids

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