“Using Images And Voice Recordings To Facilitate Underwriting Life Insurance” in Patent Application Approval Process (USPTO 20240027780): State Farm Mutual Automobile Insurance Company

2024 FEB 12 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent application by the inventors Bernico, Michael L. (Bloomington, IL, US); Myers, Jeffrey S. (Normal, IL, US), filed on September 29, 2023, was made available online on January 25, 2024, 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: “The nature of the underwriting process for life insurance includes a number of factors which limit the ability to sell policies online. For example, some providers may require collecting samples of bodily fluids to assess an applicant’s health status. Furthermore, even providers who do not require such samples are at risk of receiving fraudulent answers to personal and/or health-related questions, such as the applicant falsely claiming to be a non-smoker. Prior attempts to solve these problems include not selling high-benefit policies online, proxying the desired medical information with advanced statistical techniques using data from other sources, and pricing potential fraud into future policies.

“Also, machine vision techniques have been employed to extract health-related information from images of people. For example, one machine vision platform is able to diagnose certain medical conditions based upon analyses of images from diagnostic imaging tools, such as an X-ray, a CT scan, and/or an MRI scan. The computer’s diagnoses may even be able to identify ceratin conditions at earlier stages than doctors could identify them in some situations.”

In addition to the background information obtained for this patent application, NewsRx journalists also obtained the inventors’ summary information for this patent application: “Embodiments of the present technology relate to systems and methods for analyzing still and/or moving (i.e., video) images and/or voice recordings of applicants as part of an underwriting process to determine appropriate life insurance premiums and/or other terms of coverage.

“In a first aspect, a system for evaluating an insurance applicant as part of an underwriting process to determine one or more appropriate terms of insurance coverage may broadly comprise a communication element and a processing element. The communication element may be configured to receive an image of the insurance applicant. The processing element may be trained to probablistically correlate an aspect of appearance with a personal and/or health-related characteristic by being provided with a database of images of individuals having known personal and/or health-related characteristics. The trained processing element may be configured to analyze the image of the insurance applicant to probablistically determine the personal and/or health-related characteristic for the insurance applicant, and to suggest the appropriate term of insurance coverage based at least in part on the probablistically determined personal and/or health-related characteristic. The system may include more, fewer, or alternative components, including those discussed elsewhere herein.

“In another aspect, a computer-implemented method for evaluating an insurance applicant as part of an underwriting process to determine one or more appropriate terms of insurance coverage may be provided. The method may include training a processing element to probablistically correlate an aspect of appearance with a personal and/or health-related characteristic by providing the processing element with a database of images of individuals having known personal or health-related characteristics. The method may include receiving with a communication element an image of the insurance applicant; analyzing the image of the insurance applicant with the trained processing element to probablistically determine the personal and/or health-related characteristic for the insurance applicant; and/or suggesting with the processing element the one or more appropriate terms of insurance coverage based at least in part on the probablistically determined personal and/or health-related characteristic. The computer-implemented method may include more, fewer, or alternative actions, including those discussed elsewhere herein.

“In another aspect, a non-transitory computer-readable medium with an executable program stored thereon for evaluating an insurance applicant as part of an underwriting process to determine one or more appropriate terms of insurance coverage may broadly instruct a system (that includes a communication element and a processing element) to perform the following actions. The processing element may be trained to probablistically correlate an aspect of appearance with a personal and/or health-related characteristic by providing the processing element with a database of images of individuals having known personal or health-related characteristics. The communication element may be instructed to receive an image of the insurance applicant. The trained processing element may be instructed to analyze the image of the insurance applicant to probablistically determine the personal and/or health-related characteristic for the insurance applicant, and instructed to suggest the one or more appropriate terms of insurance coverage based at least in part on the probablistically determined personal and/or health-related characteristic. The non-transitory computer-readable medium with an executable program stored thereon may include more, fewer, or alternative instructions, including those discussed elsewhere herein.

“Various implementations of any or all of the foregoing aspects may include any one or more of the following additional features. The insurance coverage may be life insurance coverage, and the one or more appropriate terms of insurance coverage may include an insurance premium. The image of the insurance applicant may be a digital, analog, still, or moving (i.e., video) image, and the image may be an otherwise non-diagnostic conventional image, such as a “selfie” taken by the insurance applicant. The processing element may be trained using supervised or unsupervised machine learning, and may employ a neural network, which may be a convolutional neural network or a deep learning neural network. The personal and/or health-related characteristic may be, for example, any one more of age, sex, weight, height, ethnicity, lifespan, cause of death, tobacco use, alcohol use, drug use, diet, and existing medical conditions, and/or risk factors for future medical conditions.

“The communication element may be further configured to receive a voice recording of the insurance applicant. The processing element may be further trained to probablistically correlate an aspect of voice with the personal and/or health-related characteristic by being provided with a database of voice recordings of individuals having the known personal and/or health related characteristics. The processing element may be further configured to analyze the voice recording of the insurance applicant to probablistically determine the personal and/or health-related characteristic for the insurance applicant, and to suggest the appropriate term of insurance coverage based at least in part on the probablistically determined personal and/or health-related characteristic.

“The processing element may be further configured to use the probablistically determined personal and/or health-related characteristic to verify information provided by the insurance applicant. The processing element may be further configured to use the probablistically determined personal and/or health-related characteristic to wholly or at least partially automatically determine the one or more appropriate terms of coverage.

“Advantages of these and other embodiments will become more apparent to those skilled in the art from the following description of the exemplary embodiments which have been shown and described by way of illustration. As will be realized, the present embodiments described herein 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 exemplary 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:

“1-20. (canceled)

“21. A computer system comprising: at least one memory configured to store computer-executable instructions; and at least one processor configured to execute the stored instructions, which when executed cause the at least one processor to perform operations comprising: receiving, via a communication element of the computer system, image data and audio data representing an appearance and voice of an applicant; analyzing the image data and the audio data of the applicant using a machine-learning (ML) algorithm, the ML algorithm configured to determine health-related characteristics for the applicant based upon an input of the image data and the audio data; and generating or updating a health-related insurance policy based at least in part on the determined health-related characteristics of the applicant.

“22. The computer system of claim 21, wherein the ML algorithm is trained to correlate aspects of the appearance and the voice with health-related characteristics using a database of image, video, and/or audio information of individuals having known health-related characteristics.

“23. The computer system of claim 21, wherein the operations further comprise determining a life or health insurance policy, premium, or discount for the applicant based at least in part on the verified health-related characteristics of the applicant.

“24. The computer system of claim 21, wherein the health-related characteristics include a pulse or heart rate.

“25. The computer system of claim 21, wherein the health-related characteristics indicate, or are at least partly associated with, smoking, a lack of smoking, or an amount or frequency of smoking.

“26. The computer system of claim 21, wherein the health-related characteristics indicate, or are at least partly associated with, drug or alcohol use, a lack of drug or alcohol use, or an amount or frequency of drug or alcohol use.

“27. The computer system of claim 21, wherein the ML algorithm is trained using supervised machine learning.

“28. The computer system of claim 21, wherein the ML algorithm is implemented using a neural network.

“29. The computer system of claim 28, wherein the neural network is a convolutional neural network.

“30. The computer system of claim 28, wherein the neural network is a deep learning neural network.

“31. The computer system of claim 21, wherein the health-related characteristics are selected from a group including one or more of: age, sex, weight, height, lifespan, cause of death, tobacco use, alcohol use, drug use, diet, and existing medical conditions.

“32. The computer system of claim 21, wherein the operations further comprise using the determined health-related characteristics of the applicant to substantially and automatically determine appropriate terms of coverage for a life or health insurance policy.

“33. A computer-implemented method, comprising: receiving image data and audio data representing an appearance and voice of an applicant; analyzing the image data and the audio data of the applicant using a machine-learning (ML) algorithm, the ML algorithm configured to determine health-related characteristics for the applicant based upon an input of the image data and the audio data; and generating or updating a health-related insurance policy based at least in part on the determined health-related characteristics of the applicant.

“34. The computer-implemented method of claim 33, further comprising training the ML algorithm to correlate aspects of the appearance and the voice with health-related characteristics using a database of image, video, and/or audio information of individuals having known health-related characteristics.

“35. The computer-implemented method of claim 33, further comprising determining a life or health insurance policy, premium, or discount for the applicant based at least in part on the verified health-related characteristics of the applicant, wherein the health-related characteristics include, indicate, or are at least partly associated with, smoking, a lack of smoking, or an amount or frequency of smoking, a pulse rate, heart rate, drug or alcohol use, a lack of drug or alcohol use, or an amount or frequency of drug or alcohol use.

“36. The computer-implemented method of claim 33, wherein the health-related characteristics are selected from a group including one or more of: age, sex, weight, height, lifespan, cause of death, tobacco use, alcohol use, drug use, diet, and existing medical conditions.

“37. The computer-implemented method of claim 33, further comprise using the determined health-related characteristics of the applicant to substantially and automatically determine appropriate terms of coverage for a life or health insurance policy.

“38. At least one non-transitory computer-readable media having computer-executable instructions embodied thereon, wherein when executed by a computing device including at least one processor in communication with at least one memory device and in communication with a mobile device of an applicant, the computer-executable instructions cause the at least one processor to: receive, from the mobile device of the applicant, image data and audio data representing an appearance and voice of the applicant; analyze the image data and audio date of the applicant using a machine-learning (ML) algorithm, the ML algorithm configured to determine health-related characteristics for the applicant based upon an input of the image data and the audio data; and generate or update a health-related insurance policy based at least in part on the determined health-related characteristics of the applicant.

“39. The least one non-transitory computer-readable media of claim 38, wherein the computer-executable instructions further cause the at least one processor to train the ML algorithm to correlate aspects of the appearance and the voice with health-related characteristics using a database of image, video, and/or audio information of individuals having known health-related characteristics.

“40. The least one non-transitory computer-readable media of claim 38, wherein the computer-executable instructions further cause the at least one processor to use the determined health-related characteristics of the applicant to substantially and automatically determine appropriate terms of coverage for a life or health insurance policy.”

URL and more information on this patent application, see: Bernico, Michael L.; Myers, Jeffrey S. Using Images And Voice Recordings To Facilitate Underwriting Life Insurance. U.S. Patent Application Number 20240027780, filed September 29, 2023 and posted January 25, 2024. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(20240027780)&db=US-PGPUB&type=ids

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