Patent Issued for Processing system having machine learning engine for providing customized user functions (USPTO 11314798): Allstate Insurance Company
2022 MAY 12 (NewsRx) -- By a
The assignee for this patent, patent number 11314798, is
Reporters obtained the following quote from the background information supplied by the inventors: “Users interact with computing devices in a variety of ways. For example, users interact with cell phones, personal computers, fitness trackers, tablets, and the like. Each interaction yields sensor data, associated with characteristics of a user, that may be used to generate outputs unique to the user. Users might not be aware of how best to protect themselves based on the totality of their lifestyle. Accordingly, it would be advantageous to aggregate this sensor data to generate customized outputs for the user to effectively protect users.”
In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “In light of the foregoing background, the following presents a simplified summary of the present disclosure in order to provide a basic understanding of some aspects of the invention. This summary is not an extensive overview of the invention. It is not intended to identify key or critical elements of the invention or to delineate the scope of the invention. The following summary merely presents some concepts of the invention in a simplified form as a prelude to the more detailed description provided below.
“Aspects of the disclosure related to evaluating user habits/characteristics based on sensor data received from one or more devices. In some examples, sensor data may include health sensor data, transportation sensor data, social sensor data, home sensor data, security sensor data, financial sensor data, and other miscellaneous sensor data. The sensor data may be analyzed and aggregated to generate a determination and provide an output to a user. In some examples, machine learning may be used to generate one or more determinations and/or one or more outputs.
“When new, updated, or additional sensor data is received, a server may generate a recommendation output. The recommendation output may be transmitted to a computing device (cell phone, laptop, and the like) associated with the user by way of a message (text message, email, and the like). Additional data may be received which may be analyzed by the server to determine whether the recommendation output was implemented or completed. Based on a determination that the recommendation output was completed, the server may transmit, to a device associated with the user, a positive benefit or incentive. If it is determined that the recommendation output was not completed or implemented, the server may transmit, to a device associated with the user, a negative benefit. The positive benefit and the negative benefit may comprise recommended products for the user. The sensor data indicating whether the recommendation output was completed or implemented may affect a customized user output.
“The customized user output may be updated as new sensor data is received and the user may receive additional benefits (e.g., positive or negative) which may correspond with changes in the customized user output.
“The arrangements described may also include other additional elements, steps, computer-executable instructions, or computer-readable data structures. In this regard, other embodiments are disclosed and claimed herein as well. The details of these and other embodiments of the present invention are set forth in the accompanying drawings and the description below. Other features and advantages of the invention will be apparent from the description, drawings, and claims.”
The claims supplied by the inventors are:
“1. A method comprising: receiving, from a plurality of computing devices, sensor data associated with a plurality of characteristics of a user; aggregating the sensor data into a user dataset, wherein a first portion of the aggregated data corresponds to a first characteristic of the user and a second portion of the aggregated data corresponds to a second characteristic of the user; performing a first comparison between the first portion of the aggregated data and a first machine learning dataset and a second comparison between the second portion of the aggregated data and a second machine learning dataset to generate one or more customized user outputs, wherein the customized user outputs include one or more customized values that the first machine learning dataset assigned to the first characteristic based on the first comparison and one or more customized values that the second machine learning dataset assigned to the second characteristic based on the second comparison; determining, based on a combination of the values of the one or more customized user outputs falling short of a predetermined threshold, a user recommendation output indicating one or more safety precautions corresponding to a neighborhood of the user; and transmitting, to one or more user computing devices of the plurality of computing devices associated with the user, the user recommendation output; receiving an indication from the one or more computing devices that the user has completed performance of the user recommendation output; and transmitting, to the one or more user computing devices a message regarding a positive benefit based on the received indication of the completed performance of the user recommendation output.
“2. The method of claim 1, wherein the positive benefit that comprises one or more recommended products to offer to the user.
“3. The method of claim 2, wherein the one or more recommended products comprise prevention health products.
“4. The method of claim 1, further comprising: updating, based on new sensor data, the one or more customized user outputs; determining, based on the updated customized user outputs, an updated user recommendation output; transmitting, to the one or more user computing devices, an updated message comprising the updated user recommendation output; determining, based on a second indication received from at least one of the plurality of computing devices, that the updated user recommendation output was not completed; and transmitting, to the one or more user computing devices and based on the determining that the updated user recommendation output was not completed, a new message comprising an indication of a negative impact.
“5. The method of claim 4, wherein the negative impact corresponds to one or more recommended products.
“6. The method of claim 4, wherein: the sensor data includes at least one of: health sensor data associated with the user, transportation sensor data associated with the user, social sensor data associated with the user, residential sensor data associated with the user, security sensor data associated with the user, or financial sensor data associated with the user; and the new sensor data includes at least one of: new health sensor data associated with the user, new transportation sensor data associated with the user, new social sensor data associated with the user, new residential sensor data associated with the user, new security sensor data associated with the user, or new financial sensor data associated with the user.
“7. The method of claim 1, further comprising updating the one or more customized user outputs based on determining that the user has completed performance of the user recommendation output.
“8. The method of claim 1, further comprising updating, at predetermined intervals, the one or more customized user outputs.
“9. An apparatus comprising: a memory; and a processor coupled to the memory and programmed with computer-executable instructions for performing steps comprising: upon user completion of a reservation associated with a temporary residence location, determining, based on sensor data of a user, a customized user output for first user characteristic and a customized user output for a second user characteristic, wherein the first user characteristic corresponds to a first customized value assigned by a first machine learning dataset and the second user characteristic corresponds to a second customized value assigned by a second machine learning dataset; determining, based on a combination of the first customized value and the second customized value falling short of a predetermined threshold, a user recommendation output indicating one or more safety precautions corresponding to the temporary residence location; transmitting, to one or more user computing devices of a plurality of computing devices associated with the user, the user recommendation output; receiving an indication from the one or more computing devices that the user has completed performance of the user recommendation output; and transmitting, to the one or more user computing devices a message regarding a positive benefit based on the indication of the completed performance of the user recommendation output.
“10. The apparatus of claim 9, wherein the positive benefit comprises one or more recommended products to offer to the user.
“11. The apparatus of claim 9, further configured to perform the steps comprising: updating, based on new sensor data, the customized user output for at least one of the first characteristic and the second characteristic; determining, based on the updated customized user output, an updated user recommendation output; transmitting, to the one or more user computing devices, the updated user recommendation output; determining, based on a second indication received from at least one of the plurality of computing devices, that the updated user recommendation output was not completed; and transmitting, to the one or more user computing and based on the determining that the updated user recommendation output was not completed, a new message comprising an indication of a negative impact.
“12. The apparatus of claim 11, wherein the negative impact corresponds to one or more recommended products.
“13. The apparatus of claim 11, wherein: the sensor data includes at least one of: health sensor data associated with the user, transportation sensor data associated with the user, social sensor data associated with the user, residential sensor data associated with the user, security sensor data associated with the user, or financial sensor data associated with the user; and the new sensor data includes at least one of: new health sensor data associated with the user, new transportation sensor data associated with the user, new social sensor data associated with the user, new residential sensor data associated with the user, new security sensor data associated with the user, or new financial sensor data associated with the user.
“14. The apparatus of claim 9, the processor further configured to perform the steps comprising: updating, at predetermined intervals and based on the determining the completed performance of the first user recommendation output, the customized user output.
“15. A non-transitory computer-readable medium storing computer executable instructions, which when executed by a processor, cause a computing device to perform steps comprising: upon user completion of a reservation associated with a temporary residence location, determining, based on sensor data of a user, a customized user output for a first user characteristic and a customized user output for a second user characteristic, wherein the first user characteristic corresponds to a first customized value assigned by a first machine learning dataset and the second user characteristics corresponds to a second customized value assigned by a second machine learning dataset; determining, based on a combination of the first customized value and the second customized value falling short of a predetermined threshold, a user recommendation output indicating one or more safety precautions corresponding to the temporary residence location; transmitting, to one or more user computing devices of a plurality of computing devices associated with the user, the user recommendation output; receiving an indication from the one or more computing devices that the user has completed performance of the user recommendation output; and transmitting, to the one or more user computing devices a message regarding a positive benefit based on the indication of the completed performance of the user recommendation output.
“16. The non-transitory computer-readable medium of claim 15, wherein the positive benefit comprises one or more recommended products to offer to the user.
“17. The non-transitory computer-readable medium of claim 15, wherein the computing device is further configured to perform the steps comprising: updating, based on new sensor data, the customized user output for at least one of the first characteristic or the second characteristic; determining, based on the updated customized user output, an updated user recommendation output; transmitting, to the one or more user computing devices, the updated user recommendation output; determining, based on a second indication received from at least one of the plurality of computing devices, that the updated user recommendation output was not completed; and transmitting, to the one or more user computing and based on the determining that the updated user recommendation output was not completed, a new message comprising an indication of a negative impact.
“18. The non-transitory computer-readable medium of claim 17, wherein the negative impact corresponds to one or more recommended products.”
There are additional claims. Please visit full patent to read further.
For more information, see this patent: Sankovsky, Jenny. Processing system having machine learning engine for providing customized user functions.
(Our reports deliver fact-based news of research and discoveries from around the world.)
Patent Issued for Prepaid bundled healthcare services with discreet virtual payment distribution (USPTO 11315160): Mdsave Shared Services Inc.
Patent Issued for System and method for fraud detection using event driven architecture (USPTO 11315119): United Services Automobile Association
Advisor News
Annuity News
Health/Employee Benefits News
Life Insurance News