“Systems And Methods For Obtaining Data Annotations” in Patent Application Approval Process (USPTO 20220414598): Allstate Insurance Company

2023 JAN 12 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent application by the inventor Shapiro, Glenn (Northbrook, IL, US), filed on September 1, 2022, was made available online on December 29, 2022, according to news reporting originating from Washington, D.C., by NewsRx correspondents.

This patent application is assigned to Allstate Insurance Company (Northbrook, Illinois, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “Conventional insurance claims processing is a complex process that starts with a first notification of loss related to an insured item. Upon notification of loss, the claim can be routed to multiple claims adjusters that analyze different aspects of the damage associated with the insured item in order to determine whether compensation for the loss is appropriate.”

In addition to the background information obtained for this patent application, NewsRx journalists also obtained the inventor’s summary information for this patent application: “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.

“Conventional claims adjustment can involve paperwork processing, telephone calls, and potentially face-to-face meetings between claimant and adjuster. In addition, a significant amount of time can elapse between a first notice of loss from the claimant and the final settlement of the claim. Systems and methods in accordance with embodiments of the disclosure can automatically determine an adjuster device to be assigned to process a particular claim. The adjuster device can be provided with a set of data describing damage to an item and a variety of annotations can be applied to the data. In a variety of embodiments, multiple adjuster devices can review the same claim and a final claim outcome can be determined based on the multiple reviews. In many embodiments, machine classifiers may process the set of data to identify particular features within the data. Scoring data can be generated, based on annotations provided by other adjuster devices and/or machine classifiers, reflecting the adjuster device’s skill at identifying features within the data and annotating the data. Claims can be assigned to adjuster devices based on the score assigned to the adjuster device.

“The arrangements described can 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 for providing data processing from a crowdsourced group, comprising: obtaining, by a data processing server system, acceptance data generated based on job request data from at least one of a plurality of adjuster devices; determining, by the data processing server system, an adjuster score for each of the at least one of the plurality of adjuster devices, wherein the acceptance data and the adjuster score indicate a first adjuster device in the plurality of adjuster devices; transmitting, by the data processing server system and to the first adjuster device, item data associated with the job request data; receiving, by the data processing server system from the first adjuster device, first annotation data associated with a set of features in the item data; providing, by the data processing server system, the item data to a trained machine classifier; generating, by the trained machine classifier, a performance data for the first adjuster device based on accuracy of the first annotation data as determined by the trained machine classifier; generating, by the data processing server system, an updated adjuster score associated with the first adjuster device and based on the performance data for the first adjuster device; and transmitting, by the data processing server system, to the first adjuster device, the updated adjuster score.

“2. The method of claim 1, further comprising: obtaining, by the data processing server system and from a third-party server system, certification data for a set of adjuster devices of the plurality of adjuster devices, the set of adjuster devices comprising at least the at least one of the plurality of adjuster devices; and determining, by the data processing server system, the at least one of the plurality of adjuster devices, based on the certification data for the set of adjuster devices.

“3. The method of claim 2, wherein the certification data is based on an item described in the item data.

“4. The method of claim 1, further comprising obtaining, by the data processing server system and from a second adjuster device of the plurality of adjuster devices, second annotation data.

“5. The method of claim 4, further comprising generating, by the data processing server system, scoring data based on the first annotation data and the second annotation data, wherein the scoring data indicates a performance of the first adjuster device relative to the second adjuster device.

“6. The method of claim 5, further comprising: generating, by the data processing server system, an aggregate score for the item data based on the second annotation data; generating, by the data processing server system, feedback data based on the aggregate score and the scoring data; and providing, by the data processing server system, the feedback data to the first adjuster device.

“7. The method of claim 4, wherein generating, by the trained machine classifier, the performance data for the first adjuster device based on the accuracy of the first annotation data as determined by the trained machine classifier comprises: generating, by the trained machine classifier, machine annotation data, the machine annotation data comprising a first feature in the item data and a set of confidence metrics indicative of a likelihood that the first feature is present in the item data, wherein the performance data is determined based on comparing the first annotation data and the machine annotation data.

“8. The method of claim 7, wherein comparing the first annotation data and the machine annotation data comprises at least one of: determining a completeness of the first annotation data based on comparing a number of features identified in the first annotation data to a number of features identified in the machine annotation data and the second annotation data; and determining the accuracy of the first annotation data based on comparing the set of features described in the first annotation data to features described in the machine annotation data and the second annotation data.

“9. A system comprising: at least one processor; and memory storing instructions that, when executed by the at least one processor, cause the at least one processor to: obtain acceptance data generated based on job request data from at least one of a plurality of adjuster devices; determine an adjuster score for each of the at least one of the plurality of adjuster devices, wherein the acceptance data and the adjuster score indicate a first adjuster device in the plurality of adjuster devices; transmit item data associated with the job request data to the first adjuster device; receive first annotation data associated with a set of features in the item data from the first adjuster device; generate a performance data for the first adjuster device using a trained machine classifier, the performance data generated based on accuracy of the first annotation data as determined by the trained machine classifier; generate an updated adjuster score associated with the first adjuster device and based on the performance data for the first adjuster device; and transmit the updated adjuster score to the first adjuster device.

“10. The system of claim 9, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to: obtain certification data for a set of adjuster devices of the plurality of adjuster devices from a third-part server system, the set of adjuster devices comprising at least the at least one of the plurality of adjuster devices; and determine the at least one of the plurality of adjuster devices based on the certification data for the set of adjuster devices.

“11. The system of claim 10, wherein the certification data is based on a particular item described in the item data.

“12. The system of claim 9, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to obtain second annotation data from a second adjuster device of the plurality of adjuster devices.

“13. The system of claim 12, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to generate scoring data based on the first annotation data and the second annotation data, wherein the scoring data indicates a performance of the first adjuster device relative to the second adjuster device.

“14. The system of claim 13, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to: generate an aggregate score for the item data based on the second annotation data; generate feedback data based on the aggregate score and the scoring data; and provide the feedback data to the first adjuster device.

“15. The system of claim 12, wherein generating the performance data for the first adjuster device based on the accuracy of the first annotation data as determined by the trained machine classifier comprises: generating, by the trained machine classifier, machine annotation data, the machine annotation data comprising a first feature in the item data and a set of confidence metrics indicative of a likelihood that the first feature is present in the item data, wherein the performance data is determined based on comparing the first annotation data and the machine annotation data.

“16. The system of claim 15, wherein comparing the first annotation data and the machine annotation data comprises at least one of: determining a completeness of the first annotation data based on comparing a number of features identified in the first annotation data to a number of features identified in the machine annotation data and the second annotation data; and determining the accuracy of the first annotation data based on comparing the set of features described in the first annotation data to features described in the machine annotation data and the second annotation data.

“17. Non-transitory computer readable media having computer executable instructions embodied therein that, when executed by at least one processor of a computing system, cause the computing system to perform operations for providing data processing, the operations comprising: obtain acceptance data generated based on job request data from at least one of a plurality of adjuster devices; determine an adjuster score for each of the at least one of the plurality of adjuster devices, wherein the acceptance data and the adjuster score indicate a first adjuster device in the plurality of adjuster devices; transmit item data associated with the job request data to the first adjuster device; receive first annotation data associated with a set of features in the item data from the first adjuster device; generate a performance data for the first adjuster device using a trained machine classifier, the performance data generated based on accuracy of the first annotation data as determined by the trained machine classifier; generate an updated adjuster score associated with the first adjuster device and based on the performance data for the first adjuster device; and transmit the updated adjuster score to the first adjuster device.

“18. The media of claim 17, wherein the operations further comprise: obtain certification data for a set of adjuster devices of the plurality of adjuster devices from a third-part server system, the set of adjuster devices comprising at least the at least one of the plurality of adjuster devices; and determine the at least one of the plurality of adjuster devices based on the certification data for the set of adjuster devices, wherein the certification data is based on an item described in the item data.

“19. The media of claim 17, wherein the operations further comprise obtain second annotation data from a second adjuster device of the plurality of adjuster devices.”

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

URL and more information on this patent application, see: Shapiro, Glenn. Systems And Methods For Obtaining Data Annotations. U.S. Patent Application Number 20220414598, filed September 1, 2022 and posted December 29, 2022. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(20220414598)&db=US-PGPUB&type=ids

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