Patent Issued for Processing system to generate risk scores for electronic records (USPTO 11704731): Hartford Fire Insurance Company

2023 AUG 04 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent by the inventors Barnes, Shane Eric (Avon, CT, US), Hill, Peter M. (Bloomfield, CT, US), Robinson, Davis Preston (Manchester, NH, US), Schmit, Joseph Peter (Grand Ledge, MI, US), Summerson, Doug A. (Canton, CT, US), filed on April 11, 2018, was published online on July 18, 2023, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents.

Patent number 11704731 is assigned to Hartford Fire Insurance Company (Hartford, Connecticut, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “In some cases, a risk value associated with an enterprise system may depend at least in part on attribute values of electronic records representing a plurality of potential associations with the enterprise system. For example, the risk value might tend to increase when a specific type of attribute value increases (or decrease when another type of attribute value increases). Moreover, an accurate prediction of the risk value may be desired. Manually entering information to receive predictions and/or decisions about the risk value, however, can be a time consuming and error prone process, especially when a substantial number of electronic records and/or attribute variables may influence the behavior of the system. An enterprise might, under certain conditions, gather additional information about a potential association to improve the decision-making process. This approach, however, may be burdensome (e.g., because the additional information may be gathered even when it is not necessarily required). Similarly, a large and diverse amount of third-party information might further complicate these tasks. Note that improving the performance of the system and/or the accuracy of decisions made about potential associations might result in substantial improvements to the operation of the enterprise and/or one or more networks associated with the enterprise (e.g., by reducing an overall number of electronic messages that need to be created and transmitted via the network).

“It would be desirable to provide systems and methods to automatically create risk scores for electronic records in a way that provides faster, more accurate results and that allows for flexibility and effectiveness when responding to those results.”

In addition to the background information obtained for this patent, NewsRx journalists also obtained the inventors’ summary information for this patent: “According to some embodiments, systems, methods, apparatus, computer program code and means are provided to automatically create risk scores for electronic records in a way that provides faster, more accurate results and that allow for flexibility and effectiveness when responding to those results. In some embodiments, an automated scoring analysis computer may access information in a historical data store, including sets of attribute values and prior results for a plurality of prior associations, to create a scoring model. An indication of a selected potential association from a potential association data store may be received, including a set of attribute values. The scoring analysis computer may then calculate a risk score for the selected potential association based on the scoring model. A front-end application computer server may select a workflow path from a plurality of potential workflow paths.

“Some embodiments comprise: means for accessing, by an automated scoring analysis computer, information in a historical data store, including sets of attribute values and prior results for a plurality of prior associations, to create a scoring model; means for receiving an indication of a selected potential association from a potential association data store, including a set of attribute values; means for calculating a risk score for the selected potential association based on the scoring model; means for automatically selecting, by a front-end application computer server, a workflow path from a plurality of potential workflow paths.

“In some embodiments, a communication device associated with a front-end application computer server exchanges information with remote devices. The information may be exchanged, for example, via public and/or proprietary communication networks.

“A technical effect of some embodiments of the invention is an improved and computerized way to automatically create risk scores for electronic records in a way that provides faster, more accurate results and that allow for flexibility and effectiveness when responding to those results. With these and other advantages and features that will become hereinafter apparent, a more complete understanding of the nature of the invention can be obtained by referring to the following detailed description and to the drawings appended hereto.”

The claims supplied by the inventors are:

“1. A computer system of an enterprise, comprising: (a) a potential association data store containing electronic records representing a plurality of potential associations for properties, each property having a building, and the enterprise and, for each potential association, an electronic record identifier and a set of attribute values; (b) a historical data store containing electronic records representing prior associations with the enterprise and, for each prior association, an electronic record identifier, a set of attribute values, and at least one prior result; © a model training computer to access information in the historical data store, including sets of attribute values and prior results for a plurality of prior associations, to train a predictive scoring model with historic insurance claim information associated insurance policies along with third-party data and transmit the trained predictive scoring model to an automated scoring analysis computer; (d) the automated scoring analysis computer, coupled to the potential association data store and the historical data store, including: a first computer processor, and a first computer memory, coupled to the first computer processor, storing instructions that, when executed by the first computer processor, cause the automated scoring analysis computer to: (i) access, via an encrypted database management system, information in the potential association data store, including sets of attribute values, (ii) receive an indication of a selected potential association in the potential association data store, including the set of attribute values, (iii) calculate a risk score for the selected potential association, representing a risk of loss for a property, based on all of: the trained predictive scoring model, social media data of the property, third-party data, location information, business credit information, prior interactions, employee sentiment data, and information about the building, including a building limit per square foot, and (iv) output an indication of the calculated risk score; (e) the front-end application computer server, coupled to the automated scoring analysis computer, including: a second computer processor, and a second computer memory, coupled to the second computer processor, storing instructions that, when executed by the second computer processor, cause the front-end application computer server to: (v) receive the indication of the calculated risk score for the selected potential association, (vi) automatically select a workflow path from a plurality of potential workflow paths based on the indication of the calculated risk score, (vii) execute the selected workflow path by modifying a set of information requests including the automatic removal of information requests transmitted from the enterprise when the calculated risk score is below a pre-determined threshold value and the automatic completion of the potential association based on the calculated risk score and responses received in association with the modified set of information requests, and (viii) transmit training information to the model training computer to adapt the trained predictive scoring model to changing conditions; and (f) a communication port coupled to the front-end application computer server to transmit data for an interactive user interface display in accordance with the selected workflow path via security features and a distributed communication network, wherein the selected workflow path reduces an overall number of electronic messages transmitted by omitting a subset of information request messages transmitted via the communication port when the calculated risk score is below the pre-determined threshold value, and further wherein the interactive user interface display includes all of: (1) an image of the property and building, (2) a linear graphical representation of the calculated risk score, and (3) an indication of the selected workflow path.

“2. The system of claim 1, wherein the risk score is further calculated based on results of an automated image recognition process.

“3. The system of claim 1, wherein the predictive scoring model utilizes at least one of: (i) quantile bands, and (ii) clustering.

“4. The system of claim 1, wherein the selected workflow path includes completing the potential association when the risk score is below a first pre-determined threshold value, preventing the potential association when the risk score is above a second pre-determined threshold value, and applying at least one completion rule when the risk score is between the first and second pre-determined threshold values.

“5. The system of claim 1, wherein each electronic record represents a potential insurance policy and the calculated risk score comprises an underwriting grade indicating a risk of loss for a property and building covered by the potential insurance policy.

“6. The system of claim 5, wherein each potential insurance policy at least one of: (i) an insurance policy quote, (ii) an existing insurance policy, and (iii) an insurance policy renewal.

“7. The system of claim 5, wherein an indication of an electronic record of interest is returned as a result of an insurance policy search input.

“8. The system of claim 7, wherein the insurance policy search input comprises at least one of: (i) an insurance policy number, (ii) a selected location, (iii) an insured name, (iv) an insurance policy description, and (v) a building identifier.

“9. The system of claim 5, wherein at least one of the attribute values comprises information about an insured covered by the insurance policy, including at least one of: (i) an annual sales amount, (ii) an industry classification, and (iii) prior claim information.

“10. The system of claim 5, wherein the attribute values include all of: (i) a property deductible amount and (ii) a business personal property limit.

“11. The system of claim 5, wherein the attribute values include all of: (i) a construction occupancy protection and exposure attribute, (ii) a census attribute, and (iii) a geography attribute.

“12. The system of claim 5, wherein at least one of the attribute values comprises information about a location covered by the insurance policy, including at least one of: (i) a quality index, (ii) an earthquake zone, (iii) a wind zone, (iv) a sub-wind zone, and (v) a flood zone.”

URL and more information on this patent, see: Barnes, Shane Eric. Processing system to generate risk scores for electronic records. U.S. Patent Number 11704731, filed April 11, 2018, and published online on July 18, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11704731)&db=USPAT&type=ids

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