Processing system for data elements received via source inputs

• US 10,176,526 B2
• Filed: 12/17/2015
• Issued: 01/08/2019
• Est. Priority Date: 11/30/2015
• Status: Active Grant

• Current Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Original Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Inventors: McLaughlin, Kelly J., Barnes, Shane Eric, Xiong, Huimin
• Primary Examiner(s): Wong, Eric T
• Application Number:
  US14/972,939
• Publication Number:
  US 20170154382A1
• Time in Patent Office: 1,118 Days
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

Mediums, apparatus, computer program code, and means may be provided to evaluate relative risks based at least in part on source inputs received via a distributed communication network by an automated back-end application computer server. According to some embodiments, the server may access a data store containing electronic files associated with a set of entities to retrieve, for each of a plurality of the entities in the set of entities, electronic files associated with that entity. The server may also retrieve structured data elements, unstructured data elements, and external, third-party data elements for that entity. The server may then execute an automated risk model to assign a risk score to that entity based on the electronic files, the structured data elements, the unstructured data elements, and the external, third-party data elements for that entity and transmit indications of the risk scores for the plurality of entities.

Claims

1. A system to evaluate relative risks based at least in part on source inputs received via a distributed communication network by an automated back-end application computer server, comprising:

(a) a structured data element information source input;

(b) an unstructured data element information source input;

(c) an external, third-party data element information source input;

(d) a communication port to facilitate an exchange of electronic messages with the structured data element information source input, the unstructured data element information source input, and the external, third-party data element information source input via the distributed communication network;

(e) a data store containing electronic files associated with a set of entities; and

(f) the back-end application computer server, coupled to the communication port and the data store, programmed to;

(i) for each of a plurality of the entities in the set of entities, access the electronic files in the data store associated with that entity,

(ii) retrieve structured data elements for that entity from the structured data element information source input,

(iii) retrieve unstructured data elements for that entity from the unstructured data element information source input,

(iv) retrieve external, third-party data elements for that entity from the external, third-party data element information source input,

(v) determine at least one variable associated with an automated risk model, the at least one variable being assigned a predictive quality based at least in part on an input frequency over time of the variable, using a variable proving ground tool comprising a scoring matrix configured to rate variables based on at least input frequency over time,

(vi) execute the automated risk model to assign a risk score to that entity based on the at least one variable, the electronic files, the structured data elements, the unstructured data elements, and the external, third-party data elements for that entity, and

(vii) transmit indications of the risk scores for the plurality of entities.

2. The system of claim 1, wherein the data store is associated with an insurer'"'"'s book of business, and each entity in the data store comprises an insured party.

3. The system of claim 2, wherein the risk score represents a likelihood of a substantial potential loss for the insurer.

4. The system of claim 3, wherein at least some of the insured parties are associated with at least one of:

workers'"'"' compensation insurance, commercial automobile insurance, general liability insurance, property insurance, property casualty insurance, homeowners'"'"' insurance, personal lines of insurance, group benefits insurance, and life insurance.

5. The system of claim 3, wherein the automated risk model is executed at least one of:

when initiated by an administrator, responsive to a specific query submitted by the administrator, on a periodic basis, on a daily basis, on a weekly basis, on a monthly basis, and on a substantially constant basis.

6. The system of claim 3, wherein the risk score comprises at least one of:

a numerical value for each insured party, and a ranked list of insured parties.

7. The system of claim 6, wherein the plurality of insured parties are insured parties that that do not satisfy a pre-determined threshold criteria indicating that a substantial potential loss is unlikely.

8. The system of claim 3, wherein the structured data elements are associated with at least one of:

internally stored data elements about the insured party, and governmental or regulatory data elements.

9. The system of claim 3, wherein the unstructured data elements are associated with at least one of:

web pages of the insured party, web pages mentioning the insured party, text information, image information, satellite image information, drone image information, video information, and audio information.

10. The system of claim 3, wherein the external, third-party data elements are associated with at least one of social media content and online, user-submitted review content.

11. A computerized method to evaluate relative risks based at least in part on source inputs received via a distributed communication network by an automated back-end application computer server, comprising:

accessing a data store containing electronic files associated with a set of entities to retrieve, for each of a plurality of the entities in the set of entities, electronic files associated with that entity;

retrieving structured data elements for that entity from a structured data element information source input;

retrieving unstructured data elements for that entity from an unstructured data element information source input;

retrieving external, third-party data elements for that entity from an external, third-party data element information source input;

determining at least one variable associated with an automated risk model, the at least one variable being assigned a predictive quality based at least in part on an input frequency over time of the variable, using a variable proving ground tool comprising a scoring matrix configured to rate variables based on at least input frequency over time;

executing, by a computer processor of the back-end application computer server, the automated risk model to assign a risk score to that entity based on the at least one variable, the electronic files, the structured data elements, the unstructured data elements, and the external, third-party data elements for that entity; and

transmitting indications of the risk scores for the plurality of entities.

12. The method of claim 11, wherein the data store is associated with an insurer'"'"'s book of business, and each entity in the data store comprises an insured party.

13. The method of claim 12, wherein the risk score represents a likelihood of a substantial potential loss for the insurer.

14. The method of claim 13, wherein at least some of the insured parties are associated with at least one of:

workers'"'"' compensation insurance, commercial automobile insurance, general liability insurance, property insurance, and property casualty insurance.

15. The method of claim 13, wherein the automated risk model is executed at least one of:

when initiated by an administrator, on a periodic basis, on a daily basis, on a weekly basis, and on a monthly basis.

16. The method of claim 13, wherein the risk score comprises at least one of:

a numerical value for each insured party, and a ranked list of insured parties.

17. The method of claim 13, wherein:

the structured data elements are associated with at least one of;

internally stored data elements about the insured party, and governmental or regulatory data elements,

the unstructured data elements are associated with at least one of;

web pages of the insured party, web pages mentioning the insured party, text information, image information, satellite image information, drone image information, video information, and audio information, and

the external, third-party data elements are associated with at least one of social media content and online, user-submitted review content.

18. A non-transitory, computer-readable medium storing instructions, that, when executed by a processor, cause the processor to perform a method to evaluate relative risks based at least in part on source inputs received via a distributed communication network by an automated back-end application computer server, the method comprising:

accessing a data store containing electronic files associated with a set of entities to retrieve, for each of a plurality of the entities in the set of entities, electronic files associated with that entity;

retrieving structured data elements for that entity from a structured data element information source input;

retrieving unstructured data elements for that entity from an unstructured data element information source input;

retrieving external, third-party data elements for that entity from the external, third-party data element information source input;

determining at least one variable associated with an automated risk model, the at least one variable being assigned a predictive quality based at least in part on an input frequency over time of the variable, using a variable proving ground tool comprising a scoring matrix configured to rate variables based on at least input frequency over time;

executing, by a computer processor of the back-end application computer server, the automated risk model to assign a risk score to that entity based on the at least one risk factor, the electronic files, the structured data elements, the unstructured data elements, and the external, third-party data elements for that entity;

transmitting indications of the risk scores for the plurality of entities;

automatically determining a set of potential responses for a selected entity based on the associated risk score; and

presenting a graphical user interface display including the automatically determined set of potential responses.

19. The medium of claim 18, wherein the data store is associated with an insurer'"'"'s book of business, and each entity in the data store comprises an insured party.

20. The medium of claim 19, wherein the risk score represents a likelihood of a substantial potential loss for the insurer.

21. The medium of claim 20, wherein at least some of the insured parties are associated with at least one of:

workers'"'"' compensation insurance, commercial automobile insurance, general liability insurance, property insurance, and property casualty insurance.

22. The medium of claim 20, wherein the automated risk model is executed at least one of:

when initiated by an administrator, on a periodic basis, on a daily basis, on a weekly basis, and on a monthly basis.

23. The medium of claim 20, wherein the risk score comprises at least one of:

(i) a numerical value for each insured party, and (ii) a ranked list of insured parties.

24. The medium of claim 20, wherein:

the structured data elements are associated with at least one of;

Internally stored data elements about the insured party, and governmental or regulatory data elements,

the unstructured data elements are associated with at least one of;

web pages of the insured party, web pages mentioning the insured party, text information, image information, satellite image information, drone image information, video information, and audio information, and

the external, third-party data elements are associated with at least one of social media content and online, user-submitted review content.