Patent Application Titled “System To Predict Future Performance Characteristic For An Electronic Record” Published Online (USPTO 20190332623)

2019 NOV 18 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventors Galia, Kathleen H. (South Seaville, NJ); Gamble, David (West Hartford, CT); Li, Bixia (South Windsor, CT); McLaughlin, Kelly J. (Cobalt, CT); Steger, Tracey Ellen (Glastonbury, CT), filed on July 11, 2019, was made available online on October 31, 2019.

The assignee for this patent application is Hartford Fire Insurance Company (Hartford, Connecticut, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “An entity, such as enterprise, may want to analyze or ‘mine’ large amounts of data, such as text data. For example, an enterprise might want to analyze tens of thousands of text files to look for patterns (e.g., so that predictions can be made and/or resources may be allocated in appropriate ways). Note that an entity might analyze this data in connection with different purposes, and, moreover, different purposes may need to analyze the data in different ways. For example, a single acronym might refer to one thing when it appears in one type of document and different thing when it appears in a different type of document. It can be difficult to identify patterns across such large amounts of data and different purposes. In addition, manually managing the different needs and requirements (e.g., different logic rules) associated with different purposes can be a time consuming and error prone process.

“Note that electronic records may be used to store information for an enterprise. Moreover, it may be advantageous for an enterprise to correctly predict future values that might be associated with each electronic record (e.g., so that decisions can be made as appropriate). The future value of some types of information may be predictable with a high degree of certainty. For other types of information, however, the confidence an enterprise can have in predicting the future value (or values) may be much lower. The propensity for a value to differ from its predicted value is referred to herein as ‘volatility.’ In some cases, text based characteristics and/or patterns associated with an electronic might be indicative of volatility.

“Identification and proper handling of electronic records with high volatility potential may allow for improved alignment of resources. Thus, there is a need in the art for methods and systems using text mining to identify highly volatile data values. In addition, there is a need in the art for methods and systems of addressing these values.”

In addition to obtaining background information on this patent application, NewsRx editors also obtained the inventors’ summary information for this patent application: “According to some embodiments, systems, methods, apparatus, computer program code and means are provided for using text mining to identify highly volatile data values. In some embodiments, text input data for an electronic record may be aggregated and mapped to create composite text input data. A semantic event in the composite text input data may be automatically detected, and a text mining result database may be updated by adding an entry identifying the detected semantic event and a triggering semantic rule. An indication of the electronic record may then be transmitted to a back-end application computer server that also determines at least one parameter corresponding to a characteristic of the electronic record. The computer server may then execute a computerized predictive model to predict a future performance characteristic indicator for the electronic record based on the at least one parameter and the indication received from the text mining platform, wherein the future performance characteristic indicator is indicative of a likelihood of an actual value of the electronic record differing from a predicted value of the electronic record.

“Some embodiments provide: means for aggregating and mapping received text input data to create composite text input data for the electronic record; means for automatically detecting a semantic event in the composite text input data triggered by a semantic rule and associated semantic tag; means for flagging the detected semantic event as meeting a pre-determined condition; means for updating a text mining result database, responsive to the flag, by adding an entry to the database identifying the detected semantic event and the triggering semantic rule; means for transmitting an indication of the electronic record based on the associated data in the text mining result database; means for determining at least one parameter corresponding to a characteristic of the electronic record; means for executing a computerized predictive model to predict a future performance characteristic indicator for the electronic record based on the at least one parameter and the indictor received from the text mining platform, wherein the future performance characteristic indicator is indicative of a likelihood of an actual value of the electronic record differing from a predicted value of the electronic record; and means for outputting an indication of the predicted future performance characteristic indictor for the electronic record.

“A technical effect of some embodiments of the invention is an improved and computerized way of using text mining to identify highly volatile data values. 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 system for predicting a future performance characteristic associated with an electronic record, comprising: a text mining platform, including: a text mining communication device to receive text input data associated with the electronic record from multiple sources; a text mining processor coupled to the text mining communication device; and a text mining storage device in communication with said text mining processor and storing instructions adapted to be executed by said text mining processor to: (i) aggregate and map the received text input data to create composite text input data, (ii) automatically detect a semantic event in the composite text input data triggered by a semantic rule and associated semantic tag, (iii) update a text mining result database, responsive to said detection, by adding an entry to the database identifying the detected semantic event, and (iv) transmit an indication of the electronic record; and a back-end application computer server coupled to the text mining platform, including: a back-end communication device to receive the indication of the electronic record transmitted by the text mining platform; a back-end processor coupled to the back-end communication device; and a back-end storage device in communication with said back-end processor and storing instructions adapted to be executed by said back-end processor to: (i) determine at least one parameter corresponding to a characteristic of the electronic record, (ii) execute a computerized predictive model to predict a future performance characteristic indicator for the electronic record based on the at least one parameter, wherein the future performance characteristic indicator is indicative of a likelihood of an actual value of the electronic record differing from a predicted value of the electronic record, wherein the computerized predictive model is generated based at least in part on an analysis of medical spending costs for a plurality of insurance claims and the volatility indictor is used to provide a degree of certainty in connection with at least one of: (i) a loss ratio prediction, and (ii) a return on equity prediction, and (iii) output an indication of the predicted future performance characteristic indictor for the electronic record, wherein the predicted future performance characteristic is a volatility indictor, the electronic record is associated with an insurance claim, and the volatility indicator is indicative of a likelihood of an actual total resolution cost of the insurance claim differing from a predicted total resolution cost of the insurance claim.

“2. The system of claim 1, wherein the semantic event is associated with at least one of: (i) a word, (ii) a phrase, (iii) a shorthand term, (iv) a course of action, and (v) an enterprise name.

“3. The system of claim 1, wherein the triggering semantic rule was defined by an administrator using a graphical user interface and is associated with at least one of: (i) a noun, (ii) a verb, (iii) a definition, (iv) a semantic tree, (v) a named entity recognition rule, (vi) a root, (vii) a noun phrase, (viii) a prepositional phrase, and (ix) a verb phrase.

“4. The system of claim 1, wherein the volatility indicator is to adjust a collective loss reserve for a group of insurance claims.

“5. The system of claim 1, wherein the computerized predictive model is configured to update itself after at least one new insurance claim cost has been determined and the back-end application computer server is to recommend a course of treatment for a claimant of the insurance claim based on the volatility indicator.

“6. The system of claim 1, wherein a set of volatility indicators are filtered in accordance with at least one of: (i) geographic region, (ii) an insurance agency, (iii) underwriting decisions, (iv) an account, (v) claim capping, (vi) industry, (vii) differences in volatility in different segments of a book of insurance, (viii) a state, (ix) a market segment, (x) combinations of filters, (xi) a process to find profitable segments, and (xii) a process to find unprofitable segments.

“7. The system of claim 1, wherein the volatility indictor automatically triggers an outlier warning electronic message and the volatility indicator is used by at least one of: (i) an insurance policy renewal process, and (ii) an insurance policy appetite application.

“8. The system of claim 1, wherein the text input data is associated with at least one of: (i) an insurance claim file, (ii) an insurance claim note, (iii) a medical report, (iv) a police report, (v) social network data, (vi) big data information, (vii) a loss description, (viii) an injury description, (ix) a first notice of loss statement, (x) telephone call transcript, (xi) optical character recognition data, (xii) third-party data, and (xiii) a governmental agency.

“9. The system of claim 1, wherein the predicted future performance characteristic indicator is to be utilized by at least one of: (i) a workers’ compensation claim, (ii) a personal insurance policy, (iii) a business insurance policy, (iv) an automobile insurance policy, (v) a home insurance policy, (vi) a sentiment analysis, (vii) insurance event detection, (viii) a cluster analysis, (ix) a predictive model, (x) a subrogation analysis, (xi) fraud detection, (xii) a recovery factor analysis, (xiii) large loss and volatile claim detection, (xiv) a premium evasion analysis, (xv) an insurance policy comparison, (xvi) an underwriting decision, and (xvii) indicator incidence rate trending.

“10. The system of claim 1, wherein information about claims having predicted future performance characteristic indictor meeting a pre-determined threshold is pushed to an insurance platform, on at least a daily basis.

“11. The system of claim 10, wherein the text input data is associated with a claims database text and at least one of: (i) third-party data, and (ii) medical invoice information.

“12. The system of claim 1, wherein the future performance characteristic indictor is used to categorize claims into high, medium, and low tranches.

“13. The system of claim 12, wherein the tranches are determined based on least one of: (i) loss time costs, (ii) medical only costs, and (iii) total costs.

“14. The system of claim 1, wherein the future performance characteristic indictor is used to identify a substantially fast moving claim based at least in part on a prior predicted indictor for that claim.

“15. A computer-implemented method for predicting a future performance characteristic associated with an electronic record, comprising: aggregating and mapping, by a text mining platform processor, received text input data to create composite text input data for the electronic record; automatically detecting, by the text mining platform processor, a semantic event in the composite text input data triggered by a semantic rule and associated semantic tag; updating, by the text mining platform processor, a text mining result database, responsive to said detecting, by adding an entry to the database identifying the detected semantic event; transmitting, by the text mining platform processor, an indication of the electronic record based on the associated data in the text mining result database; determining, by a back-end application computer processor, at least one parameter corresponding to a characteristic of the electronic record; executing, by the back-end application computer processor, a computerized predictive model to predict a future performance characteristic indicator for the electronic record based on the at least one parameter and the indictor received from the text mining platform, wherein the future performance characteristic indicator is indicative of a likelihood of an actual value of the electronic record differing from a predicted value of the electronic record, wherein the computerized predictive model is generated based at least in part on an analysis of medical spending costs for a plurality of insurance claims and the volatility indictor is used to provide a degree of certainty in connection with at least one of: (i) a loss ratio prediction, and (ii) a return on equity prediction; and outputting, by the back-end application computer processor, an indication of the predicted future performance characteristic indictor for the electronic record, wherein the predicted future performance characteristic is a volatility indictor, the electronic record is associated with an insurance claim, and the volatility indicator is indicative of a likelihood of an actual total resolution cost of the insurance claim differing from a predicted total resolution cost of the insurance claim.

“16. The method of claim 15, wherein the semantic event is associated with at least one of: (i) a word, (ii) a phrase, (iii) a shorthand term, (iv) a course of action, and (v) an enterprise name.

“17. The method of claim 15, wherein the triggering semantic rule was defined by an administrator using a graphical user interface and is associated with at least one of: (i) a noun, (ii) a verb, (iii) a definition, (iv) a semantic tree, (v) a named entity recognition rule, (vi) a root, (vii) a noun phrase, (viii) a prepositional phrase, and (ix) a verb phrase.

“18. The method of claim 15, wherein the volatility indicator is to adjust a collective loss reserve for a group of insurance claims.

“19. The method of claim 15, wherein the computerized predictive model is configured to update itself after at least one new insurance claim cost has been determined and the back-end application computer server is to recommend a course of treatment for a claimant of the insurance claim based on the volatility indicator.

“20. The method of claim 15, wherein a set of volatility indicators are filtered in accordance with at least one of: (i) geographic region, (ii) an insurance agency, (iii) underwriting decisions, (iv) an account, (v) claim capping, (vi) industry, (vii) differences in volatility in different segments of a book of insurance, (viii) a state, (ix) a market segment, (x) combinations of filters, (xi) a process to find profitable segments, and (xii) a process to find unprofitable segments.

“21. The method of claim 15, wherein the volatility indictor automatically triggers an outlier warning electronic message and the volatility indicator is used by at least one of: (i) an insurance policy renewal process, and (ii) an insurance policy appetite application.

“22. The method of claim 15, wherein the text input data is associated with at least one of: (i) an insurance claim file, (ii) an insurance claim note, (iii) a medical report, (iv) a police report, (v) social network data, (vi) big data information, (vii) a loss description, (viii) an injury description, (ix) a first notice of loss statement, (x) telephone call transcript, (xi) optical character recognition data, (xii) third-party data, and (xiii) a governmental agency.

“23. A non-transitory computer-readable medium storing instructions adapted to be executed by a computer processor to perform a method to predict a future performance characteristic for an electronic record, said method comprising: aggregating and mapping received text input data to create composite text input data for the electronic record; automatically detecting a semantic event in the composite text input data triggered by a semantic rule and associated semantic tag; updating a text mining result database, responsive to said detection, by adding an entry to the database identifying the detected semantic event; transmitting an indication of the electronic record based on the associated data in the text mining result database; determining at least one parameter corresponding to a characteristic of the electronic record; executing a computerized predictive model to predict a future performance characteristic indicator for the electronic record based on the at least one parameter and the indictor received from the text mining platform, wherein the future performance characteristic indicator is indicative of a likelihood of an actual value of the electronic record differing from a predicted value of the electronic record, wherein the computerized predictive model is generated based at least in part on an analysis of medical spending costs for a plurality of insurance claims and the volatility indictor is used to provide a degree of certainty in connection with at least one of: (i) a loss ratio prediction, and (ii) a return on equity prediction; and outputting an indication of the predicted future performance characteristic indictor for the electronic record, wherein the predicted future performance characteristic is a volatility indictor, the electronic record is associated with an insurance claim, and the volatility indicator is indicative of a likelihood of an actual total resolution cost of the insurance claim differing from a predicted total resolution cost of the insurance claim.

“24. The medium of claim 23, wherein the predicted future performance characteristic indicator is to be utilized by at least one of: (i) a workers’ compensation claim, (ii) a personal insurance policy, (iii) a business insurance policy, (iv) an automobile insurance policy, (v) a home insurance policy, (vi) a sentiment analysis, (vii) insurance event detection, (viii) a cluster analysis, (ix) a predictive model, (x) a subrogation analysis, (xi) fraud detection, (xii) a recovery factor analysis, (xiii) large loss and volatile claim detection, (xiv) a premium evasion analysis, (xv) an insurance policy comparison, (xvi) an underwriting decision, and (xvii) indicator incidence rate trending.

“25. The medium of claim 23, wherein information about claims having predicted future performance characteristic indictor meeting a pre-determined threshold is pushed to an insurance platform, on at least a daily basis.

“26. The medium of claim 25, wherein the text input data is associated with a claims database text and at least one of: (i) third-party data, and (ii) medical invoice information.

“27. The medium of claim 23, wherein the future performance characteristic indictor is used to categorize claims into high, medium, and low tranches.

“28. The medium of claim 27, wherein the tranches are determined based on least one of: (i) loss time costs, (ii) medical only costs, and (iii) total costs.

“29. The medium of claim 23, wherein the future performance characteristic indictor is used to identify a substantially fast moving claim based at least in part on a prior predicted indictor for that claim.”

For more information, see this patent application: Galia, Kathleen H.; Gamble, David; Li, Bixia; McLaughlin, Kelly J.; Steger, Tracey Ellen. System To Predict Future Performance Characteristic For An Electronic Record. Filed July 11, 2019 and posted October 31, 2019. Patent URL: http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PG01&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.html&r=1&f=G&l=50&s1=%2220190332623%22.PGNR.&OS=DN/20190332623&RS=DN/20190332623

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