# US 11,443,384 B2 · Intelligent policy covery gap discovery and policy coverage optimization > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,384 B2 - Document ID: US11443384B2 - Status: Granted - Kind: B2 - Application number: 16/840,802 - Filed: 2020-04-06 - Published: 2021-10-07 - Granted: 2022-09-13 - Earliest claimed: 2020-04-06 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Theodora Brisimi; Vanessa Lopez Garcia; Valentina Rho; John Segrave-Daly - Web page: https://patentgrep.com/patent/US11443384B2 ## CPC - G06Q 40/08: Insurance - G06N 5/025: Extracting rules from data - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - G06Q 10/0637: Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals - G06Q 10/10: Office automation; Time management - G06Q 30/018: Certifying business or products - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Various embodiments are provided for providing intelligent policy coverage optimization in a computing environment by a processor. One or more policy coverage gaps in one or more operational rules defined by one or more rules, policies, or a combination thereof and associated with one or more non-compliant policy claims associated with the one or more policy coverage gaps may be identified. The one or more policy coverage gaps may be ranked according to one or more selected criteria. ## Claims ### Claim 1 A method for providing intelligent policy coverage optimization in a computing environment by a processor comprising: executing machine learning logic to generate a policy model using eligibility standards of an insurance policy as input data, wherein the eligibility criteria is modeled as one or more operational rules within the policy model; identifying, using the policy model, one or more policy coverage gaps in the one or more operational rules defined by one or more rules, policies, or a combination thereof and corresponding to one or more non-compliant policy claims associated with the one or more policy coverage gaps, wherein the one or more policy coverage gaps are deficiencies in the one or more operational rules that preclude enforcement of collection with respect to the one or more non-compliant policy claims previously remunerated to a claimant; ranking the one or more policy coverage gaps according to one or more selected criteria; displaying the ranked one or more policy coverage gaps on a user interface (UI): and receiving feedback data associated with an accuracy of the ranked one or more policy coverage gaps, wherein the feedback data is used to iteratively update the policy model to enhance the accuracy in identifying future policy coverage gaps over time. ### Claim 2 (depends on 1) The method of claim 1, further including clustering the one or more policy coverage gaps based on one or more of a plurality of factors. ### Claim 3 (depends on 1) The method of claim 1, further including determining one or more non-compliant operational rules from the one or more operational rules to identify the one or more policy coverage gaps. ### Claim 4 (depends on 1) The method of claim 1, further including: generating one or more additional operational rules for eliminating the one or more policy coverage gaps; identifying a possible validity or invalidity of the one or more operational rules or the one or more additional operational rules; or modifying the one or more operational rules or the one or more additional operational rules for eliminating the one or more policy coverage gaps. ### Claim 5 (depends on 1) The method of claim 1, further including executing the machine learning logic to use the policy model to learn those of the one or more operational rules that eliminate the one or more policy coverage gaps from historical data, user feedback, one or more compliant operational rules, or a combination thereof. ### Claim 6 (depends on 1) The method of claim 1, further including: learning, determining, or identifying one or more non-compliant operational rules having the one or more policy coverage gaps; and revising the one or more operational rules according to the feedback data received from the user. ### Claim 7 (depends on 1) The method of claim 1 further including: determining those of the one or more operational rules having the one or more policy coverage gaps; grouping the operational rules into one of a plurality of sub-groups, wherein each of the plurality of sub-groups represent a specific coverage area gap; creating one or more additional operational rules that address the one or more policy coverage gaps in each of the plurality of sub-groups; ranking the one or more additional operational rules; or extracting semantic data from a data source associated with the one or more operational rules, the one or more non-compliant policy claims, or one or more compliant policy claims. ### Claim 8 A system for providing intelligent policy coverage optimization in a computing environment, comprising: one or more processors with executable instructions that when executed cause the system to: execute machine learning logic to generate a policy model using eligibility standards of an insurance policy as input data, wherein the eligibility criteria is modeled as one or more operational rules within the policy model; identify, using the policy model, one or more policy coverage gaps in the one or more operational rules defined by one or more rules, policies, or a combination thereof and corresponding to one or more non-compliant policy claims associated with the one or more policy coverage gaps, wherein the one or more policy coverage gaps are deficiencies in the one or more operational rules that preclude enforcement of collection with respect to the one or more non-compliant policy claims previously remunerated to a claimant; rank the one or more policy coverage gaps according to one or more selected criteria, display the ranked one or more policy coverage gaps on a user interface (UI); and receive feedback data associated with an accuracy of the ranked one or more policy coverage gaps, wherein the feedback data is used to iteratively update the policy model to enhance the accuracy in identifying future policy coverage gaps over time. ### Claim 9 (depends on 8) The system of claim 8, wherein the executable instructions further cluster the one or more policy coverage gaps based on one or more of a plurality of factors. ### Claim 10 (depends on 8) The system of claim 8, wherein the executable instructions further determine one or more non-compliant operational rules from the one or more operational rules to identify the one or more policy coverage gaps. ### Claim 11 (depends on 8) The system of claim 8, wherein the executable instructions further: generate one or more additional operational rules for eliminating the one or more policy coverage gaps; identify a possible validity or invalidity of the one or more operational rules or the one or more additional operational rules; or modify the one or more operational rules or the one or more additional operational rules for eliminating the one or more policy coverage gaps. ### Claim 12 (depends on 8) The system of claim 8, wherein the executable instructions further execute the machine learning logic to use the policy model to learn those of the one or more operational rules that eliminate the one or more policy coverage gaps from historical data, user feedback, one or more compliant operational rules, or a combination thereof. ### Claim 13 (depends on 8) The system of claim 8, wherein the executable instructions further: learn, determine, or identify one or more non-compliant operational rules having the one or more policy coverage gaps; and revise the one or more operational rules according to the feedback data received from the user. ### Claim 14 (depends on 8) The system of claim 8, wherein the executable instructions further: determine those of the one or more operational rules having the one or more policy coverage gaps; group the operational rules into one of a plurality of sub-groups, wherein each of the plurality of sub-groups represent an specific coverage area gap; create one or more additional operational rules that address the one or more policy coverage gaps in each of the plurality of sub-groups; rank the one or more additional operational rules; or extract semantic data from a data source associated with the one or more operational rules, the one or more non-compliant policy claims, or one or more compliant policy claims. ### Claim 15 A computer program product for, by one or more processors, providing intelligent policy coverage optimization in a computing environment, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising: an executable portion that executes machine learning logic to generate a policy model using eligibility standards of an insurance policy as input data, wherein the eligibility criteria is modeled as one or more operational rules within the policy model; an executable portion that identifies, using the policy model, one or more policy coverage gaps in the one or more operational rules defined by one or more rules, policies, or a combination thereof and corresponding to one or more non-compliant policy claims associated with the one or more policy coverage gaps, wherein the one or more policy coverage gaps are deficiencies in the one or more operational rules that preclude enforcement of collection with respect to the one or more non-compliant policy claims previously remunerated to a claimant; an executable portion that ranks the one or more policy coverage gaps according to one or more selected criteria; an executable portion that displays the ranked one or more policy coverage gaps on a user interface (UI); and an executable portion that receives feedback data associated with an accuracy of the ranked one or more policy coverage gaps, wherein the feedback data is used to iteratively update the policy model to enhance the accuracy in identifying future policy coverage gaps over time. ### Claim 16 (depends on 15) The computer program product of claim 15, further including an executable portion that: clusters the one or more policy coverage gaps based on one or more of a plurality of factors; or determines one or more non-compliant operational rules from the one or more operational rules. ### Claim 17 (depends on 15) The computer program product of claim 15, further including an executable portion that: generates one or more additional operational rules for eliminating the one or more policy coverage gaps; identifies a possible validity or invalidity of the one or more operational rules or the one or more additional operational rules; or modifies the one or more operational rules or the one or more additional operational rules for eliminating the one or more policy coverage gaps. ### Claim 18 (depends on 15) The computer program product of claim 15, further including an executable portion that executes the machine learning logic to use the policy model to learn those of the one or more operational rules that eliminate the one or more policy coverage gaps from historical data, user feedback, one or more compliant operational rules, or a combination thereof. ### Claim 19 (depends on 15) The computer program product of claim 15, further including an executable portion that: learns, determines, or identifies one or more non-compliant operational rules having the one or more policy coverage gaps; and revises the one or more operational rules according to the feedback data received from the user. ### Claim 20 (depends on 15) The computer program product of claim 15, further including an executable portion that: determines those of the one or more operational rules having the one or more policy coverage gaps; groups the operational rules into one of a plurality of sub-groups, wherein each of the plurality of sub-groups represent an specific coverage area gap; creates one or more additional operational rules that address the one or more policy coverage gaps in each of the plurality of sub-groups; ranks the one or more additional operational rules; or extracts semantic data from a data source associated with the one or more operational rules, the one or more non-compliant policy claims, or one or more compliant policy claims.