Context-based policy term assistance

Patent metadata

Field	Value
Publication number	US-10915834-B2
Application number	US-201715617448-A
Country	US
Kind code	B2
Filing date	Jun 8, 2017
Priority date	Jun 8, 2017
Publication date	Feb 9, 2021
Grant date	Feb 9, 2021

Abstract

In an approach to parsing and analyzing contracts, one or more computer processors receive a policy agreement. The one or more computer processors parse the policy agreement for terms. The one or more computer processors compile a list of items associated with the terms in the policy agreement. The one or more computer processors associate each item of the list of items with one or more categories, wherein each category of the one or more categories defines an extent of coverage for each item. The one or more computer processors determine whether an item of a user is present in the list of items associated with the one or more terms in the policy agreement. The one or more computer processors determine the categories associated with the item. The one or more computer processors determine the extent of coverage for the item of the user based on the determined categories.

First claim

What is claimed is:

1. A method for parsing and analyzing contracts, the method comprising:
receiving, by one or more computer processors, a policy agreement;
parsing, by the one or more computer processors, the policy agreement for one or more terms;
compiling, by the one or more computer processors, a list of items associated with the one or more terms in the policy agreement;
associating, by the one or more computer processors, each item of the list of items with one or more categories, wherein each category of the one or more categories defines an extent of coverage for each item;
determining, by the one or more computer processors, whether an item of a user is present in the list of items associated with the one or more terms in the policy agreement;
responsive to determining that the item of the user is present in the list of items associated with the one or more parsed terms in the policy agreement, determining, by the one or more computer processors, the one or more categories associated with the item;
determining, by the one or more computer processors, the extent of coverage for the item of the user based on the determined one or more categories;
generating, by the one or more computer processors, one or more first rules associated with the extent of coverage associated with the item, wherein generating the one or more first rules associated with coverage terms for the item is achieved using a machine learning and a predictive analytics;
generating, by the one or more computer processors, one or more second rules associated with the item based on a predicted user behavior, wherein the predicted user behavior is predicted using a time-series forecast and a regression analysis based on a behavior history of the user;
creating, by the one or more computer processors, one or more item-specific responses upon a rule violation of the one or more rules;
monitoring, by the one or more computer processors, one or more data sources associated with the user;
determining, by the one or more computer processors, whether the rule violation has occurred based on the one or more data sources and the one or more first rules and the one or more second rules; and
responsive to determining that the rule violation has occurred, executing, by the one or more computer processors, the one or more item-specific responses.

2. The method of claim 1 , wherein determining whether the rule violation has occurred comprises:
determining, by the one or more computer processors, a geolocation associated with the user;
determining, by the one or more computer processors, whether the geolocation associated with the user falls outside of one or more allowed geolocations in the policy agreement; and
responsive to determining that the geolocation associated with the user falls outside of the one or more allowed geolocations, determining, by the one or more computer processors, that a rule violation has occurred.

3. The method of claim 1 , wherein determining whether the rule violation has occurred further comprises:
determining, by the one or more computer processors, a current time associated with the user;
determining, by the one or more computer processors, whether the current time associated with the user falls outside of one or more allowed times in the policy agreement; and
responsive to determining that the current time associated with the user falls outside of the one or more allowed times, determining, by the one or more computer processors, that the rule violation has occurred.

4. The method of claim 1 , wherein the one or more item-specific responses are selected from a group consisting of: a notification and an authorization hold.

5. The method of claim 1 , further comprising:
sending, by the one or more computer processors, one or more coverage terms associated with the item to the user for review.

6. A computer program product for parsing and analyzing contracts, the computer program product comprising:
one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions to receive a policy agreement;
program instructions to parse the policy agreement for one or more terms;
program instructions to compile a list of items associated with the one or more terms in the policy agreement;
program instructions to associate each item of the list of items with one or more categories, wherein each category of the one or more categories defines an extent of coverage for each item;
program instructions to determine whether an item of a user is present in the list of items associated with the one or more terms in the policy agreement;
responsive to determining that the item of the user is present in the list of items associated with the one or more parsed terms in the policy agreement, program instructions to determine the one or more categories associated with the item;
program instructions to determine the extent of coverage for the item of the user based on the determined one or more categories;
program instructions to generate one or more first rules associated with the extent of coverage associated with the item, wherein generating the one or more first rules associated with coverage terms for the item is achieved using a machine learning and a predictive analytics;
program instructions to generate one or more second rules associated with the item based on a predicted user behavior, wherein the predicted user behavior is predicted using a time-series forecast and a regression analysis based on a behavior history of the user;
program instructions to create one or more item-specific responses upon a rule violation of the one or more rules;
program instructions to monitor one or more data sources associated with the user,
program instructions to determine whether the rule violation has occurred based on the one or more data sources and the one or more first rules and the one or more second rules; and
responsive to determining that the rule violation has occurred, program instructions to execute the one or more item-specific responses.

7. The computer program product of claim 6 , wherein determining whether the rule violation has occurred comprises:
program instructions to determine a geolocation associated with the user;
program instructions to determine whether the geolocation associated with the user falls outside of one or more allowed geolocations in the policy agreement; and
responsive to determining that the geolocation associated with the user falls outside of the one or more allowed geolocations, program instructions to determine that the rule violation has occurred.

8. The computer program product of claim 6 , wherein determining whether the rule violation has occurred further comprises:
program instructions to determine a current time associated with the user;
program instructions to determine whether the current time associated with the user falls outside of one or more allowed times in the policy agreement; and
responsive to determining that the current time associated with the user falls outside of the one or more allowed times, program instructions to determine that a rule violation has occurred.

9. The computer program product of claim 6 , wherein the one or more item-specific responses are selected from a group consisting of: a notification and an authorization hold.

10. The computer program product of claim 6 , further comprising:
program instructions to send one or more coverage terms associated with the item to the user for review.

11. A computer system for parsing and analyzing contracts, the computer system comprising:
o

Assignees

• IBM

Inventors

• Hwang Inseok
• Liu Su
• Rozner Eric J
• Sze Chin Ngai

Classifications

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• H04L67/52

  specially adapted for the location of the user terminal · CPC title

• G06F40/279

  Recognition of textual entities · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06Q40/08

  Insurance · CPC title