Back to results
US 10,853,875 B2Granted
Actionable exception alerts
AssigneeBank of America Corporation
InventorsShiva-Sanjay Bhakta, Jeffrey R. Goertz, Kerry Michelle Cantley, Eric Dryer, James W. Stark, III, Mike Stoll, Tim Gauvin, Geoffrey R. Williams, Krishna Kota
Life of this patent
Estimating the term…
Abstract
Systems, method, apparatuses, and software are described for automatically detecting defects in financial transactions, automatically determining resolutions to the defects based on historical defect patterns, an interacting with customers to provide information and/or receive instructions regarding defects and how they should be resolved.
Claims20
A method directed to an improved automated teller machine equipped with a defect detection system that results in a technological improvement over operation of existing automated teller machines, comprising:
- receiving, at an automated teller machine (ATM) comprising the defect detection system, a paper check and a deposit slip, wherein the paper check comprises a first currency amount and a payee name, and the deposit slip comprises a second currency amount and an account number;
- identifying, by the ATM, that the first currency amount matches the second currency amount by optically detecting on the paper check a first text corresponding to the first currency amount and optically detecting on the deposit slip a second text corresponding to the second currency amount;
- optically detecting, by the ATM, the account number on the deposit slip;
- optically detecting, by the ATM, the payee name on the paper check;
- identifying, by the defect detection system in the ATM, that the account number on the deposit slip contains a typographical error by:
- retrieving, by the defect detection system, historical transaction information corresponding to one or more financial transactions from a non-transitory data storage device communicatively coupled to the defect detection system;
- searching, by the defect detection system in the ATM, the payee name in the non-transitory data storage device;
- analyzing, by the defect detection system, the retrieved historical transaction information to identify one or more defect patterns using predictive analytics, wherein the predictive analytics comprises one of a supervised learning technique or an unsupervised learning technique;
- and
- detecting, by the defect detection system, a defect in a financial transaction based on a comparison of the financial transaction to the one or more defect patterns determined from the retrieved historical transaction information;
- transmitting, by the defect detection system, an user interactive message including information corresponding to the detected defect to a defect resolution system in the ATM;
- determining, by the defect resolution system in the ATM, a resolution to the identified defect based on a type associated with the defect;
- and
- resolving in real-time the typographical error, by the defect resolution system in the ATM, by changing the optically detected account number to a corrected account number.
11 more elements
A non-transitory computer-readable medium storing computer-executable instructions, that when executed by a processor, cause the processor to:
- receive a paper check and a deposit slip, wherein the paper check comprises a first currency amount and a payee name, and the deposit slip comprises a second currency amount and an account number;
- identify that the first currency amount matches the second currency amount by optically detecting on the paper check a first text corresponding to the first currency amount and optically detecting on the deposit slip a second text corresponding to the second currency amount;
- optically detect the account number on the deposit slip;
- optically detect the payee name on the paper check;
- identify, by a defect detection system, that the account number on the deposit slip contains a typographical error by:
- retrieving, by the defect detection system, historical transaction information corresponding to one or more financial transactions from a non-transitory data storage device communicatively coupled to the defect detection system;
- searching, by the defect detection system, the payee name in the non-transitory data storage device;
- analyzing, by the defect detection system, the retrieved historical transaction information to identify one or more defect patterns using machine learning, wherein the machine learning comprises one of a supervised learning technique or an unsupervised learning technique;
- and
- detecting, by the defect detection system, a defect in a financial transaction based on a comparison of the financial transaction to the one or more defect patterns determined from the retrieved historical transaction information;
- transmit, by the defect detection system, an user interactive message including information corresponding to the detected defect to a defect resolution system;
- determine, by the defect resolution system, a resolution to the identified defect based on a type associated with the defect;
- and
- resolve the typographical error, by the defect resolution system, by changing the optically detected account number to a corrected account number.
11 more elements
An apparatus comprising a processor and a non-transitory computer-readable medium storing computer-executable instructions, that when executed by the processor, cause the apparatus to:
- receive a first paper and a second paper, wherein the first paper comprises a first currency amount and a name, and the second paper comprises a second currency amount and an account number;
- identify that the first currency amount matches the second currency amount by optically detecting on the first paper a first text corresponding to the first currency amount and optically detecting on the second paper a second text corresponding to the second currency amount;
- optically detect the account number on the second paper;
- optically detect the name on the first paper;
- identify, by a defect detection system, that the account number on the second paper contains a typographical error by:
- retrieving, by the defect detection system, historical transaction information corresponding to one or more financial transactions from a non-transitory data storage device communicatively coupled to the defect detection system;
- searching, by the defect detection system, the name in the non-transitory data storage device;
- analyzing, by the defect detection system, the retrieved historical transaction information to identify one or more defect patterns using predictive analytics, wherein the predictive analytics comprises one of a supervised learning technique or an unsupervised learning technique;
- and
- detecting, by the defect detection system, a defect in a financial transaction based on a comparison of the financial transaction to the one or more defect patterns determined from the retrieved historical transaction information;
- transmit, by the defect detection system, an user interactive message including information corresponding to the detected defect to a defect resolution system;
- determine, by the defect resolution system, a resolution to the identified defect based on a type associated with the defect;
- and
- resolve the typographical error, by the defect resolution system, by changing the optically detected account number to a corrected account number.
11 more elements
Dependencies are inferred from the claim text.