# US 2021/0176276 A1 · Machine learning-based event analysis for customized contract generation and negotiation in enhanced security peer-to-peer interaction applications

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0176276 A1
- Document ID: US20210176276A1
- Status: Published application
- Kind: A1
- Application number: 16/706,547
- Filed: 2019-12-06
- Published: 2021-06-10
- Earliest claimed: 2019-12-06
- Assignees: Bank of America Corporation
- Applicants: Bank of America Corporation
- Inventors: Eren Kursun
- Web page: https://patentgrep.com/patent/US20210176276A1

## CPC

- H04L 63/166: {at the transport layer}
- G06F 40/253: Grammatical analysis; Style critique
- G06F 40/30: Semantic analysis
- G06N 20/00: Machine learning
- G06Q 10/06: Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q 50/18: Legal services
- H04L 63/04: {for providing a confidential data exchange among entities communicating through data packet networks}
- H04L 67/1078: {Resource delivery mechanisms}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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

## Abstract

A system for machine learning-derived contract generation is provided. The system comprises: a machine learning engine and a controller configured to: input historical and streaming interaction data into the machine learning engine, wherein the machine learning engine is trained by the historical and streaming interaction data; determine one or more machine learning-derived interaction patterns for a resource transfer between the first user device and the second user device, wherein the one or more machine learning-derived interaction patterns comprise calculated exposure levels for one or more events for completing the resource transfer; based on the machine learning-derived interaction patterns, generate the resource transfer contract for transferring a resource from the first user device to the second user device, wherein the resource transfer contract comprises a sequential flow of the one or more events; and distribute the resource transfer contract to the first user device and the second user device.

## Claims

### Claim 1

A system for machine learning-derived contract generation, the system comprising:
a machine learning engine; and
a controller configured for generating a resource transfer contract between a first user device and a second user device, the controller comprising a memory device with computer-readable program code stored thereon, a communication device connected to a network, and a processing device, wherein the processing device is configured to execute the computer-readable program code to:
input historical and streaming interaction data into the machine learning engine, wherein the machine learning engine is trained by the historical and streaming interaction data;
determine one or more machine learning-derived interaction patterns for a resource transfer between the first user device and the second user device, wherein the one or more machine learning-derived interaction patterns comprise calculated exposure levels for one or more events for completing the resource transfer;
based on the one or more machine learning-derived interaction patterns, generate the resource transfer contract for transferring a resource from the first user device to the second user device, wherein the resource transfer contract comprises a sequential flow of the one or more events; and
distribute the resource transfer contract to the first user device and the second user device.

### Claim 2 (depends on 1)

The system of claim 1, wherein the processing device is further configured to execute the computer-readable program code to:
calculate an exposure level for each of the one or more events of the resource transfer contract based on the one or more machine learning-derived interaction patterns;
identify that the exposure level for at least one of the one or more events exceeds a predetermined threshold; and
based on the exposure level exceeding the predetermined threshold, modify the sequential flow of the one or more events, wherein modifying the sequential flow of the one or more events comprises inserting an additional security event to the sequential flow.

### Claim 3 (depends on 1)

The system of claim 1, wherein the processing device is further configured to execute the computer-readable program code to:
receive a modification to the sequential flow of the one or more events from at least one of the first user device and the second user device;
generate a modified resource transfer contract based on the modification; and
calculate a modified exposure level for the modified resource transfer contract, wherein the one or more events and the modification are input into the machine learning engine.

### Claim 4 (depends on 3)

The system of claim 3, wherein the processing device is further configured to execute the computer-readable program code to iteratively modify the sequential flow of the one or more events until the modified exposure level is below a predetermined threshold limit.

### Claim 5 (depends on 3)

The system of claim 3, wherein the processing device is further configured to execute the computer-readable program code to terminate the resource transfer contract when the modified exposure level exceeds a predetermined threshold limit.

### Claim 6 (depends on 1)

The system of claim 1, wherein the historical and streaming interaction data comprises one or more of the group consisting of resource data, a resource transfer type, user data of a first user associated with the first user device and a second user associated with the second user device, historical resource transfer data, and historical misappropriation data.

### Claim 7 (depends on 6)

The system of claim 6, wherein the historical misappropriation data further comprises previously identified misappropriation interactions and unauthorized user logs.

### Claim 8 (depends on 1)

The system of claim 1, wherein the machine learning engine further comprises a natural language processing module configured to determine the one or more machine learning-derived interaction patterns for the resource transfer based on the historical and streaming interaction data.

### Claim 9 (depends on 1)

The system of claim 1, wherein the resource transfer contract is an executable tracking module, and wherein the processing device is configured to execute the computer-readable program code to install the executable tracking module on the first user device and the second user device, and wherein the executable tracking module is configured to track completion of the one or more events.

### Claim 10

A system for natural language processing-enhanced resource transfer contract security, the system comprising:
a machine learning engine comprising a natural language processing module; and
a controller configured for securely customizing a resource transfer contract between a first user device and a second user device, the controller comprising a memory device with computer-readable program code stored thereon, a communication device connected to a network, and a processing device, wherein the processing device is configured to execute the computer-readable program code to:
input misappropriation interaction data into the natural language processing module, wherein the natural language processing module is trained by the misappropriation interaction data;
extract one or more keyword identifiers from the misappropriation interaction data, wherein the one or more keyword identifiers are associated with misappropriation interactions;
based on the one or more keyword identifiers, calculate an exposure level for the resource transfer contract;
compare the exposure level of the resource transfer contract to a predetermined exposure threshold level; and
based on the exposure level of the resource transfer contract not exceeding the predetermined exposure threshold level, distribute the resource transfer contract to the first user device and the second user device.

### Claim 11 (depends on 10)

The system of claim 10, wherein the resource transfer contract comprises a sequential flow of one or more events, and wherein the processing device is further configured to execute the computer-readable program code to:
calculate an individual exposure level for each of the one or more events of the resource transfer contract based on one or more machine-learning derived interaction patterns;
identify that the individual exposure level for at least one of the one or more events exceeds the predetermined exposure threshold level; and
based on the individual exposure level exceeding the predetermined exposure threshold level, modify the sequential flow of the one or more events, wherein modifying the sequential flow of the one or more events comprises inserting an additional security event to the sequential flow.

### Claim 12 (depends on 11)

The system of claim 11, wherein the processing device is further configured to execute the computer-readable program code to iteratively modify the sequential flow of the one or more events until the exposure level for the resource transfer contract is below the predetermined exposure threshold level.

### Claim 13 (depends on 10)

The system of claim 10, wherein the one or more keyword identifiers comprise at least one of vocabulary, syntax, semantics, grammar, and word frequency patterns.

### Claim 14 (depends on 10)

The system of claim 10, wherein the misappropriation interaction data comprises historical and streaming data.

### Claim 15

A computer-implemented method for or machine learning-derived contract generation, the computer-implemented method comprising:
inputting historical and streaming interaction data into a machine learning engine, wherein the machine learning engine is trained by the historical and streaming interaction data;
determining one or more machine learning-derived interaction patterns for a resource transfer between a first user device and a second user device, wherein the one or more machine learning-derived interaction patterns comprise calculated exposure levels for one or more events for completing the resource transfer;
based on the one or more machine learning-derived interaction patterns, generating a resource transfer contract for transferring a resource from the first user device to the second user device, wherein the resource transfer contract comprises a sequential flow of the one or more events; and
distributing the resource transfer contract to the first user device and the second user device.

### Claim 16 (depends on 15)

The computer-implemented method of claim 15 further comprising:
calculating an exposure level for each of the one or more events of the resource transfer contract based on the one or more machine learning-derived interaction patterns;
identifying that the exposure level for at least one of the one or more events exceeds a predetermined threshold; and
based on the exposure level exceeding the predetermined threshold, modifying the sequential flow of the one or more events, wherein modifying the sequential flow of the one or more events comprises inserting an additional security event to the sequential flow.

### Claim 17 (depends on 15)

The computer-implemented method of claim 15 further comprising:
receiving a modification to the sequential flow of the one or more events from at least one of the first user device and the second user device;
generating a modified resource transfer contract based on the modification; and
calculating a modified exposure level for the modified resource transfer contract, wherein the one or more events and the modification are input into the machine learning engine.

### Claim 18 (depends on 17)

The computer-implemented method of claim 17 further comprising iteratively modifying the sequential flow of the one or more events until the modified exposure level is below a predetermined threshold limit.

### Claim 19 (depends on 17)

The computer-implemented method of claim 17 further comprising terminating the resource transfer contract when the modified exposure level exceeds a predetermined threshold limit.

### Claim 20 (depends on 15)

The computer-implemented method of claim 15, wherein the historical and streaming interaction data comprises one or more of the group consisting of resource data, a resource transfer type, user data of a first user associated with the first user device and a second user associated with the second user device, historical resource transfer data, and historical misappropriation data.
