# US 2022/0036210 A1 · Machine learning based automated pairing of individual customers and small businesses

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

- Number: US 2022/0036210 A1
- Document ID: US20220036210A1
- Status: Published application
- Kind: A1
- Application number: 16/941,858
- Filed: 2020-07-29
- Published: 2022-02-03
- Earliest claimed: 2020-07-29
- Assignees: Bank of America Corporation
- Applicants: Bank of America Corporation
- Inventors: Siten Sanghvi; Morgan S. Allen; Matthew E. Carroll; Tamara S. Kingston; Stephen T. Shannon
- Web page: https://patentgrep.com/patent/US20220036210A1

## CPC

- G06N 5/04: Inference or reasoning models
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 20/00: Machine learning
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 30/0203: Market surveys; Market polls
- G06Q 30/0631: {Recommending goods or services}
- G06Q 30/08: Auctions
- G06Q 30/016: After-sales
- G06Q 40/03: Credit; Loans; Processing thereof
- 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

Aspects of the disclosure relate to automated pairing of customers and businesses. A computing platform may determine, based on historical user activity of a user, a pattern of the user activity, and may identify, based on the pattern of the user activity, an anticipated purchase activity of the user. Then, the computing platform may determine a sales offering by a vendor. Then, the computing platform may match the anticipated purchase activity with the sales offering. Then, the computing platform may retrieve user-defined preference rules associated with the anticipated purchase activity. Then, the computing platform may determine whether the preference rules apply to one or more attributes of the anticipated purchase activity. Subsequently, the computing platform may trigger, based on a determination that the preference rules apply to the one or more attributes of the anticipated purchase activity, an action associated with the anticipated purchase activity.

## Claims

### Claim 1

A computing platform, comprising:
at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
determine, via a computing device and based on historical user activity of a user, a pattern of the user activity;
identify, based on the pattern of the user activity, one or more anticipated purchase activities of the user;
determine, via the computing device and based on the one or more anticipated purchase activities of the user, a sales offering by a vendor;
match, via the computing device, the one or more anticipated purchase activities of the user with the sales offering by the vendor;
retrieve, from a repository of user data and for a purchase activity of the one or more anticipated purchase activities, one or more user-defined preference rules associated with the purchase activity;
determine whether the one or more preference rules apply to one or more attributes of the purchase activity; and
trigger, via the computing device and based on a determination that the one or more preference rules apply to the one or more attributes of the purchase activity, an action associated with the purchase activity.

### Claim 2 (depends on 1)

The computing platform of claim 1, wherein the action associated with the purchase activity comprises providing, via an intelligent virtual assistant, a recommendation to perform the purchase activity.

### Claim 3 (depends on 1)

The computing platform of claim 1, wherein the action associated with the purchase activity comprises making an automatic purchase.

### Claim 4 (depends on 1)

The computing platform of claim 1, wherein the instructions comprise additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
retrieve, from one or more external sources of data, one or more events that may impact the purchase activity;
identify an event of the one or more events that impacts the purchase activity, and
wherein the action associated with the purchase activity comprises a recommendation that minimizes the impact of the event for the user.

### Claim 5 (depends on 4)

The computing platform of claim 4, wherein the one or more external sources of data are artificial intelligence based systems.

### Claim 6 (depends on 4)

The computing platform of claim 4, wherein the event comprises one or more of a weather related event, an employment related event, a geopolitical event, a civic unrest, and a medical event.

### Claim 7 (depends on 1)

The computing platform of claim 1, wherein the instructions comprise additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to determine the one or more user-defined preference rules by:
establishing, via an intelligent virtual assistant, an interactive session with the user;
providing, to the user, one or more questions in sequential format;
receiving, from the user, responses to the one or more questions;
providing, to the user and based on the responses, one or more additional questions; and
receiving, from the user, responses to the one or more additional questions.

### Claim 8 (depends on 7)

The computing platform of claim 7, wherein the instructions comprise additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
train the intelligent virtual assistant based on a machine learning model.

### Claim 9 (depends on 1)

The computing platform of claim 1, wherein the one or more user-defined preference rules comprise one or more of a preference associated with an automatic loan amount, a secondary funding source, automatic payment options, a designated alternate decision making authority, and preferred communication channels.

### Claim 10 (depends on 1)

The computing platform of claim 1, wherein the instructions comprise additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
train a machine learning model to determine the pattern of the user activity.

### Claim 11 (depends on 1)

The computing platform of claim 1, wherein the instructions comprise additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
train a machine learning model to identify the one or more anticipated purchase activities of the user.

### Claim 12

A method, comprising:
at a computing platform comprising at least one processor, at least one physical sensor communicatively coupled to the at least one processor, and memory:
determining, via a computing device and based on historical user activity of a user, a pattern of the user activity;
identifying, based on the pattern of the user activity, one or more anticipated purchase activities of the user;
determining, via the computing device and based on the one or more anticipated purchase activities of the user, a sales offering by a vendor;
matching, via the computing device, the one or more anticipated purchase activities of the user with the sales offering by the vendor;
retrieving, from a repository of user data and for an anticipated purchase activity of the one or more anticipated purchase activities of the user, one or more user-defined preference rules associated with the anticipated purchase activity;
determining whether the one or more preference rules apply to one or more attributes of the anticipated purchase activity; and
triggering, via the computing device and based on a determination that the one or more preference rules apply to one or more attributes of the anticipated purchase activity, an action associated with the anticipated purchase activity.

### Claim 13 (depends on 12)

The method of claim 12, wherein the action associated with the purchase activity comprises providing, via an intelligent virtual assistant, a recommendation to perform the purchase activity.

### Claim 14 (depends on 12)

The method of claim 12, wherein the action associated with the purchase activity comprises making an automatic purchase.

### Claim 15 (depends on 12)

The method of claim 12, further comprising:
retrieving, from one or more external sources of data, one or more events that may impact the purchase activity;
identifying an event of the one or more events that impacts the purchase activity, and
wherein the action associated with the purchase activity comprises a recommendation that minimizes the impact of the event for the user.

### Claim 16 (depends on 15)

The method of claim 15, wherein the event comprises one or more of a weather related event, an employment related event, a geopolitical event, a civic unrest, and a medical event.

### Claim 17 (depends on 15)

The method of claim 15, wherein the one or more external sources of data are artificial intelligence based systems.

### Claim 18 (depends on 12)

The method of claim 12, wherein determining the one or more user-defined preference rules further comprises:
establishing, via an intelligent virtual assistant, an interactive session with the user;
providing, to the user, one or more questions in sequential format;
receiving, from the user, responses to the one or more questions;
providing, to the user and based on the responses, one or more additional questions; and
receiving, from the user, responses to the one or more additional questions.

### Claim 19 (depends on 18)

The method of claim 18, further comprising:
training the intelligent virtual assistant based on a machine learning model.

### Claim 19

(canceled)

### Claim 20

One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, at least one physical sensor communicatively coupled to the at least one processor, and memory, cause the computing platform to:
determine, via a computing device and based on historical user activity of a user, a pattern of the user activity;
identify, based on the pattern of the user activity, one or more anticipated purchase activities of the user;
determine, via the computing device and based on the one or more anticipated purchase activities of the user, a sales offering by a vendor;
match, via the computing device, the one or more anticipated purchase activities of the user with the sales offering by the vendor;
retrieve, from a repository of user data and for a purchase activity of the one or more anticipated purchase activities, one or more user-defined preference rules associated with the purchase activity;
determine whether the one or more preference rules apply to one or more attributes of the purchase activity;
initiate, via an intelligent virtual assistant and based on a determination that the one or more preference rules apply to the one or more attributes of the purchase activity, an interactive session with the user; and
trigger, based on the interactive session, an action associated with the purchase activity.
