# US 2026/0087043 A1 · Model-based personal advisor system

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

- Number: US 2026/0087043 A1
- Document ID: US20260087043A1
- Status: Published application
- Kind: A1
- Application number: 19/337,525
- Filed: 2025-09-23
- Published: 2026-03-26
- Earliest claimed: 2024-09-24
- Assignees: Wells Fargo Bank, N.A.
- Applicants: Wells Fargo Bank, N.A.
- Inventors: Michael Liersch; Evelyn Varner; David J. Furst
- Web page: https://patentgrep.com/patent/US20260087043A1

## CPC

- G06N 20/20: Ensemble learning
- G06F 16/33295: {in dialogue systems}
- G06F 16/337: {Profile generation, learning or modification}
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- 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 30/02011: {Profiling or inferring profiles of users or market based on their behaviour}
- G06Q 30/0205: {based on location or geographical consideration}
- G06Q 40/065: {Budgeting}
- G06Q 40/066: {Retirement planning}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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

Systems, apparatuses, methods, and computer program products are disclosed for providing a multimodal interactive personal advisor (MIPA). An example method includes retrieving first user data associated with a user. The example method also includes facilitating an first interaction between the user and an MIPA model via a first user device. The example method also includes extracting, based on the first interaction, a set of data features associated with the user and determining, based on the set of data features, second user data. The example method also includes generating, based on the first user data and the second user data, a first model response and providing the first model response to the user via a second user device associated with the user.

## Claims

### Claim 1

A multimodal interactive personal advisor (MIPA) system comprising:
user data circuitry configured to retrieve first user data associated with a user;
MIPA management circuitry configured to:
facilitate a first interaction between the user and an MIPA model, wherein the first interaction is facilitated on a first user device associated with the user; and
the MIPA model, wherein the MIPA model is configured to:
extract, based on first user input received during the first interaction, a first set of data features associated with the user;
determine, based on the first set of data features, second user data; and
generate, based on the first user data and the second user data, a first model response, wherein the MIPA management circuitry is configured to provide the first model response to the user via a second user device associated with the user.

### Claim 2 (depends on 1)

The MIPA system of claim 1, wherein:
the MIPA management circuitry is configured to facilitate a second interaction between the user and the MIPA model, wherein the second interaction is facilitated on a third user device associated with the user; and
the MIPA model is configured to:
extract, based on second user input received during the second interaction, a second set of data features associated with the user;
determine, based on the second set of data features, third user data; and
generate, based on the second user data and the third user data, a second model response, wherein the MIPA management circuitry is configured to provide the second model response to the user.

### Claim 3 (depends on 2)

The MIPA system of claim 2, wherein one or more of the first interaction or the second interaction is associated with one or more of a conversational interaction, a documentation upload interaction, or a video-based interaction.

### Claim 4 (depends on 3)

The MIPA system of claim 3, wherein one or more of the first user input or the second user input comprise text input data, audio input data, or video input data associated with the user.

### Claim 5 (depends on 4)

The MIPA system of claim 4, wherein the MIPA model is configured to:
extract a set of user input data features from the second user input;
determine, based on the set of user input data features, a set of user input attributes associated with the second user input; and
generate the second model response based on the set of user input attributes.

### Claim 6 (depends on 5)

The MIPA system of claim 5, wherein the set of user input attributes indicates one or more of a user sentiment, a user intent, a user tone, a user emotion, a level of technicality, or a level of subject matter knowledge of the user.

### Claim 7 (depends on 6)

The MIPA system of claim 6, wherein the MIPA model is configured to:
determine, based on the set of user input attributes, an appropriate response format; and
generate the second model response according to the appropriate response format.

### Claim 8 (depends on 7)

The MIPA system of claim 7, wherein the MIPA management circuitry is configured to provide a notification to the user that the second model response has been generated according to the appropriate response format, wherein the notification indicates a means in which the user can access the second model response.

### Claim 9 (depends on 7)

The MIPA system of claim 7, wherein the MIPA model is configured to:
determine one or more inferred character traits of the user; and
determine, based on the one or more inferred character traits of the user, the appropriate response format with which to generate the second model response.

### Claim 10 (depends on 3)

The MIPA system of claim 3, wherein the MIPA model is configured to generate at least a first pathway associated with the user based on based on the first user data, the second user data, and the third user data, wherein the first pathway is an actionable plan associated with one or more of a primary goal, a set of subgoals related to the primary goal, a set of insights, a set of important considerations, a set of product offers, a set of opportunities, a set of scenarios, a set of action item lists, or a set of tradeoffs.

### Claim 11

A method comprising:
retrieving, by user data circuitry, first user data associated with a user;
facilitating, by multimodal interactive personal advisor (MIPA) management circuitry, a first interaction between the user and an MIPA model, wherein the first interaction is facilitated on a first user device associated with the user;
extracting, by the MIPA model and based on first user input received during the first interaction, a first set of data features associated with the user;
determining, by the MIPA model and based on the first set of data features, second user data;
generating, by the MIPA model and based on the first user data and the second user data, a first model response; and
providing, by the MIPA management circuitry, the first model response to the user via a second user device associated with the user.

### Claim 12 (depends on 11)

The method of claim 11, the method comprising:
facilitating, by the MIPA management circuitry, a second interaction between the user and the MIPA model, wherein the second interaction is facilitated on a third user device associated with the user;
extracting, by the MIPA model and based on second user input received during the second interaction, a second set of data features associated with the user;
determining, by the MIPA model and based on the second set of data features, third user data;
generating, by the MIPA model and based on the second user data and the third user data, a second model response; and
providing, by the MIPA management circuitry, the second model response to the user.

### Claim 13 (depends on 12)

The method of claim 12, wherein one or more of the first interaction or the second interaction is associated with one or more of a conversational interaction, a documentation upload interaction, or a video-based interaction.

### Claim 14 (depends on 13)

The method of claim 13, wherein one or more of the first user input or the second user input comprise text input data, audio input data, or video input data associated with the user.

### Claim 15 (depends on 14)

The method of claim 14, the method comprising:
extracting, by the MIPA model, a set of user input data features from the second user input;
determining, by the MIPA model and based on the set of user input data features, a set of user input attributes associated with the second user input; and
generating, by the MIPA model, the second model response based on the set of user input attributes.

### Claim 16 (depends on 15)

The method of claim 15, wherein the set of user input attributes indicates one or more of a user sentiment, a user intent, a user tone, a user emotion, a level of technicality, or a level of subject matter knowledge of the user.

### Claim 17 (depends on 16)

The method of claim 16, the method comprising:
determining, by the MIPA model and based on the set of user input attributes, an appropriate response format; and
generating, by the MIPA model, the second model response according to the appropriate response format.

### Claim 18 (depends on 17)

The method of claim 17, wherein the MIPA management circuitry is configured to provide a notification to the user that the second model response has been generated according to the appropriate response format, wherein the notification indicates a means in which the user can access the second model response.

### Claim 19 (depends on 17)

The method of claim 17, the method comprising:
determining, by the MIPA model, one or more inferred character traits of the user; and
determining, by the MIPA model and based on the one or more inferred character traits of the user, the appropriate response format with which to generate the second model response.

### Claim 20

A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to:
retrieve first user data associated with a user;
facilitate a first interaction between the user and a multimodal interactive personal advisor (MIPA) model, wherein the first interaction is facilitated on a first user device associated with the user;
extract, based on first user input received during the first interaction, a first set of data features associated with the user;
determine, based on the first set of data features, second user data;
generate, based on the first user data and the second user data, a first model response; and
provide the first model response to the user via a second user device associated with the user.
