# US 2023/0267280 A1 · Systems and methods for generating dynamic conversational responses using machine learning models

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

- Number: US 2023/0267280 A1
- Document ID: US20230267280A1
- Status: Published application
- Kind: A1
- Application number: 18/306,196
- Filed: 2023-04-24
- Published: 2023-08-24
- Earliest claimed: 2020-08-05
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Victor Alvarez MIRANDA; Rui ZHANG
- Web page: https://patentgrep.com/patent/US20230267280A1

## CPC

- G06F 40/35: Discourse or dialogue representation
- G06F 16/3329: Natural language query formulation
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 20/00: Machine learning
- G06Q 20/108: {Remote banking, e.g. home banking}
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- G06F 3/04883: for inputting data by handwriting, e.g. gesture or text
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Methods and systems are described for generating dynamic conversational responses using machine learning models. The dynamic conversational responses may be generated in real time and reflect the likely goals and/or intents of a user. The machine learning model may provide these features by monitoring one or more user actions and/or lengths of time between one or more user actions during conversational interactions.

## Claims

### Claim 1

A system for generating dynamic conversational responses using machine learning models, the system comprising:
storage circuitry configured to store a first machine learning model that is trained to:
determine predetermined numbers of dynamic conversational responses for simultaneously displaying in user interfaces in response to user actions; and
select subsets of dynamic conversational responses from a plurality of dynamic conversational responses, wherein a number of dynamic conversational responses in the subsets match the predetermined numbers, and wherein each dynamic conversational response in the subsets corresponds to inputted user actions, inputted lengths of time, and metadata;
control circuitry configured to:
receive a first user action, from a first user, during a conversational interaction with a user interface;
determine a first user interface position of the first user action in the user interface;
retrieve metadata related to the first user interface position;
monitor for a second user action during the conversational interaction with the user interface;
determine a first length of time since the first user action while monitoring for the second user action;
generate a first feature input based on the first user action, the first length of time, and the metadata; and
input the first feature input into the first machine learning model; and
input/output circuitry configured to:
simultaneously generate, at the user interface, a subset of dynamic conversational responses that corresponds to the first user action, second user action, and the first length of time.

### Claim 2

A method for generating dynamic conversational responses using machine learning models, the method comprising:
receiving a first user action, from a first user, during a conversational interaction with a user interface;
monitoring for a second user action during the conversational interaction with the user interface;
while monitoring for the second user action, determining a first length of time since the first user action;
selecting a subset of dynamic conversational responses from a plurality of dynamic conversational responses, wherein a number of dynamic conversational responses in the subset match a predetermined number, and wherein each dynamic conversational response in the subset corresponds to the first user action, the second user action, and the first length of time; and
simultaneously generating, at the user interface, the subset.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
generating a first feature input based on the first user action and the first length of time; and
inputting the first feature input into a first machine learning model, wherein the first machine learning model is trained to determine the predetermined numbers of dynamic conversational responses and select the subsets of dynamic conversational responses.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
determining a first user interface position of the first user action in the user interface; and
retrieving metadata related to the first user interface position, wherein the first feature input is further based on the metadata.

### Claim 5 (depends on 4)

The method of claim 4, further comprising selecting a second user interface position for generating a dynamic conversational response based on the first user interface position.

### Claim 6 (depends on 5)

The method of claim 5, wherein boundaries of the second user interface position are located within boundaries of the first user interface position.

### Claim 7 (depends on 2)

The method of claim 2, further comprising while monitoring for the second user action, monitoring for a third user action during the conversational interaction with the user interface, wherein the third user action corresponds to a user-initiated end to the conversational interaction.

### Claim 8 (depends on 7)

The method of claim 7, further comprising:
in response to detecting the third user action, determining a result of the first user action;
generating a second feature input based on the result;
inputting the second feature input into a second machine learning model, wherein the second machine learning model is trained to determine a level of variance of the result from prior results of prior user actions; and
generating, at the user interface, a push notification based on the level of variance.

### Claim 9 (depends on 7)

The method of claim 7, further comprising:
in response to detecting the third user action, monitoring for a fourth user action, wherein the fourth user action is not received via the user interface, and wherein the fourth user action corresponds to the first user contacting a second user; and
in response to detecting the fourth user action, generating, at a second user interface corresponding to the second user, a recommendation based on a dynamic conversational response selected by the machine learning model.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
determining user information corresponding to the recommendation;
determining a network location of the user information; and
generating a network pathway to the user information.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
automatically retrieving the user information from the network location in response to the fourth user action; and
generating for display the user information on the second user interface.

### Claim 12

A non-transitory, computer-readable medium for generating dynamic conversational responses using machine learning models, comprising instructions that, when executed by one or more processors, cause operations comprising:
receiving a first user action, from a first user, during a conversational interaction with a user interface;
monitoring for a second user action during the conversational interaction with the user interface;
while monitoring for the second user action, determining a first length of time since the first user action;
selecting a subset of dynamic conversational responses from a plurality of dynamic conversational responses, wherein a number of dynamic conversational responses in the subset match a predetermined number, and wherein each dynamic conversational response in the subset corresponds to the first user action, the second user action, and the first length of time; and
simultaneously generating, at the user interface, the subset.

### Claim 13 (depends on 12)

The non-transitory, computer-readable medium of claim 12, further comprising instructions that cause further operations comprising:
generating a first feature input based on the first user action and the first length of time; and
inputting the first feature input into a first machine learning model, wherein the first machine learning model is trained to determine the predetermined numbers of dynamic conversational responses and select the subsets of dynamic conversational responses.

### Claim 14 (depends on 13)

The non-transitory, computer-readable medium of claim 13, further comprising instructions that cause further operations comprising:
determining a first user interface position of the first user action in the user interface; and
retrieving metadata related to the first user interface position, wherein the first feature input is further based on the metadata.

### Claim 15 (depends on 14)

The non-transitory, computer-readable medium of claim 14, further comprising instructions that cause further operations comprising selecting a second user interface position for generating a dynamic conversational response based on the first user interface position, wherein boundaries of the second user interface position are located within boundaries of the first user interface position.

### Claim 16 (depends on 12)

The non-transitory, computer-readable medium of claim 12, further comprising instructions that cause further operations comprising while monitoring for the second user action, monitoring for a third user action during the conversational interaction with the user interface, wherein the third user action corresponds to a user-initiated end to the conversational interaction.

### Claim 17 (depends on 16)

The non-transitory, computer-readable medium of claim 16, further comprising instructions that cause further operations comprising:
in response to detecting the third user action, determining a result of the first user action; generating a second feature input based on the result;
inputting the second feature input into a second machine learning model, wherein the second machine learning model is trained to determine a level of variance of the result from prior results of prior user actions; and
generating, at the user interface, a push notification based on the level of variance.

### Claim 18 (depends on 17)

The non-transitory, computer-readable medium of claim 17, further comprising instructions that cause further operations comprising:
in response to detecting the third user action, monitoring for a fourth user action, wherein the fourth user action is not received via the user interface, and wherein the fourth user action corresponds to the first user contacting a second user; and
in response to detecting the fourth user action, generating, at a second user interface corresponding to the second user, a recommendation based on a dynamic conversational response selected by the machine learning model.

### Claim 19 (depends on 18)

The non-transitory, computer-readable medium of claim 18, further comprising instructions that cause further operations comprising:
determining user information corresponding to the recommendation;
determining a network location of the user information; and
generating a network pathway to the user information.

### Claim 20 (depends on 19)

The non-transitory, computer-readable medium of claim 19, further comprising instructions that cause further operations comprising:
automatically retrieving the user information from the network location in response to the fourth user action; and
generating for display the user information on the second user interface.
