# US 2022/0012075 A1 · Virtual assistant interaction enhancement

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

- Number: US 2022/0012075 A1
- Document ID: US20220012075A1
- Status: Published application
- Kind: A1
- Application number: 16/923,173
- Filed: 2020-07-08
- Published: 2022-01-13
- Earliest claimed: 2020-07-08
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Michal Paluch; Nicolò Sgobba; Erik Rueger; Julien Loeve
- Web page: https://patentgrep.com/patent/US20220012075A1

## CPC

- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 9/453: {Help systems}
- G06F 3/048: Interaction techniques based on graphical user interfaces [GUI]
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 3/045: Combinations of networks
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A user input is received. The user input is classified using a neural network. A set of contextual information for the user input is determined, based on the classification. The user input is modified, based on the classification and the set of contextual information. The modified user input is passed to a virtual assistant.

## Claims

### Claim 1

A method for enhancing virtual assistant interactions, the method comprising:
receiving a user input;
classifying, using a neural network, the user input;
determining, based on the classification, a set of contextual information for the user input;
modifying the user input, based on the classification and the set of contextual information;
aggregating the modified user input with a plurality of historical modified user inputs wherein the historical modified user inputs are user inputs from prior inputs;
generating an aggregate modified user input, based on the classification, the set of contextual information, and the aggregated plurality of historical modified user inputs; and
passing the aggregated modified user input to a virtual assistant.

### Claim 2 (depends on 1)

The method of claim 1, wherein the neural network is a classifier neural network, and wherein the user input is classified as a question, a statement, or an answer.

### Claim 3 (depends on 1)

The method of claim 1, wherein the set of contextual information includes an intent, an entity, and a context.

### Claim 4

(canceled)

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
receiving, from the virtual assistant, a response to the user input; and
notifying the user of the response.

### Claim 6 (depends on 5)

The method of claim 5, wherein modifying the user input is predicated upon the set of contextual information meeting a context threshold.

### Claim 7 (depends on 5)

The method of claim 5, wherein the classified user input is cached and aggregated with a plurality of classified user inputs, and wherein passing the modified user input is predicated upon the modified user input meeting a context threshold.

### Claim 8 (depends on 5)

The method of claim 5, wherein the neural network is trained prior to receiving the user input and wherein the training includes adjusting a weight or a bias of the neural network.

### Claim 9

A computer program product for enhancing virtual assistant interactions, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:
receive a user input;
classify, using a neural network, the user input;
determine, based on the classification, a set of contextual information for the user input;
modify the user input, based on the classification and the set of contextual information;
aggregate the modified user input with a plurality of historical modified user inputs;
generate an aggregate modified user input, based on the classification, the set of contextual information, and the aggregated plurality of historical modified user inputs; and
pass the aggregated modified user input to a virtual assistant.

### Claim 10 (depends on 9)

The computer program product of claim 9, wherein the neural network is a classifier neural network, and wherein the user input is classified as a question, a statement, or an answer.

### Claim 11 (depends on 9)

The computer program product of claim 9, wherein the set of contextual information includes an intent, an entity, and a context.

### Claim 12

(canceled)

### Claim 13 (depends on 9)

The computer program product of claim 9, wherein the program instructions further cause the device to:
receive, from the virtual assistant, a response to the user input; and
notify the user of the response.

### Claim 14 (depends on 13)

The computer program product of claim 13, wherein modifying the user input is predicated upon the set of contextual information meeting a context threshold.

### Claim 15 (depends on 13)

The computer program product of claim 13, wherein the classified user input is cached and aggregated with a plurality of classified user inputs, and wherein passing the modified user input is predicated upon the modified user input meeting a context threshold.

### Claim 16

A system for enhancing virtual assistant interactions, comprising:
a memory with program instructions included thereon; and
a processor in communication with the memory, wherein the program instructions cause the processor to:
receive a user input;
classify, using a neural network, the user input;
determine, based on the classification, a set of contextual information for the user input;
modify the user input, based on the classification and the set of contextual information;
aggregate the modified user input with a plurality of historical modified user inputs;
generate an aggregate modified user input, based on the classification, the set of contextual information, and the aggregated plurality of historical modified user inputs; and
pass the aggregated modified user input to a virtual assistant.

### Claim 17 (depends on 16)

The system of claim 16, wherein the neural network is a classifier neural network, and wherein the user input is classified as a question, a statement, or an answer.

### Claim 18 (depends on 16)

The system of claim 16, wherein the set of contextual information includes an intent, an entity, and a context.

### Claim 19

(canceled)

### Claim 20 (depends on 16)

The system of claim 16, wherein the program instructions further cause the processor to:
receive, from the virtual assistant, a response to the user input; and
notify the user of the response.
