# US 2025/0166618 A1 · Preventing non-transient storage of assistant interaction data and/or wiping of stored assistant interaction data

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

- Number: US 2025/0166618 A1
- Document ID: US20250166618A1
- Status: Published application
- Kind: A1
- Application number: 19/029,358
- Filed: 2025-01-17
- Published: 2025-05-22
- Earliest claimed: 2020-01-07
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Fadi Biadsy; Johan Schalkwyk; Jason Pelecanos
- Web page: https://patentgrep.com/patent/US20250166618A1

## CPC

- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 2015/223: {Execution procedure of a spoken command}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Implementations disclosed herein are directed to techniques for selectively enabling and/or disabling non-transient storage of one or more instances of assistant interaction data for turn(s) of a dialog between a user and an automated assistant. Implementations are additionally or alternatively directed to techniques for retroactive wiping of non-transiently stored assistant interaction data from previous assistant interaction(s).

## Claims

### Claim 1

A method implemented by one or more processors, the method comprising:
determining, based on user input received at an assistant device, to prevent utilization of any personal data in generating assistant responses until one or more termination conditions are satisfied;
prior to the one or more termination conditions being satisfied:
processing audio data, using a speech recognition model, to generate recognized text of a spoken utterance, of a user, that is captured in the audio data, wherein the audio data is detected via one or more microphones of the assistant device;
determining, based on the recognized text, an assistant response that is responsive to the spoken utterance, wherein determining the assistant response that is responsive to the spoken utterance comprises, in response to determining to additionally prevent utilization of any personal data in generating assistant responses, determining the assistant response independent of any personal data; and
causing the assistant response to be rendered at the assistant device; and responsive to determining the one or more termination conditions are satisfied:
enabling determining of assistant responses utilizing personal data.

### Claim 2 (depends on 1)

The method of claim 1, wherein causing the assistant response to be rendered at the assistant device comprises:
causing an audible portion of the assistant response to be rendered in a particular synthesized voice, wherein causing the audible portion to be rendered in the particular synthesized voice is responsive to determining to prevent the non-transient storage of assistant interaction data.

### Claim 3 (depends on 2)

The method of claim 2, wherein the particular synthesized voice is utilized, at least for the user, only when non-transient storage of assistant interaction data is being prevented.

### Claim 4 (depends on 2)

The method of claim 2, further comprising:
while preventing the non-transient storage of assistant interaction data and prior to the one or more termination conditions being satisfied:
causing the assistant device to render a visually perceptible cue; and
responsive to determining the one or more termination conditions are satisfied:
causing the assistant device to cease rendering of the visually perceptible cue.

### Claim 5 (depends on 4)

The method of claim 4, further comprising, while preventing the non-transient storage of assistant interaction data and prior to the one or more termination conditions being satisfied:
causing a plurality of additional assistant devices, that are in addition to the assistant device, to each render a corresponding visually perceptible and/or audibly perceptible cue.

### Claim 6 (depends on 5)

The method of claim 5, wherein causing the plurality of additional assistant devices, that are in addition to the assistant device, to each render the corresponding visually perceptible and/or audibly perceptible cue comprises transmitting, by the assistant device and to the plurality of additional assistant devices that are in addition to the assistant device, a command that causes the rendering of the corresponding visually perceptible and/or audibly perceptible cues.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
while preventing the non-transient storage of assistant interaction data and prior to the one or more termination conditions being satisfied:
causing the assistant device to render a visually perceptible cue; and
responsive to determining the one or more termination conditions are satisfied:
causing the assistant device to cease rendering of the visually perceptible cue.

### Claim 8 (depends on 1)

The method of claim 1, wherein the one or more termination conditions comprise passage of a threshold amount of time.

### Claim 9 (depends on 1)

The method of claim 1, wherein the one or more termination conditions comprise completion of a dialog session that immediately follows the user input.

### Claim 10

A method implemented by one or more processors, the method comprising:
determining, based on user input received at an assistant device, to prevent non-transient storage of assistant interaction data until one or more termination conditions are satisfied;
while preventing the non-transient storage of assistant interaction data and prior to the one or more termination conditions being satisfied:
processing audio data, using a speech recognition model, to generate recognized text of a spoken utterance, of a user, that is captured in the audio data, wherein the audio data is detected via one or more microphones of the assistant device;
determining, based on the recognized text, an assistant response that is responsive to the spoken utterance;
causing the assistant response to be rendered at the assistant device; and
responsive to determining to prevent the non-transient storage of assistant interaction data, preventing non-transient storage of the audio data, the recognized text, and/or the assistant response; and
responsive to determining the one or more termination conditions are satisfied:
enabling non-transient storage of assistant interaction data.

### Claim 11 (depends on 10)

The method of claim 10, wherein causing the assistant response to be rendered at the assistant device comprises:
causing an audible portion of the assistant response to be rendered in a particular synthesized voice, wherein causing the audible portion to be rendered in the particular synthesized voice is responsive to determining to prevent the non-transient storage of assistant interaction data.

### Claim 12 (depends on 11)

The method of claim 11, wherein the particular synthesized voice is utilized, at least for the user, only when non-transient storage of assistant interaction data is being prevented.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
while preventing the non-transient storage of assistant interaction data and prior to the one or more termination conditions being satisfied:
causing the assistant device to render a visually perceptible cue; and
responsive to determining the one or more termination conditions are satisfied:
causing the assistant device to cease rendering of the visually perceptible cue.

### Claim 14 (depends on 13)

The method of claim 13, further comprising, while preventing the non-transient storage of assistant interaction data and prior to the one or more termination conditions being satisfied:
causing a plurality of additional assistant devices, that are in addition to the assistant device, to each render a corresponding visually perceptible and/or audibly perceptible cue.

### Claim 15 (depends on 14)

The method of claim 14, wherein causing the plurality of additional assistant devices, that are in addition to the assistant device, to each render the corresponding visually perceptible and/or audibly perceptible cue comprises transmitting, by the assistant device and to the plurality of additional assistant devices that are in addition to the assistant device, a command that causes the rendering of the corresponding visually perceptible and/or audibly perceptible cues.

### Claim 16 (depends on 11)

The method of claim 11, further comprising:
while preventing the non-transient storage of assistant interaction data and prior to the one or more termination conditions being satisfied:
causing the assistant device to render a visually perceptible cue; and
responsive to determining the one or more termination conditions are satisfied:
causing the assistant device to cease rendering of the visually perceptible cue.

### Claim 17 (depends on 11)

The method of claim 11, wherein the one or more termination conditions comprise passage of a threshold amount of time.

### Claim 18 (depends on 11)

The method of claim 11, wherein the one or more termination conditions comprise completion of a dialog session that immediately follows the user input.

### Claim 19 (depends on 11)

The method of claim 11, wherein responsive to determining to prevent the non-transient storage of assistant interaction data, non-transient storage of the audio data and the recognized text is prevented.

### Claim 20 (depends on 11)

The method of claim 11, wherein responsive to determining to prevent the non-transient storage of assistant interaction data, non-transient storage of the audio data and the assistant response is prevented.
