# US 2021/0233524 A1 · Placing a voice response system into a forced sleep state

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

- Number: US 2021/0233524 A1
- Document ID: US20210233524A1
- Status: Published application
- Kind: A1
- Application number: 16/749,997
- Filed: 2020-01-23
- Published: 2021-07-29
- Earliest claimed: 2020-01-23
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Shikhar KWATRA; Adam Lee GRIFFIN; Michael SPISAK; Sarbajit K. RAKSHIT
- Web page: https://patentgrep.com/patent/US20210233524A1

## CPC

- G06F 1/3215: Monitoring of peripheral devices
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- 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 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L 2015/228: {of application context}
- 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

Embodiments generally relate placing a voice response system into a forced sleep state. In some embodiments, a method includes receiving a voice command from a given user to place a voice response system in a woke state. The method further includes obtaining current context data, and analyzing the current context data using a voice response model trained using a voice response corpus that incorporated a history of interactions and context data by one or more users with the voice response system. The method further includes, from the analysis of the current context data using the voice response model, determining whether the voice response system is to be placed in the woke state; and, responsive to determining that the voice response system is not to be placed in the woke state, placing the voice response system in a sleep state contrary to the voice command.

## Claims

### Claim 1

A system comprising:
at least one processor and a computer readable storage medium having program instructions embodied therewith, the program instructions executable by the at least one processor to cause the at least one processor to perform operations comprising:
receiving a voice command from a given user to place a voice response system in a woke state;
responsive to receiving the voice command, obtaining current context data;
analyzing the current context data using a voice response model trained using a voice response corpus that incorporated a history of interactions and context data by one or more users with the voice response system;
from the analysis of the current context data using the voice response model, determining whether the voice response system is to be placed in the woke state; and
responsive to determining that the voice response system is not to be placed in the woke state, placing the voice response system in a sleep state contrary to the voice command.

### Claim 2 (depends on 1)

The system of claim 1, wherein the at least one processor further performs operations comprising, responsive to determining that the voice response system is not to be placed in the woke state, queuing the voice command to be executed when an analysis of future context data using the voice response model determines that the voice response system is to be placed in the woke state.

### Claim 3 (depends on 1)

The system of claim 1, wherein the at least one processor further performs operations comprising:
from the analysis of the current context data using the voice response model, determining an alternative command consistent with the current context data; and
executing the alternative command.

### Claim 4 (depends on 1)

The system of claim 1, wherein the at least one processor further performs operations comprising determining if there are any restriction policies that restrict how the voice response system responds to voice responses.

### Claim 5 (depends on 1)

The system of claim 1, wherein the at least one processor further performs operations comprising applying a restriction policy, wherein the voice response system is forced into a sleep state if a particular user is studying.

### Claim 6 (depends on 1)

The system of claim 1, wherein the at least one processor further performs operations comprising applying a restriction policy, wherein the voice response system is forced into a sleep state if users are discussing a sensitive topic.

### Claim 7 (depends on 1)

The system of claim 1, wherein the at least one processor further performs operations comprising applying a restriction policy, wherein the voice response system is forced into a sleep state during a predetermined time period.

### Claim 8

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by at least one processor to cause the at least one processor to perform operations comprising:
receiving a voice command from a given user to place a voice response system in a woke state;
responsive to receiving the voice command, obtaining current context data;
analyzing the current context data using a voice response model trained using a voice response corpus that incorporated a history of interactions and context data by one or more users with the voice response system;
from the analysis of the current context data using the voice response model, determining whether the voice response system is to be placed in the woke state; and
responsive to determining that the voice response system is not to be placed in the woke state, placing the voice response system in a sleep state contrary to the voice command.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein the at least one processor further performs operations comprising responsive to determining that the voice response system is not to be placed in the woke state, queuing the voice command to be executed when an analysis of future context data using the voice response model determines that the voice response system is to be placed in the woke state.

### Claim 10 (depends on 8)

The computer program product of claim 8, wherein the at least one processor further performs operations comprising:
from the analysis of the current context data using the voice response model, determining an alternative command consistent with the current context data; and
executing the alternative command.

### Claim 11 (depends on 8)

The computer program product of claim 8, wherein the at least one processor further performs operations comprising determining if there are any restriction policies that restrict how the voice response system responds to voice responses.

### Claim 12 (depends on 8)

The computer program product of claim 8, wherein the at least one processor further performs operations comprising applying a restriction policy, wherein the voice response system is forced into a sleep state if a particular user is studying.

### Claim 13 (depends on 8)

The computer program product of claim 8, wherein the at least one processor further performs operations comprising applying a restriction policy, wherein the voice response system is forced into a sleep state if users are discussing a sensitive topic.

### Claim 14 (depends on 8)

The computer program product of claim 8, wherein the at least one processor further performs operations comprising applying a restriction policy, wherein the voice response system is forced into a sleep state during a predetermined time period.

### Claim 15

A computer-implemented method for placing a voice response system into a forced sleep state, the method comprising:
receiving a voice command from a given user to place a voice response system in a woke state;
responsive to receiving the voice command, obtaining current context data;
analyzing the current context data using a voice response model trained using a voice response corpus that incorporated a history of interactions and context data by one or more users with the voice response system;
from the analysis of the current context data using the voice response model, determining whether the voice response system is to be placed in the woke state; and
responsive to determining that the voice response system is not to be placed in the woke state, placing the voice response system in a sleep state contrary to the voice command.

### Claim 16 (depends on 15)

The method of claim 15, further comprising responsive to determining that the voice response system is not to be placed in the woke state, queuing the voice command to be executed when an analysis of future context data using the voice response model determines that the voice response system is to be placed in the woke state.

### Claim 17 (depends on 15)

The method of claim 15, further comprising:
from the analysis of the current context data using the voice response model, determining an alternative command consistent with the current context data; and
executing the alternative command.

### Claim 18 (depends on 15)

The method of claim 15, further comprising determining if there are any restriction policies that restrict how the voice response system responds to voice responses.

### Claim 19 (depends on 15)

The method of claim 15, further comprising applying a restriction policy, wherein the voice response system is forced into a sleep state if a particular user is studying.

### Claim 20 (depends on 15)

The method of claim 15, further comprising applying a restriction policy, wherein the voice response system is forced into a sleep state if users are discussing a sensitive topic.
