# US 2021/0082397 A1 · Dynamic contextual dialog session extension

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

- Number: US 2021/0082397 A1
- Document ID: US20210082397A1
- Status: Published application
- Kind: A1
- Application number: 16/923,483
- Filed: 2020-07-08
- Published: 2021-03-18
- Earliest claimed: 2019-09-12
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Michael Richard Kennewick
- Web page: https://patentgrep.com/patent/US20210082397A1

## CPC

- G10L 15/05: Word boundary detection
- 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 25/87: Detection of discrete points within a voice signal
- G06F 40/205: Parsing
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A dialog system is described that is capable of maintaining a single dialog session covering multiple user utterances, which may be separated by pauses or time gaps, and that continuously determines intent across the multiple utterances within a session.

## Claims

### Claim 1

A computer-implemented method comprising:
initiating, by a dialog system, a dialog session;
receiving, by the dialog system, a first speech input;
detecting, by the dialog system, a pause in the first speech input indicative of completion of a first spoken utterance;
determining, by the dialog system based on the first spoken utterance, a stopping condition for the dialog session, wherein the stopping condition indicates a first time value by which the dialog session is to be extended;
determining, by the dialog system, that the stopping condition for the dialog session is not met; and
responsive to determining that the stopping condition is not met, extending the dialog session by at least the first time value indicated by the stopping condition.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
determining, by the dialog system, that the dialog session is in a particular state, of a plurality of configured states,
wherein the dialog system determines the stopping condition for the dialog session based on the determined state.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
generating, by the dialog system, a response based on the first speech input; and
outputting, by the dialog system, the response.

### Claim 4 (depends on 3)

The method of claim 3, wherein generating and outputting the response is performed prior to determining that the stopping condition is not met.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
receiving, by the dialog system, a second speech input;
detecting, by the dialog system, a second pause in the second speech input indicative of completion of a second spoken utterance; and
determining, by the dialog system based on the second spoken utterance, a second stopping condition for the dialog session, wherein the second stopping condition indicates a second time value by which the dialog session is to be extended.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
identifying, by the dialog system, an intent based on the first speech input and the second speech input.

### Claim 7 (depends on 5)

The method of claim 5, further comprising:
generating, by the dialog system, a response based on one or more of the first speech input or the second speech input; and
outputting, by the dialog system, the response.

### Claim 8 (depends on 7)

The method of claim 7, further comprising:
subsequent to outputting the response, determining, by the dialog system, that the second stopping condition is met; and
terminating, by the dialog system, the dialog session.

### Claim 9 (depends on 5)

The method of claim 5, wherein:
the dialog system determines the second stopping condition based upon one or more of: a length of the pause, the first speech input, or the second speech input.

### Claim 10 (depends on 1)

The method of claim 1, wherein initiating the dialog session comprises one or more of:
detecting a wake word; or
detecting interaction with a start button.

### Claim 11 (depends on 1)

The method of claim 1, further comprising:
receiving, by the dialog system, a third speech input;
based upon the third speech input and the first speech input, determining, by the dialog system, that the third speech input is not relevant to the first speech input; and
disregarding, by the dialog system, the third speech input.

### Claim 12

A non-transitory computer-readable memory storing a plurality of instructions executable by one or more processors, the plurality of instructions comprising instructions that when executed by the one or more processors cause the one or more processors to perform processing comprising:
initiating a dialog session;
receiving a first speech input;
detecting a pause in the first speech input indicative of completion of a first spoken utterance;
determining, based on the first spoken utterance, a stopping condition for the dialog session, wherein the stopping condition indicates a first time value by which the dialog session is to be extended;
determining that the stopping condition for the dialog session is not met; and
responsive to determining that the stopping condition is not met, extending the dialog session by at least the first time value indicated by the stopping condition.

### Claim 13 (depends on 12)

The non-transitory computer-readable memory of claim 12, the processing further comprising:
determining that the dialog session is in a particular state, of a plurality of configured states,
wherein the stopping condition for the dialog session is determined based on the determined state.

### Claim 14 (depends on 12)

The non-transitory computer-readable memory of claim 12, the processing further comprising:
generating a response based on the first speech input; and
outputting the response, wherein generating and outputting the response is performed prior to determining that the stopping condition is not met.

### Claim 15 (depends on 12)

The non-transitory computer-readable memory of claim 12, the processing further comprising:
receiving a second speech input;
detecting a second pause in the second speech input indicative of completion of a second spoken utterance; and
determining, based on the second spoken utterance, second stopping condition for the dialog session, wherein the second stopping condition indicates a second time value by which the dialog session is to be extended.

### Claim 16 (depends on 15)

The non-transitory computer-readable memory of claim 15, the processing further comprising:
identifying an intent based on the first speech input and the second speech input.

### Claim 17

A system comprising:
one or more processors;
a memory coupled to the one or more processors, the memory storing a plurality of instructions executable by the one or more processors, the plurality of instructions comprising instructions that when executed by the one or more processors cause the one or more processors to perform processing comprising:
initiating a dialog session;
receiving a first speech input;
detecting a pause in the first speech input indicative of completion of a first spoken utterance;
determining, based on the first spoken utterance, a stopping condition for the dialog session, wherein the stopping condition indicates a first time value by which the dialog session is to be extended;
determining that the stopping condition for the dialog session is not met; and
responsive to determining that the stopping condition is not met, extending the dialog session by at least the first time value indicated by the stopping condition.

### Claim 18 (depends on 17)

The system of claim 17, the processing further comprising:
determining that the dialog session is in a particular state, of a plurality of configured states,
wherein the determination that the stopping condition is not met is based upon the determined state.

### Claim 19 (depends on 17)

The system of claim 17, the processing further comprising:
generating a response based on the first speech input; and
outputting the response, wherein generating and outputting the response is performed prior to determining that the stopping condition is not met.

### Claim 20 (depends on 17)

The system of claim 17, the processing further comprising:
receiving a second speech input;
detecting a second pause in the second speech input indicative of completion of a second spoken utterance;
determining, based on the second spoken utterance, a second stopping condition for the dialog session, wherein the second stopping condition indicates a second time value by which the dialog session is to be extended; and
identifying an intent based on the first speech input and the second speech input.
