# US 2019/0172454 A1 · Automatic dialogue design

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

- Number: US 2019/0172454 A1
- Document ID: US20190172454A1
- Status: Published application
- Kind: A1
- Application number: 15/833,762
- Filed: 2017-12-06
- Published: 2019-06-06
- Earliest claimed: 2017-12-06
- Assignees: Sony Interactive Entertainment Inc.
- Applicants: Sony Interactive Entertainment Inc.
- Inventors: Marie Kitajima; Masanori Omote
- Web page: https://patentgrep.com/patent/US20190172454A1

## CPC

- 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 15/08: Speech classification or search
- G10L 2015/088: {Word spotting}
- G10L 2015/223: {Execution procedure of a spoken command}
- 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 chatbot learns a person's related “intents” when asking for information and thereafter, in response to an initial query, which the chatbot answers, the chatbot generates a secondary dialogue, either providing the person with additional information or inquiring as to whether the person wishes to know more about a subject. The chatbot may use an external trigger such as time, event, etc. and automatically generate a query or give information to the person without any initial query from the person.

## Claims

### Claim 1

A device comprising:
at least one computer memory that is not a transitory signal and that comprises instructions executable by at least one processor to:
receive an utterance from a person;
access a data structure based on the utterance to retrieve a response to the utterance;
display the response;
based at least in part on the utterance, generate a secondary dialog; and
automatically play the secondary dialogue without any further prompt from the person apart from the utterance.

### Claim 2 (depends on 1)

The device of claim 1, wherein the response is audibly displayed.

### Claim 3 (depends on 2)

The device of claim 2, comprising at least one speaker for playing the response.

### Claim 4 (depends on 1)

The device of claim 1, wherein the response is visibly displayed.

### Claim 5 (depends on 4)

The device of claim 4, comprising at least one display for presenting the response.

### Claim 6 (depends on 1)

The device of claim 1, comprising the at least one processor.

### Claim 7 (depends on 1)

The device of claim 1, wherein the instructions are executable to:
correlate utterances from the person to generate a data structure of learned correlations; and
generate the secondary dialogue based at least in part on the learned correlations.

### Claim 8 (depends on 1)

The device of claim 1, wherein the instructions are executable to:
identify at least one trigger that is not based on an utterance by the person; and
responsive to the trigger, generate the secondary dialogue.

### Claim 9

An apparatus, comprising:
at least one processor;
at least one computer storage with instructions executable by the at least one processor to:
receive a trigger generated by a person;
access a data structure based on the trigger to retrieve a response to the trigger;
display the response;
generate a secondary dialogue; and
automatically play the secondary dialogue without any further prompt from the person apart from the trigger.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein the trigger is an utterance.

### Claim 11 (depends on 9)

The apparatus of claim 9, wherein the trigger is an action related to a vehicle.

### Claim 12 (depends on 9)

The apparatus of claim 9, wherein the response is audibly displayed.

### Claim 13 (depends on 12)

The apparatus of claim 12, comprising at least one speaker for playing the response.

### Claim 14 (depends on 9)

The apparatus of claim 9, wherein the response is visibly displayed.

### Claim 15 (depends on 14)

The apparatus of claim 14, comprising at least one display for presenting the response.

### Claim 16 (depends on 9)

The apparatus of claim 9, wherein the instructions are executable to:
correlate utterances from the person to generate a data structure of learned correlations; and
generate the secondary dialogue based at least in part on the learned correlations.

### Claim 17 (depends on 9)

The apparatus of claim 9, wherein the instructions are executable to:
identify at least one trigger that is not based on an utterance by the person; and
responsive to the trigger, generate the secondary dialogue.

### Claim 18

A method, comprising:
receiving a trigger generated by a person;
accessing a data structure based on the trigger to retrieve a response to the trigger;
displaying the response;
generating a secondary dialogue; and
automatically playing the secondary dialogue without any further prompt from the person apart from the trigger.

### Claim 19 (depends on 18)

The method claim 18, wherein the trigger is an utterance.

### Claim 20 (depends on 18)

The method claim 18, wherein the trigger is not an utterance.
