# US 2023/0154461 A1 · Voice Application Platform

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

- Number: US 2023/0154461 A1
- Document ID: US20230154461A1
- Status: Published application
- Kind: A1
- Application number: 17/947,679
- Filed: 2022-09-19
- Published: 2023-05-18
- Earliest claimed: 2018-06-05
- Assignees: Voicify, LLC
- Applicants: Voicify, LLC
- Inventors: Robert T. Naughton; Nicholas G. Laidlaw; Alexander M. Dunn; Jeffrey K. McMahon
- Web page: https://patentgrep.com/patent/US20230154461A1

## CPC

- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- G06F 16/9035: Filtering based on additional data, e.g. user or group profiles
- G06F 16/909: using geographical or spatial information, e.g. location (spatiotemporally dependent retrieval from the web G06F16/9537)
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- 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

Among other things, requests are received from voice assistant devices expressed in accordance with different corresponding protocols of one or more voice assistant frameworks. Each of the requests represents a voiced input by a user to the corresponding voice assistant device. The received requests are re-expressed in accordance with a common request protocol. Based on the received requests, responses to the requests are expressed in accordance with a common response protocol. Each of the responses is re-expressed according to a protocol of the framework with respect to which the corresponding request was expressed. The responses are sent to the voice assistant devices for presentation to the users.

## Claims

### Claim 31

A method comprising:
receiving request messages through a communication network from voice assistant devices, each of the request messages being expressed as structured data including data corresponding to linguistic elements of a voiced input spoken by a user to a voice assistant device operating according to a voice assistant framework, each of the request messages expressing the linguistic elements of the voiced input in accordance with a native protocol defined for the corresponding voice assistant framework, the native protocols for expressing the linguistic elements of a given request message being different for different respective voice assistant frameworks, each of the request messages expressing, in accordance with the defined native protocol of the corresponding voice assistant framework, the linguistic elements of the voiced input spoken by the user to the corresponding voice assistant device,
re-expressing structured data of received request messages expressed in accordance with different native protocols of corresponding voice assistant frameworks, in accordance with a common request protocol for expressing linguistic elements of received request messages,
using the received request messages re-expressed in accordance with the common request protocol, generating response messages to the request messages, and
sending the response messages to the voice assistant devices for presentation to the users, the response messages being configured to cause the voice assistant devices to provide responses corresponding to the response messages.

### Claim 32 (depends on 31)

The method of claim 31, wherein the request messages are received at an application programming interface (API) layer, and
wherein re-expressing the structured data in accordance with the common request protocol is performed by the API layer.

### Claim 33 (depends on 32)

The method of claim 32, wherein the API layer comprises a plurality of different endpoints corresponding to different native protocols of the corresponding voice assistant frameworks.

### Claim 34 (depends on 31)

The method of claim 31, wherein re-expressing the structured data in accordance with the common request protocol comprises:
detecting a first voice assistant framework associated with a first request message; and
based on the detection of the first voice assistant framework, mapping a key-value pair of the first request message to a corresponding data type; and
re-expressing the key-value pair in a common format associated with the corresponding data type.

### Claim 35 (depends on 31)

The method of claim 31, wherein the different native protocols are associated with different key-value pairs for indicating the same content.

### Claim 36 (depends on 31)

The method of claim 31, wherein a first request message of the received request messages is re-expressed as a first re-expressed message, and wherein generating the response messages to the request messages comprises:
traversing a graph to map a re-expressed feature of the first re-expressed message to a corresponding feature.

### Claim 37 (depends on 36)

The method of claim 36, wherein generating the response messages to the request messages comprises:
applying the corresponding feature to a search engine, to obtain an item of content; and
including the item of content in a first response message corresponding to the first request message.

### Claim 38 (depends on 31)

The method of claim 31, in which the response messages comprise verbal output.

### Claim 39

An apparatus comprising:
one or more processors; and
a storage storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving request messages through a communication network from voice assistant devices, each of the request messages being expressed as structured data including data corresponding to linguistic elements of a voiced input spoken by a user to a voice assistant device operating according to a voice assistant framework, each of the request messages expressing the linguistic elements of the voiced input in accordance with a native protocol defined for the corresponding voice assistant framework, the native protocols for expressing the linguistic elements of a given request message being different for different respective voice assistant frameworks, each of the request messages expressing, in accordance with the defined native protocol of the corresponding voice assistant framework, the linguistic elements of the voiced input spoken by the user to the corresponding voice assistant device,
re-expressing structured data of received request messages expressed in accordance with different native protocols of corresponding voice assistant frameworks, in accordance with a common request protocol for expressing linguistic elements of received request messages,
using the received request messages re-expressed in accordance with the common request protocol, generating response messages to the request messages, and
sending the response messages to the voice assistant devices for presentation to the users, the response messages being configured to cause the voice assistant devices to provide responses corresponding to the response messages.

### Claim 40 (depends on 39)

The apparatus of claim 39, wherein the request messages are received at an application programming interface (API) layer, and
wherein re-expressing the structured data in accordance with the common request protocol is performed by the API layer.

### Claim 41 (depends on 40)

The apparatus of claim 40, wherein the API layer comprises a plurality of different endpoints corresponding to different native protocols of the corresponding voice assistant frameworks.

### Claim 42 (depends on 39)

The apparatus of claim 39, wherein re-expressing the structured data in accordance with the common request protocol comprises:
detecting a first voice assistant framework associated with a first request message; and
based on the detection of the first voice assistant framework, mapping a key-value pair of the first request message to a corresponding data type; and
re-expressing the key-value pair in a common format associated with the corresponding data type.

### Claim 43 (depends on 39)

The apparatus of claim 39, wherein the different native protocols are associated with different key-value pairs for indicating the same content.

### Claim 44 (depends on 39)

The apparatus of claim 39, wherein a first request message of the received request messages is re-expressed as a first re-expressed message, and wherein generating the response messages to the request messages comprises:
traversing a graph to map a re-expressed feature of the first re-expressed message to a corresponding feature.

### Claim 45 (depends on 44)

The apparatus of claim 44, wherein generating the response messages to the request messages comprises:
applying the corresponding feature to a search engine, to obtain an item of content; and
including the item of content in a first response message corresponding to the first request message.

### Claim 46 (depends on 39)

The apparatus of claim 39, in which the response messages comprise verbal output.

### Claim 47

A non-transitory storage storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving request messages through a communication network from voice assistant devices, each of the request messages being expressed as structured data including data corresponding to linguistic elements of a voiced input spoken by a user to a voice assistant device operating according to a voice assistant framework, each of the request messages expressing the linguistic elements of the voiced input in accordance with a native protocol defined for the corresponding voice assistant framework, the native protocols for expressing the linguistic elements of a given request message being different for different respective voice assistant frameworks, each of the request messages expressing, in accordance with the defined native protocol of the corresponding voice assistant framework, the linguistic elements of the voiced input spoken by the user to the corresponding voice assistant device,
re-expressing structured data of received request messages expressed in accordance with different native protocols of corresponding voice assistant frameworks, in accordance with a common request protocol for expressing linguistic elements of received request messages,
using the received request messages re-expressed in accordance with the common request protocol, generating response messages to the request messages, and
sending the response messages to the voice assistant devices for presentation to the users, the response messages being configured to cause the voice assistant devices to provide responses corresponding to the response messages.

### Claim 48 (depends on 47)

The non-transitory storage of claim 47, wherein the request messages are received at an application programming interface (API) layer, and
wherein re-expressing the structured data in accordance with the common request protocol is performed by the API layer.

### Claim 49 (depends on 48)

The non-transitory storage of claim 48, wherein the API layer comprises a plurality of different endpoints corresponding to different native protocols of the corresponding voice assistant frameworks.

### Claim 50 (depends on 47)

The non-transitory storage of claim 47, wherein a first request message of the received request messages is re-expressed as a first re-expressed message, and wherein generating the response messages to the request messages comprises:
traversing a graph to map a re-expressed feature of the first re-expressed message to a corresponding feature.
