# US 10,943,589 B2 · 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 10,943,589 B2
- Document ID: US10943589B2
- Status: Granted
- Kind: B2
- Application number: 16/353,977
- Filed: 2019-03-14
- Published: 2019-12-05
- Granted: 2021-03-09
- 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/US10943589B2

## CPC

- 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 16/9038: Presentation of query results
- G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit
- G10L 15/28: Constructional details of speech recognition systems
- G10L 2015/221: {Announcement of recognition results}
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L 2015/225: {Feedback of the input speech}
- 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

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 1

A computer-implemented method comprising
receiving through a communication network from voice assistant devices that conform to one or more different voice assistant frameworks, requests for service based on speech of end-users, the speech of the end users expressing intents,
determining responses to the received requests, the responses configured to be sent through the communication network to the voice assistant devices to cause them to respond to the respective end users,
evaluating measures of the success of the determinations of the responses,
based on the relative measures of success of the responses enabling a user through a user interface to manage subsequent responses to requests for service,
in which evaluating measures of the success comprises evaluating success of the responses relative to the respective voice assistant frameworks of the voice assistant devices to which the responses are to be sent.

### Claim 2 (depends on 1)

The method of claim 1 in which the voice assistant devices from which the requests are received conform to two or more different voice assistant frameworks.

### Claim 3 (depends on 1)

The method of claim 1 comprising
presenting suggested responses to the user through the user interface based on the evaluated measures of success and enabling the user to select responses to be sent to the voice assistant devices based on the suggested responses.

### Claim 4 (depends on 1)

The method of claim 1 in which evaluating measures of the success comprises evaluating success of items of content carried by the responses across two or more of the different voice assistant frameworks.

### Claim 5 (depends on 1)

The method of claim 1 in which evaluating measures of the success comprises evaluating success of the responses relative to two or more different voice applications configured to receive the requests and determine the responses.

### Claim 6 (depends on 1)

The method of claim 1 comprising managing items of content to be carried in subsequent responses based on the measures of success.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1 in which the responses include items of content, the items of content included in a given one of the responses being selected from alternative possible items of content, the selection of the items of content to be included in the given response being based on a context of the expressed intent of an end user.

### Claim 8 (depends on 1)

The method of claim 1 in which the voice assistant devices from which the requests are received conform to two or more different voice assistant frameworks.

### Claim 9 (depends on 1)

The method of claim 1 in which one of the voice assistant frameworks comprises a chatbot framework.

### Claim 10 (depends on 1)

The method of claim 1 in which the context of the expressed intent of the end user comprises a geographic location of the voice assistant device to which the response is to be sent.

### Claim 11 (depends on 1)

The method of claim 1 in which the context of the expressed intent of the end user comprises demographic characteristics of the end user.

### Claim 12 (depends on 11)

The method of claim 11 in which the demographic characteristics comprise age.

### Claim 13 (depends on 11)

The method of claim 11 in which the demographic characteristics comprise linguistic characteristics inferred from a geographic location of the voice assistant device to which the responses to be sent or inferred from characteristics of words contained in the received requests.

### Claim 14 (depends on 13)

The method of claim 13 in which the linguistic characteristics comprise an accent.

### Claim 15 (depends on 13)

The method of claim 13 in which the linguistic characteristics comprise local colloquialisms or local references.

### Claim 16 (depends on 11)

The method of claim 11 in which the demographic characteristics comprise gender.

### Claim 17 (depends on 11)

The method of claim 11 comprising end user preferences based on which the items of content to be included in the given response can be selected.

### Claim 18 (depends on 1)

The method of claim 1 comprising
presenting a user interface for development of voice applications,
configuring the user interface to enable creation of voice applications for processing received requests and for generating corresponding responses for the voice assistant devices to present to end users,
maintaining modules of features to which the requests can be matched to generate the responses,
including in each of the modules, a set of features that correspond to contexts in which the responses will be presented to the end users,
the maintaining of the modules comprising (a) maintaining standard modules for corresponding contexts, and (b) enabling generation and maintenance of custom modules of features to which the requests can be matched to generate custom responses for the voice assistant devices, and
exposing the modules through the user interface.

### Claim 19 (depends on 18)

The method of claim 18 comprising
maintaining items of content to be used with the features in generating the responses,
the maintaining of the items of content comprising (a) maintaining standard items of content, and (b) enabling generation and maintenance of custom items of content to be used with the features to generate custom responses for the voice assistant devices.

### Claim 20 (depends on 18)

The method of claim 18 in which the contexts relate to products or services in a defined market segment.

### Claim 21 (depends on 18)

The method of claim 18 in which the contexts relate to demographics of target groups of end users.

### Claim 22 (depends on 18)

The method of claim 18 in which the contexts relate to capabilities of the voice assistant devices.

### Claim 23 (depends on 18)

The method of claim 18 in which the contexts relate to types of content items to be used with the features in generating the responses.
