# US 2019/0244608 A1 · Method and Apparatus To Provide Comprehensive Smart Assistant Services

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

- Number: US 2019/0244608 A1
- Document ID: US20190244608A1
- Status: Published application
- Kind: A1
- Application number: 16/133,899
- Filed: 2018-09-18
- Published: 2019-08-08
- Earliest claimed: 2018-02-08
- Assignees: Computime, Ltd.
- Applicants: Computime, Ltd.
- Inventors: Hung Bun Choi; Kai Nang Pang; Yau Wai Ng; Chi Chung Liu; Tsz Kin Lee
- Web page: https://patentgrep.com/patent/US20190244608A1

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/08: Speech classification or search
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 2015/088: {Word spotting}
- 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

## Abstract

An apparatus supports smart assistant services with a plurality of smart service providers. The apparatus includes an audio device that receives a speech signal having a user utterance, captures the user utterance when the user utterance includes a user wake word, and sends the captured utterance to a backend computing device. The backend computing device replaces the user wake word with specific wake words associated with different smart service providers. The processed utterances are then sent to selected smart service providers. The backend computing device subsequently constructs feedback to the user utterance based on voice responses from the different smart service providers. The backend computing device then passes a digital representation of the feedback to the audio device, and the audio device converts the digital representation to an audio reply to the user utterance.

## Claims

### Claim 1

An apparatus supporting smart assistant services with at least one smart service provider, the apparatus comprising:
an audio device configured to receiver a speech signal comprising a user utterance and capturing the user utterance when the user utterance includes a user wake word; and
a backend computing device configured to receive the captured user utterance from the audio device, replace the user wake word with a first specific wake word in the user utterance to form a first processed utterance, and send the first processed utterance to a first smart service provider, wherein the user wake word and the first specific wake word are different and wherein the at least one smart service provider includes the first smart service provider.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein:
the at least one smart service provider includes a second smart service provider;
the backend computing device configured to replace the user wake word with a second specific wake word in the user utterance to form a second processed utterance, and to send the second processed utterance to the second smart service provider; and
wherein the second specific wake word and the first specific wake word are different.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein:
the backend computing device configured to obtain first and second voice responses from the first and second smart service providers, respectively;
the backend computing device configured to construct feedback to the user utterance based on the first and second voice responses from the first and second smart service providers;
the backend computing device configured to pass a digital representation of the feedback to the audio device; and
the audio device configured to convert the digital representation to an audio reply to the user utterance.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the backend computing device constructs the feedback by selecting one of the voice responses from the first and second smart service providers.

### Claim 5 (depends on 3)

The apparatus of claim 3, wherein the backend computing device constructs the feedback by combining the first and second voice responses from the first and second smart service providers.

### Claim 6 (depends on 3)

The apparatus of claim 3, wherein the backend computing device is configured to convert the user utterance into text data and sends the text data to a search engine.

### Claim 7 (depends on 6)

The apparatus of claim 6, wherein the backend computing device is configured to receive a text response from the search engine and combine the feedback with the text response.

### Claim 8 (depends on 4)

The apparatus of claim 4, wherein the selecting includes:
identifying a characteristic of a user; and
matching the selected smart service provider with the identified characteristic of the user.

### Claim 9

A method for supporting smart assistant services with a smart service provider, the method comprising:
receiving a speech signal comprising a user utterance;
capturing the user utterance when the user utterance includes a user wake word;
identifying a first smart service provider from a plurality of service providers;
replacing the user wake word with a first specific wake word in the user utterance to form a first processed utterance, wherein the first specific wake word is specific to the first smart service provider and wherein the user wake word and the specific wake word are different;
sending the first processed utterance to the first smart service provider;
obtaining a first voice response from the first smart service provider;
in response to the obtaining, constructing feedback to the user utterance; and
generating an audio reply to the user utterance from the feedback.

### Claim 10 (depends on 9)

The method of claim 9 further comprising:
identifying a second smart service provider from the plurality of service providers;
replacing the user wake word with a second specific wake word in the user utterance to form a second processed utterance, wherein the second specific wake word is specific to the second smart service provider and wherein the first and second specific wake words are different;
sending the second processed utterance to the second smart service provider; and
obtaining a second voice response from the second smart service provider.

### Claim 11 (depends on 10)

The method of claim 10 further comprising:
combining the second voice response with the first voice response to construct the feedback.

### Claim 12 (depends on 10)

The method of claim 10 further comprising:
selecting only one of the voice responses from the first and second smart service providers to construct the feedback.

### Claim 13 (depends on 12)

The method of claim 12, wherein the selecting includes:
identifying a characteristic of a user; and
matching the selected smart service provider with the identified characteristic of the user.

### Claim 14 (depends on 13)

The method of claim 13, wherein the characteristic is indicative of a language of the user.

### Claim 15 (depends on 12)

The method of claim 12, wherein the selecting includes:
when the first smart service provider responds before the second smart service provider, selecting the first voice response to construct the feedback.

### Claim 16 (depends on 9)

The method of claim 9 further comprising:
converting the user utterance to a text message;
extracting at least one keyword from the text message;
conducting a web-based search for the at least one keyword;
obtaining results of the web-based search; and
combining the results of the web-based search with the first voice response from the first smart service provider to form a complete search result.

### Claim 17 (depends on 16)

The method of claim 16 further comprising:
converting the complete search result into voice feedback to a user.

### Claim 18 (depends on 9)

The method of claim 9, wherein the user wake word is specific a first user of a plurality of users.

### Claim 19 (depends on 10)

The method of claim 10 further comprising:
obtaining accuracy metrics for the first and second voice responses; and
discarding one the first and second voice responses from the first and second smart service providers, respectively, based on the accuracy metrics.

### Claim 20 (depends on 19)

The method of claim 19 further comprising:
storing the accuracy metrics; and
blocking subsequent requests for a user to said one of the first and second smart service providers based on the accuracy metrics.

### Claim 21

An apparatus supporting smart assistant services with at least one smart service provider, the apparatus comprising:
an audio device configured to receiver a speech signal comprising a user utterance and capturing the user utterance when a user trigger is detected; and
a backend computing device configured to receive the captured user utterance from the audio device, include a specific wake word in the user utterance to form a processed utterance, and send the processed utterance to a smart service provider.

### Claim 22 (depends on 21)

An apparatus of claim 21, wherein the user trigger comprises a non-verbal component.
