# US 2019/0244602 A1 · Smart network device and method thereof

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

- Number: US 2019/0244602 A1
- Document ID: US20190244602A1
- Status: Published application
- Kind: A1
- Application number: 16/191,588
- Filed: 2018-11-15
- Published: 2019-08-08
- Earliest claimed: 2018-02-06
- Assignees: Wistron Neweb Corp.
- Applicants: Wistron Neweb Corporation
- Inventors: YEE-LEE SHYONG; CHEN-CHAO CHANG; YING-HUI LIANG
- Web page: https://patentgrep.com/patent/US20190244602A1

## CPC

- G10L 15/08: Speech classification or search
- G06F 16/9017: {using directory or table look-up (use of a directory or look-up table in file systems G06F16/13)}
- G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit
- G10L 15/28: Constructional details of speech recognition systems
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 15/32: Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
- G10L 2015/088: {Word spotting}
- 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 network device is connected to user device and includes a processor and a memory storing executable code executed by the processor. The network device is configured to receive first keyword data and speech data followed by the first keyword data; determine whether the first keyword data corresponds to a first keyword; in response to determining that the first keyword data corresponds to the first keyword, recognize word information from the speech data to generate at least one word recognition result; send the at least one word recognition result through a first communication path to a first network; and in response to determining that the first keyword data corresponds to a second keyword, stop recognizing the word information from the speech data followed by the first keyword data, and send the speech data through a second communication path to the first user device.

## Claims

### Claim 1

A network device, connected to a first user device and comprising a processor and a memory storing computer executable code executed by the processor, and the network device is configured to:
receive first keyword data and speech data followed by the first keyword data;
determine whether the first keyword data corresponds to a first keyword;
in response to determining that the first keyword data corresponds to the first keyword, recognize word information from the speech data to generate at least one word recognition result;
send the at least one word recognition result through a first communication path to a first network; and
in response to determining that the first keyword data corresponds to a second keyword, stop recognizing the word information from the speech data followed by the first keyword data, and send the speech data through a second communication path to the first user device.

### Claim 2 (depends on 1)

The network device according to claim 1, wherein the network device is further configured to:
receive device information of the user device; and
establish a look-up table (LUT) including a corresponding relationship between the second keyword and first user device availability according to the device information.

### Claim 3 (depends on 2)

The network device according to claim 2, wherein the device information of the first user device includes a type of a voice interaction application (VIA) or an operating system (OS).

### Claim 4 (depends on 2)

The network device according to claim 2, wherein the first keyword corresponds to a first voice interaction application (VIA) or a first operating system (OS) and the second keyword corresponds to a second VIA or a second OS, wherein the first VIA or the first OS is installed in the network device and the second VIA or the second OS is installed in the first user device.

### Claim 5 (depends on 4)

The network device according to claim 4, wherein the LUT further includes another corresponding relationship between the first keyword and network device availability.

### Claim 6 (depends on 2)

The network device according to claim 2, wherein the second communication path is connected to a second network via the first user device, and databases of the first network and the second network are different.

### Claim 7 (depends on 1)

The network device according to claim 1, further comprising a first communication circuit forming the first communication path and a second communication circuit forming the second communication path, wherein an operating power of the second communication circuit is lower than the operating power of the first communication circuit.

### Claim 8 (depends on 1)

The network device according to claim 1, wherein the network device is connected to a second user device and the network device is further configured to:
receive second keyword data when the first keyword data corresponds to the second keyword;
determine whether the second keyword data corresponds to a third keyword; and
in response to determining that the first keyword data corresponds to the second keyword and the second keyword data corresponds to the third keyword, implement the second user device to recognize the word information from the speech data to generate the at least one word recognition result, wherein the second keyword and the third keyword correspond to the second user device.

### Claim 9

A method for determining a communication path for a network device, the network device being connected to a first user device, the method comprising:
receiving first keyword data and speech data followed by the first keyword data;
determining whether the first keyword data corresponds to a first keyword by a processor;
in response to determining that the first keyword data corresponds to the first keyword, recognizing word information from the speech data to generate at least one word recognition result;
sending the at least one word recognition result through a first communication path to a first network; and
in response to determining that the first keyword data corresponds to a second keyword, stopping recognition of the word information from the speech data, and sending the speech data through a second communication path to the first user device.

### Claim 10 (depends on 9)

The method for determining the communication path for the network device according to claim 9, further comprising:
receiving device information of the user device; and
establishing a look-up table (LUT) including a corresponding relationship between the second keyword and first user device availability according to the device information by the processor.

### Claim 11 (depends on 10)

The method for determining the communication path for the network device according to claim 10, wherein the device information of the first user device includes a voice interaction application (VIA) or an operating system (OS).

### Claim 12 (depends on 10)

The method for determining the communication path for the network device according to claim 10, wherein the first keyword corresponds to a first VIA or a first OS and the second keyword corresponds to a second VIA or a second OS, wherein the first VIA or the first OS is installed in the network device and the second VIA or the second OS is installed in the first user device.

### Claim 13 (depends on 12)

The method for determining the communication path for the network device according to claim 12, wherein the LUT further includes another corresponding relationship between the first keyword and network device availability.

### Claim 14 (depends on 10)

The method for determining the communication path for the network device according to claim 10, wherein the second communication path is connected to a second network via the first user device, and databases of the first network and the second network are different.

### Claim 15 (depends on 9)

The method for determining the communication path for the network device according to claim 9, further comprising a first communication circuit forming the first communication path and a second communication circuit forming the second communication path, wherein an operating power of the second communication circuit is lower than the operating power of the first communication circuit.

### Claim 16 (depends on 9)

The method for determining the communication path for the network device according to claim 9, wherein the network device is connected to a second user device, the method further comprising:
receiving second keyword data when the first keyword data corresponds to the second keyword;
determining whether the second keyword data corresponds to a third keyword; and
in response to determining that the first keyword data corresponds to the second keyword and the second keyword data corresponds to the third keyword, implementing the second user device to recognize the word information from the speech data to generate the at least one word recognition result, wherein the second keyword and the third keyword correspond to the second user device.

### Claim 17 (depends on 9)

The method for determining the communication path for the network device according to claim 9, further comprising:
sending a command or the first keyword data to enable a voice interaction application (VIA) of the first user device in response to determining that the first keyword data corresponds to the second keyword.
