# US 2023/0053765 A1 · Speech Control Method and Apparatus, Server, Terminal Device, and Storage Medium

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

- Number: US 2023/0053765 A1
- Document ID: US20230053765A1
- Status: Published application
- Kind: A1
- Application number: 17/789,873
- Filed: 2020-10-30
- Published: 2023-02-23
- Earliest claimed: 2019-12-31
- Assignees: Huawei Technologies Co., Ltd.
- Applicants: Huawei Technologies Co., Ltd.
- Inventors: Xionghui He; Wei Yang; Jianhui Zhou
- Web page: https://patentgrep.com/patent/US20230053765A1

## CPC

- G06F 40/30: Semantic analysis
- G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning}
- G06F 40/35: Discourse or dialogue representation
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- H04N 21/4131: {home appliance, e.g. lighting, air conditioning system, metering devices (home automation data switching networks exchanging configuration information on appliance services H04L12/2807)}
- H04N 21/42204: {User interfaces specially adapted for controlling a client device through a remote control device; Remote control devices therefor (constructive details of casings for the remote control device H01H9/0235; user interfaces for controlling a tuning device of a television receiver through a remote control H03J9/00; remote control of peripheral devices connected to a television receiver through the remote control device of the television receiver H04B1/205)}
- H04N 21/436: Interfacing a local distribution network, e.g. communicating with another STB {or one or more peripheral devices} inside the home
- H04N 21/6547: comprising parameters, e.g. for client setup
- G10L 2015/223: {Execution procedure of a spoken command}
- H04N 21/42203: {sound input device, e.g. microphone}
- 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
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A speech control method includes: receiving a speech instruction recognition result sent by a first terminal; performing semantic processing on the speech instruction recognition result to obtain operation information, where the operation information includes a first semantic instruction and a second semantic instruction; sending the first semantic instruction and the second semantic instruction to the first terminal, where the first semantic instruction is used to instruct the first terminal to send the second semantic instruction to a second terminal; and receiving an execution command fed back by the second terminal after the second terminal recognizes the second semantic instruction, and sending, according to the execution command, service logic corresponding to the second semantic instruction to the second terminal.

## Claims

### Claim at position 1

-19. (canceled)

### Claim 20

A speech control method, comprising:
receiving a speech instruction recognition result from a first terminal;
performing semantic processing on the speech instruction recognition result to obtain operation information that comprises a first semantic instruction and a second semantic instruction;
sending the first semantic instruction and the second semantic instruction to the first terminal, wherein the first semantic instruction instructs the first terminal to send the second semantic instruction to a second terminal;
receiving an execution command from the second terminal after the second terminal recognizes the second semantic instruction; and
sending, according to the execution command, service logic corresponding to the second semantic instruction to the second terminal.

### Claim 21 (depends on 20)

The speech control method of claim 20, wherein sending the first semantic instruction and the second semantic instruction to the first terminal comprises sending the first semantic instruction and the second semantic instruction to the first terminal in a semantic representation form.

### Claim 22 (depends on 20)

The speech control method of claim 20, wherein the speech control method is performed by a server.

### Claim 23 (depends on 20)

The speech control method of claim 20, wherein performing the semantic processing comprises:
recognizing the speech instruction recognition result to obtain a target intent and a target sub-intent of the speech instruction recognition result;
pre-verifying the target sub-intent based on the target intent to obtain response logic of the target intent and a pre-run result of the target sub-intent;
using the response logic as the first semantic instruction; and
using the target sub-intent and the pre-run result as the second semantic instruction.

### Claim 24 (depends on 23)

The speech control method of claim 23, wherein sending the service logic to the second terminal comprises:
parsing the pre-run result according to the execution command to obtain a parsed pre-run result;
invoking the service logic based on the parsed pre-run result; and
sending the service logic to the second terminal in a semantic representation form.

### Claim 25 (depends on 23)

The speech control method of claim 23, wherein the speech instruction recognition result is text information that corresponds to a speech instruction of a user and that is based on speech recognition on audio information of the speech instruction.

### Claim 26 (depends on 25)

The speech control method of claim 25, wherein the target intent corresponds to a first portion of the text information and the target sub-intent corresponds to a second portion of the text information.

### Claim 27 (depends on 26)

The speech control method of claim 26, wherein the target sub-intent identifies a target device, and wherein the second terminal is the target device.

### Claim 28 (depends on 23)

The speech control method of claim 23, wherein the target intent corresponds to an operation to be performed by the first terminal.

### Claim 29 (depends on 28)

The speech control method of claim 28, wherein the target sub-intent corresponds to an operation to be performed to control a target device, and wherein the second terminal is the target device.

### Claim 30 (depends on 28)

The speech control method of claim 28, wherein the target intent corresponds to a switching intent.

### Claim 31

A server, comprising:
a memory configured to store instructions; and
a processor coupled to the memory and configured to execute the instructions to cause the server to:
receive a speech instruction recognition result from a first terminal;
perform semantic processing on the speech instruction recognition result to obtain operation information that comprises a first semantic instruction and a second semantic instruction;
send the first semantic instruction and the second semantic instruction to the first terminal, wherein the first semantic instruction instructs the first terminal to send the second semantic instruction to a second terminal;
receive an execution command from the second terminal after the second terminal recognizes the second semantic instruction, and
send, according to the execution command, service logic corresponding to the second semantic instruction to the second terminal.

### Claim 32 (depends on 31)

The server of claim 31, wherein when executed by the processor, the instructions cause the server to send the first semantic instruction and the second semantic instruction to the first terminal by causing the server to send the first semantic instruction and the second semantic instruction to the first terminal in a semantic representation form.

### Claim 33 (depends on 31)

The server of claim 31, wherein when executed by the processor, the instructions cause the server to perform the semantic processing by causing the server to:
recognize the speech instruction recognition result to obtain a target intent and a target sub-intent of the speech instruction recognition result;
pre-verify the target sub-intent based on the target intent to obtain response logic of the target intent and a pre-run result of the target sub-intent;
use the response logic as the first semantic instruction; and
use the target sub-intent and the pre-run result as the second semantic instruction.

### Claim 34 (depends on 33)

The server of claim 33, wherein when executed by the processor, the instructions cause the server to send the service logic to the second terminal by causing the server to:
parse the pre-run result according to the execution command to obtain a parsed pre-run result;
invoke the service logic based on the parsed pre-run result; and
send the service logic to the second terminal in a semantic representation form.

### Claim 35

A computer program product comprising instructions that are stored on a computer-readable medium and that, when executed by a processor, cause a server to:
receive a speech instruction recognition result from a first terminal;
perform semantic processing on the speech instruction recognition result to obtain operation information that comprises a first semantic instruction and a second semantic instruction;
send the first semantic instruction and the second semantic instruction to the first terminal, wherein the first semantic instruction instructs the first terminal to send the second semantic instruction to a second terminal;
receive an execution command from the second terminal after the second terminal recognizes the second semantic instruction; and
send, according to the execution command, service logic corresponding to the second semantic instruction to the second terminal.

### Claim 36 (depends on 35)

The computer program product of claim 35, wherein sending the first semantic instruction and the second semantic instruction to the first terminal comprises sending the first semantic instruction and the second semantic instruction to the first terminal in a semantic representation form.

### Claim 37 (depends on 35)

The computer program product of claim 35, wherein when executed by the processor, the instructions cause the server to perform the semantic processing by causing the server to:
recognize the speech instruction recognition result to obtain a target intent and a target sub-intent of the speech instruction recognition result;
pre-verify the target sub-intent based on the target intent to obtain response logic of the target intent and a pre-run result of the target sub-intent;
use the response logic as the first semantic instruction; and
use the target sub-intent and the pre-run result as the second semantic instruction.

### Claim 38 (depends on 37)

The computer program product of claim 37, wherein when executed by the processor, the instructions cause the server to send the service logic to the second terminal by causing the server to:
parse the pre-run result according to the execution command to obtain a parsed pre-run result;
invoke the service logic based on the parsed pre-run result; and
send the service logic to the second terminal in a semantic representation form.

### Claim 39 (depends on 37)

The computer program product of claim 37, wherein the speech instruction recognition result is text information that corresponds to a speech instruction of a user and that is based on speech recognition on audio information of the speech instruction.