WO2017118037A1 - Voice-triggering method for smart device and smart device - Google Patents

Abstract

A voice-triggering method for smart devices and a smart device, comprising: acquiring a valid voice within a preset voice frequency range, converting the voice into a valid voice clip and triggering a corresponding function of the smart device according to the vocal characteristics of the valid voice clip. The embodiment of the present invention, through its ability to identify vocal characteristics, eliminates the need for a user to execute voice control or manual triggering, enabling convenient voice control of smart devices and improving user experience.

Description

Sound triggering method and intelligent device of smart device Technical field

This document relates to, but is not limited to, the field of communications, and in particular, to a sound triggering method and a smart device of a smart device.

Background technique

For devices with smart voice recognition, such as smart phones, smart speakers, smart home devices, etc., in order to receive the user's voice commands, there are usually two ways: First, the microphone, audio channel, and recognition engine are always working. The status is to receive the user voice command input at any time. Second, the device is normally in a dormant state, and the voice recognition function is triggered/activated by a physical switch such as a button, a touch or a gesture, and then the user voice command input can be received.

In these usage scenarios, the device is always running to receive the user's voice command, and the voice control is implemented by the voice command, or the user needs to actively initiate the wake-up action to receive the user's voice command, and then implement voice control through the voice command. That is, the current smart device can only achieve the voice recognition function by sacrificing power consumption or by the user making a wake-up action, resulting in low efficiency of voice control processing and affecting the user experience.

Summary of the invention

The following is an overview of the topics detailed in this document. This Summary is not intended to limit the scope of the claims.

The embodiment of the invention provides a sound triggering method and an intelligent device of a smart device, which can improve the efficiency of using the voice control function and the user experience.

According to an aspect of the embodiments of the present invention, a sound triggering method for a smart device is provided, including:

Collect sounds within the set sound frequency range;

Converting the sound into a valid sound sheet;

The corresponding function of the smart device is triggered according to the sound characteristics of the active sound film.

Optionally, the collecting the sounds within the set sound frequency range includes:

Collecting sounds in the set sound frequency range by a digital sound pressure sensor to obtain a sound signal stream of sound output;

Converting the sound into a valid sound piece includes:

The sound signal stream is buffered in units of set time intervals to form the effective sound sheet.

Optionally, the triggering the corresponding function of the smart device according to the sound feature of the effective sound piece includes:

Determining a current scene corresponding to the sound feature according to the sound feature of the effective sound sheet;

Trigger the corresponding function of the smart device according to the current scene.

Optionally, the determining the current scene corresponding to the sound feature includes:

A corresponding current scene is determined according to a change trend of the amplitude value and/or the amplitude of the effective sound piece.

Optionally, determining the corresponding current scene according to the change trend of the amplitude value and/or the amplitude of the effective sound piece includes:

Determining an amplitude value of the effective sound piece, determining that the current scene is when the sum of the amplitude values of all the valid sound pieces is greater than the first set threshold or the sum of the amplitude values of all the valid sound pieces exceeds the second set threshold First scene;

The triggering the corresponding function of the smart device according to the current scenario includes:

When the current scene is the first scene, the smart device is woken up or the screen is illuminated.

Optionally, the determining, according to a change trend of the amplitude value and/or the amplitude of the effective sound piece, determining a corresponding current scene, including:

Determining an amplitude value of the effective sound piece, when an average value of amplitude values of all the valid sound pieces is less than or equal to a first set threshold or a sum of amplitude values of all the valid sound pieces is less than or equal to a second set threshold Determining a trend of the amplitude of the effective sound piece, and determining that the current scene is the second scene when the change trend is from small to large;

The triggering the corresponding function of the smart device according to the current scenario includes:

When the current scenario is the second scenario, the smart device is switched from the sleep state to the working state.

Optionally, the determining, according to a change trend of the amplitude value and/or the amplitude of the effective sound piece, determining a corresponding current scene, including:

Determining an amplitude value of the effective sound piece, when an average value of amplitude values of all the valid sound pieces is less than or equal to a first set threshold or a sum of amplitude values of all the valid sound pieces is less than or equal to a second set threshold Determining a trend of the amplitude of the effective sound piece, and determining the current scene as the third scene when the change trend is greater than the hour;

The triggering the corresponding function of the smart device according to the current scenario includes:

When the current scenario is the third scenario, the smart device is switched to the sleep state.

The embodiment of the invention further provides a smart device, including:

a collecting unit configured to collect sounds within a set sound frequency range;

The processing unit is configured to convert the sound into a valid sound piece and trigger a corresponding function of the smart device according to the sound characteristics of the effective sound piece.

Optionally, the collecting unit is configured to:

The sound in the set sound frequency range is collected by the digital sound pressure sensor to obtain a sound signal stream of the sound output;

Converting the sound into a valid sound sheet by the processing unit includes:

The sound signal stream is buffered in units of set time intervals to form the effective sound sheet.

Optionally, the processing unit triggers a corresponding function of the smart device according to the sound feature of the effective sound piece, including:

Determining a current scene corresponding to the sound feature according to the sound characteristics of the effective sound sheet;

Trigger the corresponding function of the smart device according to the current scene.

Optionally, the processing unit determines, according to the sound feature of the effective sound piece, the current scene corresponding to the sound feature, including:

The corresponding current scene is determined according to the trend of the amplitude value and/or the amplitude of the effective sound piece.

Optionally, the processing unit determines, according to a change trend of the amplitude value and/or the amplitude of the effective sound piece, the corresponding current scene, including:

Determining an amplitude value of the effective sound piece, determining that the current scene is when the sum of the amplitude values of all the valid sound pieces is greater than the first set threshold or the sum of the amplitude values of all the valid sound pieces exceeds the second set threshold First scene;

The processing unit triggers corresponding functions of the smart device according to the current scenario, including:

When the current scene is the first scene, the smart device is woken up or the screen is illuminated.

Optionally, the processing unit determines, according to a change trend of the amplitude value and/or the amplitude of the effective sound piece, the corresponding current scene, including:

Determining an amplitude value of the effective sound piece, when an average value of amplitude values of all the valid sound pieces is less than or equal to a first set threshold or a sum of amplitude values of all the valid sound pieces is less than or equal to a second set threshold Determining a trend of the amplitude of the effective sound piece, and determining that the current scene is the second scene when the change trend is from small to large;

The processing unit triggers corresponding functions of the smart device according to the current scenario, including:

When the current scenario is the second scenario, the smart device is switched from the sleep state to the working state.

Optionally, the processing unit determines, according to a change trend of the amplitude value and/or the amplitude of the effective sound piece, the corresponding current scene, including:

Determining an amplitude value of the effective sound piece, when an average value of amplitude values of all the valid sound pieces is less than or equal to a first set threshold or a sum of amplitude values of all the valid sound pieces is less than or equal to a second set threshold Determining a trend of the amplitude of the effective sound piece, and determining the current scene as the third scene when the change trend is greater than the hour;

The processing unit triggers corresponding functions of the smart device according to the current scenario, including:

When the current scenario is the third scenario, the smart device is switched to the sleep state.

Compared with the related art, the technical solution provided by the embodiment of the present invention includes: collecting sounds in a set sound frequency range, converting the sound into an effective sound piece, and triggering a corresponding function of the smart device according to the sound characteristics of the effective sound piece. When the voice feature can be recognized, the embodiment of the invention does not require the user to perform voice control or manual triggering, and the voice control is conveniently implemented, thereby improving the user's use.

Other aspects will be apparent upon reading and understanding the drawings and detailed description.

BRIEF abstract

FIG. 1 is a flowchart of a sound triggering method of a smart device according to an embodiment of the present invention;

2 is a schematic diagram of waveforms approximately restored by a sound film according to an embodiment of the present invention;

3 is a flowchart of a method for triggering a sound of a room lighting according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a smart device according to an embodiment of the present invention.

Embodiments of the invention

Embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be noted that, in the case of no conflict, the features in the embodiments and the embodiments in the present application may be arbitrarily combined with each other.

As shown in FIG. 1 , a sound triggering method of a smart device according to an embodiment of the present invention includes:

Step 101: Collect sounds in a range of set sound frequencies;

Step 102: Convert the sound into a valid sound film;

Step 103: Trigger a corresponding function of the smart device according to the sound feature of the effective sound piece.

By analyzing the sound characteristics of the collected sounds, the corresponding functions can be triggered. When the sound features can be recognized, the user does not need to perform voice triggering or manual triggering, which is convenient for the user to use.

The sound triggering method of the smart device can be implemented by a system including a digital sound pressure sensor circuit, a sound data processing unit and a trigger control unit, wherein the digital sound pressure sensor circuit performs acoustic-electrical conversion, and outputs a digital signal flow reflecting the sound waveform at a certain sampling rate. The sound data processing unit buffers, analyzes the sound data picked up by the digital sound pressure sensor circuit and outputs the processing result; the trigger control unit performs the trigger control action according to the processing result. The system can be embedded in the main system of the device as part of the whole system, or it can work as a slave system and interface with the main system of the device through the trigger control unit.

Optionally, collect sounds within the set sound frequency range, including:

The sound in the set sound frequency range is collected by the digital sound pressure sensor to obtain a sound signal stream of the sound output;

Optionally, converting the sound into a valid sound film, including:

The sound signal stream is buffered in units of set time intervals to form a valid sound sheet.

The step 101 can be completed by the digital sound pressure sensor circuit, and the portion of the sound feature determined in steps 102 and 103 can be completed by the sound data processing unit, and the portion of the corresponding function that triggers the smart device in step 103 is completed by the trigger control unit.

In the embodiment of the present invention, in order to improve the accuracy of the scene recognition, the digital sound pressure sensor circuit can be adjusted to a specific frequency response range, and only a specific sound is picked up. For example, the frequency response range of the embodiment can be 82 Hz to 1100 Hz. , that is, the human voice, the sound other than the human voice is filtered out, and the digital sound pressure sensor circuit outputs the sound data in a digital form. For example, the pulse code modulation (PCM) code stream can be used in this embodiment;

In step 102, the sound data processing unit continuously receives the PCM code stream, and buffers the sound data in units of a certain time interval. For example, in the embodiment, a 150 millisecond interval may be used, and for a voice having a frequency range of 150 Hz to 600 Hz. The waveform of 22.5 to 90 cycles can be approximately reduced, that is, each discrete sound slice formed includes a sound waveform of 22.5 to 90 cycles; FIG. 2 is a waveform diagram approximately restored by the sound slice, and the horizontal axis For time, in milliseconds, slice[i] is a valid sound slice formed by a 150 millisecond interval.

In order to facilitate the use of the user, the current scene may be determined according to the sound feature, and then the corresponding function of the smart device is triggered according to the current scene. At this step, in step 103, the corresponding function of the smart device is triggered according to the sound feature of the effective sound piece, including :

Determining a current scene corresponding to the sound feature according to the sound characteristics of the effective sound sheet;

Trigger the corresponding function of the smart device according to the current scene.

Optionally, in step 103, determining a current scene corresponding to the sound feature according to the sound feature of the effective sound piece, including:

The corresponding current scene is determined according to the trend of the amplitude value and/or the amplitude of the effective sound piece.

Optionally, in a possible scenario, the sound around the smart device continues to be large. At this time, according to the change trend of the amplitude value and/or the amplitude of the effective sound piece, the corresponding current scene is determined, including:

The amplitude value of the effective sound piece is determined. When the average value of the amplitude values of all the effective sound pieces is greater than the first set threshold or the sum of the amplitude values of all the effective sound pieces exceeds the second set threshold, the current scene is determined to be the first scene.

Optionally, the corresponding function of the smart device is triggered according to the current scenario, including:

When the current scene is the first scene, wake up the smart device or light up the screen.

Optionally, in another possible scenario, the sound around the smart device is changed from small to large. At this time, according to the change trend of the amplitude value and/or the amplitude of the effective sound piece, the corresponding current scene is determined, including:

Determining the amplitude value of the effective sound piece, determining the amplitude of the effective sound piece when the average value of the amplitude values of all the effective sound pieces is less than or equal to the first set threshold or the sum of the amplitude values of all the effective sound pieces is less than or equal to the second set threshold The trend of change, when the trend is small and large, determine the current scene as the second scene;

Trigger the corresponding functions of the smart device according to the current scenario, including:

When the current scenario is the second scenario, the smart device is switched from the sleep state to the working state.

Optionally, in another possible scenario, the sound around the smart device is changed from large to small. At this time, according to the change trend of the amplitude value and/or the amplitude of the effective sound piece, the corresponding current scene is determined, including:

Determining the amplitude value of the effective sound piece, determining the amplitude of the effective sound piece when the average value of the amplitude values of all the effective sound pieces is less than or equal to the first set threshold or the sum of the amplitude values of all the effective sound pieces is less than or equal to the second set threshold The trend of change, when the trend is changed from large to small, determine the current scene as the third scene;

Trigger the corresponding functions of the smart device according to the current scenario, including:

When the current scene is the third scene, the smart device is switched to the sleep state.

The following example illustrates the corresponding scene identified by the sound film, and triggers the corresponding function of the smart device according to the current scene.

Suppose the valid sound slices sorted in the order of reception time are the following sequence: slice[1], slice[2],...,slice[i-1],slice[i],slice[i+1],...,slice[n ].

Embodiment 1:

When the frequency (tone) of the sound parsed from the sequence of slice[1],...,slice[i],...,slice[n] is the same (accurately, the approximation is the same after ignoring the Doppler effect), And the waveform is approximately the same within the allowable tolerance range, but the amplitude (loudness) has a tendency to gradually increase, assuming that the average or sum of the amplitudes of slice[i] is expressed as Am-slice[i], ie Am-slice[1] <Am-slice[2]<...<Am-slice[i-1]<Am-slice[i]<Am-slice[i+1]<...<Am-slice[n], then according to the loudness and the sound The principle that the square of the source distance is inversely proportional, the sound data processing unit determines that the person is relative to the device From the far and near movement, recorded as the scene sc[1];

When the scene sc[1] is recognized, a wake-up command can be issued to wake up the device and end the sleep.

Embodiment 2:

When the frequency (tone) of the sound waveform parsed from the sequence of slice[1],..., slice[i],...,slice[n] changes the same trend (accurately, the approximation is the same after ignoring the Doppler effect) And the waveform is approximately the same within the allowable tolerance range, but the amplitude (loudness) tends to decrease gradually, assuming that the average or sum of the amplitudes of slice[i] is expressed as Am-slice[i], ie Am-slice[1] ]>Am-slice[2]>...>Am-slice[i-1]>Am-slice[i]>Am-slice[i+1]>...>Am-slice[n], then according to the loudness and The principle that the square of the sound source distance is inversely proportional, the sound data processing unit determines that the person is moving from near to far with respect to the device, and records it as scene sc[2];

When the scene sc[2] is recognized, a sleep command can be issued to put the device into hibernation;

Embodiment 3:

When the Am-slice values of some consecutive valid sound slices slice[i], slice[i+1],...,slice[j](i<j) exceed the first set threshold ref1, it is recorded as scene sc [3];

When the scene sc[3] is recognized, the device can be woken up or the screen is lit.

The number of continuous sound slices and the first set threshold ref1 may be set according to experience, or may be adjusted by the user according to usage habits. For example, if the user wants to increase the sensitivity, the number of continuous sound slices may be reduced. / or reduce the first set threshold ref1.

For example, the embodiment can be applied to the lighting of the room lighting. At this time, as shown in FIG. 3, it includes:

Step 301, picking up an ambient sound, and completing acoustic-electrical conversion and digital-to-analog conversion, and outputting a sound signal stream;

Step 302: Cache the sound signal stream at a set time interval to form a plurality of effective sound slices;

Step 303: Analyze whether the amplitude (Am-slice) values of the continuous effective sound slice slice[i], slice[i+1], . . . , slice[j](i<j) exceed the first set threshold ref1, if If the Am-slice values of the continuous effective sound slices slice[i], slice[i+1], . . . , slice[j](i<j) exceed the first set threshold ref1, then step 304 is performed, otherwise, the effective sound The Slice_[i], slice[i+1], ..., slice[j] (i<j) Am-slice values do not exceed the first set threshold ref1, continue to perform step 301;

Step 304: Send an instruction to the main control unit of the smart home controller, and the main control unit of the smart home controller controls the room lighting to automatically light up.

Of course, in addition to the above implementations, according to different application scenarios and requirements, these sound films can also be used to combine other different scenes and trigger corresponding functions.

The embodiment of the invention further provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute a sound triggering method of the smart device.

The embodiment of the present invention further provides a smart device, as shown in FIG. 4, including:

The collecting unit 401 is configured to collect sounds within a set sound frequency range;

The processing unit 402 is configured to convert the sound into a valid sound piece and trigger a corresponding function of the smart device according to the sound characteristics of the effective sound piece.

The collecting unit 401 may include the aforementioned digital sound pressure sensor, and the processing unit 402 may correspond to the foregoing sound data processing unit and the trigger control unit.

Optionally, the collecting unit 401 is configured to:

The sound in the set sound frequency range is collected by the digital sound pressure sensor to obtain a sound signal stream of the sound output;

The processing unit 402 converts the sound into a valid sound piece, including:

The sound signal stream is buffered in units of set time intervals to form a valid sound sheet.

In the embodiment of the present invention, the set sound frequency range may be: 82 Hz to 1100 Hz;

The set time interval can be: 150 milliseconds.

Optionally, the processing unit 402 triggers a corresponding function of the smart device according to the sound feature of the effective sound piece, including:

Determining a current scene corresponding to the sound feature according to the sound characteristics of the effective sound sheet;

Trigger the corresponding function of the smart device according to the current scene.

Optionally, the processing unit 402 determines, according to the sound feature of the effective sound piece, the sound feature corresponding Current scenario for:

The corresponding current scene is determined according to the trend of the amplitude value and/or the amplitude of the effective sound piece.

Optionally, in a possible scenario, the sound surrounding the smart device continues to be large. At this time, the processing unit 402 determines the corresponding current scene according to the change trend of the amplitude value and/or the amplitude of the effective sound piece, including:

Determining an amplitude value of the effective sound piece, determining that the current scene is the first scene when the average value of the amplitude values of all the active sound pieces is greater than the first set threshold or the sum of the amplitude values of all the valid sound pieces exceeds the second set threshold;

The processing unit 402 triggers corresponding functions of the smart device according to the current scenario, including:

When the current scene is the first scene, wake up the smart device or light up the screen.

Optionally, in another possible scenario, the sound around the smart device is changed from small to large. At this time, the processing unit 402 determines the corresponding current scene according to the change trend of the amplitude value and/or the amplitude of the effective sound piece, including :

Determining an amplitude value of the effective sound piece, when an average value of amplitude values of all the valid sound pieces is less than or equal to a first set threshold or a sum of amplitude values of all the valid sound pieces is less than or equal to a second set threshold A trend of the amplitude of the effective sound piece is determined, and when the change trend is small and large, the current scene is determined to be the second scene.

The processing unit 402 triggers corresponding functions of the smart device according to the current scenario, including:

When the current scenario is the second scenario, the smart device is switched from sleep to normal working state.

Optionally, in another possible scenario, the sound around the smart device is changed from large to large. At this time, the processing unit 402 determines the corresponding current scene according to the change trend of the amplitude value and/or the amplitude of the effective sound piece, including :

Determining the amplitude value of the effective sound piece, determining the amplitude of the effective sound piece when the average value of the amplitude values of all the effective sound pieces is less than or equal to the first set threshold or the sum of the amplitude values of all the effective sound pieces is less than or equal to the second set threshold The trend of change, when the trend is changed from large to small, determine the current scene as the third scene;

The processing unit 402 triggers corresponding functions of the smart device according to the current scenario, including:

When the current scene is the third scene, the smart device is switched to the sleep state.

Through the sound triggering method of the smart device, the sound in the set sound frequency range can be collected, and the sound is converted into an effective sound piece, and then the current scene corresponding to the sound feature is determined according to the sound feature of the effective sound piece, and then the basis can be realized. The current scenario triggers the corresponding function of the smart device. In the identifiable scenario, the user does not need to perform voice control or manual triggering, which is convenient for the user to use.

The embodiments in the present specification are described in a progressive manner, and the same or similar parts between the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. Especially for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

While the present invention has been described by the embodiments of the invention, it will be understood that Thus, it is intended that the present invention cover the modifications and modifications of the invention

One of ordinary skill in the art will appreciate that all or a portion of the above steps may be performed by a program to instruct related hardware, such as a processor, which may be stored in a computer readable storage medium, such as a read only memory, disk or optical disk. Wait. Alternatively, all or part of the steps of the above embodiments may also be implemented using one or more integrated circuits. Correspondingly, each module/unit in the foregoing embodiment may be implemented in the form of hardware, for example, by implementing an integrated circuit to implement its corresponding function, or may be implemented in the form of a software function module, for example, being executed by a processor and stored in a memory. Programs/instructions to implement their respective functions. The invention is not limited to any specific form of combination of hardware and software.

The embodiments disclosed in the present application are as described above, but the descriptions are only for the purpose of understanding the present application, and are not intended to limit the present application, such as the specific implementation method in the embodiments of the present invention. Any modifications and changes in the form and details of the embodiments may be made by those skilled in the art without departing from the spirit and scope of the disclosure. The scope defined by the appended claims shall prevail.

Industrial applicability

The above technical solution conveniently realizes voice control and improves the user experience.

Claims (14)

A sound triggering method for a smart device, comprising: Collect sounds within the set sound frequency range; Converting the sound into a valid sound sheet; The corresponding function of the smart device is triggered according to the sound characteristics of the active sound film. The method of claim 1 wherein said collecting sounds within a set sound frequency range comprises: Collecting sounds in the set sound frequency range by a digital sound pressure sensor to obtain a sound signal stream of sound output; Converting the sound into a valid sound piece includes: The sound signal stream is buffered in units of set time intervals to form the effective sound sheet. The method of claim 1, wherein the triggering the corresponding function of the smart device according to the sound feature of the active sound sheet comprises: Determining a current scene corresponding to the sound feature according to the sound feature of the effective sound sheet; Trigger the corresponding function of the smart device according to the current scene. The method of claim 3, wherein the determining the current scene corresponding to the sound feature comprises: A corresponding current scene is determined according to a change trend of the amplitude value and/or the amplitude of the effective sound piece. The method of claim 4, wherein the determining the corresponding current scene based on the trend of the amplitude value and/or the amplitude of the effective sound sheet comprises: Determining an amplitude value of the effective sound piece, determining that the current scene is when the sum of the amplitude values of all the valid sound pieces is greater than the first set threshold or the sum of the amplitude values of all the valid sound pieces exceeds the second set threshold First scene; The triggering the corresponding function of the smart device according to the current scenario includes: When the current scene is the first scene, the smart device is woken up or the screen is illuminated. The method of claim 4, wherein the determining a corresponding current scene based on a change trend of amplitude values and/or amplitudes of the active sound sheet comprises: Determining an amplitude value of the effective sound piece, when an average value of amplitude values of all the valid sound pieces is less than or equal to a first set threshold or a sum of amplitude values of all the valid sound pieces is less than or equal to a second set threshold Determining a trend of the amplitude of the effective sound piece, and determining that the current scene is the second scene when the change trend is from small to large; The triggering the corresponding function of the smart device according to the current scenario includes: When the current scenario is the second scenario, the smart device is switched from the sleep state to the working state. The method of claim 4, wherein the determining a corresponding current scene based on a change trend of amplitude values and/or amplitudes of the active sound sheet comprises: Determining an amplitude value of the effective sound piece, when an average value of amplitude values of all the valid sound pieces is less than or equal to a first set threshold or a sum of amplitude values of all the valid sound pieces is less than or equal to a second set threshold Determining a trend of the amplitude of the effective sound piece, and determining the current scene as the third scene when the change trend is greater than the hour; The triggering the corresponding function of the smart device according to the current scenario includes: When the current scenario is the third scenario, the smart device is switched to the sleep state. A smart device that includes: a collecting unit configured to collect sounds within a set sound frequency range; The processing unit is configured to convert the sound into a valid sound piece and trigger a corresponding function of the smart device according to the sound characteristics of the effective sound piece. The smart device of claim 8, wherein the collection unit is configured to: The sound in the set sound frequency range is collected by the digital sound pressure sensor to obtain a sound signal stream of the sound output; Converting the sound into a valid sound sheet by the processing unit includes: The sound signal stream is buffered in units of set time intervals to form the effective sound sheet. The smart device of claim 8, wherein the processing unit triggers a corresponding function of the smart device according to the sound feature of the active sound piece, including: Determining a current scene corresponding to the sound feature according to the sound characteristics of the effective sound sheet; Trigger the corresponding function of the smart device according to the current scene. The smart device of claim 10, wherein the determining, by the processing unit, the current scene corresponding to the sound feature according to the sound feature of the effective sound piece comprises: The corresponding current scene is determined according to the trend of the amplitude value and/or the amplitude of the effective sound piece. The smart device according to claim 11, wherein the processing unit determines a corresponding current scene according to a change trend of an amplitude value and/or an amplitude of the effective sound piece, including: Determining an amplitude value of the effective sound piece, determining that the current scene is when the sum of the amplitude values of all the valid sound pieces is greater than the first set threshold or the sum of the amplitude values of all the valid sound pieces exceeds the second set threshold First scene; The processing unit triggers corresponding functions of the smart device according to the current scenario, including: When the current scene is the first scene, the smart device is woken up or the screen is illuminated. The smart device according to claim 11, wherein the processing unit determines a corresponding current scene according to a change trend of an amplitude value and/or an amplitude of the effective sound piece, including: Determining an amplitude value of the effective sound piece, when an average value of amplitude values of all the valid sound pieces is less than or equal to a first set threshold or a sum of amplitude values of all the valid sound pieces is less than or equal to a second set threshold Determining a trend of the amplitude of the effective sound piece, and determining that the current scene is the second scene when the change trend is from small to large; The processing unit triggers corresponding functions of the smart device according to the current scenario, including: When the current scenario is the second scenario, the smart device is switched from the sleep state to the working state. The smart device according to claim 11, wherein the processing unit determines a corresponding current scene according to a change trend of an amplitude value and/or an amplitude of the effective sound piece, including: Determining an amplitude value of the effective sound piece, when an average value of amplitude values of all the valid sound pieces is less than or equal to a first set threshold or a sum of amplitude values of all the valid sound pieces is less than or equal to a second set threshold Determining a trend of the amplitude of the effective sound piece, when the change trend is greater than Hours, determining that the current scene is the third scene; The processing unit triggers corresponding functions of the smart device according to the current scenario, including: When the current scenario is the third scenario, the smart device is switched to the sleep state.

Images