WO2020038010A1

WO2020038010A1 - Intelligent device, voice wake-up method, voice wake-up apparatus, and storage medium

Info

Publication number: WO2020038010A1
Application number: PCT/CN2019/084362
Authority: WO
Inventors: 迟欣; 吴海全; 张恩勤; 曹磊; 师瑞文
Original assignee: 深圳市冠旭电子股份有限公司
Priority date: 2018-08-23
Filing date: 2019-04-25
Publication date: 2020-02-27
Also published as: CN110858483A

Abstract

Provided is an intelligent device, comprising a voice collection apparatus (103), a wake-up chip (102), and a main control chip (101). The voice collection apparatus (103) is connected to the wake-up chip (102) for collecting first voice information and sending the first voice information to the wake-up chip (102); the wake-up chip (102) is connected to the main control chip (101) for receiving the first voice information and recognizing and analyzing the first voice information, when the first voice information comprises a preset voice instruction, a wake-up notification is generated, and the wake-up notification is sent to the main control chip (101); after the wake-up notification is received, the main control chip (101) wakes up a control function of the intelligent device. By adding an independent wake-up chip (102) in the intelligent device, the main control chip (101) is not required to be always in an operation state during a standby process, thereby reducing a power consumption of the intelligent device. Also provided are a voice wake-up method and apparatus and a storage medium of the intelligent device.

Description

Intelligent device, voice wake-up method, voice wake-up device and storage medium

Technical field

The present invention relates to the technical field of voice processing, and in particular, to a smart device, a voice wake-up method for a smart device, a voice wake-up device, and a storage medium.

Background technique

Among the existing smart devices, the wake-up system mainly includes a manual wake-up system, an action wake-up system and a voice wake-up system. Among them, the manual wake-up system mainly activates the smart device through the activation of a remote control or a body button. If this method is used for a long time, It is easy to cause the button to malfunction, at the same time, the power consumption is large, and the operation is inconvenient. In the wake-up system, an acceleration device needs to be set in the smart device or the control device of the smart device to detect whether there is acceleration in the smart device or control device. When the acceleration meets the preset conditions, the smart device is activated, that is, the motion wake-up system needs to be used with an acceleration sensor. The use and production costs are relatively high, and the acceleration sensor consumes large power. In the voice wake-up system, external voice information is collected in real time. And activate the smart device according to the analysis and processing result of the voice information of the master, that is, in the existing voice wake-up system, the master of the smart device must be able to process the voice information at any time, so that the master is always in the standby working state. Expensive and existing voice Wake up the system is also a problem in speech recognition is low, the efficiency of slow.

technical problem

In summary, how to quickly and accurately wake up a smart device through voice and reduce power consumption has become an urgent problem for those skilled in the art.

Technical solutions

Embodiments of the present invention provide a smart device, a voice wake-up method for a smart device, a voice wake-up device, and a computer-readable storage medium, which can quickly and accurately wake up a smart device through voice and reduce the standby power consumption of the smart device.

According to a first aspect of the embodiments of the present invention, an intelligent device is provided, including: a voice acquisition device, a wake-up chip, and a main control chip;

The voice acquisition device is connected to the wake-up chip, and is configured to collect first voice information and send the first voice information to the wake-up chip;

The wake-up chip is connected to the main control chip, and is configured to receive the first voice information, and perform recognition analysis on the first voice information. When the first voice information includes a preset voice instruction, generate the A wake-up notification, and sending the wake-up notification to the main control chip;

After receiving the wake-up notification, the main control chip wakes up a control function of the smart device.

Further, the voice acquisition device is further connected to the main control chip, and is configured to send the collected second voice information to the main control chip, and the main control chip sends the received second voice The information is sent to a cloud server, and a corresponding operation is performed on the smart device according to an analysis result returned after the cloud server analyzes and processes the second voice information.

Optionally, the wake-up chip includes a buffer unit, where the buffer unit is configured to store third voice information collected by the voice collection device, and send the third voice information to the main control chip, where The main control chip sends the received third voice information to the cloud server, and performs a corresponding operation on the smart device according to an analysis result returned after the cloud server analyzes and processes the third voice information.

Preferably, the smart device includes a digital signal processor, and the digital signal processor is connected to the voice acquisition device, and is configured to analyze and process the voice information collected by the voice acquisition device, and analyze the processed voice The information is sent to the wake-up chip and / or the main control chip.

Furthermore, the voice collection device is a single microphone or a microphone array.

According to a second aspect of the embodiments of the present invention, a voice wakeup method for a smart device is provided, including:

Obtaining first voice information;

Performing recognition analysis on the first voice information to obtain a recognition result;

Generating a wake-up notification when the recognition result includes a preset voice instruction;

Waking up the smart device based on the wake-up notification.

Further, the preset voice instruction includes a wake-up instruction for waking the smart device and a first control instruction for operating the smart device;

Correspondingly, when the recognition result includes the first control instruction, after waking up the smart device based on the wake-up notification, the method further includes:

Perform a corresponding operation on the smart device according to the first control instruction.

Optionally, after waking up the smart device based on the wake-up notification, the method includes:

Obtaining second voice information;

Analyze and process the second voice information to obtain an analysis result;

Determining whether the analysis result includes a preset second control instruction;

When the analysis result includes the second control instruction, a corresponding operation is performed on the smart device based on the second control instruction.

According to a third aspect of the embodiments of the present invention, a voice wakeup device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer The program realizes the steps of the voice wake-up method as described in the second aspect.

According to a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the voice wakeup according to the foregoing second aspect is implemented. Method steps.

Beneficial effect

It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:

In the embodiment of the present invention, the smart device includes a voice acquisition device, a wake-up chip, and a main control chip; the voice acquisition device is connected to the wake-up chip and is configured to collect the first voice information and send the first voice information to the wake-up chip; the wake-up chip and The main control chip is connected to receive the first voice information, and perform recognition analysis on the first voice information. When the first voice information includes a preset voice instruction, a wake-up notification is generated, and the wake-up notification is sent to the main control chip; After receiving the wake-up notification, the main control chip wakes up the control function of the smart device. In the embodiment of the present invention, by adding an independent wake-up chip to the smart device, the main control chip does not need to be always in the working state during the standby process, and a wake-up chip with a lower power consumption realizes an uninterrupted wake-up function. Thereby reducing the power consumption of the smart device during the standby process and extending the use time of the smart device. In addition, in the embodiment of the present invention, the wake-up chip can perform real-time monitoring and recognition analysis on the voice, and decide whether to send a wake-up notification to the main control chip according to whether the recognition result includes a preset voice instruction, so as to prevent any voice from calling the smart Device to improve the efficiency and accuracy of voice wake-up of smart devices.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only the present invention. For some embodiments, for those of ordinary skill in the art, other drawings can be obtained according to these drawings without paying creative labor.

FIG. 1 is a schematic structural diagram of a smart device according to a first embodiment of the present invention; FIG.

2 is a schematic structural diagram of an intelligent device in an application scenario according to Embodiment 1 of the present invention;

3 is a schematic structural diagram of a smart device according to a second embodiment of the present invention;

4 is a schematic structural diagram of an intelligent device in an application scenario according to Embodiment 2 of the present invention;

5 is a method flowchart of a method for waking up a voice of a smart device according to a third embodiment of the present invention;

6 is a schematic flowchart of a voice wakeup method provided in Embodiment 3 of the present invention in an application scenario;

FIG. 7 is a schematic structural diagram of a voice wake-up device provided by Embodiment 4 of the present invention.

Embodiments of the invention

Embodiments of the present invention provide a smart device, a voice wake-up method for a smart device, a voice wake-up device, and a computer-readable storage medium, which are used to quickly and accurately wake up a smart device through voice and reduce the standby power consumption of the smart device.

In order to make the objectives, features, and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be described clearly and completely in combination with the drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only some, but not all, of the embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Referring to FIG. 1, a first embodiment of the present invention provides a smart device. The smart device includes a voice collection device 103, a wake-up chip 102, and a main control chip 101.

The voice acquisition device 103 is connected to the wake-up chip 102 and is configured to collect first voice information and send the first voice information to the wake-up chip 102;

The wake-up chip 102 is connected to the main control chip 101, and is configured to receive the first voice information and perform recognition analysis on the first voice information. When the first voice information includes a preset voice command To generate a wake-up notification and send the wake-up notification to the main control chip 101;

After receiving the wake-up notification, the main control chip 101 wakes up the control function of the smart device.

Further, the voice acquisition device 103 is also connected to the main control chip 101, and is configured to send the collected second voice information to the main control chip 101, and the main control chip 101 sends all received The second voice information is sent to a cloud server, and a corresponding operation is performed on the smart device according to an analysis result returned after the cloud server analyzes and processes the second voice information.

In this embodiment, the voice acquisition device 103 may be connected to the wake-up chip 102 and the main control chip 101 through buses such as I2S, PCM, TDM, and PDM to send the collected voice information to the wake-up Chip 102 and the main control chip 101. Communication between the wake-up chip 102 and the main control chip 101 can be achieved through communication protocols such as UART, GPIO interrupt, SPI, and I2C.

Preferably, in this embodiment, the voice collection device 103 is connected to the wake-up chip 102 and the main control chip 101 through an I2S bus, that is, the voice collection device 103, the wake-up chip 102, and the master The three control chips 10 are connected to the same group of I2S buses. In order to ensure that the main control chip 101 is always in a low power consumption state before waking up, in order to reduce the power consumption of the smart device, the voice collection device 103 or the wake-up chip 102 may be selected as the master of the I2S bus to Provide the clock on the bus, and the other two are in I2S slave mode.

When the smart device is in a standby state, the main control chip 101 enters a low power consumption state, and the voice acquisition device 103 is turned on for real-time acquisition of the first voice information, and the acquired first Voice information is sent to the wake-up chip 102, and the wake-up chip 102 is also turned on to receive the first voice information sent from the voice collection device 103, and perform recognition analysis on the first voice information. When the wake-up chip 102 recognizes and analyzes that the first voice information includes a preset voice instruction, it generates a wake-up notification, and sends the wake-up notification to the main control chip 101 through a GPIO interrupt. After receiving the wake-up notification, the main control chip 101 wakes up the smart device from a standby state, so that subsequent control operations can be performed on the smart device.

The preset voice command may be a wake-up command that only wakes up the smart device, such as "Ding-Dang." Of course, the preset voice command may also be a local control command that performs a corresponding operation on the smart device, such as "Play Music", "Volume Down", "Next Song", etc. When the preset voice command is a wake-up command of "Ding-Dong", only the smart device is woken up; when the preset command is a local control command of "play music" or "volume reduction", the wake-up first The smart device then automatically plays music based on a control instruction of "play music", or lowers the volume of the smart device based on a control instruction of "volume reduction". It can be understood that the preset voice wake-up instruction can be preset by the user according to actual needs. For example, special words such as "Qi Tian Da Sheng" can be set as the wake-up instruction.

Further, after the preset voice instruction is a wake-up instruction and the smart device is woken up, the smart device may trigger a cloud server by wireless means such as Bluetooth, and the voice acquisition device 103 further collects the second wake-up second Voice information, and send the collected second voice information to the main control chip 101, the main control chip 101 sends the second voice information to a cloud server by wireless means such as Bluetooth, and the cloud server The second voice information is analyzed, and a corresponding message is returned to the smart device according to the analysis result, and the smart device performs a corresponding operation based on the corresponding message.

For example, when the smart device is awakened, the voice collection device 103 then collects the second voice information of “Query Beijing Today ’s Weather”, that is, the second voice information is sent to the main control chip 101, so The main control chip 101 sends the second voice information to the cloud server, and the cloud server queries the weather conditions in Beijing today based on this. For example, when the query obtains the corresponding message "Beijing today is sunny, the temperature is 13 degrees," it sends "Beijing Today, the corresponding message is sent to the smart device. The smart device receives the corresponding message, and then the smart device can control the screen of the smart device to display "Beijing today is sunny, the temperature is 13 degrees." The text message may also control the speaker of the smart device to play a voice message of "Beijing today is sunny with a temperature of 13 degrees".

Preferably, after the preset voice instruction is a wake-up instruction and wakes up the smart device, the smart device enters an activated state and triggers an APP of a remote device connected to the smart device by Bluetooth. At this time, The APP of the remote device is activated and performs Bluetooth recording of the activated voice message, and simultaneously transmits the recorded recording data to the cloud server, and the cloud server analyzes the recording data and returns a corresponding message according to the analysis result Go to the remote device and / or the smart device and perform a corresponding operation, such as the remote device and / or the smart device playing a corresponding voice, and so on.

Further, in order to improve the accuracy and clarity of voice information collection, in this embodiment, the voice collection device 103 is a single microphone or a microphone array. The wake-up chip 102 and the main control chip 101 are both connected to a microphone or a microphone array, so that the wake-up chip 102 and the main control chip 101 can share a microphone to obtain voice data to reduce the microphone in the smart device. The number of settings simplifies the structure of the smart device and reduces the manufacturing cost of the smart device.

In this embodiment, an independent wake-up chip is added to the smart device, so that the main control chip does not need to be always in the working state during the standby process, and a wake-up chip with a lower power consumption implements an uninterrupted wake-up function, thereby Reduce the power consumption of smart devices during standby, and extend the use time of smart devices. In addition, in this embodiment, the wake-up chip can perform real-time monitoring and recognition analysis on the voice, and decide whether to send a wake-up notification to the main control chip according to whether the recognition result includes a preset voice instruction, so as to prevent any voice from calling the smart device. , Improve the efficiency and accuracy of voice wake-up of smart devices.

FIG. 2 is a schematic structural diagram of an intelligent device in an application scenario according to Embodiment 1 of the present invention. As shown in FIG. 2, the smart device includes a voice collection device 103, a wake-up chip 102, a main control chip 101 and a digital signal processor 204.

In this scenario, the voice acquisition device 103 is connected to the digital signal processor 204. The voice acquisition device 103 is configured to collect first voice information and send the first voice information to the digital signal processor. 204.

The digital signal processor 204 is configured to pre-process the received first voice information, and at the same time, the digital signal processor 204 is also connected to the wake-up chip 102 to convert the pre-processed first voice information. Information is sent to the wake-up chip 102.

The wake-up chip 102 is also connected to the main control chip 101, for receiving the first voice information preprocessed by the digital signal processor 204, and performing recognition analysis on the first voice information preprocessed, When it is identified that the pre-processed first voice information includes a preset voice instruction, a wake-up notification is generated, and the wake-up notification is sent to the main control chip 101.

Further, the digital signal processor 204 is further connected to the main control chip 101, and is configured to preprocess the second voice information collected by the voice acquisition device 103, and to preprocess the second voice after the preprocessing Information is sent to the main control chip 101.

In this scenario, a digital signal processor 204 is added between the voice acquisition device 103, the wake-up chip 102, and the main control chip 101 of the smart device provided in the first embodiment to pass the digital signal processor. 204 Perform preprocessing such as echo cancellation and noise reduction on the voice information collected by the voice acquisition device 103, and further perform preprocessing such as microphone array algorithms such as beamforming or blind source signal separation to improve voice quality and long-distance voice. Recognition rate, thereby improving the accuracy and efficiency of voice wake-up and voice control.

As shown in FIG. 3, a second embodiment of the present invention provides a smart device. The smart device includes a voice collection device 103, a wake-up chip 102, and a main control chip 101.

In this embodiment, the voice acquisition device 103 may be connected to the wake-up chip 102 through a bus such as I2S, PCM, TDM, and PDM to send the collected voice information to the wake-up chip 102, and the wake-up chip 102 It can also be connected to the main control chip 101 through I2S, PCM, TDM, PDM and other buses, so that when the main control chip 101 needs voice information, the voice information collected by the voice acquisition device 103 is forwarded to the The main control chip 101. At the same time, the wake-up chip 102 and the main control chip 101 can also communicate through communication protocols such as UART, GPIO interrupt, SPI, and I2C, so as to pass the awakening notification generated by the wake-up chip 102 through the UART And other communication methods to the main control chip 101.

Preferably, in this embodiment, the voice acquisition device 103 is connected to the wake-up chip 102 through an I2S bus, and the wake-up chip 102 is connected to the main control chip 101 through an I2S bus. At this time, the I2S bus between the voice acquisition device 103 and the wake-up chip 102 may select any one end as the master, and the master control chip 101 and the wake-up chip 102 may select the master control chip 101. As a master, therefore, when the main control chip 101 is in a low-power state that has not been awakened, the main control chip 101 does not output a clock, thereby preventing the wake-up chip 102 from outputting unnecessary data.

Optionally, the wake-up chip 102 includes a buffer unit 305, where the buffer unit 305 is configured to store the third voice information collected by the voice collection device 103, and send the third voice information to the main control unit. Chip 101, and the main control chip 101 sends the received third voice information to a cloud server, and sends the third voice information to the smart device according to an analysis result returned after the cloud server analyzes the third voice information Perform the corresponding operation.

That is, after the preset voice instruction is a wake-up instruction and the smart device is woken up, when the voice collection device 103 also collects third voice information, it sends the collected third voice information to the smart device. The wake-up chip 102 stores the third voice information in the buffer unit 305. After the smart device is awakened and the cloud server is triggered by wireless means such as Bluetooth, the main control chip 101 can obtain the third voice information from the buffer unit 305 and use wireless means such as Bluetooth to The third voice information is sent to a cloud server, the cloud server analyzes the third voice information, and returns a corresponding message to the smart device according to the analysis result, and the smart device performs a corresponding operation based on the corresponding message.

In this embodiment, the main control chip obtains information by awakening the chip, and at the same time wakes up the cache unit in the chip to effectively store the voice information, thereby effectively avoiding the problem of voice loss caused by network delay, and improving the effectiveness of voice wake-up and voice control. Sex.

FIG. 4 is a schematic structural diagram of an intelligent device in an application scenario according to Embodiment 2 of the present invention. As shown in FIG. 4, the smart device includes a voice collection device 103, a wake-up chip 102, a main control chip 101, and a digital signal processor 204.

It can be understood that the digital signal processor 204 can also be used to perform pre-processing such as echo cancellation and denoising on the third voice information collected by the voice collection device 103.

In this scenario, a digital signal processor 204 is added between the voice acquisition device 103 and the wake-up chip 102 of the smart device provided in the second embodiment to collect the voice through the digital signal processor 204 The voice information collected by the device 103 is subjected to preprocessing such as echo cancellation and noise reduction to improve voice quality and voice recognition rate, thereby improving the accuracy and efficiency of voice wake-up.

The above mainly describes a smart device, and a voice wakeup method of the smart device will be described in detail below.

FIG. 5 shows a method flowchart of a method for waking up a voice of a smart device according to a third embodiment of the present invention. As shown in FIG. 5, the voice wakeup method includes:

Step S501: Obtain first voice information.

Step S502: Perform recognition analysis on the first voice information to obtain a recognition result.

Step S503: Generate a wake-up notification when the recognition result includes a preset voice instruction;

Step S504: Wake up the smart device based on the wake-up notification.

It can be understood that, in this embodiment, after acquiring the first voice information, the voice acquisition device in the smart device sends the first voice information to the wake-up chip, and the wake-up chip performs recognition analysis on the first voice information. A recognition result is obtained. When the recognition result includes a preset voice instruction, a wake-up notification is generated, and the wake-up notification is sent to a main control chip, and the main control chip wakes up the smart device based on the wake-up notification.

Further, the preset voice instruction includes a wake-up instruction for waking the smart device and a first control instruction for operating the smart device; therefore, when the recognition result includes the first control instruction When the smart device is woken up based on the wake-up notification, a corresponding operation is performed on the smart device according to the first control instruction.

That is, the preset voice command may be a wake-up command that only wakes up the smart device, such as "Ding Dong", and at the same time, the preset voice command may also be a local control command that performs a corresponding operation on the smart device, such as " Play Music "," Volume Down "," Next Song ", etc. When the preset voice command is a wake-up command of "Ding-Dong", only the smart device is woken up; when the preset command is a local control command of "play music" or "volume reduction", the wake-up first The smart device then automatically plays music based on a control instruction of "play music", or lowers the volume of the smart device based on a control instruction of "volume reduction". It can be understood that the preset voice wake-up instruction can be preset by the user according to actual needs. For example, special words such as "Qi Tian Da Sheng" can be set as the wake-up instruction.

To facilitate understanding, the following describes the voice wakeup method provided in Embodiment 3 of the present invention with an actual application scenario:

FIG. 6 is a schematic flowchart of a method for waking up a voice of a smart device according to the third embodiment of the present invention in an application scenario. As shown in FIG. 6, in this scenario, the voice wakeup method includes: step S601, step S602, step S603, step S604, step S605, step S606, step S607, and step S608.

In step S601, obtaining the first voice information is similar to the above-mentioned step S501; in step S602, performing recognition analysis on the first voice information, and obtaining a recognition result similar to the above-mentioned step S502; in step S603, when the recognition result includes a preset When a voice instruction is issued, the wake-up notification is generated similarly to the above-mentioned step S503; in step S604, the wake-up of the smart device based on the wake-up notification is similar to the above-mentioned step S504.

In step S605, acquiring second voice information;

In step S606, analyze and process the second voice information to obtain an analysis result;

In step S607, it is determined whether the analysis result includes a preset second control instruction;

In step S608, when the analysis result includes the second control instruction, operate the smart device based on the second control instruction

It can be understood that, in this scenario, after the preset voice command is a wake-up command and the smart device is woken up, the smart device can trigger a cloud server through wireless means such as Bluetooth, and the voice acquisition device can collect Wake up the second voice information, and send the collected second voice information to the main control chip, and the main control chip sends the second voice information to a cloud server via wireless such as Bluetooth The server analyzes the second voice information, and returns a corresponding message to the smart device according to the analysis result, and the smart device performs a corresponding operation based on the corresponding message.

Further, after the preset voice instruction is a wake-up instruction and wakes up the smart device, the smart device enters an activated state and triggers an APP of a remote device connected to the smart device by Bluetooth. At this time, The APP of the remote device is activated and performs Bluetooth recording of the activated voice message, and simultaneously transmits the recorded recording data to the cloud server, and the cloud server analyzes the recording data and returns a corresponding message according to the analysis result Go to the remote device and / or the smart device and perform a corresponding operation, such as the remote device and / or the smart device playing a corresponding voice, and so on.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

FIG. 7 is a schematic diagram of a voice wake-up device according to a fourth embodiment of the present invention. As shown in FIG. 7, the voice wakeup device 700 of this embodiment includes a processor 701, a memory 702, and a computer program 703, such as a voice wakeup program, stored in the memory 702 and executable on the processor 701. When the processor 701 executes the computer program 703, the steps in the foregoing embodiments of the voice wakeup method are implemented, for example, steps S501 to S504 shown in FIG. Alternatively, when the processor 701 executes the computer program 703, the functions of the modules / units in the embodiments of the smart devices described above are implemented, such as the functions of the voice acquisition device 101, the wake-up chip 102, and the main control chip 103 shown in FIG. .

The voice wake-up device 700 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The voice wake-up device may include, but is not limited to, a processor 701 and a memory 702. Those skilled in the art can understand that FIG. 7 is only an example of the voice wake-up device 700 and does not constitute a limitation on the voice wake-up device 700. It may include more or fewer components than shown in the figure, or combine some components, or be different The components, for example, the voice wake-up device may further include an input-output device, a network access device, a bus, and the like.

The processor 701 may be a central processing unit (Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), and application-specific integrated circuits (Applications) Specific Integrated Circuit (ASIC), off-the-shelf Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 702 may be an internal storage unit of the voice wake-up device 700, such as a hard disk or a memory of the voice wake-up device 700. The memory 702 may also be an external storage device of the voice wake-up device 700, such as a plug-in hard disk, a smart media card (SMC), and a secure digital (Secure Digital, SD card, flash memory card (Flash Card) and so on. Further, the memory 702 may further include both an internal storage unit of the voice wakeup apparatus 700 and an external storage device. The memory 702 is configured to store the computer program and other programs and data required by the voice wake-up device. The memory 702 may also be used to temporarily store data that has been output or is to be output.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and are not repeated here.

In the above embodiments, the description of each embodiment has its own emphasis. For a part that is not detailed or recorded in an embodiment, reference may be made to related descriptions of other embodiments.

Those of ordinary skill in the art may realize that the modules, units, and / or method steps of the embodiments described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, which may be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objective of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional unit.

When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the methods of the above embodiments, and may also be completed by a computer program instructing related hardware. The computer program may be stored in a computer-readable storage medium. The computer When the program is executed by a processor, the steps of the foregoing method embodiments can be implemented. The computer program includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signals, telecommunication signals, and software distribution media. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdictions. For example, in some jurisdictions, the computer-readable medium Excludes electric carrier signals and telecommunication signals.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, but not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still explain the foregoing. The technical solutions described in the embodiments are modified, or some technical features are equivalently replaced; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

An intelligent device, characterized in that the intelligent device includes a voice acquisition device, a wake-up chip, and a main control chip;

The voice acquisition device is connected to the wake-up chip, and is configured to collect first voice information and send the first voice information to the wake-up chip;

The wake-up chip is connected to the main control chip, and is configured to receive the first voice information, and perform recognition analysis on the first voice information. When the first voice information includes a preset voice instruction, generate the A wake-up notification, and sending the wake-up notification to the main control chip;

After receiving the wake-up notification, the main control chip wakes up a control function of the smart device.
The smart device according to claim 1, wherein the voice acquisition device is further connected to the main control chip, and is configured to send the collected second voice information to the main control chip, and the main control The chip sends the received second voice information to a cloud server, and performs a corresponding operation on the smart device according to an analysis result returned after the cloud server analyzes and processes the second voice information.
The smart device according to claim 1, wherein the wake-up chip includes a buffer unit, the buffer unit is configured to store the third voice information collected by the voice acquisition device, and store the third voice information Sending to the main control chip, and the main control chip sends the received third voice information to a cloud server, and compares the third voice information with the analysis result returned by the cloud server after analyzing and processing the third voice information The smart device performs a corresponding operation.
The smart device according to claim 1, wherein the smart device comprises a digital signal processor, and the digital signal processor is connected to the voice acquisition device, and is configured to collect voice information collected by the voice acquisition device. Perform analysis processing, and send the analysis-processed voice information to the wake-up chip and / or the main control chip.
The smart device according to any one of claims 1 to 4, wherein the voice collection device is a single microphone or a microphone array.
A voice wake-up method for a smart device, comprising:

Obtaining first voice information;

Performing recognition analysis on the first voice information to obtain a recognition result;

Generating a wake-up notification when the recognition result includes a preset voice instruction;

Waking up the smart device based on the wake-up notification.
The voice wake-up method according to claim 6, wherein the preset voice instruction comprises a wake-up instruction for waking the smart device and a first control instruction for operating the smart device;

Correspondingly, when the recognition result includes the first control instruction, after waking up the smart device based on the wake-up notification, the method further includes:

Perform a corresponding operation on the smart device according to the first control instruction.
The method according to claim 6, wherein after waking up the smart device based on the wake-up notification, the method comprises:

Obtaining second voice information;

Analyze and process the second voice information to obtain an analysis result;

Determining whether the analysis result includes a preset second control instruction;

When the analysis result includes the second control instruction, a corresponding operation is performed on the smart device based on the second control instruction.
A voice wake-up device includes a memory, a processor, and a computer program stored in the memory and operable on the processor, characterized in that when the processor executes the computer program, it implements claim 6 The steps of the voice wakeup method according to any one of 8 to 8.
A computer-readable storage medium storing a computer program, characterized in that when the computer program is executed by a processor, the method for implementing the voice wake-up method according to any one of claims 6 to 8 is implemented. step.