CN108806673B - Intelligent device control method and device and intelligent device - Google Patents

Intelligent device control method and device and intelligent device Download PDF

Info

Publication number
CN108806673B
CN108806673B CN201710309605.2A CN201710309605A CN108806673B CN 108806673 B CN108806673 B CN 108806673B CN 201710309605 A CN201710309605 A CN 201710309605A CN 108806673 B CN108806673 B CN 108806673B
Authority
CN
China
Prior art keywords
cpu
data processor
standby state
voice information
working state
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710309605.2A
Other languages
Chinese (zh)
Other versions
CN108806673A (en
Inventor
姜朝
卜弋天
周金利
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Orion Star Technology Co Ltd
Original Assignee
Beijing Orion Star Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Orion Star Technology Co Ltd filed Critical Beijing Orion Star Technology Co Ltd
Priority to CN201710309605.2A priority Critical patent/CN108806673B/en
Publication of CN108806673A publication Critical patent/CN108806673A/en
Application granted granted Critical
Publication of CN108806673B publication Critical patent/CN108806673B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Power Sources (AREA)
  • Telephone Function (AREA)

Abstract

The embodiment of the invention provides an intelligent device control method and device and an intelligent device. The method is applied to a data processor of the intelligent device, and comprises the following steps: receiving user voice information sent by a recording unit when the intelligent device is in a complete standby state, wherein the complete standby state is at least: the data processor is in a working state, and the CPU is in a standby state; carrying out voice recognition on the voice information of the user to obtain a target recognition result; judging whether a target recognition result contains a preset trigger word or not; if so, sending a first interrupt signal to the CPU, so that the CPU is switched to a working state from a standby state when receiving the first interrupt signal, and controlling the intelligent equipment to respond to the processing instruction corresponding to the preset trigger word. According to the scheme, the intelligent device can be ensured to be capable of responding to the user instruction in time, and meanwhile, the power consumption of the intelligent device in a non-working state is reduced, so that the consumption of electric energy is reduced.

Description

Intelligent device control method and device and intelligent device
Technical Field
The invention relates to the technical field of intelligent equipment control, in particular to an intelligent equipment control method, an intelligent equipment control device and intelligent equipment.
Background
With the rapid development of scientific technology, intelligent devices (such as intelligent sound boxes, intelligent robots, etc.) are gradually applied to various industries. In order to reduce the power consumption of the intelligent device, the intelligent device enters a standby state when the intelligent device does not respond to a user instruction for a long time. However, since the smart device needs to be able to respond to the user command at any time, in the prior art, when the smart device is in the standby state, a Central Processing Unit (CPU) of the smart device is continuously in a working state, so as to ensure that the smart device can respond to the user command in time when the smart device is in the standby state. For example, the CPU may continuously receive the voice information sent by the recording unit, perform voice recognition on the received voice information, detect whether the voice recognition result includes a preset wake-up word, and control the smart device to enter a full-power-consumption operating state when detecting that the voice recognition result includes the preset wake-up word.
Therefore, in the process that the intelligent device is continuously in the standby state, because the CPU is still in the working state to ensure that the intelligent device responds to the user instruction in time, a large power consumption is still generated, thereby causing a large consumption of electric energy.
Disclosure of Invention
The embodiment of the invention aims to provide an intelligent device control method, an intelligent device control device and an intelligent device, so that intelligent identification can be responded to a user instruction, and meanwhile, the power consumption of the intelligent device in a non-working state is reduced. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides an intelligent device control method, which is applied to a data processor of an intelligent device, where the data processor is in communication connection with a CPU and a recording unit of the intelligent device, respectively, and the method includes:
and receiving user voice information sent by the recording unit when the intelligent device is in a full standby state, wherein the full standby state is at least: the data processor is in a working state, and the CPU is in a standby state;
carrying out voice recognition on the user voice information to obtain a target recognition result;
judging whether the target recognition result contains a preset trigger word or not;
if so, sending a first interrupt signal to the CPU, so that the CPU is switched to a working state from a standby state when receiving the first interrupt signal, and controlling the intelligent equipment to respond to a processing instruction corresponding to the preset trigger word.
Optionally, the power consumption of the data processor is lower than that of a central processing unit CPU of the smart device.
Optionally, when it is determined that the target recognition result includes a preset trigger word, the method further includes:
switching the data processor itself from an operating state to a standby state.
Optionally, after switching the data processor itself from the operating state to the standby state, the method further includes:
and when a second interrupt signal sent by the CPU is received, switching the data processor from a standby state to a working state, wherein the second interrupt signal is sent when the CPU is switched from the working state to the standby state.
Optionally, the data processor is a microprocessor.
Optionally, when detecting that a predetermined condition is satisfied, the CPU switches the CPU itself from a working state to a standby state.
Optionally, the predetermined condition is:
and the first time interval is greater than a target time interval threshold, wherein the first time interval is a time interval when the voice information of the user is not received from the moment when the CPU is in the working state.
Optionally, the predetermined condition is:
and a second time interval is greater than a target time interval threshold, wherein the second time interval is a time interval when the intelligent equipment does not receive the user voice information from the moment when the intelligent equipment finishes responding the interactive instruction corresponding to any user voice information.
Optionally, the predetermined condition is:
and the voice recognition result corresponding to the user voice information received by the CPU comprises a preset standby word.
In a second aspect, an embodiment of the present invention further provides an intelligent device control apparatus, which is applied to a data processor of an intelligent device, where the data processor is respectively in communication connection with the CPU and a recording unit of the intelligent device, and the apparatus includes:
the device comprises a receiving module, a voice recognition module, a judgment module and an interrupt signal sending module;
wherein the content of the first and second substances,
the receiving module is configured to receive the user voice information sent by the recording unit when the intelligent device is in a full standby state, where the full standby state is at least: the data processor is in a working state, and the CPU is in a standby state;
the voice recognition module is used for carrying out voice recognition on the user voice information to obtain a target recognition result;
the judging module is used for judging whether the target recognition result contains a preset trigger word or not;
and the interrupt signal sending module is used for sending a first interrupt signal to the CPU when the judgment result of the judgment module is yes, so that the CPU is switched from a standby state to a working state when receiving the first interrupt signal, and controls the intelligent equipment to respond to the processing instruction corresponding to the preset trigger word.
Optionally, the power consumption of the data processor is lower than that of a central processing unit CPU of the smart device.
Optionally, the apparatus further comprises:
and the working state switching module is used for switching the data processor from the working state to the standby state when the judgment result of the judgment module is yes.
Optionally, the apparatus further comprises:
and the interrupt signal receiving module is used for switching the data processor from the standby state to the working state when receiving a second interrupt signal sent by the CPU after the interrupt signal sending module switches the data processor from the working state to the standby state, wherein the second interrupt signal is sent when the CPU is switched from the working state to the standby state.
Optionally, the data processor is a microprocessor.
Optionally, when detecting that a predetermined condition is satisfied, the CPU switches the CPU itself from a working state to a standby state.
Optionally, the predetermined condition is:
and the first time interval is greater than a target time interval threshold, wherein the first time interval is a time interval when the voice information of the user is not received from the moment when the CPU is in the working state.
Optionally, the predetermined condition is:
and a second time interval is greater than a target time interval threshold, wherein the second time interval is a time interval when the intelligent equipment does not receive the user voice information from the moment when the intelligent equipment finishes responding the interactive instruction corresponding to any user voice information.
Optionally, the predetermined condition is:
and the voice recognition result corresponding to the user voice information received by the CPU comprises a preset standby word.
In a third aspect, an embodiment of the present invention further provides an intelligent device, where the intelligent device includes: the system comprises a data processor, a Central Processing Unit (CPU) and a recording unit; the data processor is respectively in communication connection with the central processing unit CPU and the recording unit;
the recording unit is used for acquiring user voice information;
the data processor is used for receiving the user voice information sent by the recording unit when the intelligent equipment is in a complete standby state; carrying out voice recognition on the user voice information to obtain a target recognition result; judging whether the target recognition result contains a preset awakening word or not; if yes, sending a first interrupt signal to the CPU, wherein the full standby state is at least: the data processor is in a working state, and the CPU is in a standby state;
and the CPU is used for switching from a standby state to a working state when receiving the first interrupt signal and controlling the intelligent equipment to respond to the processing instruction corresponding to the preset trigger word.
Compared with the prior art, the scheme provided by the embodiment of the invention is characterized in that the data processor is arranged in the intelligent equipment, and the power consumption of the data processor is lower than that of the CPU. When the intelligent device is in a non-working state, the CPU of the intelligent device is in a standby state, the low-power-consumption data processor is in a working state, specifically, the low-power-consumption data processor receives user voice information sent by the recording unit, performs voice recognition on the user voice information to obtain a target recognition result, and when the target recognition result contains a preset trigger word, the CPU of the intelligent device enters the working state and controls the intelligent device to respond to a processing instruction corresponding to the preset trigger word.
It can be seen that, in this scheme, when the smart device is in the non-operating state, only the data processor of low-power consumption is in the operating state, and the CPU is in the standby state, and, carry out trigger word discernment by the data processor, awaken the CPU in time when discerning trigger word, and then control the smart device to respond to the processing instruction corresponding with presetting trigger word by the CPU, consequently, can reduce the power consumption that the smart device is in the non-operating state when guaranteeing that the smart device can be responded to user's instruction in time through this scheme, thereby reduce the consumption of electric energy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an intelligent device control method according to an embodiment of the present invention;
fig. 2 is another flowchart of a method for controlling an intelligent device according to an embodiment of the present invention;
fig. 3 is another flowchart of a method for controlling an intelligent device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an intelligent device control apparatus according to an embodiment of the present invention;
fig. 5 is another schematic structural diagram of an intelligent device control apparatus according to an embodiment of the present invention;
fig. 6 is another schematic structural diagram of an intelligent device control apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an intelligent device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the problem of the prior art, embodiments of the present invention provide an intelligent device control method, an intelligent device control apparatus, and an intelligent device, so as to ensure that the intelligent device can respond to a user instruction in time, and reduce power consumption of the intelligent device in a non-operating state, thereby reducing power consumption.
An intelligent control method for a device according to an embodiment of the present invention will be described below.
It should be noted that the method for controlling an intelligent device provided by the embodiment of the present invention is applied to a data processor, the data processor is disposed in the intelligent device, and the data processor is in communication connection with a recording unit and a CPU of the intelligent device, where the recording unit may be a microphone or a microphone array.
It is emphasized that the above-mentioned smart device may be: the intelligent mobile phone, the intelligent household product (such as an intelligent sound box), the intelligent vehicle-mounted equipment, the intelligent wearable equipment, the intelligent robot and the like are reasonable; moreover, the intelligent device may operate in a communication connection with the server or may operate alone, which is not limited in the embodiments of the present invention.
In a specific application, the data processor may be a microprocessor having advantages of low power consumption, low cost, small size, high reliability, good performance, and the like, but is not limited thereto. It is understood that any processor having a data processing function and consuming less power than a processor of a CPU in a smart device may be used as the data processor according to the embodiment of the present invention.
Alternatively, the microprocessor may be a digital signal processing DSP chip, an ARM chip, or an application specific integrated circuit ASIC chip, wherein the ARM chip is a semiconductor chip developed by ARM Holdings, a british chip design company. The power consumption of the DSP chip, the ARM chip and the ASIC chip is lower than that of the CPU.
It should be noted that, in the embodiment of the present invention, a program or a code may be stored in the data processor, and further, when the data processor receives the user voice information, the program or the code is executed to perform voice recognition on the user voice information, obtain a target recognition result, and determine whether the target recognition result includes a trigger word, and when the determination result is yes, the CPU is triggered to execute the next operation, and for clarity of the scheme description, the operation of the CPU is described in detail in the embodiment shown in fig. 1. It is understood that the manner in which the program or code is executed by the data processor may be various, and is not particularly limited in the embodiments of the present invention.
For example, a program or a code stored in the data processor can realize awakening word recognition, so that when the microprocessor receives user voice information, voice recognition is performed on the user voice information, a target recognition result is obtained, whether the target recognition result contains a preset awakening word or not is judged, and if the target recognition result contains the awakening word, a first interrupt signal is sent to the CPU, so that the CPU is triggered to execute the next operation.
As shown in fig. 1, an intelligent device control method provided in an embodiment of the present invention includes the following steps:
s101, the data processor receives user voice information sent by the recording unit when the intelligent device is in a complete standby state, wherein the complete standby state is at least: the data processor is in a working state, and the CPU is in a standby state;
in order to ensure that the intelligent device can be awakened in time and the power consumption of the intelligent device in a complete standby state is reduced, the intelligent device is set to have two running states: the first operating state is: a full standby state, i.e. a non-operating state; the first operating state is: and (5) working state. Specifically, when the intelligent device is in a complete standby state, a recording unit and a data processor of the intelligent device are in a working state, and a CPU is in a standby state; when the intelligent device is in a working state, the recording unit and the CPU of the intelligent device are in a working state, and the data processor is in a standby state.
When the intelligent equipment is in a complete standby state, a recording unit of the intelligent equipment continuously collects user voice information and sends the collected user voice information to the data processor; accordingly, the data processor can receive the user voice information sent by the recording unit and carry out recognition processing on the received user voice information. Therefore, when the intelligent device is in a complete standby state, the data processor receives the user voice information sent by the recording unit, so that the power consumption of the intelligent device in a non-working state can be reduced, and the electric energy is saved.
S102, carrying out voice recognition on the user voice information to obtain a target recognition result;
when the data processor receives the user voice information sent by the recording unit, the data processor may perform voice recognition on the user voice information to obtain a target recognition result, and then perform the subsequent S103. The specific implementation manner of recognizing the user voice information may be an implementation manner existing in the prior art, and is not limited herein.
For example, the data processor may perform a simple wake word recognition model to perform speech recognition on the user speech information.
S103, judging whether the target recognition result contains a preset trigger word, if so, executing S104, and if not, continuing to execute S101;
after the data processor obtains the target recognition result, in order to determine whether the user needs the intelligent device to respond to the user instruction, therefore, the data processor determines whether the target recognition result contains a preset trigger word, if the target recognition result contains the preset trigger word, it indicates that the user needs the intelligent device to respond to the user instruction, and then S104 is executed; if the target recognition result does not contain the preset trigger word, it indicates that the user does not need the intelligent device to respond to the user instruction, and at this time, S101 is continuously executed, that is, the intelligent device is continuously in a full standby state, and the data processor continuously receives the user voice information sent by the recording unit so as to respond to the user instruction at any time.
It should be noted that, before receiving the user voice information sent by the recording unit, the data processor presets a trigger word, and the preset trigger word may be determined according to the needs of the user.
For example, the preset trigger word may be a preset wake-up word, and the preset wake-up word may be used to wake up the smart device, that is, the preset wake-up word may switch the smart device from a non-operating state to an operating state. Specifically, if the nickname of the intelligent device is referred to as "xiaoming", the preset wake-up word may be "xiaoming", and if the target identification result includes the preset wake-up word "xiaoming", it indicates that the user wants to wake up the intelligent device, at this time, the data processor performs S104, otherwise, the data processor performs S101. For another example: the preset wake-up word may be "hello", and if the target recognition result includes the preset wake-up word "hello", it indicates that the user wants to wake up the smart device, at this time, the data processor performs S104, otherwise, the data processor performs S101.
It is emphasized that in certain applications, it is reasonable that the preset trigger may be set by the system or manually.
And S104, sending a first interrupt signal to the CPU, so that the CPU is switched to a working state from a standby state when receiving the first interrupt signal, and controlling the intelligent equipment to respond to a processing instruction corresponding to the preset trigger word.
When the target recognition result obtained by the data processor contains a preset trigger word, the situation that the user needs the intelligent equipment to respond to the user instruction is indicated, a first interrupt signal is sent to the CPU, when the CPU receives the first interrupt signal, the standby state is switched to the working state, and the intelligent equipment is controlled to respond to the processing instruction corresponding to the preset trigger word.
Specifically, assuming that the preset trigger word is a preset wake-up word, after the target recognition result obtained by the data processor includes the preset wake-up word, sending a first interrupt signal to the CPU, and when receiving the first interrupt signal, the CPU switches from a standby state to a working state and controls the intelligent device to enter the working state with full power consumption.
For example, assuming that a preset wake-up word is 'xiaoming', a target recognition result obtained by a data processor includes 'xiaoming', a first interrupt signal is sent to a CPU, the CPU controls an intelligent device to switch from a non-working state to a working state when receiving the first interrupt signal, when a recording unit collects user voice information again, the received user voice information is sent to the CPU, the CPU performs voice recognition on the received user voice information or sends the received user voice information to a server, and the server performs voice recognition to obtain a voice recognition result, assuming that the voice recognition result is 'playing a newest song of zhougeny'? ", the intelligent device obtains the latest song of Zhou Ji Lun from the local and plays the song; or the smart device may obtain the latest song of zhou jeron from the server and play the song.
Moreover, the preset trigger word may also be a non-preset wake-up word, where the non-preset wake-up word is used to trigger the smart device to respond to a processing instruction corresponding to the preset trigger word. For example, if the preset trigger word is "call mother", when the target recognition result obtained by the data processor includes "call mother", a first interrupt signal is sent to the CPU, and when the CPU receives the first interrupt signal, the CPU switches from the standby state to the operating state, and controls a function module, such as an address list module, of the smart device related to the call making.
Compared with the prior art, the scheme provided by the embodiment of the invention is characterized in that the data processor is arranged in the intelligent equipment, and the power consumption of the data processor is lower than that of the CPU. When the intelligent device is in a non-working state, the CPU of the intelligent device is in a standby state, the low-power-consumption data processor is in a working state, specifically, the low-power-consumption data processor receives user voice information sent by the recording unit, performs voice recognition on the user voice information to obtain a target recognition result, and when the target recognition result contains a preset trigger word, the CPU of the intelligent device enters the working state and controls the intelligent device to respond to a processing instruction corresponding to the preset trigger word.
It can be seen that, in this scheme, when the smart device is in the non-operating state, only the data processor of low-power consumption is in the operating state, and the CPU is in the standby state, and, carry out trigger word discernment by the data processor, awaken the CPU in time when discerning trigger word, and then control the smart device to respond to the processing instruction corresponding with presetting trigger word by the CPU, consequently, can reduce the power consumption that the smart device is in the non-operating state when guaranteeing that the smart device can be responded to user's instruction in time through this scheme, thereby reduce the consumption of electric energy.
It can be understood that, when the data processor determines that the target recognition result includes the preset trigger word, the data processor may be in a working state, and at this time, compared with the prior art in which the CPU is always in the working state, the possibility of reducing power consumption and saving electric energy is also provided. For example, assume that the CPU is operating at 10 watts per second and the data processor is operating at 2 watts per second. Assuming that the time of the smart device in the inactive state is 7 hours and the time of the smart device in the active state is 1 hour, the smart device consumes at least 80 joules in the prior art, and the power consumption is 24 joules in the embodiment of the present invention. Therefore, compared with the prior art, the embodiment of the invention achieves the effects of reducing power consumption and saving electric energy.
It should be noted that, in a specific application, when the data processor determines that the target recognition result includes the preset trigger word, in order to further reduce power consumption of the intelligent device when responding to the user instruction, as shown in fig. 2, the method for controlling the intelligent device according to the embodiment of the present invention may further include, on the basis of fig. 1:
s105, the data processor itself is switched from the operating state to the standby state.
When the data processor judges that the target recognition result contains the preset trigger word, in order to further reduce the power consumption of the intelligent device when responding to the user instruction, the data processor is switched from the working state to the standby state, at the moment, when the recording unit collects the user voice information again, the collected user voice information is not sent to the data processor, but the collected user voice information is sent to the CPU, when the CPU receives the user voice information sent by the recording unit, the CPU carries out voice recognition on the received user voice information and obtains a voice recognition result, after the voice recognition result is obtained, the intelligent device can obtain response content corresponding to the voice recognition result from a local place or a server and plays the obtained response content.
It can be understood that after receiving the user voice information sent by the recording unit, the CPU can perform voice recognition locally and obtain a voice recognition result; in this case, the server may directly determine the corresponding response content according to the voice recognition result, and send the response content to the intelligent device, and the intelligent device plays the response content.
In order to ensure that the smart device can be effectively switched from the operating state to the full standby state when the user does not need the smart device to respond to the user instruction, so as to reduce power consumption, that is, when the CPU is switched from the operating state to the standby state, the data processor can be switched from the standby state to the operating state, as shown in fig. 3, the smart device control method provided in the embodiment of the present invention may further include, after switching the data processor from the operating state to the standby state, on the basis of fig. 2:
and S106, when a second interrupt signal sent by the CPU is received, switching the data processor from a standby state to a working state, wherein the second interrupt signal is sent when the CPU is switched from the working state to the standby state.
When a user does not need to perform voice interaction with the intelligent device, the intelligent device needs to be switched from a working state to a complete standby state, at the moment, the CPU can be switched from the working state to the standby state, and in order to enable the data processor to be switched from the standby state to the working state, the power consumption of the intelligent device in the complete standby state is reduced while the intelligent device can be awakened in time, so that the consumption of electric energy is reduced, and when the CPU can be switched from the working state to the standby state, a second interrupt signal is sent to the data processor; correspondingly, when the data processor in the standby state receives the second interrupt signal sent by the CPU, the data processor switches itself from the standby state to the operating state, so that the intelligent device enters the full standby state, and then, after the intelligent device enters the full standby state, the data processor may continue to execute the steps of S101 to S104.
Optionally, the CPU switches itself from the operating state to the standby state when detecting that a predetermined condition is satisfied.
Optionally, in a specific embodiment, the predetermined condition is:
and the first time interval is greater than a target time interval threshold, wherein the first time interval is a time interval when the voice information of the user is not received from the moment when the CPU is in the working state.
After the CPU is in a working state, the intelligent device can send the received user voice information to the CPU, when the CPU does not receive the user voice information within a preset time interval threshold, the fact that the user does not perform voice interaction with the intelligent device within a short time is indicated, at the moment, in order to reduce power consumption, the CPU is switched from the working state to a standby state and controls the intelligent device to enter a complete standby state, specifically, the CPU can at least send a second interrupt signal to the data processor, and when the data processor receives the second interrupt signal, the CPU is switched from the standby state to the working state.
It should be noted that, from the time when the CPU is in the operating state, it is possible to receive the voice information within the preset time interval threshold, but the voice information received by the CPU is subjected to voice recognition, and then no valid information is obtained in the voice recognition result, where the valid information refers to a word, or a sentence, that is, the voice information received by the CPU within the preset time interval threshold is not the user voice information. For example, if the user voice information sent by the recording unit to the CPU is noise information, then there is no valid information in the voice recognition result obtained after voice recognition, and at this time, in order to reduce power consumption, the CPU also switches from the operating state to the standby state and sends a second interrupt signal to the data processor, and the data processor switches from the standby state to the operating state when receiving the second interrupt signal.
In addition, the target time interval threshold may be a fixed value set in advance, for example, may be set to 5 seconds, 10 seconds, 15 seconds, 20 seconds, and the like, which are all reasonable; the target time interval threshold may also be determined according to the expression habit, the speech speed, etc. of the user, for example, when the expression habit of the user is that the frequency of speech pause is high or the speech speed is slow, a large target time interval threshold may be set, so as to prevent the CPU from switching from the working state to the standby state when the speech information of the user is incomplete, and control the intelligent device to enter the full standby state; in addition, a target time interval threshold can be determined according to the environmental noise parameter, when the environmental noise is high, a high target time threshold can be set to obtain user voice information needing to be responded, and when the environmental noise is high, in order to prevent the user voice information from being received by mistake, the CPU can be directly switched from the working state to the standby state and controls the intelligent device to enter the full standby state.
In addition, the target time interval threshold may be determined comprehensively according to two or three of the age of the user, the speech rate, and the noise parameter of the environment, and of course, the target time interval threshold may also be determined according to other parameters, which is not limited in the embodiment of the present invention.
Optionally, in a specific embodiment, the predetermined condition is:
and a second time interval is greater than a target time interval threshold, wherein the second time interval is a time interval when the intelligent equipment does not receive the user voice information from the moment when the intelligent equipment finishes responding the interactive instruction corresponding to any user voice information.
After the intelligent equipment responds to the interactive instruction corresponding to any user voice information, if the interactive instruction is within a preset time interval threshold value, the CPU receives the user voice information again, and after voice recognition, when the obtained voice recognition result is effective information, the intelligent equipment can also respond to the interactive instruction corresponding to the user voice information which is received again, wherein the effective information is characters, words or sentences; however, if after the interactive instruction corresponding to any user voice message is responded, the CPU does not receive the user voice message again within the preset time interval threshold, which indicates that the user does not perform voice interaction with the smart device within a short time.
Optionally, in a specific embodiment, the predetermined condition is:
and the voice recognition result corresponding to the user voice information received by the CPU comprises a preset standby word.
When the CPU is in a working state, the recording unit sends the collected user voice information to the CPU, and the CPU performs voice recognition on the received user voice information and obtains a voice recognition result; or the CPU sends the received user voice information to the server, and the server carries out voice recognition and obtains a voice recognition result. When the voice recognition result contains the preset standby word, it indicates that the user does not perform voice interaction with the intelligent device temporarily, at this time, the CPU switches from the working state to the standby state and controls the intelligent device to enter the full standby state from the working state, specifically, the CPU can at least send a second interrupt signal to the data processor, and when the data processor receives the second interrupt signal, the CPU switches from the standby state to the working state.
For example, assuming that the preset standby word is "end", when the CPU performs voice recognition on the received user voice information and the voice recognition result includes the preset standby word "end", the CPU switches from the operating state to the standby state and controls the smart device to enter the full standby state, specifically, at least a second interrupt signal may be sent to the data processor, and when the data processor receives the second interrupt signal, the CPU switches from the standby state to the operating state.
Compared with the prior art, when the intelligent equipment is in a non-working state, only the data processor with low power consumption is in a working state, the CPU is in a standby state, the data processor identifies the awakening words, the CPU is awakened in time when the awakening words are identified, and then the intelligent equipment is awakened by the CPU; moreover, when the intelligent device is in the working state, when the preset condition is met, the CPU can be switched to the standby state from the working state, the intelligent device is controlled to enter the non-working state, and when the intelligent device is in the non-working state, the data processor with low power consumption is in the working state, so that the power consumption of the intelligent device in the non-working state can be reduced while the intelligent device can be timely awakened through the scheme, and the consumption of electric energy is reduced.
Corresponding to the above method embodiment, an embodiment of the present invention provides an intelligent device control apparatus, which is applied to a data processor of an intelligent device, where the data processor is respectively connected to the CPU and a recording unit of the intelligent device in a communication manner, and as shown in fig. 4, the apparatus includes:
a receiving module 410, a voice recognition module 420, a judging module 430 and an interrupt signal sending module 440;
wherein the content of the first and second substances,
a receiving module 410, configured to receive, when the intelligent device is in a full standby state, user voice information sent by the sound recording unit, where the full standby state is at least: the data processor is in a working state, and the CPU is in a standby state;
the voice recognition module 420 is configured to perform voice recognition on the user voice information to obtain a target recognition result;
the judging module 430 is configured to judge whether the target recognition result includes a preset trigger word;
an interrupt signal sending module 440, configured to send a first interrupt signal to the CPU when the determination result of the determining module is yes, so that the CPU switches from a standby state to a working state when receiving the first interrupt signal, and controls the intelligent device to respond to the processing instruction corresponding to the preset trigger word.
Compared with the prior art, the scheme provided by the embodiment of the invention is characterized in that the intelligent device is provided with the data processor with low power consumption, namely, the power consumption of the data processor is lower than that of the CPU. When the intelligent device is in a non-working state, the CPU of the intelligent device is in a standby state, the low-power-consumption data processor is in a working state, specifically, the low-power-consumption data processor receives user voice information sent by the recording unit, carries out voice recognition on the user voice information, obtains a target recognition result, and when the target recognition result contains a preset awakening word, the CPU of the intelligent device enters the working state and awakens the intelligent device.
It can be seen that, in this scheme, when the smart machine is in the non-operating state, only the data processor of low-power consumption is in the operating state, and CPU is in standby state to, awaken up word discernment by the data processor, in time awaken up CPU when discerning awakening up the word, and then awaken up the smart machine by CPU, consequently, can reduce the smart machine and be in the consumption under the non-operating state when guaranteeing that the smart machine can in time be awakened up through this scheme, thereby reduce the consumption of electric energy.
Optionally, the power consumption of the data processor is lower than that of a central processing unit CPU of the smart device.
Optionally, in an embodiment, as shown in fig. 5, the apparatus further includes:
a working state switching module 450, configured to switch the data processor from a working state to a standby state when the determination result of the determining module is yes.
Optionally, in an embodiment, as shown in fig. 6, the apparatus further includes:
an interrupt signal receiving module 460, configured to switch the data processor from the standby state to the operating state when receiving a second interrupt signal sent by the CPU after the interrupt signal sending module switches the data processor from the operating state to the standby state, where the second interrupt signal is sent when the CPU switches from the operating state to the standby state. Optionally, in an embodiment, the data processor is a microprocessor.
Optionally, in an embodiment, the CPU switches the CPU itself from the operating state to the standby state when detecting that a predetermined condition is satisfied.
Optionally, in an embodiment, the predetermined condition is:
and the first time interval is greater than a target time interval threshold, wherein the first time interval is a time interval when the voice information of the user is not received from the moment when the CPU is in the working state.
Optionally, in an embodiment, the predetermined condition is:
and a second time interval is greater than a target time interval threshold, wherein the second time interval is a time interval when the intelligent equipment does not receive the user voice information from the moment when the intelligent equipment finishes responding the interactive instruction corresponding to any user voice information.
Optionally, in an embodiment, the predetermined condition is:
and the voice recognition result corresponding to the user voice information received by the CPU comprises a preset standby word.
Corresponding to the method embodiment, the embodiment of the invention also provides the intelligent device. As shown in fig. 7, the smart device 700 includes: a data processor 710, a central processing unit CPU720 and a recording unit 730; the data processor is respectively in communication connection with the CPU and the recording unit of the intelligent device;
the recording unit is used for acquiring user voice information;
the data processor is used for receiving the user voice information sent by the recording unit when the intelligent equipment is in a complete standby state; carrying out voice recognition on the user voice information to obtain a target recognition result; judging whether the target recognition result contains a preset trigger word or not; if yes, sending a first interrupt signal to the CPU; wherein the full standby state is at least: the data processor is in a working state, and the CPU is in a standby state;
and the CPU is used for switching from a standby state to a working state when receiving the first interrupt signal and controlling the intelligent equipment to respond to the processing instruction corresponding to the preset trigger word.
Compared with the prior art, the scheme provided by the embodiment of the invention is characterized in that the data processor is arranged in the intelligent equipment, and the power consumption of the data processor is lower than that of the CPU. When the intelligent device is in a non-working state, the CPU of the intelligent device is in a standby state, the low-power-consumption data processor is in a working state, specifically, the low-power-consumption data processor receives user voice information sent by the recording unit, performs voice recognition on the user voice information to obtain a target recognition result, and when the target recognition result contains a preset trigger word, the CPU of the intelligent device enters the working state and controls the intelligent device to respond to a processing instruction corresponding to the preset trigger word.
It can be seen that, in this scheme, when the smart device is in the non-operating state, only the data processor of low-power consumption is in the operating state, and the CPU is in the standby state, and, carry out trigger word discernment by the data processor, awaken the CPU in time when discerning trigger word, and then control the smart device to respond to the processing instruction corresponding with presetting trigger word by the CPU, consequently, can reduce the power consumption that the smart device is in the non-operating state when guaranteeing that the smart device can be responded to user's instruction in time through this scheme, thereby reduce the consumption of electric energy.
Optionally, the power consumption of the data processor is lower than the power consumption of a central processing unit CPU of the smart device. Optionally, when the data processor determines that the target recognition result includes a preset trigger word, the data processor is switched from a working state to a standby state.
Optionally, the CPU is further configured to send a second interrupt signal to the data processor when the operating state is switched to the standby state after the intelligent device is controlled to enter the operating state;
and the data processor is further used for switching the data processor from the standby state to the working state when receiving a second interrupt signal sent by the CPU after the data processor is switched from the working state to the standby state.
Optionally, the data processor is a microprocessor.
Optionally, the CPU is specifically configured to switch the CPU itself from an operating state to a standby state when it is detected that a predetermined condition is satisfied.
Optionally, in a specific implementation manner, the predetermined condition is:
and the first time interval is greater than a target time interval threshold, wherein the first time interval is a time interval when the voice information of the user is not received from the moment when the CPU is in the working state.
Optionally, in a specific implementation manner, the predetermined condition is:
and a second time interval is greater than a target time interval threshold, wherein the second time interval is a time interval when the intelligent equipment does not receive the user voice information from the moment when the intelligent equipment finishes responding the interactive instruction corresponding to any user voice information.
Optionally, in a specific implementation manner, the predetermined condition is:
and the voice recognition result corresponding to the user voice information received by the CPU comprises a preset standby word.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims (19)

1. A control method of an intelligent device is characterized in that the control method is applied to a data processor of the intelligent device, the data processor is respectively in communication connection with a CPU and a recording unit of the intelligent device, and the method comprises the following steps:
and receiving user voice information sent by the recording unit when the intelligent device is in a full standby state, wherein the full standby state is at least: the data processor is in a working state, and the CPU is in a standby state;
carrying out voice recognition on the user voice information to obtain a target recognition result;
judging whether the target recognition result contains a preset trigger word or not;
if so, sending a first interrupt signal to the CPU, so that the CPU is switched to a working state from a standby state when receiving the first interrupt signal, and controlling the intelligent device to respond to a processing instruction corresponding to the preset trigger word, wherein the data processor is switched to the standby state from the working state.
2. The method of claim 1, wherein the power consumption of the data processor is lower than the power consumption of a Central Processing Unit (CPU) of the smart device.
3. The method according to claim 1, wherein when it is determined that the target recognition result includes a preset trigger word, the method further comprises:
switching the data processor itself from an operating state to a standby state.
4. The method of claim 3, wherein after switching the data processor itself from an operating state to a standby state, the method further comprises:
and when a second interrupt signal sent by the CPU is received, switching the data processor from a standby state to a working state, wherein the second interrupt signal is sent when the CPU is switched from the working state to the standby state.
5. The method according to any one of claims 1 to 4, wherein the data processor is a microprocessor.
6. The method according to claim 4, characterized in that the CPU switches itself from an operating state to a standby state upon detecting that a predetermined condition is met.
7. The method according to claim 6, wherein the predetermined condition is:
and the first time interval is greater than a target time interval threshold, wherein the first time interval is a time interval when the voice information of the user is not received from the moment when the CPU is in the working state.
8. The method according to claim 6, wherein the predetermined condition is:
and a second time interval is greater than a target time interval threshold, wherein the second time interval is a time interval when the intelligent equipment does not receive the user voice information from the moment when the intelligent equipment finishes responding the interactive instruction corresponding to any user voice information.
9. The method according to claim 6, wherein the predetermined condition is:
and the voice recognition result corresponding to the user voice information received by the CPU comprises a preset standby word.
10. The intelligent equipment control device is characterized in that the intelligent equipment control device is applied to a data processor of intelligent equipment, the data processor is respectively in communication connection with a CPU and a recording unit of the intelligent equipment, and the intelligent equipment control device comprises:
the device comprises a receiving module, a voice recognition module, a judgment module and an interrupt signal sending module;
wherein the content of the first and second substances,
the receiving module is configured to receive the user voice information sent by the recording unit when the intelligent device is in a full standby state, where the full standby state is at least: the data processor is in a working state, and the CPU is in a standby state;
the voice recognition module is used for carrying out voice recognition on the user voice information to obtain a target recognition result;
the judging module is used for judging whether the target recognition result contains a preset trigger word or not;
and the interrupt signal sending module is used for sending a first interrupt signal to the CPU when the judgment result of the judgment module is yes, so that the CPU is switched from a standby state to a working state when receiving the first interrupt signal, and controls the intelligent equipment to respond to a processing instruction corresponding to the preset trigger word, wherein the data processor is switched from the working state to the standby state.
11. The apparatus of claim 10, wherein the power consumption of the data processor is lower than the power consumption of a Central Processing Unit (CPU) of the smart device.
12. The apparatus of claim 10, further comprising:
and the working state switching module is used for switching the data processor from the working state to the standby state when the judgment result of the judgment module is yes.
13. The apparatus of claim 12, further comprising:
and the interrupt signal receiving module is used for switching the data processor from the standby state to the working state when receiving a second interrupt signal sent by the CPU after the interrupt signal sending module switches the data processor from the working state to the standby state, wherein the second interrupt signal is sent when the CPU is switched from the working state to the standby state.
14. The apparatus of any one of claims 10 to 13, wherein the data processor is a microprocessor.
15. The apparatus of claim 13, wherein the CPU switches itself from an operating state to a standby state upon detecting that a predetermined condition is satisfied.
16. The apparatus of claim 15, wherein the predetermined condition is:
and the first time interval is greater than a target time interval threshold, wherein the first time interval is a time interval when the voice information of the user is not received from the moment when the CPU is in the working state.
17. The apparatus of claim 15, wherein the predetermined condition is:
and a second time interval is greater than a target time interval threshold, wherein the second time interval is a time interval when the intelligent equipment does not receive the user voice information from the moment when the intelligent equipment finishes responding the interactive instruction corresponding to any user voice information.
18. The apparatus of claim 15, wherein the predetermined condition is:
and the voice recognition result corresponding to the user voice information received by the CPU comprises a preset standby word.
19. A smart device, the smart device comprising: the system comprises a data processor, a Central Processing Unit (CPU) and a recording unit; the data processor is respectively in communication connection with the central processing unit CPU and the recording unit;
the recording unit is used for acquiring user voice information;
the data processor is used for receiving the user voice information sent by the recording unit when the intelligent equipment is in a complete standby state; carrying out voice recognition on the user voice information to obtain a target recognition result; judging whether the target recognition result contains a preset trigger word or not; if yes, sending a first interrupt signal to the CPU, wherein the full standby state is at least: the data processor is in a working state, and the CPU is in a standby state;
the CPU is used for switching from a standby state to a working state when receiving the first interrupt signal and controlling the intelligent equipment to respond to a processing instruction corresponding to the preset trigger word;
and the data processor is also used for switching the working state to the standby state when the CPU is switched from the standby state to the working state.
CN201710309605.2A 2017-05-04 2017-05-04 Intelligent device control method and device and intelligent device Active CN108806673B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710309605.2A CN108806673B (en) 2017-05-04 2017-05-04 Intelligent device control method and device and intelligent device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710309605.2A CN108806673B (en) 2017-05-04 2017-05-04 Intelligent device control method and device and intelligent device

Publications (2)

Publication Number Publication Date
CN108806673A CN108806673A (en) 2018-11-13
CN108806673B true CN108806673B (en) 2021-01-15

Family

ID=64053604

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710309605.2A Active CN108806673B (en) 2017-05-04 2017-05-04 Intelligent device control method and device and intelligent device

Country Status (1)

Country Link
CN (1) CN108806673B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111283675B (en) * 2018-12-07 2021-08-13 北京猎户星空科技有限公司 Robot action regression control method and device, robot and storage medium
CN109683708A (en) * 2018-12-14 2019-04-26 北京猎户星空科技有限公司 Smart machine control method, device, electronic equipment and storage medium
CN110033764A (en) * 2019-03-08 2019-07-19 中国科学院深圳先进技术研究院 Sound control method, device, system and the readable storage medium storing program for executing of unmanned plane
CN110223693B (en) * 2019-06-21 2021-08-20 北京猎户星空科技有限公司 Robot control method and device, electronic equipment and readable storage medium
CN111240634A (en) * 2020-01-08 2020-06-05 百度在线网络技术（北京）有限公司 Sound box working mode adjusting method and device
CN111369999B (en) * 2020-03-12 2024-05-14 北京百度网讯科技有限公司 Signal processing method and device and electronic equipment
CN112492393A (en) * 2020-11-25 2021-03-12 海信视像科技股份有限公司 Method for realizing MIC switch associated energy-saving mode and display equipment
CN113220073B (en) * 2021-05-06 2023-07-28 恒玄科技(上海)股份有限公司 Control method and device and wearable equipment

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1239361A1 (en) * 2001-02-28 2002-09-11 Canon Kabushiki Kaisha Ink jet recording apparatus provided with interrupt control circuit and method for controlling recording apparatus
CN105094816A (en) * 2015-07-09 2015-11-25 北京君正集成电路股份有限公司 Method for reducing power consumption of intelligent device and intelligent device
CN105511857A (en) * 2015-11-27 2016-04-20 小米科技有限责任公司 System language setting method and device
WO2016125988A1 (en) * 2015-02-05 2016-08-11 주식회사 현대아이티 Multi-power board energy saving device for electronic bulletin board
CN105957527A (en) * 2016-05-16 2016-09-21 珠海格力电器股份有限公司 Electric appliance speech control method and device and speech control air-conditioner
CN106055079A (en) * 2016-05-31 2016-10-26 广东欧珀移动通信有限公司 Method and device for managing central processing unit

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105529025B (en) * 2014-09-28 2019-12-24 联想(北京)有限公司 Voice operation input method and electronic equipment
CN105575395A (en) * 2014-10-14 2016-05-11 中兴通讯股份有限公司 Voice wake-up method and apparatus, terminal, and processing method thereof

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1239361A1 (en) * 2001-02-28 2002-09-11 Canon Kabushiki Kaisha Ink jet recording apparatus provided with interrupt control circuit and method for controlling recording apparatus
WO2016125988A1 (en) * 2015-02-05 2016-08-11 주식회사 현대아이티 Multi-power board energy saving device for electronic bulletin board
CN105094816A (en) * 2015-07-09 2015-11-25 北京君正集成电路股份有限公司 Method for reducing power consumption of intelligent device and intelligent device
CN105511857A (en) * 2015-11-27 2016-04-20 小米科技有限责任公司 System language setting method and device
CN105957527A (en) * 2016-05-16 2016-09-21 珠海格力电器股份有限公司 Electric appliance speech control method and device and speech control air-conditioner
CN106055079A (en) * 2016-05-31 2016-10-26 广东欧珀移动通信有限公司 Method and device for managing central processing unit

Also Published As

Publication number Publication date
CN108806673A (en) 2018-11-13

Similar Documents

Publication Publication Date Title
CN108806673B (en) Intelligent device control method and device and intelligent device
CN108231079B (en) Method, apparatus, device and computer-readable storage medium for controlling electronic device
CN106910500B (en) Method and device for voice control of device with microphone array
CN106847285B (en) Robot and voice recognition method thereof
CN104347072A (en) Remote-control unit control method and device and remote-control unit
CN102905029A (en) Mobile phone and method for looking for mobile phone through intelligent voice
CN111161714A (en) Voice information processing method, electronic equipment and storage medium
CN105677004A (en) Terminal processing method and terminal
CN111599361A (en) Awakening method and device, computer storage medium and air conditioner
CN110968353A (en) Central processing unit awakening method and device, voice processor and user equipment
CN110727821A (en) Method, apparatus, system and computer storage medium for preventing device from being awoken by mistake
CN110853644B (en) Voice wake-up method, device, equipment and storage medium
CN103901782A (en) Sound control method, electronic device and sound control apparatus
CN103686962A (en) Low-power-consumption mobile terminal awakening method and device
KR20180132011A (en) Electronic device and Method for controlling power using voice recognition thereof
CN112230877A (en) Voice operation method and device, storage medium and electronic equipment
CN108665900B (en) Cloud wake-up method and system, terminal and computer readable storage medium
CN110515462A (en) It is a kind of intelligence wearable device in apply control method, device
CN111128201A (en) Interaction method, device, system, electronic equipment and storage medium
CN112233676A (en) Intelligent device awakening method and device, electronic device and storage medium
CN111954868A (en) Multi-voice assistant control method, device, system and computer readable storage medium
CN104598192A (en) Information processing method and electronic equipment
CN108093350B (en) Microphone control method and microphone
CN111792465B (en) Elevator control system and method
CN116705033A (en) System on chip for wireless intelligent audio equipment and wireless processing method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant