WO2020000637A1 - 基于声音的设备控制方法、装置、设备及存储介质 - Google Patents

基于声音的设备控制方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2020000637A1
WO2020000637A1 PCT/CN2018/103790 CN2018103790W WO2020000637A1 WO 2020000637 A1 WO2020000637 A1 WO 2020000637A1 CN 2018103790 W CN2018103790 W CN 2018103790W WO 2020000637 A1 WO2020000637 A1 WO 2020000637A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
user
unlocking
sound
instruction
Prior art date
Application number
PCT/CN2018/103790
Other languages
English (en)
French (fr)
Inventor
潘燕飞
Original Assignee
平安科技（深圳）有限公司
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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2020000637A1 publication Critical patent/WO2020000637A1/zh

Links

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
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • 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
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • 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
    • 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
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/441—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card
    • H04N21/4415—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card using biometric characteristics of the user, e.g. by voice recognition or fingerprint scanning

Definitions

  • the present application relates to the field of home appliances, and in particular, to a sound-based device control method, apparatus, device, and computer-readable storage medium.
  • the TV has become one of the essential appliances in family life, and the TV is no longer limited to the function of receiving only TV programs, but is developing in the direction of intelligence.
  • Smart TV breaks through the old model of traditional TV.
  • users can implement more interactive and personalized customization functions according to the situation and needs.
  • many TVs on the market have the function of child lock, that is, to lock some functions by a simple password input method, thereby preventing children at home from watching the TV uncontrollably.
  • many children have a strong learning ability, it is easy to remember the unlock password, and then they can unlock it with the unlock password. Therefore, the traditional child lock does not play a corresponding role in many cases. How to set the child lock of a smart TV to be opened by a specific person has become a technical problem to be solved urgently.
  • the main purpose of this application is to provide a sound-based device control method, device, device, and computer-readable storage medium, which are aimed at solving the technical problem that the unlocking password of the existing child lock is too simple.
  • the sound-based device control method includes the following steps:
  • the user voice information is parsed to generate user semantic information, and it is determined whether the user semantic information is unlocked information ;
  • an unlocking instruction is generated, and the child lock is unlocked according to the unlocking instruction.
  • generating an unlocking instruction and controlling the unlocking of the child lock according to the unlocking instruction includes:
  • the sound-based device control method further includes:
  • training voice information and corresponding training semantic information input by the user are collected, and a preset voiceprint recognition model and a preset semantic analysis model are trained according to the training voice information and the training semantic information.
  • the method further includes:
  • an unlock instruction is generated, and a program corresponding to the playback-locked program information is played correspondingly according to a program identifier corresponding to the playback-locked program information.
  • an unlock instruction is generated, and a program corresponding to the playback-locked program information is played according to a program identifier corresponding to the playback-locked program information
  • a program identifier corresponding to the playback-locked program information
  • a lock instruction is generated, and the child lock is controlled to lock according to the lock instruction.
  • the method further includes:
  • an unlock failure instruction is generated, and a reminder message of the unlock failure is displayed through the display module.
  • the user's voice information is parsed to generate user semantic information, and the user is judged
  • the steps of whether the semantic information is unlocked include:
  • generating an unlocking instruction, and controlling the unlocking of the child lock according to the unlocking instruction includes:
  • the present application further provides a sound-based device control apparatus, where the sound-based device control apparatus includes:
  • a voiceprint judging module configured to collect user voice information of the current user, and determine whether the voiceprint information in the user voice information matches the voiceprint information of an authorized user with unlocking authority;
  • the semantic judgment module is configured to: when determining that the voiceprint information in the user's voice information matches the voiceprint information of the authorized user, analyze the user's voice information to generate user semantic information, and judge the user Whether the semantic information is unlocked information;
  • An unlocking module is configured to generate an unlocking instruction when determining that the user semantic information is the unlocking information, and control the child lock to be unlocked according to the unlocking instruction.
  • the present application further provides a sound-based device control device.
  • the sound-based device control device includes a processor, a memory, and a processor stored in the memory and executable by the processor.
  • Computer-readable instructions wherein the computer-readable instructions, when executed by the processor, implement the steps of the sound-based device control method as described above.
  • the present application further provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer-readable instructions, wherein when the computer-readable instructions are executed by a processor, To implement the steps of the sound-based device control method as described above.
  • This application collects the user's voice information of the current user and determines whether the voiceprint information in the user's voice information matches the voiceprint information of an authorized user with unlocking authority; in determining the voiceprint information in the user's voice information
  • the voiceprint information of the authorized user is matched, the user's voice information is parsed to generate user semantic information, and it is determined whether the user semantic information is unlocked information; it is determined that the user semantic information is the unlocked information Information, an unlock instruction is generated, and the child lock is unlocked according to the unlock instruction.
  • the user's voiceprint information is used as the unlocking password, which solves the technical problem that the existing unlocking password of the child lock is too simple, and ensures that children cannot use their parental rights to unlock the device.
  • FIG. 1 is a schematic diagram of a hardware structure of a sound-based device control device involved in a solution according to an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a first embodiment of a sound-based device control method of the present application
  • FIG. 3 is a schematic flowchart of a second embodiment of a sound-based device control method of the present application.
  • FIG. 4 is a schematic flowchart of a third embodiment of a sound-based device control method of the present application.
  • FIG. 5 is a schematic diagram of functional modules of a first embodiment of a sound-based device control apparatus of the present application.
  • the sound-based device control method is mainly applied to a sound-based device control device.
  • the sound-based device control device may be a device with display and processing functions such as a PC, a portable computer, or a mobile terminal.
  • FIG. 1 is a schematic diagram of a hardware structure of a sound-based device control device involved in a solution according to an embodiment of the present application.
  • the sound-based device control device may include a processor 1001 (for example, a CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005.
  • the communication bus 1002 is used to implement connection and communication between these components.
  • the user interface 1003 may include a display and an input unit such as a keyboard.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface.
  • the memory 1005 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory, the memory 1005 may optionally be a storage device independent of the foregoing processor 1001.
  • FIG. 1 does not constitute a limitation on the sound-based device control device, and may include more or fewer components than shown in the figure, or combine some components, or different Parts arrangement.
  • the memory 1005 as a computer-readable storage medium in FIG. 1 may include an operating system, a network communication module, and computer-readable instructions.
  • a network communication module is mainly used to connect to a server and perform data communication with the server; and the processor 1001 can call computer-readable instructions stored in the memory 1005 and execute the sound-based device control method provided in the embodiment of the present application. .
  • An embodiment of the present application provides a sound-based device control method.
  • FIG. 2 is a schematic flowchart of a first embodiment of a sound-based device control method of the present application.
  • the device control method is applied to a device control device.
  • the device control device includes an information acquisition module, a voiceprint recognition module, a speech analysis module, a semantic recognition module, and an unlocking module.
  • the sound-based device control method It includes the following steps:
  • Step S10 Collect user voice information of the current user, and determine whether the voiceprint information in the user voice information matches the voiceprint information of an authorized user with unlocking authority;
  • TV sets have not only fulfilled the function of only receiving TV programs, but also developed in the direction of intelligence.
  • Smart TV breaks through the old model of traditional TV.
  • users can implement more interactive and personalized customization functions according to the situation and needs.
  • many TVs on the market have the function of child lock, that is, to lock some functions by a simple password input method, thereby preventing children at home from watching the TV uncontrollably.
  • many children have a strong learning ability, it is easy to remember the unlock password, and then they can unlock it with the unlock password. Therefore, the traditional child lock does not play a corresponding role in many cases. How to set the child lock of a smart TV to be opened by a specific person has become a technical problem to be solved urgently.
  • a sound-based device control method can add a voiceprint recognition module based on the existing smart TV or other terminals with a voice information acquisition module and a voice recognition module, and verify the user's voice information through the voiceprint recognition module and the voice recognition module.
  • the device control method can add a voiceprint recognition module based on the existing smart TV or other terminals with a voice information acquisition module and a voice recognition module, and verify the user's voice information through the voiceprint recognition module and the voice recognition module.
  • the voice information of an unlockable user can be entered and stored in advance, and the voice information of the user can be set as the voice information of the authorized user.
  • a parent user inputs his own voice information through a remote control in advance, and stores the voice information. Upload it to the TV's storage module for storage, or store your own voice information to the SD card through the input device, and then insert the SD card into the TV.
  • the voiceprint recognition module compares the voiceprint information of the user voice information with the voiceprint information of the pre-stored voice information.
  • Step S20 When it is determined that the voiceprint information in the user's voice information matches the voiceprint information of the authorized user, the user's voice information is parsed to generate user semantic information, and it is determined whether the user semantic information is For unlocking information;
  • the voiceprint recognition module determines that the voiceprint information of the user's voice information is consistent with the voiceprint information of the pre-stored voice information, it means that the current user is a parent user with unlocking authority, and can generate a first unlock instruction.
  • the first unlock instruction is then sent to the unlock module, and the user voice information is sent to the voice analysis module.
  • the voiceprint identification module determines that the voice information of the user is inconsistent with the voiceprint information of the pre-stored voice information, it indicates that the current user is an illegal user without unlocking authority, such as a child user, and can generate an unlock failure instruction, and
  • the display terminal displays a reminder message indicating that the unlock has failed. If there is no operation permission information, a prompt message of "the current user does not have operation permission" is displayed on the current TV screen.
  • the voiceprint information in the user's voice information matches the voiceprint information of the authorized user, generating first unlock information; sending the user voice information to the voice analysis module for analysis, Generate user semantic information and determine whether the user semantic information is unlocked information.
  • step S10 the method further includes:
  • an unlock failure instruction is generated, and a reminder message of the unlock failure is displayed through the display module.
  • the voiceprint identification module determines that the voiceprint information of the current user does not match the voiceprint information of a user with a preset authority
  • the current user is identified as a user who does not have unlocking authority, and is displayed through the display module.
  • Reminder message for unlock failure That is, if the voiceprint recognition module judges that the voice information of the user is inconsistent with the voiceprint information of the pre-stored voice information, it means that the current user is an illegal user without unlocking authority, such as a child user, and can generate an unlock failure instruction, and A reminder message indicating the unlock failure is displayed on the display terminal. If there is no operation permission information, a prompt message of "the current user does not have operation permission" is displayed on the current TV screen.
  • step S30 when it is determined that the user semantic information is the unlock information, an unlock instruction is generated, and the child lock is controlled to be unlocked according to the unlock instruction.
  • the voice analysis module when the voice analysis module receives user voice information, the user voice information is parsed and converted, and corresponding user semantic information is generated according to a preset voice conversion list, that is, the voice message is converted into semantic information.
  • the user voice information is then sent to the semantic recognition module.
  • the semantic recognition module compares the user semantic message with pre-stored unlocked semantic information to determine whether the user semantic information is unlocked information.
  • the semantic recognition module determines that the user semantic information is unlocking information, it generates a second unlocking instruction, and sends the second unlocking instruction to the unlocking module.
  • the unlocking module receives the first unlocking instruction and the second unlocking instruction, it can control the child lock of the television to unlock.
  • the information collection module is provided in a remote controller corresponding to the child lock to be used.
  • the remote controller includes at least voice buttons. When the user uses the remote controller to collect voice information, press the voice button to accept voice input and release The voice button ends voice input.
  • Voiceprint recognition module, speech analysis module and semantic recognition module can be set in the cloud server.
  • a second unlock information is generated; an unlock instruction is generated according to the first unlock information and the second unlock information, and a child is controlled according to the unlock instruction The lock is unlocked.
  • This embodiment collects user voice information of the current user, and determines whether the voiceprint information in the user voice information matches the voiceprint information of an authorized user with unlocking authority; in determining the voiceprint in the user voice information, When the information matches the voiceprint information of the authorized user, the user's voice information is parsed to generate user semantic information, and it is determined whether the user semantic information is unlocked information; when the user semantic information is determined to be the When the information is unlocked, an unlock instruction is generated, and the child lock is unlocked according to the unlock instruction.
  • the user's voiceprint information is used as the unlocking password, which solves the technical problem that the existing unlocking password of the child lock is too simple, and ensures that children cannot use their parental rights to unlock the device.
  • FIG. 3 is a schematic flowchart of a second embodiment of a sound-based device control method of the present application.
  • the step S30 specifically includes:
  • Step S31 When it is determined that the user semantic information is the unlocking information, generate an unlocking instruction, and send a reminder message whether to allow unlocking to a preset terminal;
  • step S32 it is determined whether a confirmation unlocking instruction fed back by the preset terminal is received, and the child lock is controlled to be unlocked when the confirmation unlocking instruction is received.
  • the secondary verification can be performed again through the mobile terminal of the authorized user.
  • the preset terminal may be a mobile phone of an authorized user or another electronic terminal carried by the user.
  • the semantic recognition module compares the user semantic information with a list of pre-stored instructions, and determines whether the user voice information is the unlock information instruction in the pre-stored instruction list. Match. If the user's voice information matches the unlock information instruction, it is determined that the user sent the unlocked voice information to the television, generates an unlock instruction, and sends the unlock instruction to the unlock module.
  • the unlocking module receives the unlocking instruction, in order to further confirm whether the unlocking instruction is sent by the authorized user, to prevent others from using the recording of the authorized user for unlocking, and generating a reminder message of whether the unlocking is allowed to the preset terminal.
  • the preset terminal may be a mobile terminal of a pre-bound authorized user for the authorized user to confirm whether a child lock unlock operation can be performed.
  • the user can trigger the unlock confirmation command on the mobile terminal through the function button that allows unlocking.
  • the unlocking module controls the child lock to be unlocked when receiving the unlock confirmation confirmation feedback from the preset terminal. In this embodiment, the authorized user can also be informed of the unlocking of the child lock of the TV terminal in time.
  • FIG. 4 is a schematic flowchart of a third embodiment of a sound-based device control method of the present application.
  • the step S30 specifically includes:
  • Step S33 When determining that the user semantic information is non-unlocked information, determine whether the user semantic information is playback-locked program information through a preset instruction list;
  • step S34 if it is determined that the user semantic information is the playback-locked program information, an unlock instruction is generated, and a program corresponding to the playback-locked program information is played correspondingly according to a program identifier corresponding to the playback-locked program information.
  • the semantic recognition module when it receives user semantic information converted by the voice recognition module, it determines whether the user semantic information is unlocked information. When it is determined that the user semantic information is inconsistent with the unlock information, that is, the user semantic information is non-unlock information. The user semantic information is further compared with a pre-stored instruction list to determine whether the user semantic information is consistent with the locked program information, that is, whether the user semantic information is the locked program information. If the user semantic information is consistent with the locked program information, an unlock instruction is generated, and a program identifier corresponding to the play-locked program information is sent to a display module to control the display module to play the locked program information correspondingly. That is, the authorized user can directly speak the locked program information to the TV, directly unlock and watch the locked program information, further improving the user experience.
  • step S34 the method further includes:
  • a lock instruction is generated, and the child lock is controlled to lock according to the lock instruction.
  • the child lock can be locked again by a voice message.
  • the information acquisition module receives the voice information sent by the current user, it serves as secondary voice information, and the secondary voice information is parsed by the voice analysis module, and converted into secondary semantic information.
  • the secondary semantic information is sent to the semantic recognition module.
  • the semantic recognition module compares the secondary semantic information with a preset instruction list to determine whether the secondary semantic information is lock information. If it is determined that the secondary semantic information is lock information, a lock instruction is generated, and the child lock is controlled to lock according to the lock instruction.
  • the sound-based device control method further includes:
  • training voice information and corresponding training semantic information input by the user are collected, and a preset voiceprint recognition model and a preset semantic analysis model are trained according to the training voice information and the training semantic information.
  • voice-controlled TV there are relatively few voice authentications for small languages, most of which are English, Chinese, and languages of countries with large populations. Therefore, for the elderly / children who only understand the local language, there will be language barriers in terminals such as voice-controlled TV.
  • it can help the elderly to enter some commonly used Voice instructions, such as letting the elderly say common instructions such as turning on, unlocking, selecting channels (central one, central three, etc.) or shutting down according to their own language, store the voice instructions spoken by the elderly to the voiceprint recognition model, and The voiceprint information corresponding to the voice instruction is set as the authorized user in the voiceprint recognition model.
  • the voice instruction is then stored in a semantic analysis model of a voice analysis module, and corresponding semantic information is set for the voice instruction in the semantic analysis model, so that the semantic analysis model can identify the voice information.
  • an embodiment of the present application further provides a sound-based device control apparatus.
  • FIG. 5 is a schematic diagram of functional modules of a first embodiment of a sound-based device control apparatus of the present application.
  • the sound-based device control apparatus includes:
  • the voiceprint determination module 10 is configured to collect user voice information of the current user, and determine whether the voiceprint information in the user voice information matches the voiceprint information of an authorized user with unlocking authority;
  • the semantic judging module 20 is configured to: when determining that the voiceprint information in the user's voice information matches the voiceprint information of the authorized user, analyze the user's voice information to generate user semantic information, and judge the user Whether the user's semantic information is unlocked information;
  • the unlocking module 30 is configured to generate an unlocking instruction when determining that the user semantic information is the unlocking information, and control the child lock to be unlocked according to the unlocking instruction.
  • unlocking module 30 further includes:
  • a secondary verification unit configured to generate an unlocking instruction when determining that the user semantic information is the unlocking information, and send a reminder message whether to allow unlocking to a preset terminal;
  • the first unlocking unit is configured to determine whether a confirmation unlocking instruction fed back by the preset terminal is received, and control the child lock to be unlocked when the confirmation unlocking instruction is received.
  • unlocking module 30 further includes:
  • a program judging unit configured to determine whether the user semantic information is playback-locked program information through a preset instruction list when determining that the user semantic information is non-unlocked information
  • a second unlocking unit configured to generate an unlocking instruction if it is determined that the user semantic information is the playback-locked program information, and according to the program identifier corresponding to the playback-locked program information, correspondingly play the corresponding playback-locked program information. program.
  • unlocking unit 30 further includes:
  • a lock judging unit configured to: upon receiving the secondary voice information of the current user, parse the secondary voice information to generate secondary semantic information, and determine whether the secondary semantic information is locked information;
  • the locking unit is configured to generate a lock instruction when determining that the secondary semantic information is the lock information, and control the child lock to be locked according to the lock instruction.
  • the sound-based equipment device further includes:
  • a training module is configured to collect training voice information and corresponding training semantic information input by a user when receiving a training instruction triggered by a user operation, and train a preset voiceprint recognition model and pre-training based on the training voice information and training semantic information. Set up a semantic analysis model.
  • Each module in the sound-based device control apparatus corresponds to each step in the embodiment of the sound-based device control method, and its functions and implementation processes are not described here one by one.
  • an embodiment of the present application further provides a computer-readable storage medium.
  • the computer-readable storage medium of the present application stores computer-readable instructions, wherein the computer-readable storage medium may be a non-volatile readable storage medium, and when the computer-readable instructions are executed by a processor, the implementation is as described above. Steps of a sound-based device control method.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Selective Calling Equipment (AREA)
  • Lock And Its Accessories (AREA)

Abstract

本申请提供一种基于声音的设备控制方法、装置、设备及计算机可读存储介质，该方法通过采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配；在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。通过用户的声纹信息作为解锁密码，解决了现有儿童锁的解锁密码过于简单的技术问题，确保儿童无法冒用父母的身份权限来解锁设备。

Description

基于声音的设备控制方法、装置、设备及存储介质
本申请要求于2018年6月27日提交中国专利局、申请号为201810675754.5、发明名称为“基于声音的设备控制方法、装置、设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请涉及家电设备领域，尤其涉及一种基于声音的设备控制方法、装置、设备及计算机可读存储介质。
背景技术
目前，电视机已成为家庭生活中必不可少的电器之一，而且电视机不再局限于只接收电视节目的功能，而是面向智能化方向发展。智能电视突破了传统电视的旧模式，用户在观看电视的时候，可以根据情况和需要实现更多的交互和个性定制功能。目前市场上许多电视都拥有儿童锁的功能，即以简单的密码输入的方式来锁定部分功能，从而防止家里的小孩子无节制的观看电视。但是很多小孩的学习能力较强，很容易记住解锁密码，然后即可通过解锁密码解锁。所以，传统儿童锁在很多情况下没有起到相应的作用。如何将智能电视的儿童锁设定为只能由特定的人打开，成为了目前亟待解决的技术问题。
发明内容
本申请的主要目的在于提供一种基于声音的设备控制方法、装置、设备及计算机可读存储介质，旨在解决现有儿童锁的解锁密码过于简单的技术问题。
为实现上述目的，本申请提供一种基于声音的设备控制方法，所述基于声音的设备控制方法包括以下步骤：
采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配；
在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；
在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。
可选地，所述在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁的步骤包括：
在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并发送是否允许解锁的提醒消息至预设终端；
判断是否接收到所述预设终端反馈的确认解锁指令，并在接收到所述确认解锁指令时控制所述儿童锁解锁。
可选地，所述基于声音的设备控制方法还包括：
在接收到用户操作触发的训练指令时，采集用户输入的训练语音信息以及对应的训练语义信息，并根据所述训练语音信息以及训练语义信息训练预设声纹识别模型和预设语义分析模型。
可选地，所述在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息的步骤之后，还包括：
在判定所述用户语义信息为非解锁信息时，通过预设指令列表，判断所述用户语义信息是否为播放锁定节目信息；
若判定所述用户语义信息为所述播放锁定节目信息，则生成解锁指令，并根据所述播放锁定节目信息对应的节目标识，对应播放所述播放锁定节目信息对应的节目。
可选地，所述若判定所述用户语义信息为所述播放锁定节目信息，则生成解锁指令，并根据所述播放锁定节目信息对应的节目标识，对应播放所述播放锁定节目信息对应的节目的步骤之后，还包括：
在接收到所述当前用户的二次语音信息时，将所述二次语音信息进行解析，生成二次语义信息，并判断所述二次语义信息是否为锁定信息；
在判定所述二次语义信息为所述锁定信息时，生成锁定指令，并根据所述锁定指令控制儿童锁上锁。
可选地，所述采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配的步骤之后，还包括：
在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息不匹配时，生成解锁失败指令，并通过显示模块显示解锁失败的提醒消息。
可选地，所述在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息的步骤包括：
在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，生成第一解锁信息；
将所述用户语音信息发送至所述语音分析模块进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；
所述在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁的步骤包括：
在判定所述用户语义信息为所述解锁信息时，生成第二解锁信息；
根据所述第一解锁信息和所述第二解锁信息，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。
此外，为实现上述目的，本申请还提供一种基于声音的设备控制装置，所述基于声音的设备控制装置包括：
声纹判断模块，用于采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配；
语义判断模块，用于在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；
解锁模块，用于在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。
此外，为实现上述目的，本申请还提供一种基于声音的设备控制设备，所述基于声音的设备控制设备包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的计算机可读指令，其中所述计算机可读指令被所述处理器执行时，实现如上述的基于声音的设备控制方法的步骤。
此外，为实现上述目的，本申请还提供一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有计算机可读指令，其中所述计算机可读指令被处理器执行时，实现如上述的基于声音的设备控制方法的步骤。
本申请通过采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配；在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。通过用户的声纹信息作为解锁密码，解决了现有儿童锁的解锁密码过于简单的技术问题，确保儿童无法冒用父母的身份权限来解锁设备。
附图说明
图1为本申请实施例方案中涉及的基于声音的设备控制设备的硬件结构示意图；
图2为本申请基于声音的设备控制方法第一实施例的流程示意图；
图3为本申请基于声音的设备控制方法第二实施例的流程示意图；
图4为本申请基于声音的设备控制方法第三实施例的流程示意图；
图5为本申请基于声音的设备控制装置第一实施例的功能模块示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请实施例涉及的基于声音的设备控制方法主要应用于基于声音的设备控制设备，该基于声音的设备控制设备可以是PC、便携计算机、移动终端等具有显示和处理功能的设备。
参照图1，图1为本申请实施例方案中涉及的基于声音的设备控制设备的硬件结构示意图。本申请实施例中，基于声音的设备控制设备可以包括处理器1001（例如CPU），通信总线1002，用户接口1003，网络接口1004，存储器1005。其中，通信总线1002用于实现这些组件之间的连接通信；用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard）；网络接口1004可选的可以包括标准的有线接口、无线接口（如WI-FI接口）；存储器1005可以是高速RAM存储器，也可以是稳定的存储器（non-volatile memory），例如磁盘存储器，存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解，图1中示出的硬件结构并不构成对基于声音的设备控制设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
继续参照图1，图1中作为一种计算机可读存储介质的存储器1005可以包括操作***、网络通信模块以及计算机可读指令。
在图1中，网络通信模块主要用于连接服务器，与服务器进行数据通信；而处理器1001可以调用存储器1005中存储的计算机可读指令，并执行本申请实施例提供的基于声音的设备控制方法。
本申请实施例提供了一种基于声音的设备控制方法。
参照图2，图2为本申请基于声音的设备控制方法第一实施例的流程示意图。
本实施例中，所述设备控制方法应用于设备控制装置，所述设备控制装置包括信息采集模块、声纹识别模块、语音分析模块、语义识别模块和解锁模块，所述基于声音的设备控制方法包括以下步骤：
步骤S10，采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配；
目前电视机已经不仅满足只是接收电视节目的功能，而是面向智能化方向发展。智能电视突破了传统电视的旧模式，用户在观看电视的时候，可以根据情况和需要实现更多的交互和个性定制功能。目前市场上许多电视都拥有儿童锁的功能，即以简单的密码输入的方式来锁定部分功能，从而防止家里的小孩子无节制的观看电视。但是很多小孩的学习能力较强，很容易记住解锁密码，然后即可通过解锁密码解锁。所以，传统儿童锁在很多情况下没有起到相应的作用。如何将智能电视的儿童锁设定为只能由特定的人打开，成为了目前亟待解决的技术问题。
本实施例中，为了解决上述技术问题，提供一种基于声音的设备控制方法。所述设备控制方法可以在现有具有语音信息采集模块和语音识别模块的智能电视或者其他终端的基础上，增加声纹识别模块，通过声纹识别模块和语音识别模块对用户的语音信息进行验证，从而判断当前用户是否为具有解锁权限的用户。具体为通过遥控器或者电视机等显示终端上的麦克风等信息采集模块，获取当前用户的用户语音信息，并将所述用户语音信息发送至声纹识别模块进行用户身份判断，即判断当前用户是否为具有解锁权限的权限用户。其中，可预先将可解锁的用户的语音信息进行录入并存储，并将该用户的语音信息设置为权限用户的语音信息，如家长用户预先通过遥控器录入自己的语音信息，并将该语音信息上传至电视机的存储模块进行存储，或者是通过录入设备将自己的语音信息存储至SD卡，然后将SD卡***电视机。所述声纹识别模块将所述用户语音信息的声纹信息与预存语音信息的声纹信息进行比对。
步骤S20，在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；
本实施例中，所述声纹识别模块在判断所述用户语音信息的声纹信息与预存语音信息的声纹信息一致时，即表示当前用户为具有解锁权限的家长用户，可生成第一解锁指令。然后将所述第一解锁指令发送至所述解锁模块，并将所述用户语音信息发送至所述语音分析模块。若所述声纹识别模块在判断所述用户语音信息与预存语音信息的声纹信息不一致时，即表示当前用户为不具有解锁权限的非法用户，如儿童用户，可生成解锁失败指令，并在显示终端上显示解锁失败的提醒消息，如若为无操作权限信息，则在当前电视画面上短暂显示“当前用户无操作权限”的提示信息。
进一步地，在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，生成第一解锁信息；将所述用户语音信息发送至所述语音分析模块进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息。
进一步地，步骤S10之后，还包括：
在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息不匹配时，生成解锁失败指令，并通过显示模块显示解锁失败的提醒消息。
本实施例中，在所述声纹识别模块判断所述当前用户的声纹信息与预设权限用户的声纹信息不匹配时，则标识当前用户为不具有解锁权限的用户，通过显示模块显示解锁失败的提醒消息。即若所述声纹识别模块在判断所述用户语音信息与预存语音信息的声纹信息不一致时，即表示当前用户为不具有解锁权限的非法用户，如儿童用户，可生成解锁失败指令，并在显示终端上显示解锁失败的提醒消息，如若为无操作权限信息，则在当前电视画面上短暂显示“当前用户无操作权限”的提示信息。
步骤S30，在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。
本实施例中，所述语音分析模块在接收到用户语音信息时，将所述用户语音信息进行解析转换，根据预设语音转换列表，生成对应的用户语义信息，即将语音消息转换为语义信息。然后将所述用户语音信息发送至所述语义识别模块。所述语义识别模块在接收到所述用户语义信息时，将所述用户语义消息与预存解锁语义信息进行比较，判断所述用户语义信息是否为解锁信息。所述语义识别模块在判定所述用户语义信息为解锁信息时，生成第二解锁指令，并将所述第二解锁指令发送至所述解锁模块。所述解锁模块在接收到第一解锁指令和第二解锁指令时，即可控制电视机的儿童锁进行解锁。具体实施例中，信息采集模块设置在与欲使用的儿童锁对应的遥控器中，遥控器至少包括语音按键，当用户使用遥控器对语音信息采集时，按下语音按键接受语音输入，松开语音按键结束语音输入。声纹识别模块、语音分析模块和语义识别模块可设置在云端服务器中。
进一步地，在判定所述用户语义信息为所述解锁信息时，生成第二解锁信息；根据所述第一解锁信息和所述第二解锁信息，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。
本实施例通过采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配；在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。通过用户的声纹信息作为解锁密码，解决了现有儿童锁的解锁密码过于简单的技术问题，确保儿童无法冒用父母的身份权限来解锁设备。
参照图3，图3为本申请基于声音的设备控制方法第二实施例的流程示意图。
基于上述图2所示实施例，本实施例中，所述步骤S30具体包括：
步骤S31，在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并发送是否允许解锁的提醒消息至预设终端；
步骤S32，判断是否接收到所述预设终端反馈的确认解锁指令，并在接收到所述确认解锁指令时控制所述儿童锁解锁。
本实施例中，为了保证只有权限用户可以解锁，可通过权限用户的手机终端再次进行二次验证。其中，预设终端可以是权限用户的手机或者其他随身携带的电子终端。具体地，所述语义识别模块在接收到语音识别模块转换的用户语义信息时，将所述用户语义信息与预存指令列表进行对比，判断所述用户语音信息是否与预存指令列表中的解锁信息指令相匹配。若所述用户语音信息与所述解锁信息指令相匹配，则判定用户向电视机发送了解锁的语音信息，生成解锁指令，并将所述解锁指令发送至解锁模块。所述解锁模块在接收到所述解锁指令时，为了进一步确认是否为权限用户发送的解锁指令，避免他人使用权限用户的录音等进行解锁，生成是否允许解锁的提醒消息至预设终端。预设终端可以是预先绑定的权限用户的手机终端，以供权限用户确认是否可以进行儿童锁解锁操作。用户可以在手机终端上通过允许解锁的功能按钮触发确认解锁指令。所述解锁模块在接收到所述预设终端反馈的确认解锁指令时，控制儿童锁解锁。本实施例中，还可以使权限用户及时了解电视终端的儿童锁的解锁情况。
参照图4，图4为本申请基于声音的设备控制方法第三实施例的流程示意图。
基于上述图3所示实施例，本实施例中，所述步骤S30具体包括：
步骤S33，在判定所述用户语义信息为非解锁信息时，通过预设指令列表，判断所述用户语义信息是否为播放锁定节目信息；
步骤S34，若判定所述用户语义信息为所述播放锁定节目信息，则生成解锁指令，并根据所述播放锁定节目信息对应的节目标识，对应播放所述播放锁定节目信息对应的节目。
本实施例中，所述语义识别模块在接收到所述语音识别模块转换的用户语义信息时，判断所述用户语义信息是否为解锁信息。在判定所述用户语义信息与解锁信息不一致时，即所述用户语义信息为非解锁信息。进一步将所述用户语义信息与预存指令列表进行比对，判断所述用户语义信息是否与被锁定的节目信息一致，即判断所述用户语义信息是否为播放锁定节目信息。若所述用户语义信息与被锁定的节目信息一致，则生成解锁指令，并将所述播放锁定节目信息对应的节目标识发送至显示模块，以控制所述显示模块对应播放被锁定的节目信息。即权限用户可以直接向电视机说出被锁定节目信息，直接进行解锁并观看被锁定节目信息，进一步提升用户体验。
进一步地，步骤S34之后，还包括：
在接收到所述当前用户的二次语音信息时，将所述二次语音信息进行解析，生成二次语义信息，并判断所述二次语义信息是否为锁定信息；
在判定所述二次语义信息为所述锁定信息时，生成锁定指令，并根据所述锁定指令控制儿童锁上锁。
本实施例中，若权限用户在解锁观看节目后，需要重新设定儿童锁，即可以通过语音消息对所述儿童锁重新进行上锁。所述信息采集模块在接收到所述当前用户发送的语音信息时，作为二次语音信息，并通过语音分析模块对所述二次语音信息进行解析，并转换为二次语义信息，然后将所述二次语义信息发送至所述语义识别模块。所述语义识别模块在接收到所述二次语义信息时，将所述二次语义信息与预设指令列表进行比对，判断所述二次语义信息是否为锁定信息。若判定所述二次语义信息为锁定信息时，生成锁定指令，并根据所述锁定指令控制所述儿童锁上锁。
进一步地，所述基于声音的设备控制方法还包括：
在接收到用户操作触发的训练指令时，采集用户输入的训练语音信息以及对应的训练语义信息，并根据所述训练语音信息以及训练语义信息训练预设声纹识别模型和预设语义分析模型。
目前对小语种的语音认证比较少，大多为英文、中文以及使用人群较多的国家的语言。因此，对只懂本地语言的老年人/儿童来说，语音控制电视等终端会存在语言障碍，本实施例中，为了便于只会某种其他语言的用户使用，如可帮助老人输入一些常用的语音指令，如让老人按照自己的语言说出开机、解锁、选台（中央一套、中央三套等）或关机等常用指令，将老人说出的语音指令存储至声纹识别模型，并在声纹识别模型中将该语音指令对应的声纹信息设置为权限用户。然后将所述语音指令存储至语音分析模块的语义分析模型中，并在所述语义分析模型中为所述语音指令设置对应的语义信息，以便所述语义分析模型能够识别所述语音信息。
此外，本申请实施例还提供一种基于声音的设备控制装置。
参照图5，图5为本申请基于声音的设备控制装置第一实施例的功能模块示意图。
本实施例中，所述基于声音的设备控制装置包括：
声纹判断模块10，用于采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配；
语义判断模块20，用于在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；
解锁模块30，用于在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。
进一步的，所述解锁模块30还包括：
二次验证单元，用于在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并发送是否允许解锁的提醒消息至预设终端；
第一解锁单元，用于判断是否接收到所述预设终端反馈的确认解锁指令，并在接收到所述确认解锁指令时控制所述儿童锁解锁。
进一步的，所述解锁模块30还包括：
节目判断单元，用于在判定所述用户语义信息为非解锁信息时，通过预设指令列表，判断所述用户语义信息是否为播放锁定节目信息；
第二解锁单元，用于若判定所述用户语义信息为所述播放锁定节目信息，则生成解锁指令，并根据所述播放锁定节目信息对应的节目标识，对应播放所述播放锁定节目信息对应的节目。
进一步地，所述解锁单元30还包括：
锁定判断单元，用于在接收到所述当前用户的二次语音信息时，将所述二次语音信息进行解析，生成二次语义信息，并判断所述二次语义信息是否为锁定信息；
上锁单元，用于在判定所述二次语义信息为所述锁定信息时，生成锁定指令，并根据所述锁定指令控制儿童锁上锁。
进一步地，所述基于声音的设备装置还包括：
训练模块，用于在接收到用户操作触发的训练指令时，采集用户输入的训练语音信息以及对应的训练语义信息，并根据所述训练语音信息以及训练语义信息训练预设声纹识别模型和预设语义分析模型。
其中，上述基于声音的设备控制装置中各个模块与上述基于声音的设备控制方法实施例中各步骤相对应，其功能和实现过程在此处不再一一赘述。
此外，本申请实施例还提供一种计算机可读存储介质。
本申请计算机可读存储介质上存储有计算机可读指令，其中，所述计算机可读存储介质可以为非易失性可读存储介质，所述计算机可读指令被处理器执行时，实现如上述的基于声音的设备控制方法的步骤。
其中，计算机可读指令被执行时所实现的方法可参照本申请基于声音的设备控制方法的各个实施例，此处不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者***不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者***所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者***中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种基于声音的设备控制方法，其特征在于，所述基于声音的设备控制方法包括以下步骤：
    采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配；
    在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；
    在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。
  2. 如权利要求1所述的基于声音的设备控制方法，其特征在于，所述在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁的步骤包括：
    在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并发送是否允许解锁的提醒消息至预设终端，并判断是否接收到所述预设终端反馈的确认解锁指令；
    在接收到所述确认解锁指令时控制所述儿童锁解锁。
  3. 如权利要求1所述的基于声音的设备控制方法，其特征在于，所述基于声音的设备控制方法还包括：
    在接收到用户操作触发的训练指令时，采集用户输入的训练语音信息以及对应的训练语义信息，并根据所述训练语音信息以及训练语义信息训练预设声纹识别模型和预设语义分析模型。
  4. 如权利要求1所述的基于声音的设备控制方法，其特征在于，所述在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息的步骤之后，还包括：
    在判定所述用户语义信息为非解锁信息时，通过预设指令列表，判断所述用户语义信息是否为播放锁定节目信息；
    若判定所述用户语义信息为所述播放锁定节目信息，则生成解锁指令，并根据所述播放锁定节目信息对应的节目标识，对应播放所述播放锁定节目信息对应的节目。
  5. 如权利要求4所述的基于声音的设备控制方法，其特征在于，所述若判定所述用户语义信息为所述播放锁定节目信息，则生成解锁指令，并根据所述播放锁定节目信息对应的节目标识，对应播放所述播放锁定节目信息对应的节目的步骤之后，还包括：
    在接收到所述当前用户的二次语音信息时，将所述二次语音信息进行解析，生成二次语义信息，并判断所述二次语义信息是否为锁定信息；
    在判定所述二次语义信息为所述锁定信息时，生成锁定指令，并根据所述锁定指令控制儿童锁上锁。
  6. 如权利要求1所述的基于声音的设备控制方法，其特征在于，所述采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配的步骤之后，还包括：
    在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息不匹配时，生成解锁失败指令，并通过显示模块显示解锁失败的提醒消息。
  7. 如权利要求1所述的基于声音的设备控制方法，其特征在于，所述在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息的步骤包括：
    在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，生成第一解锁信息；
    将所述用户语音信息发送至所述语音分析模块进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；
    所述在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁的步骤包括：
    在判定所述用户语义信息为所述解锁信息时，生成第二解锁信息；
    根据所述第一解锁信息和所述第二解锁信息，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。
  8. 一种基于声音的设备控制装置，其特征在于，所述基于声音的设备控制装置包括：
    声纹判断模块，用于采集当前用户的用户语音信息，并判断所述用户语音信息中的声纹信息是否与具有解锁权限的权限用户的声纹信息相匹配；
    语义判断模块，用于在判定所述用户语音信息中的声纹信息与所述权限用户的声纹信息相匹配时，将所述用户语音信息进行解析，生成用户语义信息，并判断所述用户语义信息是否为解锁信息；
    解锁模块，用于在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并根据所述解锁指令控制儿童锁解锁。
  9. 如权利要求8所述的电量数据的管理装置，其特征在于，所述解锁模块包括：
    二次验证单元，用于在判定所述用户语义信息为所述解锁信息时，生成解锁指令，并发送是否允许解锁的提醒消息至预设终端；
    第一解锁单元，用于判断是否接收到所述预设终端反馈的确认解锁指令，并在接收到所述确认解锁指令时控制所述儿童锁解锁。
  10. 如权利要求8所述的电量数据的管理装置，其特征在于，所述解锁模块还包括：
    节目判断单元，用于在判定所述用户语义信息为非解锁信息时，通过预设指令列表，判断所述用户语义信息是否为播放锁定节目信息；
    第二解锁单元，用于若判定所述用户语义信息为所述播放锁定节目信息，则生成解锁指令，并根据所述播放锁定节目信息对应的节目标识，对应播放所述播放锁定节目信息对应的节目。
  11. 如权利要求8所述的电量数据的管理装置，其特征在于，所述解锁单元还包括：
    锁定判断单元，用于在接收到所述当前用户的二次语音信息时，将所述二次语音信息进行解析，生成二次语义信息，并判断所述二次语义信息是否为锁定信息；
    上锁单元，用于在判定所述二次语义信息为所述锁定信息时，生成锁定指令，并根据所述锁定指令控制儿童锁上锁。
  12. 如权利要求8所述的电量数据的管理装置，其特征在于，所述基于声音的设备装置还包括：
    训练模块，用于在接收到用户操作触发的训练指令时，采集用户输入的训练语音信息以及对应的训练语义信息，并根据所述训练语音信息以及训练语义信息训练预设声纹识别模型和预设语义分析模型。
  13. 一种基于声音的设备控制设备，其特征在于，所述基于声音的设备控制设备包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的计算机可读指令，其中所述计算机可读指令被所述处理器执行时，实现如权利要求1所述的基于声音的设备控制方法的步骤。
  14. 一种基于声音的设备控制设备，其特征在于，所述基于声音的设备控制设备包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的计算机可读指令，其中所述计算机可读指令被所述处理器执行时，实现如权利要求2所述的基于声音的设备控制方法的步骤。
  15. 一种基于声音的设备控制设备，其特征在于，所述基于声音的设备控制设备包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的计算机可读指令，其中所述计算机可读指令被所述处理器执行时，实现如权利要求3所述的基于声音的设备控制方法的步骤。
  16. 一种基于声音的设备控制设备，其特征在于，所述基于声音的设备控制设备包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的计算机可读指令，其中所述计算机可读指令被所述处理器执行时，实现如权利要求4所述的基于声音的设备控制方法的步骤。
  17. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有计算机可读指令，其中所述计算机可读指令被处理器执行时，实现如权利要求1所述的基于声音的设备控制方法的步骤。
  18. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有计算机可读指令，其中所述计算机可读指令被处理器执行时，实现如权利要求2所述的基于声音的设备控制方法的步骤。
  19. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有计算机可读指令，其中所述计算机可读指令被处理器执行时，实现如权利要求3所述的基于声音的设备控制方法的步骤。
  20. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有计算机可读指令，其中所述计算机可读指令被处理器执行时，实现如权利要求4所述的基于声音的设备控制方法的步骤。
PCT/CN2018/103790 2018-06-27 2018-09-03 基于声音的设备控制方法、装置、设备及存储介质 WO2020000637A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810675754.5 2018-06-27
CN201810675754.5A CN109729400A (zh) 2018-06-27 2018-06-27 基于声音的设备控制方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2020000637A1 true WO2020000637A1 (zh) 2020-01-02

Family

ID=66294566

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/103790 WO2020000637A1 (zh) 2018-06-27 2018-09-03 基于声音的设备控制方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN109729400A (zh)
WO (1) WO2020000637A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111443616A (zh) * 2020-04-21 2020-07-24 珠海格力电器股份有限公司 一种家用电器控制方法、装置及家用电器
CN114582053A (zh) * 2022-02-25 2022-06-03 珠海格力电器股份有限公司 智能锁的控制方法、装置、电子设备及存储介质

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110134022B (zh) * 2019-05-10 2022-03-18 平安科技（深圳）有限公司 智能家居设备的声音控制方法、装置、及电子装置
CN110579977B (zh) * 2019-09-17 2021-11-23 珠海格力电器股份有限公司 一种电器设备的控制方法、装置及计算机可读存储介质
CN111583921A (zh) * 2020-04-22 2020-08-25 珠海格力电器股份有限公司 语音控制方法、装置、计算机设备和存储介质
CN111916086B (zh) * 2020-07-01 2024-03-29 中电金信软件有限公司 语音交互控制方法、装置、计算机设备和存储介质
CN113154640A (zh) * 2021-02-02 2021-07-23 珠海格力电器股份有限公司 空调增值功能的控制方法、空调及存储介质
CN116831474A (zh) * 2021-04-15 2023-10-03 北京石头创新科技有限公司 童锁控制方法及装置、机器人、存储介质、电子设备
CN114339342A (zh) * 2021-12-23 2022-04-12 歌尔科技有限公司 一种遥控器控制方法、遥控器、控制装置及介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1760566A1 (en) * 2005-08-29 2007-03-07 Top Digital Co., Ltd. Voiceprint-lock system for electronic data
CN103730120A (zh) * 2013-12-27 2014-04-16 深圳市亚略特生物识别科技有限公司 电子设备的语音控制方法及***
EP2945090A1 (en) * 2013-01-10 2015-11-18 Nec Corporation Terminal, unlocking method, and program
CN105138882A (zh) * 2015-07-30 2015-12-09 广东欧珀移动通信有限公司 一种终端解锁方法和装置
CN106757996A (zh) * 2016-11-30 2017-05-31 无锡小天鹅股份有限公司 洗衣机及通过声纹识别设置洗衣机安全锁的方法和***

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4984899B2 (ja) * 2007-01-11 2012-07-25 富士通株式会社 テレビジョン受信機
KR20130118115A (ko) * 2012-04-19 2013-10-29 현대모비스 주식회사 부정 사용 차단 가능한 스마트키 및 부정 사용 차단 방법
CN103888606A (zh) * 2014-03-11 2014-06-25 上海乐今通信技术有限公司 移动终端及其解锁方法
CN104202486A (zh) * 2014-09-26 2014-12-10 上海华勤通讯技术有限公司 移动终端及其屏幕解锁方法
CN104575504A (zh) * 2014-12-24 2015-04-29 上海师范大学 采用声纹和语音识别进行个性化电视语音唤醒的方法
CN105898441A (zh) * 2015-12-09 2016-08-24 乐视网信息技术（北京）股份有限公司 用于视频应用程序的加锁、解锁方法及服务器
CN105872688A (zh) * 2016-03-31 2016-08-17 乐视控股（北京）有限公司 一种智能电视的语音控制方法及装置
CN107580237A (zh) * 2017-09-05 2018-01-12 深圳Tcl新技术有限公司 电视的操作方法、装置、***和存储介质
CN107767875A (zh) * 2017-10-17 2018-03-06 深圳市沃特沃德股份有限公司 语音控制方法、装置和终端设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1760566A1 (en) * 2005-08-29 2007-03-07 Top Digital Co., Ltd. Voiceprint-lock system for electronic data
EP2945090A1 (en) * 2013-01-10 2015-11-18 Nec Corporation Terminal, unlocking method, and program
CN103730120A (zh) * 2013-12-27 2014-04-16 深圳市亚略特生物识别科技有限公司 电子设备的语音控制方法及***
CN105138882A (zh) * 2015-07-30 2015-12-09 广东欧珀移动通信有限公司 一种终端解锁方法和装置
CN106757996A (zh) * 2016-11-30 2017-05-31 无锡小天鹅股份有限公司 洗衣机及通过声纹识别设置洗衣机安全锁的方法和***

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111443616A (zh) * 2020-04-21 2020-07-24 珠海格力电器股份有限公司 一种家用电器控制方法、装置及家用电器
CN114582053A (zh) * 2022-02-25 2022-06-03 珠海格力电器股份有限公司 智能锁的控制方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN109729400A (zh) 2019-05-07

Similar Documents

Publication Publication Date Title
WO2020000637A1 (zh) 基于声音的设备控制方法、装置、设备及存储介质
WO2017222169A1 (ko) 스마트 카드를 이용한 결제 승인 방법, 이를 수행하는 카드사 서버 및 스마트 카드
WO2019144738A1 (zh) 金融业务的验证方法、装置、设备和计算机存储介质
WO2019143022A1 (ko) 음성 명령을 이용한 사용자 인증 방법 및 전자 장치
WO2020042463A1 (zh) 基于生物特征识别的门禁解锁方法、装置、设备和介质
WO2011062339A1 (en) Method for user authentication, and video communication apparatus and display apparatus thereof
WO2019024485A1 (zh) 数据共享方法、装置及计算机可读存储介质
WO2021003975A1 (zh) 网关接口测试方法、终端设备、存储介质及装置
WO2015069018A1 (ko) 보안 로그인 시스템, 방법 및 장치
WO2017161832A1 (zh) 电梯控制方法、电梯控制装置和终端
WO2015170797A1 (en) Display device and method for controlling the same
WO2020062661A1 (zh) 合同数据一致性的核实方法、装置、设备及存储介质
WO2020006886A1 (zh) 门禁***的识别方法、装置、门禁***及存储介质
WO2011025232A2 (en) Method for managing user schedule and device using the same
WO2017128588A1 (zh) 一种实现数字电视的实时监控方法及装置
WO2012060479A1 (ko) 위치정보 제공 인증관리 서비스 시스템과 제공 방법
WO2016179880A1 (zh) 网络医院平台、专家平台及基于专家平台的紧急专家会诊请求方法
WO2020155773A1 (zh) 文本输入异常监控方法、装置、计算机设备及存储介质
WO2014175642A1 (ko) 부인방지 가능한 본인 인증 시스템 및 그 제공방법
WO2020107591A1 (zh) 重复投保限制方法、装置、设备及可读存储介质
WO2020007099A1 (zh) 电视终端控制方法、设备及计算机可读存储介质
WO2021157956A1 (ko) 방송 관리 서버 및 이를 이용한 방송 관리 방법
CN106846557A (zh) 通过无线路由器实现的门禁管理方法
WO2021017332A1 (zh) 语音控制报错方法、电器及计算机可读存储介质
CN111586336B (zh) 一种远程会见方法、装置和电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18924781

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18924781

Country of ref document: EP

Kind code of ref document: A1