WO2021212907A1 - 语音控制方法、装置、计算机设备和存储介质 - Google Patents
语音控制方法、装置、计算机设备和存储介质 Download PDFInfo
- Publication number
- WO2021212907A1 WO2021212907A1 PCT/CN2020/140645 CN2020140645W WO2021212907A1 WO 2021212907 A1 WO2021212907 A1 WO 2021212907A1 CN 2020140645 W CN2020140645 W CN 2020140645W WO 2021212907 A1 WO2021212907 A1 WO 2021212907A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- controlled device
- preset
- voice
- control
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000007781 pre-processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 230000004044 response Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 10
- 238000011022 operating instruction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000005406 washing Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 2
- 208000033748 Device issues Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001208 nuclear magnetic resonance pulse sequence Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
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
- 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
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition 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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Definitions
- the present disclosure relates to the technical field of voice control, and in particular to a voice control method, device, computer equipment and storage medium.
- voice-controlled smart devices in related technologies are all mutually independent control methods, and cannot cooperate and communicate with other smart devices, which cannot meet the actual needs of users.
- the present disclosure provides a voice control method, device, computer equipment, and storage medium, which solves the problem that the voice control method of related technologies can only target mutually independent smart devices, and cannot realize the collaboration and intercommunication with other smart devices, and cannot meet the actual needs of users.
- the question of demand is a case in which the voice control method of related technologies can only target mutually independent smart devices, and cannot realize the collaboration and intercommunication with other smart devices, and cannot meet the actual needs of users. The question of demand.
- the present disclosure provides a voice control method.
- the control method includes: collecting voice data; parsing out semantic text information according to the voice data; generating corresponding control information according to the semantic text information, the control
- the information includes controlled device information and operation instructions; it is determined whether the controlled device information in the control information exists in the preset controlled device information set; when the controlled device information exists in the preset controlled device information set At this time, the operation instruction is sent to the controlled device, so that the controlled device makes a corresponding response.
- the method further includes: when the controlled device information does not exist in the preset controlled device information set, issuing a first voice prompt.
- sending the operation instruction to the controlled device includes: when the controlled device information is in the When the preset controlled device information exists collectively, it is determined whether the operation instruction in the control information exists in the preset operation instruction set; when the operation instruction exists in the preset operation instruction set, the second voice prompt is issued; When the operation instruction does not exist in the preset operation instruction set, the operation instruction is sent to the controlled device.
- control information when the control information further includes the identity information of the voice data, judging whether the controlled device information in the control information exists before the preset controlled device information collection, the method further includes: judging Whether the identity information of the voice data exists in a preset identity information template library.
- parsing the semantic text information according to the voice data includes: preprocessing the voice data to obtain a voice preprocessing signal; performing feature extraction on the voice preprocessing signal to obtain semantic text information.
- generating corresponding control information according to the semantic text information includes: determining whether the semantic text information exists in a preset semantic text information database; when the semantic text information is in the preset semantic text When the information database exists, corresponding control information is generated according to the semantic text information; when the semantic text information does not exist in the preset semantic text information database, a corresponding third voice prompt is issued.
- the method before the voice data is collected, the method further includes: obtaining information of all controlled devices in the same local area network; configuring the information of all controlled devices in the preset controlled device information set; All operation instructions for each controlled device are configured into the preset operation instruction set.
- the present disclosure provides a voice control device.
- the control device includes: an acquisition module configured to collect voice data; an analysis module configured to parse out semantic text information based on the voice data; and a generation module, Is set to generate corresponding control information according to the semantic text information, the control information includes controlled device information and operation instructions; the judgment module is set to judge whether the controlled device information in the control information is under preset acceptance
- the information of the controlled device is centralized; the sending module is configured to send the operation instruction to the controlled device when the information of the controlled device is centralized in the preset controlled device information, so that the controlled device Respond accordingly.
- the present disclosure provides a computer device including a memory, a processor, and a computer program stored in the memory and capable of running on the processor.
- the processor includes the following steps when the processor executes the computer program: collecting voice data Analyze semantic text information according to the voice data; generate corresponding control information according to the semantic text information, the control information including controlled device information and operation instructions; determine whether the controlled device information in the control information The information of the preset controlled device exists collectively; when the information of the controlled device exists collectively in the preset controlled device information, the operation instruction is sent to the controlled device to make the controlled device perform corresponding the response to.
- the present disclosure provides a computer-readable storage medium on which a computer program is stored.
- the feature is that, when the computer program is executed by a processor, the following steps are implemented: collecting voice data; Generate semantic text information; generate corresponding control information based on the semantic text information, the control information including controlled device information and operation instructions; determine whether the controlled device information in the control information is in the preset controlled device information set Exist; when the controlled device information exists in the preset controlled device information set, the operation instruction is sent to the controlled device to make the controlled device respond accordingly.
- the control method includes: collecting voice data; analyzing semantic text information according to the voice data; generating corresponding control information according to the semantic text information,
- the control information includes controlled device information and operation instructions; it is determined whether the controlled device information in the control information exists in the preset controlled device information set; when the controlled device information is in the preset controlled device When the information exists in a centralized manner, the operation instruction is sent to the controlled device, so that the controlled device makes a corresponding response.
- the voice control method of the present disclosure collects voice data according to devices with voice functions, analyzes and generates corresponding control instructions according to the voice data, and then sends the control instructions to the corresponding controlled device for response, so that other devices without Devices with voice control functions can be controlled by voice; therefore, users can control all networked devices in the home through a voice control device, and configure different control permissions for different controlled devices by customizing the preset controlled device information set. Realize the customized management and control of smart devices, and improve the coverage of voice-controlled smart devices; therefore, the voice control method that solves related technologies can only be used for independent smart devices, and cannot achieve collaborative and intercommunication with other smart devices, which is not enough. The actual needs of users.
- Figure 1 is a flowchart of a voice control method provided by an embodiment of the present disclosure
- Figure 2 is a flowchart of a voice control method provided by an embodiment of the present disclosure
- Figure 3 is a structural block diagram of a voice control device provided by an embodiment of the present disclosure.
- Fig. 4 is an application scenario diagram of a voice control system provided by an embodiment of the present disclosure.
- Fig. 1 is a flowchart of a voice control method provided by an embodiment of the present disclosure; as shown in Fig. 1, the voice control method in an embodiment of the present disclosure specifically includes the following steps:
- Step S101 Collect voice data.
- the voice control method provided in this embodiment can be applied to a smart home voice control system.
- the control system includes a voice master control device and a controlled device.
- the voice master control device mainly performs voice collection, voice analysis, and generates corresponding control instructions.
- the controlled equipment mainly responds according to the control instructions sent by the voice master control device; the voice acquisition module in the voice master control device converts the received original voice signal into pulse sequence voice data, and the collection of voice data can be related
- the signal processing procedures such as acoustic/electric conversion, signal conditioning, and sampling in the technology will not be repeated here; wherein, the language master control device may be a household device with a voice receiving function, or a gateway with a voice function.
- Step S102 parse out semantic text information according to the voice data.
- the voice master control device recognizes the acquired voice data into corresponding text information according to the word segmentation method of self-formation, and then parses the text information into semantic information that can be understood by the machine, and obtains the The semantic text information that matches the voice data.
- Step S103 Generate corresponding control information according to the semantic text information.
- control instruction includes controlled device information and operation instructions.
- the control instruction generated after parsing includes the humidifier's IP address or MAC address, and also includes the start operation instruction.
- Step S104 Determine whether the controlled device information in the control information exists in a preset controlled device information set.
- the voice master control device first queries whether the controlled device has preset controlled device information based on the controlled device information in the control information, proportional to the device information that uniquely represents the identity such as the ID and MAC address of the controlled device In the list, if there is no controlled device in the list, it means that the master device has no right to control the controlled device; when the controlled device exists in the controlled device list, it means that the master device has the right to control the controlled device.
- Control equipment wherein the preset controlled equipment information set includes one or more controlled equipment information, that is to say, a master control device can control multiple controlled devices, and a controlled device can be controlled by multiple master devices Controlled.
- Step S105 When the controlled device information exists in the preset controlled device information set, the operation instruction is sent to the controlled device, so that the controlled device makes a corresponding response.
- a first voice prompt is issued.
- sending the operation instruction to the controlled device includes: when the controlled device information is in the When the preset controlled device information exists collectively, it is determined whether the operation instruction in the control information exists in the preset operation instruction set; when the operation instruction exists in the preset operation instruction set, the second voice prompt is issued; When the operation instruction does not exist in the preset operation instruction set, the operation instruction is sent to the controlled device.
- step S104 when the voice master control device has the authority to control the controlled device in this step, it means that the voice master control device has the authority to control the controlled device and has the right to carry out corresponding instructions. Operation; therefore, when there is authority to control the corresponding operation instruction of the controlled device, the voice master control device sends the operation instruction to the controlled device, so that the controlled device receives the operation instruction and Respond accordingly; when the voice master control device does not have the authority to control the controlled device, the voice master control device issues a voice prompt, prompting the user that the control authority of the controlled device is not set or the receiving device is not set
- the operation authority of the control device wherein, the first voice prompt may be that the main control device does not have the authority to control the controlled device, and the second voice prompt may be that the main control device does not have the authority to control the controlled device Carry out the corresponding operation, for example, the power-on operation can be performed, but the power-off operation cannot be performed.
- the control method includes: collecting voice data; analyzing semantic text information according to the voice data; generating corresponding control information according to the semantic text information, and the control information includes the controlled device Information and operation instructions; determine whether the controlled device information in the control information exists in the preset controlled device information set; when the controlled device information exists in the preset controlled device information set, send the The operation instruction is sent to the controlled device to make the controlled device respond accordingly.
- the voice control method of the present disclosure collects voice data according to devices with voice functions, analyzes and generates corresponding control instructions according to the voice data, and then sends the control instructions to the corresponding controlled device for response, so that other devices without Devices with voice control functions can be controlled by voice; therefore, users can control all networked devices in the home through a voice control device, and configure different control permissions for different controlled devices by customizing the preset controlled device information set. Realize the customized management and control of smart devices, and improve the coverage of voice-controlled smart devices; therefore, the voice control method that solves related technologies can only be used for independent smart devices, and cannot achieve collaborative and intercommunication with other smart devices, which is not enough. The actual needs of users.
- the method before the collecting voice data, the method further includes:
- All operation instructions for each controlled device are configured into the preset operation instruction set.
- this embodiment can realize the customization of the control authority between the voice master control device and the controlled device, so that one master control device can control multiple controlled devices.
- one controlled device can be controlled by multiple masters.
- Device control In some embodiments, a master control device can control one or more operation instructions of a controlled device; when the controlled device information is configured in the preset controlled device information set, it means that the master control The device has the authority to send operation instructions to the controlled device; when the operation instruction exists in the preset operation instruction set, it means that the master control device has the authority to send the operation instruction to the controlled device, and the controlled device The device will also respond according to the operating instructions.
- control information when the control information further includes the identity information of the voice data, it is determined whether the controlled device information in the control information exists before the preset controlled device information is concentrated, and the method further include:
- this embodiment shows that the master control device determines whether the user identity information sending the voice exists in the preset template library based on the collected voice data, and when it exists in the preset identity information template library, then judges the controlled device Whether the information exists in the preset controlled device information collection; when there is no preset identity information template library, a voice prompts that the user's sound source is not preset in the template library, and the user who emits the voice is set to prevent all People perform error operations on voice control, which is conducive to the reasonable management and control of smart devices.
- Fig. 2 is a flowchart of a voice control method provided by an embodiment of the present disclosure; as shown in Fig. 2, the voice control method in an embodiment of the present disclosure further includes the following steps:
- Step S201 preprocessing the voice data to obtain a voice preprocessing signal.
- Step S202 Perform feature extraction on the voice preprocessing signal to obtain semantic text information.
- Step S203 Determine whether the semantic text information exists in the preset semantic text information database, and execute step S204 when the semantic text information exists in the preset semantic text information database. If the preset semantic text information database does not exist, step S205 is executed.
- Step S204 Generate corresponding control information according to the semantic text information.
- step S205 a corresponding third voice prompt is issued.
- the voice master control device preprocesses the collected voice data through filtering to remove interference signals to obtain a voice preprocessing signal, and performs feature extraction processing on the voice preprocessing signal to obtain the acoustic characteristics of the voice data,
- the acoustic features of the voice data are recognized through a preset voice recognition model to obtain the recognized text of the voice data; then the recognized text of the voice data is semantically analyzed to obtain the semantic text information of the voice data.
- the acquired semantic text information is compared with a preset semantic text information library, and when the voice text information is stored in the preset semantic text information library, a corresponding control instruction is generated and sent to the corresponding
- FIG. 3 is a structural block diagram of a voice control device provided by an embodiment of the present disclosure. As shown in FIG. 3, the voice control device provided by an embodiment of the present disclosure can be applied to a smart home voice control system, and the control system includes a voice master Equipment and controlled equipment, the control device includes:
- the collection module 100 is set to collect voice data
- the parsing module 200 is configured to parse out semantic text information according to the voice data
- the generating module 300 is configured to generate corresponding control information according to the semantic text information, the control information including controlled device information and operation instructions;
- the determining module 400 is configured to determine whether the controlled device information in the control information exists in a preset controlled device information set;
- the sending module 500 is configured to send the operation instruction to the controlled device when the controlled device information exists in the preset controlled device information set, so that the controlled device makes a corresponding response.
- control device further includes a first voice prompt module configured to issue a first voice prompt when the controlled device information does not exist in the preset controlled device information set.
- the sending module 500 includes: an operation instruction judging module configured to determine whether the operation instruction in the control information is in the preset operation instruction when the controlled device information exists in the preset controlled device information set Centralized presence; the second voice prompt module is set to issue a second voice prompt when the operating instruction exists in the preset operating instruction set; the operating instruction sending module is set to issue the second voice prompt when the operating instruction is in the preset operating instruction When the concentration does not exist, send the operation instruction to the controlled device.
- the control device further includes: an identity information judgment module configured to judge whether the identity information of the voice data exists in a preset identity information template library.
- the analysis module 200 includes: a preprocessing module configured to preprocess the voice data to obtain a voice preprocessing signal; a feature extraction module configured to perform feature extraction on the voice preprocessing signal to obtain semantic text information .
- the generating module 300 includes: a voice and text information judgment module, which is configured to judge whether the semantic text information exists in a preset semantic text information database; a control information generation module, which is configured to determine whether the semantic text information exists in the When the preset semantic text information database exists, corresponding control information is generated according to the semantic text information; the third voice prompt module is set to when the semantic text information does not exist in the preset semantic text information database , Send out the corresponding third voice prompt.
- the apparatus further includes: a controlled device information acquisition module, which is configured to acquire information about all controlled devices in the same local area network; a first configuration module, which is configured to acquire information about all controlled devices. Configure to the preset controlled device information set; the second configuration module is configured to configure all operation instructions for each controlled device to the preset operation instruction set.
- FIG 4 is an application scenario diagram of a smart home voice control system provided by an embodiment of the present disclosure.
- the living room air conditioner is the voice master control device in the smart home voice control system, including a voice collection module and a voice emission module , Command issuing modules and controllers, air purifiers, humidifiers and smart speakers are controlled devices that are wirelessly connected to the voice master control device via WiFi or Bluetooth, and receive operating instructions from the living room air conditioner and respond to corresponding instructions .
- the voice portal device can control itself and other voice/non-voice devices through voice.
- the voice portal device can control any networked device in the home through voice, and the non-voice portal device can only be performed on the app with the network. Control or control of voice portal devices.
- the user needs to set the controllable device authority of the voice portal and whether it can control the specified device.
- the user After the user successfully configures the network through the designated app, all the devices are in the same family; the user can configure the voice portal device to control the permissions of other devices, so that each voice portal can only do what it can do, and there is no device voice portal configured with control permissions.
- Equipment cannot be controlled; there are many networked devices in a family, including some voice entrance devices (living room air conditioners, bedroom air conditioners, etc.), non-voice entrance devices (living room air purifiers, washing machines, bedroom humidifiers, etc.), and users are equipped with networks After success, all devices are under one family. The user can configure the voice portal to control the permissions of other devices on the app/voice.
- the voice portal device can access its configured permissions.
- the control authority of the device Other devices that are not configured for the voice portal device cannot be controlled. At this time, it will return/broadcast "Insufficient device authority"; for example, there are voice portal devices in a family (living room air conditioner, bedroom air conditioner Etc.), non-voice entrance equipment (living room air purifier, washing machine, bedroom humidifier, etc.), the user can configure the controllable device permissions of the living room air conditioner for the living room air purifier, washing machine, bedroom humidifier, bedroom air conditioner; bedroom air conditioner configuration
- the control device authority is: bedroom humidifier.
- the user can issue control instructions for any device in the living room air conditioner, and the corresponding device will execute the instruction; when the user issues an instruction to control the bedroom humidifier, the bedroom humidifier can execute normally, and when the control instruction is issued to the living room air conditioner, it will Prompt that the device control authority is insufficient.
- the control authority of the device can specifically include each function of the device.
- the air purifier has the functions of opening, closing, purifying, dust removal, etc.
- each function of the air purifier can be configured with the corresponding authority; that is to say: this can be configured for the voice inlet device (such as: air conditioner)
- the control authority of the opening and closing functions of the air purifier is not granted with other authority; then the control of the air purifier through this voice portal device can only be the control command of opening and closing, and other commands will feedback insufficient authority;
- the principle of App control equipment is that the app sends a request to the cloud, and the cloud sends the corresponding operation to the designated machine.
- the designated machine receives the instruction, parses the instruction, and executes the action.
- a computer device including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, and the processor includes the following steps when the processor executes the computer program: Collect voice data; parse out semantic text information according to the voice data; generate corresponding control information based on the semantic text information, the control information including controlled device information and operation instructions; determine the controlled information in the control information Whether the device information exists in the preset controlled device information set; when the controlled device information exists in the preset controlled device information set, the operation instruction is sent to the controlled device to make the controlled device The device responds accordingly.
- a computer-readable storage medium on which a computer program is stored.
- the computer program includes the following steps: collecting voice data; Semantic text information; generate corresponding control information based on the semantic text information, the control information including controlled device information and operation instructions; determine whether the controlled device information in the control information exists in the preset controlled device information set When the controlled device information is concentrated in the preset controlled device information, the operation instruction is sent to the controlled device to make the controlled device respond accordingly.
- the control method includes: collecting voice data; analyzing semantic text information according to the voice data; generating corresponding control information according to the semantic text information,
- the control information includes controlled device information and operation instructions; it is determined whether the controlled device information in the control information exists in the preset controlled device information set; when the controlled device information is in the preset controlled device When the information exists in a centralized manner, the operation instruction is sent to the controlled device, so that the controlled device makes a corresponding response.
- the voice control method of the present disclosure collects voice data according to devices with voice functions, analyzes and generates corresponding control instructions according to the voice data, and then sends the control instructions to the corresponding controlled device for response, so that other devices without Devices with voice control functions can be controlled by voice; therefore, users can control all networked devices in the home through a voice control device, and configure different control permissions for different controlled devices by customizing the preset controlled device information set. Realize the customized management and control of smart devices, and improve the coverage of voice-controlled smart devices; therefore, the voice control method that solves related technologies can only be used for independent smart devices, and cannot achieve collaborative and intercommunication with other smart devices, which is not enough. The actual needs of users.
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
- Selective Calling Equipment (AREA)
Abstract
语音控制方法、装置、计算机设备和存储介质，控制方法包括：采集语音数据（S101）；根据语音数据，解析出语义文本信息（S102）；根据语义文本信息生成相应的控制信息（S103）；判断控制信息中的受控设备信息是否在预设受控设备信息集中存在（S104）；当受控设备信息在预设受控设备信息集中存在时，发送操作指令到受控设备，使受控设备进行相应的响应（S105）。解决了相关技术的语音控制方法只能针对相互独立的智能设备，不能实现与其他智能设备的协同互通，满足不了用户的实际需求的问题。
Description
本公开要求于2020年04月22日提交中国专利局、申请号为202010323111.1、发明名称为“语音控制方法、装置、计算机设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
本公开涉及语音控制技术领域，尤其涉及一种语音控制方法、装置、计算机设备和存储介质。
随着物联网技术的不断发展，在智能设备给人们带来便捷生活的同时，人们的控制习惯逐渐发生改变，语音技术的发展也逐渐代替遥控器和手动操作等传统控制方式，通过发送语音让家居环境达到舒适状态，让生活更便捷和智能。
但是相关技术中语音控制智能设备都是相互独立的控制方法，不能与其他智能设备进行协同互通，满足不了用户的实际需求。
发明内容
本公开提供了一种语音控制方法、装置、计算机设备和存储介质，解决了相关技术的语音控制方法只能针对相互独立的智能设备，不能实现与其他智能设备的协同互通，满足不了用户的实际需求的问题。
第一方面，本公开提供一种语音控制方法，所述控制方法包括：采集语音数据；根据所述语音数据，解析出语义文本信息；根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；当所述受控设备信息在所述预设受控设备信息集中 存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
在一些实施方式中，所述方法还包括：当所述受控设备信息在所述预设受控设备信息集中不存在时，发出第一语音提示。
在一些实施方式中，当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，包括：当所述受控设备信息在所述预设受控设备信息集中存在时，判断所述控制信息中的操作指令是否在预设操作指令集中存在；当所述操作指令在预设操作指令集中存在时，发出第二语音提示；当所述操作指令在预设操作指令集中不存在时，发送所述操作指令到所述受控设备。
在一些实施方式中，当所述控制信息还包括语音数据的身份信息时，判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在之前，所述方法还包括：判断所述语音数据的身份信息是否存在预设身份信息模板库。
在一些实施方式中，根据所述语音数据，解析出语义文本信息，包括：将所述语音数据进行预处理，得到语音预处理信号；对所述语音预处理信号进行特征提取得到语义文本信息。
在一些实施方式中，根据所述语义文本信息生成相应的控制信息，包括：判断所述语义文本信息是否在预设语义文本信息库中存在；当所述语义文本信息在所述预设语义文本信息库中存在时，根据所述语义文本信息生成相应的控制信息；当所述语义文本信息在所述预设语义文本信息库中不存在时，发出相应的第三语音提示。
在一些实施方式中，所述采集语音数据之前，所述方法还包括：获取同一局域网内所有受控设备信息；将所述所有受控设备信息配置到所述预设受控设备信息集中；将对每个受控设备的所有操作指令配置到所述预设操作指令集中。
第二方面，本公开提供一种语音控制装置，所述控制装置包括：采集模块，被设置为采集语音数据；解析模块，被设置为根据所述语音数据，解析出语义文本信息；生成模块，被设置为根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；判断模块，被设置为判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；发送模块，被设置为当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
第三方面，本公开提供一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时包括如下步骤：采集语音数据；根据所述语音数据，解析出语义文本信息；根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
第四方面，本公开提供一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如下步骤：采集语音数据；根据所述语音数据，解析出语义文本信息；根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
本公开提供的语音控制方法、装置、计算机设备和存储介质，所述控制方法包括：采集语音数据；根据所述语音数据，解析出语义文本信息；根据所述语义文本信息生成相应的控制信息，所述控制信息 包括受控设备信息和操作指令；判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。本公开的语音控制方法是根据带语音功能的设备采集语音数据，根据所述语音数据解析和生成相应的控制指令，再将所述控制指令发送到相应的受控设备进行响应，使其他不带有语音控制功能的设备可以通过语音来控制；因此用户可以通过一台语音控制设备控制家中所有的联网设备，并且通过自定义预设受控设备信息集来配置不同受控设备的不同控制权限，实现智能设备的定制化管理和控制，提高了语音控制智能设备的覆盖率；因此解决了相关技术的语音控制方法只能针对相互独立的智能设备，不能实现与其他智能设备的协同互通，满足不了用户的实际需求的问题。
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
为了更清楚地说明本公开实施例或相关技术中的技术方案，下面将对实施例或相关技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本公开实施例提供的一种语音控制方法的流程图；
图2是本公开实施例提供的一种语音控制方法的流程图；
图3是本公开实施例提供的一种语音控制装置的结构框图；
图4是本公开实施例提供的一种语音控制系统的应用场景图。
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、 完整地描述，显然，所描述的实施例是本公开的一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
图1是本公开实施例提供的一种语音控制方法的流程图；如图1所示，本公开实施例中的语音控制方法具体包括如下步骤：
步骤S101，采集语音数据。
具体地，本实施例提供的语音控制方法可以应用于智能家居语音控制系统，所述控制系统包括语音主控设备和受控设备语音主控设备主要进行语音采集、语音解析和生成相应控制指令，受控设备主要是根据语音主控设备发送的控制指令进行相应的响应；语音主控设备中的语音采集模块将接收到的原始语音信号转换成脉冲序列的语音数据，语音数据的采集可采用相关技术中的声/电转换、信号调理和采样等信号处理过程，此处不再赘述；其中，所述语言主控设备可以是带语音接收功能的家居设备，也可以是带语音功能的网关。
步骤S102，根据所述语音数据，解析出语义文本信息。
在一些实施方式中，所述语音主控设备根据自构词的分词法，将获取到的语音数据识别成相应的文本信息，再将所述文本信息解析出机器可以理解的语义信息，得到所述语音数据相匹配的语义文本信息。
步骤S103，根据所述语义文本信息生成相应的控制信息。
具体地，所述控制指令包括受控设备信息和操作指令，例如用户发出的语音为打开加湿器，因此经过解析生成的控制指令中包括加湿器的IP地址或者MAC地址，还包括启动操作指令。
步骤S104，判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在。
具体地，语音主控设备先根据控制信息中的受控设备信息，比例受控设备的ID、MAC地址等唯一表示身份的设备信息，查询所述受控 设备是否存在预设的受控设备信息列表中，如果不存在受控设备的列表中表示主控设备无权控制所述受控设备；当所述受控设备存在所述受控设备列表中，表示主控设备有权控制所述受控设备；其中，所述预设受控设备信息集包括一个或者多个受控设备信息，也就是说一个主控设备可以控制多个受控设备，一个受控设备可以被多个主控设备所控制。
步骤S105，当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
在一些实施方式中，当所述受控设备信息在所述预设受控设备信息集中不存在时，发出第一语音提示。
在一些实施方式中，当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，包括：当所述受控设备信息在所述预设受控设备信息集中存在时，判断所述控制信息中的操作指令是否在预设操作指令集中存在；当所述操作指令在预设操作指令集中存在时，发出第二语音提示；当所述操作指令在预设操作指令集中不存在时，发送所述操作指令到所述受控设备。
具体地，根据步骤S104的阐述，本步骤中当所述语音主控设备有权限控制所述受控设备表示所述语音主控设备有权控制所述受控设备，并且有权进行相应指令的操作；因此当有权限控制所述受控设备的相应操作指令时，所述语音主控设备将所述操作指令发送到所述受控设备中，使所述受控设备接收所述操作指令并进行相应的响应；当所述语音主控设备没有权限控制所述受控设备时，所述语音主控设备发出语音提示，提示用户没有设置所述受控设备的控制权限或者没有设置所述受控设备的操作权限；其中，所述第一语音提示可以是关于主控设备没有权限控制所述受控设备，所述第二语音提示可以是所述主控设备没有权限对所述受控设备进行相应的操作，例如可以进行开 机操作，但不能进行关机操作。
本公开提供的语音控制方法，所述控制方法包括：采集语音数据；根据所述语音数据，解析出语义文本信息；根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。本公开的语音控制方法是根据带语音功能的设备采集语音数据，根据所述语音数据解析和生成相应的控制指令，再将所述控制指令发送到相应的受控设备进行响应，使其他不带有语音控制功能的设备可以通过语音来控制；因此用户可以通过一台语音控制设备控制家中所有的联网设备，并且通过自定义预设受控设备信息集来配置不同受控设备的不同控制权限，实现智能设备的定制化管理和控制，提高了语音控制智能设备的覆盖率；因此解决了相关技术的语音控制方法只能针对相互独立的智能设备，不能实现与其他智能设备的协同互通，满足不了用户的实际需求的问题。
在本公开的一个实施例中，所述采集语音数据之前，所述方法还包括：
获取同一局域网内所有受控设备信息；
将所述所有受控设备信息配置到所述预设受控设备信息集中；
将对每个受控设备的所有操作指令配置到所述预设操作指令集中。
具体地，本实施例可以实现语音主控设备与受控设备之间控制权限的自定义，使一个主控设备可以控制多个受控设备，相应地，一个受控设备可以被多个主控设备控制；在一些实施方式中，一个主控设备可以控制一个受控设备的一个或者多个操作指令；当所述受控设备 信息配置在所述预设受控设备信息集中时，表示主控设备有权限向所述受控设备发送操作指令；当所述操作指令存在所述预设操作指令集中，表示主控设备有权限向所述受控设备发送所述操作指令，并且所述受控设备还会根据所述操作指令进行响应。
在本公开的一个实施例中，当所述控制信息还包括语音数据的身份信息时，判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在之前，所述方法还包括：
判断所述语音数据的身份信息是否存在预设身份信息模板库。
具体地，本实施例表示主控设备根据采集到的语音数据，判断发送语音的用户身份信息是否存在预设模板库中，当存在预设身份信息模板库中时，再判断所述受控设备信息是否存在预设受控设备信息集中；当不存在预设身份信息模板库中时，发出语音提示此用户的声音源未预设在模板库中，将发出语音的用户进行权限设置后防止所有人对语音控制进行误差操作，有利于智能设备的合理管控。
图2是本公开实施例提供的一种语音控制方法的流程图；如图2所示，本公开实施例中的语音控制方法还包括如下步骤：
步骤S201，将所述语音数据进行预处理，得到语音预处理信号。
步骤S202，对所述语音预处理信号进行特征提取得到语义文本信息。
步骤S203，判断所述语义文本信息是否在预设语义文本信息库中存在，当所述语义文本信息在所述预设语义文本信息库中存在时执行步骤S204，当所述语义文本信息在所述预设语义文本信息库中不存在时执行步骤S205。
步骤S204，根据所述语义文本信息生成相应的控制信息。
步骤S205，发出相应的第三语音提示。
具体地，所述语音主控设备将采集到的语音数据经过滤除干扰信 号等预处理得到语音预处理信号，对所述与语音预处理信号进行特征提取处理，得到该语音数据的声学特征，通过预设的语音识别模型对语音数据的声学特征进行识别，得到语音数据的识别文本；然后对语音数据的识别文本进行语义分析，得到所述语音数据的语义文本信息。
在一些实施方式中，将获取到的语义文本信息与预设语义文本信息库进行比较，当所述语音文本信息存在所述预设的语义文本信息库中，生成相应的控制指令并发送到相应的受控设备，当所述语音文本信息不存在所述预设的语义文本信息库中，发出相应的语音提示，例如提示用户按照语音样本进行语音输入等。
图3是本公开实施例提供的一种语音控制装置的结构框图；如图3所示，本公开实施例提供的语音控制装置可以应用于智能家居语音控制系统，所述控制系统包括语音主控设备和受控设备，所述控制装置包括：
采集模块100，被设置为采集语音数据；
解析模块200，被设置为根据所述语音数据，解析出语义文本信息；
生成模块300，被设置为根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；
判断模块400，被设置为判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；
发送模块500，被设置为当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
在本公开的实施例中，所述控制装置还包括第一语音提示模块，被设置为当所述受控设备信息在所述预设受控设备信息集中不存在时，发出第一语音提示。
所述发送模块500包括：操作指令判断模块，被设置为当所述受 控设备信息在所述预设受控设备信息集中存在时，判断所述控制信息中的操作指令是否在预设操作指令集中存在；第二语音提示模块，被设置为当所述操作指令在预设操作指令集中存在时，发出第二语音提示；操作指令发送模块，被设置为当所述操作指令在预设操作指令集中不存在时，发送所述操作指令到所述受控设备。
所述控制装置还包括：身份信息判断模块，被设置为判断所述语音数据的身份信息是否存在预设身份信息模板库。
所述解析模块200包括：预处理模块，被设置为将所述语音数据进行预处理，得到语音预处理信号；特征提取模块，被设置为对所述语音预处理信号进行特征提取得到语义文本信息。
所述生成模块300包括：语音文本信息判断模块，被设置为判断所述语义文本信息是否在预设语义文本信息库中存在；控制信息生成模块，被设置为当所述语义文本信息在所述预设语义文本信息库中存在时，根据所述语义文本信息生成相应的控制信息；第三语音提示模块，被设置为当所述语义文本信息在所述预设语义文本信息库中不存在时，发出相应的第三语音提示。
在本公开的实施例中，所述装置还包括：受控设备信息获取模块，被设置为获取同一局域网内所有受控设备信息；第一配置模块，被设置为将所述所有受控设备信息配置到所述预设受控设备信息集中；第二配置模块，被设置为将对每个受控设备的所有操作指令配置到所述预设操作指令集中。
图4是本公开实施例提供的一种智能家居语音控制系统的应用场景图，如图4所示，客厅空调为智能家居语音控制系统中的语音主控设备，包括语音采集模块、语音发出模块、指令发出模块和控制器，空气净化器、加湿器和智能音箱等为受控设备，通过WiFi或者蓝牙与所述语音主控设备无线连接，接收客厅空调发出的操作指令并进行相 应指令的响应。
在本公开的一个实施例中，家庭中联网的智能家居设备分为两种：一种是语音入口设备，一种是非语音入口设备。语音入口设备是可以通过语音来控制自身和控制其他语音/非语音设备，简单来说：语音入口设备可以通过语音控制家庭内任何联网设备，非语音入口设备则只能在配网的app上进行控制或者语音入口设备的控制。
在实际应用中，需要由用户设定语音入口的可控设备权限、是否能控制指定设备两部分构成。用户通过指定app配网成功后，所有设备在一个家庭下；用户可以配置语音入口设备控制其他设备的权限，这样每个语音入口只能做自己能做的事，没有配置控制权限的设备语音入口设备是无法进行控制的；一个家庭中有很多联网设备，包括一些语音入口设备(客厅空调、卧室空调等)、非语音入口设备(客厅空气净化器、洗衣机、卧室加湿器等)，用户配网成功后，所有设备在一个家庭下。用户可以在app上/语音配置语音入口控制其他设备的权限，当用户完成权限的划分后要求输入家庭账号的密码才能提交配置的权限，当配置成功后，该语音入口设备就可以访问其配置的设备的控制权限，其他的未配置给该语音入口设备的设备是不能够进行控制的，此时会返回/播报“设备权限不足”；例如，一个家庭中有语音入口设备(客厅空调、卧室空调等)、非语音入口设备(客厅空气净化器、洗衣机、卧室加湿器等)，用户配置客厅空调的可控制设备权限为客厅空气净化器、洗衣机及、卧室加湿器、卧室空调；卧室空调配置的控制设备权限为：卧室加湿器。此时，用户可以对客厅空调下达任何设备的控制指令，相应设备都会执行指令；用户对卧室空调下达控制卧室加湿器的指令时，卧室加湿器能正常执行，对客厅空调下达控制指令时，会提示设备控制权限不足。
首先，设备的控制权限具体可以包括设备的每个功能。比如说： 空气净化器有打开、关闭、净化、除尘等功能，那么这个空气净化器的每一个功能都能被配置为相应的权限；就是说：可以给语音入口设备(比如：空调)配置这个空气净化器的打开、关闭功能的控制权限，其他权限不赋予；则通过这台语音入口设备对这台空气净化器的控制就只能是打开、关闭的控制指令，其他指令都会反馈权限不足；其中，App控制设备的原理是app发送请求到云端，云端将对应操作下发到指定机器，指定机器接收到指令，解析指令，执行动作
在本公开的一个实施例中，提供一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时包括如下步骤：采集语音数据；根据所述语音数据，解析出语义文本信息；根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
在本公开的一个实施例中，提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时包括如下步骤：采集语音数据；根据所述语音数据，解析出语义文本信息；根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
本公开提供的语音控制方法、装置、计算机设备和存储介质，所述控制方法包括：采集语音数据；根据所述语音数据，解析出语义文本信息；根据所述语义文本信息生成相应的控制信息，所述控制信息 包括受控设备信息和操作指令；判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。本公开的语音控制方法是根据带语音功能的设备采集语音数据，根据所述语音数据解析和生成相应的控制指令，再将所述控制指令发送到相应的受控设备进行响应，使其他不带有语音控制功能的设备可以通过语音来控制；因此用户可以通过一台语音控制设备控制家中所有的联网设备，并且通过自定义预设受控设备信息集来配置不同受控设备的不同控制权限，实现智能设备的定制化管理和控制，提高了语音控制智能设备的覆盖率；因此解决了相关技术的语音控制方法只能针对相互独立的智能设备，不能实现与其他智能设备的协同互通，满足不了用户的实际需求的问题。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，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、物品或者设备不仅包括那些要素，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、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅是本公开的具体实施方式，使本领域技术人员能够理解或实现本公开。对这些实施例的多种修改对本领域的技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本公开的精神或范围的情况下，在其它实施例中实现。因此，本公开将不会被限制于本文所示的这些实施例，而是要符合与本文所申请的原理和新颖特点相一致的最宽的范围。
Claims (10)
- 一种语音控制方法，所述控制方法包括：采集语音数据；根据所述语音数据，解析出语义文本信息；根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
- 根据权利要求1所述的方法，其中，所述方法还包括：当所述受控设备信息在所述预设受控设备信息集中不存在时，发出第一语音提示。
- 根据权利要求1所述的方法，其中，当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，包括：当所述受控设备信息在所述预设受控设备信息集中存在时，判断所述控制信息中的操作指令是否在预设操作指令集中存在；当所述操作指令在预设操作指令集中存在时，发出第二语音提示；当所述操作指令在预设操作指令集中不存在时，发送所述操作指令到所述受控设备。
- 根据权利要求1所述的方法，其中，当所述控制信息还包括语音数据的身份信息时，判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在之前，所述方法还包括：判断所述语音数据的身份信息是否存在预设身份信息模板库。
- 根据权利要求1所述的方法，其中，根据所述语音数据，解析 出语义文本信息，包括：将所述语音数据进行预处理，得到语音预处理信号；对所述语音预处理信号进行特征提取得到语义文本信息。
- 根据权利要求5所述的方法，其中，根据所述语义文本信息生成相应的控制信息，包括：判断所述语义文本信息是否在预设语义文本信息库中存在；当所述语义文本信息在所述预设语义文本信息库中存在时，根据所述语义文本信息生成相应的控制信息；当所述语义文本信息在所述预设语义文本信息库中不存在时，发出相应的第三语音提示。
- 根据权利要求1-6任一项所述的方法，其中，所述采集语音数据之前，所述方法还包括：获取同一局域网内所有受控设备信息；将所述所有受控设备信息配置到所述预设受控设备信息集中；将对每个受控设备的所有操作指令配置到所述预设操作指令集中。
- 一种语音控制装置，所述控制装置包括：采集模块，被设置为采集语音数据；解析模块，被设置为根据所述语音数据，解析出语义文本信息；生成模块，被设置为根据所述语义文本信息生成相应的控制信息，所述控制信息包括受控设备信息和操作指令；判断模块，被设置为判断所述控制信息中的受控设备信息是否在预设受控设备信息集中存在；发送模块，被设置为当所述受控设备信息在所述预设受控设备信息集中存在时，发送所述操作指令到所述受控设备，使所述受控设备进行相应的响应。
- 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现权利要求1至7中任一项所述方法的步骤。
- 一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1至7中任一项所述的方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010323111.1A CN111583921A (zh) | 2020-04-22 | 2020-04-22 | 语音控制方法、装置、计算机设备和存储介质 |
| CN202010323111.1 | 2020-04-22 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021212907A1 true WO2021212907A1 (zh) | 2021-10-28 |
Family
ID=72116686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/140645 WO2021212907A1 (zh) | 2020-04-22 | 2020-12-29 | 语音控制方法、装置、计算机设备和存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111583921A (zh) |
| WO (1) | WO2021212907A1 (zh) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112233672A (zh) * | 2020-09-30 | 2021-01-15 | 成都长虹网络科技有限责任公司 | 分布式语音控制方法、系统、计算机设备和可读存储介质 |
| CN112423053B (zh) * | 2020-11-06 | 2024-04-09 | 歌尔科技有限公司 | 一种音频共享方法、系统、遥控器及计算机可读存储介质 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5774841A (en) * | 1995-09-20 | 1998-06-30 | The United States Of America As Represented By The Adminstrator Of The National Aeronautics And Space Administration | Real-time reconfigurable adaptive speech recognition command and control apparatus and method |
| CN107885089A (zh) * | 2017-11-06 | 2018-04-06 | 四川长虹电器股份有限公司 | 基于自定义语音指令库的智慧家居语音操控方法 |
| CN108337139A (zh) * | 2018-01-29 | 2018-07-27 | 广州索答信息科技有限公司 | 家电语音控制方法、电子设备、存储介质及系统 |
| CN108683574A (zh) * | 2018-04-13 | 2018-10-19 | 青岛海信智慧家居系统股份有限公司 | 一种设备控制方法、服务器和智能家居系统 |
| CN109584869A (zh) * | 2018-11-29 | 2019-04-05 | 罗国富 | 家电语音采集方法、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 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106385347A (zh) * | 2016-09-09 | 2017-02-08 | 珠海格力电器股份有限公司 | 一种家电设备控制方法和装置 |
| CN109729400A (zh) * | 2018-06-27 | 2019-05-07 | 平安科技（深圳）有限公司 | 基于声音的设备控制方法、装置、设备及存储介质 |
| CN108766432A (zh) * | 2018-07-02 | 2018-11-06 | 珠海格力电器股份有限公司 | 一种控制家电间协同工作的方法 |
| CN110534107A (zh) * | 2019-09-11 | 2019-12-03 | 北京安云世纪科技有限公司 | 智能设备的语音控制方法、装置、系统及电子设备 |
| CN110632854A (zh) * | 2019-10-15 | 2019-12-31 | 深圳平正智能科技有限公司 | 语音控制方法及装置、语音控制节点及系统及存储介质 |
| CN110890094A (zh) * | 2019-12-02 | 2020-03-17 | 苏州思必驰信息科技有限公司 | 物联网设备语音控制方法及语音服务端 |
-
2020
- 2020-04-22 CN CN202010323111.1A patent/CN111583921A/zh active Pending
- 2020-12-29 WO PCT/CN2020/140645 patent/WO2021212907A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5774841A (en) * | 1995-09-20 | 1998-06-30 | The United States Of America As Represented By The Adminstrator Of The National Aeronautics And Space Administration | Real-time reconfigurable adaptive speech recognition command and control apparatus and method |
| CN107885089A (zh) * | 2017-11-06 | 2018-04-06 | 四川长虹电器股份有限公司 | 基于自定义语音指令库的智慧家居语音操控方法 |
| CN108337139A (zh) * | 2018-01-29 | 2018-07-27 | 广州索答信息科技有限公司 | 家电语音控制方法、电子设备、存储介质及系统 |
| CN108683574A (zh) * | 2018-04-13 | 2018-10-19 | 青岛海信智慧家居系统股份有限公司 | 一种设备控制方法、服务器和智能家居系统 |
| CN109584869A (zh) * | 2018-11-29 | 2019-04-05 | 罗国富 | 家电语音采集方法、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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111583921A (zh) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021212907A1 (zh) | 语音控制方法、装置、计算机设备和存储介质 | |
| WO2020168725A1 (zh) | 语音控制方法、装置、存储介质及智能家居系统 | |
| CN106257355B (zh) | 设备控制方法和控制器 | |
| CN107622652B (zh) | 家电系统的语音控制方法与家电控制系统 | |
| US10755706B2 (en) | Voice-based user interface with dynamically switchable endpoints | |
| CN106297781B (zh) | 控制方法和控制器 | |
| CN111542810B (zh) | 数字语音助理计算设备当中的信号处理协调 | |
| CN110085233B (zh) | 语音控制方法及其装置、电子设备和计算机可读存储介质 | |
| WO2019161686A1 (en) | Machine generation of context-free grammar for intent deduction | |
| WO2019091171A1 (zh) | 语音控制智能家电的方法、装置、系统和电子设备 | |
| WO2015033523A1 (ja) | 音声対話制御方法 | |
| CN107622767A (zh) | 家电系统的语音控制方法与家电控制系统 | |
| CN108470568B (zh) | 智能设备控制方法及装置、存储介质、电子设备 | |
| CN109377995B (zh) | 一种控制设备的方法与装置 | |
| WO2021047248A1 (zh) | 基于多控制终端的iot设备控制方法、控制终端及存储介质 | |
| CN110618614A (zh) | 一种智能家居的控制方法、装置、存储介质及机器人 | |
| CN111477230A (zh) | 一种智能音箱系统、智能音箱系统的控制方法及存储介质 | |
| CN211791560U (zh) | 分布式语音控制系统 | |
| CN110767225A (zh) | 一种语音交互方法、装置及系统 | |
| CN112838967B (zh) | 主控设备、智能家居及其控制装置、控制系统及控制方法 | |
| WO2019227370A1 (zh) | 一种多语音助手控制方法、装置、系统及计算机可读存储介质 | |
| CN112908321A (zh) | 设备控制方法、装置、存储介质及电子装置 | |
| CN112233672A (zh) | 分布式语音控制方法、系统、计算机设备和可读存储介质 | |
| CN113053369A (zh) | 智能家电的语音控制方法及装置、智能家电 | |
| CN114582318A (zh) | 一种基于语音识别的智能家居控制方法及系统 |
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: 20932051 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: 20932051 Country of ref document: EP Kind code of ref document: A1 |