WO2020228280A1 - 智能家居设备的声音控制方法、装置、及电子装置 - Google Patents
智能家居设备的声音控制方法、装置、及电子装置 Download PDFInfo
- Publication number
- WO2020228280A1 WO2020228280A1 PCT/CN2019/117721 CN2019117721W WO2020228280A1 WO 2020228280 A1 WO2020228280 A1 WO 2020228280A1 CN 2019117721 W CN2019117721 W CN 2019117721W WO 2020228280 A1 WO2020228280 A1 WO 2020228280A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- voice
- voice response
- natural language
- language content
- voiceprint feature
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000004044 response Effects 0.000 claims abstract description 84
- 238000012795 verification Methods 0.000 claims abstract description 29
- 230000015654 memory Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Definitions
- This application relates to the field of smart homes, and in particular, to a sound control method, device, and electronic device of smart home equipment.
- the embodiments of the present application provide a sound control method, device, and electronic device for smart home equipment, so as to at least solve the problem that the sound control method of smart home equipment in the prior art is not smart enough.
- a voice control method for a smart home device includes: acquiring collected voice instructions; identifying voiceprint features in the voice instructions; and comparing the voiceprint features in the voice instructions with a model library Match each voiceprint feature model in to determine whether the first object issuing the voice instruction has operation authority; if it has operation authority, recognize the natural language content in the voice instruction to control the smart home device to execute the natural language content instruction If you do not have the operation authority, prompt the target question, obtain the collected voice answer, and verify the voice answer. If the voice answer verification is successful, configure the operation authority for the first object and recognize the voice
- the natural language content in the instruction is used to control the smart home device to perform the target operation indicated by the natural language content.
- a sound control device for smart home equipment.
- the device includes: an acquisition module for acquiring the collected voice instructions of the first object, where the voice instructions are used to instruct the smart home equipment Perform target operations; recognition module, used to identify voiceprint features in voice instructions; matching module, used to match voiceprint features in voice instructions with each voiceprint feature model in the model library to determine the voice instruction Whether the first object has operation authority; the first execution module is used to identify the natural language content in the voice instruction if it has the operation authority to control the smart home device to perform the target operation indicated by the natural language content; the second execution module, It is used to prompt the target question if it does not have the operation authority, and obtain the collected voice answer, and verify the voice answer. If the voice answer verification is successful, configure the operation authority for the first object and identify the voice command Natural language content to control the smart home device to perform the target operation indicated by the natural language content.
- non-volatile readable storage medium in which computer readable instructions are stored, wherein the computer readable instructions are configured to execute the above Steps in any method embodiment.
- an electronic device including a memory and a processor, the memory stores computer-readable instructions, and the processor is configured to run the computer-readable instructions to execute Steps in any of the above method embodiments.
- the embodiment of the present application recognizes the voiceprint feature after each voice command is received, and when the voiceprint feature matches the voiceprint feature with operation authority, the operation indicated by the voice instruction is executed, and the voiceprint feature matches the voiceprint feature.
- the voiceprint feature with operation authority in the database does not match, the user who issued the voice command is asked a question to determine whether the obtained voice response is successfully verified. If it is successful, the voiceprint of the first object Features are added to the library to achieve a more intelligent technical effect of responding to user instructions. When a new user uses it for the first time, even if he does not have permission, he will ask questions and obtain voice answers to verify whether the new user is granted operation permissions, simplifying the addition. Steps for new users with operating rights.
- Fig. 1 is a flowchart of a sound control method of a smart home device according to an embodiment of the present application
- Fig. 2 is a schematic diagram of a sound control device of a smart home device according to an embodiment of the present application
- Fig. 3 is a block diagram of the hardware structure of a smart home device according to an embodiment of the present application.
- This embodiment provides a sound control method for smart home devices, which can be applied to the client side, where the client can be running in smart home devices, such as smart air conditioners, smart air purifiers, smart refrigerators, and smart lamps. and many more.
- smart home devices such as smart air conditioners, smart air purifiers, smart refrigerators, and smart lamps. and many more.
- the intelligence mentioned in the embodiments of the present application means that the household equipment provides a processor and other modules for performing calculations, so as to run the methods provided in the embodiments of the present application in combination with the hardware of the household equipment. It should be noted that running in different smart home devices is only a difference in the execution subject of the solution. Those skilled in the art can foresee that running in different computing devices can produce the same technical effect.
- the voice control method of the smart home device recognizes the voiceprint feature after each voice instruction is received, and in the case that the voiceprint feature matches the voiceprint feature with operation authority, executes the voice instruction Operation, and in the case that it does not match any voiceprint feature with operating authority in the voiceprint feature database, by asking questions to the user who issued the voice command, it is determined whether the obtained voice response is successfully verified, and if successful ,
- the voiceprint feature of the first object is added to the library to achieve a more intelligent technical effect of responding to user instructions. When a new user uses it for the first time, even if he does not have permission, he will ask questions and obtain voice answers to verify whether Granting new users operation permissions simplifies the steps of adding new users with operating permissions.
- the sound control method of the smart home device includes the following steps:
- Step 101 Acquire the collected voice instructions of the first object.
- Voice commands are used to instruct smart home devices to perform target operations.
- the content indicated by the voice instruction is determined by recognizing the semantic information in the sound. After the semantic information in the sound is recognized, if it is an instruction, it is determined that the collected voice is a voice instruction, and the semantic content is what it indicates operating.
- the sound collection module can be installed on the smart home device, or can be installed in other devices or spaces.
- the executor of the embodiment of this application can connect to the sound collection module to obtain the sound collection module.
- the collected sound is then identified and the semantics in the sound are determined to be an instruction.
- the first object does not specifically refer to a specific object, and is only used to indicate the object that issued the voice command.
- Step 102 Identify voiceprint features in the voice command.
- Voiceprint characteristics are the characteristics of the sound wave spectrum of human sounds. Human voices have specificity and stability. Each person’s voice has specific characteristics in terms of pitch, intensity, length, and timbre. These aspects are also It can be decomposed into more than ninety kinds of characteristics to express the wavelength, frequency, intensity, and rhythm of different people's voices. Therefore, the voiceprint feature can be used to distinguish the object that emits the sound.
- the specific voiceprint features that need to be recognized are determined by the voiceprint features that need to be compared during the subsequent voiceprint feature matching. Which voiceprint feature matching is specifically selected, that is, which voiceprint features need to be recognized. It is selected according to specific conditions, such as adopting an existing algorithm for identifying and matching voiceprint features or an improved algorithm thereof, which is not specifically limited in the embodiment of the present application.
- Step 103 Match the voiceprint feature in the voice instruction with each voiceprint feature model in the model library to determine whether the first object issuing the voice instruction has operation authority.
- the way to determine whether the first object has operation authority is to judge according to the matching result of the voiceprint feature. If the voiceprint feature of the first object is successfully matched with an object in the model library, and it has operation authority, It is determined that the first object has the operation authority. Otherwise, if the voiceprint feature of the first object does not match any object in the model library successfully, or the voiceprint feature of the first object matches an object in the model library successfully but If it is not specified that it has operation authority, it is determined that the first object does not have operation authority.
- the model library is a database of pre-stored voiceprint feature models, including multiple voiceprint feature models.
- Each voiceprint feature model in the model library is pre-trained for a user.
- the training method can be to receive the user multiple times
- the voice of the spoken voice is identified and stored.
- each voiceprint feature model in the model library also corresponds to the user's operation authority for the smart home device.
- the voiceprint feature can be matched with all voiceprint feature models in the model library one by one to determine whether the voiceprint feature of the voice instruction matches any pre-stored voiceprint feature model. If the matching is successful, for example, if the matching percentage value of the voiceprint feature of the first object with any voiceprint feature model exceeds 99% after matching, it is determined that the voiceprint feature of the first object matches the corresponding voiceprint feature model successfully, Furthermore, it is determined that the operation authority of the first object is the operation authority corresponding to the successfully matched voiceprint feature model. If the matching is not successful, it means that the voiceprint feature of the first object has not been trained and stored in advance.
- Step 104 If you have the operation authority, recognize the natural language content in the voice instruction to control the smart home device to perform the target operation indicated by the natural language content.
- the voiceprint feature of the first object has a matching voiceprint feature model in the voiceprint feature model library, it is determined that the first object has operating authority to the smart home device, and then recognizes the natural language content in the voice instruction and controls the intelligence
- the home equipment performs the target operation indicated by the natural language content.
- each person's operation authority may be individually configured for different operations, and the first object may only have operation authority for one or several operations.
- the voiceprint feature of the first object is successfully matched with the voiceprint feature model of the voiceprint feature model library and the target operation indicated by the first object is identified, it is necessary to further determine whether the operation authority of the first object allows the target operation to be performed. If yes, the target operation is executed, if not, the target operation is still not allowed.
- the specific implementation may be to assign different operation permissions to different objects, with a certain object as the object with the highest authority, and configure the operations that can be performed for other objects.
- the configuration method may be through manual operation panel and/or voice recognition, etc.; Or, another implementation manner is to preset (may be factory settings or manual settings) several different operating authority levels and the operations that can be performed at each level.
- granting authority to the first object Other users grant permissions to the first object, where the permissions granted to the first object by other users may be equal to or lower than their own permission levels. If the operation that can be performed by the operation authority of the first object is not configured, the default configuration is assigned to it.
- Step 105 If the operation authority is not available, the target question is prompted, the collected voice answer is obtained, and the voice answer is verified. If the voice answer verification is successful, the operation authority is configured for the first object and the voice command is recognized In order to control the smart home device to perform the target operation indicated by the natural language content.
- an embodiment of the application provides a technical solution for prompting if the voiceprint feature does not match any voiceprint feature model in the model library The question is to verify the acquired voice answer to determine whether to grant the operation authority of the smart home device to the first object.
- a technical solution combining one or more verification methods can be used. For example, it is verified whether the voiceprint feature of the voice response is a voice response made by a user who has operation authority, if it is, the verification is successful, if not, the verification fails.
- the preset question may be to prompt the user who has the operation authority to make a voice response.
- extract the voiceprint feature in the voice response extract the voiceprint feature in the voice response, and judge whether the voiceprint feature in the voice response has operation Permission, where, if the voiceprint feature has operation permission, it is determined that the voice response verification is successful.
- the above-mentioned optional implementation manner is to use users who already have operation authority to assist users who do not have operation authority to verify.
- semantic recognition of voice responses can also be used directly to verify whether the answers to the voice answers are consistent with the preset questions prompted The answer is the same.
- another optional implementation manner for verifying the collected voice response is to identify whether the voice response matches a preset answer, and if it matches, confirm that the verification is successful. This optional implementation includes the following steps:
- Step 201 Identify the natural language content in the voice response
- Step 202 Verify the natural language content in the voice answer based on the preset answer.
- voice recognition can be performed on the voice response to obtain the text of the voice response, and then it is judged whether it is consistent with the preset answer. For example, a first object without operation authority issues a voice command, and the smart home device recognizes the voiceprint feature, and determines that the voiceprint feature of the first object is different from all voiceprint feature models in the preset voiceprint feature model library. If it matches, it is judged that the first object does not have operation authority, and the smart home device prompts "please answer the owner's name" by voice. After the first object answers the owner's name by voice, the smart home device is performing voice recognition to determine the voice response After the text, whether the pronunciation matches with the preset answer (the owner’s name) is the same. If they are the same, confirm that the verification is successful, grant operation authority to the first object, and execute the voice command issued by the first object.
- the semantic content of the voice response can also be recognized. If it is a predetermined response, for example, the first object without operation authority issues a voice command, and the smart home device recognizes the voiceprint feature and determines that the first object has no Operation authority, the smart home device prompts "please verify whether to add this user" through the voice, and the second user with the operation authority answers "Yes" through the voice, the smart home device confirms that the verification is successful, grants the operation authority to the first object, and Execute the voice command issued by the first object. After the voice response is verified, if the verification fails, the voiceprint feature of the first object may also be stored in the model library, and the first object may be designated as having no operation authority.
- the step of configuring operation authority for the first object may include the following steps:
- Step 301 Prompt the first object to make multiple sounds to obtain voiceprint feature training samples
- Step 302 Use the voiceprint feature training samples to train a preset model
- Step 303 Add the trained preset model to the model library.
- the preset model is the default recognition model. To enable the recognition model to more accurately determine whether the voiceprint features match, the first object can be prompted to make multiple sounds to obtain multiple voiceprint feature training samples, using multiple voiceprint features The training samples train the preset model, and the trained preset model can better recognize whether the voiceprint feature is the voiceprint feature of the first object.
- the method may further include the following steps:
- Step 401 Receive an input setting operation for assigning a permission level to a first object, where a user with a higher permission level has a higher operation priority;
- Step 402 Determine whether the authority level of the user inputting the setting operation is higher than the authority level assigned to the first object
- Step 403 If the judgment result is yes, assign the entered authority level to the first object.
- the authority level may be divided into N preset levels, or the authority level may be to sort the authority levels of multiple objects that have operation authority. If the authority level of the first object is configured to be the i-th level, a user with a authority level higher than the i-th level is required to confirm by voice.
- the voice command issued by the user with a lower authority level will be ignored, for example, the first object’s If the authority level is higher than the second object, the first object issues a voice command to instruct the air conditioner to "increase wind speed". If the second object issues a voice command within 1 minute, it will automatically be ignored and the voice command issued by the second object will not be executed.
- the setting operation of assigning a permission level to the first object may be input by the user through voice, the user's identity can be determined by recognizing voiceprint features, and the permission level assigned to the first object can be determined by recognizing voice semantics, and further determining the setting Whether the authority level of the operating user is higher than the authority level assigned to the first object. For example, user A says "set user B to the second level" to the air conditioner. After receiving the voice, the air conditioner recognizes the voiceprint characteristics of user A and determines that user A's level is the first level, which is higher than the one set for user B The air conditioner sets the user B's level to the second level.
- the recognized voiceprint feature is matched with each voiceprint feature model that has operation authority in the model library. If the voiceprint feature of the issued voice instruction matches the model library If any of the voiceprint feature models do not match, the preset question is prompted, and the verification is performed according to the voice answer. If the verification is successful, the operation indicated by the voice instruction is performed, and the operation authority is configured for the first object that issued the voice instruction, simplifying Steps to add a new user with operation authority.
- the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is Better implementation.
- the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes several instructions to enable a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the method described in each embodiment of the present application.
- a sound control device for smart home equipment is also provided, which is used to implement the above-mentioned embodiment 1 and its preferred embodiments.
- a sound control device for smart home equipment is also provided, which is used to implement the above-mentioned embodiment 1 and its preferred embodiments.
- please refer to the implementation The related descriptions in Example 1 will not be repeated for those that have already been described.
- module is a combination of software and/or hardware that can implement predetermined functions.
- devices described in the following embodiments are preferably implemented by software, the implementation of hardware or a combination of software and hardware can also be conceived.
- Fig. 2 is a schematic diagram of a sound control device for smart home equipment according to an embodiment of the present application. As shown in Fig. 2, the device includes: an acquisition module 10, an identification module 20, a matching module 30, a first execution module 40, and a second execution Module 50.
- the acquiring module is used to acquire the collected voice instructions of the first object, where the voice instructions are used to instruct the smart home device to perform the target operation; the recognition module is used to identify voiceprint features in the voice instructions; the matching module is used to The voiceprint feature in the voice instruction is matched with each voiceprint feature model in the model library to determine whether the first object issuing the voice instruction has operation authority; the first execution module is used to identify if it has operation authority The natural language content in the voice instruction is used to control the smart home device to perform the target operation indicated by the natural language content; the second execution module is used to prompt the target question if it does not have the operation authority, and obtain the collected voice answer, and The voice response is verified.
- the first object is configured with operation authority, and the natural language content in the voice instruction is recognized to control the smart home device to perform the target operation indicated by the natural language content.
- the verification module includes: a first extraction unit for extracting voiceprint features in a voice response; a first judging unit for judging whether the voiceprint feature in the voice response has operation authority, where if the voiceprint feature With operation authority, it is determined that the voice answer verification is successful.
- the verification module includes: an identification unit for identifying natural language content in the voice response; and a verification unit for verifying the natural language content in the voice response based on a preset answer.
- the verification module includes: a second extraction unit for extracting voiceprint features in a voice response; a second judging unit for judging whether the voiceprint feature in a voice response has operation authority; an execution unit for if With the operation authority, the natural language content in the voice response is recognized, and the natural language content in the voice response is verified based on the preset answer.
- the third execution module includes: a prompt unit for prompting the first object to make multiple sounds to obtain a voiceprint feature training sample; a training unit for training a preset model using the voiceprint feature training sample; an adding unit , Used to add the pre-trained model to the model library.
- the device further includes: a receiving module for receiving the input setting operation of assigning a permission level to the first object after the trained preset model is added to the model library, wherein the user with a higher permission level The operation priority is higher; the judgment module is used to judge whether the permission level of the user inputting the setting operation is higher than the permission level assigned to the first object; the allocation module is used to assign input to the first object if the judgment result is yes The permission level.
- each of the above modules can be implemented by software or hardware.
- it can be implemented in the following manner, but not limited to this: the above modules are all located in the same processor; or, the above modules are combined in any combination The forms are located in different processors.
- modules or steps of this application can be implemented by a general computing device, and they can be concentrated on a single computing device or distributed in a network composed of multiple computing devices.
- they can be implemented with program codes executable by the computing device, so that they can be stored in the storage device for execution by the computing device, and in some cases, can be executed in a different order than here.
- the embodiment of the present application also provides a non-volatile readable storage medium, the storage medium stores a computer readable instruction, wherein the computer readable instruction is set to execute any of the above method embodiments when running Steps in.
- the foregoing storage medium may include, but is not limited to: U disk, Read-Only Memory (Read-Only Memory, ROM for short), Random Access Memory (Random Access Memory, RAM for short), Various media that can store computer-readable instructions, such as mobile hard disks, magnetic disks, or optical disks.
- An embodiment of the present application also provides an electronic device, including a memory and a processor, the memory stores computer readable instructions, and the processor is configured to run the computer readable instructions to execute any of the above method embodiments.
- the aforementioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the aforementioned processor, and the input-output device is connected to the aforementioned processor.
- FIG. 3 is a hardware structure block diagram of a smart home device according to an embodiment of the present application. As shown in FIG. 3, the smart home device may include one or more (only one is shown in FIG.
- processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA.
- the aforementioned smart home device may also include a transmission device 306 and an input/output device 308 for communication functions.
- FIG. 3 is only for illustration, and it does not limit the structure of the above-mentioned smart home device.
- the smart home device may also include more or fewer components than shown in FIG. 3, or have a different configuration from that shown in FIG.
- the memory 304 may be used to store computer-readable instructions, for example, software programs and modules of application software, such as computer-readable instructions corresponding to the image recognition method in the embodiment of the present application.
- the processor 302 runs the computer stored in the memory 304
- the instructions are readable to execute various functional applications and data processing, that is, to implement the above methods.
- the memory 304 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.
- the memory 304 may further include a memory remotely provided with respect to the processor 302, and these remote memories may be connected to a smart home device through a network.
- the transmission device 306 is used to receive or send data via a network.
- the foregoing specific examples of the network may include a wireless network provided by a communication provider of a smart home device.
- the transmission device 306 includes a network adapter (Network Interface Controller, NIC for short), which can be connected to other network devices through a base station to communicate with the Internet.
- the transmission device 306 may be a radio frequency (RF) module, which is used to communicate with the Internet in a wireless manner.
- RF radio frequency
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Selective Calling Equipment (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
一种智能家居设备的声音控制方法、装置、及电子装置,其中,该方法包括:获取采集的声音指令(S101);识别声音指令中的声纹特征(S102);将声音指令中的声纹特征与模型库中的每个声纹特征模型进行匹配,以确定发出声音指令的第一对象是否有操作权限(S103);如果具有操作权限,则识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作(S104);如果不具备操作权限,则提示目标问题,并对采集到的声音回答进行验证,在声音回答验证成功的情况下,为第一对象配置操作权限,并识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作(S105)。解决了现有技术中智能家居设备的声音控制方法不够智能的问题。
Description
本申请要求与2019年5月10日提交中国专利局、申请号为201910390794X、申请名称为“智能家居设备的声音控制方法、装置、及电子装置”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。
本申请涉及智能家居领域,具体而言,涉及一种智能家居设备的声音控制方法、装置、及电子装置。
随着科技的发展,智能家居越来越受到用户的欢迎,其中,通过智能语音控制家居可以取消用户按下遥控器按键的操作,用户只需要说出指令,智能家居即可根据指令执行控制命令,对房间中的智能家居设备进行操控,如音乐播放、家电控制等,成为极为重要的用户体验。发明人发现为了使智能家居设备仅根据拥有主人权限的用户的声音指令进行操作,可以通过一些方式对身份进行验证,但是,现有的验证方式比较复杂,通常需要用户参考说明书进行操作,不够智能。
针对相关技术中存在的上述问题,目前尚未发现有效的解决方案。
发明内容
本申请实施例提供了一种智能家居设备的声音控制方法、装置、及电子装置,以至少解决现有技术中的智能家居设备的声音控制方法不够智能的问题。
根据本申请的一个实施例,提供了一种智能家居设备的声音控制方法,该方法包括:获取采集的声音指令;识别声音指令中的声纹特征;将声音指令中的声纹特征与模型库中的每个声纹特征模型进行匹配,以确定发出声音指令的第一对象是否有操作权限;如果具有操作权限,则识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作;如果不具备操作权限,则提示目标问题,并获取采集到的声音回答,并对声音回答进行验证,在声音回答验证成功的情况下,为第一对象配置操作权限,并识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作。
根据本申请的另一个实施例,提供了一种智能家居设备的声音控制装置,该装置包括:获取模块,用于获取采集的第一对象的声音指令,其中,声音指令用于指示智能家居设备执行目标操作;识别模块,用于识别声音指令中的声纹特征;匹配模块,用于将声音指令中的声纹特征与模型库中的每个声纹特征模型进行匹配,以确定发出声音指令的第一对象是否有操作权限;第一执行模块,用于如果具有操作权限,则识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作;第二执行模块,用于如果不具备操作权限,则提示目标问题,并获取采集到的声音回答,并对声音回答进行验证,在声音回答验证成功的情况下,为第一对象配置操作权限,并识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作。
根据本申请的又一个实施例,还提供了一种非易失性可读存储介质,所述存储介质中存储有计算机可读指令,其中,所述计算机可读指令被设置为运行时执行上述任一项方法实施例中的步骤。
根据本申请的又一个实施例,还提供了一种电子装置,包括存储器和处理器,所述存储器中存储有计算机可读指令,所述处理器被设置为运行所述计算机可读指令以执行上述任一项方法实施例中的步骤。
本申请实施例通过在每次接收到声音指令之后识别声纹特征,在声纹特征与具有操作权限的声纹特征匹配的情况下,执行声音指令所指示的操作,而在与声纹特征的数据库中的任意一个具有操作权限的声纹特征都不匹配的情况下,通过向发出声音指令的用户提出问题,判断获取到的声音回答是否验证成功,如果成功,则将第一对象的声纹特征加入到库中,以达到更智能的响应用户指令的技术效果,新用户在初次使用时,即使没有权限,也会通过提出问题、获取声音回答来验证是否赋予新用户操作权限,简化了添加具有操作权限的新用户的步骤。
此处所说明的附图用来提供对本申请的进一步理解,构成本申请的一部分,本申请的示意性实施例及其说明用于解释本申请,并不构成对本申请的不当限定。在附图中:
图1是根据本申请实施例的智能家居设备的声音控制方法的流程图;
图2是根据本申请实施例的智能家居设备的声音控制装置的示意图;
图3是本申请实施例的一种智能家居设备的硬件结构框图。
为了使本技术领域的人员更好地理解本申请方案,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本申请一部分的实施例,而不是全部的实施例,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互组合。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都应当属于本申请保护的范围。
需要说明的是,本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
实施例1
本实施例提供了一种智能家居设备的声音控制方法,可以应用于客户端侧,其中,客户端可以运行中智能的家居设备中,例如,智能空调、智能空气净化器、智能冰箱、智能灯具等等。本申请实施例中所述的智能是指家居设备提供了处理器等用于进行运算的模块,以结合家居设备的硬件运行本申请实施例所提供的方法。需要说明的是,运行在不同的智能家居设备中仅是方案在执行主体 上的差异,本领域人员可预见在不同运算设备中运行能够产生相同的技术效果。
本实施例提供的智能家居设备的声音控制方法,通过在每次接收到声音指令之后识别声纹特征,在声纹特征与具有操作权限的声纹特征匹配的情况下,执行声音指令所指示的操作,而在与声纹特征的数据库中的任意一个具有操作权限的声纹特征都不匹配的情况下,通过向发出声音指令的用户提出问题,判断获取到的声音回答是否验证成功,如果成功,则将第一对象的声纹特征加入到库中,以达到更智能的响应用户指令的技术效果,新用户在初次使用时,即使没有权限,也会通过提出问题、获取声音回答来验证是否赋予新用户操作权限,简化了添加具有操作权限的新用户的步骤。
如图1所示,本实施例提供的智能家居设备的声音控制方法包括如下步骤:
步骤101,获取采集的第一对象的声音指令。
声音指令用于指示智能家居设备执行目标操作。声音指令所指示的内容是通过识别声音中的语义来确定的,在识别出声音中的语义信息之后,如果是一条指令,则确定采集到的声音为声音指令,语义的内容为其所指示的操作。
采集声音的模块可以是设置在智能家居设备上,也可以是设置于其它设备或空间中,在采集到声音之后,本申请实施例的执行方可以与采集声音的模块联网,以获取采集声音模块所采集到的声音,进而识别声音中的语义,确定其为一条指令。
第一对象非特指某一个特定的对象,仅用于表示发出声音指令的对象。
步骤102,识别声音指令中的声纹特征。
在获取到声音指令之后,识别声音指令中的声纹特征。声纹特征是人发出声音的声波频谱的特征,人的声音具有特定性和稳定性,每个人的声音在音高、音强、音长、音色这几个方面具有特定的特征,这些方面又可分解成九十余种特征,以表现不同人的声音的波长、频率、强度、节奏的不同。因此,可以采用声纹特征来区分发出声音的对象。
具体需要识别哪些声纹特征,是由后续在进行声纹特征的匹配时所需要比对的声纹特征来决定,具体选择采用哪些声纹特征匹配,也即需要识别出哪些声纹特征,可以根据具体的情况选择,如采用现有的识别声纹特征和匹配声纹特征的算法或其改进算法,本申请实施例对此不做具体限定。
步骤103,将声音指令中的声纹特征与模型库中的每个声纹特征模型进行匹配,以确定发出声音指令的第一对象是否有操作权限。
在该步骤中,确定第一对象是否有操作权限的方式是根据声纹特征的匹配结果进行判断,如果第一对象的声纹特征与模型库中的某一个对象匹配成功,并且具有操作权限,则确定第一对象具有操作权限,否则,如果第一对象的声纹特征与模型库中的任一对象均未匹配成功,或者第一对象的声纹特征与模型库中的一个对象匹配成功但是并未指定其具有操作权限,则确定第一对象不具有操作权限。
模型库是预先存储的声纹特征模型的数据库,包括多个声纹特征模型,模型库中的每个声纹特征模型是预先针对一个用户训练出的,训练的方式可以是接收该用户多次说话的声音,识别出其声纹特征,并存储,进一步地,模型库中的每个声纹特征模型还对应有该用户对智能家居设备所具有的操作权限。
在识别出声音指令的声纹特征之后,可以将声纹特征与模型库中的所有声纹特征模型一一匹配,以判断声音指令的声纹特征是否与预先存储的任一声纹特征模型匹配。如果匹配成功,例如,如果经过匹配确定第一对象的声纹特征与任一声纹特征模型的匹配百分比值超过99%,则确定第一对象的声纹特征与对应的声纹特征模型匹配成功,进而,确定第一对象的操作权限为匹配成功的声纹特征模型所对应的操作权限。如果未匹配成功,则说明预先并未对第一对象的声纹特征进行训练和存储。
步骤104,如果具有操作权限,则识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作。
如果确定第一对象的声纹特征在声纹特征模型库中具有匹配的声纹特征模型,则确定第一对象对智能家居设备具有操作权限,进而识别声音指令中的自然语言内容,并控制智能家居设备执行自然语言内容指示的目标操作。
可选的,作为一种可选的实施方式,每个人的操作权限可以针对不同的操作单独的配置,第一对象可以仅针对一种或几种操作具有操作权限,在这种应用场景中,在第一对象的声纹特征与声纹特征模型库的声纹特征模型匹配成功并识别出第一对象指示的目标操作之后,还需要进一步确定第一对象的操作权限是否允许执行目标操作,如果是,则执行目标操作,如果不是,依然不允许执行目标操作。
为了实现上述应用场景,需要预先对第一对象的操作权限所允许执行的操作进行配置。具体实施方式可以是对不同对象分配不同的操作权限,由某一个对象作为最高权限的对象,为其他对象配置所能执行的操作,配置的方式可以是通过手动操作面板和/或语音识别等;或者,另一种实施方式是预先设定(可以是出厂设定、或人工设定)几个不同的操作权限的等级以及每个等级所能执行的操作,在为第一对象赋予权限时,由其他用户为第一对象赋予权限,其中,其他用户为第一对象赋予的权限可以等于或低于其自身的权限等级。如果未对第一对象的操作权限所能执行的操作进行配置,则为其赋予默认的配置。
步骤105,如果不具备操作权限,则提示目标问题,并获取采集到的声音回答,并对声音回答进行验证,在声音回答验证成功的情况下,为第一对象配置操作权限,并识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作。
为了简化新用户申请智能家居设备的操作权限的步骤,本申请实施例提供了一种技术方案,用于在声纹特征与模型库中的任一声纹特征模型均不匹配的情况下,通过提示问题,对获取的声音回答进行验证来判断是否将智能家居设备的操作权限赋予给第一对象。
可选的,在对声音回答进行验证时,可以采用一种或多种验证方式相结合的技术方案。例如,验证声音回答的声纹特征是否是已具有操作权限的用户所发出的声音回答,如果是,则验证成功,如果不是,则验证失败。相应的,预设问题可以是提示已具有操作权限的用户发出声音回答,在对采集到的声音回答进行验证时,提取声音回答中的声纹特征,判断声音回答中的声纹特征是否具有操作权限,其中,如果声纹特征具有操作权限,则确定声音回答验证成功。
上述可选的实施方式是利用已经具有操作权限的用户协助没有操作权限的用户进行验证,可选的,还可以直接采用对声音回答的语义识别验证声音回答的答案是否与提示的预设问题的答案相同。 具体而言,对采集到的声音回答进行验证的另一种可选的实施方式为,识别声音回答是否与预设的答案相匹配,如果匹配,则确认验证成功。本可选的实施方式包括如下步骤:
步骤201,识别声音回答中的自然语言内容;
步骤202,基于预设答案验证声音回答中的自然语言内容。
在识别声音回答中的自然语言内容时,可以针对声音回答执行语音识别,以得到声音回答的文字,进而,判断是否与预设答案相符合。例如,没有操作权限的第一对象发出声音指令,智能家居设备对声纹特征进行识别,判断出第一对象的声纹特征与预设的声纹特征模型库中的所有声纹特征模型均不匹配,则判断出第一对象没有操作权限,智能家居设备通过声音提示“请回答主人的姓名”,第一对象在通过声音回答出主人的姓名之后,智能家居设备在执行语音识别确定声音回答中的文字之后,与预设答案(主人的姓名)的读音匹配是否相同,如果相同,则确认验证成功,对第一对象赋予操作权限,并执行第一对象发出的声音指令。
可选的,还可以对声音回答的语义内容进行识别,如果是预定的回答,例如,没有操作权限的第一对象发出声音指令,智能家居设备对声纹特征进行识别,判断出第一对象没有操作权限,智能家居设备通过声音提示“请主人验证是否添加该用户”,有操作权限的第二用户通过声音回答“是”,则智能家居设备确认验证成功,对第一对象赋予操作权限,并执行第一对象发出的声音指令。在对声音回答进行验证之后,如果验证失败,也可以将第一对象的声纹特征存储至模型库中,并指定第一对象是没有操作权限的。
可选的,为第一对象配置操作权限的步骤,可以包括如下步骤:
步骤301,提示第一对象发出多次声音,以得到声纹特征训练样本;
步骤302,利用声纹特征训练样本训练预设模型;
步骤303,将训练后的预设模型加入模型库。
预设模型是默认的识别模型,为了使识别模型能够更准确的判断声纹特征是否匹配,可以提示第一对象发出多次声音,以得到多个声纹特征训练样本,利用多个声纹特征训练样本对预设模型进行训练,训练后的预设模型的能够更好的识别声纹特征是否是第一对象的声纹特征。
可选的,在将训练后的预设模型加入模型库之后,该方法还可以包括如下步骤:
步骤401,接收输入的为第一对象分配权限等级的设置操作,其中,权限等级较高的用户操作优先级较高;
步骤402,判断输入设置操作的用户的权限等级是否高于为第一对象分配的权限等级;
步骤403,如果判断结果为是,则为第一对象分配输入的权限等级。例如,权限等级可以分为预设的N个级别,或者,权限等级可以是对已具有操作权限的多个对象的权限等级进行排序。如果配置第一对象的权限等级为第i级,则需要权限等级高于第i级的用户通过声音进行确认。
在应用时,如果权限等级较高的用户对智能家居设备发出声音指令指示进行目标操作,在预设时间间隔之内,会忽略权限等级低于该用户发出的声音指令,例如,第一对象的权限等级高于第二对象,第一对象发出声音指令指示空调“风速增大”,如果在1分钟内第二对象发出声音指令,则自 动忽略,不执行第二对象发出的声音指令。
可选的,为第一对象分配权限等级的设置操作可以是用户通过语音输入的,可以通过识别声纹特征确定用户身份,并通过识别语音语义确定为第一对象分配的权限等级,进一步确定设置操作的用户的权限等级是否高于为第一对象分配的权限等级。例如,用户A对空调说“设置用户B为第二级别”,空调在接收到语音之后,识别出用户A的声纹特征,确定用户A的等级为第一级别,高于为用户B设置的级别,进而空调将用户B的级别设置为第二级别。
本实施例提供的方法,在接收到声音指令之后,将识别出的声纹特征与模型库中具有操作权限的每个声纹特征模型进行匹配,如果发出声音指令的声纹特征与模型库中的任一声纹特征模型不匹配,则提示预设的问题,并根据声音回答进行验证,如果验证成功,则执行声音指令所指示的操作,并对发出声音指令的第一对象配置操作权限,简化了添加具有操作权限的新用户的步骤。
需要说明的是,在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行,并且,虽然在流程图中示出了逻辑顺序,但是在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤。
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根据上述实施例的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,或者网络设备等)执行本申请各个实施例所述的方法。
实施例2
在本实施例中还提供了一种智能家居设备的声音控制装置,该装置用于实现上述实施例1及其优选实施方式,对于本实施例中未详述的术语或实现方式,可参见实施例1中的相关说明,已经进行过说明的不再赘述。
如以下所使用的术语“模块”,是可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现,但是硬件,或者软件和硬件的组合的实现也是可以被构想的。
图2是根据本申请实施例的智能家居设备的声音控制装置的示意图,如图2所示,该装置包括:获取模块10,识别模块20,匹配模块30,第一执行模块40和第二执行模块50。
其中,获取模块,用于获取采集的第一对象的声音指令,其中,声音指令用于指示智能家居设备执行目标操作;识别模块,用于识别声音指令中的声纹特征;匹配模块,用于将声音指令中的声纹特征与模型库中的每个声纹特征模型进行匹配,以确定发出声音指令的第一对象是否有操作权限;第一执行模块,用于如果具有操作权限,则识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作;第二执行模块,用于如果不具备操作权限,则提示目标问题,并获取采集到的声音回答,并对声音回答进行验证,在声音回答验证成功的情况下,为第一对象配置操作权限,并识别声音指令中的自然语言内容,以控制智能家居设备执行自然语言内容指示的目标操作。
可选的,验证模块包括:第一提取单元,用于提取声音回答中的声纹特征;第一判断单元,用于判断声音回答中的声纹特征是否具有操作权限,其中,如果声纹特征具有操作权限,则确定声音回答验证成功。
可选的,验证模块包括:识别单元,用于识别声音回答中的自然语言内容;验证单元,用于基于预设答案对声音回答中的自然语言内容进行验证。
可选的,验证模块包括:第二提取单元,用于提取声音回答中的声纹特征;第二判断单元,用于判断声音回答中的声纹特征是否具有操作权限;执行单元,用于如果具有操作权限,则识别声音回答中的自然语言内容,并基于预设答案对声音回答中的自然语言内容进行验证。
可选的,第三执行模块包括:提示单元,用于提示第一对象发出多次声音,以得到声纹特征训练样本;训练单元,用于利用声纹特征训练样本训练预设模型;添加单元,用于将训练后的预设模型加入模型库。
可选的,该装置还包括:接收模块,用于在将训练后的预设模型加入模型库之后,接收输入的为第一对象分配权限等级的设置操作,其中,权限等级较高的用户的操作优先级较高;判断模块,用于判断输入设置操作的用户的权限等级是否高于为第一对象分配的权限等级;分配模块,用于如果判断结果为是,则为第一对象分配输入的权限等级。
需要说明的是,上述各个模块是可以通过软件或硬件来实现的,对于后者,可以通过以下方式实现,但不限于此:上述模块均位于同一处理器中;或者,上述各个模块以任意组合的形式分别位于不同的处理器中。
显然,本领域的技术人员应该明白,上述的本申请的各模块或各步骤可以用通用的计算装置来实现,它们可以集中在单个的计算装置上,或者分布在多个计算装置所组成的网络上,可选地,它们可以用计算装置可执行的程序代码来实现,从而,可以将它们存储在存储装置中由计算装置来执行,并且在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤,或者将它们分别制作成各个集成电路模块,或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样,本申请不限制于任何特定的硬件和软件结合。
实施例3
本申请的实施例还提供了一种非易失性可读存储介质,该存储介质中存储有计算机可读指令,其中,该计算机可读指令被设置为运行时执行上述任一项方法实施例中的步骤。可选地,在本实施例中,上述存储介质可以包括但不限于:U盘、只读存储器(Read-Only Memory,简称为ROM)、随机存取存储器(Random Access Memory,简称为RAM)、移动硬盘、磁碟或者光盘等各种可以存储计算机可读指令的介质。
实施例4
本申请的实施例还提供了一种电子装置,包括存储器和处理器,该存储器中存储有计算机可读指令,该处理器被设置为运行计算机可读指令以执行上述任一项方法实施例中的步骤。可选地,上述电子装置还可以包括传输设备以及输入输出设备,其中,该传输设备和上述处理器连接,该输入输出设备和上述处理器连接。以电子装置为智能家居设备为例,图3是本申请实施例的一种智能家 居设备的硬件结构框图。如图3所示,智能家居设备可以包括一个或多个(图3中仅示出一个)处理器102(处理器302可以包括但不限于微处理器MCU或可编程逻辑器件FPGA等的处理装置)和用于存储数据的存储器304,可选地,上述智能家居设备还可以包括用于通信功能的传输设备306以及输入输出设备308。本领域普通技术人员可以理解,图3所示的结构仅为示意,其并不对上述智能家居设备的结构造成限定。例如,智能家居设备还可包括比图3中所示更多或者更少的组件,或者具有与图3所示不同的配置。存储器304可用于存储计算机可读指令,例如,应用软件的软件程序以及模块,如本申请实施例中的图像的识别方法对应的计算机可读指令,处理器302通过运行存储在存储器304内的计算机可读指令,从而执行各种功能应用以及数据处理,即实现上述的方法。存储器304可包括高速随机存储器,还可包括非易失性存储器,如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中,存储器304可进一步包括相对于处理器302远程设置的存储器,这些远程存储器可以通过网络连接至智能家居设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。传输装置306用于经由一个网络接收或者发送数据。上述的网络具体实例可包括智能家居设备的通信供应商提供的无线网络。在一个实例中,传输装置306包括一个网络适配器(Network Interface Controller,简称为NIC),其可通过基站与其他网络设备相连从而可与互联网进行通讯。在一个实例中,传输装置306可以为射频(Radio Frequency,简称为RF)模块,其用于通过无线方式与互联网进行通讯。
以上所述仅为本申请的优选实施例而已,并不用于限制本申请,对于本领域的技术人员来说,本申请可以有各种更改和变化。凡在本申请的原则之内,所作的任何修改、等同替换、改进等,均应包含在本申请的保护范围之内。
Claims (20)
- 一种智能家居设备的声音控制方法,所述方法包括:获取采集的声音指令;识别所述声音指令中的声纹特征;将所述声音指令中的声纹特征与模型库中的每个声纹特征模型进行匹配,以确定发出所述声音指令的第一对象是否有操作权限;如果具有操作权限,则识别所述声音指令中的自然语言内容,以控制智能家居设备执行所述自然语言内容指示的目标操作;如果不具备操作权限,则提示目标问题,并获取采集到的声音回答,并对所述声音回答进行验证,在所述声音回答验证成功的情况下,为所述第一对象配置所述操作权限,并识别所述声音指令中的自然语言内容,以控制所述智能家居设备执行所述自然语言内容指示的目标操作。
- 根据权利要求1所述的方法,所述对所述声音回答进行验证的步骤,包括:提取所述声音回答中的声纹特征,判断所述声音回答中的声纹特征是否具有所述操作权限,其中,如果所述声纹特征具有所述操作权限,则确定所述声音回答验证成功。
- 根据权利要求1所述的方法,所述对所述声音回答进行验证的步骤,包括:识别所述声音回答中的自然语言内容;基于预设答案对所述声音回答中的自然语言内容进行验证。
- 根据权利要求1所述的方法,所述对所述声音回答进行验证的步骤,包括:提取所述声音回答中的声纹特征,判断所述声音回答中的声纹特征是否具有所述操作权限;如果具有所述操作权限,则识别所述声音回答中的自然语言内容,并基于预设答案对所述声音回答中的自然语言内容进行验证。
- 根据权利要求1所述的方法,所述为所述第一对象配置所述操作权限的步骤,包括:提示所述第一对象发出多次声音,以得到声纹特征训练样本;利用所述声纹特征训练样本训练预设模型;将训练后的预设模型加入所述模型库。
- 根据权利要求5所述的方法,在将训练后的预设模型加入所述模型库之后,所述方法还包括:接收输入的为所述第一对象分配权限等级的设置操作,其中,所述权限等级较高的用户的操作优先级较高;判断输入设置操作的用户的权限等级是否高于为所述第一对象分配的权限等级;如果判断结果为是,则为所述第一对象分配输入的权限等级。
- 一种智能家居设备的声音控制装置,所述装置包括:获取模块,用于获取采集的第一对象的声音指令,其中,所述声音指令用于指示智能家居设备执行目标操作;识别模块,用于识别所述声音指令中的声纹特征;匹配模块,用于将所述声音指令中的声纹特征与模型库中的每个声纹特征模型进行匹配,以确定发出所述声音指令的第一对象是否有操作权限;第一执行模块,用于如果具有操作权限,则识别所述声音指令中的自然语言内容,以控制智能家居设备执行所述自然语言内容指示的目标操作;第二执行模块,用于如果不具备操作权限,则提示目标问题,并获取采集到的声音回答,并对所述声音回答进行验证,在所述声音回答验证成功的情况下,为所述第一对象配置所述操作权限,并识别所述声音指令中的自然语言内容,以控制所述智能家居设备执行所述自然语言内容指示的目标操作。
- 根据权利要求7所述的装置,所述第二执行模块包括:第一提取单元,用于提取所述声音回答中的声纹特征;第一判断单元,用于判断所述声音回答中的声纹特征是否具有所述操作权限,其中,如果所述声纹特征具有所述操作权限,则确定所述声音回答验证成功。
- 根据权利要求7所述的装置,所述第二执行模块包括:识别单元,用于识别所述声音回答中的自然语言内容;验证单元,用于基于预设答案对所述声音回答中的自然语言内容进行验证。
- 根据权利要求7所述的装置,所述第二执行模块,包括:第二提取单元,用于提取所述声音回答中的声纹特征,判断所述声音回答中的声纹特征是否具有所述操作权限;第二判断单元,用于如果具有所述操作权限,则识别所述声音回答中的自然语言内容,并基于预设答案对所述声音回答中的自然语言内容进行验证。
- 根据权利要求7所述的装置,所述执行模块包括:提示单元,用于提示所述第一对象发出多次声音,以得到声纹特征训练样本;训练单元,用于利用所述声纹特征训练样本训练预设模型;添加单元,用于将训练后的预设模型加入所述模型库。
- 根据权利要求11所述的装置,所述装置还包括:接收模块,用于在将训练后的预设模型加入所述模型库之后,接收输入的为所述第一对象分配权限等级的设置操作,其中,所述权限等级较高的用户的操作优先级较高;判断模块,用于判断输入设置操作的用户的权限等级是否高于为所述第一对象分配的权限等级;分配模块,用于如果判断结果为是,则为所述第一对象分配输入的权限等级。
- 一种非易失性可读存储介质,所述存储介质中存储有计算机可读指令,其中,所述计算机可读指令被设置为运行时执行智能家居设备的声音控制方法,包括:获取采集的声音指令;识别所述声音指令中的声纹特征;将所述声音指令中的声纹特征与模型库中的每个声纹特征模型进行匹配,以确定发出所述声音指令的第一对象是否有操作权限;如果具有操作权限,则识别所述声音指令中的自然语言内容,以控制智能家居设备执行所述自然语言内容指示的目标操作;如果不具备操作权限,则提示目标问题,并获取采 集到的声音回答,并对所述声音回答进行验证,在所述声音回答验证成功的情况下,为所述第一对象配置所述操作权限,并识别所述声音指令中的自然语言内容,以控制所述智能家居设备执行所述自然语言内容指示的目标操作。
- 根据权利要求13所述的存储介质,所述计算机可读指令被设置为运行时执行所述对所述声音回答进行验证的步骤,包括:提取所述声音回答中的声纹特征,判断所述声音回答中的声纹特征是否具有所述操作权限,其中,如果所述声纹特征具有所述操作权限,则确定所述声音回答验证成功。
- 根据权利要求13所述的存储介质,所述计算机可读指令被设置为运行时执行所述对所述声音回答进行验证的步骤,包括:识别所述声音回答中的自然语言内容;基于预设答案对所述声音回答中的自然语言内容进行验证。
- 根据权利要求13所述的存储介质,所述计算机可读指令被设置为运行时执行所述对所述声音回答进行验证的步骤,包括:提取所述声音回答中的声纹特征,判断所述声音回答中的声纹特征是否具有所述操作权限;如果具有所述操作权限,则识别所述声音回答中的自然语言内容,并基于预设答案对所述声音回答中的自然语言内容进行验证。
- 一种电子装置,包括存储器和处理器,所述存储器中存储有计算机可读指令,所述处理器被设置为运行所述计算机可读指令以执行智能家居设备的声音控制方法,包括:获取采集的声音指令;识别所述声音指令中的声纹特征;将所述声音指令中的声纹特征与模型库中的每个声纹特征模型进行匹配,以确定发出所述声音指令的第一对象是否有操作权限;如果具有操作权限,则识别所述声音指令中的自然语言内容,以控制智能家居设备执行所述自然语言内容指示的目标操作;如果不具备操作权限,则提示目标问题,并获取采集到的声音回答,并对所述声音回答进行验证,在所述声音回答验证成功的情况下,为所述第一对象配置所述操作权限,并识别所述声音指令中的自然语言内容,以控制所述智能家居设备执行所述自然语言内容指示的目标操作。
- 根据权利要求17所述的电子装置,所述处理器被设置为运行所述计算机可读指令以执行所述对所述声音回答进行验证的步骤,包括:提取所述声音回答中的声纹特征,判断所述声音回答中的声纹特征是否具有所述操作权限,其中,如果所述声纹特征具有所述操作权限,则确定所述声音回答验证成功。
- 根据权利要求17所述的电子装置,所述处理器被设置为运行所述计算机可读指令以执行所述对所述声音回答进行验证的步骤,包括:识别所述声音回答中的自然语言内容;基于预设答案对所述声音回答中的自然语言内容进行验证。
- 根据权利要求17所述的电子装置,所述处理器被设置为运行所述计算机可读指令以执行所述对所述声音回答进行验证的步骤,包括:提取所述声音回答中的声纹特征,判断所述声音回答中的声纹特征是否具有所述操作权限;如果具有所述操作权限,则识别所述声音回答中的自然语言内容,并基于预设答案对所述声音回答中的自然语言内容进行验证。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910390794.XA CN110134022B (zh) | 2019-05-10 | 2019-05-10 | 智能家居设备的声音控制方法、装置、及电子装置 |
CN201910390794.X | 2019-05-10 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020228280A1 true WO2020228280A1 (zh) | 2020-11-19 |
Family
ID=67573312
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2019/117721 WO2020228280A1 (zh) | 2019-05-10 | 2019-11-12 | 智能家居设备的声音控制方法、装置、及电子装置 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110134022B (zh) |
WO (1) | WO2020228280A1 (zh) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113241073A (zh) * | 2021-06-29 | 2021-08-10 | 深圳市欧瑞博科技股份有限公司 | 智能语音控制方法、装置、电子设备及存储介质 |
CN113393836A (zh) * | 2021-06-08 | 2021-09-14 | 成都傅立叶电子科技有限公司 | 一种机载电台语音识别控制方法及系统 |
CN113419440A (zh) * | 2021-07-16 | 2021-09-21 | 武汉施尔诺新能源科技有限公司 | 一种基于智能家居环境下使用的智能控制系统 |
CN113593582A (zh) * | 2021-06-24 | 2021-11-02 | 青岛海尔科技有限公司 | 智能设备的控制方法和装置、存储介质及电子设备 |
CN113960930A (zh) * | 2021-10-26 | 2022-01-21 | 珠海格力电器股份有限公司 | 智能家居控制面板间的通信方法、装置和设备 |
CN115424622A (zh) * | 2022-11-04 | 2022-12-02 | 之江实验室 | 一种人机语音智能交互方法和装置 |
CN115580868A (zh) * | 2021-06-30 | 2023-01-06 | 青岛海尔科技有限公司 | 网络接入方法和装置、存储介质及电子装置 |
CN115580869A (zh) * | 2021-06-30 | 2023-01-06 | 青岛海尔科技有限公司 | 待入网设备的入网方法和装置、存储介质及电子装置 |
CN117826666A (zh) * | 2022-11-29 | 2024-04-05 | 看见未来科技发展(深圳)有限公司 | 一种智能马桶及其交互方法 |
Families Citing this family (12)
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 |
CN110989390A (zh) * | 2019-12-25 | 2020-04-10 | 海尔优家智能科技(北京)有限公司 | 智能家居的控制方法及装置 |
CN113489628A (zh) * | 2020-05-28 | 2021-10-08 | 海信集团有限公司 | 一种智能终端的控制方法、人机交互设备及智能终端 |
CN111653277A (zh) * | 2020-06-10 | 2020-09-11 | 北京百度网讯科技有限公司 | 车辆语音控制方法、装置、设备、车辆及存储介质 |
CN111953572A (zh) * | 2020-08-07 | 2020-11-17 | 北京猎户星空科技有限公司 | 一种智能服务设备的控制方法及装置 |
CN112152894B (zh) * | 2020-08-31 | 2022-02-18 | 青岛海尔空调器有限总公司 | 基于虚拟现实的家电控制方法及虚拟现实系统 |
CN112466053B (zh) * | 2020-11-24 | 2022-05-17 | 珠海格力电器股份有限公司 | 一种家电设备的控制系统及目标操作的执行方法和装置 |
CN112861745A (zh) * | 2021-02-20 | 2021-05-28 | 珠海格力电器股份有限公司 | 智能家居及其控制方法、模组、计算机可读介质 |
CN115376522B (zh) * | 2021-05-21 | 2024-10-01 | 佛山市顺德区美的电子科技有限公司 | 空调器的声纹控制方法、空调器及可读存储介质 |
CN114090997B (zh) * | 2021-11-24 | 2024-08-27 | 北京邮电大学 | 一种语音指令进程调度方法及装置 |
CN114694648A (zh) * | 2022-02-22 | 2022-07-01 | 青岛海尔科技有限公司 | 设备的控制方法和装置、存储介质及电子装置 |
CN117079652B (zh) * | 2023-10-16 | 2024-01-30 | 明度智云(浙江)科技有限公司 | 一种scada系统语音控制方法、装置和服务器 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080154599A1 (en) * | 2006-12-22 | 2008-06-26 | International Business Machines Corporation | Spoken free-form passwords for light-weight speaker verification using standard speech recognition engines |
CN102737634A (zh) * | 2012-05-29 | 2012-10-17 | 百度在线网络技术(北京)有限公司 | 一种基于语音的认证方法及装置 |
CN108882032A (zh) * | 2018-06-08 | 2018-11-23 | 百度在线网络技术(北京)有限公司 | 用于输出信息的方法和装置 |
CN109412910A (zh) * | 2018-11-20 | 2019-03-01 | 三星电子(中国)研发中心 | 控制智能家居设备的方法和装置 |
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 |
CN110134022A (zh) * | 2019-05-10 | 2019-08-16 | 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 |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130006626A1 (en) * | 2011-06-29 | 2013-01-03 | International Business Machines Corporation | Voice-based telecommunication login |
CN102307126B (zh) * | 2011-08-15 | 2014-06-11 | 武汉安通科技产业发展有限公司 | 多网接入多功能数字家庭智能终端及其控制方法 |
US20150271557A1 (en) * | 2014-03-24 | 2015-09-24 | Joseph Akwo Tabe | Multimedia television system for interactive social media and social network |
CN104618391B (zh) * | 2015-02-25 | 2020-04-24 | 联想(北京)有限公司 | 一种接入控制方法和电子设备 |
WO2016206060A1 (zh) * | 2015-06-25 | 2016-12-29 | 宇龙计算机通信科技(深圳)有限公司 | 控制方法及控制系统、智能家居控制中心设备 |
TW201717655A (zh) * | 2015-11-05 | 2017-05-16 | 宏碁股份有限公司 | 語音控制方法及語音控制系統 |
CN105527852A (zh) * | 2015-12-11 | 2016-04-27 | 四川长虹电器股份有限公司 | 一种控制智能家居系统的方法和控制器 |
CN105511287A (zh) * | 2016-01-27 | 2016-04-20 | 珠海格力电器股份有限公司 | 智能家电控制方法和装置及系统 |
US9849364B2 (en) * | 2016-02-02 | 2017-12-26 | Bao Tran | Smart device |
CN106228988A (zh) * | 2016-07-29 | 2016-12-14 | 珠海市魅族科技有限公司 | 一种基于声纹信息的习惯信息匹配方法及装置 |
CN106782526B (zh) * | 2016-12-12 | 2020-12-29 | 深圳Tcl数字技术有限公司 | 语音控制方法和装置 |
CN107180632A (zh) * | 2017-06-19 | 2017-09-19 | 微鲸科技有限公司 | 语音控制方法、装置及可读存储介质 |
CN107748500A (zh) * | 2017-10-10 | 2018-03-02 | 三星电子(中国)研发中心 | 用于控制智能设备的方法和装置 |
CN108305623A (zh) * | 2018-01-15 | 2018-07-20 | 珠海格力电器股份有限公司 | 电器控制方法及装置 |
CN109256136B (zh) * | 2018-08-31 | 2021-09-17 | 三星电子(中国)研发中心 | 一种语音识别方法和装置 |
CN109360559A (zh) * | 2018-10-23 | 2019-02-19 | 三星电子(中国)研发中心 | 多智能设备同时存在时处理语音指令的方法和系统 |
CN109617772A (zh) * | 2018-12-11 | 2019-04-12 | 鹤壁国立光电科技股份有限公司 | 一种基于语音识别的智能家居系统 |
-
2019
- 2019-05-10 CN CN201910390794.XA patent/CN110134022B/zh active Active
- 2019-11-12 WO PCT/CN2019/117721 patent/WO2020228280A1/zh active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080154599A1 (en) * | 2006-12-22 | 2008-06-26 | International Business Machines Corporation | Spoken free-form passwords for light-weight speaker verification using standard speech recognition engines |
CN102737634A (zh) * | 2012-05-29 | 2012-10-17 | 百度在线网络技术(北京)有限公司 | 一种基于语音的认证方法及装置 |
CN108882032A (zh) * | 2018-06-08 | 2018-11-23 | 百度在线网络技术(北京)有限公司 | 用于输出信息的方法和装置 |
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 |
CN109412910A (zh) * | 2018-11-20 | 2019-03-01 | 三星电子(中国)研发中心 | 控制智能家居设备的方法和装置 |
CN110134022A (zh) * | 2019-05-10 | 2019-08-16 | 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 |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113393836A (zh) * | 2021-06-08 | 2021-09-14 | 成都傅立叶电子科技有限公司 | 一种机载电台语音识别控制方法及系统 |
CN113393836B (zh) * | 2021-06-08 | 2023-09-12 | 成都傅立叶电子科技有限公司 | 一种机载电台语音识别控制方法及系统 |
CN113593582A (zh) * | 2021-06-24 | 2021-11-02 | 青岛海尔科技有限公司 | 智能设备的控制方法和装置、存储介质及电子设备 |
CN113593582B (zh) * | 2021-06-24 | 2024-05-24 | 青岛海尔科技有限公司 | 智能设备的控制方法和装置、存储介质及电子设备 |
CN113241073A (zh) * | 2021-06-29 | 2021-08-10 | 深圳市欧瑞博科技股份有限公司 | 智能语音控制方法、装置、电子设备及存储介质 |
CN113241073B (zh) * | 2021-06-29 | 2023-10-31 | 深圳市欧瑞博科技股份有限公司 | 智能语音控制方法、装置、电子设备及存储介质 |
CN115580868A (zh) * | 2021-06-30 | 2023-01-06 | 青岛海尔科技有限公司 | 网络接入方法和装置、存储介质及电子装置 |
CN115580869A (zh) * | 2021-06-30 | 2023-01-06 | 青岛海尔科技有限公司 | 待入网设备的入网方法和装置、存储介质及电子装置 |
CN113419440A (zh) * | 2021-07-16 | 2021-09-21 | 武汉施尔诺新能源科技有限公司 | 一种基于智能家居环境下使用的智能控制系统 |
CN113960930A (zh) * | 2021-10-26 | 2022-01-21 | 珠海格力电器股份有限公司 | 智能家居控制面板间的通信方法、装置和设备 |
CN115424622A (zh) * | 2022-11-04 | 2022-12-02 | 之江实验室 | 一种人机语音智能交互方法和装置 |
CN117826666A (zh) * | 2022-11-29 | 2024-04-05 | 看见未来科技发展(深圳)有限公司 | 一种智能马桶及其交互方法 |
Also Published As
Publication number | Publication date |
---|---|
CN110134022B (zh) | 2022-03-18 |
CN110134022A (zh) | 2019-08-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020228280A1 (zh) | 智能家居设备的声音控制方法、装置、及电子装置 | |
KR102373905B1 (ko) | 어시스턴트 애플리케이션을 위한 음성 사용자 인터페이스 단축 | |
WO2019141028A1 (zh) | 电器设备的控制方法、装置和系统 | |
US20170346947A1 (en) | Method and apparatus for processing voice information | |
US20150206534A1 (en) | Method of controlling interactive system, method of controlling server, server, and interactive device | |
CN112634897B (zh) | 设备唤醒方法、装置和存储介质及电子装置 | |
CN110851221A (zh) | 一种智慧家居场景配置的方法及装置 | |
CN107729433B (zh) | 一种音频处理方法及设备 | |
US9311461B2 (en) | Security system based on questions that do not publicly identify the speaker | |
CN108932947B (zh) | 语音控制方法及家电设备 | |
CN108922522B (zh) | 设备的控制方法、装置、存储介质及电子装置 | |
CN110648664A (zh) | 家电控制方法、装置和具有存储功能的装置 | |
CN111583921A (zh) | 语音控制方法、装置、计算机设备和存储介质 | |
CN110853631A (zh) | 智能家居的语音识别方法及装置 | |
CN111353771A (zh) | 一种远程控制支付的方法、装置、设备和介质 | |
CN112712444A (zh) | 一种基于物联网的酒店管理方法及相关设备 | |
CN109976703B (zh) | 指引说明方法、计算机可读存储介质和烹饪设备 | |
CN115376522B (zh) | 空调器的声纹控制方法、空调器及可读存储介质 | |
CN116105307A (zh) | 空调控制方法、装置、电子设备和存储介质 | |
CN108303900A (zh) | 播放音频的方法、装置和系统 | |
CN114694648A (zh) | 设备的控制方法和装置、存储介质及电子装置 | |
CN112580007B (zh) | 一种验证方法及装置 | |
CN109635078A (zh) | 基于对话系统的运维方法及服务器 | |
CN115314379B (zh) | 一种设备参数的配置方法、系统、装置以及介质 | |
CN113409793B (zh) | 语音识别方法及智能家居系统、会议设备、计算设备 |
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: 19928772 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: 19928772 Country of ref document: EP Kind code of ref document: A1 |