WO2023185005A1 - Working mode switching method and apparatus - Google Patents

Working mode switching method and apparatus Download PDF

Info

Publication number
WO2023185005A1
WO2023185005A1 PCT/CN2022/132599 CN2022132599W WO2023185005A1 WO 2023185005 A1 WO2023185005 A1 WO 2023185005A1 CN 2022132599 W CN2022132599 W CN 2022132599W WO 2023185005 A1 WO2023185005 A1 WO 2023185005A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
voiceprint
user
working mode
category
Prior art date
Application number
PCT/CN2022/132599
Other languages
French (fr)
Chinese (zh)
Inventor
张凯月
张桂芳
Original Assignee
青岛海尔空调器有限总公司
青岛海尔空调电子有限公司
海尔智家股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 青岛海尔空调器有限总公司, 青岛海尔空调电子有限公司, 海尔智家股份有限公司 filed Critical 青岛海尔空调器有限总公司
Publication of WO2023185005A1 publication Critical patent/WO2023185005A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/50—Control or safety arrangements characterised by user interfaces or communication
    • F24F11/54—Control or safety arrangements characterised by user interfaces or communication using one central controller connected to several sub-controllers
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/50—Control or safety arrangements characterised by user interfaces or communication
    • F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63—Electronic processing
    • F24F11/64—Electronic processing using pre-stored data
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63—Electronic processing
    • F24F11/65—Electronic processing for selecting an operating mode
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/22—Interactive procedures; Man-machine interfaces

Definitions

  • This application relates to the field of artificial intelligence technology, and in particular, to a working mode switching method.
  • Air conditioning has become an indispensable product in people's lives, greatly improving people's quality of life.
  • This application provides a working mode switching method and device to solve the shortcomings of the existing technology that cannot meet the personalized needs of users, and to provide customized operation solutions for specific family members.
  • This application provides a working mode switching method, which includes: receiving target voice information from a target user;
  • performing voiceprint analysis on the target voice information to determine the target user category includes:
  • the target user category is determined based on the user category tag of the target user.
  • a working mode switching method after the comparison of the target voiceprint characteristics and the input voiceprint characteristics of all registered users, it also includes:
  • a boot prompt is generated.
  • performing voiceprint analysis on the target voice information to obtain target voiceprint characteristics includes:
  • Voiceprint extraction is performed on the windowed voice information to obtain target voiceprint features of the target voice information.
  • the method before comparing the target voiceprint characteristics with the input voiceprint characteristics of all registered users, the method further includes:
  • the entry category is input by any user in response to the entry category prompt.
  • switching to the working mode corresponding to the target user according to the target user category includes:
  • the target user category is the second user category
  • switching to the target working mode corresponding to the target user is performed according to the usage habits of the target user.
  • This application also provides a working mode switching device, including:
  • the receiving module is used to receive the target voice information of the target user
  • An analysis module used to perform voiceprint analysis on the target voice information and determine the target user category
  • a switching module configured to switch to a working mode corresponding to the target user according to the target user category.
  • This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the program, it implements any one of the above working mode switching. method.
  • the present application also provides a non-transitory computer-readable storage medium on which a computer program is stored.
  • the computer program When executed by a processor, it implements any one of the above working mode switching methods.
  • the present application also provides a computer program product, which includes a computer program.
  • a computer program product which includes a computer program.
  • the computer program When executed by a processor, it implements any one of the above working mode switching methods.
  • the working mode switching method and device provided by this application obtain the user's category by performing voiceprint recognition on the user's voice information, thereby providing a customized operation plan for specific family members.
  • FIG. 1 is a schematic flow chart of the working mode switching method provided by this application.
  • FIG. 2 is a schematic structural diagram of the working mode switching device provided by this application.
  • Figure 3 is a schematic structural diagram of an electronic device provided by this application.
  • Registration voiceprint technology can achieve:
  • the elderly are more sensitive to temperature and air quality, and those over 80 years old need the help of their children to adjust the temperature and mode to a suitable and healthy temperature.
  • Voiceprint recognition technology helps the elderly automatically enter the elderly mode when turning on the air conditioner with their voice, providing customized care.
  • the execution subject may be an electronic device or a software or functional module or functional entity in the electronic device that can implement the working mode switching method.
  • the electronic device includes but is not limited to smart air conditioning equipment. . It should be noted that the above execution entities do not constitute a limitation on this application.
  • Figure 1 is a schematic flow chart of the working mode switching method provided by this application. As shown in Figure 1, it includes but is not limited to the following steps:
  • step S1 target voice information of the target user is received.
  • the target user who sends the target voice message can be a registered user whose voiceprint has been recorded.
  • the target voice message can be a boot command.
  • step S2 voiceprint analysis is performed on the target voice information to determine the target user category.
  • the target voice information is preprocessed such as pre-emphasis, framing, and windowing, and the preprocessed target voice information is converted into a voiceprint feature map.
  • the voiceprint feature map may be a Mel energy spectrum map. Mel energy spectrogram can represent the frequency distribution of sounds that people can hear, which is the deep feature of people identifying things through sound. Using this distribution characteristic in the Mel frequency domain is more suitable for building a speaker recognition system.
  • the speech signal passes through Through such conversion, the speech signal becomes an image carrying voiceprint information. For a single signal, its Mel energy spectrum is black and white and can be understood as a single-channel feature map.
  • the corresponding user category label can be obtained as the target user category.
  • User category tags can include: child tags, adult tags, and elderly tags; each adult tag is unique.
  • step S3 switch to the working mode corresponding to the target user according to the target user category.
  • the target user category When the target user category is children, switch the working mode of the air conditioner to children's mode; when the target user category is the elderly, switch the working mode of the air conditioner to elderly mode; when the target user category is adults, In this case, according to the external environment and the individual usage habits of the target user, the working mode of the air conditioner is switched to the corresponding working mode of the target user at the current time and environment.
  • the working mode switching method provided by this application obtains the user's category by performing voiceprint recognition on the user's voice information, thereby providing a customized operation plan for specific family members.
  • the method further includes:
  • the entry category is input by any user in response to the entry category prompt.
  • the smart air conditioner After receiving the instruction to enter the voiceprint, the smart air conditioner switches to the voiceprint entry mode and issues a voice prompt to remind the user to enter the voiceprint test voice.
  • the user repeats the voiceprint test voice more than twice.
  • the feature information of the filter group Frter bank, Fbank
  • the voiceprint recognition model converts the Fbank feature information into the segment.
  • the voiceprint characteristics of the voice are averaged as the characteristics of the input voiceprint sent by the user; the smart air conditioner generates the input age prompt, and after receiving the input age sent by the user, the input voiceprint and Enter the age as the user's registration information, and the voice broadcast module will prompt that the entry is successful.
  • the voiceprint recognition model is a deep neural network model, which is trained from multiple Chinese corpus and has strong noise resistance and robustness.
  • the method of recording voiceprints is combined with age-based group recognition and individualized voiceprint recognition, and provides voiceprint recognition and customized care for children and the elderly.
  • the most suitable air solution is provided.
  • performing voiceprint analysis on the target voice information to determine the target user category includes:
  • the target user category is determined based on the user category tag of the target user.
  • performing voiceprint analysis on the target voice information to obtain target voiceprint features includes:
  • Voiceprint extraction is performed on the windowed voice information to obtain target voiceprint features of the target voice information.
  • the high-frequency end is attenuated at about 6 decibels/octave (dB/oct) above 800 Hz.
  • Digital filters can be used to pre-emphasize the target speech information.
  • the voiceprint signal is divided into several frames at intervals of 10 to 20 milliseconds (ms), and one frame is a basic unit to achieve the framing of pre-emphasized voice information.
  • the Hamming window function is used to window the framed speech information.
  • the working mode setting method provided by this application, through pre-emphasis, framing and windowing of the target speech information, the aliasing and high-order harmonics caused by the human vocal organs themselves and the equipment for collecting speech signals can be eliminated. Distortion, high frequency and other factors affect the quality of speech signals. Try to ensure that the signal obtained by subsequent speech processing is more uniform and smooth, provide high-quality parameters for signal parameter extraction, and improve the quality of speech processing.
  • Perform voiceprint analysis on the target voice information extract the Fbank feature information of the target voice information, input it into the voiceprint recognition model, and output it as the target voiceprint feature of the target voice information.
  • the user who sends the voice information can determine the user category tag based on the user's registration information, and determine the target user category based on the user category tag; if the highest similarity is lower than the set voiceprint threshold, determine the user who sent the target voice information.
  • the target is not a registered user.
  • user categories are determined through voiceprint recognition, providing a basis for providing customized operating solutions for each group.
  • switching to the working mode corresponding to the target user according to the target user category includes:
  • the target user category is the second user category
  • switching to the target working mode corresponding to the target user is performed according to the usage habits of the target user.
  • the first user category may include: the elderly and children.
  • the first working mode is the elderly mode; when the first user category is children, the first working mode is the children mode. .
  • the second user category may be adults, and the usage habits include learning results of voiceprint recognition and network computer behavior learning results.
  • the air conditioner When the target user speaks the "air conditioner on” command through any method such as voice air conditioner, APP voice assistant or smart speaker, the air conditioner performs voiceprint analysis on the command to determine whether the target user is a registered user.
  • the user category label of the target user is determined as the target user category.
  • the upper and lower guide plates are in the upward blowing position in summer, and the upper and lower guide plates are in the downward blowing position in winter.
  • the smart air conditioner switches the working mode to the elderly mode, and automatically enters the elderly mode every time it recognizes the command to turn on the air conditioner from the voiceprint of the target user.
  • the specific parameters of the elderly mode are related to the season: in the summer from June to September, turn on the PMV, set the temperature to 27°C cooling mode, set the wind speed to low wind, set the upper and lower guide plates to the maximum upward blowing position 1, and the air cleanliness is Turn on the health mode; in the winter from December to February, turn on the PMV, set the temperature to 26°C heating mode; set the wind speed to low wind, and set the upper and lower guide plates to the maximum downward blowing position 5; the air cleanliness is set to turn on the health mode ; In other months, turn on the PMV, set the temperature to 26°C, cool when the indoor temperature is higher than 26°C, and heat when the indoor temperature is not higher than 26°C; the wind speed is set to low wind, and the air cleanliness is Open health.
  • the smart air conditioner After turning on the elderly mode, the smart air conditioner broadcasts: "Hello elders, the elder care mode has been turned on, and you can blow the air conditioner healthily and comfortably.”
  • the smart air conditioner switches the working mode to the child mode, and automatically enters the child mode each time the target user's voiceprint command to turn on the air conditioner is recognized.
  • the specific parameters of the children's mode are related to the season: in the summer from June to September, turn on the PMV, set the temperature to 26°C cooling mode, set the wind speed to low wind, set the upper and lower guide plates to the maximum upward blowing position 1, and the air cleanliness is Turn on the health mode; in the winter from December to February, turn on the PMV, set the temperature to the heating mode of 23°C, set the wind speed to low wind, set the upper and lower guide plates to the maximum downward blowing position 5, and set the air cleanliness to turn on the health mode; In other months, the PMV is turned on, the temperature is set to 26°C, cooling is performed when the indoor temperature is higher than 26°C, heating is performed when the indoor temperature is not higher than 26°C, the wind speed is set to low wind, and the air cleanliness is set to Turn on health mode.
  • the air conditioner broadcasts: "Hello kids, the child mode is on, you can suddenly blow on the air conditioner.”
  • the target user category is the adult label
  • the learning results of the voiceprint recognition are retrieved in the background, and the learning results are sent to set the working mode; If there is no learning result of voiceprint recognition, the learning result of the network server behavior is retrieved, and the learning result is delivered to set the working mode.
  • smart learning based on voiceprint recognition can obtain the learning results of each voiceprint recognition.
  • Each adult's entered voiceprint features have their own unique adult label.
  • the cloud learns the user startup data of each adult male and adult female.
  • the startup data is consistent with the user category label of the entered voiceprint.
  • User startup data includes the user's settings for air conditioner temperature, wind speed, mode and other parameters each time the machine is turned on.
  • a certain smart air conditioner there are four user category labels including the elderly, adult male 1, adult female 1, and children. If the identified target user category is the elderly or children, no learning will be performed.
  • the identified target user category is "Adult Male 1”
  • the startup data of "Adult Male 1” this time and in history will be learned, and recorded as the learning result of the voiceprint recognition of "Adult Male 1”.
  • the learning results are used as the working mode settings corresponding to "Adult Male 1" next time.
  • the identified target user category is "Adult Women 1”
  • the learning results are used as the working mode settings corresponding to "Adult Female 1" next time.
  • Smart learning based on network device behavior uses a historical database to learn the sample external parameters of the smart air conditioner and the user boot data labels corresponding to the sample external parameters as training samples to train the network device built based on the neural network model, taking into account the user
  • the use of the air conditioner will change with the temperature, sleep and other factors of the day. It adopts three-stage learning to learn the user's power-on setting operations at each time period. External parameters include temperature, time period and other parameters.
  • the time is set to a 24-hour clock, the night period is from 17:00 to 21:00, the day period is from 7:00 to 17:00, and the sleeping period is from 21:00 to 7:00.
  • the criteria for accurate learning results of network device behavior include: the error between the predicted set temperature and the actual set temperature in the startup data label does not exceed 1 degree, the predicted mode is the same as the actual mode in the startup data label, the predicted wind speed is the same as the startup data label The actual wind speed in is the same.
  • the time since the smart air conditioner was last turned on If there are neither voiceprint recognition learning results nor network device behavior learning results, obtain the time since the smart air conditioner was last turned on. If the time is greater than 30 days, issue the PMV mode to be turned on and the temperature is 26 degrees. The wind speed is automatic wind, and the announcement is: "Hello Sir/Ms., Xiaoyou has also helped you adjust the mode you like. The current temperature is 26°C, automatic wind speed.”
  • the announcement content can also include the operating mode of the smart air conditioner; if this If the time since the last power-on is no more than 30 days, only a power-on command will be issued and an announcement will be made: "Hello sir/ma'am, the air conditioner has been turned on”.
  • the working mode setting method by determining the user category and using the registration-based voiceprint recognition method, different family members can learn their usage habits, achieve intelligent recognition of people and user preference learning, and learn the preferences of each user. Customize care for each group and provide the most suitable air solution.
  • the method further includes:
  • a boot prompt is generated.
  • the preset duration threshold can be set to 30 days; the default working mode is to turn on PMV, the temperature is 26 degrees, and the wind speed is automatic wind.
  • the learning results of the network device behavior are retrieved and the learning results are delivered; if there are no learning results of the network device behavior, the length of time since the smart air conditioner was last turned on is obtained.
  • the broadcast content can also include the operating mode of the smart air conditioner; if it is not more than 30 days since the last time it was turned on, only a start command will be issued and the announcement will be: "Hello Sir/Ms., the air conditioner has been turned on. Power on”.
  • big data is used to conduct artificial intelligence (AI) deep learning of user habits, thereby making the air conditioner more in line with the usage habits of various user groups.
  • AI artificial intelligence
  • the working mode switching device provided by the present application will be described below.
  • the working mode switching device described below and the working mode switching method described above may be mutually referenced.
  • FIG 2 is a schematic structural diagram of the working mode switching device provided by this application. As shown in Figure 2, it includes:
  • the receiving module 201 is used to receive the target voice information of the target user
  • the analysis module 202 is used to perform voiceprint analysis on the target voice information and determine the target user category;
  • the switching module 203 is used to switch to the working mode corresponding to the target user according to the target user category.
  • the receiving module 201 receives the target voice information of the target user.
  • the target user who sends the target voice message can be a registered user whose voiceprint has been recorded.
  • the target voice message can be a boot command.
  • the analysis module 202 performs voiceprint analysis on the target voice information to determine the target user category.
  • the target voice information is preprocessed such as pre-emphasis, framing, and windowing, and the preprocessed target voice information is converted into a voiceprint feature map.
  • the voiceprint feature map may be a Mel energy spectrum map. Mel energy spectrogram can represent the frequency distribution of sounds that people can hear, which is the deep feature of people identifying things through sound. Using this distribution characteristic in the Mel frequency domain is more suitable for building a speaker recognition system.
  • the speech signal passes through Through such conversion, the speech signal becomes an image carrying voiceprint information. For a single signal, its Mel energy spectrum is black and white and can be understood as a single-channel feature map.
  • the corresponding user category label can be obtained as the target user category.
  • User category tags can include: child tags, adult tags, and elderly tags; each adult tag is unique.
  • the switching module 203 switches to the working mode corresponding to the target user according to the target user category.
  • the target user category When the target user category is children, switch the working mode of the air conditioner to children's mode; when the target user category is the elderly, switch the working mode of the air conditioner to elderly mode; when the target user category is adults, In this case, according to the external environment and the individual usage habits of the target user, the working mode of the air conditioner is switched to the corresponding working mode of the target user at the current time and environment.
  • the working mode switching device obtained by this application obtains the user's category by performing voiceprint recognition on the user's voice information, thereby providing a customized operation plan for specific family members.
  • Figure 3 is a schematic structural diagram of an electronic device provided by this application.
  • the electronic device may include: a processor (processor) 310, a communications interface (Communications Interface) 320, a memory (memory) 330 and a communication bus 340.
  • the processor 310, the communication interface 320, and the memory 330 complete communication with each other through the communication bus 340.
  • the processor 310 can call the logical instructions in the memory 330 to execute the working mode switching method.
  • the method includes: receiving the target voice information of the target user; performing voiceprint analysis on the target voice information to determine the target user category; according to the Target user category, switch to the working mode corresponding to the target user.
  • the above-mentioned logical instructions in the memory 330 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.
  • the technical solution of the present application is essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code. .
  • the present application also provides a computer program product.
  • the computer program product includes a computer program.
  • the computer program can be stored on a non-transitory computer-readable storage medium.
  • the computer can Execute the working mode switching method provided by each of the above methods.
  • the method includes: receiving target voice information of the target user; performing voiceprint analysis on the target voice information to determine the target user category; switching to the target user category according to the target user category. Describe the working mode corresponding to the target user.
  • the present application also provides a non-transitory computer-readable storage medium on which a computer program is stored.
  • the computer program is implemented when executed by the processor to perform the working mode switching method provided by the above methods.
  • the method includes : Receive the target voice information of the target user; conduct voiceprint analysis on the target voice information to determine the target user category; switch to the working mode corresponding to the target user according to the target user category.
  • the device embodiments described above are only illustrative.
  • the units described as separate components may or may not be physically separated.
  • the components shown as units may or may not be physical units, that is, they may be located in One location, or it can be distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of this embodiment. Persons of ordinary skill in the art can understand and implement the method without any creative effort.
  • each embodiment can be implemented by software plus a necessary general hardware platform, and of course, it can also be implemented by hardware.
  • the computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., including a number of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments.

Abstract

A working mode switching method and apparatus, an electronic device, a non-transitory computer-readable storage medium, and a computer program product. The method comprises: receiving target voice information of a target user (S1); performing voiceprint analysis on the target voice information to determine a target user category (S2); and according to the target user category, switching to a working mode corresponding to the target user (S3). According to the method, voiceprint recognition is carried out on voice information of a user to obtain the category of the user, so that a customized operation scheme is provided for specific family members.

Description

一种工作模式切换方法及装置A working mode switching method and device
相关申请的交叉引用Cross-references to related applications
本申请要求于2022年3月29日提交的申请号为202210324179.0，名称为“一种工作模式切换方法及装置”的中国专利申请的优先权，其通过引用方式全部并入本文。This application claims priority to the Chinese patent application with application number 202210324179.0 and titled "A working mode switching method and device" submitted on March 29, 2022, which is fully incorporated herein by reference.
技术领域Technical field
本申请涉及人工智能技术领域，尤其涉及一种工作模式切换方法。This application relates to the field of artificial intelligence technology, and in particular, to a working mode switching method.
背景技术Background technique
空调已经在人们的生活中成为不可或缺的必备产品，大大提高了人们的生活质量。Air conditioning has become an indispensable product in people's lives, greatly improving people's quality of life.
然而，每个用户对空调温度，风速等的习惯、需求、偏好都是不一样的。However, each user has different habits, needs, and preferences for air conditioning temperature, wind speed, etc.
现有的空调无法满足用户的个性化需求。Existing air conditioners cannot meet the individual needs of users.
发明内容Contents of the invention
本申请提供一种工作模式切换方法及装置，用以解决现有技术中无法满足用户的个性化需求的缺陷，实现针对特定家庭成员给予定制化的运行方案。This application provides a working mode switching method and device to solve the shortcomings of the existing technology that cannot meet the personalized needs of users, and to provide customized operation solutions for specific family members.
本申请提供一种工作模式切换方法，包括：接收目标用户的目标语音信息；This application provides a working mode switching method, which includes: receiving target voice information from a target user;
对所述目标语音信息进行声纹分析，确定目标用户类别；Perform voiceprint analysis on the target voice information to determine the target user category;
根据所述目标用户类别，切换至所述目标用户对应的工作模式。According to the target user category, switch to the working mode corresponding to the target user.
根据本申请提供的一种工作模式切换方法，所述对所述目标语音信息进行声纹分析，确定目标用户类别，包括：According to a working mode switching method provided by this application, performing voiceprint analysis on the target voice information to determine the target user category includes:
对所述目标语音信息进行声纹分析，获取目标声纹特征；Perform voiceprint analysis on the target voice information to obtain target voiceprint characteristics;
比对所述目标声纹特征与所有注册用户的录入声纹特征；Compare the target voiceprint features with the entered voiceprint features of all registered users;
在确定所述目标用户属于注册用户的情况下，根据所述目标用户的用户类别标签，确定所述目标用户类别。When it is determined that the target user belongs to a registered user, the target user category is determined based on the user category tag of the target user.
根据本申请提供的一种工作模式切换方法，在所述比对所述目标声纹特征与所有注册用户的录入声纹特征之后，还包括：According to a working mode switching method provided by this application, after the comparison of the target voiceprint characteristics and the input voiceprint characteristics of all registered users, it also includes:
在确定所述目标用户属于非注册用户的情况下，获取开机间隔时长；When it is determined that the target user is a non-registered user, obtain the boot interval time;
在所述开机间隔时长大于预设时长阈值的情况下，切换默认工作模式；When the boot interval is longer than the preset duration threshold, switch to the default working mode;
在所述开机间隔时长不大于预设时长阈值的情况下，生成开机提示。When the boot interval is not greater than the preset duration threshold, a boot prompt is generated.
根据本申请提供的一种工作模式切换方法，所述对所述目标语音信息进行声纹分析，获取目标声纹特征，包括：According to a working mode switching method provided by this application, performing voiceprint analysis on the target voice information to obtain target voiceprint characteristics includes:
对所述目标语音信息进行预加重，确定预加重语音信息；Perform pre-emphasis on the target voice information to determine the pre-emphasis voice information;
对所述预加重语音信息进行分帧，确定分帧语音信息；Divide the pre-emphasized voice information into frames to determine the framed voice information;
对所述分帧语音信息进行加窗，获取加窗语音信息；Window the framed speech information to obtain the windowed speech information;
对所述加窗语音信息进行声纹提取，获取所述目标语音信息的目标声纹特征。Voiceprint extraction is performed on the windowed voice information to obtain target voiceprint features of the target voice information.
根据本申请提供的一种工作模式切换方法，在所述比对所述目标声纹特征与所有注册用户的录入声纹特征之前，还包括：According to a working mode switching method provided by this application, before comparing the target voiceprint characteristics with the input voiceprint characteristics of all registered users, the method further includes:
接收录入声纹指令；Receive voiceprint input instructions;
根据所述录入声纹指令，生成录入声纹提示；According to the voiceprint input instruction, generate a voiceprint input prompt;
在接收到任一用户发送的声纹测试语音的情况下，提取所述任一用户的录入声纹特征；Upon receiving the voiceprint test voice sent by any user, extract the recorded voiceprint features of any user;
根据所述任一用户的录入声纹特征，生成录入类别提示；Generate an entry category prompt based on the entry voiceprint characteristics of any user;
接收所述任一用户录入类别，以确定所述任一用户的用户类别标签；Receive the category entered by any user to determine the user category label of any user;
所述录入类别是所述任一用户响应所述录入类别提示后输入的。The entry category is input by any user in response to the entry category prompt.
根据本申请提供的一种工作模式切换方法，所述根据所述目标用户类别，切换至所述目标用户对应的工作模式，包括：According to a working mode switching method provided by this application, switching to the working mode corresponding to the target user according to the target user category includes:
在确定所述目标用户类别为第一用户类别的情况下，切换为第一工作模式；When it is determined that the target user category is the first user category, switch to the first working mode;
在确定所述目标用户类别为第二用户类别的情况下，根据所述目标用户的使用习惯，切换为所述目标用户对应的目标工作模式。When it is determined that the target user category is the second user category, switching to the target working mode corresponding to the target user is performed according to the usage habits of the target user.
本申请还提供一种工作模式切换装置，包括：This application also provides a working mode switching device, including:
接收模块，用于接收目标用户的目标语音信息；The receiving module is used to receive the target voice information of the target user;
分析模块，用于对所述目标语音信息进行声纹分析，确定目标用户类 别；An analysis module, used to perform voiceprint analysis on the target voice information and determine the target user category;
切换模块，用于根据所述目标用户类别，切换至所述目标用户对应的工作模式。A switching module, configured to switch to a working mode corresponding to the target user according to the target user category.
本申请还提供一种电子设备，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程序时实现如上述任一种所述工作模式切换方法。This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements any one of the above working mode switching. method.
本申请还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如上述任一种所述工作模式切换方法。The present application also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements any one of the above working mode switching methods.
本申请还提供一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现如上述任一种所述工作模式切换方法。The present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements any one of the above working mode switching methods.
本申请提供的工作模式切换方法及装置，通过对用户的语音信息进行声纹识别，得到用户的类别，从而针对特定家庭成员给予定制化的运行方案。The working mode switching method and device provided by this application obtain the user's category by performing voiceprint recognition on the user's voice information, thereby providing a customized operation plan for specific family members.
附图说明Description of drawings
为了更清楚地说明本申请或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to explain the technical solutions in this application or the prior art more clearly, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are of the present invention. For some embodiments of the application, those of ordinary skill in the art can also obtain other drawings based on these drawings without exerting creative efforts.
图1是本申请提供的工作模式切换方法的流程示意图；Figure 1 is a schematic flow chart of the working mode switching method provided by this application;
图2是本申请提供的工作模式切换装置的结构示意图；Figure 2 is a schematic structural diagram of the working mode switching device provided by this application;
图3是本申请提供的电子设备的结构示意图。Figure 3 is a schematic structural diagram of an electronic device provided by this application.
具体实施方式Detailed ways
为使本申请的目的、技术方案和优点更加清楚，下面将结合本申请中的附图，对本申请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申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application. , not all examples. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.
当前空调的控制是通过遥控器、手机应用程序(Application，APP)语 音实现，无法主动的一步到位实现用户的最佳使用习惯。注册制声纹技术可实现：Currently, the control of air conditioners is achieved through remote control and mobile phone application (Application, APP) voice, and it is impossible to proactively realize the user's best usage habits in one step. Registration voiceprint technology can achieve:
由于大多儿童不知道如何调空调，可能会因儿童乱调空调而导致感冒等身体不适的情况，当家里的儿童使用语音开启空调时，空调会自动进入儿童模式；Since most children do not know how to adjust the air conditioner, they may suffer from colds and other physical discomforts due to random adjustments of the air conditioner. When children at home use voice to turn on the air conditioner, the air conditioner will automatically enter children's mode;
青年及成人有着不同的调空调偏好，当不同的家庭成员打开空调时，则自动进入不同用户喜好的模式；Young people and adults have different preferences for adjusting air conditioners. When different family members turn on the air conditioners, they will automatically enter the modes preferred by different users;
老人对温度和空气质量较为敏感，且80岁以上老人需要在儿女帮助调到合适的健康的温度和模式，声纹识别技术帮助老人语音开启空调时自动进入老人模式，给与定制化呵护。The elderly are more sensitive to temperature and air quality, and those over 80 years old need the help of their children to adjust the temperature and mode to a suitable and healthy temperature. Voiceprint recognition technology helps the elderly automatically enter the elderly mode when turning on the air conditioner with their voice, providing customized care.
下面结合图1至图3描述本申请的实施例所提供的工作模式切换方法及装置。The working mode switching method and device provided by embodiments of the present application will be described below with reference to FIGS. 1 to 3 .
本申请实施例提供的工作模式切换方法，执行主体可以为电子设备或者电子设备中能够实现该工作模式切换方法的软件或功能模块或功能实体，本申请实施例中电子包括但不限于智能空调设备。需要说明的是，上述执行主体并不构成对本申请的限制。For the working mode switching method provided by the embodiment of the present application, the execution subject may be an electronic device or a software or functional module or functional entity in the electronic device that can implement the working mode switching method. In the embodiment of the present application, the electronic device includes but is not limited to smart air conditioning equipment. . It should be noted that the above execution entities do not constitute a limitation on this application.
图1是本申请提供的工作模式切换方法的流程示意图，如图1所示，包括但不限于以下步骤：Figure 1 is a schematic flow chart of the working mode switching method provided by this application. As shown in Figure 1, it includes but is not limited to the following steps:
首先，在步骤S1中，接收目标用户的目标语音信息。First, in step S1, target voice information of the target user is received.
发送目标语音信息的目标用户可以是已录入声纹的注册用户。The target user who sends the target voice message can be a registered user whose voiceprint has been recorded.
目标语音信息可以为开机指令。The target voice message can be a boot command.
用户可以使用语音空调、APP语音助手或智能音箱三种方式对空调进行语音操控，使用语音说出“空调开机”指令后，空调为用户智慧开机。Users can use voice air conditioners, APP voice assistants or smart speakers to control the air conditioner by voice. After using the voice to say the "air conditioner start" command, the air conditioner will be turned on for the user intelligently.
进一步地，在步骤S2中，对所述目标语音信息进行声纹分析，确定目标用户类别。Further, in step S2, voiceprint analysis is performed on the target voice information to determine the target user category.
在获取到目标语音信息之后，将该目标语音信息进行预加重、分帧和加窗等预处理，将预处理后的目标语音信息转换为声纹特征图。其中声纹特征图可以为梅尔能量谱图。梅尔能量谱图能表征人能听到的声音的频率分布，是人通过声音辨别事物的深层特征，利用这种在梅尔频域的分布特性，更适合构建说话人识别系统，语音信号经过这样的转换，语音信号就 变为了携带声纹信息的图像，对于单个信号，其梅尔能量谱图是黑白的，可以理解为单通道的特征图。After the target voice information is obtained, the target voice information is preprocessed such as pre-emphasis, framing, and windowing, and the preprocessed target voice information is converted into a voiceprint feature map. The voiceprint feature map may be a Mel energy spectrum map. Mel energy spectrogram can represent the frequency distribution of sounds that people can hear, which is the deep feature of people identifying things through sound. Using this distribution characteristic in the Mel frequency domain is more suitable for building a speaker recognition system. The speech signal passes through Through such conversion, the speech signal becomes an image carrying voiceprint information. For a single signal, its Mel energy spectrum is black and white and can be understood as a single-channel feature map.
将声纹特征图与空调中已注册用户的录入声纹特征进行比对，在已注册用户中确定目标用户之后，可以得到相应的用户类别标签，作为目标用户类别。Compare the voiceprint feature map with the voiceprint features entered by registered users in the air conditioner. After determining the target user among the registered users, the corresponding user category label can be obtained as the target user category.
用户类别标签可以包括：儿童标签、成人标签和老人标签；每个成人标签均是唯一的。User category tags can include: child tags, adult tags, and elderly tags; each adult tag is unique.
进一步地，在步骤S3中，根据所述目标用户类别，切换至所述目标用户对应的工作模式。Further, in step S3, switch to the working mode corresponding to the target user according to the target user category.
在目标用户类别为儿童群体的情况下，将空调的工作模式切换为儿童模式；在目标用户类别为老人群体的情况下，将空调的工作模式切换为老人模式；在目标用户类别为成人群体的情况下，根据外界环境，以及目标用户的个体使用习惯，将空调的工作模式切换为目标用户在当前时间和环境下对应的工作模式。When the target user category is children, switch the working mode of the air conditioner to children's mode; when the target user category is the elderly, switch the working mode of the air conditioner to elderly mode; when the target user category is adults, In this case, according to the external environment and the individual usage habits of the target user, the working mode of the air conditioner is switched to the corresponding working mode of the target user at the current time and environment.
本申请提供的工作模式切换方法，通过对用户的语音信息进行声纹识别，得到用户的类别，从而针对特定家庭成员给予定制化的运行方案。The working mode switching method provided by this application obtains the user's category by performing voiceprint recognition on the user's voice information, thereby providing a customized operation plan for specific family members.
可选地，在所述比对所述目标声纹特征与所有注册用户的录入声纹特征之前，还包括：Optionally, before comparing the target voiceprint features with the entered voiceprint features of all registered users, the method further includes:
接收录入声纹指令；Receive voiceprint input instructions;
根据所述录入声纹指令，生成录入声纹提示；According to the voiceprint input instruction, generate a voiceprint input prompt;
在接收到任一用户发送的声纹测试语音的情况下，提取所述任一用户的录入声纹特征；Upon receiving the voiceprint test voice sent by any user, extract the recorded voiceprint features of any user;
根据所述任一用户的录入声纹特征，生成录入类别提示；Generate an entry category prompt based on the entry voiceprint characteristics of any user;
接收所述任一用户录入类别，以确定所述任一用户的用户类别标签；Receive the category entered by any user to determine the user category label of any user;
所述录入类别是所述任一用户响应所述录入类别提示后输入的。The entry category is input by any user in response to the entry category prompt.
智能空调在接收到录入声纹的指令之后，切换至声纹录入模式，并发出语音提示提醒用户录入声纹测试语音。After receiving the instruction to enter the voiceprint, the smart air conditioner switches to the voiceprint entry mode and issues a voice prompt to remind the user to enter the voiceprint test voice.
用户重复发音两次以上的声纹测试语音，每次发音后，提取该段纹测试语音的滤波器组的特征(Filter bank，Fbank)特征信息，声纹识别模型将Fbank特征信息转化为该段语音的声纹特征；最后将各次发音得到的声 纹特征求平均值作为用户发出的录入声纹特征；智能空调生成录入年龄提示，在接收到用户发送的录入年龄之后，将录入声纹和录入年龄作为用户的注册信息，并语音播报模块提示该次录入成功。The user repeats the voiceprint test voice more than twice. After each pronunciation, the feature information of the filter group (Filter bank, Fbank) of the segment of the voiceprint test voice is extracted. The voiceprint recognition model converts the Fbank feature information into the segment. The voiceprint characteristics of the voice; finally, the voiceprint characteristics obtained from each pronunciation are averaged as the characteristics of the input voiceprint sent by the user; the smart air conditioner generates the input age prompt, and after receiving the input age sent by the user, the input voiceprint and Enter the age as the user's registration information, and the voice broadcast module will prompt that the entry is successful.
声纹识别模型是一个深度神经网络模型，由多个中文语料训练而得，具有很强的抗噪性和鲁棒性。The voiceprint recognition model is a deep neural network model, which is trained from multiple Chinese corpus and has strong noise resistance and robustness.
根据本申请提供的工作模式切换方法，以录入声纹的方式，结合基于年龄的群体识别，以及个体化声纹识别于一体，并针对儿童，老人年龄段的声纹识别及定制化呵护，提供最合适的空气方案。According to the working mode switching method provided by this application, the method of recording voiceprints is combined with age-based group recognition and individualized voiceprint recognition, and provides voiceprint recognition and customized care for children and the elderly. The most suitable air solution.
可选地，所述对所述目标语音信息进行声纹分析，确定目标用户类别，包括：Optionally, performing voiceprint analysis on the target voice information to determine the target user category includes:
对所述目标语音信息进行声纹分析，获取目标声纹特征；Perform voiceprint analysis on the target voice information to obtain target voiceprint characteristics;
比对所述目标声纹特征与所有注册用户的录入声纹特征；Compare the target voiceprint features with the entered voiceprint features of all registered users;
在确定所述目标用户属于注册用户的情况下，根据所述目标用户的用户类别标签，确定所述目标用户类别。When it is determined that the target user belongs to a registered user, the target user category is determined based on the user category tag of the target user.
可选地，所述对所述目标语音信息进行声纹分析，获取目标声纹特征，包括：Optionally, performing voiceprint analysis on the target voice information to obtain target voiceprint features includes:
对所述目标语音信息进行预加重，确定预加重语音信息；Perform pre-emphasis on the target voice information to determine the pre-emphasis voice information;
对所述预加重语音信息进行分帧，确定分帧语音信息；Divide the pre-emphasized voice information into frames to determine the framed voice information;
对所述分帧语音信息进行加窗，获取加窗语音信息；Window the framed speech information to obtain the windowed speech information;
对所述加窗语音信息进行声纹提取，获取所述目标语音信息的目标声纹特征。Voiceprint extraction is performed on the windowed voice information to obtain target voiceprint features of the target voice information.
由于语音信号的平均功率谱受声门激励和口鼻辐射的影响，高频端大约在800赫兹(Hz)以上按6分贝/倍频程(dB/oct)衰减，频率越高相应的成分越小，为此要在对语音信号进行分析之前对其高频部分加以提升。可以利用数字滤波器实现对目标语音信息的预加重。Since the average power spectrum of the speech signal is affected by glottal excitation and oral and nasal radiation, the high-frequency end is attenuated at about 6 decibels/octave (dB/oct) above 800 Hz. The higher the frequency, the higher the corresponding component. Small, for this reason, the high-frequency part of the speech signal must be improved before analyzing it. Digital filters can be used to pre-emphasize the target speech information.
以10至20毫秒(ms)为间隔将声纹信号分为若干帧，一帧为一个基本单位，实现对预加重语音信息的分帧。The voiceprint signal is divided into several frames at intervals of 10 to 20 milliseconds (ms), and one frame is a basic unit to achieve the framing of pre-emphasized voice information.
采用汉明窗函数对分帧语音信息来进行窗化。The Hamming window function is used to window the framed speech information.
根据本申请提供的工作模式设置方法，经过对目标语音信息的预加重、分帧和加窗，能够消除因为人类发声器官本身和由于采集语音信号的设备 所带来的混叠、高次谐波失真、高频等等因素，对语音信号质量的影响。尽可能保证后续语音处理得到的信号更均匀、平滑，为信号参数提取提供优质的参数，提高语音处理质量。According to the working mode setting method provided by this application, through pre-emphasis, framing and windowing of the target speech information, the aliasing and high-order harmonics caused by the human vocal organs themselves and the equipment for collecting speech signals can be eliminated. Distortion, high frequency and other factors affect the quality of speech signals. Try to ensure that the signal obtained by subsequent speech processing is more uniform and smooth, provide high-quality parameters for signal parameter extraction, and improve the quality of speech processing.
对目标语音信息进行声纹分析，提取目标语音信息的Fbank特征信息，并输入至声纹识别模型，输出为目标语音信息的目标声纹特征。将目标声纹特征与所有注册用户已储存的录入声纹特征进行相似度计算；若得到的最高相似度高于设置的声纹阈值，则判定该最高相似度对应的录入声纹特征用户为目标语音信息的发出用户，可以根据该用户的注册信息确定用户类别标签，并根据用户类别标签，确定目标用户类别；若最高相似度低于设置的声纹阈值，则确定发送所述目标语音信息的对象不为注册用户。Perform voiceprint analysis on the target voice information, extract the Fbank feature information of the target voice information, input it into the voiceprint recognition model, and output it as the target voiceprint feature of the target voice information. Calculate the similarity between the target voiceprint feature and the recorded voiceprint features that have been stored by all registered users; if the highest similarity obtained is higher than the set voiceprint threshold, the user with the recorded voiceprint feature corresponding to the highest similarity is determined to be the target The user who sends the voice information can determine the user category tag based on the user's registration information, and determine the target user category based on the user category tag; if the highest similarity is lower than the set voiceprint threshold, determine the user who sent the target voice information. The target is not a registered user.
根据本申请提供的工作模式设置方法，通过声纹识别，确定用户类别，为每个群体提供定制化的运行方案提供基础。According to the working mode setting method provided in this application, user categories are determined through voiceprint recognition, providing a basis for providing customized operating solutions for each group.
可选地，所述根据所述目标用户类别，切换至所述目标用户对应的工作模式，包括：Optionally, switching to the working mode corresponding to the target user according to the target user category includes:
在确定所述目标用户类别为第一用户类别的情况下，切换为第一工作模式；When it is determined that the target user category is the first user category, switch to the first working mode;
在确定所述目标用户类别为第二用户类别的情况下，根据所述目标用户的使用习惯，切换为所述目标用户对应的目标工作模式。When it is determined that the target user category is the second user category, switching to the target working mode corresponding to the target user is performed according to the usage habits of the target user.
其中，第一用户类别可以包括：老人、儿童，在第一用户类别为老人的情况下，第一工作模式为老人模式；在第一用户类别为儿童的情况下，第一工作模式为儿童模式。Wherein, the first user category may include: the elderly and children. When the first user category is the elderly, the first working mode is the elderly mode; when the first user category is children, the first working mode is the children mode. .
第二用户类别可以为成人，使用习惯包括声纹识别的学习结果和网器行为的学习结果。The second user category may be adults, and the usage habits include learning results of voiceprint recognition and network computer behavior learning results.
当目标用户通过语音空调、APP语音助手或智能音箱任一种方式说出“空调开机”类指令，空调对指令进行声纹分析，判断目标用户是否属于已注册用户。When the target user speaks the "air conditioner on" command through any method such as voice air conditioner, APP voice assistant or smart speaker, the air conditioner performs voiceprint analysis on the command to determine whether the target user is a registered user.
在确定目标用户为注册用户的情况下，确定目标用户的用户类别标签，作为目标用户类别。When the target user is determined to be a registered user, the user category label of the target user is determined as the target user category.
由于热空气轻容易上浮，冷空气重容易下沉，故夏季的上下导板处于上吹位置，冬季的上下导板处于下吹位置。Since hot air is light and easy to float, and cold air is heavy and easy to sink, the upper and lower guide plates are in the upward blowing position in summer, and the upper and lower guide plates are in the downward blowing position in winter.
在目标用户类别为老人标签的情况下，智能空调将工作模式切换至老人模式，且在每次识别到该目标用户声纹的打开空调指令时，自动进入老人模式。When the target user category is labeled as the elderly, the smart air conditioner switches the working mode to the elderly mode, and automatically enters the elderly mode every time it recognizes the command to turn on the air conditioner from the voiceprint of the target user.
老人模式的具体参数与季节相关：在6月至9月的夏季，打开PMV，温度设置为27℃的制冷模式，风速设为低风，上下导板设置在最大上吹位置1，空气洁净度为打开健康模式；在12月到至2月的冬季，打开PMV，温度设为26℃的制热模式；风速设为低风，上下导板设置在最大下吹位置5；空气洁净度为打开健康模式；在其他月份，打开PMV，温度设置为26℃，在室内温度高于26℃的情况下制冷，在室内温度不高于26℃的情况下制热；风速设为低风，空气洁净度为打开健康。The specific parameters of the elderly mode are related to the season: in the summer from June to September, turn on the PMV, set the temperature to 27°C cooling mode, set the wind speed to low wind, set the upper and lower guide plates to the maximum upward blowing position 1, and the air cleanliness is Turn on the health mode; in the winter from December to February, turn on the PMV, set the temperature to 26°C heating mode; set the wind speed to low wind, and set the upper and lower guide plates to the maximum downward blowing position 5; the air cleanliness is set to turn on the health mode ; In other months, turn on the PMV, set the temperature to 26°C, cool when the indoor temperature is higher than 26°C, and heat when the indoor temperature is not higher than 26°C; the wind speed is set to low wind, and the air cleanliness is Open health.
在打开老人模式之后，智能空调播报：“长辈好，长辈关怀模式已开启，可以健康舒适地吹空调啦”。After turning on the elderly mode, the smart air conditioner broadcasts: "Hello elders, the elder care mode has been turned on, and you can blow the air conditioner healthily and comfortably."
在目标用户类别为儿童标签的情况下，智能空调将工作模式切换至儿童模式，且在每次识别到该目标用户声纹的打开空调指令时，自动进入儿童模式。When the target user category is labeled as a child, the smart air conditioner switches the working mode to the child mode, and automatically enters the child mode each time the target user's voiceprint command to turn on the air conditioner is recognized.
儿童模式的具体参数与季节相关：在6月至9月的夏季，打开PMV，温度设置为26℃的制冷模式，风速设为低风，上下导板设为最大上吹位置1，空气洁净度为打开健康模式；在12月至2月的冬季，打开PMV，温度设置为23℃的制热模式，风速设为低风，上下导板设为最大下吹位置5，空气洁净度为打开健康模式；在其他月份，打开PMV，温度设置为26℃，在室内温度高于26℃的情况下制冷，在室内温度不高于26℃的情况下制热，风速设为低风，空气洁净度设置为打开健康模式。The specific parameters of the children's mode are related to the season: in the summer from June to September, turn on the PMV, set the temperature to 26°C cooling mode, set the wind speed to low wind, set the upper and lower guide plates to the maximum upward blowing position 1, and the air cleanliness is Turn on the health mode; in the winter from December to February, turn on the PMV, set the temperature to the heating mode of 23°C, set the wind speed to low wind, set the upper and lower guide plates to the maximum downward blowing position 5, and set the air cleanliness to turn on the health mode; In other months, the PMV is turned on, the temperature is set to 26°C, cooling is performed when the indoor temperature is higher than 26°C, heating is performed when the indoor temperature is not higher than 26°C, the wind speed is set to low wind, and the air cleanliness is set to Turn on health mode.
空调播报：“你好小朋友，儿童模式已开启，可以开心地吹空调了哦”。The air conditioner broadcasts: "Hello kids, the child mode is on, you can happily blow on the air conditioner."
在目标用户类别为成人标签的情况下，则在每次识别到该用户声纹的打开空调指令时，后台调取对该声纹识别的学习结果，并下发将学习结果以设置工作模式；如果没有声纹识别的学习结果，则调取网器行为的学习结果，并下发将学习结果以设置工作模式。In the case where the target user category is the adult label, each time the user's voiceprint is recognized and the air conditioning command is turned on, the learning results of the voiceprint recognition are retrieved in the background, and the learning results are sent to set the working mode; If there is no learning result of voiceprint recognition, the learning result of the network server behavior is retrieved, and the learning result is delivered to set the working mode.
其中，基于声纹识别的智慧学习，可以得到每个声纹识别的学习结果。Among them, smart learning based on voiceprint recognition can obtain the learning results of each voiceprint recognition.
每个成人的录入声纹特征均有自己唯一的成人标签，云端对每个成年男性以及成年女性的用户开机数据进行学习，开机数据与录入声纹的用户 类别标签保持一致。用户开机数据包括用户每次开机对空调温度、风速、模式等参数的设置。Each adult's entered voiceprint features have their own unique adult label. The cloud learns the user startup data of each adult male and adult female. The startup data is consistent with the user category label of the entered voiceprint. User startup data includes the user's settings for air conditioner temperature, wind speed, mode and other parameters each time the machine is turned on.
例如，在某一台智能空调中，包括老人、成年男性1、成年女性1、儿童，共计四个用户类别标签。若识别出来的目标用户类别为老人或儿童，则不学习。For example, in a certain smart air conditioner, there are four user category labels including the elderly, adult male 1, adult female 1, and children. If the identified target user category is the elderly or children, no learning will be performed.
若识别出来的目标用户类别为“成年男性1”，则学习本次及历史上的“成年男性1”开机数据，记为“成年男性1”的声纹识别的学习结果，该声纹识别的学习结果作为下次“成年男性1”对应的工作模式设置。If the identified target user category is "Adult Male 1", then the startup data of "Adult Male 1" this time and in history will be learned, and recorded as the learning result of the voiceprint recognition of "Adult Male 1". The learning results are used as the working mode settings corresponding to "Adult Male 1" next time.
若识别出来的目标用户类别为“成年女性1”，则学习本次及历史上的“成年女性1”开机数据，记为“成年女性1”的声纹识别的学习结果，该声纹识别的学习结果作为下次“成年女性1”对应的工作模式设置。If the identified target user category is "Adult Woman 1", then learn the boot data of "Adult Woman 1" this time and in history, and record it as the learning result of the voiceprint recognition of "Adult Woman 1". The learning results are used as the working mode settings corresponding to "Adult Female 1" next time.
基于网器行为的智慧学习，利用历史数据库，学习该智能空调的样本外界参数，以及样本外界参数对应的用户开机数据标签为训练样本，对基于神经网络模型构建的网器进行训练，考虑到用户的空调使用会随着当天气温、睡眠等因素变化，三段式学习，学习用户各时间段的开机设定操作。外界参数包括温度、时段等参数。Smart learning based on network device behavior uses a historical database to learn the sample external parameters of the smart air conditioner and the user boot data labels corresponding to the sample external parameters as training samples to train the network device built based on the neural network model, taking into account the user The use of the air conditioner will change with the temperature, sleep and other factors of the day. It adopts three-stage learning to learn the user's power-on setting operations at each time period. External parameters include temperature, time period and other parameters.
时间设置为24小时制，晚上的时段为17：00至21：00，白天的时段为7：00至17：00，睡眠的时段为21：00至7：00。The time is set to a 24-hour clock, the night period is from 17:00 to 21:00, the day period is from 7:00 to 17:00, and the sleeping period is from 21:00 to 7:00.
以空调开机30分钟内使用概率最高的设定温度、模式、风速等用户开机数据作为学习对象，并判断网器行为的学习结果是否准确。网器行为的学习结果准确的标准包括：预测设定温度与开机数据标签中的实际设定温度的误差不超过1度，预测模式与开机数据标签中的实际模式相同，预测风速与开机数据标签中的实际风速相同。Use the user start-up data such as the set temperature, mode, wind speed, etc. with the highest probability of use within 30 minutes of the air conditioner being turned on as the learning object, and determine whether the learning results of the network device behavior are accurate. The criteria for accurate learning results of network device behavior include: the error between the predicted set temperature and the actual set temperature in the startup data label does not exceed 1 degree, the predicted mode is the same as the actual mode in the startup data label, the predicted wind speed is the same as the startup data label The actual wind speed in is the same.
若既没有声纹识别的学习结果，也没有网器行为的学习结果，则获取智能空调距离上次开机的时长，在时长大于30天的情况下，下发打开PMV模式，温度为26度，风速为自动风，并播报：“你好先生/女士，小优还帮您调整了您喜欢的模式，当前温度为26℃、自动风速”，播报内容还可以包括智能空调的运行模式；若本次距离上次开机的时长不大于30天，则只下发开机指令，并播报：“你好先生/女士，空调已开机”。If there are neither voiceprint recognition learning results nor network device behavior learning results, obtain the time since the smart air conditioner was last turned on. If the time is greater than 30 days, issue the PMV mode to be turned on and the temperature is 26 degrees. The wind speed is automatic wind, and the announcement is: "Hello Sir/Ms., Xiaoyou has also helped you adjust the mode you like. The current temperature is 26℃, automatic wind speed." The announcement content can also include the operating mode of the smart air conditioner; if this If the time since the last power-on is no more than 30 days, only a power-on command will be issued and an announcement will be made: "Hello sir/ma'am, the air conditioner has been turned on".
儿童模式和老人模式均是经人体舒适研究院实验得出的最优的空气 解决方案。Both the children's mode and the elderly mode are the optimal air solutions obtained through experiments by the Human Comfort Research Institute.
根据本申请提供的工作模式设置方法，通过确定用户的类别，利用注册制声纹识别的方式，可针对不同的家庭成员去学习其使用习惯，做到智慧识人与用户的偏好学习，对每个群体进行定制化呵护，提供最合适的空气方案。According to the working mode setting method provided by this application, by determining the user category and using the registration-based voiceprint recognition method, different family members can learn their usage habits, achieve intelligent recognition of people and user preference learning, and learn the preferences of each user. Customize care for each group and provide the most suitable air solution.
可选地，在所述比对所述目标声纹特征与所有注册用户的录入声纹特征之后，还包括：Optionally, after the comparison of the target voiceprint features and the entered voiceprint features of all registered users, the method further includes:
在确定所述目标用户属于非注册用户的情况下，获取开机间隔时长；When it is determined that the target user is a non-registered user, obtain the boot interval time;
在所述开机间隔时长大于预设时长阈值的情况下，切换默认工作模式；When the boot interval is longer than the preset duration threshold, switch to the default working mode;
在所述开机间隔时长不大于预设时长阈值的情况下，生成开机提示。When the boot interval is not greater than the preset duration threshold, a boot prompt is generated.
预设时长阈值可以设置为30天；默认工作模式为打开PMV，温度为26度，风速为自动风。The preset duration threshold can be set to 30 days; the default working mode is to turn on PMV, the temperature is 26 degrees, and the wind speed is automatic wind.
当确定目标声纹特征为非注册用户声纹时，调取网器行为的学习结果，并将学习结果下发；如果没有网器行为的学习结果，则获取智能空调距离上次开机的时长，在时长大于30天的情况下，下发打开PMV，温度为26度，风速为自动风，并播报：“你好先生/女士，小优还帮您调整了您喜欢的模式，当前温度为26℃、自动风速”，播报内容还可以包括智能空调的运行模式；若本次距离上次开机的时长不大于30天，则只下发开机指令，并播报：“你好先生/女士，空调已开机”。When it is determined that the target voiceprint feature is the voiceprint of a non-registered user, the learning results of the network device behavior are retrieved and the learning results are delivered; if there are no learning results of the network device behavior, the length of time since the smart air conditioner was last turned on is obtained. If the duration is more than 30 days, the PMV is issued to open, the temperature is 26 degrees, the wind speed is automatic wind, and the announcement is: "Hello sir/ma'am, Xiaoyou has also helped you adjust the mode you like, the current temperature is 26 ℃, automatic wind speed", the broadcast content can also include the operating mode of the smart air conditioner; if it is not more than 30 days since the last time it was turned on, only a start command will be issued and the announcement will be: "Hello Sir/Ms., the air conditioner has been turned on. Power on".
根据本申请提供的工作模式切换方法，利用大数据进行用户习惯人工智能(Artificial Intelligence，AI)深度学习，从而使空调更加的符合各个用户群体的使用习惯。According to the working mode switching method provided in this application, big data is used to conduct artificial intelligence (AI) deep learning of user habits, thereby making the air conditioner more in line with the usage habits of various user groups.
下面对本申请提供的工作模式切换装置进行描述，下文描述的工作模式切换装置与上文描述的工作模式切换方法可相互对应参照。The working mode switching device provided by the present application will be described below. The working mode switching device described below and the working mode switching method described above may be mutually referenced.
图2是本申请提供的工作模式切换装置的结构示意图，如图2所示，包括：Figure 2 is a schematic structural diagram of the working mode switching device provided by this application. As shown in Figure 2, it includes:
接收模块201，用于接收目标用户的目标语音信息；The receiving module 201 is used to receive the target voice information of the target user;
分析模块202，用于对所述目标语音信息进行声纹分析，确定目标用户类别；The analysis module 202 is used to perform voiceprint analysis on the target voice information and determine the target user category;
切换模块203，用于根据所述目标用户类别，切换至所述目标用户对 应的工作模式。The switching module 203 is used to switch to the working mode corresponding to the target user according to the target user category.
首先，接收模块201接收目标用户的目标语音信息。First, the receiving module 201 receives the target voice information of the target user.
发送目标语音信息的目标用户可以是已录入声纹的注册用户。The target user who sends the target voice message can be a registered user whose voiceprint has been recorded.
目标语音信息可以为开机指令。The target voice message can be a boot command.
用户可以使用语音空调、APP语音助手或智能音箱三种方式对空调进行语音操控，使用语音说出“空调开机”指令后，空调为用户智慧开机。Users can use voice air conditioners, APP voice assistants or smart speakers to control the air conditioner by voice. After using the voice to say the "air conditioner start" command, the air conditioner will be turned on for the user intelligently.
进一步地，分析模块202对所述目标语音信息进行声纹分析，确定目标用户类别。Further, the analysis module 202 performs voiceprint analysis on the target voice information to determine the target user category.
在获取到目标语音信息之后，将该目标语音信息进行预加重、分帧和加窗等预处理，将预处理后的目标语音信息转换为声纹特征图。其中声纹特征图可以为梅尔能量谱图。梅尔能量谱图能表征人能听到的声音的频率分布，是人通过声音辨别事物的深层特征，利用这种在梅尔频域的分布特性，更适合构建说话人识别系统，语音信号经过这样的转换，语音信号就变为了携带声纹信息的图像，对于单个信号，其梅尔能量谱图是黑白的，可以理解为单通道的特征图。After the target voice information is obtained, the target voice information is preprocessed such as pre-emphasis, framing, and windowing, and the preprocessed target voice information is converted into a voiceprint feature map. The voiceprint feature map may be a Mel energy spectrum map. Mel energy spectrogram can represent the frequency distribution of sounds that people can hear, which is the deep feature of people identifying things through sound. Using this distribution characteristic in the Mel frequency domain is more suitable for building a speaker recognition system. The speech signal passes through Through such conversion, the speech signal becomes an image carrying voiceprint information. For a single signal, its Mel energy spectrum is black and white and can be understood as a single-channel feature map.
将声纹特征图与空调中已注册用户的录入声纹特征进行比对，在已注册用户中确定目标用户之后，可以得到相应的用户类别标签，作为目标用户类别。Compare the voiceprint feature map with the voiceprint features entered by registered users in the air conditioner. After determining the target user among the registered users, the corresponding user category label can be obtained as the target user category.
用户类别标签可以包括：儿童标签、成人标签和老人标签；每个成人标签均是唯一的。User category tags can include: child tags, adult tags, and elderly tags; each adult tag is unique.
进一步地，切换模块203根据所述目标用户类别，切换至所述目标用户对应的工作模式。Further, the switching module 203 switches to the working mode corresponding to the target user according to the target user category.
在目标用户类别为儿童群体的情况下，将空调的工作模式切换为儿童模式；在目标用户类别为老人群体的情况下，将空调的工作模式切换为老人模式；在目标用户类别为成人群体的情况下，根据外界环境，以及目标用户的个体使用习惯，将空调的工作模式切换为目标用户在当前时间和环境下对应的工作模式。When the target user category is children, switch the working mode of the air conditioner to children's mode; when the target user category is the elderly, switch the working mode of the air conditioner to elderly mode; when the target user category is adults, In this case, according to the external environment and the individual usage habits of the target user, the working mode of the air conditioner is switched to the corresponding working mode of the target user at the current time and environment.
本申请提供的工作模式切换装置，通过对用户的语音信息进行声纹识别，得到用户的类别，从而针对特定家庭成员给予定制化的运行方案。The working mode switching device provided by this application obtains the user's category by performing voiceprint recognition on the user's voice information, thereby providing a customized operation plan for specific family members.
图3是本申请提供的电子设备的结构示意图，如图3所示，该电子设 备可以包括：处理器(processor)310、通信接口(Communications Interface)320、存储器(memory)330和通信总线340，其中，处理器310，通信接口320，存储器330通过通信总线340完成相互间的通信。处理器310可以调用存储器330中的逻辑指令，以执行工作模式切换方法，该方法包括：接收目标用户的目标语音信息；对所述目标语音信息进行声纹分析，确定目标用户类别；根据所述目标用户类别，切换至所述目标用户对应的工作模式。Figure 3 is a schematic structural diagram of an electronic device provided by this application. As shown in Figure 3, the electronic device may include: a processor (processor) 310, a communications interface (Communications Interface) 320, a memory (memory) 330 and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 complete communication with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute the working mode switching method. The method includes: receiving the target voice information of the target user; performing voiceprint analysis on the target voice information to determine the target user category; according to the Target user category, switch to the working mode corresponding to the target user.
此外，上述的存储器330中的逻辑指令可以通过软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。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或者该技术方案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中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。In addition, the above-mentioned logical instructions in the memory 330 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code. .
另一方面，本申请还提供一种计算机程序产品，所述计算机程序产品包括计算机程序，计算机程序可存储在非暂态计算机可读存储介质上，所述计算机程序被处理器执行时，计算机能够执行上述各方法所提供的工作模式切换方法，该方法包括：接收目标用户的目标语音信息；对所述目标语音信息进行声纹分析，确定目标用户类别；根据所述目标用户类别，切换至所述目标用户对应的工作模式。On the other hand, the present application also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can Execute the working mode switching method provided by each of the above methods. The method includes: receiving target voice information of the target user; performing voiceprint analysis on the target voice information to determine the target user category; switching to the target user category according to the target user category. Describe the working mode corresponding to the target user.
又一方面，本申请还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现以执行上述各方法提供的工作模式切换方法，该方法包括：接收目标用户的目标语音信息；对所述目标语音信息进行声纹分析，确定目标用户类别；根据所述目标用户类别，切换至所述目标用户对应的工作模式。On the other hand, the present application also provides a non-transitory computer-readable storage medium on which a computer program is stored. The computer program is implemented when executed by the processor to perform the working mode switching method provided by the above methods. The method includes : Receive the target voice information of the target user; conduct voiceprint analysis on the target voice information to determine the target user category; switch to the working mode corresponding to the target user according to the target user category.
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现 本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in One location, or it can be distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of this embodiment. Persons of ordinary skill in the art can understand and implement the method without any creative effort.
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各实施方式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。基于这样的理解，上述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，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the part of the above technical solution that essentially contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., including a number of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments.
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent substitutions are made to some of the technical features; however, these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions in the embodiments of the present application.

Claims (10)

  1. 一种工作模式切换方法，包括：A working mode switching method includes:
    接收目标用户的目标语音信息；Receive target voice information from the target user;
    对所述目标语音信息进行声纹分析，确定目标用户类别；Perform voiceprint analysis on the target voice information to determine the target user category;
    根据所述目标用户类别，切换至所述目标用户对应的工作模式。According to the target user category, switch to the working mode corresponding to the target user.
  2. 根据权利要求1所述的工作模式切换方法，其中，所述对所述目标语音信息进行声纹分析，确定目标用户类别，包括：The working mode switching method according to claim 1, wherein said performing voiceprint analysis on the target voice information to determine the target user category includes:
    对所述目标语音信息进行声纹分析，获取目标声纹特征；Perform voiceprint analysis on the target voice information to obtain target voiceprint characteristics;
    比对所述目标声纹特征与所有注册用户的录入声纹特征；Compare the target voiceprint features with the entered voiceprint features of all registered users;
    在确定所述目标用户属于注册用户的情况下，根据所述目标用户的用户类别标签，确定所述目标用户类别。When it is determined that the target user belongs to a registered user, the target user category is determined based on the user category tag of the target user.
  3. 根据权利要求2所述的工作模式切换方法，其中，在所述比对所述目标声纹特征与所有注册用户的录入声纹特征之后，还包括：The working mode switching method according to claim 2, wherein after the comparison of the target voiceprint characteristics and the input voiceprint characteristics of all registered users, it further includes:
    在确定所述目标用户属于非注册用户的情况下，获取开机间隔时长；When it is determined that the target user is a non-registered user, obtain the boot interval time;
    在所述开机间隔时长大于预设时长阈值的情况下，切换至默认工作模式；When the boot interval is longer than the preset duration threshold, switch to the default working mode;
    在所述开机间隔时长不大于预设时长阈值的情况下，生成开机提示。When the boot interval is not greater than the preset duration threshold, a boot prompt is generated.
  4. 根据权利要求2所述的工作模式切换方法，其中，所述对所述目标语音信息进行声纹分析，获取目标声纹特征，包括：The working mode switching method according to claim 2, wherein said performing voiceprint analysis on the target voice information to obtain target voiceprint characteristics includes:
    对所述目标语音信息进行预加重，确定预加重语音信息；Perform pre-emphasis on the target voice information to determine the pre-emphasis voice information;
    对所述预加重语音信息进行分帧，确定分帧语音信息；Divide the pre-emphasized voice information into frames to determine the framed voice information;
    对所述分帧语音信息进行加窗，获取加窗语音信息；Window the framed speech information to obtain the windowed speech information;
    对所述加窗语音信息进行声纹提取，获取所述目标语音信息的目标声纹特征。Voiceprint extraction is performed on the windowed voice information to obtain target voiceprint features of the target voice information.
  5. 根据权利要求2所述的工作模式切换方法，其中，在所述比对所述目标声纹特征与所有注册用户的录入声纹特征之前，还包括：The working mode switching method according to claim 2, wherein before comparing the target voiceprint characteristics with the input voiceprint characteristics of all registered users, it further includes:
    接收录入声纹指令；Receive voiceprint input instructions;
    根据所述录入声纹指令，生成录入声纹提示；According to the voiceprint input instruction, generate a voiceprint input prompt;
    在接收到任一用户发送的声纹测试语音的情况下，提取所述任一用户的录入声纹特征；Upon receiving the voiceprint test voice sent by any user, extract the recorded voiceprint features of any user;
    根据所述任一用户的录入声纹特征，生成录入类别提示；Generate an entry category prompt based on the entry voiceprint characteristics of any user;
    接收所述任一用户录入类别，以确定所述任一用户的用户类别标签；Receive the category entered by any user to determine the user category label of any user;
    所述录入类别是所述任一用户响应所述录入类别提示后输入的。The entry category is input by any user in response to the entry category prompt.
  6. 根据权利要求1所述的工作模式切换方法，其中，所述根据所述目标用户类别，切换至所述目标用户对应的工作模式，包括：The working mode switching method according to claim 1, wherein said switching to the working mode corresponding to the target user according to the target user category includes:
    在确定所述目标用户类别为第一用户类别的情况下，切换为第一工作模式；When it is determined that the target user category is the first user category, switch to the first working mode;
    在确定所述目标用户类别为第二用户类别的情况下，根据所述目标用户的使用习惯，切换为所述目标用户对应的目标工作模式。When it is determined that the target user category is the second user category, switching to the target working mode corresponding to the target user is performed according to the usage habits of the target user.
  7. 一种工作模式切换装置，包括：A working mode switching device, including:
    接收模块，用于接收目标用户的目标语音信息；The receiving module is used to receive the target voice information of the target user;
    分析模块，用于对所述目标语音信息进行声纹分析，确定目标用户类别；An analysis module, used to perform voiceprint analysis on the target voice information and determine the target user category;
    切换模块，用于根据所述目标用户类别，切换至所述目标用户对应的工作模式。A switching module, configured to switch to a working mode corresponding to the target user according to the target user category.
  8. 一种电子设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现如权利要求1至6任一项所述工作模式切换方法。An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, any one of claims 1 to 6 is implemented. The working mode switching method described in the item.
  9. 一种非暂态计算机可读存储介质，其上存储有计算机程序，其中，所述计算机程序被处理器执行时实现如权利要求1至6任一项所述工作模式切换方法。A non-transitory computer-readable storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the working mode switching method according to any one of claims 1 to 6 is implemented.
  10. 一种计算机程序产品，包括计算机程序，其中，所述计算机程序被处理器执行时实现如权利要求1至6任一项所述工作模式切换方法。A computer program product includes a computer program, wherein when the computer program is executed by a processor, the working mode switching method according to any one of claims 1 to 6 is implemented.
PCT/CN2022/132599 2022-03-29 2022-11-17 Working mode switching method and apparatus WO2023185005A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210324179.0 2022-03-29
CN202210324179.0A CN114863931A (en) 2022-03-29 2022-03-29 Working mode switching method and device

Publications (1)

Publication Number Publication Date
WO2023185005A1 true WO2023185005A1 (en) 2023-10-05

Family

ID=82630335

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/132599 WO2023185005A1 (en) 2022-03-29 2022-11-17 Working mode switching method and apparatus

Country Status (2)

Country Link
CN (1) CN114863931A (en)
WO (1) WO2023185005A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114863932A (en) * 2022-03-29 2022-08-05 青岛海尔空调器有限总公司 Working mode setting method and device
CN114863931A (en) * 2022-03-29 2022-08-05 青岛海尔空调器有限总公司 Working mode switching method and device

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103743065A (en) * 2014-01-20 2014-04-23 美的集团股份有限公司 Air conditioner, control method and control system thereof and terminal
CN105444332A (en) * 2014-08-19 2016-03-30 青岛海尔智能家电科技有限公司 Equipment voice control method and device
JP2019061334A (en) * 2017-09-25 2019-04-18 Kddi株式会社 Equipment control device, equipment control method and equipment control system
CN110081577A (en) * 2019-04-30 2019-08-02 深圳创维空调科技有限公司 Air conditioning control method, device, air-conditioning equipment and storage medium
JP2020086170A (en) * 2018-11-27 2020-06-04 三菱電機株式会社 Electrical equipment, speech processing device, control device, and voice operation system and program
CN112201233A (en) * 2020-09-01 2021-01-08 沈澈 Voice control method, system and device of intelligent household equipment and computer storage medium
CN114863931A (en) * 2022-03-29 2022-08-05 青岛海尔空调器有限总公司 Working mode switching method and device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103743065A (en) * 2014-01-20 2014-04-23 美的集团股份有限公司 Air conditioner, control method and control system thereof and terminal
CN105444332A (en) * 2014-08-19 2016-03-30 青岛海尔智能家电科技有限公司 Equipment voice control method and device
JP2019061334A (en) * 2017-09-25 2019-04-18 Kddi株式会社 Equipment control device, equipment control method and equipment control system
JP2020086170A (en) * 2018-11-27 2020-06-04 三菱電機株式会社 Electrical equipment, speech processing device, control device, and voice operation system and program
CN110081577A (en) * 2019-04-30 2019-08-02 深圳创维空调科技有限公司 Air conditioning control method, device, air-conditioning equipment and storage medium
CN112201233A (en) * 2020-09-01 2021-01-08 沈澈 Voice control method, system and device of intelligent household equipment and computer storage medium
CN114863931A (en) * 2022-03-29 2022-08-05 青岛海尔空调器有限总公司 Working mode switching method and device

Also Published As

Publication number Publication date
CN114863931A (en) 2022-08-05

Similar Documents

Publication Publication Date Title
WO2023185005A1 (en) Working mode switching method and apparatus
WO2019134473A1 (en) Speech recognition system, method and apparatus
CN112066528A (en) Air conditioner control method and device, storage medium and air conditioner
CN110347367A (en) Volume adjusting method, terminal device, storage medium and electronic equipment
CN109949808A (en) The speech recognition appliance control system and method for compatible mandarin and dialect
CN112201233A (en) Voice control method, system and device of intelligent household equipment and computer storage medium
CN111667818A (en) Method and device for training awakening model
CN108758989A (en) A kind of air-conditioning and its application method
CN110415694A (en) A kind of method that more intelligent sound boxes cooperate
CN107341747A (en) Class management method and system
WO2023185007A1 (en) Sleep scene setting method and apparatus
CN110286600B (en) Scene setting method and device of intelligent household operating system
WO2023185006A1 (en) Working mode setting method and apparatus
WO2022166340A1 (en) Air conditioner indoor unit control method and control device
CN114999472A (en) Air conditioner control method and device and air conditioner
KR102493280B1 (en) Server and method for generating artificial intelligence character using user data, and healthcare method using the same
CN209181285U (en) A kind of warm-air blower control and warm-air drier
CN115175415A (en) Digital twinning light adjusting method, device and system
CN116105307A (en) Air conditioner control method, device, electronic equipment and storage medium
CN213119453U (en) Indoor thermal environment control system
WO2022126734A1 (en) Voice interaction processing method and apparatus, electronic device, and storage medium
CN114842843A (en) Terminal device control method and device, electronic device and storage medium
Steffens et al. Early vocal development in tactually aided children with severe-profound hearing loss
CN111767083A (en) Method for collecting false wake-up audio data, playing device, electronic device and medium
CN110425693A (en) A kind of intelligent air condition and its application method

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: 22934823

Country of ref document: EP

Kind code of ref document: A1