CN114694635A - Sleep scene setting method and device - Google Patents
Sleep scene setting method and device Download PDFInfo
- Publication number
- CN114694635A CN114694635A CN202210322466.8A CN202210322466A CN114694635A CN 114694635 A CN114694635 A CN 114694635A CN 202210322466 A CN202210322466 A CN 202210322466A CN 114694635 A CN114694635 A CN 114694635A
- Authority
- CN
- China
- Prior art keywords
- sleep
- voiceprint
- voice information
- target user
- setting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
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
- G10L15/00—Speech recognition
- G10L15/01—Assessment or evaluation of speech recognition systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Abstract
The invention provides a sleep scene setting method and a sleep scene setting device, wherein the sleep scene setting method comprises the following steps: performing voiceprint analysis on the sleeping voice information of a target user to acquire the confidence coefficient of the target user which is determined as a target group; and setting a sleep scene according to the confidence coefficient. According to the sleep scene setting method and device, voiceprint analysis is carried out on the voice information containing the sleep intention, whether the user is a child group or not is determined according to the confidence coefficient, and then the immersive sleep scene suitable for the child sleep is automatically set.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a sleep scene setting method.
Background
The body of the child is in the growth and development period, the child is very sensitive to temperature, humidity and air cleanliness, cold or respiratory diseases are often caused by inappropriate air-conditioning temperature at night, and meanwhile, the child needs to be particularly cared for sleeping, so that the body and mind of the child can enter deep sleep, and the healthy growth of the child is cared.
The existing air conditioner can judge whether a user is a child according to a picture, and further determine whether to execute an instruction.
The method can only prevent young children from mistakenly triggering some function keys of the air conditioner remote controller, and cannot be intelligently adjusted to be suitable for sleeping scenes of the children.
Disclosure of Invention
The invention provides a sleep scene setting method and device, which are used for overcoming the defect that the sleep scene cannot be intelligently adjusted to be suitable for children in the prior art and realizing automatic setting of the sleep scene of the children.
The invention provides a sleep scene setting method, which comprises the following steps:
performing voiceprint analysis on the sleeping voice information of a target user to acquire the confidence coefficient of the target user which is determined as a target group;
and setting a sleep scene according to the confidence coefficient.
According to the method for setting the sleep scene provided by the invention, the setting of the sleep scene according to the confidence coefficient comprises the following steps:
determining that the target user belongs to the target population if it is determined that the confidence is not less than a confidence threshold;
generating a command for closing the household appliance, determining working parameters and judging the state of music setting;
under the condition that the music setting state is determined to be the opening state, generating a music playing instruction so as to set the sleep scene according to the household appliance closing instruction, the working parameters and the music playing instruction;
under the condition that the music setting state is determined to be the closing state, setting the sleep scene according to the household appliance closing instruction and the working parameters;
the operational parameters are determined based on sleep curves of the target population.
According to the sleep scene setting method provided by the invention, the voiceprint analysis is performed on the sleep voice information of the target user to obtain the confidence coefficient that the target user is determined as the target group, and the method comprises the following steps:
performing voiceprint analysis on the sleep voice information to obtain sleep voiceprint characteristics;
comparing the sleep voiceprint features with the input voiceprint features of all registered users;
and under the condition that the sleep voiceprint features do not belong to any registered user, scoring the voiceprint similarity between the target user and the target group according to the sleep voiceprint features to obtain the confidence.
According to the sleep scene setting method provided by the invention, after comparing the sleep voiceprint features with the input voiceprint features of all registered users, the method further comprises the following steps:
under the condition that the sleep voiceprint feature is determined to belong to any registered user, acquiring a user category label of the target user;
and setting the sleep scene under the condition that the target user is determined to belong to the target group according to the user category label.
According to the sleep scene setting method provided by the invention, the voiceprint analysis is performed on the sleep voice information to obtain the sleep voiceprint characteristics, and the method comprises the following steps:
pre-emphasis is carried out on the sleep voice information, and pre-emphasis voice information is determined;
framing the pre-emphasis voice information, and determining framed voice information;
windowing the frame voice information to obtain windowed voice information;
and carrying out voiceprint extraction on the windowed voice information to obtain the sleep voiceprint characteristics of the sleep voice information.
According to the sleep scene setting method provided by the invention, before the voiceprint analysis is performed on the sleep voice information of the target user, the method further comprises the following steps:
receiving a voice instruction of the target user;
and under the condition that the voice instruction is subjected to semantic analysis and contains a sleep keyword, determining that the voice instruction is the sleep voice information.
The present invention also provides a sleep scene setting apparatus, comprising:
the analysis module is used for carrying out voiceprint analysis on the sleeping voice information of the target user to acquire the confidence coefficient of the target user which is determined as a target group;
and the setting module is used for setting a sleep scene according to the confidence coefficient.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the sleep scene setting method.
The present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a sleep scene setting method as in any one of the above.
The present invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the sleep scene setting method as described in any of the above.
According to the sleep scene setting method and device provided by the invention, the voice information containing the sleep intention is subjected to voiceprint analysis, whether the user is a child group is determined according to the confidence coefficient, and then the immersive sleep scene suitable for the sleep of the child is automatically set, so that the operation is simple and direct, and the method and device are user-friendly.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a sleep scene setting method provided by the present invention;
FIG. 2 is a schematic structural diagram of a sleep scene setting apparatus according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The following describes a sleep scene setting method and apparatus provided by an embodiment of the present invention with reference to fig. 1 to 3.
According to the sleep scene setting method provided by the embodiment of the invention, the execution main body can be electronic equipment or software or a functional module or a functional entity capable of realizing the sleep scene setting method in the electronic equipment, and the electronic equipment in the embodiment of the invention includes but is not limited to air conditioning equipment. It should be noted that the above-mentioned executing body does not constitute a limitation to the present invention.
Fig. 1 is a schematic flowchart of a sleep scene setting method provided by the present invention, as shown in fig. 1, including but not limited to the following steps:
first, in step S1, a voiceprint analysis is performed on the sleep voice information of the target user, and a confidence that the target user is identified as the target group is obtained.
The target user can be a registered user or a non-registered user; the target population may be a population of children.
And under the condition that the voice instruction sent by the target user contains the sleep keyword, determining that the voice instruction is the sleep voice information.
After the sleep voice information is acquired, preprocessing such as pre-emphasis, framing and windowing is carried out on the sleep voice information, and the preprocessed sleep voice information is converted into a voiceprint characteristic diagram. Wherein the voiceprint feature map can be a mel-energy spectrum. The Mel energy spectrogram can represent the frequency distribution of sound which can be heard by a person, is a deep feature of things which can be distinguished by the person through sound, is more suitable for constructing a speaker recognition system by utilizing the distribution characteristic in the Mel frequency domain, and the voice signal is converted into an image carrying voiceprint information through the conversion.
And inputting the voiceprint characteristic graph into a pre-trained scoring neural network model to obtain a score of the voiceprint similarity of the target user and the child group as a confidence degree. Realized wisdom and know people, children can easily open, and non-children then do not open, and the very simple and convenient operation that leads to also avoids the mistake to trigger simultaneously.
The scoring neural network model is trained by a large amount of sample data, the sample data comprises group class labels of sample users and a sample voiceprint feature map, and therefore the confidence of the target user can be obtained after the voiceprint feature map of the target user is input.
Further, in step S2, a sleep scene is set according to the confidence.
Under the condition that the confidence degree of the target user is larger than the confidence degree threshold value, determining that the target user is a child group, and setting the working mode to be a child sleep mode so as to set the sleep mode of the child group; and under the condition that the confidence degree of the target user is not larger than the confidence degree threshold value, determining that the target user is not a child group, and setting the working mode as a default sleep mode.
The child sleep mode can be set intelligent air conditioner working parameters aiming at the sleep characteristics of a child group; the default sleep mode can be that the user sets working parameters of the intelligent air conditioner according to sleep habits, wherein the working parameters comprise the settings of temperature, wind speed, wind direction and the like.
According to the sleep scene setting method provided by the invention, the voice information containing the sleep intention is subjected to voiceprint analysis, whether the user is a child group is determined according to the confidence coefficient, and then the immersive sleep scene suitable for the child sleep is automatically set, so that the operation is simple and direct, and the method is user-friendly.
Optionally, before the voiceprint analysis of the sleep voice information of the target user, the method further includes:
receiving a voice instruction of the target user;
and under the condition that the voice instruction is subjected to semantic analysis and contains a sleep keyword, determining that the voice instruction is the sleep voice information.
After receiving a voice instruction of a target user, the voice instruction can be converted into an instruction text through semantic analysis, the instruction text is matched by using a user corpus, and the voice instruction can be determined to be sleep voice information under the condition that the instruction text contains a sleep keyword.
Table 1 is a sleep scene setting table, and includes a function scene, user corpora, interaction logic, and broadcast corpora as shown in table 1.
For example, the voice instruction is "open a child sleep mode", and the instruction text includes a keyword "sleep", so that it can be determined that the user has an intention to switch to a child sleep scene, and therefore the voice instruction is used as sleep voice information.
For example, in the power-on state, the user wakes up the little good at the main control air conditioner end, directly sends out the intention of switching to the children sleep scene, and the main control air conditioner executes the children sleep scene. The master control air conditioner is an intelligent air conditioner.
According to the sleep scene setting method provided by the invention, the voiceprint recognition technology is combined with the sleep scene of the child, the identity of the child can be automatically recognized, and the child can automatically enter the sleep-assisting scene when saying the intention of the child to sleep.
Optionally, the performing voiceprint analysis on the sleep voice information to obtain sleep voiceprint characteristics includes:
pre-emphasis is carried out on the sleep voice information, and pre-emphasis voice information is determined;
framing the pre-emphasis voice information, and determining framed voice information;
windowing the frame voice information to obtain windowed voice information;
and carrying out voiceprint extraction on the windowed voice information to obtain the sleep voiceprint characteristics of the sleep voice information.
Since the average power spectrum of a speech signal is affected by glottal excitation and oronasal radiation, the high frequency side is attenuated by 6 decibels/octaves (dB/oct) above about 800 hertz (Hz), with higher frequencies corresponding to smaller components, and for this purpose the high frequency portion of the speech signal is boosted before it is analyzed. Pre-emphasis of the sleep speech information may be achieved using digital filters.
Dividing the voiceprint signal into a plurality of frames at intervals of 10 to 20 milliseconds (ms), wherein one frame is a basic unit, and realizing the framing of the pre-emphasis voice information.
Windowing is performed on the framed speech information using a hamming window function.
According to the sleep scene setting method provided by the invention, through pre-emphasis, framing and windowing of the sleep voice information, the influence of aliasing, higher harmonic distortion, high frequency and other factors brought by human vocal organs and equipment for acquiring voice signals on the quality of voice signals can be eliminated. The signals obtained by subsequent voice processing are ensured to be more uniform and smooth as much as possible, high-quality parameters are provided for signal parameter extraction, and the voice processing quality is improved.
Optionally, the performing voiceprint analysis on the sleep voice information of the target user to obtain the confidence that the target user is determined as the target group includes:
performing voiceprint analysis on the sleep voice information to obtain sleep voiceprint characteristics;
comparing the sleep voiceprint features with the input voiceprint features of all registered users;
and under the condition that the sleep voiceprint features do not belong to any registered user, scoring the voiceprint similarity between the target user and the target group according to the sleep voiceprint features to obtain the confidence degree.
And carrying out voiceprint analysis on the sleep voice information, extracting the characteristic information of the sleep voice information, inputting the characteristic information into a voiceprint recognition model, and outputting the sleep voiceprint characteristic of the sleep voice information. The voiceprint recognition model is a deep neural network model, is obtained by training a large amount of Chinese linguistic data, and has strong noise immunity and robustness.
And inputting the sleep voiceprint characteristics into a scoring model for scoring to obtain the confidence coefficient that the sleep voice information is a child group.
The scoring model is obtained by training a neural network model through a training sample which is composed of a plurality of sample voiceprint characteristics and a group class label corresponding to each sample voiceprint characteristic.
Optionally, after the comparing the sleep voiceprint feature with the entered voiceprint features of all registered users, the method further includes:
under the condition that the sleep voiceprint feature is determined to belong to any registered user, acquiring a user category label of the target user;
and setting the sleep scene under the condition that the target user is determined to belong to the target group according to the user category label.
Similarity calculation is carried out on the sleep voiceprint features of the sleep voice information and the input voiceprint features of all registered users stored in the intelligent air conditioner; if the obtained highest similarity is higher than the set similarity threshold, the user with the voiceprint characteristic input corresponding to the highest similarity is judged to be the user sending the sleep voice information, the user category label can be determined according to the registration information of the user, the target user is determined to be a child group according to the user category label, and the child sleep mode is opened so as to set the sleep scene of the child group.
And if the highest similarity is lower than the set voiceprint threshold, determining that the target user sending the sleep voice information is not the registered user.
If the target user sends sleep voice information containing sleep intention, if the target user is determined to be a registered user and the user class label is a child, entering a child sleep curve, and starting a third-party music library to synchronously play a child sleep-aiding song and then putting the child sleep-aiding song into sleep on an Application program (APP) of a mobile terminal if the sleep-aiding music is started; if the sleep aid music is turned off, the children's song is not played.
Optionally, the setting a sleep scene according to the confidence level includes:
determining that the target user belongs to the target population if it is determined that the confidence is not less than a confidence threshold;
generating a command for closing the household appliance, determining working parameters and judging the state of music setting;
under the condition that the music setting state is determined to be the opening state, generating a music playing instruction so as to set the sleep scene according to the household appliance closing instruction, the working parameters and the music playing instruction;
under the condition that the music setting state is determined to be the closing state, setting the sleep scene according to the household appliance closing instruction and the working parameters;
the operational parameters are determined based on sleep curves of the target population.
Wherein, the confidence threshold value can be set to 75, or adjusted according to the actual situation, and the music setting state can be the on-off state of the sleep-aid music on the APP.
In the case that the confidence is less than 75, the target user is determined to be a non-registered user.
The method comprises the steps that a user sends an intention to sleep, if 'I want to sleep', air conditioner main control equipment judges whether a user who is currently interacting is a child or not through voiceprint recognition, if the judgment result is that the confidence coefficient is greater than or equal to 75, the user enters a child sleep curve, on an APP at a mobile end, if sleep-aiding music is started, the APP end switches the sleep curve to a child curve, a third-party music library is started to synchronously play a child sleep-aiding song to enable the child sleep song to fall asleep, the song is played randomly and circularly, the play is stopped half an hour later, meanwhile, the sleep curve is switched to the sleep curve setting before the child curve, and better sleep-aiding experience is brought to the user through the sleep-aiding music; if the sleep aid music is turned off, the children's song is not played.
Firstly, setting specific working parameters according to a professional children sleep curve customized according to the constitution of children, creating an optimum temperature and humidity environment, and protecting the sleep health of the children all night, wherein the working parameters comprise the settings of temperature, humidity, wind speed, wind direction and the like; in the second aspect, other household appliances such as lamps and televisions are linked, and when a sleep scene is started, the other household appliances are automatically closed or the brightness is reduced, so that a home environment most suitable for sleeping is formed; in the third aspect, specialized children sleep-assisting music is provided to create an immersive sleep environment; therefore, the immersive sleep-aiding experience of multi-sense linkage of body touch, hearing, vision and the like is created, and the most specialized sleep care is provided from multiple physical and mental dimensions.
According to the sleep scene setting method provided by the invention, the healthy and professional sleep-aiding scenes of children are provided according to the characteristics of the children by identifying the voiceprints of the children, the customized care is carried out on children groups, and the scheme of the most appropriate sleep scene is automatically started, so that the sleep scene setting method is suitable for a plurality of scenes and can be used by non-registered users.
The following describes the sleep scene setting apparatus provided by the present invention, and the sleep scene setting apparatus described below and the sleep scene setting method described above may be referred to in correspondence with each other.
Fig. 2 is a schematic structural diagram of a sleep scene setting apparatus provided in the present invention, as shown in fig. 2, including:
an analysis module 201, configured to perform voiceprint analysis on sleep voice information of a target user, and obtain a confidence that the target user is determined as a target group;
a setting module 202, configured to set a sleep scene according to the confidence.
First, the analysis module 201 performs voiceprint analysis on the sleep voice information of the target user to obtain the confidence that the target user is determined as the target group.
The target user can be a registered user or a non-registered user; the target population may be a population of children.
And under the condition that the voice instruction sent by the target user contains the sleep keyword, determining that the voice instruction is sleep voice information.
After the sleep voice information is acquired, preprocessing such as pre-emphasis, framing and windowing is carried out on the sleep voice information, and the preprocessed sleep voice information is converted into a voiceprint characteristic diagram. Wherein the voiceprint feature map can be a mel-energy spectrum. The Mel energy spectrogram can represent the frequency distribution of sound which can be heard by a person, is a deep characteristic that the person can distinguish things through the sound, is more suitable for constructing a speaker recognition system by utilizing the distribution characteristic in the Mel frequency domain, a voice signal is converted into an image carrying voiceprint information through the conversion, and for a single signal, the Mel energy spectrogram is black and white and can be understood as a single-channel characteristic diagram.
And inputting the voiceprint characteristic graph into a pre-trained scoring neural network model to obtain a score of the voiceprint similarity of the target user and the child group as a confidence degree. Realized wisdom and know people, children can easily open, and non-children then do not open, and the very simple and convenient operation that leads to also avoids the mistake to trigger simultaneously.
The scoring neural network model is trained by a large amount of sample data, the sample data comprises group class labels of sample users and a sample voiceprint feature map, and therefore the confidence of the target user can be obtained after the voiceprint feature map of the target user is input.
Further, the setting module 202 sets a sleep scene according to the confidence.
Under the condition that the confidence degree of the target user is larger than the confidence degree threshold value, determining that the target user is a child group, and setting the working mode to be a child sleep mode so as to set the sleep mode of the child group; and under the condition that the confidence degree of the target user is not larger than the confidence degree threshold value, determining that the target user is not a child group, and setting the working mode as a default sleep mode.
The child sleep mode can be set intelligent air conditioner working parameters aiming at the sleep characteristics of a child group; the default sleep mode can be that the user sets working parameters of the intelligent air conditioner according to sleep habits, wherein the working parameters comprise the settings of temperature, wind speed, wind direction and the like.
According to the sleep scene setting device provided by the invention, the voice information containing the sleep intention is subjected to voiceprint analysis, whether the user is a child group is determined according to the confidence coefficient, and then the immersive sleep scene suitable for the child sleep is automatically set, so that the sleep scene setting device is simple and direct to operate and is user-friendly.
Fig. 3 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)310, a communication Interface (communication Interface)320, a memory (memory)330 and a communication bus 340, wherein the processor 310, the communication Interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may invoke logic instructions in the memory 330 to perform a sleep scenario setting method comprising: performing voiceprint analysis on the sleeping voice information of a target user to acquire the confidence coefficient of the target user which is determined as a target group; and setting a sleep scene according to the confidence coefficient.
In addition, the logic instructions in the memory 330 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being storable on a non-transitory computer-readable storage medium, the computer program being capable of executing, when executed by a processor, the sleep scene setting method provided by the above methods, the method including: performing voiceprint analysis on the sleeping voice information of a target user to acquire the confidence coefficient of the target user which is determined as a target group; and setting a sleep scene according to the confidence coefficient.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements a sleep scene setting method provided by the above methods, the method including: performing voiceprint analysis on the sleeping voice information of a target user to acquire the confidence coefficient of the target user which is determined as a target group; and setting a sleep scene according to the confidence coefficient.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A sleep scene setting method, comprising:
performing voiceprint analysis on the sleeping voice information of a target user to acquire the confidence coefficient of the target user which is determined as a target group;
and setting a sleep scene according to the confidence coefficient.
2. The sleep scene setting method according to claim 1, wherein the setting a sleep scene according to the confidence degree includes:
determining that the target user belongs to the target population if it is determined that the confidence is not less than a confidence threshold;
generating a command for closing the household appliance, determining working parameters and judging the music setting state;
under the condition that the music setting state is determined to be the opening state, generating a music playing instruction so as to set the sleep scene according to the household appliance closing instruction, the working parameters and the music playing instruction;
under the condition that the music setting state is determined to be the closing state, setting the sleep scene according to the household appliance closing instruction and the working parameters;
the operational parameters are determined based on sleep curves of the target population.
3. The sleep scene setting method according to claim 1, wherein the performing voiceprint analysis on the sleep voice information of the target user to obtain the confidence that the target user is determined as the target group comprises:
performing voiceprint analysis on the sleep voice information to obtain sleep voiceprint characteristics;
comparing the sleep voiceprint features with the input voiceprint features of all registered users;
and under the condition that the sleep voiceprint features do not belong to any registered user, scoring the voiceprint similarity between the target user and the target group according to the sleep voiceprint features to obtain the confidence.
4. The sleep scene setting method according to claim 3, further comprising, after the comparing the sleep voiceprint feature with the entered voiceprint features of all registered users:
under the condition that the sleep voiceprint feature is determined to belong to any registered user, acquiring a user category label of the target user;
and setting the sleep scene under the condition that the target user is determined to belong to the target group according to the user category label.
5. The sleep scene setting method according to claim 3, wherein the performing voiceprint analysis on the sleep voice information to obtain sleep voiceprint characteristics includes:
pre-emphasis is carried out on the sleep voice information, and pre-emphasis voice information is determined;
framing the pre-emphasis voice information, and determining framed voice information;
windowing the frame voice information to obtain windowed voice information;
and carrying out voiceprint extraction on the windowed voice information to obtain the sleep voiceprint characteristics of the sleep voice information.
6. The sleep scene setting method according to claim 1, further comprising, before the voiceprint analysis of the sleep speech information of the target user:
receiving a voice instruction of the target user;
and under the condition that the voice instruction is subjected to semantic analysis and contains a sleep keyword, determining that the voice instruction is the sleep voice information.
7. A sleep scene setting apparatus, comprising:
the analysis module is used for carrying out voiceprint analysis on the sleeping voice information of the target user to acquire the confidence coefficient of the target user which is determined as a target group;
and the setting module is used for setting a sleep scene according to the confidence coefficient.
8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the sleep scenario setting method according to any one of claims 1 to 6 when executing the program.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the sleep scene setting method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the sleep scenario setting method of any of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210322466.8A CN114694635A (en) | 2022-03-29 | 2022-03-29 | Sleep scene setting method and device |
| PCT/CN2022/132602 WO2023185007A1 (en) | 2022-03-29 | 2022-11-17 | Sleep scene setting method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210322466.8A CN114694635A (en) | 2022-03-29 | 2022-03-29 | Sleep scene setting method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114694635A true CN114694635A (en) | 2022-07-01 |
Family
ID=82141896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210322466.8A Pending CN114694635A (en) | 2022-03-29 | 2022-03-29 | Sleep scene setting method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114694635A (en) |
| WO (1) | WO2023185007A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023185007A1 (en) * | 2022-03-29 | 2023-10-05 | 青岛海尔空调器有限总公司 | Sleep scene setting method and apparatus |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013150660A (en) * | 2012-01-24 | 2013-08-08 | Rohm Co Ltd | Sleep sensor |
| CN106371802A (en) * | 2016-10-31 | 2017-02-01 | 北京小米移动软件有限公司 | Terminal volume control method and device |
| CN107453964A (en) * | 2017-07-21 | 2017-12-08 | 北京小米移动软件有限公司 | Sleep environment management method and device |
| CN108305615B (en) * | 2017-10-23 | 2020-06-16 | 腾讯科技（深圳）有限公司 | Object identification method and device, storage medium and terminal thereof |
| CN107743289B (en) * | 2017-10-25 | 2020-08-07 | 宁波向往智能科技有限公司 | Intelligent sound box control method in intelligent household scene |
| 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 |
| CN111078017A (en) * | 2019-12-19 | 2020-04-28 | 珠海格力电器股份有限公司 | Control method and device for constructing virtual scene, electronic equipment and storage medium |
| CN111895631A (en) * | 2020-08-07 | 2020-11-06 | 珠海格力电器股份有限公司 | Air conditioning system control method, air conditioner, computer device, and computer-readable 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 |
| CN114694635A (en) * | 2022-03-29 | 2022-07-01 | 青岛海尔空调器有限总公司 | Sleep scene setting method and device |
-
2022
- 2022-03-29 CN CN202210322466.8A patent/CN114694635A/en active Pending
- 2022-11-17 WO PCT/CN2022/132602 patent/WO2023185007A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023185007A1 (en) * | 2022-03-29 | 2023-10-05 | 青岛海尔空调器有限总公司 | Sleep scene setting method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023185007A1 (en) | 2023-10-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10013977B2 (en) | Smart home control method based on emotion recognition and the system thereof | |
| CN105957527A (en) | Electric appliance speech control method and device and speech control air-conditioner | |
| CN108159702B (en) | Multi-player voice game processing method and device | |
| CN109189980A (en) | The method and electronic equipment of interactive voice are carried out with user | |
| CN108146360A (en) | Method, apparatus, mobile unit and the readable storage medium storing program for executing of vehicle control | |
| CN109147800A (en) | Answer method and device | |
| KR20010113919A (en) | Method of interacting with a consumer electronics system | |
| WO2023185005A1 (en) | Working mode switching method and apparatus | |
| CN109166584A (en) | Sound control method, device, ventilator and storage medium | |
| Chiu et al. | The impact of lexical characteristics and noise on intelligibility of Parkinsonian speech | |
| WO2023184942A1 (en) | Voice interaction method and apparatus and electric appliance | |
| CN107277276A (en) | One kind possesses voice control function smart mobile phone | |
| CN114999472A (en) | Air conditioner control method and device and air conditioner | |
| CN114694635A (en) | Sleep scene setting method and device | |
| JP2005031540A (en) | Household electric appliance with voice function | |
| WO2023185004A1 (en) | Tone switching method and apparatus | |
| WO2023185006A1 (en) | Working mode setting method and apparatus | |
| CN112735423A (en) | Voice interaction method and device, electronic equipment and storage medium | |
| CN112700765A (en) | Assistance techniques | |
| CN111429917A (en) | Equipment awakening method and terminal equipment | |
| WO2019128632A1 (en) | Audio playback method, device, and system | |
| CN116386623A (en) | Voice interaction method of intelligent equipment, storage medium and electronic device | |
| CN115175415A (en) | Digital twinning light adjusting method, device and system | |
| CN112420063A (en) | Voice enhancement method and device | |
| CN109040211A (en) | A kind of content delivery method and system based on speech recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |