CN207505115U - A kind of intelligent sound box - Google Patents
A kind of intelligent sound box Download PDFInfo
- Publication number
- CN207505115U CN207505115U CN201721752274.1U CN201721752274U CN207505115U CN 207505115 U CN207505115 U CN 207505115U CN 201721752274 U CN201721752274 U CN 201721752274U CN 207505115 U CN207505115 U CN 207505115U
- Authority
- CN
- China
- Prior art keywords
- user
- target
- music
- sound box
- intelligent sound
- 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.)
- Expired - Fee Related
Links
Abstract
The utility model discloses a kind of intelligent sound box, including:Babinet;Speech recognition equipment for receiving the sound of user, when determining play instruction of the sound for user, determines the target location of user according to sound and is sent to human face detection device;Mounted on top of the box, and the human face detection device being connect with speech recognition equipment, for receiving target location, the face characteristic of user is obtained based on target location, when determining user as negative emotions according to face characteristic, then target music play command is sent to playing device;The playing device being connect with human face detection device, for carrying out the broadcasting of corresponding music according to the target music play command received.Using intelligent sound box provided by the utility model, when user is in negative emotions, corresponding music is played, typically pacifies class music or the music of user preset so that the intelligent sound box carries emotive function, is conducive to be promoted the usage experience of user.
Description
Technical field
The utility model is related to Smart Home technical field, more particularly to a kind of intelligent sound box.
Background technology
With the continuous development of science and technology, user experience is increasingly noted by various equipment and product
Weight.
In life, user inevitably has when feel blue, when feeling blue, with greater need for listening the music of pacifying class
Or the music that user likes, to be supplied to user's comfort so that mood, which improves, to smooth down.It, can only in existing speaker
According to the operation of user, the broadcasting of corresponding music is carried out, but user is when in negative emotions, sometimes completely without mood again
The music that speaker is voluntarily set to play is gone, only played in order can be carried out according to common playlist, at this moment not conform to if heard
Appropriate to the occasion music, such as celebrating music, may so that user mood is even worse, poor user experience instead.
Therefore, a negative emotions that can recognize that user how are designed, the speaker of suitable music is played automatically, is
The technical issues of those skilled in the art are badly in need of solving at present.
Utility model content
The purpose of this utility model is to provide a kind of intelligent sound box, when user is in negative emotions, plays corresponding close
Suitable music so that the intelligent sound box carries emotive function, is conducive to be promoted the usage experience of user.
In order to solve the above technical problems, the utility model provides following technical solution:
A kind of intelligent sound box, the intelligent sound box include:
Babinet;
Speech recognition equipment, for receiving the sound of user, when determining play instruction of the sound for user, according to
The sound determines the target location of the user and is sent to human face detection device;
Mounted on the top of the box, and the human face detection device being connect with the speech recognition equipment, for connecing
The target location is received, the face characteristic of the user is obtained based on the target location, is determined when according to the face characteristic
When the user is negative emotions, then target music play command is sent to playing device;
The playing device being connect with the human face detection device, for according to the target music play command received
Carry out the broadcasting of corresponding music.
Preferably, the speech recognition equipment is fixed on the outer surface of the babinet.
Preferably, the human face detection device be mounted on the top of the box, and can realize 360 degree rotate freely take the photograph
As head.
Preferably, the display device being connect with the human face detection device is further included, for receiving the Face datection dress
The target picture play command that sends when putting the determining user as negative emotions, and according to the target picture play command into
The broadcasting of the corresponding target picture of row.
Preferably, the negative emotions recording device being connect with the human face detection device is further included, for determining described
User is after negative emotions, preserves the user information of the user and date on the same day.
Preferably, the children's mood recording device being connect with the negative emotions recording device is further included, it is pre- for reading
If each user information that the negative emotions device preserves in the period, and calculate the target letter when user is children
Cease item number.
Preferably, the information presentation device being connect with children's mood recording device is further included, for described when determining
When target information item number is more than preset item number threshold value, prompt message is exported.
Preferably, the babinet is bookshelf-type babinet.
Using intelligent sound box provided by the utility model, including:Babinet;Speech recognition equipment, for receiving user's
Sound when determining play instruction of the sound for user, determines the target location of user according to sound and is sent to Face datection
Device;Mounted on top of the box, and the human face detection device being connect with speech recognition equipment, for receiving target location, it is based on
Target location obtains the face characteristic of user, when determining user as negative emotions according to face characteristic, is then sent out to playing device
Send target music play command;The playing device being connect with human face detection device, for according to the target music received
Order carries out the broadcasting of corresponding music.
Speech recognition equipment can receive the sound of user, when determining play instruction of the sound for user, according to sound
Determine the target location of user.Human face detection device is connect with speech recognition equipment, and the face of user is obtained based on target location
Feature.That is, when user wants to listen to music, the speaker of the utility model can obtain the position of user and face spy
Sign.When human face detection device determines user as negative emotions according to face characteristic, target music is sent to playing device
Order, playing device then carry out the broadcasting of corresponding music.That is, the speaker of this programme can automatically identify user's
Negative emotions after the negative emotions of user are identified, carry out the broadcasting of corresponding music.Certainly, user is in negative emotions
When, the music of broadcasting is usually that can pacify the music of user emotion.The intelligent sound box of the utility model carries emotive function, has
Conducive to the usage experience for promoting user.
Description of the drawings
It in order to illustrate the embodiment of the utility model or the technical proposal in the existing technology more clearly, below will be to embodiment
Or attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
It is some embodiments of the utility model, for those of ordinary skill in the art, in the premise not made the creative labor
Under, it can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is a kind of structure diagram of intelligent sound box in the utility model;
Fig. 2 is another structure diagram of intelligent sound box in the utility model.
Specific embodiment
The core of the utility model is to provide a kind of intelligent sound box, when user is in negative emotions, plays corresponding sound
Happy, the music of broadcasting is usually that can pacify the music of user emotion so that the intelligent sound box carries emotive function, is conducive to carry
Rise the usage experience of user.
In order to which those skilled in the art is made to more fully understand the utility model, below in conjunction with the accompanying drawings and it is embodied
The utility model is described in further detail for mode.Obviously, described embodiment is only the utility model part
Embodiment, instead of all the embodiments.Based on the embodiment in the utility model, those of ordinary skill in the art are not doing
Go out all other embodiments obtained under the premise of creative work, shall fall within the protection scope of the present invention.
It please refers to Fig.1, is a kind of structure diagram of intelligent sound box in the utility model, which includes:
Babinet.
The babinet of intelligent sound box can be common sound box, such as can select vertical cabinet or low boy cabinet,
In the internal structure of babinet, the diversified forms such as closed, band general formula, labyrinth type can be chosen.Certainly, concrete shape can root
It is set and is adjusted according to actual conditions, such as the adjustment for carrying out box shape construction is liked according to market.Babinet is in Fig. 1 not
It shows.
In a kind of specific embodiment, the babinet of the intelligent sound box of the utility model can be bookshelf-type babinet.Bookshelf
Formula babinet is conveniently placed on higher position compared to vertical cabinet, can facilitate the determining and people for carrying out user location
The identification of face feature.
Speech recognition equipment 100, for receiving the sound of user, when determining play instruction of the sound for user, according to
Sound determines the target location of user and is sent to human face detection device 200.
Speech recognition equipment 100 can be mounted on the suitable position of intelligent sound box according to actual conditions, can be babinet
Internal or babinet outer surface.In a kind of specific embodiment, speech recognition equipment 100 is fixed on the outer of babinet
Surface, this modes of emplacement enable to speech recognition equipment 100 more clearly to receive the sound of user.
After the sound for receiving user, when determining the play instruction that sound is user, determine user's according to sound
Target location is simultaneously sent to human face detection device 200.Speech recognition equipment 100 can be carried out according to the keyword in user voice
The confirmation of play instruction, such as the keywords such as " singing ", " broadcasting ".When the sound for determining user is play instruction, Ke Yigen
The position of the target location of user, i.e. user is determined according to the sound, target location is sent to human face detection device 200.
It should be pointed out that when determining the position, i.e. target location of user, constantly the position of user can be carried out true
It is fixed, in order to more accurately carry out determining for face characteristic.
Mounted on top of the box, and the human face detection device 200 being connect with speech recognition equipment 100, for receiving target
Position obtains the face characteristic of user based on target location, when according to face characteristic, to determine user be negative emotions, then to broadcasting
It puts device 300 and sends target music play command.
Human face detection device 200 is mounted on top of the box, and is connect with speech recognition equipment 100, is known with receiving by voice
The target location for the user that other device 100 is sent.Human face detection device 200 is mounted on top of the box, can face be examined
The broader visual field can be obtained by surveying device 200.
After target location is received, the face characteristic of user is obtained based on target location.It is determined when according to face characteristic
When user is negative emotions, then target music play command is sent to playing device 300.Face characteristic can be the face of user
Point position, face's point position can include human eye key point position, lip key point position etc..According to face characteristic, it may be determined that use
The mood at family.It for example, can be by the mood of the lip key point location determination user in face characteristic, specifically, for example may be used
With the angle according to the lip key point location determination corners of the mouth, when the angle of the corners of the mouth is less than preset corners of the mouth angle threshold, determine
The mood of user is negative emotions.When the mood for determining user is negative emotions, sends target music to playing device 300 and broadcast
Put order.
The playing device 300 being connect with human face detection device 200, for according to the target music play command that receives into
The broadcasting of the corresponding music of row.
Playing device 300 is connect with human face detection device 200, can be received target music play command and be carried out corresponding
The broadcasting of music.It should be pointed out that when receiving target music play command and when carrying out the broadcasting of corresponding music, due to
Family is in negative emotions, can usually play the music for pacifying class, such as will partly pacify class music merging intelligent sound box in advance
In one list of acquiescence, when receiving target music play command, the music in the list is played.The list can be carried out
Update, such as connect internet and monthly update the list.Certainly, user can also pre-set orders with target music
Corresponding music is enabled, has no effect on the implementation of the utility model.For example, can preset one it is corresponding with target music play command
Object listing, music in the list is user preset, it is desirable to be heard in negative emotions, can carry out mood and pacify
Music.
Using intelligent sound box provided by the utility model, including:Babinet;Speech recognition equipment, for receiving user's
Sound when determining play instruction of the sound for user, determines the target location of user according to sound and is sent to Face datection
Device;Mounted on top of the box, and the human face detection device being connect with speech recognition equipment, for receiving target location, it is based on
Target location obtains the face characteristic of user, when determining user as negative emotions according to face characteristic, is then sent out to playing device
Send target music play command;The playing device being connect with human face detection device, for according to the target music received
Order carries out the broadcasting of corresponding music.
Speech recognition equipment can receive the sound of user, when determining play instruction of the sound for user, according to sound
Determine the target location of user.Human face detection device is connect with speech recognition equipment, and the face of user is obtained based on target location
Feature.That is, when user wants to listen to music, the speaker of the utility model can obtain the position of user and face spy
Sign.When human face detection device determines user as negative emotions according to face characteristic, target music is sent to playing device
Order, playing device then carry out the broadcasting of corresponding music.That is, the speaker of this programme can automatically identify user's
Negative emotions after the negative emotions of user are identified, carry out the broadcasting of corresponding music.Certainly, user is in negative emotions
When, the music of broadcasting is usually that can pacify the music of user emotion.The intelligent sound box of the utility model carries emotive function, has
Conducive to the usage experience for promoting user.
In a kind of specific embodiment of the utility model, human face detection device 200 be mounted on top of the box, and can
Realize 360 degree of cameras rotated freely.Camera can realize that 360 degree rotate freely, can be more easily to face characteristic
It is identified.Camera can be embedded or external hanging type.
In a kind of specific embodiment of the utility model, reference can be made to Fig. 2, further includes and connects with human face detection device 200
The display device 400 connect plays for receiving the target picture sent when human face detection device 200 determines that user is negative emotions
Order, and according to the broadcasting of the corresponding target picture of target picture play command progress.
When human face detection device 200 determines user as negative emotions according to face characteristic, can be sent out to display device 400
Target picture play command is sent, display device 400 can receive the target picture play command, and play and order according to target picture
Enable the broadcasting for carrying out corresponding target picture.Target picture can be the picture of user preset, such as user can be allowed to feel warm
To carry out the picture that mood is calmed down.Using for display device 400 can improve use so that user quickly breaks away from negative emotions
It experiences at family.
In a kind of specific embodiment of the utility model, Fig. 2 is seen, further includes and connects with human face detection device 200
The negative emotions recording device 500 connect, for after determining user for negative emotions, preserving the user information of user and working as
Date day.
Negative emotions recording device 500 is connect with human face detection device 200, when human face detection device 200 is according to face
Feature determine user be negative emotions when, negative emotions recording device 500 can preserve user user information and ought be everyday
Phase.For example, in one day, human face detection device 200 detects that a negative emotions respectively occurs in user A and user B respectively, negatively
Mood recording device 500 can record user A and occur a negative emotions on the day of, and records user B and occur one on the day of
Secondary negative emotions.The application of negative emotions recording device 500 can carry out the mood of a period in order to user and summarize, carry
High user experience.
In a kind of specific embodiment of the utility model, Fig. 2 is seen, is further included and negative emotions recording device
Children's mood recording device 600 of 500 connections, for reading each user that negative emotions device preserves in preset time period
Information, and calculate target information item number when user is children.
Children's mood recording device 600 is connect with negative emotions recording device 500, can be read and be born in preset time period
Each user information that face mood recording device 500 preserves can calculate the item number of children's information in these information, referred to as
Target information item number.For example, in one month, negative emotions recording device 500 preserves 5 records, wherein 3 are user
The record of A, and user A be the family in children, 2 be user B record, then negative emotions recording device 500 can read
This 5 records are taken, and it is 3 to calculate target information item number when user is children.
In a kind of specific embodiment of the utility model, Fig. 2 is seen, is further included and children's mood recording device
The information presentation device 700 of 600 connections, for when determining that target information item number is more than preset item number threshold value, output to be prompted
Information.
Information presentation device 700 is connect with children's mood recording device 600, when determine target information item number be more than it is preset
During item number threshold value, prompt message is exported.When target information item number is more than preset item number threshold value, illustrate in the preset period
Interior, the negative emotions of children are more, can export prompt message.The way of output of prompt message can be indicator light, Huo Zhefa
Short message is sent to parent etc., in order to which parent has found the unhealthy emotion of children in time.
Specific case used herein is expounded the principle and embodiment of the utility model, above example
Explanation be merely used to help understand the technical solution of the utility model and its core concept.It should be pointed out that this technology is led
For the those of ordinary skill in domain, under the premise of the utility model principle is not departed from, if can also be carried out to the utility model
Dry improvement and modification, these improvement and modification are also fallen into the protection domain of the utility model claims.
Claims (8)
1. a kind of intelligent sound box, which is characterized in that including:
Babinet;
Speech recognition equipment, for receiving the sound of user, when determining play instruction of the sound for user, according to described
Sound determines the target location of the user and is sent to human face detection device;
Mounted on the top of the box, and the human face detection device being connect with the speech recognition equipment, for receiving
Target location is stated, the face characteristic of the user is obtained based on the target location, described in being determined according to the face characteristic
When user is negative emotions, then target music play command is sent to playing device;
The playing device being connect with the human face detection device, for being carried out according to the target music play command received
The broadcasting of corresponding music.
2. intelligent sound box according to claim 1, which is characterized in that the speech recognition equipment is fixed on the babinet
Outer surface.
3. intelligent sound box according to claim 1, which is characterized in that the human face detection device is mounted on the babinet
Top, and can realize 360 degree of cameras rotated freely.
4. intelligent sound box according to any one of claims 1 to 3, which is characterized in that further include and filled with the Face datection
The display device of connection is put, is drawn for receiving the target sent when the human face detection device determines that the user is negative emotions
Face play command, and according to the broadcasting of the corresponding target picture of target picture play command progress.
5. intelligent sound box according to any one of claims 1 to 3, which is characterized in that further include and filled with the Face datection
The negative emotions recording device of connection is put, for after determining the user for negative emotions, preserving the user of the user
Information and date on the same day.
6. intelligent sound box according to claim 5, which is characterized in that further include and connect with the negative emotions recording device
Children's mood recording device, for reading each user information that the negative emotions device preserves in preset time period,
And target information item number when calculating the user as children.
7. intelligent sound box according to claim 6, which is characterized in that further include and connect with children's mood recording device
Information presentation device, for when determine the target information item number be more than preset item number threshold value when, export prompt message.
8. intelligent sound box according to any one of claims 1 to 3, which is characterized in that the babinet is bookshelf-type babinet.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201721752274.1U CN207505115U (en) | 2017-12-13 | 2017-12-13 | A kind of intelligent sound box |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201721752274.1U CN207505115U (en) | 2017-12-13 | 2017-12-13 | A kind of intelligent sound box |
Publications (1)
Publication Number | Publication Date |
---|---|
CN207505115U true CN207505115U (en) | 2018-06-15 |
Family
ID=62508980
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201721752274.1U Expired - Fee Related CN207505115U (en) | 2017-12-13 | 2017-12-13 | A kind of intelligent sound box |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN207505115U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111009241A (en) * | 2019-07-29 | 2020-04-14 | 恒大智慧科技有限公司 | Music playing method based on intelligent door lock and storage medium |
CN111506183A (en) * | 2019-01-30 | 2020-08-07 | 阿里巴巴集团控股有限公司 | Intelligent terminal and user interaction method |
-
2017
- 2017-12-13 CN CN201721752274.1U patent/CN207505115U/en not_active Expired - Fee Related
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111506183A (en) * | 2019-01-30 | 2020-08-07 | 阿里巴巴集团控股有限公司 | Intelligent terminal and user interaction method |
CN111009241A (en) * | 2019-07-29 | 2020-04-14 | 恒大智慧科技有限公司 | Music playing method based on intelligent door lock and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2015518680A (en) | Media program presentation control based on passively detected audience responses | |
KR102247642B1 (en) | Media item selection using user-specific grammar | |
CN103236259B (en) | Voice recognition processing and feedback system, voice replying method | |
CN106648524A (en) | Audio paying method and audio playing equipment | |
US10250925B2 (en) | Determining a playback rate of media for a requester | |
CN207505115U (en) | A kind of intelligent sound box | |
US20170244928A1 (en) | Information processing system, control method, and storage medium | |
MX2018011973A (en) | Systems and methods for providing a playlist of user-relevant content for playback in place of advertisement content. | |
CN109413537A (en) | Audio signal playback method, device and earphone | |
WO2014131054A3 (en) | Dynamic audio perspective change during video playback | |
TW202022851A (en) | Voice interaction method and device | |
WO2018139117A1 (en) | Information processing device, information processing method and program thereof | |
JP2008040893A5 (en) | ||
Święciński | An EMA study of articulatory settings in Polish speakers of English | |
CN109584877A (en) | Interactive voice control method and device | |
CN104008753B (en) | A kind of information processing method and electronic equipment | |
Woodhall | Audio Production and Postproduction | |
CN107808666A (en) | For the apparatus and method of visual information to be presented over the display | |
CN111967380A (en) | Content recommendation method and system | |
CN205105373U (en) | Multi -functional WIFI intelligence stereo set | |
CN203415114U (en) | Children story machine | |
Haworth | Mina as Transnational Popular Music Star in the Early 1960s | |
Walks et al. | Mothers, sex, and sexuality | |
TW200625133A (en) | System and method for automatically making a program | |
Artemenko | App-titude: Apps that excite our youngest clients: These interactive apps feature visuals that make word-learning and talking fun for tots. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180615 Termination date: 20191213 |
|
CF01 | Termination of patent right due to non-payment of annual fee |