CN110135600A - A kind of mattress sound collector, mattress after-sale service system and method - Google Patents
A kind of mattress sound collector, mattress after-sale service system and method Download PDFInfo
- Publication number
- CN110135600A CN110135600A CN201910412510.2A CN201910412510A CN110135600A CN 110135600 A CN110135600 A CN 110135600A CN 201910412510 A CN201910412510 A CN 201910412510A CN 110135600 A CN110135600 A CN 110135600A
- Authority
- CN
- China
- Prior art keywords
- mattress
- information
- sale service
- sale
- layer
- 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
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000005540 biological transmission Effects 0.000 claims description 19
- 238000003062 neural network model Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 11
- 230000004913 activation Effects 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 5
- 210000005036 nerve Anatomy 0.000 claims description 3
- 230000005236 sound signal Effects 0.000 claims description 3
- 230000003862 health status Effects 0.000 abstract description 17
- 238000004891 communication Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009223 counseling Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- 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
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Signal Processing (AREA)
- Entrepreneurship & Innovation (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of mattress sound collector, mattress after-sale service system and methods.Mattress sound collector can acquire the voice data information issued in mattress use process, and send that information to after-sale service device.The voice data information can more intuitively reflect the current health status of mattress, the mattress institute problem is described with after-sale service personnel again without user, reduce communication link, after-sale service personnel can accurately hold the problem of user is reflected, to further provide for good service, user's after-sale service experience is promoted.
Description
Technical field
The present invention relates to mattress technical fields, more specifically to a kind of mattress sound collector, mattress after-sale service
System and method.
Background technique
Nowadays, mattress has become one of essential bedding in people's life.But mattress with using when
Between increase, internal structure may be damaged, and cause mattress that can not play the effect of should having.Under normal circumstances, due to
Mattress internal structure can not be observed, and user does not have again judges skill accordingly, so damage user occurs in mattress internal structure
It is difficult to discover.If solved not in time at damage generation initial stage, it would be possible that will lead to bigger Factual Damage.Even if secondly,
User knows perfectly well to go wrong inside mattress, during through telephone counseling technical staff after sale possibly can not accurate description ask
Phenomenon is inscribed, causes technical staff that can not provide solution in time, reduces user's after-sale service experience.
Summary of the invention
In view of this, the first purpose of this invention is to provide a kind of mattress sound collector, make for acquiring mattress
The voice data information that used time is issued, the voice data information can more accurately characterize the health status of mattress, by sound
Sound data information is sent to after-sale service device, and after-sale service personnel can accurately hold the current state of mattress.
It is another object of the present invention to provide a kind of mattress after-sale service system and methods, and user is facilitated to obtain at any time
The health status information and issue-resolution of mattress.
In order to achieve the above object, the invention provides the following technical scheme:
A kind of mattress sound collector, comprising:
Sound collection unit, for obtaining the acoustic information issued when mattress use；
Storage unit, for prestoring and mattress uniquely corresponding characteristic information and the acoustic information；
Remote data transmission unit, for the acoustic information and the characteristic information to be sent to after-sale service device.
Further, the characteristic information includes the transmission address of the after-sale service device, the remote data transmission list
The acoustic information is sent to the after-sale service device according to the transmission address by member.
Further, the mattress sound collector further includes service feedback unit, for obtaining the after-sale service device
The feedback information after sale sent.
Further, the feedback information after sale includes that mattress health status judges that information, after-sales staff are made house calls letter
One of breath, issue-resolution are a variety of.
A kind of mattress after-sale service system, comprising:
The mattress sound collector, the mattress sound collector prestore and the unique corresponding characteristic information of mattress；
After-sale service device, when the mattress sound collector and the foundation communication connection of after-sale service device, the mattress sound
The acoustic information and the characteristic information are sent to after-sale service device by sound collector.
It further, further include technical support terminal, when the after-sale service device receives the acoustic information and described
When characteristic information, retransmit to the technical support terminal.
A kind of mattress post-sell service method, comprising:
Step 1 acquires the acoustic information issued when mattress use using mattress sound collector；
Step 2, mattress sound collector and after-sale service device, which are established, to be communicated to connect, by the acoustic information and mattress
Characteristic information is sent to after-sale service device.
Further, after the step 2 further include: the after-sale service device will be sent to mattress by feedback information after sale
Sound collector.
Further, after the step 2 further include: after-sale service device is sentenced according to the acoustic information and characteristic information
Whether disconnected mattress is in normal condition, if so, will judge that information is sent to mattress sound collector, if it is not, then again will be described
Acoustic information and the characteristic information are sent to technical support terminal.
Further, the after-sale service device judges whether mattress is in just according to the acoustic information and characteristic information
The method of normal state are as follows: be based on the acoustic information using the neural network model in the after-sale service device and carry out judgement mattress
Whether normal condition is in, comprising:
(1) neural network model is constructed, the neural network model includes five layers, in which:
First layer is input layer, uses 10000 sampled points of original sound signal；
The second layer is convolutional layer C1, and convolution kernel size is 2*2, and convolution nuclear volume is 10, and convolution step-length is 1, uses Google
The Swish activation primitive of proposition, then the maximum pond layer of addition, pond size 4, step-length 2, the second layer network terminate, and network is defeated
It is connected to third layer out；
Third layer is convolutional layer C2, and convolution kernel size is 2*2, and convolution nuclear volume is 10, and convolution step-length is 1, uses Google
The Swish activation primitive of proposition, then the maximum pond layer of addition, pond size 2, step-length 1, third layer network terminate, and network is defeated
It is connected to the 4th layer out；
4th layer is full articulamentum, data dimension 64；
Layer 5 is that softmax classification layer is connect using 2 neurons with the neuron in full articulamentum entirely, defeated
2 predicted values out, output dimension is consistent with Status Type number, uses softmax activation primitive；
(2) training neural network model acquires the voice data information under mattress normal condition and abnormality in advance, right
The neural network model is trained, until the recognition accuracy of the neural network model is greater than 97%；
(3) by the mattress of mattress sound collector acquisition using when the acoustic information that is issued be input to it is trained
Neural network model, exports whether current mattress is in normal condition.
Compared with prior art, the beneficial effects of the present invention are: the present invention provides a kind of mattress sound collectors, can
To acquire the voice data information issued in mattress use process, and after-sale service device is sent that information to, makes selling for mattress
Attendant provides for user according to the voice data information and more accurately, timely services afterwards.It is issued in mattress use process
Voice data information can more intuitively reflect the current health status of mattress, retouched again with after-sale service personnel without user
The mattress institute problem is stated, communication link is reduced, after-sale service personnel can accurately hold the problem of user is reflected, from
And good service is further provided for, promote user's after-sale service experience.
The present invention also provides a kind of mattress after-sale service system and method, mattress sound collector collects mattress correlation
Voice data information after, voice data information is sent to after-sale service device.On the one hand, after-sale service device can be by sound number
It is believed that breath is forwarded directly to technical support terminal, mattress health status is directly judged by technical staff after sale and provides corresponding solution
Certainly scheme；On the other hand, intellectual analysis program can be pre-installed on server after sale, and whether mattress is first judged by after-sale service device
In normal condition, if it is, will directly judge that information feeds back to user, if not, being again sent to voice data information
Technical support terminal provides corresponding solution by technical staff after sale, so that the work load of technical staff after sale is reduced,
And information feedback is carried out for user in time, promotion is experienced after sale.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is mattress sound collector schematic diagram in one embodiment of the invention；
Fig. 2 is mattress after-sale service system schematic diagram in one embodiment of the invention；
Fig. 3 is mattress post-sell service method flow chart in one embodiment of the invention.
Wherein, it is marked in attached drawing as follows:
100- mattress sound collector, 110- sound collection unit, 120- storage unit, 130- remote data transmission list
Member, 200- after-sale service device, 300- technical support terminal.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1~3 is please referred to, Fig. 1 is mattress sound collector schematic diagram in one embodiment of the invention；Fig. 2 is the present invention
Mattress after-sale service system schematic diagram in one embodiment；Fig. 3 is mattress post-sell service method stream in one embodiment of the invention
Cheng Tu.
As shown in Figure 1, the invention proposes a kind of mattress sound collector 100, including sound collection unit 110, storage
Unit 120 and remote data transmission unit 130.
Specifically, sound collection unit 110 can be microphone for obtaining the acoustic information issued when mattress use
Equal recording devices, are not defined the acquisition modes of acoustic information herein.The voice data information issued when mattress use
In contain the internal structure status information of mattress, sentenced by certain computer for analysis program or experienced technical staff
It is disconnected, it can accurately judge whether mattress is in health status, even judge where there is a problem inside mattress, from
And provide corresponding solution.Such as if there is spring is broken in the spring layer in mattress, then the bullet of these fractures
Spring can make a noise when in use, can judge that spring goes wrong according to the noise.In short, mattress is in complete normal condition
The sound issued under the sound and abnormality of lower sending certainly exists certain difference, is believed by voice data under different conditions
Collection, arrangement, the analysis of breath, a series of available contrast samples, the sample can be used for training smart analysis software model,
The health status of mattress is independently judged using the model after training.
Storage unit 120, for prestoring and mattress uniquely corresponding characteristic information and the acoustic information.Mattress is corresponding
Characteristic information may include model, date of manufacture, sales date, station address and user contact details of mattress etc., conveniently sell
Personnel are well understood the structure of mattress and contact user when needing afterwards.The corresponding characteristic information of mattress can also be a string only
One digital coding, after which is sent to after-sale service device 200, after-sale service device 200 can transfer the correspondence prestored
Information (model, date of manufacture, sales date, station address and user contact details of mattress etc.), so can be improved information
Efficiency of transmission.
Remote data transmission unit 130, for the acoustic information and the characteristic information to be sent to after-sale service device
200.Remote data transmission unit 130 be realize with the component of 200 linkage function of after-sale service device, and with the component really
It is no that be directly connected to server unrelated.Remote data transmission unit 130 can be the telecommunications components at prior art center, such as
Remote data transmission unit 130 can be Wi-Fi module, which is connected to by agreement with home router, and is passed through
Home router is connected to internet, communicates to connect so as to finally establish with after-sale service device 200.I.e. Wi-Fi module is real
Show the function of establishing connection with server, becomes remote data transmission unit 130.
In one embodiment of the invention, the characteristic information further includes the transmission address of the after-sale service device 200.
At this point, the acoustic information is sent to the after-sale service according to the transmission address by the remote data transmission unit 130
Device 200.
After the acoustic information and the characteristic information are sent to after-sale service device 200, user needs to obtain feedback letter
Breath.The acquisition modes of feedback information can be multiplicity, such as after-sale service personnel are by way of making a phone call or sending short message
Feedback information is informed into user, is not specifically limited herein.Preferably, the mattress sound collector further includes service feedback list
Member, the feedback information after sale sent for obtaining the after-sale service device 200.The service feedback unit may include that voice is broadcast
Feedback information is informed user by voice broadcasting modes by reporting device；The service feedback unit can also include display screen, will
Feedback information is shown by display screen to user.
On that basi of the above embodiments, the feedback information after sale may include that mattress health status judges information, after sale
Personnel make house calls one of information, issue-resolution or a variety of.If mattress is in health status by judgement,
As long as judging information as feedback information after sale mattress health status.And if be in abnormality, need by
Above-mentioned a variety of feedback informations after sale are combined, combination can be it is diversified, such as: if mattress is in abnormal shape
State, and corresponding solution must be executed by professional technician, then mattress health status is judged information and after sale people
Member makes house calls information as feedback information after sale；If mattress is in abnormality, and corresponding solution can be by
User voluntarily implements, then mattress health status can be judged information and issue-resolution as feedback information after sale.
As shown in Fig. 2, the invention also provides a kind of mattress after-sale service system, including the mattress sound collector
100 and after-sale service device 200.
Specifically, prestored in the mattress sound collector 100 with the unique corresponding characteristic information of mattress, and be used for
The acoustic information of acquisition mattress is sent to after-sale service device 200.The internal structure state of mattress is contained in the acoustic information
Information.
After-sale service device 200, when the mattress sound collector 100 is established with after-sale service device 200 to be communicated to connect, institute
It states mattress sound collector 100 and the acoustic information and the characteristic information is sent to after-sale service device 200.After-sale service device
Certain computer for analysis program can be prestored in 200, which can judge according to the acoustic information and the characteristic information
Whether mattress is in health status out, and provides corresponding solution, then will judge that information and/or solution are sent to
User.User can understand the health status of mattress by mattress after-sale service system at any time, in mattress exception, moreover it is possible in time
Corresponding solution is obtained, so that greatly the user experience is improved.
The after-sale service device 200 is preferably based on the nerve of deep learning using the method for acoustic information identification mattress failure
Network.The training method of the neural network includes:
(1) acoustic information acquires.Sound of the mattress under different conditions is adopted using mattress sound collector 100
Collection, the length of every frame data are set as 10000 sampled points.
(2) neural network model is built.Neural network model involved in the present invention includes five layers, in which:
First layer is input layer, uses 10000 sampled points of original sound signal；
The second layer is convolutional layer C1, and convolution kernel size is 2*2, and convolution nuclear volume is 10, and convolution step-length is 1, uses Google
The Swish activation primitive of proposition, then the maximum pond layer of addition, pond size 4, step-length 2, the second layer network terminate, and network is defeated
It is connected to third layer out；
Third layer is convolutional layer C2, and convolution kernel size is 2*2, and convolution nuclear volume is 10, and convolution step-length is 1, uses Google
The Swish activation primitive of proposition, then the maximum pond layer of addition, pond size 2, step-length 1, third layer network terminate, and network is defeated
It is connected to the 4th layer out；
4th layer is full articulamentum, data dimension 64；
Layer 5 is that softmax classification layer is connect using 2 neurons with the neuron in full articulamentum entirely, defeated
2 predicted values out, output dimension and Status Type number (normal or abnormal) unanimously, use softmax activation primitive.
Training neural network model.In one embodiment in the present invention, main training neural network model is directed to mattress
Identification under middle spring layer normal condition and malfunction.Training data is the sound number under two states gathered in advance
According to 5000 groups of data, totally 10000 groups of two states of acquisition under every kind of state.70% is extracted as in neural network in data set
Training set, 50% is randomly selected as the test set in network, when network training, by 10000 sampled points of every group of data
It is inputted with corresponding Status Type, carries out more wheel traversals using classical error backpropagation algorithm (BP algorithm).By training
Afterwards, neural network model recognition accuracy has reached 97% or more.
If it is determined that mattress goes wrong, and when server 200 can not provide solution after sale, in order to ensure user
It can be resolved scheme in time, at this time, it may be necessary to obtain the support of experienced technical staff.In an implementation of the invention
In example, mattress after-sale service system further includes technical support terminal 300, when the after-sale service device 200 receives the sound
When information and the characteristic information, retransmit to the technical support terminal 300.Corresponding solution party is provided by technical staff
Case, and solution is sent to after-sale service device 200 by technical support terminal 300, then use is sent to by after-sale service device 200
Family.The technical support terminal 300 can be existing smart machine, such as computer, PAD or smart phone.
As shown in figure 3, the invention also provides a kind of mattress post-sell service methods, comprising:
S10 acquires the acoustic information issued when mattress use using the mattress sound collector 100.
S20, mattress sound collector 100 and after-sale service device 200, which are established, to be communicated to connect, by the acoustic information and mattress
Characteristic information be sent to after-sale service device 200.At this point, feature of the after-sale service device 200 according to the acoustic information and mattress
Information provides a user after-sale service, such as: the after-sale service device 200 will be sent to mattress sound collection by feedback information after sale
Device.The feedback information after sale may include that mattress health status judges that information, after-sales staff are made house calls information, Resolving probiems
One of scheme is a variety of.
In order to reduce the operating pressure of after-sale service personnel, can will judge mattress whether distribute to after sale by Jian Kang work
Server 200 executes.In one embodiment of the invention, after S20 further include: after-sale service device 200 is according to the sound
Information and characteristic information, judge whether mattress is in normal condition, if so, will judge that information is sent to mattress sound collection
Device, if it is not, the acoustic information and the characteristic information are then sent to technical support terminal 300 again, then by after-sale service people
Member provides solution.In this way, after-sale service person works' task can be greatly reduced.
Wherein, after-sale service device 200 judges whether mattress is in normal condition according to the acoustic information and characteristic information
Method particularly includes: the acoustic information is inputted in trained neural network model, the current health status of output mattress.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of mattress sound collector characterized by comprising
Sound collection unit, for obtaining the acoustic information issued when mattress use；
Storage unit, for prestoring and mattress uniquely corresponding characteristic information and the acoustic information；
Remote data transmission unit, for the acoustic information and the characteristic information to be sent to after-sale service device.
2. mattress sound collector as described in claim 1, which is characterized in that the characteristic information includes the after-sale service
The transmission address of device, the remote data transmission unit according to the transmission address by the acoustic information be sent to it is described after sale
Server.
3. mattress sound collector as described in claim 1, which is characterized in that the mattress sound collector further includes service
Feedback unit, the feedback information after sale sent for obtaining the after-sale service device.
4. mattress sound collector as claimed in claim 3, which is characterized in that the feedback information after sale includes mattress health
State judges that information, after-sales staff are made house calls one of information, issue-resolution or a variety of.
5. a kind of mattress after-sale service system characterized by comprising
The described in any item mattress sound collectors of Claims 1 to 4, the mattress sound collector prestore unique with mattress
Corresponding characteristic information；
After-sale service device, when the mattress sound collector and after-sale service device are established when communicating to connect, the mattress sound is adopted
The acoustic information and the characteristic information are sent to after-sale service device by storage.
6. mattress after-sale service system described in claim 5, which is characterized in that further include technical support terminal, sold when described
When server receives the acoustic information and the characteristic information afterwards, retransmit to the technical support terminal.
7. a kind of mattress post-sell service method characterized by comprising
Step 1 acquires the acoustic information issued when mattress use using mattress sound collector；
Step 2, mattress sound collector and after-sale service device, which are established, to be communicated to connect, by the feature of the acoustic information and mattress
Information is sent to after-sale service device.
8. mattress post-sell service method as claimed in claim 7, which is characterized in that after the step 2 further include: described
After-sale service device will be sent to mattress sound collector by feedback information after sale.
9. mattress post-sell service method as claimed in claim 7, which is characterized in that after the step 2 further include: after sale
Server judges whether mattress is in normal condition according to the acoustic information and characteristic information, if so, will judge information hair
It send to mattress sound collector, if it is not, the acoustic information and the characteristic information are then sent to technical support terminal again.
10. mattress post-sell service method as claimed in claim 9, which is characterized in that the after-sale service device is according to the sound
Message breath and characteristic information, judge the method whether mattress is in normal condition are as follows: utilize the nerve in the after-sale service device
Network model is based on the acoustic information and carries out judging whether mattress is in normal condition, comprising:
(1) neural network model is constructed, the neural network model includes five layers, in which:
First layer is input layer, uses 10000 sampled points of original sound signal；
The second layer is convolutional layer C1, and convolution kernel size is 2*2, and convolution nuclear volume is 10, and convolution step-length is 1, is proposed using Google
Swish activation primitive, be then added maximum pond layer, pond size 4, step-length 2, the second layer network terminates, and network exports company
It is connected to third layer；
Third layer is convolutional layer C2, and convolution kernel size is 2*2, and convolution nuclear volume is 10, and convolution step-length is 1, is proposed using Google
Swish activation primitive, be then added maximum pond layer, pond size 2, step-length 1, third layer network terminates, and network exports company
It is connected to the 4th layer；
4th layer is full articulamentum, data dimension 64；
Layer 5 is that softmax classification layer is connect using 2 neurons with the neuron in full articulamentum entirely, output 2
A predicted value, output dimension is consistent with Status Type number, uses softmax activation primitive；
(2) training neural network model acquires the voice data information under mattress normal condition and abnormality, to described in advance
Neural network model is trained, until the recognition accuracy of the neural network model is greater than 97%；
(3) by the mattress of mattress sound collector acquisition using when the acoustic information that is issued be input to trained nerve
Network model, exports whether current mattress is in normal condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910412510.2A CN110135600A (en) | 2019-05-17 | 2019-05-17 | A kind of mattress sound collector, mattress after-sale service system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910412510.2A CN110135600A (en) | 2019-05-17 | 2019-05-17 | A kind of mattress sound collector, mattress after-sale service system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110135600A true CN110135600A (en) | 2019-08-16 |
Family
ID=67574931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910412510.2A Pending CN110135600A (en) | 2019-05-17 | 2019-05-17 | A kind of mattress sound collector, mattress after-sale service system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135600A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114343373A (en) * | 2022-01-05 | 2022-04-15 | 浙江想能睡眠科技股份有限公司 | Method, system and storage medium for intelligently adjusting mattress |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103231962A (en) * | 2013-05-15 | 2013-08-07 | 北京晶科华盛科技有限公司 | Diagnosis and early-warning system for elevator faults |
| CN103884073A (en) * | 2013-12-27 | 2014-06-25 | 广东美的制冷设备有限公司 | Air conditioner wireless controller, air conditioner, and after-sales service providing method and system of air conditioner |
| CN106404388A (en) * | 2016-09-13 | 2017-02-15 | 西安科技大学 | Scraper conveyor chain fluttering fault diagnosis method |
| CN106502153A (en) * | 2016-11-04 | 2017-03-15 | 合肥天讯亿达光电技术有限公司 | A kind of car after-sale service management system |
-
2019
- 2019-05-17 CN CN201910412510.2A patent/CN110135600A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103231962A (en) * | 2013-05-15 | 2013-08-07 | 北京晶科华盛科技有限公司 | Diagnosis and early-warning system for elevator faults |
| CN103884073A (en) * | 2013-12-27 | 2014-06-25 | 广东美的制冷设备有限公司 | Air conditioner wireless controller, air conditioner, and after-sales service providing method and system of air conditioner |
| CN106404388A (en) * | 2016-09-13 | 2017-02-15 | 西安科技大学 | Scraper conveyor chain fluttering fault diagnosis method |
| CN106502153A (en) * | 2016-11-04 | 2017-03-15 | 合肥天讯亿达光电技术有限公司 | A kind of car after-sale service management system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114343373A (en) * | 2022-01-05 | 2022-04-15 | 浙江想能睡眠科技股份有限公司 | Method, system and storage medium for intelligently adjusting mattress |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20020161833A1 (en) | Methods for registering and notifying wireless devices | |
| CN101523804B (en) | Methods and apparatus to combine data from multiple sources to characterize communication systems | |
| CN109768970B (en) | Configurable universal protocol generation method | |
| CN109245990B (en) | Message display method, device, terminal and storage medium | |
| CN108366006A (en) | A kind of intelligent appliance distribution method, apparatus and system | |
| CN106844220A (en) | A kind of method of testing and system of simulation computer web application real running environment | |
| CN106791229A (en) | The identification method and device of number | |
| JP2007183890A (en) | Living condition monitoring system, apparatus, method, and program | |
| JP2005518682A (en) | Cable modem with autonomous diagnostic function | |
| JP4897899B2 (en) | Ticket number issuing system, method and program | |
| CN108848280A (en) | Call processing method, device, storage medium and service equipment | |
| CN105929697A (en) | Smart home maintenance method and device and terminal | |
| CN109962893A (en) | A kind of intelligent call method and its relevant device | |
| CN109062957A (en) | The acquisition of case source and recommended method and system | |
| CN110135600A (en) | A kind of mattress sound collector, mattress after-sale service system and method | |
| CN108398607A (en) | Distribution terminal comprehensive test platform and method | |
| CN110708216B (en) | Switch LLDP protocol test method and test system | |
| CN109005107A (en) | The means of communication, intelligent terminal and the device with store function | |
| CN103905233B (en) | Realize method, system and the access network device of analog sensor plug and play | |
| CN106878570A (en) | A kind of speech business method of testing and system | |
| CN103944779B (en) | A kind of WAP service features monitoring method and system | |
| CN106911832A (en) | A kind of method and device of voice record | |
| US7020249B1 (en) | Voice interface unit for line conditioner control | |
| CN101615336A (en) | Gas alarm method, device and home gateway based on home gateway | |
| CN108010518A (en) | A kind of voice acquisition method, system and the storage medium of interactive voice equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190816 |
|
| RJ01 | Rejection of invention patent application after publication |