CN108307049A - Electronic device falls model update method and Related product - Google Patents
Electronic device falls model update method and Related product Download PDFInfo
- Publication number
- CN108307049A CN108307049A CN201810045061.8A CN201810045061A CN108307049A CN 108307049 A CN108307049 A CN 108307049A CN 201810045061 A CN201810045061 A CN 201810045061A CN 108307049 A CN108307049 A CN 108307049A
- Authority
- CN
- China
- Prior art keywords
- model
- electronic device
- result
- input data
- input
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000001133 acceleration Effects 0.000 claims abstract description 125
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 230000005484 gravity Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 12
- 238000013497 data interchange Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 20
- 239000003990 capacitor Substances 0.000 description 12
- 238000013473 artificial intelligence Methods 0.000 description 9
- 238000003780 insertion Methods 0.000 description 7
- 230000037431 insertion Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000033001 locomotion Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000010409 thin film Substances 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/02—Constructional features of telephone sets
- H04M1/0202—Portable telephone sets, e.g. cordless phones, mobile phones or bar type handsets
- H04M1/026—Details of the structure or mounting of specific components
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Environmental & Geological Engineering (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
Fall model update method and Related product this application provides a kind of electronic device, this method includes：Acquire the acceleration information of the electronic device；Electronic device is acquired at a distance from ground；Acceleration value is calculated according to acceleration information, acceleration value and distance value under state are fallen in extraction, the acceleration value and distance value for falling under state are formed into the first input data, model is fallen in first input data input first to carry out that the first output result is calculated, fall model using first input data as training data pair first and carry out re -training and obtains second and fall model, first input data is input to second falls model and obtains the second output result, by the first output result and the second output results contrast, as the second output result is more than the first output result, fall model replacement first using second and falls model.Technical solution provided by the present application has the advantages that user experience is high.
Description
Technical field
This application involves terminal device technical fields, and in particular to a kind of electronic device falls model update method and phase
Close product.
Background technology
In the prior art, mobile terminal (such as mobile phone, tablet computer) has become user's first choice and frequency of use highest
Electronic device, for mobile terminal, it is producer or the unavoidable problem of user that screen is fragile, after screen is broken,
The surplus value of terminal is just had a greatly reduced quality, because the price that most of factory repair changes screen almost alreadys exceed the residue of terminal
Value.And industry prevalence 2.5D glass is more prone to fall bad and broken screen, each mainstream producer is all spending greatly as screen at present
The R＆D costs research raising complete machine of amount falls drop resistant ability.
The existing calculating for falling data is there are many mode, such as is calculated by falling model, but existing falls
The parameter of stamping die type will not change after factory setting, but the parameter of electronic device is lacked and converted at any time, so existing
The result of calculation that some falls model is inaccurate, and influences the Experience Degree of client.
Apply for content
What the embodiment of the present application provided a kind of electronic device falls model update method and Related product, may be implemented pair
The scene fallen is restored, and user is allowed intuitively to watch, and improves user experience.
In a first aspect, the embodiment of the present application provides a kind of electronic device, the electronic device includes：Application processor AP,
Touching display screen, gravity sensor and range sensor, which is characterized in that
The gravity sensor, the acceleration information for acquiring the electronic device；
The range sensor, for acquiring electronic device at a distance from ground；
The AP determines that the electronics fills for acceleration value to be calculated according to acceleration information according to the acceleration value
The state being in is set, which includes：Normal state and fall state；
The AP, for extracting the acceleration value and distance value that fall under state, the acceleration that will fall under state
Value and distance value form the first input data, and model is fallen in first input data input first to carry out being calculated first
Output falls mould as a result, falling model progress re -training using first input data as training data pair first and obtaining second
Type, by the first input data be input to second fall model obtain the second output as a result, by first output result with second output
Results contrast, such as the second output result are more than the first output and fall model as a result, falling model using second and replacing first.
Second aspect, provide it is a kind of method for computing data is fallen based on artificial intelligence, the method is filled applied to electronics
In setting, the electronic device includes：Application processor AP, touching display screen, gravity sensor and range sensor, the method
Including：
Acquire the acceleration information of the electronic device；
Electronic device is acquired at a distance from ground；
Acceleration value is calculated according to acceleration information, the shape that the electronic device is in is determined according to the acceleration value
State, the state include：Normal state and fall state；
Acceleration value and distance value under state, the acceleration value and the distance value that will fall under state are fallen in extraction
The first input data is formed, model is fallen in first input data input first to be carried out that the first output is calculated as a result, will
First input data, which as training data pair first falls model and carries out re -training, to be obtained second and falls model, defeated by first
Enter data be input to second fall model obtain the second output as a result, by first output result with second output results contrast, such as
Second output result is more than the first output and falls model as a result, falling model using second and replacing first.
The third aspect, provides a kind of electronic device, and the electronic device includes：Processing unit, touching display screen, gravity pass
Sensor, circuit and range sensor,
The gravity sensor, the acceleration information for acquiring the electronic device；
The range sensor, for acquiring electronic device at a distance from ground；
The processing unit, for acceleration value to be calculated according to acceleration information, being determined according to the acceleration value should
The state that electronic device is in, the state include：Normal state and fall state；
The processing unit will fall being somebody's turn to do under state for extracting the acceleration value and distance value that fall under state
Acceleration value and distance value form the first input data, and model is fallen in first input data input first calculate
Second is obtained to the first output as a result, falling model using first input data as training data pair first and carrying out re -training
Fall model, the first input data is input to second falls model and obtain the second output as a result, by the first output result and the
Two output results contrasts, such as the second output result are more than the first output and fall mould as a result, falling model using second and replacing first
Type.
Fourth aspect provides a kind of computer readable storage medium, computer journey of the storage for electronic data interchange
Sequence, wherein the computer program makes computer execute the method that second aspect provides.
5th aspect, provides a kind of computer program product, and the computer program product includes storing computer journey
The non-transient computer readable storage medium of sequence, the computer program are operable to that computer is made to execute second aspect offer
Method.
Implement the embodiment of the present application, has the advantages that：
As can be seen that after technical solution provided by the present application collects acceleration information, calculated according to acceleration information
Acceleration value, acquisition electronic device at a distance from ground, when being determined as falling state, extraction fall state acceleration figure and
The acceleration value and distance value are formed the first input data, which are input to first and is fallen by distance value
Carry out that the first output is calculated in model as a result, then using the first input data as training data pair first fall model into
Row re -training obtains second and falls model, by the first input data be input to second fall model obtain the second output as a result,
First falls model as a result, falling model using second and replacing as the second output result is more than the first output, it in this way can be according to
The existing parameter for falling model is updated according to actual detection data, to more adapt to and the current shape of electronic device
State improves the accuracy of calculating, improves the Experience Degree of user.
Description of the drawings
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is some embodiments of the present application, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of structural schematic diagram of electronic device provided by the embodiments of the present application.
Fig. 1 a are a kind of schematic diagrames of plane-parallel capacitor provided by the embodiments of the present application.
Fig. 1 b are the schematic diagrames of another plane-parallel capacitor provided by the embodiments of the present application.
Fig. 1 c are the schematic diagrames of another plane-parallel capacitor provided by the embodiments of the present application.
Fig. 1 d are the schematic diagrames of acceleration provided by the embodiments of the present application.
Fig. 2 is a kind of schematic diagram of electronic device disclosed in the embodiment of the present application.
Fig. 3 a are a kind of schematic diagrames of convolution disclosed in the embodiment of the present application.
Fig. 3 b are a kind of mobile schematic diagrames of input data of the embodiment of the present application.
Fig. 3 c are a kind of schematic diagrames of input data of the embodiment of the present application.
Fig. 3 d are a kind of insertion schematic diagrames of input data of the embodiment of the present application.
Fig. 4 is a kind of flow diagram for falling model update method of electronic device provided by the embodiments of the present application.
Fig. 5 is a kind of structural schematic diagram of electronic device provided by the embodiments of the present application.
Fig. 6 is a kind of structural schematic diagram of mobile phone disclosed in the embodiment of the present application.
Specific implementation mode
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation describes, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on this Shen
Please in embodiment, the every other implementation that those of ordinary skill in the art are obtained without creative efforts
Example, shall fall in the protection scope of this application.
Term " first ", " second ", " third " in the description and claims of this application and the attached drawing and "
Four " etc. be for distinguishing different objects, rather than for describing particular order.In addition, term " comprising " and " having " and it
Any deformation, it is intended that cover and non-exclusive include.Such as it contains the process of series of steps or unit, method, be
The step of system, product or equipment are not limited to list or unit, but further include the steps that optionally not listing or list
Member, or further include optionally for the intrinsic other steps of these processes, method, product or equipment or unit.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Electronic device in the application may include smart mobile phone (such as Android phone, iOS mobile phones, Windows
Phone mobile phones etc.), tablet computer, palm PC, laptop, mobile internet device (MID, Mobile Internet
Devices) or Wearable etc., above-mentioned electronic device are only citings, and non exhaustive, are filled including but not limited to above-mentioned electronics
It sets, for convenience of description, above-mentioned electronic device is known as user equipment (User equipment, UE) in following example.
Certainly in practical applications, above-mentioned user equipment is also not necessarily limited to above-mentioned realization form, such as can also include：Intelligent vehicle-carried end
End, computer equipment etc..
In the electronic device that first aspect provides, the electronic device further includes：Communication module；
The AP is additionally operable to control communication module and the weight data that described second falls model is sent to network side sets
It is standby.
In the electronic device that first aspect provides, the AP is specifically used for if any n acceleration value, by the suitable of collection point
Sequence traverses n acceleration value, and such as continuous m acceleration value is more than given threshold, is determined as falling state, is otherwise determined as common
State.
In the electronic device that first aspect provides, the AP is specifically used for using first input data as training data
Input first falls V layers of forward operation of model execution and obtains the V layer forward operation of forward operation as a result, being transported to V layer forward direction
It calculates result treatment and obtains V layer input data gradient, V layer input data gradient is input to the first V layer for falling model
It executes V layers of reversed operation and obtains V weights gradient, using V weights gradient V layers of weights are updated with weights after being updated
Updated weight data is determined as the second weight data for falling model by data.
In the method that second aspect provides, the method further includes：
The weight data that described second falls model is sent to network side equipment.
It is described to determine that the electronics fills according to the acceleration value if any n acceleration value in the method that second aspect provides
The state being in is set, including：
By n acceleration value of order traversal of collection point, such as continuous m acceleration value is more than given threshold, is determined as falling
State is fallen, normal state is otherwise determined as.
It is described to fall model using first input data as training data pair first in the method that second aspect provides
Progress re -training obtains second and falls model, including：
First input data is fallen into V layers of forward operation of model execution as training data input first and obtains positive fortune
The V layer forward operation of calculation is defeated by V layer as a result, obtain V layer input data gradient to V layer forward operation result treatment
Enter data gradient be input to first fall model V layer execute V layers of reversed operation obtain V weights gradient, using V weights
Gradient is updated V layers of weights updated after weight data, updated weight data is determined as second and falls model
Weight data.
Referring to Fig. 1, Fig. 1, which is the embodiment of the present application, provides a kind of electronic device, referring to Fig. 1, Fig. 1 is of the invention real
The structural schematic diagram that example provides a kind of electronic device 100 is applied, above-mentioned electronic device 100 includes：Shell 110, circuit board 120,
Battery 130, cover board 140, touching display screen 150, gravity sensor (English：Gravity Sensor, referred to as：G-sensor)
170, the circuit board 120, the battery 130 and the cover board 140, institute is arranged on the shell 110 in range sensor 180
It states circuit board 120 and is additionally provided with the circuit for connecting the touching display screen 150；The circuit board 120 can also include：Using place
Manage device AP190, gravity sensor 170 and range sensor 180.
Above-mentioned touching display screen is specifically as follows Thin Film Transistor-LCD (Thin Film Transistor-
Liquid Crystal Display, TFT-LCD), light emitting diode (Light Emitting Diode, LED) display screen, have
Machine light emitting diode (Organic Light-Emitting Diode, OLED) display screen etc..
Gravity sensor 170, the direction for detecting acceleration and size are equivalent to the movement shape of detection electronic installation
State.The function of G-sensor understands fairly simple, the mainly variation of perception acceleration of getting up, for example shake, fall, rising,
The various mobile variations such as decline can be converted into electric signal by G-sensor, then pass through the calculating of application processor AP190 point
After analysis, it will be able to determine the acceleration value of the electronic device.
Optionally, above-mentioned electronic device can also include：Geomagnetic sensor and gyroscope, the geomagnetic sensor and gyroscope
It is connect respectively with application processor AP190.On the electronic device, G-sensor not only works independently, and can also be passed with earth magnetism
Sensor 171, gyroscope 172 cooperate together, provide more accurate and comprehensive action induction ability.
Specifically, in electronic device, gravity sensor 170 can be actually a kind of plane-parallel capacitor, for parallel
The capacitance size and distance between plates of plate capacitor are inversely proportional, and pass through the capacitance variations in detection X, Y, Z-direction, so that it may to calculate
Linear acceleration size on to all directions.
In the acceleration calculation mode of X-direction as an example, acceleration value is specifically as follows：
As shown in Figure 1a, it is a kind of schematic diagram of plane-parallel capacitor.
The corresponding acceleration of a refering to fig. 1, Fig. 1 a is 0, as shown in Figure 1a, due at this time without acceleration value, so intermediate
Parallel-plate be located at initial position, so capacitance C at this time1=C0, the C1Capacitance that can be between parallel-plate and lower electrode
Value, the C0It can be initial capacitance value.Capacitance C at this time2=C0, the C2Capacitance that can be between parallel-plate and top electrode
Value, at this point, capacitance C1Corresponding distance d1=d0；Capacitance C2Corresponding distance d2=d0；Wherein, d1Can be parallel-plate and lower electricity
The distance between pole, d2Can be the distance between parallel-plate and top electrode.Since acceleration value at this time is zero, so C1=
C2=C0；A can be calculated according to above-mentioned formulax=0.
The corresponding acceleration of b refering to fig. 1, Fig. 1 b is positive value, and due to the effect of positive value acceleration, parallel-plate can downward electrode
It is mobile, it is assumed that displacement distance x can increase x then for the distance between parallel-plate and top electrode, so at this time, d1
=d0- x, d2=d0+x；According to the calculation formula of capacity plate antenna, as shown in following formula：
Wherein, S can corresponding area, ε be that (it is by tablet for dielectric constant between two plates of plane-parallel capacitor
The material of electrode determines), k is dielectric constant, and d is the distance between two plates of plane-parallel capacitor.
Capacitance as shown in Figure 1 b is as follows：
So due to the downward electrode movement of the parallel-plate of plane-parallel capacitor, so C1＞ C2, i.e. ax＞ 0.
The corresponding acceleration of c refering to fig. 1, Fig. 1 c is negative value, and due to the effect of negative value acceleration, parallel-plate can be to top electrode
It is mobile, it is assumed that displacement distance x can increase x then for the distance between parallel-plate and top electrode, so at this time, d1
=d0+ x, d2=d0-x；According to the calculation formula of capacity plate antenna, as shown in following formula：
Capacitance as illustrated in figure 1 c is as follows：
At this time due to the upward electrode movement of the parallel-plate of plane-parallel capacitor, so C1＜ C2, i.e. ax＜ 0.
I.e. by the test to above-mentioned plane-parallel capacitor, specific acceleration value can be accessed, and the value can
Show the direction of acceleration.
Specifically, for electronic device, the value tool of the acceleration of test is as shown in Figure 1 d there are three direction
The schematic diagram in three directions of testing of electronic devices has specifically, can be divided into X-direction, Y direction and Z-direction
The display signal of body is as shown in Figure 1 d.
Specifically, in an optional drop test, its corresponding acceleration value can be in falling process：
ax=0.049m/S2
ay=-0.026m/S2
az=9.800m/S2。
The state that the electronic device is in falling can be determined according to above-mentioned data.
As shown in Fig. 2, being a kind of structural schematic diagram of electronic device provided by the present application, as shown in Fig. 2, the electronic device
200 include：Shell, application processor AP210, touching display screen 220, gravity sensor 250, range sensor 260 and circuit
240, the outside of the shell is provided with camera 230, the camera, the touching display screen by least one circuit with
The application processor AP connections.Wherein, the AP210 connects gravity sensor 250 and Distance-sensing by another circuit
Device, wherein the circuit 240 can specifically include：Bus, flexible PCB, connection chip etc., certainly in practical applications,
Foregoing circuit 240 can also be other forms of expression, and the application specific implementation mode is not intended to limit the specific of foregoing circuit 240
The form of expression.Above-mentioned electronic device 200 can also include：Geomagnetic sensor and gyroscope, the geomagnetic sensor and gyroscope can
To combine 250 gathered data of gravity sensor；The electronic device 200 can also include：Artificial intelligence process device, the artificial intelligence
Processor can be separately provided, and can also be integrated with application processor AP210, for convenience, as shown in Figure 2
Artificial intelligence process device is integrated in AP210 by embodiment.
The acceleration information is transferred at by gravity sensor 250, the acceleration information for acquiring electronic device
Manage device AP；
Range sensor 260, for acquiring electronic device at a distance from ground；
AP210 determines the electronic device for acceleration value to be calculated according to acceleration information according to the acceleration value
The state being in, the state include：Normal state and fall state；
Optionally, above-mentioned acceleration information can be multiple capacitances of plane-parallel capacitor, specifically, can be as schemed
1a, such as Fig. 1 b, C as illustrated in figure 1 c1And C2Value.Certainly in practical applications, due to need to acquire X, Y as shown in Figure 1 d,
The acceleration information of tri- axis of Z.Certainly in practical applications, using other gravity sensors, the acceleration information can also
It is other kinds of data, the application specific implementation mode is not intended to limit the practical manifestation form of above-mentioned acceleration information.
The number of above-mentioned acceleration value can be n acceleration value.Specifically, order traversals n of the AP210 by collection point
Acceleration value, such as continuous m acceleration value are more than given threshold, are determined as falling state, are otherwise determined as normal state.Its
In, n, m are integer more than or equal to 2, and m ＜ n.
AP210 forms the acceleration value and distance value for extracting the acceleration value and distance that fall under state
First input data, by first input data input first fall model carry out that the first output is calculated as a result, by this
One input data, which as training data pair first falls model and carries out re -training, to be obtained second and falls model, and number is inputted by first
According to be input to second fall model obtain the second output as a result, by first output result with second output results contrast, such as second
Output result is more than the first output and falls model as a result, falling model using second and replacing first.
After technical solution provided by the present application collects acceleration information, acceleration value is calculated according to acceleration information,
Electronic device is acquired at a distance from ground, when being determined as falling state, the acceleration figure and distance value of state are fallen in extraction, will
The acceleration value and distance value form the first input data, which is input to first falls in model and carry out
The first output is calculated as a result, the first input data is then fallen model as training data pair first carries out re -training
Obtain second and fall model, by the first input data be input to second fall model obtain the second output as a result, as second output
As a result it is more than the first output and falls model as a result, falling model using second and replacing first, it in this way can be according to actual inspection
Measured data is updated the existing parameter for falling model, to more adapt to calculate with the current state of electronic device, raising
Accuracy, improve the Experience Degree of user.
Optionally, above-mentioned AP210 is additionally operable to, when determining that the second output result is less than or equal to the first output result, delete
Fall model except second.
Second be less than or equal to for the second output result after the technical solution i.e. training of the first output result falls mould
Type falls model inferior to first, at this point, without falling model modification to first, so directly deleting second falls model.
The method of comparison that above-mentioned first output result exports result with second can be,
Such as first output result and the second output result are data block, which can specifically include：Vector, square
One kind in battle array, three-dimensional data, 4 D data.The greatest member value X of extraction the first output resultmax1, extraction the second output knot
The greatest member value X of fruitmax2；Such as Xmax2＞ Xmax1, determine that the second output result is more than the first output as a result, such as Xmax2≤Xmax1,
Determine that the second output result is less than or equal to the first output result.Certainly its method compared can also use other modes, this
The concrete mode of above-mentioned comparison is not limited in application.
Optionally, above-mentioned electronic device further includes：Communication module；
The AP is additionally operable to control communication module and the weight data that described second falls model is sent to network side sets
It is standby.
Optionally, AP210 is executed specifically for first input data is fallen model as training data input first
V layers of forward operation obtain the V layer forward operation of forward operation as a result, to obtain V layer to V layer forward operation result treatment defeated
Enter data gradient, V layer input data gradient, which is input to the V layer V layers of reversed operation of execution that first falls model, obtains V
Weights gradient is updated V layers of weights using V weights gradient weight data after being updated, by updated weights number
According to being determined as the second weight data for falling model.
Optionally, AP210 inputs number specifically for obtaining V layer to V layer forward operation result and empirical coefficient product
According to gradient；
Or array type conversion is carried out to V layer forward operation result and obtains V layer input data gradient.
AP210 is specifically used for the quantity n of the extraction acceleration value and quantity m of distance value, extracts and preset input data
Quantity, that is, CI*H*W；Wherein, H is height value, and W is width value, and CI is depth value, if n+m is less than CI*H*W, then presses preset strategy
The quantity of quantity and pressure value to the acceleration value adds n '+m '=CI*H*W so that after addition.
Optionally, AP210 is specifically used in n+m=CI*H*W/2, a line insert number is inserted into every line in the directions H
According to the insertion data are the average value in the rectangular adjacent rows of H.Specifically, such as the data that insertion is the 2nd row of the directions H, then it is inserted into
Data are the average value of the directions H the 1st row and the 3rd row.
The principle of drop stamping die type is described below, falls the operation that model largely belongs to artificial intelligence, for artificial intelligence
The most of calculating using neural network of calculating of energy, the operation for neural network, although its operation with multilayer,
But basic operation is convolution algorithm.
As shown in Figure 3a, it is a kind of schematic diagram of convolution algorithm, as shown in Figure 3a, input data can be the three of CI*H*W
Dimension data can be the convolved data of CO*CI*3*3 for weights, that is, convolution kernel of convolution algorithm, and the result of output can be with
For：As a result, as shown in Figure 3a, each grid is a numerical value, which, which is specifically as follows, adds for the output of CO* (H-2) * (W-2)
A value in the quantity n of the velocity amplitude or quantity m of pressure value.
According to Fig. 3 a, the Computing Principle of neural network is introduced, in the operation of neural network, that is, artificial intelligence, instructing
The artificial intelligence model perfected passes through the default input data defined and obtains weight data by trained operation, trains
Artificial intelligence model be determining convolution kernel, i.e. CO*CI*3*3, for core kernel, with 3*3 and 5*5
Specification (SIZE), certainly in practical applications, above-mentioned weights can also be other specifications, and the application be not intended to limit above-mentioned rule
The concrete form of lattice.
For training operation, i.e., by more parts of input data CI*H*W, in actual training, more parts of input datas CI, H, W
Value can be different, the multilayer forward operation for executing neural network is exported as a result, being obtained according to output result defeated
Go out result gradient, output result gradient, which is then executed the reversed operation of multilayer, obtains every layer of weights gradient, then passes through weights
Gradient is updated every layer of weights, and the calculating by multiple iteration obtains final weights, neural network at this time
Model is trained neural network model.Input the input data of acquisition again for this trained neural network model
Output result i.e. CO* (H-2) * (W-2) that forward operation obtains is carried out, it can by analyzing CO* (H-2) * (W-2)
Corresponding classification is obtained, is applied in the application, it can be by obtaining final falling original to CO* (H-2) * (W-2) analyses
Cause.
When for convolution algorithm, for convolution kernel, that is, CO*CI*3*3 be can not directly with input data i.e. CI*H*W it is direct
Convolution algorithm is carried out, the mode of operation can be that convolution kernel, that is, CO*CI*3*3 is cut into a kernel【3】【3】；
Then with kernel【3】【3】Convolution algorithm is executed for basic granularity and input data CI*H*W, i.e., with kernel【3】【3】For base
This granularity moves on the input data, and a kind of specific mobile schematic diagram of mode is as shown in Figure 3b, wherein such as the box in 3b
For the data of the cutting after movement.It is tested and is found by the applicant, for different neural network models, input data
The quantity of size, the i.e. value of CI*H*W and the default input data in trained model exports the calculating of result closer to it and gets over
Accurately, user experience is better.
Illustrated with an actual example, it is assumed that the default input data of trained neural network model can be：H
=50, W=50, CI=64, if that obtain value very little for collected input data, it is assumed that the three-dimensional data of composition is：H=
20, W=20, CI=12, then the number no matter trained, more, weights are more accurate, the output result calculated obtain fall
The precision for falling result is very low, is found through experiments that, i.e. the number and the cutting times of default input data of convolution cutting are inclined
Difference is bigger, then the precision of its obtained output result is lower, for example, H, W in H=50, W=50, CI=64 in one layer of CI
Cutting times be：48*48；Cutting times for H, W in one layer of CI of the input data of acquisition are：10*10 is calculated
Quantity is also mutually far short of what is expected, so in order to solve this problem, technical solution provided by the present application passes through preset strategy addition element
It is worth (i.e. the quantity of square), specific preset strategy can be to carry out the addition of data by way of addition zero, so i.e.
Corresponding value can be reached by zero-adding, specifically, as shown in Figure 3c, original input data is：H=9, W=7, CI=
4, the H=18 of preset input data, W=7, CI=4；The mode of so its addition zero can be, in a manner of interlacing zero insertion
It is inserted into original input data, the data after specific insertion are as shown in Figure 3d, and the black interval in Fig. 3 d is to be inserted into
The position of zero.
Certainly in practical applications, above-mentioned preset strategy can also be to be added in a manner of average value, black by taking Fig. 3 d as an example
Color section is the position for the average value being inserted into, and wherein the average value is the average value between two adjacent values of the directions H, for example, H
7 numerical value of the second row of direction can be the average value of 7 numerical value of the directions H the first row and 7 numerical value of the third line, corresponding
, the value of last column of insertion, the i.e. value of the 18th row of the directions H can be identical value with the 17th row value.It is found through experiments that,
By the way of average value, the precision higher of the output data that is calculated than the output result that zero insertion mode is calculated.
A kind of model update method that falls of electronic device is provided refering to Fig. 4, Fig. 4, the method is applied to electronic device
Interior, the electronic device includes：Application processor AP, touching display screen, gravity sensor and range sensor, the touch-control are aobvious
Display screen is connect by least one circuit with the application processor；As shown in figure 4, the method includes：
Step S401, the acceleration information of the electronic device is acquired；
Step S402, acquisition electronic device is at a distance from ground；
Step S403, acceleration value is calculated according to acceleration information, the electronic device is determined according to the acceleration value
The state being in, the state include：Normal state and fall state；
Step S404, acceleration value and distance value under state, the acceleration value that will fall under state are fallen in extraction
And distance value forms the first input data, by first input data input first fall model carry out being calculated first it is defeated
Go out and falls mould as a result, falling model progress re -training using first input data as training data pair first and obtaining second
Type, by the first input data be input to second fall model obtain the second output as a result, by first output result with second output
Results contrast, such as the second output result are more than the first output and fall model as a result, falling model using second and replacing first.
Refering to Fig. 5, Fig. 5 provides a kind of electronic device, and the electronic device includes：Shell, circuit board, battery, cover board, again
Force snesor 504, touching display screen 503, range sensor 501 and processing unit 502, wherein
Gravity sensor 504, the acceleration information for acquiring the electronic device；
Pressure sensor 501, for acquiring electronic device at a distance from ground；
Processing unit 502 determines the electricity for acceleration value to be calculated according to acceleration information according to the acceleration value
The state that sub-device is in, the state include：Normal state and fall state；
Processing unit 502 will fall should add under state for extracting the acceleration value and distance value that fall under state
Velocity amplitude and distance value form the first input data, and model is fallen in first input data input first to be calculated
First output is fallen as a result, falling model progress re -training using first input data as training data pair first and obtaining second
Stamping die type, is input to second by the first input data and falls model and obtain the second output as a result, by the first output result with second
Results contrast is exported, such as the second output result is more than the first output and falls model as a result, falling model using second and replacing first.
After technical solution provided by the present application collects acceleration information, acceleration value is calculated according to acceleration information,
The pressure value for acquiring shell, when being determined as falling state, the acceleration figure and pressure value of state are fallen in extraction, by the acceleration
Value and pressure value form input data, which is input in artificial nerve network model and carries out that output is calculated
As a result, this makes it possible to obtain electronic device according to the output result to fall reason.
Fig. 6 shows the block diagram with the part-structure of the relevant mobile phone of mobile terminal provided by the embodiments of the present application.Ginseng
Fig. 6 is examined, mobile phone includes：Radio frequency (Radio Frequency, RF) circuit 910, memory 920, input unit 930, sensor
950, voicefrequency circuit 960, Wireless Fidelity (Wireless Fidelity, WiFi) module 970, application processor AP980 and
The components such as power supply 990.It will be understood by those skilled in the art that handset structure shown in Fig. 6 does not constitute the restriction to mobile phone,
May include either combining certain components or different components arrangement than illustrating more or fewer components.
Each component parts of mobile phone is specifically introduced with reference to Fig. 6：
Input unit 930 can be used for receiving the number or character information of input, and generate with the user setting of mobile phone with
And the related key signals input of function control.Specifically, input unit 930 may include touching display screen 933, fingerprint identification device
931, face identification device 936, iris identification device 937 and other input equipments 932.Input unit 930 can also include
Other input equipments 932.Specifically, other input equipments 932 can include but is not limited to physical button, function key (such as sound
Measure control button, switch key etc.), it is trace ball, mouse, one or more in operating lever etc..Wherein,
Sensor 950, the acceleration information and mobile phone for acquiring the electronic device described will add at a distance from ground
Speed data and distance value are transferred to AP980.
AP980 determines the electronic device for acceleration value to be calculated according to acceleration information according to the acceleration value
The state being in, the state include：Normal state and fall state；Acceleration value and distance value under state are fallen in extraction,
The acceleration value and distance value for falling under state are formed into the first input data, first input data input first is fallen
Stamping die type carries out that the first output is calculated to be carried out as a result, first input data is fallen model as training data pair first
Re -training obtains second and falls model, by the first input data be input to second fall model obtain the second output as a result, will
First output result and the second output results contrast, such as the second output result are more than the first output as a result, falling mould using second
Type replaces first and falls model.
AP980 is the control centre of mobile phone, using the various pieces of various interfaces and connection whole mobile phone, passes through fortune
Row executes the software program and/or module being stored in memory 920, and calls the data being stored in memory 920,
The various functions and processing data for executing mobile phone, to carry out integral monitoring to mobile phone.Optionally, AP980 may include one or
Multiple processing units；Optionally, AP980 can integrate application processor and modem processor, wherein application processor is main
Processing operation system, user interface and application program etc., modem processor mainly handle wireless communication.It is appreciated that
It is that above-mentioned modem processor can not also be integrated into AP980.
In addition, memory 920 may include high-speed random access memory, can also include nonvolatile memory, example
Such as at least one disk memory, flush memory device or other volatile solid-state parts.
RF circuits 910 can be used for sending and receiving for information.In general, RF circuits 910 include but not limited to antenna, at least one
A amplifier, transceiver, coupler, low-noise amplifier (Low Noise Amplifier, LNA), duplexer etc..In addition,
RF circuits 910 can also be communicated with network and other equipment by radio communication.Above-mentioned wireless communication can use any communication
Standard or agreement, including but not limited to global system for mobile communications (Global System of Mobile
Communication, GSM), general packet radio service (General Packet Radio Service, GPRS), code it is point more
Location (Code Division Multiple Access, CDMA), wideband code division multiple access (Wideband Code Division
Multiple Access, WCDMA), long term evolution (Long Term Evolution, LTE), Email, short message service
(Short Messaging Service, SMS) etc..
Mobile phone may also include at least one sensor 950, such as optical sensor, motion sensor and other sensors.
Specifically, optical sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can be according to ambient light
Light and shade adjust the brightness of touching display screen, proximity sensor can when mobile phone is moved in one's ear, close touching display screen and/
Or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (generally three axis) acceleration
Size can detect that size and the direction of gravity when static, can be used to identify mobile phone posture application (such as horizontal/vertical screen switching,
Dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；It can also configure as mobile phone
The other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, details are not described herein.
Voicefrequency circuit 960, loud speaker 961, microphone 962 can provide the audio interface between user and mobile phone.Audio-frequency electric
The transformed electric signal of the audio data received can be transferred to loud speaker 961 by road 960, and sound is converted to by loud speaker 961
Signal plays；On the other hand, the voice signal of collection is converted to electric signal by microphone 962, is turned after being received by voicefrequency circuit 960
It is changed to audio data, then after audio data is played AP980 processing, through RF circuits 910 to be sent to such as another mobile phone, or
Audio data is played to memory 920 to be further processed.
WiFi belongs to short range wireless transmission technology, and mobile phone can help user's transceiver electronics postal by WiFi module 970
Part, browsing webpage and access streaming video etc., it has provided wireless broadband internet to the user and has accessed.Although Fig. 6 is shown
WiFi module 970, but it is understood that, and it is not belonging to must be configured into for mobile phone, it can not change as needed completely
Become in the range of the essence of application and omits.
Mobile phone further includes the power supply 990 (such as battery) powered to all parts, and optionally, power supply can pass through power supply pipe
Reason system and AP980 are logically contiguous, to realize the work(such as management charging, electric discharge and power managed by power-supply management system
Energy.
Although being not shown, mobile phone can also be including camera, bluetooth module, light compensating apparatus, light sensor etc., herein not
It repeats again.
As can be seen that by the embodiment of the present application, after collecting acceleration information, electronics is determined according to acceleration information
The state of device, when being determined as falling state, by camera acquire ground the first picture, then according to acceleration value with
And acquisition time obtains the distance on the ground of electronic device, the second picture for extracting electronic device (is specifically as follows outline drawing
Piece), this makes it possible to generate the 3D animations for dropping into ground with electronic device, improve the Experience Degree of user.
The embodiment of the present application also provides a kind of computer storage media, wherein computer storage media storage is for electricity
The computer program that subdata exchanges, it is any as described in above method embodiment which so that computer is executed
A kind of electronic device falls some or all of model update method step.
The embodiment of the present application also provides a kind of computer program product, and the computer program product includes storing calculating
The non-transient computer readable storage medium of machine program, the computer program are operable to that computer is made to execute such as above-mentioned side
Any type electronic device described in method embodiment falls some or all of model update method step.
It should be noted that for each method embodiment above-mentioned, for simple description, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, certain steps can be performed in other orders or simultaneously.Secondly, those skilled in the art should also know
It knows, embodiment described in this description belongs to alternative embodiment, involved action and module not necessarily the application
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, for example, the unit division, it is only a kind of
Division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING or communication connection of device or unit,
Can be electrical or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the application can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of software program module.
If the integrated unit is realized in the form of software program module and sells or use as independent product
When, it can be stored in a computer-readable access to memory.Based on this understanding, the technical solution of the application substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a memory, including some instructions are used so that a computer equipment
(can be personal computer, server or network equipment etc.) executes all or part of each embodiment the method for the application
Step.And memory above-mentioned includes：USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer-readable memory, memory
May include：Flash disk, read-only memory (English：Read-Only Memory, referred to as：ROM), random access device (English：
Random Access Memory, referred to as：RAM), disk or CD etc..
The embodiment of the present application is described in detail above, specific case used herein to the principle of the application and
Embodiment is expounded, the description of the example is only used to help understand the method for the present application and its core ideas；
Meanwhile for those of ordinary skill in the art, according to the thought of the application, can in specific embodiments and applications
There is change place, in conclusion the contents of this specification should not be construed as limiting the present application.
Claims (11)
1. a kind of electronic device, the electronic device include：Application processor AP, touching display screen, gravity sensor and distance
Sensor, which is characterized in that
The gravity sensor, the acceleration information for acquiring the electronic device；
The range sensor, for acquiring electronic device at a distance from ground；
The AP is determined according to the acceleration value at the electronic device for acceleration value to be calculated according to acceleration information
In state, which includes：Normal state and fall state；
The AP, for extracting the acceleration value and distance value that fall under state, by the acceleration value fallen under state with
And distance value forms the first input data, model is fallen in first input data input first carries out that the first output is calculated
Fall model as a result, falling model progress re -training using first input data as training data pair first and obtaining second,
By the first input data be input to second fall model obtain the second output as a result, by first output result with second output result
Compare, such as the second output result is more than the first output and falls model as a result, falling model using second and replacing first.
2. electronic device according to claim 1, which is characterized in that the electronic device further includes：Communication module；
The AP is additionally operable to control communication module and the weight data that described second falls model is sent to network side equipment.
3. electronic device according to claim 1, which is characterized in that
The AP is specifically used for if any n acceleration value, and by n acceleration value of order traversal of collection point, such as continuous m add
Velocity amplitude is more than given threshold, is determined as falling state, is otherwise determined as normal state.
4. electronic device according to claim 3, which is characterized in that
The AP executes V layers of positive fortune specifically for first input data is fallen model as training data input first
The V layer forward operation for obtaining forward operation is calculated as a result, obtaining V layer input data ladder to V layer forward operation result treatment
V layer input data gradient is input to the V layer V layers of reversed operation of execution that first falls model and obtains V weights ladder by degree
Degree, is updated V layers of weights using V weights gradient weight data after being updated, updated weight data is determined
The weight data for falling model for second.
5. a kind of electronic device falls model update method, the method is applied in electronic device, the electronic device packet
It includes：Application processor AP, touching display screen, gravity sensor and range sensor, which is characterized in that the method includes：
Acquire the acceleration information of the electronic device；
Electronic device is acquired at a distance from ground；
Acceleration value is calculated according to acceleration information, the state that the electronic device is in is determined according to the acceleration value, it should
State includes：Normal state and fall state；
Acceleration value and distance value under state are fallen in extraction, and the acceleration value and distance value for falling under state are formed
First input data, by first input data input first fall model carry out that the first output is calculated as a result, by this
One input data, which as training data pair first falls model and carries out re -training, to be obtained second and falls model, and number is inputted by first
According to be input to second fall model obtain the second output as a result, by first output result with second output results contrast, such as second
Output result is more than the first output and falls model as a result, falling model using second and replacing first.
6. according to the method described in claim 5, it is characterized in that, the method further includes：
The weight data that described second falls model is sent to network side equipment.
7. described true according to the acceleration value according to the method described in claim 5, it is characterized in that, if any n acceleration value
The state that the fixed electronic device is in, including：
By n acceleration value of order traversal of collection point, such as continuous m acceleration value is more than given threshold, is determined as falling shape
Otherwise state is determined as normal state.
8. the method according to the description of claim 7 is characterized in that described using first input data as training data pair
One, which falls model, carries out re -training and obtains second and fall model, including：
First input data is fallen into V layers of forward operation of model execution as training data input first and obtains forward operation
V layer forward operation to V layer forward operation result treatment as a result, obtain V layer input data gradient, by V layer input number
It is input to the V layer V layers of reversed operation of execution that first falls model according to gradient and obtains V weights gradient, using V weights gradient
V layers of weights are updated with weight data after being updated, updated weight data is determined as the second power for falling model
Value Data.
9. a kind of electronic device, the electronic device include：Processing unit, touching display screen, gravity sensor, circuit and distance
Sensor, which is characterized in that
The gravity sensor, the acceleration information for acquiring the electronic device；
The range sensor, for acquiring electronic device at a distance from ground；
The processing unit determines the electronics for acceleration value to be calculated according to acceleration information according to the acceleration value
The state that device is in, the state include：Normal state and fall state；
The processing unit, for extracting the acceleration value and distance value that fall under state, the acceleration that will fall under state
Angle value and distance value form the first input data, and model is fallen in first input data input first be calculated the
One output is fallen as a result, falling model progress re -training using first input data as training data pair first and obtaining second
Model, is input to second by the first input data and falls model and obtain the second output as a result, by the first output result and second defeated
Go out results contrast, such as the second output result is more than the first output and falls model as a result, falling model using second and replacing first.
10. a kind of computer readable storage medium, which is characterized in that it stores the computer program for electronic data interchange,
Wherein, the computer program makes computer execute such as claim 5-8 any one of them methods.
11. a kind of computer program product, which is characterized in that the computer program product includes storing computer program
Non-transient computer readable storage medium, the computer program are operable to that computer is made to execute such as claim 5-8
Method described in one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810045061.8A CN108307049B (en) | 2018-01-17 | 2018-01-17 | Drop model updating method of electronic device and related product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810045061.8A CN108307049B (en) | 2018-01-17 | 2018-01-17 | Drop model updating method of electronic device and related product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108307049A true CN108307049A (en) | 2018-07-20 |
| CN108307049B CN108307049B (en) | 2020-07-03 |
Family
ID=62865737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810045061.8A Expired - Fee Related CN108307049B (en) | 2018-01-17 | 2018-01-17 | Drop model updating method of electronic device and related product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108307049B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242554A (en) * | 2018-08-24 | 2019-01-18 | 深圳艺达文化传媒有限公司 | The switching method and Related product of elevator card |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201533351U (en) * | 2009-05-19 | 2010-07-21 | 上海闻泰电子科技有限公司 | Device for snapping dropping surface under free falling situation of mobile phone |
| US20150061863A1 (en) * | 2013-09-03 | 2015-03-05 | Hti Ip, L.L.C. | Adaptive classification of fall detection for personal emergency response systems |
| CN106021007A (en) * | 2016-05-20 | 2016-10-12 | 深圳天珑无线科技有限公司 | Method for detecting fault of terminal and terminal |
| CN106453767A (en) * | 2016-09-06 | 2017-02-22 | 广东欧珀移动通信有限公司 | Method and device for detecting failure after dropping |
| CN106534579A (en) * | 2016-12-12 | 2017-03-22 | 北京羲和科技有限公司 | Mobile phone posture judging method and apparatus based on deep learning |
| US20170147921A1 (en) * | 2015-11-24 | 2017-05-25 | Ryosuke Kasahara | Learning apparatus, recording medium, and learning method |
| CN107153871A (en) * | 2017-05-09 | 2017-09-12 | 浙江农林大学 | Fall detection method based on convolutional neural networks and mobile phone sensor data |
| CN107271083A (en) * | 2017-06-26 | 2017-10-20 | 上海斐讯数据通信技术有限公司 | A kind of method that sensor and terminal and detection terminal are fallen |
| CN107301454A (en) * | 2016-04-15 | 2017-10-27 | 北京中科寒武纪科技有限公司 | The artificial neural network reverse train apparatus and method for supporting discrete data to represent |
| US20170352240A1 (en) * | 2016-06-03 | 2017-12-07 | John Carlton-Foss | Method and system for motion analysis and fall prevention |
-
2018
- 2018-01-17 CN CN201810045061.8A patent/CN108307049B/en not_active Expired - Fee Related
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201533351U (en) * | 2009-05-19 | 2010-07-21 | 上海闻泰电子科技有限公司 | Device for snapping dropping surface under free falling situation of mobile phone |
| US20150061863A1 (en) * | 2013-09-03 | 2015-03-05 | Hti Ip, L.L.C. | Adaptive classification of fall detection for personal emergency response systems |
| US20170147921A1 (en) * | 2015-11-24 | 2017-05-25 | Ryosuke Kasahara | Learning apparatus, recording medium, and learning method |
| CN107301454A (en) * | 2016-04-15 | 2017-10-27 | 北京中科寒武纪科技有限公司 | The artificial neural network reverse train apparatus and method for supporting discrete data to represent |
| CN106021007A (en) * | 2016-05-20 | 2016-10-12 | 深圳天珑无线科技有限公司 | Method for detecting fault of terminal and terminal |
| US20170352240A1 (en) * | 2016-06-03 | 2017-12-07 | John Carlton-Foss | Method and system for motion analysis and fall prevention |
| CN106453767A (en) * | 2016-09-06 | 2017-02-22 | 广东欧珀移动通信有限公司 | Method and device for detecting failure after dropping |
| CN106534579A (en) * | 2016-12-12 | 2017-03-22 | 北京羲和科技有限公司 | Mobile phone posture judging method and apparatus based on deep learning |
| CN107153871A (en) * | 2017-05-09 | 2017-09-12 | 浙江农林大学 | Fall detection method based on convolutional neural networks and mobile phone sensor data |
| CN107271083A (en) * | 2017-06-26 | 2017-10-20 | 上海斐讯数据通信技术有限公司 | A kind of method that sensor and terminal and detection terminal are fallen |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242554A (en) * | 2018-08-24 | 2019-01-18 | 深圳艺达文化传媒有限公司 | The switching method and Related product of elevator card |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108307049B (en) | 2020-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103576578B (en) | Method, device and equipment for adopting earphone wire to control terminal | |
| CN107122760B (en) | Fingerprint identification method and Related product | |
| CN107292237A (en) | The acquisition method and Related product of fingerprint | |
| CN106066767A (en) | A kind of unlocking method and mobile terminal | |
| CN109408303A (en) | Test data analysis method and Related product | |
| CN107967129A (en) | Display control method and related product | |
| CN106505699B (en) | Charge control method, device and terminal | |
| CN105447583A (en) | User churn prediction method and device | |
| CN105335653A (en) | Abnormal data detection method and apparatus | |
| CN107302628A (en) | The control method and Related product of application function | |
| CN106951850A (en) | The method and mobile terminal of a kind of control fingerprint recognition module | |
| CN104091600B (en) | A kind of song method for detecting position and device | |
| CN108307051A (en) | Electronic device, collision data processing method and related product | |
| CN103869977B (en) | Method for displaying image, device and electronics | |
| CN108255632A (en) | Method for computing data and Related product are fallen based on artificial intelligence | |
| CN107707618A (en) | Method and Related product based on position adjustment download | |
| CN108307049A (en) | Electronic device falls model update method and Related product | |
| CN108989546A (en) | The proximity test method and Related product of electronic device | |
| CN110456923A (en) | A kind of posture sensing data processing method and electronic equipment | |
| CN110246561A (en) | A kind of moving distance calculation method, device and system | |
| CN108037874A (en) | Screenshotss method and Related product | |
| CN108121583A (en) | Screenshotss method and Related product | |
| CN108307057A (en) | Fall the analysis method and Related product of data | |
| CN108845261A (en) | A kind of electric quantity reminding method and terminal device | |
| CN108111677A (en) | The touching display screen display methods and Related product of electronic device |
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 | ||
| CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: 523860 No. 18 Wusha Haibin Road, Chang'an Town, Dongguan City, Guangdong Province Applicant before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200703 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |