CN108897757A - A kind of photo storage method, storage medium and server - Google Patents
A kind of photo storage method, storage medium and server Download PDFInfo
- Publication number
- CN108897757A CN108897757A CN201810456993.1A CN201810456993A CN108897757A CN 108897757 A CN108897757 A CN 108897757A CN 201810456993 A CN201810456993 A CN 201810456993A CN 108897757 A CN108897757 A CN 108897757A
- Authority
- CN
- China
- Prior art keywords
- photo
- value
- shooting
- category attribution
- storage folder
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The present invention provides a kind of photo storage method, storage medium and servers, including：Obtain the shooting attribute of photo；According to the shooting attribute and preset attribute weight of the photo, the category attribution value of the photo is calculated；The corresponding photo storage folder of category attribution value described in the preset classification table of comparisons is searched, and the photo is stored in the corresponding photo storage folder of the category attribution value；If searching photo storage folder corresponding less than the category attribution value, a store path, the corresponding new photo storage folder of the store path are automatically generated, and the photo is stored in the new photo storage folder.The present invention compares piece classification storage without user manually, can save the time of user, improves the efficiency of photo storage.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of photo storage methods, storage medium and server.
Background technique
With the development of science and technology, the volume for having the mobile terminals such as mobile phone, the digital camera of camera function is more and more frivolous,
The photographic quality taken also is become better and better.People often carry the intelligent terminal with camera function, to clap at any time
Take the photograph photo.
However, usually storing clapped photo according to shooting time at present with the intelligent terminal of camera function, having
It can also be classified according to the APP of photo origin, but all cannot be classified and be stored automatically according to the information in photo.When
When user needs to filter out the photo including same photograph information from a large amount of photos, it can only be searched one by one by manual operation
Identification, to waste a large amount of manpower and time.
Summary of the invention
The embodiment of the invention provides a kind of photo storage method, storage medium and servers, to solve in the prior art,
When user needs to filter out the photo including same photograph information from a large amount of photos, can only be looked into one by one by manual operation
Identification is looked for, thus the problem of wasting a large amount of manpower and time.
The first aspect of the embodiment of the present invention provides a kind of photo storage method, including：
Obtain the shooting attribute of photo；
According to the shooting attribute and preset attribute weight of the photo, the category attribution value of the photo is calculated；
Search the corresponding photo storage folder of category attribution value described in the preset classification table of comparisons, and by the photo
It is stored in the corresponding photo storage folder of the category attribution value；
If searching photo storage folder corresponding less than the category attribution value, a store path, institute are automatically generated
The corresponding new photo storage folder of store path is stated, and the photo is stored in the new photo storage folder.
The second aspect of the embodiment of the present invention provides a kind of server, including memory and processor, the storage
Device is stored with the computer program that can be run on the processor, and the processor is realized such as when executing the computer program
Lower step：
Obtain the shooting attribute of photo；
According to the shooting attribute and preset attribute weight of the photo, the category attribution value of the photo is calculated；
Search the corresponding photo storage folder of category attribution value described in the preset classification table of comparisons, and by the photo
It is stored in the corresponding photo storage folder of the category attribution value；
If searching photo storage folder corresponding less than the category attribution value, a store path, institute are automatically generated
The corresponding new photo storage folder of store path is stated, and the photo is stored in the new photo storage folder.
The third aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the computer program realizes following steps when being executed by processor：
Obtain the shooting attribute of photo；
According to the shooting attribute and preset attribute weight of the photo, the category attribution value of the photo is calculated；
Search the corresponding photo storage folder of category attribution value described in the preset classification table of comparisons, and by the photo
It is stored in the corresponding photo storage folder of the category attribution value；
If searching photo storage folder corresponding less than the category attribution value, a store path, institute are automatically generated
The corresponding new photo storage folder of store path is stated, and the photo is stored in the new photo storage folder.
In the embodiment of the present invention, by obtaining the shooting attribute of photo, according to the shooting attribute of the photo and preset
Attribute weight calculates the category attribution value of the photo, then searches category attribution value pair described in the preset classification table of comparisons
The photo storage folder answered, and the photo is stored in the corresponding photo storage folder of the category attribution value, if looking into
It can not find the corresponding photo storage folder of the category attribution value, automatically generate a store path, the store path pair
A new photo storage folder is answered, and the photo is stored in the new photo storage folder, when shooting completion
Photo classification can be stored, compare piece classification storage manually without user, save the time of user, and improved photo and deposit
The efficiency of storage.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation flow chart of photo storage method provided in an embodiment of the present invention；
Fig. 2 is the specific implementation flow chart of photo storage method S102 provided in an embodiment of the present invention；
Fig. 3 is the specific implementation flow chart of photo storage method B2 provided in an embodiment of the present invention；
Fig. 4 is the specific implementation flow chart of photo storage method S103 provided in an embodiment of the present invention；
Fig. 5 be another embodiment of the present invention provides photo storage method implementation flow chart；
Fig. 6 is the structural block diagram of photo storage device provided in an embodiment of the present invention；
Fig. 7 be another embodiment of the present invention provides photo storage device structural block diagram；
Fig. 8 is the schematic diagram of server provided in an embodiment of the present invention.
Specific embodiment
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
Those of ordinary skill's all other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
Fig. 1 shows the implementation process of photo storage method provided in an embodiment of the present invention, and this method process includes step
S101 to S104.The specific implementation principle of each step is as follows：
S101：Obtain the shooting attribute of photo.
Specifically, the shooting attribute includes shooting time, shooting location and photo type.Wherein, photo type includes
Personage is shone, food shines, landscape shines and two dimensional code.
In embodiments of the present invention, the shooting attribute of photo can be made by oneself according to the user for using intelligent terminal to shoot photo
Adopted label determines.For example, 10 points of January 20 in 2018, one self-timer face of shooting of being in shines, and wherein shooting location can pass through use
The customized location label in family, such as defining geographical location is family, work unit or certain sight spot.User may be same in every day
A time same place shoots photo, for example, in the two-dimension code image of parking lot shooting when going to work.
Optionally, the location information of intelligent terminal is counted by big data to determine shooting location, for example, pressing work for one day
Make the period and time of having a rest section be split, for example, 9 points of morning to afternoon 6 points be working time section, ten one points extremely at night
6 points of the next morning, be time of having a rest section.Intelligent terminal is obtained in preset working day, the geographical position of each period
Set, add up at the same time section the same geographical location total duration, by the longest geographical location of working time section total duration
Place marks be work unit, the place marks by time of having a rest section total duration longest geographical location are family.
Optionally, the geographical location of intelligent terminal in preset working day is subjected to clustering.It specifically, will be preset
In working day, the geographical location deposit working time set of all working period randomly selects the geography of the first specified number
Position is the first cluster centre, calculates the distance value in each geographical location and the first cluster centre in working time set, root
According to the distance value and specified cluster centre of calculating, the geographical location in working time set is subjected to initial clustering, from complete
At the geographical location for choosing the second specified number in the geographical location after initial clustering again as the second cluster centre, will complete just
Begin cluster after geographical location centered on the second cluster centre cluster clustered, and so on, until the working time collection
Cluster centre convergence in conjunction, the location label for the cluster centre (geographical location) that the working time gathers after definition convergence are work
Unit.According to above-mentioned same method, the location label for the cluster centre (geographical location) that the working time gathers after definition convergence
For family.It should be noted that shooting location not only includes work unit and family, it further include parking lot, school etc., for other shootings
Place can equally be determined according to the above method.
It optionally, can be by the way that photo be input to trained convolutional neural networks model for the photo type of photo
Middle determination.Specifically, the characteristics of image of the photo of extraction is input to the convolution trained by the characteristics of image for extracting the photo
The input layer of neural network model exports the photo type of the photo in output layer.The trained convolutional neural networks
Model is obtained according to following steps：
A1：The sample photo of setting quantity is obtained, the sample photo is previously provided with type label.Specifically, by obtaining
The sample photo of setting quantity is taken, which is all previously provided with such as landscape, personage, food, two dimensional code label.
A2：Foundation includes the convolutional neural networks model of input layer, convolutional layer, full articulamentum and output layer.
A3：When training for the first time, by the network connection weight and threshold between each node layer of convolutional neural networks model
Value is predisposed to the random value for meeting preset condition, and sets the idea output of the sample photo, from the setting number
Sample photo is randomly selected in the sample photo of amount, is input to input layer, by convolutional layer and full articulamentum, is transmitted to output
Layer obtains the real output value of the sample photo, completes a wheel training, and calculate the difference of real output value and idea output
Value.
A4：According to the difference of calculating, according to specified learning rules to the network connection weight and threshold between each node layer
Value is adjusted, and is trained again to convolutional neural networks model, until when the difference of calculating is not more than preset threshold value,
Training is completed, trained convolutional neural networks model is obtained.
Specifically, foundation includes the convolutional neural networks model of input layer, convolutional layer, full articulamentum and output layer, training
It is point as follows, randomly select sample input convolutional neural networks model from sample photo, the output valve of calculating sample photo, and
Only in first time training, the network connection weight between each node layer of convolutional neural networks model, threshold value are predisposed to
It is small close to 0 random value, and set the idea output of sample photo, by sample photo from input layer by convolutional layer and
Full articulamentum, is transmitted to output layer, obtains the real output value of the sample photo, completes a wheel training, calculates real output value
With the difference of idea output.In embodiments of the present invention, the global difference of the convolutional neural networks is calculated according to the following formula
D：
Wherein, DtFor the idea output I of t sample photostWith real output value RtDifference, n is positive integer, and n
For the quantity sum for the sample photo being trained.Weight matrix is adjusted by the method for minimization error.Step-up error threshold value, if D
Greater than the threshold value, then according to Delta learning rules between each node layer network connection weight and threshold value be adjusted, then
Convolutional neural networks model is trained again, until network global error D no more than until the threshold value, terminates training, it will
The weight and threshold value of this time training save the optimal model parameters as the convolutional neural networks, obtain trained convolutional Neural
Network model.Wherein, the learning signal of Delta learning rules is defined as：R=(dj-f (wTjx)) f ' (wTjx)=(dj-oj))
f′(netj)。
In embodiments of the present invention, it is carried out by the way that the sample photo of the setting quantity is input to convolutional neural networks model
Training, determines the optimal model parameters of the neural network model, to obtain trained convolutional neural networks model, pass through by
The photo of shooting be input to trained convolutional neural networks model can photo described in quick obtaining photo type, Jin Erti
The efficiency of high photo classification storage.
S102：According to the shooting attribute and preset attribute weight of the photo, the category attribution value of the photo is calculated.
Specifically, each shooting attribute corresponds to a kind of preset attribute weight, for example, shooting location corresponds to presetly
Point weight, shooting time correspond to preset time weighting, and photo type corresponds to preset type weight.According to the bat of the photo
Attribute and preset attribute weight are taken the photograph, the categorical attribute value of the photo is calculated, thus by the shooting attribute value of the photo
Change, convenient for storing the photo classification.
As an embodiment of the present invention, as shown in Fig. 2, above-mentioned S102 is specifically included：
B1：Establish three-dimensional system of coordinate.
B2：According to the corresponding attribute weight of the shooting attribute, by the shooting time of the photo, shooting location and
Photo type maps in the three-dimensional system of coordinate, determines three-dimensional coordinate of the photo in the three-dimensional system of coordinate.Specifically
The shooting attribute of the photo is mapped as any in the three-dimensional system of coordinate by ground.
B3：The distance value of the three-dimensional coordinate corresponding point and the three-dimensional system of coordinate origin of the photo is calculated, it will be described
Category attribution value of the distance value as the photo.
The embodiment of the present invention is by being mapped as a point in three-dimensional system of coordinate for photo, by the photo in the three-dimensional
The corresponding point of coordinate system to origin category attribution value of the distance value as the photo, by the shooting attribute value of the photo
Change, to carry out classification storage according to the category attribution value.
As an embodiment of the present invention, Fig. 3 shows photo storage method step B2 provided in an embodiment of the present invention
Specific implementation flow, details are as follows：
B21：Mapping table is preestablished, includes the different corresponding numerical value of shooting time, difference in the mapping table
The corresponding numerical value in shooting location and the corresponding numerical value of different photo types.Specifically, shooting time is by shooting day
Phase or shooting time are divided, and in the mapping table, if the shooting time is divided by shooting date, shoot day
Phase, corresponding numerical value was incremented by day by day by specified difference；If the shooting time is divided by shooting time, shooting time is drawn
It is divided into several periods, period, corresponding numerical value was incremented by paragraph by paragraph by specified difference.If shooting time section is for example, the morning
10 points of corresponding numerical value are 5, and 3 points of corresponding numerical value in afternoon are 8.For shooting location, the longitude and latitude of different shooting locations is not
It together, include the corresponding numerical value of different longitude and latitude in the mapping table in the mapping table.And shot type is by predefining
By the determining photo type of big data statistical analysis, and different numerical value is set for different photo types, if personage is according to being
10, it is 20 that landscape, which shines,.
B22：Shooting time, shooting location and the photo type that the photo is searched from the mapping table are respectively corresponded
Numerical value.
B23：According to the shooting time of the photo, shooting location and the photo type corresponding numerical value of institute and the category
Property weight, determines three-dimensional coordinate of the photo in the three-dimensional system of coordinate.Specifically, by the shooting time pair of the photo
The product of the numerical value and preset time weighting answered, as the value in the first reference axis in the three-dimensional system of coordinate, by the photograph
The product of the corresponding numerical value in the shooting location of piece and preset location weight is as in the second reference axis in the three-dimensional system of coordinate
Value, using the product of the corresponding numerical value of the photo type of the photo and preset type weight as in the three-dimensional system of coordinate
Value in third reference axis, to obtain three-dimensional coordinate of the photo in the three-dimensional system of coordinate.
S103：Search the corresponding photo storage folder of category attribution value described in the preset classification table of comparisons, and by institute
Photo is stated to be stored in the corresponding photo storage folder of the category attribution value.
It in embodiments of the present invention, include category attribution value and photo storage folder in the preset classification table of comparisons
The corresponding relationship of corresponding default value.
Specifically, Fig. 4 shows the specific implementation flow of photo storage method S103 provided in an embodiment of the present invention, is described in detail
It is as follows：
C1：The corresponding default value of each photo storage folder is obtained from the preset classification table of comparisons.
Specifically, the category attribution value that the corresponding default value of the photo storage folder can open photo according to deposit first determines.
C2：The category attribution value of the photo is compared one by one with the default value got, determining and institute
State the smallest default value of absolute difference of the category attribution value of photo.
C3：If it is determined that the default value and the category attribution value of the photo absolute difference be located at it is preset
Difference section then determines that the default value determined is matched with the category attribution value of the photo.Certainly, if it is described default
The absolute difference of the category attribution value of numerical value and the photo then determines to determine not within the preset difference section
The default value and the photo category attribution value mismatch.
C4：In the corresponding photo storage folder of the default value that photo deposit is determined.Specifically
The photo is stored in photo storage folder corresponding with the matched default value of category attribution value of the photo by ground.
S104：If searching photo storage folder corresponding less than the category attribution value, a storage road is automatically generated
Diameter, the corresponding new photo storage folder of the store path, and the photo is stored in the new photo and stores text
Part folder.
Specifically, the difference for defining the category attribution value of the default value and the photo is E, as E≤η, by this
Photo is stored in photo storage folder corresponding with the default value, as E > η, i.e., the described preset classification table of comparisons
In there is no being located at the default value in preset difference section with the absolute difference of the category attribution value of the photo, this
When, a store path is automatically generated, as soon as the store path corresponds to a new photo storage folder, file is after all
It is the store path of a file, i.e., by automatically generating a store path, creates a photo storage folder, and should
In the newly-built file of photo deposit.It should be noted that if searching photo storage file corresponding less than the category attribution value
Folder, it is not identical to automatically generate store path store path corresponding with existing photo storage folder.Further, will
Default value of the category attribution value of the photo as the photo storage file.
Optionally, for the photo of personage's type, according to the area value of the face in photo to photo further progress point
Class is taken pictures certainly for example, being further subdivided into.Specifically, row recognition of face is shone into personage, and calculates the area of the face of identification
Value determines the area value of face area ratio shared in the personage is shone, if the area ratio is greater than preset area ratio
Example threshold value, then further by the personage according to storing from file of taking pictures, so that user quickly shines into capable processing to self-timer.
Optionally, for the photo in the same photo storage folder, the similarity of photo can be calculated, according to photo
Similarity establishes the sub-folder of the photo storage folder, the photo that similarity is greater than default similarity threshold is stored in same
In one sub-folder.It is shone for example, the similarity for calculating photo judges whether it is same face, if so, being stored in the photo
Sub-folder is established in file, and the photo of same face is stored in the sub-folder.
In the embodiment of the present invention, by obtaining the shooting attribute of photo, according to the shooting attribute of the photo and preset
Attribute weight calculates the category attribution value of the photo, then searches category attribution value pair described in the preset classification table of comparisons
The photo storage folder answered, and the photo is stored in the corresponding photo storage folder of the category attribution value, if looking into
It can not find the corresponding photo storage folder of the category attribution value, automatically generate a store path, the store path pair
A new photo storage folder is answered, and the photo is stored in the new photo storage folder, when shooting completion
Photo classification can be stored, compare piece classification storage manually without user, save the time of user, and improved photo and deposit
The efficiency of storage.
Further, based on photo storage method provided in above-mentioned Fig. 1 embodiment, another implementation of the invention is proposed
Example.In embodiments of the present invention, on the basis of step S101-S104 shown in Fig. 1, as shown in figure 5, the photo storage side
Method further includes：
S201：Obtain the shooting attribute of photo.
S202：According to the shooting attribute and preset attribute weight of the photo, the category attribution value of the photo is calculated.
S203：Search the corresponding photo storage folder of category attribution value described in the preset classification table of comparisons, and by institute
Photo is stated to be stored in the corresponding photo storage folder of the category attribution value.
S204：If searching photo storage folder corresponding less than the category attribution value, a storage road is automatically generated
Diameter, the corresponding new photo storage folder of the store path, and the photo is stored in the new photo and stores text
Part folder.
In the present embodiment, the specific steps of step S201 to step S204 are referring to previous embodiment step S101 to step
S104, details are not described herein.
S205：By store the photo in the same photo storage folder by be stored in the photo storage folder when
Between line arrange.
S206：According to the timeline for being stored in the photo storage folder, using the photo of newest deposit this document folder as
The cover of the photo storage folder.
Specifically, the priority of shooting time is higher than photo type, and the priority of photo type is higher than shooting location, will be same
Photo in one photo storage folder is arranged by the timeline of deposit, when the photo storage folder is newly stored in photo
When, the photo being newly stored in is replaced to the cover of the photo storage folder, becomes the new cover of the photo storage folder,
Realize the cover according to shooting storage photo dynamic more new photo storage folder, user can be quickly clear without point open file folder
The photo type stored in Chu's file improves user experience.
In the embodiment of the present invention, by obtaining the shooting attribute of photo, according to the shooting attribute of the photo and preset
Attribute weight calculates the category attribution value of the photo, then searches category attribution value pair described in the preset classification table of comparisons
The photo storage folder answered, and the photo is stored in the corresponding photo storage folder of the category attribution value, if looking into
It can not find the corresponding photo storage folder of the category attribution value, automatically generate a store path, the store path pair
A new photo storage folder is answered, and the photo is stored in the new photo storage folder, when shooting completion
Photo classification can be stored, compare piece classification storage manually without user, save the time of user, and improved photo and deposit
The efficiency of storage, meanwhile, the photo in the same photo storage folder will be stored in by the deposit photo storage folder
Timeline arrangement, according to the timeline for being stored in the photo storage folder, using the photo of newest deposit this document folder as institute
The cover of photo storage folder is stated, dynamic updates cover, and user can quickly understand file memory without point open file folder
The photo type of storage improves user experience.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Corresponding to photo storage method described in foregoing embodiments, Fig. 6 shows photo provided by the embodiments of the present application and deposits
The structural block diagram of storage device illustrates only part relevant to the embodiment of the present application for ease of description.
Referring to Fig. 6, which includes：Attribute acquiring unit 61, ascribed value computing unit 62, the first storage are single
Member 63, the second storage unit 64, wherein：
Attribute acquiring unit 61, for obtaining the shooting attribute of photo；
Ascribed value computing unit 62, for the shooting attribute and preset attribute weight according to the photo, described in calculating
The category attribution value of photo；
First storage unit 63, for searching the corresponding photo storage of category attribution value described in the preset classification table of comparisons
File, and the photo is stored in the corresponding photo storage folder of the category attribution value；
Second storage unit 64, if for searching photo storage folder corresponding less than the category attribution value, automatically
Generate a store path, the corresponding new photo storage folder of the store path, and will be described in photo deposit
New photo storage folder.
Optionally, the ascribed value computing unit 62 includes：
Establishment of coordinate system module, for establishing three-dimensional system of coordinate；
Coordinate determining module is used for according to the corresponding attribute weight of the shooting attribute, by the shooting of the photo
Time, shooting location and photo type map in the three-dimensional system of coordinate, determine the photo in the three-dimensional system of coordinate
Three-dimensional coordinate；
Ascribed value determining module, the corresponding point of three-dimensional coordinate and the three-dimensional system of coordinate origin for calculating the photo
Distance value, using the distance value as the category attribution value of the photo.
Optionally, the coordinate determining module includes：
Default submodule includes that different shooting times respectively corresponds for preestablishing mapping table, in the mapping table
Numerical value, the corresponding numerical value in different shooting locations and the corresponding numerical value of different photo types；
Numerical value searches submodule, for searching shooting time, shooting location and the photograph of the photo from the mapping table
The corresponding numerical value of sheet type institute；
Coordinate determines submodule, for right respectively according to the shooting time of the photo, shooting location and photo type institute
The numerical value and the attribute weight answered, determine three-dimensional coordinate of the photo in the three-dimensional system of coordinate.
Optionally, first storage unit 63 includes：
First searching module, for obtaining each photo storage folder pair from the preset classification table of comparisons
The default value answered；
Numerical value comparison module, for carrying out one by one the category attribution value of the photo with the default value got
It compares, the determining the smallest default value of absolute difference with the category attribution value of the photo；
Determination module, for if it is determined that the default value and the photo category attribution value absolute difference
Positioned at preset difference section, then determine that the default value determined is matched with the category attribution value of the photo；
Memory module, for the photo to be stored in the corresponding photo storage file of the default value determined
In folder.
Optionally, the attribute acquiring unit 61 includes：
Characteristic extracting module, for extracting the characteristics of image of the photo；
Type output module, it is defeated for the characteristics of image of extraction to be input to trained convolutional neural networks model
The photo type of the photo out；
The trained convolutional neural networks model is obtained according to following steps：
The sample photo of setting quantity is obtained, the sample photo is previously provided with type label；
Foundation includes the convolutional neural networks model of input layer, convolutional layer, full articulamentum and output layer；
For the first time train when, by between each node layer of convolutional neural networks model network connection weight and threshold value it is pre-
First it is arranged to meet the random value of preset condition, and sets the idea output of the sample photo, from the setting quantity
Sample photo is randomly selected in sample photo, is input to input layer, by convolutional layer and full articulamentum, is transmitted to output layer, is obtained
The real output value of the sample photo is taken, completes a wheel training, and calculate the difference of real output value and idea output；
According to the difference of calculating, according to specified learning rules between each node layer network connection weight and threshold value into
Row adjustment, is again trained convolutional neural networks model, until completing when the difference of calculating is not more than preset threshold value
Training, obtains trained convolutional neural networks model.
Optionally, as shown in fig. 7, the photo storage device further includes：
Photo arrangement units 71, the photo for that will be stored in the same photo storage folder is by the deposit photo
The timeline of storage folder arranges；
Cover determination unit 72, for the timeline according to the deposit photo storage folder, by newest deposit this article
Cover of the photo of part folder as the photo storage folder.
In the embodiment of the present invention, by obtaining the shooting attribute of photo, according to the shooting attribute of the photo and preset
Attribute weight calculates the category attribution value of the photo, then searches category attribution value pair described in the preset classification table of comparisons
The photo storage folder answered, and the photo is stored in the corresponding photo storage folder of the category attribution value, if looking into
It can not find the corresponding photo storage folder of the category attribution value, automatically generate a store path, the store path pair
A new photo storage folder is answered, and the photo is stored in the new photo storage folder, when shooting completion
Photo classification can be stored, compare piece classification storage manually without user, save the time of user, and improved photo and deposit
The efficiency of storage.
Fig. 8 is the schematic diagram for the server that one embodiment of the invention provides.As shown in figure 8, the server 8 of the embodiment wraps
It includes：Processor 80, memory 81 and it is stored in the computer that can be run in the memory 81 and on the processor 80
Program 82, such as photo store program.The processor 80 realizes that above-mentioned each photo is deposited when executing the computer program 82
Step in method for storing embodiment, such as step 101 shown in FIG. 1 is to 104.Alternatively, the processor 80 executes the calculating
The function of each module/unit in above-mentioned each Installation practice, such as the function of module 61 to 64 shown in Fig. 6 are realized when machine program 82
Energy.
Illustratively, the computer program 82 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 81, and are executed by the processor 80, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 82 in the server 8 is described.
The server 8 can be desktop PC, notebook, palm PC and cloud server etc. and calculate equipment.
The server may include, but be not limited only to, processor 80, memory 81.It will be understood by those skilled in the art that Fig. 8 is only
It is the example of server 8, does not constitute the restriction to server 8, may include than illustrating more or fewer components or group
Close certain components or different components, for example, the server can also include input-output equipment, network access equipment,
Bus etc..
The processor 80 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 81 can be the internal storage unit of the server 8, such as the hard disk or memory of server 8.
The memory 81 is also possible to the External memory equipment of the server 8, such as the plug-in type being equipped on the server 8 is hard
Disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card
(Flash Card) etc..Further, the memory 81 can also both include the internal storage unit of the server 8 or wrap
Include External memory equipment.The memory 81 is for other programs needed for storing the computer program and the server
And data.The memory 81 can be also used for temporarily storing the data that has exported or will export.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
May include：Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic of the computer program code can be carried
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that：It still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of photo storage method, which is characterized in that including：
Obtain the shooting attribute of photo；
According to the shooting attribute and preset attribute weight of the photo, the category attribution value of the photo is calculated；
The corresponding photo storage folder of category attribution value described in the preset classification table of comparisons is searched, and the photo is stored in
In the corresponding photo storage folder of the category attribution value；
If searching photo storage folder corresponding less than the category attribution value, a store path is automatically generated, it is described to deposit
The corresponding new photo storage folder in path is stored up, and the photo is stored in the new photo storage folder.
2. photo storage method according to claim 1, which is characterized in that the shooting attribute includes shooting time, claps
Place and photo type are taken the photograph, the shooting attribute and preset attribute weight according to the photo calculates point of the photo
Class ascribed value, including：
Establish three-dimensional system of coordinate；
According to the corresponding attribute weight of the shooting attribute, by the shooting time of the photo, shooting location and photo class
Type maps in the three-dimensional system of coordinate, determines three-dimensional coordinate of the photo in the three-dimensional system of coordinate；
The distance value for calculating the three-dimensional coordinate corresponding point and the three-dimensional system of coordinate origin of the photo, the distance value is made
For the category attribution value of the photo.
3. photo storage method according to claim 2, which is characterized in that described according to the corresponding institute of the shooting attribute
Attribute weight is stated, the shooting time of the photo, shooting location and photo type are mapped in the three-dimensional system of coordinate, is determined
Three-dimensional coordinate of the photo in the three-dimensional system of coordinate, including：
It preestablishes mapping table, includes the different corresponding numerical value of shooting time, different shootings in the mapping table
The corresponding numerical value of point and the corresponding numerical value of different photo types；
Shooting time, the corresponding numerical value in shooting location and photo type institute of the photo are searched from the mapping table；
According to the shooting time of the photo, shooting location and the photo type institute corresponding numerical value and attribute weight,
Determine three-dimensional coordinate of the photo in the three-dimensional system of coordinate.
4. photo storage method according to claim 1, which is characterized in that described to search institute in the preset classification table of comparisons
The corresponding photo storage folder of category attribution value is stated, and the photo is stored in the corresponding photo of the category attribution value and is stored
In file, including：
The corresponding default value of each photo storage folder is obtained from the preset classification table of comparisons；
The category attribution value of the photo is compared one by one with the default value got, it is determining and the photo
The smallest default value of the absolute difference of category attribution value；
If it is determined that the default value and the absolute difference of category attribution value of the photo be located at preset difference area
Between, then determine that the default value determined is matched with the category attribution value of the photo；
In the corresponding photo storage folder of the default value that photo deposit is determined.
5. photo storage method according to claim 1, which is characterized in that the shooting attribute includes photo type, institute
The shooting attribute for obtaining photo is stated, including：
Extract the characteristics of image of the photo；
The characteristics of image of extraction is input to trained convolutional neural networks model, exports the photo type of the photo；
The trained convolutional neural networks model is obtained according to following steps：
The sample photo of setting quantity is obtained, the sample photo is previously provided with type label；
Foundation includes the convolutional neural networks model of input layer, convolutional layer, full articulamentum and output layer；
When training for the first time, the network connection weight between each node layer of convolutional neural networks model is set in advance with threshold value
It is set to the random value for meeting preset condition, and sets the idea output of the sample photo, from the sample of the setting quantity
Sample photo is randomly selected in photo, is input to input layer, by convolutional layer and full articulamentum, is transmitted to output layer, is obtained institute
The real output value of sample photo is stated, completes a wheel training, and calculate the difference of real output value and idea output；
According to the difference of calculating, according to specified learning rules between each node layer network connection weight and threshold value adjust
It is whole, convolutional neural networks model is trained again, until completing instruction when the difference of calculating is not more than preset threshold value
Practice, obtains trained convolutional neural networks model.
6. photo storage method according to any one of claims 1 to 5, which is characterized in that the photo storage method is also
Including：
The photo in the same photo storage folder will be stored in arrange by the timeline for being stored in the photo storage folder；
According to the timeline for being stored in the photo storage folder, the photo of newest deposit this document folder is deposited as the photo
Store up the cover of file.
7. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the step of realization photo storage method as described in any one of claims 1 to 6 when the computer program is executed by processor
Suddenly.
8. a kind of server, including memory, processor and storage can transport in the memory and on the processor
Capable computer program, which is characterized in that the processor realizes following steps when executing the computer program：
Obtain the shooting attribute of photo；
According to the shooting attribute and preset attribute weight of the photo, the category attribution value of the photo is calculated；
The corresponding photo storage folder of category attribution value described in the preset classification table of comparisons is searched, and the photo is stored in
In the corresponding photo storage folder of the category attribution value；
If searching photo storage folder corresponding less than the category attribution value, a store path is automatically generated, it is described to deposit
The corresponding new photo storage folder in path is stored up, and the photo is stored in the new photo storage folder.
9. server according to claim 8, which is characterized in that the shooting attribute includes shooting time, shooting location
And photo type, the shooting attribute and preset attribute weight according to the photo calculate the category attribution of the photo
Value, including：
Establish three-dimensional system of coordinate；
According to the corresponding attribute weight of the shooting attribute, by the shooting time of the photo, shooting location and photo class
Type maps in the three-dimensional system of coordinate, determines three-dimensional coordinate of the photo in the three-dimensional system of coordinate；
The distance value for calculating the three-dimensional coordinate corresponding point and the three-dimensional system of coordinate origin of the photo, the distance value is made
For the category attribution value of the photo.
10. server according to claim 8, which is characterized in that described search is divided described in the preset classification table of comparisons
The corresponding photo storage folder of class ascribed value, and the photo is stored in the corresponding photo storage file of the category attribution value
In folder, including：
The corresponding default value of each photo storage folder is obtained from the preset classification table of comparisons；
The category attribution value of the photo is compared one by one with the default value got, it is determining and the photo
The smallest default value of the absolute difference of category attribution value；
If it is determined that the default value and the absolute difference of category attribution value of the photo be located at preset difference area
Between, then determine that the default value determined is matched with the category attribution value of the photo；
In the corresponding photo storage folder of the default value that photo deposit is determined.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810456993.1A CN108897757B (en) | 2018-05-14 | 2018-05-14 | Photo storage method, storage medium and server |
| PCT/CN2018/097097 WO2019218459A1 (en) | 2018-05-14 | 2018-07-25 | Photo storage method, storage medium, server, and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810456993.1A CN108897757B (en) | 2018-05-14 | 2018-05-14 | Photo storage method, storage medium and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108897757A true CN108897757A (en) | 2018-11-27 |
| CN108897757B CN108897757B (en) | 2023-08-22 |
Family
ID=64342970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810456993.1A Active CN108897757B (en) | 2018-05-14 | 2018-05-14 | Photo storage method, storage medium and server |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108897757B (en) |
| WO (1) | WO2019218459A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109508398A (en) * | 2018-11-30 | 2019-03-22 | 维沃移动通信有限公司 | A kind of photo classification method and its terminal device |
| CN109766461A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Photo management method, device, computer equipment and medium based on micro- expression |
| CN111414966A (en) * | 2020-03-25 | 2020-07-14 | 北京字节跳动网络技术有限公司 | Classification method, classification device, electronic equipment and computer storage medium |
| CN112395037A (en) * | 2020-12-07 | 2021-02-23 | 深圳云天励飞技术股份有限公司 | Dynamic cover selection method and device, electronic equipment and storage medium |
| CN112766139A (en) * | 2021-01-14 | 2021-05-07 | 北京迈格威科技有限公司 | Target identification method and device, storage medium and electronic equipment |
| CN115035785A (en) * | 2022-06-17 | 2022-09-09 | 云知声智能科技股份有限公司 | Method and device for displaying photos, electronic equipment and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114840620B (en) * | 2022-04-01 | 2023-06-27 | 广东省国土资源测绘院 | Evidence-providing material management method, intelligent terminal and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070115373A1 (en) * | 2005-11-22 | 2007-05-24 | Eastman Kodak Company | Location based image classification with map segmentation |
| KR20080028698A (en) * | 2006-09-27 | 2008-04-01 | 삼성전자주식회사 | Method and system for mapping image objects in photo to geographic objects |
| CN103870599A (en) * | 2014-04-02 | 2014-06-18 | 联想(北京)有限公司 | Shooting data collecting method, device and electronic equipment |
| CN104598932A (en) * | 2015-02-13 | 2015-05-06 | 成都品果科技有限公司 | Method and system for photograph classification based on event information |
| CN104699842A (en) * | 2015-03-31 | 2015-06-10 | 百度在线网络技术（北京）有限公司 | Method and device for displaying pictures |
| US20150201298A1 (en) * | 2013-03-30 | 2015-07-16 | Tsinghua University | Method for positioning ip location and server |
| CN105608425A (en) * | 2015-12-17 | 2016-05-25 | 小米科技有限责任公司 | Method and device for sorted storage of pictures |
| CN105760533A (en) * | 2016-03-08 | 2016-07-13 | 广东欧珀移动通信有限公司 | Photo management method and photo management device |
| CN106101224A (en) * | 2016-06-12 | 2016-11-09 | 腾讯科技（深圳）有限公司 | Identify the method and device of the classification of user geographic location |
| CN106155592A (en) * | 2016-07-26 | 2016-11-23 | 深圳天珑无线科技有限公司 | A kind of photo processing method and terminal |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101510205B (en) * | 2009-03-16 | 2013-02-27 | 广州市有福数码科技有限公司 | Method for implementing automatically clustering photographs, apparatus and system |
| JP5934653B2 (en) * | 2010-11-29 | 2016-06-15 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ | Image classification device, image classification method, program, recording medium, integrated circuit, model creation device |
| CN104866500B (en) * | 2014-02-25 | 2021-10-15 | 腾讯科技（深圳）有限公司 | Picture classification display method and device |
-
2018
- 2018-05-14 CN CN201810456993.1A patent/CN108897757B/en active Active
- 2018-07-25 WO PCT/CN2018/097097 patent/WO2019218459A1/en active Application Filing
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070115373A1 (en) * | 2005-11-22 | 2007-05-24 | Eastman Kodak Company | Location based image classification with map segmentation |
| KR20080028698A (en) * | 2006-09-27 | 2008-04-01 | 삼성전자주식회사 | Method and system for mapping image objects in photo to geographic objects |
| US20150201298A1 (en) * | 2013-03-30 | 2015-07-16 | Tsinghua University | Method for positioning ip location and server |
| CN103870599A (en) * | 2014-04-02 | 2014-06-18 | 联想(北京)有限公司 | Shooting data collecting method, device and electronic equipment |
| CN104598932A (en) * | 2015-02-13 | 2015-05-06 | 成都品果科技有限公司 | Method and system for photograph classification based on event information |
| CN104699842A (en) * | 2015-03-31 | 2015-06-10 | 百度在线网络技术（北京）有限公司 | Method and device for displaying pictures |
| CN105608425A (en) * | 2015-12-17 | 2016-05-25 | 小米科技有限责任公司 | Method and device for sorted storage of pictures |
| CN105760533A (en) * | 2016-03-08 | 2016-07-13 | 广东欧珀移动通信有限公司 | Photo management method and photo management device |
| CN106101224A (en) * | 2016-06-12 | 2016-11-09 | 腾讯科技（深圳）有限公司 | Identify the method and device of the classification of user geographic location |
| CN106155592A (en) * | 2016-07-26 | 2016-11-23 | 深圳天珑无线科技有限公司 | A kind of photo processing method and terminal |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109508398A (en) * | 2018-11-30 | 2019-03-22 | 维沃移动通信有限公司 | A kind of photo classification method and its terminal device |
| CN109508398B (en) * | 2018-11-30 | 2020-09-15 | 维沃移动通信有限公司 | Photo classification method and terminal equipment thereof |
| CN109766461A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Photo management method, device, computer equipment and medium based on micro- expression |
| CN111414966A (en) * | 2020-03-25 | 2020-07-14 | 北京字节跳动网络技术有限公司 | Classification method, classification device, electronic equipment and computer storage medium |
| CN111414966B (en) * | 2020-03-25 | 2023-08-15 | 抖音视界有限公司 | Classification method, classification device, electronic equipment and computer storage medium |
| CN112395037A (en) * | 2020-12-07 | 2021-02-23 | 深圳云天励飞技术股份有限公司 | Dynamic cover selection method and device, electronic equipment and storage medium |
| CN112766139A (en) * | 2021-01-14 | 2021-05-07 | 北京迈格威科技有限公司 | Target identification method and device, storage medium and electronic equipment |
| CN115035785A (en) * | 2022-06-17 | 2022-09-09 | 云知声智能科技股份有限公司 | Method and device for displaying photos, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019218459A1 (en) | 2019-11-21 |
| CN108897757B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108897757A (en) | A kind of photo storage method, storage medium and server | |
| CN106407311B (en) | Method and device for obtaining search result | |
| CN107748799B (en) | Method for aligning multiple data source movie and television data entities | |
| CN103440318B (en) | The landscape identifying system of mobile terminal | |
| Sinha et al. | Summarization of personal photologs using multidimensional content and context | |
| CN101853295B (en) | Image search method | |
| CN109685121A (en) | Training method, image search method, the computer equipment of image encrypting algorithm | |
| WO2022095356A1 (en) | Transfer learning method for image classification, related device, and storage medium | |
| CN104834693A (en) | Depth-search-based visual image searching method and system thereof | |
| CN107832794B (en) | Convolutional neural network generation method, vehicle system identification method and computing device | |
| CN107395680B (en) | Shop group's information push and output method and device, equipment | |
| CN115688913A (en) | Cloud-side collaborative personalized federal learning method, system, equipment and medium | |
| CN109992590B (en) | Approximate space keyword query method and system with digital attributes in traffic network | |
| CN109947987A (en) | A kind of intersection collaborative filtering recommending method | |
| Chen et al. | Integrated content and context analysis for mobile landmark recognition | |
| CN103353881A (en) | Method and device for searching application | |
| CN109840559A (en) | Method for screening images, device and electronic equipment | |
| CN104346356A (en) | Method and device for storing photo files in classifying manner | |
| Choi et al. | Multimodal location estimation of consumer media: Dealing with sparse training data | |
| CN104598932B (en) | A kind of photo classification method and system based on event information | |
| US11127199B2 (en) | Scene model construction system and scene model constructing method | |
| Alfarrarjeh et al. | A data-centric approach for image scene localization | |
| CN104156475B (en) | Geography information read method and device | |
| CN104123382B (en) | A kind of image set abstraction generating method under Social Media | |
| CN107766881B (en) | Way finding method and device based on basic classifier and storage 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |