CN109190919A - It is sold critical sales index generation method, system, equipment and storage medium - Google Patents
It is sold critical sales index generation method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN109190919A CN109190919A CN201810907163.6A CN201810907163A CN109190919A CN 109190919 A CN109190919 A CN 109190919A CN 201810907163 A CN201810907163 A CN 201810907163A CN 109190919 A CN109190919 A CN 109190919A
- Authority
- CN
- China
- Prior art keywords
- region
- commodity
- stratose
- reference line
- stored
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/759—Region-based matching
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of retail critical sales index generation method, system, equipment and storage mediums, comprising: is identified to a collected image by preset stratose identification model, identifies the corresponding stratose region of each stratose on image；The region to be stored for identifying each commodity corresponding commodity region and commodity to be stored on each stratose, according to the memory space in the areal calculation region to be stored in a commodity region；Critical sales index is generated according to the memory space in the quantity in commodity region and region to be stored, critical sales index includes at least goods holding amount.In the present invention before being identified to commodity region and region to be stored, first to progress stratose region recognition on each image, to identify each stratose, and then commodity region in each stratose and region to be stored are identified, to provide the recognition accuracy in commodity region and region to be stored, retail trade critical sales index is improved, such as the accuracy in computation of goods holding amount.
Description
Technical field
The present invention relates to new retail technologies, and in particular, to a kind of retail critical sales index generation method, is set system
Standby and storage medium.
Background technique
In retail trade, need to count some critical sales indexes, consequently facilitating businessman formulates suitable marketing strategy.But
It is the statistics of critical sales index, the cargo for spending a large amount of manpower put on shelf and refrigerator is needed to be counted.
Such as businessman often leases some refrigerators in market, subway, railway station public place and carries out selling for some commodity.
Refrigerator is leased in public places such as some laughable companies carries out selling for bottled or canned client.But the quantity of these refrigerators compared with
It is more, it is distributed extremely wide.Therefore, businessman be difficult to dispose available manpower check each refrigerator, in each refrigerator the arrangement of commodity and
The deployment scenarios of commodity in refrigerator.Furthermore on the shelf in many markets, since quantity is more, and putting on each shelf
Commodity amount it is extremely more, therefore when by manually carry out commodity amount statistics when, not only workload is more, and be easy system
Count mistake.
With the development of artificial intelligence technology, the especially appearance of deep learning method, image recognition is made to start to have in fact
With the value of change.Therefore, can be in terms of artificial intelligence, above-mentioned technical problem proposes a solution.
Summary of the invention
For the defects in the prior art, the object of the present invention is to provide a kind of retail critical sales index generation method,
System, equipment and storage medium.
The retail critical sales index generation method provided according to the present invention, includes the following steps:
Step S1: a collected image is identified by preset stratose identification model, to identify the figure
As the upper corresponding stratose region of each stratose；
Step S2: the area to be stored in each commodity corresponding commodity region and commodity to be stored on each stratose is identified
Domain, and then the memory space in the region to be stored according to the areal calculation in a commodity region；
Step S3: critical sales are generated according to the memory space in the quantity in the commodity region and the region to be stored and are referred to
Mark, the critical sales index include at least goods holding amount.
Preferably, the step S1 includes the following steps:
Step S101: multiple first training images for stratose identification are obtained, to each first training image root
Multiple second training images are divided into according to stratose；
Step S102: the stratose identification model is generated by second training image training；
Step S103: identifying each image by the stratose identification model, identifies every in described image
The corresponding stratose region of one stratose.
Preferably, further include following steps between the step S2 and the step S3:
Step M1: one stratose region of selection determines reference line l with the upper side edge of the stratose1, lower side determines reference line l2；
Step M2: reference line l is determined with the left side of described image3, the reference line l3With the reference line l1, it is described
Reference line l2(x is met at respectively1,y1) point, (x4,y4) point, with right edge determination and the reference line l of described image3Parallel
Reference line l4, the reference line l4With the reference line l1, the reference line l2(x is met at respectively2,y2) point, (x3,y3) point；
Step M3: the reference line l will be adjusted1、l2、l3、l4, so that l2⊥l3, l1||l2, thus the reference line l3With
Reference line l1Intersection point (x1,y1) become (x1,y1) ', the reference line l3With reference line l2Intersection point (x4,y4) become (x4,
y4) ', the reference line l4With reference line l1Intersection point (x3,y3) become (x3,y3) ', the reference line l4With reference line l1Friendship
Point (x2,y2) become (x2,y2) ', the reference line l4With reference line l2Intersection point (x3,y3) become (x3,y3)′；
Step M4: according to (x1,y1), (x2,y2), (x3,y3), (x4,y4), (x1,y1) ', (x2,y2) ', (x3,y3) ', (x4,
y4) ' acquire perspective transformation matrix H, and then described image is corrected according to the perspective transformation matrix H.
Preferably, the step S2 includes the following steps:
Step S201: the area to be stored in each commodity corresponding commodity region and commodity to be stored on each stratose is identified
Domain；
Step S202: the area ratio coefficient between adjacent commodity region, root are successively found out according to order from left to right
Area ratio mean coefficient is generated according to multiple area ratio coefficient average values；
Step S203: according to the area and the area in the adjacent commodity region in the left side in each region to be stored
Ratio mean coefficient successively calculates the memory space in the region to be stored.
Preferably, in step s3, the critical sales index further includes vacancy rate, degree of purity and row's face rate；
The goods holding amount calculates in the following way:
Using each commodity region as a memory space；
Add up the memory space in each storage position region and the memory space generation described image in each commodity region
The memory capacity of upper refrigerator or shelf；
The vacancy rate calculates in the following way:
It is generated according to the ratio of the memory space in each of cumulative storage position region and goods holding amount described vacant
Rate；
The degree of purity calculates in the following way:
Type of article will be set in described image and sets the target brand article in type of article and is identified, and in turn
Determine the setting type of article quantity and the target brand article quantity；
The degree of purity is generated according to the ratio of the target brand article quantity and the commodity amount of the type；
Row face rate calculates in the following way:
According to calculated in multiple images setting type in target brand article quantity with it is calculated in multiple images
The ratio for setting the commodity amount of type generates row face rate.
Preferably, further include following steps after the step S3:
When described image is refrigerator image, when identifying multiple stratoses being arranged successively in the horizontal direction, it is determined that
The refrigerator is multi-door refrigerator.
Preferably, the commodity region and the region to be stored are identified as follows:
Step N1: obtaining the third training image that multiple groups are used for commodity region recognition, and every group of third training image includes
Multiple end article images establish commodity identification model using training image described in multiple groups；
Step N2: described image is obtained, the commodity region in described image is identified by the commodity identification model；
Step N3: calculating the spacer area in adjacent commodity region, when the spacer area is greater than the commodity area threshold of setting
When value, then judge that there are regions to be stored between the adjacent commodity region.
Retail critical sales index provided by the invention generates system, raw for realizing the retail critical sales index
At method, comprising:
Stratose identification module, for being identified to a collected image by preset stratose identification model, to know
It Chu not each stratose in described image；
Memory space generation module, for identification each corresponding commodity region of commodity and quotient to be stored on each stratose out
The region to be stored of product, and then the memory space in the region to be stored according to the areal calculation in the commodity region；
Critical sales index generation module, for according to the commodity region and the Area generation critical sales to be stored
Index includes at least goods holding amount described in the critical sales index.
Retail critical sales index generating device provided by the invention, comprising:
Processor；
Memory, wherein being stored with the executable instruction of the processor；
Wherein, the processor is configured to execute the retail critical sales index via the executable instruction is executed
The step of generation method.
Computer readable storage medium provided by the invention, for storing program, described program is performed described in realization
The step of being sold critical sales index generation method.
Compared with prior art, the present invention have it is following the utility model has the advantages that
In the present invention before being identified to commodity region and region to be stored, first to progress stratose area on each image
Domain identification, to identify each stratose, and then identifies commodity region in each stratose and region to be stored, to provide
The recognition accuracy in commodity region and region to be stored, improves retail trade critical sales index, such as goods holding amount
Accuracy in computation；
The present invention first on each image carry out stratose region recognition when, can recognize that the layer of shelf or refrigerator in image
Number, and then commodity region in each stratose is identified, thus the corresponding stratose in each commodity region；Furthermore work as described image
When for refrigerator image, it can be avoided the commodity reflected on the glass door by refrigerator and be identified, be mixed into retail trade critical sales
Statistical data in, when described image be shelf image when, the commodity that also can be avoided outside the shelf are identified, and are mixed into zero
In the statistical data for selling industry critical sales.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is the step flow chart that critical sales index generation method is sold in the present invention；
Fig. 2 is the step flow chart of middle layer column region of the present invention identification；
Fig. 3 is in the present invention to the step flow chart corrected to the image after identification；
Fig. 4 is the schematic illustration that image is corrected in the present invention；
Fig. 5 is the calculating flow chart of steps of the memory space in region to be stored in the present invention；
Fig. 6 is the step flow chart of regional determination to be stored in the present invention；
Fig. 7 is the module diagram that retail critical sales index generates system in the present invention；
Fig. 8 is the structural schematic diagram that critical sales index generating device is sold in the present invention；And
Fig. 9 is the structural schematic diagram of computer readable storage medium in the present invention.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, various modifications and improvements can be made.These belong to the present invention
Protection scope.
Fig. 1 is the step flow chart that critical sales index generation method is sold in the present invention, as shown in Figure 1, the present invention mentions
The retail critical sales index generation method of confession, includes the following steps:
Step S1: a collected image is identified by preset stratose identification model, to identify the figure
As the upper corresponding stratose region of each stratose；
Step S2: the area to be stored in each commodity corresponding commodity region and commodity to be stored on each stratose is identified
Domain, and then the memory space in the region to be stored according to the areal calculation in a commodity region；
Step S3: critical sales are generated according to the memory space in the quantity in the commodity region and the region to be stored and are referred to
Mark, the critical sales index include at least goods holding amount.
In the present embodiment, in the present invention before being identified to commodity region and region to be stored, first to each figure
As upper progress stratose region recognition, to identify each stratose, and then to commodity region in each stratose and region to be stored into
Row identification, to provide the recognition accuracy in commodity region and region to be stored, improves retail trade critical sales index,
Such as the accuracy in computation of goods holding amount.The present invention can adapt to the identification in commodity region and region to be stored in a variety of images,
Such as the image of shooting angle deflection.
In the present embodiment, the present invention first on each image carry out stratose region recognition when, can recognize that in image
The number of plies of shelf or refrigerator, and then commodity region in each stratose is identified, thus the corresponding stratose in each commodity region；
Furthermore when described image is refrigerator image, the commodity reflected on the glass door by refrigerator is can be avoided and be identified, be mixed into zero
In the statistical data for selling industry critical sales, when described image is shelf image, it also can be avoided the commodity outside the shelf
It is identified, is mixed into the statistical data of retail trade critical sales.
In the present embodiment, each stratose region area is calculated according to the multiple stratose regions identified, generates stratose
The average value of region area, and then the stratose region that can will be less than the average value half of the stratose region area is arranged
It removes, so that the commodity region on the non-targeted shelf introduced when image taking is tilted excludes.
In the present embodiment, described image is refrigerator image or shelf image, and the stratose region is each on refrigerator
Each layer region of layer region or shelf.The goods holding amount is the commodity amount or a shelf energy that a refrigerator can accommodate
The commodity amount enough accommodated.
In the present embodiment, described image is clapped by mobile phone, camera, the robot for loading camera or unmanned plane etc.
It takes the photograph.
Fig. 2 is the step flow chart of middle layer column region of the present invention identification, as shown in Fig. 2, the step S1 includes following step
It is rapid:
Step S101: multiple first training images for stratose identification are obtained, to each first training image root
Multiple second training images are divided into according to stratose；
Step S102: the stratose identification model is generated by second training image training；
Step S103: identifying each image by the stratose identification model, identifies every in described image
The corresponding stratose region of one stratose.
I.e. in the present embodiment, by the way that the image of collected refrigerator or shelf to be split, formation is a variety of only to be had
The image of one stratose of one stratose of refrigerator or shelf forms second training image.
In step S101, first training is schemed by stratose polygonal mark, will be realized in the first training image
The segmentation of picture generates second training image.It, can be just with pentagonal label such as by a shelf image since shooting tilts
Place.
Fig. 3 is in the present invention to the step flow chart corrected to the image after identification, as shown in figure 3, in the step
Further include following steps between the rapid S2 and step S3:
Step M1: one stratose region of selection determines reference line l with the upper side edge of the stratose1, lower side determines reference line l2；
Step M2: reference line l is determined with the left side of described image3, the reference line l3With the reference line l1, it is described
Reference line l2(x is met at respectively1,y1) point, (x4,y4) point, with right edge determination and the reference line l of described image3Parallel
Reference line l4, the reference line l4With the reference line l1, the reference line l2(x is met at respectively2,y2) point, (x3,y3) point；
Step M3: the reference line l will be adjusted1、l2、l3、l4, so that l2⊥l3, l1||l2, thus the reference line l3With
Reference line l1Intersection point (x1,y1) become (x1,y1) ', the reference line l3With reference line l2Intersection point (x4,y4) become (x4,
y4) ', the reference line l4With reference line l1Intersection point (x3,y3) become (x3,y3) ', the reference line l4With reference line l1Friendship
Point (x2,y2) become (x2,y2) ', the reference line l4With reference line l2Intersection point (x3,y3) become (x3,y3)′；
Step M4: according to (x1,y1), (x2,y2), (x3,y3), (x4,y4), (x1,y1) ', (x2,y2) ', (x3,y3) ', (x4,
y4) ' acquire perspective transformation matrix H, and then described image is corrected according to the perspective transformation matrix H.
In the present embodiment, described image is corrected before step S3, so that the commodity region in described image
Between size gap, to improve the estimation correctness for treating the memory space of storage area by image-region.
Fig. 4 is the schematic illustration that image is corrected in the present invention, as shown in figure 4, setting image f after correction0There is l '1,
l′2, l '3,l′4, and l '1||l′2,l′3||l′4,l′2⊥l′3Become image f after perspective transform, i.e., by the l in image f1,l2,
l3, l4And f0In l '1,l′2,l′3,l′4Regard the point set on corresponding flat as respectively, that is, has l '1=Hl1,f0=Hf, H are to become
Change matrix.Therefore known four couples of match point (x1,y1), (x2,y2), (x3,y3), (x4,y4), (x1,y1) ', (x2,y2) ', (x3,
y3) ', (x4,y4) ', can find out H, further acquire f0。
Fig. 5 is the calculating flow chart of steps of the memory space in region to be stored in the present invention, as shown in figure 5, the step
S2 includes the following steps:
Step S201: the area to be stored in each commodity corresponding commodity region and commodity to be stored on each stratose is identified
Domain；
Step S202: the area ratio coefficient between adjacent commodity region, root are successively found out according to order from left to right
Area ratio mean coefficient is generated according to multiple area ratio coefficient average values；
Step S203: according to the area and the area in the adjacent commodity region in the left side in each region to be stored
Ratio mean coefficient successively calculates the memory space in the region to be stored.
There are certain angle when in the present embodiment, due to Image Acquisition, the corresponding commodity region of same commodity
Area is not identical, but zooms in or out in certain ratio.In the present embodiment, successively asked by from left to right order
Area ratio system between adjacent commodity region out, so it is average according to area ratio coefficient average value generation area ratio is stated
Coefficient, and then region to be stored is extrapolated according to the commodity region on the left of the area ratio mean coefficient and region to be stored
Memory space.
It, can also be by the way that region to be stored will be extrapolated by the commodity region on the left of region to be stored in variation
Memory space and the average value between the memory space in region to be stored is extrapolated by the commodity region on the right side of region to be stored
Final memory space as the region to be stored.
In the present embodiment, in step s3, the critical sales index further includes vacancy rate, degree of purity and row face
Rate；
The goods holding amount calculates in the following way:
Using each commodity region as a memory space；
Add up the memory space in each storage position region and the memory space generation described image in each commodity region
The memory capacity of upper refrigerator or shelf；
The vacancy rate calculates in the following way:
It is generated according to the ratio of the memory space in each of cumulative storage position region and goods holding amount described vacant
Rate；
The degree of purity calculates in the following way:
Type of article will be set in described image and sets the target brand article in type of article and is identified, and in turn
Determine the setting type of article quantity and the target brand article quantity；
The degree of purity is generated according to the ratio of the target brand article quantity and the commodity amount of the type；
Row face rate (SOVI) calculates in the following way:
According to calculated in multiple images setting type in target brand article quantity with it is calculated in multiple images
The ratio for setting the commodity amount of type generates row face rate.
In the present embodiment, further include following steps after the step S3:
When described image is refrigerator image, when identifying multiple stratoses being arranged successively in the horizontal direction, it is determined that
The refrigerator is multi-door refrigerator.
Such as when the refrigerator is two-door refrigerator, when the image to the refrigerator identifies, it can recognize that along water
Square to two stratose regions being arranged successively, it can judge that the refrigerator in the image is two-door refrigerator.
Fig. 6 is the module diagram that retail critical sales index generates system in the present invention, as shown in fig. 6, the commodity
Region and the region to be stored are identified as follows:
Step N1: obtaining the third training image that multiple groups are used for commodity region recognition, and every group of third training image includes
Multiple end article images establish commodity identification model using training image described in multiple groups；
Step N2: described image is obtained, the commodity region in described image is identified by the commodity identification model；
Step N3: calculating the spacer area in adjacent commodity region, when the spacer area is greater than the commodity area threshold of setting
When value, then judge that there are regions to be stored between the adjacent commodity region.
In the present embodiment, the commodity area threshold is the area average in adjacent commodity region.It, can in variation
To be configured based on experience value to the commodity area threshold.
In the present embodiment, the commodity identification model and the stratose identification model use convolutional neural networks structure,
It is trained to obtain under deep learning frame.
Fig. 7 is the structural schematic diagram that critical sales index generating device is sold in the present invention, as shown in fig. 7, the present invention mentions
The retail critical sales index of confession generates system, for realizing the retail critical sales index generation method comprising:
Stratose identification module, for being identified to a collected image by preset stratose identification model, to know
It Chu not each stratose in described image；
Memory space generation module, for identification each corresponding commodity region of commodity and quotient to be stored on each stratose out
The region to be stored of product, and then the memory space in the region to be stored according to the areal calculation in the commodity region；
Critical sales index generation module, for according to the commodity region and the Area generation critical sales to be stored
Index includes at least goods holding amount described in the critical sales index.
A kind of retail critical sales index generating device, including processor are also provided in the embodiment of the present invention.Memory,
In be stored with the executable instruction of processor.Wherein, processor is configured to be performed retail pass via execution executable instruction
The step of key performance index generation method.
As above, in the embodiment by before being identified to commodity region and region to be stored, first on each image
Stratose region recognition is carried out, to identify each stratose, and then commodity region in each stratose and region to be stored are known
Not, to provide the recognition accuracy in commodity region and region to be stored, retail trade critical sales index, such as quotient are improved
The accuracy in computation of product saturation.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as " circuit ", " module " or " platform ".
Fig. 8 is the structural schematic diagram of retail critical sales index generating device of the invention.Root is described referring to Fig. 8
According to the electronic equipment 600 of the embodiment of the invention.The electronic equipment 600 that Fig. 8 is shown is only an example, should not be right
The function and use scope of the embodiment of the present invention bring any restrictions.
As shown in figure 8, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
Include but be not limited to: at least one processing unit 610, at least one storage unit 620, connection different platform component (including storage
Unit 620 and processing unit 610) bus 630, display unit 640 etc..
Wherein, storage unit is stored with program code, and program code can be executed with unit 610 processed, so that processing is single
Member 610 executes various exemplary implementations according to the present invention described in this specification above-mentioned electronic prescription circulation processing method part
The step of mode.For example, processing unit 610 can execute step as shown in fig. 1.
Storage unit 620 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 660 can be communicated by bus 630 with other modules of electronic equipment 600.It should
Understand, although being not shown in Fig. 8, other hardware and/or software module can be used in conjunction with electronic equipment 600, including unlimited
In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage platform etc..
A kind of computer readable storage medium is also provided in the embodiment of the present invention, for storing program, program is performed
The step of retail critical sales index generation method of realization.In some possible embodiments, various aspects of the invention
It is also implemented as a kind of form of program product comprising program code, when program product is run on the terminal device, journey
Sequence code is for executing terminal device described in this specification above-mentioned electronic prescription circulation processing method part according to this hair
The step of bright various illustrative embodiments.
As it appears from the above, the program of the computer readable storage medium of the embodiment is when being executed, to commodity in the present invention
Before region and region to be stored are identified, first to stratose region recognition is carried out on each image, to identify each stratose,
And then commodity region in each stratose and region to be stored are identified, to provide commodity region and region to be stored
Recognition accuracy improves retail trade critical sales index, such as the accuracy in computation of goods holding amount.
Fig. 9 is the structural schematic diagram of computer readable storage medium of the invention.Refering to what is shown in Fig. 9, describing according to this
The program product 800 for realizing the above method of the embodiment of invention can use the read-only storage of portable compact disc
Device (CD-ROM) and including program code, and can be run on terminal device, such as PC.However, journey of the invention
Sequence product is without being limited thereto, and in this document, readable storage medium storing program for executing can be any tangible medium for including or store program, the journey
Sequence can be commanded execution system, device or device use or in connection.
Program product can be using any combination of one or more readable mediums.Readable medium can be readable signal Jie
Matter or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or partly lead
System, device or the device of body, or any above combination.More specific example (the non exhaustive column of readable storage medium storing program for executing
Table) it include: the electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only storage
Device (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer readable storage medium may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, including but not
It is limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, programming language include object oriented program language-Java, C++ etc., further include conventional process
Formula programming language-such as " C " language or similar programming language.Program code can be calculated fully in user
It executes in equipment, partly execute on a user device, executing, as an independent software package partially in user calculating equipment
Upper part executes on a remote computing or executes in remote computing device or server completely.It is being related to remotely counting
In the situation for calculating equipment, remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In the present embodiment, in the present invention before being identified to commodity region and region to be stored, first to each figure
As upper progress stratose region recognition, to identify each stratose, and then to commodity region in each stratose and region to be stored into
Row identification, to provide the recognition accuracy in commodity region and region to be stored, improves retail trade critical sales index,
Such as the accuracy in computation of goods holding amount.The present invention first on each image carry out stratose region recognition when, can recognize that figure
The number of plies of shelf or refrigerator as in, and then commodity region in each stratose is identified, so that each commodity region is corresponding
Stratose；Furthermore when described image is refrigerator image, the commodity reflected on the glass door by refrigerator is can be avoided and be identified, mixed
In the statistical data for entering retail trade critical sales, when described image is shelf image, also it can be avoided outside the shelf
Commodity are identified, and are mixed into the statistical data of retail trade critical sales.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make various deformations or amendments within the scope of the claims, this not shadow
Ring substantive content of the invention.
Claims (10)
1. a kind of retail critical sales index generation method, which comprises the steps of:
Step S1: a collected image is identified by preset stratose identification model, to identify in described image
The corresponding stratose region of each stratose；
Step S2: identifying the region to be stored in each commodity corresponding commodity region and commodity to be stored on each stratose, into
And the memory space in the region to be stored according to the areal calculation in a commodity region；
Step S3: generating critical sales index according to the memory space in the quantity in the commodity region and the region to be stored,
The critical sales index includes at least goods holding amount.
2. retail critical sales index generation method according to claim 1, which is characterized in that the step S1 includes such as
Lower step:
Step S101: multiple first training images for stratose identification are obtained, to each first training image according to layer
Column split is multiple second training images；
Step S102: the stratose identification model is generated by second training image training；
Step S103: identifying each image by the stratose identification model, identifies each layer in described image
Arrange corresponding stratose region.
3. retail critical sales index generation method according to claim 1, which is characterized in that in the step S2 and institute
Stating between step S3 further includes following steps:
Step M1: one stratose region of selection determines reference line l with the upper side edge of the stratose1, lower side determines reference line l2；
Step M2: reference line l is determined with the left side of described image3, the reference line l3With the reference line l1, the reference
Line l2(x is met at respectively1, y1) point, (x4, y4) point, with right edge determination and the reference line l of described image3Parallel reference
Line l4, the reference line l4With the reference line l1, the reference line l2(x is met at respectively2, y2) point, (x3, y3) point；
Step M3: the reference line l will be adjusted1、l2、l3、l4, so that l2⊥l3, l1||l2, thus the reference line l3With reference
Line l1Intersection point (x1, y1) become (x1, y1) ', the reference line l3With reference line l2Intersection point (x4, y4) become (x4, y4) ', institute
State reference line l4With reference line l1Intersection point (x3, y3) become (x3, y3) ', the reference line l4With reference line l1Intersection point (x2,
y2) become (x2, y2) ', the reference line l4With reference line l2Intersection point (x3, y3) become (x3, y3)′；
Step M4: according to (x1, y1), (x2, y2), (x3, y3), (x4, y4), (x1, y1) ', (x2, y2) ', (x3, y3) ', (x4, y4)′
Perspective transformation matrix H is acquired, and then described image is corrected according to the perspective transformation matrix H.
4. retail critical sales index generation method according to claim 1, which is characterized in that the step S2 includes such as
Lower step:
Step S201: the region to be stored in each commodity corresponding commodity region and commodity to be stored on each stratose is identified；
Step S202: the area ratio coefficient between adjacent commodity region is successively found out according to order from left to right, according to more
A area ratio coefficient average value generates area ratio mean coefficient；
Step S203: according to the area and the area ratio in the adjacent commodity region in the left side in each region to be stored
Mean coefficient successively calculates the memory space in the region to be stored.
5. retail critical sales index generation method according to claim 4, which is characterized in that in step s3, described
Critical sales index further includes vacancy rate, degree of purity and row's face rate；
The goods holding amount calculates in the following way:
Using each commodity region as a memory space；
Ice in the memory space in each storage position region and the memory space generation described image in each commodity region of adding up
The memory capacity of case or shelf；
The vacancy rate calculates in the following way:
The vacancy rate is generated according to the memory space in each of cumulative storage position region and the ratio of goods holding amount；
The degree of purity calculates in the following way:
Type of article will be set in described image and sets the target brand article in type of article and is identified, and is determined in turn
The setting type of article quantity and the target brand article quantity；
The degree of purity is generated according to the ratio of the target brand article quantity and the commodity amount of the type；
Row face rate calculates in the following way:
According to calculated setting in the target brand article quantity and multiple images calculated in multiple images in setting type
The ratio of the commodity amount of type generates row face rate.
6. retail critical sales index generation method according to claim 1, which is characterized in that after the step S3 also
Include the following steps:
When described image is refrigerator image, when identifying multiple stratoses being arranged successively in the horizontal direction, it is determined that described
Refrigerator is multi-door refrigerator.
7. retail critical sales index generation method according to claim 1, which is characterized in that the commodity region and institute
Region to be stored is stated to identify as follows:
Step N1: the third training image that multiple groups are used for commodity region recognition is obtained, every group of third training image includes multiple
End article image establishes commodity identification model using training image described in multiple groups；
Step N2: described image is obtained, the commodity region in described image is identified by the commodity identification model；
Step N3: calculating the spacer area in adjacent commodity region, when the spacer area is greater than the commodity area threshold of setting,
Then judge that there are regions to be stored between the adjacent commodity region.
8. a kind of retail critical sales index generates system, for realizing the key of retail described in any one of claims 1 to 7
Performance index generation method characterized by comprising
Stratose identification module, for being identified to a collected image by preset stratose identification model, to identify
Each stratose in described image；
Memory space generation module, for identification each corresponding commodity region of commodity and commodity to be stored on each stratose out
Region to be stored, and then the memory space in the region to be stored according to the areal calculation in the commodity region；
Critical sales index generation module, for being referred to according to the commodity region and the Area generation critical sales to be stored
It marks, goods holding amount is included at least described in the critical sales index.
9. a kind of retail critical sales index generating device characterized by comprising
Processor；
Memory, wherein being stored with the executable instruction of the processor；
Wherein, the processor is configured to come any one of perform claim requirement 1 to 7 institute via the execution executable instruction
The step of stating retail critical sales index generation method.
10. a kind of computer readable storage medium, for storing program, which is characterized in that described program is performed realization power
Benefit require any one of 1 to 7 described in retail critical sales index generation method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810907163.6A CN109190919A (en) | 2018-08-10 | 2018-08-10 | It is sold critical sales index generation method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810907163.6A CN109190919A (en) | 2018-08-10 | 2018-08-10 | It is sold critical sales index generation method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109190919A true CN109190919A (en) | 2019-01-11 |
Family
ID=64920839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810907163.6A Pending CN109190919A (en) | 2018-08-10 | 2018-08-10 | It is sold critical sales index generation method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190919A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948736A (en) * | 2019-04-04 | 2019-06-28 | 上海扩博智能技术有限公司 | Commodity identification model active training method, system, equipment and storage medium |
| CN110543839A (en) * | 2019-08-20 | 2019-12-06 | 南京掌控网络科技有限公司 | commodity goods laying rate acquisition method based on computer vision |
| CN110781780A (en) * | 2019-10-11 | 2020-02-11 | 浙江大华技术股份有限公司 | Vacancy detection method and related device |
| CN111008804A (en) * | 2019-12-06 | 2020-04-14 | 拉货宝网络科技有限责任公司 | Intelligent recommendation method for goods position of warehouse goods |
| WO2020199776A1 (en) * | 2019-03-29 | 2020-10-08 | 京东方科技集团股份有限公司 | Shelf vacancy rate calculation method and device, and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101809601A (en) * | 2007-08-31 | 2010-08-18 | 埃森哲环球服务有限公司 | Planogram extraction based on image processing |
| CN102523758A (en) * | 2010-08-31 | 2012-06-27 | 新日铁系统集成株式会社 | Augmented reality provision system, information processing terminal, information processor, augmented reality provision method, information processing method, and program |
| CN102982332A (en) * | 2012-09-29 | 2013-03-20 | 顾坚敏 | Retail terminal goods shelf image intelligent analyzing system based on cloud processing method |
| CN105701519A (en) * | 2014-12-10 | 2016-06-22 | 株式会社理光 | Realogram scene analysis of images: superpixel scene analysis |
| CN106934581A (en) * | 2017-03-31 | 2017-07-07 | 联想(北京)有限公司 | Information processing method, information processor and electronic equipment |
| CN107045641A (en) * | 2017-04-26 | 2017-08-15 | 广州图匠数据科技有限公司 | A kind of identification of pallets method based on image recognition technology |
| CN107730168A (en) * | 2017-09-28 | 2018-02-23 | 中南大学 | A kind of automatic vending machine automated stock control system and method based on image recognition |
| WO2018132691A1 (en) * | 2017-01-13 | 2018-07-19 | Bet Information Systems, Inc. | System and method for share of shelf data capture and analysis |
-
2018
- 2018-08-10 CN CN201810907163.6A patent/CN109190919A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101809601A (en) * | 2007-08-31 | 2010-08-18 | 埃森哲环球服务有限公司 | Planogram extraction based on image processing |
| CN102523758A (en) * | 2010-08-31 | 2012-06-27 | 新日铁系统集成株式会社 | Augmented reality provision system, information processing terminal, information processor, augmented reality provision method, information processing method, and program |
| CN102982332A (en) * | 2012-09-29 | 2013-03-20 | 顾坚敏 | Retail terminal goods shelf image intelligent analyzing system based on cloud processing method |
| CN105701519A (en) * | 2014-12-10 | 2016-06-22 | 株式会社理光 | Realogram scene analysis of images: superpixel scene analysis |
| WO2018132691A1 (en) * | 2017-01-13 | 2018-07-19 | Bet Information Systems, Inc. | System and method for share of shelf data capture and analysis |
| CN106934581A (en) * | 2017-03-31 | 2017-07-07 | 联想(北京)有限公司 | Information processing method, information processor and electronic equipment |
| CN107045641A (en) * | 2017-04-26 | 2017-08-15 | 广州图匠数据科技有限公司 | A kind of identification of pallets method based on image recognition technology |
| CN107730168A (en) * | 2017-09-28 | 2018-02-23 | 中南大学 | A kind of automatic vending machine automated stock control system and method based on image recognition |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020199776A1 (en) * | 2019-03-29 | 2020-10-08 | 京东方科技集团股份有限公司 | Shelf vacancy rate calculation method and device, and storage medium |
| CN109948736A (en) * | 2019-04-04 | 2019-06-28 | 上海扩博智能技术有限公司 | Commodity identification model active training method, system, equipment and storage medium |
| CN110543839A (en) * | 2019-08-20 | 2019-12-06 | 南京掌控网络科技有限公司 | commodity goods laying rate acquisition method based on computer vision |
| CN110781780A (en) * | 2019-10-11 | 2020-02-11 | 浙江大华技术股份有限公司 | Vacancy detection method and related device |
| CN111008804A (en) * | 2019-12-06 | 2020-04-14 | 拉货宝网络科技有限责任公司 | Intelligent recommendation method for goods position of warehouse goods |
| CN111008804B (en) * | 2019-12-06 | 2023-04-18 | 拉货宝网络科技有限责任公司 | Intelligent recommendation method for warehouse-in goods position of warehouse goods |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190919A (en) | It is sold critical sales index generation method, system, equipment and storage medium | |
| CN108647553B (en) | Method, system, device and storage medium for rapidly expanding images for model training | |
| CN108734162B (en) | Method, system, equipment and storage medium for identifying target in commodity image | |
| US20190193956A1 (en) | System for dynamic pallet-build | |
| CN108389230A (en) | Refrigerator capacity automatic testing method, system, equipment and storage medium | |
| CN109902636A (en) | Commodity identification model training method, system, equipment and storage medium | |
| CN110322300B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110648363A (en) | Camera posture determining method and device, storage medium and electronic equipment | |
| CN109918513A (en) | Image processing method, device, server and storage medium | |
| CN110516628A (en) | Shelf vacant locations merchandise news acquisition methods, system, equipment and storage medium | |
| EP4167194A1 (en) | Key point detection method and apparatus, model training method and apparatus, device and storage medium | |
| CN109885628A (en) | A kind of tensor transposition method, device, computer and storage medium | |
| CN109919716A (en) | Online shopping householder method, system, equipment and storage medium based on augmented reality | |
| CN110046116A (en) | A kind of tensor fill method, device, equipment and storage medium | |
| CN109948736A (en) | Commodity identification model active training method, system, equipment and storage medium | |
| CN110717405B (en) | Face feature point positioning method, device, medium and electronic equipment | |
| CN108805823A (en) | Commodity image antidote, system, equipment and storage medium | |
| CN111368860B (en) | Repositioning method and terminal equipment | |
| CN109598021B (en) | Information display method, device, equipment and storage medium | |
| CN114283398A (en) | Method and device for processing lane line and electronic equipment | |
| Shi et al. | Segment-based adaptive window and multi-feature fusion for stereo matching | |
| CN113360683A (en) | Method for training cross-modal retrieval model and cross-modal retrieval method and device | |
| CN108446693B (en) | Marking method, system, equipment and storage medium of target to be identified | |
| CN114972146A (en) | Image fusion method and device based on generation countermeasure type double-channel weight distribution | |
| CN113781653A (en) | Object model generation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |