CN108648338A - The shopping saving system method, apparatus and vending machine of automatic vending machine - Google Patents
The shopping saving system method, apparatus and vending machine of automatic vending machine Download PDFInfo
- Publication number
- CN108648338A CN108648338A CN201810327007.2A CN201810327007A CN108648338A CN 108648338 A CN108648338 A CN 108648338A CN 201810327007 A CN201810327007 A CN 201810327007A CN 108648338 A CN108648338 A CN 108648338A
- Authority
- CN
- China
- Prior art keywords
- end article
- target customer
- vending machine
- target
- image
- 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
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F9/00—Details other than those peculiar to special kinds or types of apparatus
- G07F9/002—Vending machines being part of a centrally controlled network of vending machines
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Abstract
The present invention relates to a kind of shopping saving system method of automatic vending machine, shopping saving system device, computer equipment, computer storage media and the vending machine of automatic vending machine, wherein method includes：The image before the automatic vending machine of shooting is obtained, target customer is identified from image.The end article paid close attention to according to image recognition target customer.Residence time of the target customer before automatic vending machine is calculated, and selection time of the target customer to end article is determined according to the residence time.According to the selection time, the sales performance information of end article is generated, it will be in the end article information of sales performance information deposit acquisition.The above method, by Image Acquisition identification record target customer to the selection time of end article, the target customer represented in conjunction with the feature of selection time is to the feedback information of end article, the sales performance information of corresponding end article is generated, the accuracy of the sales information of the end article of acquisition is effectively promoted.
Description
Technical field
The present invention relates to information acquiring technology fields, more particularly to a kind of shopping saving system side of automatic vending machine
Method, device, computer equipment, computer storage media and vending machine.
Background technology
Currently, vending machine such as automatic vending machine sets up site in each position in city, convenient clothes are provided for people
Business.Traditional store is compared, automatic vending machine has the advantages such as efficient of selling goods.In the operational process of automatic vending machine, usually
It needs to be acquired the merchandise news of vending machine, such as the acquisition to article sales data.The prior art is to merchandise news
When being acquired, the type of the merchandising typically obtained by camera or sensor or internal interface collection analysis and
The information of number.
However the prior art, in gathered data, the data of acquisition are only capable of reaction type of merchandize sum number purpose information, information
Acquisition is more single, cannot meet diversified shopping saving system needs, cannot accurately be reacted the letter of product features
Breath.
Invention content
Based on this, it is necessary in view of the above technical problems, provide a kind of letter that can be obtained and accurately acquire product features
The shopping saving system method of the automatic vending machine of breath, the shopping saving system device of automatic vending machine, computer equipment, calculating
Machine storage medium and vending machine.
A kind of shopping saving system method of automatic vending machine, the method includes：
The image before the automatic vending machine of shooting is obtained, target customer is identified from described image.
The end article of target customer's concern is identified according to described image.
Residence time of the target customer before automatic vending machine is calculated, and target visitor is determined according to the residence time
Selection time of the family to the end article.
According to the selection time, the sales performance information of the end article is generated, the sales performance information is deposited
In the end article information for entering acquisition.
The shopping saving system method of above-mentioned automatic vending machine only acquires commodity compared to traditional shopping saving system
The information of sales volume and sale type carries out sales performance information extraction to commodity, and the said program of the application passes through Image Acquisition
Identification record target customer is to selection time of end article, and according to the selection time of target customer, in conjunction with the selection time
The target customer that feature represents carries out the sales performance of various different classes of end articles the feedback information of end article
Analysis, generates the sales performance information of corresponding end article, effectively promotes the diversity to merchandise sales situation information extraction,
Promote the accuracy of the sales information of the end article of acquisition.
In one embodiment, described when determining selection of the target customer to the end article according to the residence time
Between the step of after, further include：Obtain the sales volume data of the end article；It is described according to the selection time, described in generation
The step of sales performance information of end article includes：According to the selection time and sales volume data, the end article is generated
Sales performance information.
The technical solution of above-described embodiment, except through acquisition image recording target customer to the selection of end article when
Between it is outer, also further read the sales volume data of end article, integration objective user when time to the selection temporal characteristics of end article,
And the sales volume data of current goal commodity, sales situation evaluation analysis is carried out to end article, generates corresponding sales performance
Information further promotes diversification and the accuracy of shopping saving system.
In one embodiment, described according to the selection time and sales volume data, generate the sale of the end article
Characteristic information includes：When the selection time is without departing from first time threshold, it is not attract to generate and mark the end article
The sales performance information of client；When the sales volume of the selection time beyond first time threshold and the end article is not up to sold
When measuring threshold value, it is to attract clients but sales performance information that sales volume is bad to generate and mark the end article.When the selection
Between the sales volume beyond first time threshold and end article when reaching predetermined sales volume, it is to inhale to generate and mark the end article
Draw client and the measured sales performance information of pin.
The technical solution of above-described embodiment, according to target customer to the selection time of end article and the pin of end article
Data are measured, classification of assessment are carried out to the sales situation of end article, by the selection temporal information of end article and end article pair
The Attraction Degree information association of client, by between the current sales volume information of end article and specified sales volume difference and end article it is smooth
End article is divided in the sale evaluating characteristic classification of corresponding classification, generates corresponding sales performance by pin degree information association
Information carries out accurately classification of assessment to end article feature, the sales information of commodity is intuitively known convenient for businessman, with to mesh
Mark the sales tactics adjusting and optimizing of commodity.
In one embodiment, described when the selection time is without departing from first time threshold, it generates and marks the mesh
Before marking the step of commodity are the sales performance information not attracted clients, further include：When the selection time is without departing from second
Between threshold value when, abandon it is described selection the time information；Wherein, the second time threshold is less than first time threshold.
When recording selection time of the target customer to end article, if the selection time of record is too short, the secondary selection
The record of time is likely to invalid data, such as client is only to pass by the vending machine and by the capture of camera short time
It arrives, and there is no the commodity on actual concern shelf by client.A second time threshold is arranged in the technical solution of above-described embodiment
Value rejects the selection temporal information less than the target customer of the second time threshold to selecting the information of time to screen,
Invalid selection time record can be screened out, the accuracy extracted to target customer's housing choice behavior time is promoted.
In one embodiment, the step of end article that target customer's concern is identified according to described image includes：
Obtain the shooting image in different monitoring region；Wherein, each monitoring area is formed to correspond and be closed with a kind of end article
System；The image obtained to the monitoring of each monitoring area carries out target signature identification, determines the monitoring area that the target is fallen into, according to
The monitoring area that the target is fallen into determines the end article of target customer's concern.
When being recorded to the selection time of end article to target customer, one has problem to be solved is how to sentence
Determining specifically which or which kind of the end article of existing customer concern can select to lead to as possible solution
Image recognition operation is crossed, the feature of the target customer and end article in image are extracted, to judge current goal client selection
End article, but this method has the defect of operation complexity.And the technical solution of the above embodiment of the present invention, it proposes for every
A kind of end article is corresponded by dividing monitoring area range with all kinds of end articles, according to the target of image recognition
The monitoring area that client falls into, the corresponding end article for differentiating target customer concern, this method is simple and is easily achieved, can be with
Effectively promote the efficiency of operation identification.
In one embodiment, the residence time for calculating the target customer before automatic vending machine, and according to institute
The step of stating the selection time that the residence time determines target customer to the end article include：To the video frame images of acquisition into
Row target identification, in the setting regions range before recognizing the target customer and falling into automatic vending machine, by corresponding frame image
It is included in the target classification, and the residence time of target customer described in start recording；The frame image that calculated for subsequent obtains
In target customer and target classification in frame image in target customer similarity parameter whether in threshold range, if
It is that then the frame image is included in the target classification；If recognize the target customer beyond setting regions range, stop
Only the residence time of the target customer is recorded, obtains the residence time of the target customer of record as the target customer couple
The selection time of the end article.
When the residence time to target customer carrying out timing, if counted according only to the character features of the client of acquisition
When, it is understood that there may be the case where multiple target customers continuously occur, such as custom queueing occurs, the residence time of different target client
Entered in the primary residence time by error count, causes to target stay time misregister.The technical solution of above-described embodiment,
According to the acquisition sequential of acquisition frame image, similarity identification sorting of operation, the phase that will continuously occur are carried out to the frame image of acquisition
Like degree, multiframe target customer is classified as a kind of progress timing in threshold range, can effectively distinguish the different mesh occurred in image
Client is marked, and timing respectively is carried out to different target customers, promotes the accuracy to target customer's residence time timing.
In one embodiment, in the target customer and target classification in the frame image that the calculated for subsequent obtains
The step of similarity parameter of target customer in frame image includes：Obtain the frame image subsequently obtained and the frame in target classification
The corresponding image data of target object in image obtains the characteristic point letter of the target object from described image data respectively
Breath, obtains fisrt feature point set and second feature point set；According to the information of the feature point set, fisrt feature point set is obtained
The two-way similarity distance between second feature point set is closed, is determined in the two framings image according to the two-way similarity distance
Identify the similarity of target.
The technical solution of above-described embodiment, by extracting the target customer in the frame image subsequently obtained and target point
The fisrt feature point set and second feature point set of the characteristic point information of target customer in frame image this two groups of images in class,
The two-way similarity distance between fisrt feature point set and second feature point set is calculated, fisrt feature point set and second are obtained
The information of the maximum mismatch degree of set of characteristic points, determines the similarity that target is identified in two framing images, can be simple and high
The extraction of effect ground compares the similarity of target customer in two groups of images.
In one embodiment, fisrt feature point set indicates such as relative to the unidirectional similarity distance of second feature point set
Under：
In above formula, H is fisrt feature point set, and G is second feature point set, and h is the feature in fisrt feature point set
Point, g are the characteristic point in second feature point set, and d (H, G) fisrt feature point sets are relative to the unidirectional of second feature point set
Similarity distance.
Second feature point set indicates as follows relative to the unidirectional similarity distance of fisrt feature point set：
In above formula, H is fisrt feature point set, and G is second feature point set, and h is the feature in fisrt feature point set
Point, g are the characteristic point in second feature point set, and d (G, H) second feature point sets are relative to the unidirectional of fisrt feature point set
Similarity distance.
The two-way similarity distance is obtained according to following formula：
D (H, G)=max (d (H, G), d (G, H))
The technical solution of above-described embodiment, by the unidirectional similarity distance between two groups of image feature point sets of calculating
Higher value, as the similarity of two groups of image feature point set sums, wherein each spy that unidirectional similarity distance Expressive Features point is concentrated
The information for levying the mismatch degree of the position relationship of point, by each characteristic point in one of calculating set relative to another
Characteristic point therein progress minimum distance match is corresponded to similitude, and obtained by the minimum range of any one characteristic point in set
The minimum range between similitude two-by-two is taken, then obtains the maximum value in each minimum range, two group pictures are extracted by distance operation
The information of maximum mismatch degree between the characteristic point of picture, operation mode are simple, it is easy to accomplish, it can effectively promote operation effect
Rate.
In one embodiment, described to obtain the frame image subsequently obtained and target customer in the frame image in target classification
Corresponding image data obtains the characteristic point information of the target customer from described image data, obtains fisrt feature respectively
The step of point set and second feature point set includes：According to the gray-scale intensity value of image to the frame image and target that subsequently obtain
The target customer identified in frame image in classification carries out shape segmentations, obtains the shaped wheel profile of the target customer, to even
The image of continuous frame obtains moving region and the shaped wheel profile for calculating and obtaining is compared as drop shadow curve；It is bent to calculate the projection
The center of gravity of line area image converts drop shadow curve to point set using the center of gravity as origin, and the information for obtaining the point set is target
The characteristic point information of client obtains fisrt feature point set and second feature point set.
The technical solution of above-described embodiment calculates center of gravity by the drop shadow curve of target customer's feature outlines of extraction
The characteristic point being converted into point set extraction image carries out operation, can simplify operational data, avoid to the entire feature of target customer
The pixel in region carries out operation, and the problem that efficiency is low caused by operand is huge and system loading is heavy promotes operation efficiency.
A kind of shopping saving system device of automatic vending machine, described device include：
Target customer's identification module, the image before automatic vending machine for obtaining shooting, is identified from described image
Target customer；
End article matching module, the end article for identifying target customer's concern according to described image；
Time recording module is selected, for calculating residence time of the target customer before automatic vending machine, and according to
The residence time determines selection time of the target customer to the end article；
Shopping saving system module, for according to the selection time, generating the sales performance information of the end article,
It will be in the end article information of sales performance information deposit acquisition.
The shopping saving system device of above-mentioned automatic vending machine only acquires commodity compared to traditional shopping saving system
The information of sales volume and sale type carries out sales performance information extraction to commodity, and the said program of the application passes through Image Acquisition
Identification record target customer is to selection time of end article, and according to the selection time of target customer, in conjunction with the selection time
The target customer that feature represents carries out the sales performance of various different classes of end articles the feedback information of end article
Analysis, generates the sales performance information of corresponding end article, effectively promotes the diversity to merchandise sales situation information extraction,
Promote the accuracy of the sales information of the end article of acquisition.
A kind of computer equipment, including memory, processor and storage can be run on a memory and on a processor
Computer program, the processor realize following steps when executing the computer program：
The image before the automatic vending machine of shooting is obtained, target customer is identified from described image；
The end article of target customer's concern is identified according to described image；
Residence time of the target customer before automatic vending machine is calculated, and target visitor is determined according to the residence time
Selection time of the family to the end article；
According to the selection time, the sales performance information of the end article is generated, the sales performance information is deposited
In the end article information for entering acquisition.
Above computer equipment, when processor executes program, by realizing step as above, so as to be adopted by image
Collect selection time of the identification record target customer to end article, and according to the selection time of target customer, in conjunction with the selection time
The target customer that represents of feature to the feedback information of end article, to the sales performances of various different classes of end articles into
Row analysis, generates the sales performance information of corresponding end article, is effectively promoted to the various of merchandise sales situation information extraction
Property, promote the accuracy of the sales information of the end article of acquisition.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Following steps are realized when row：
The image before the automatic vending machine of shooting is obtained, target customer is identified from described image；
The end article of target customer's concern is identified according to described image；
Residence time of the target customer before automatic vending machine is calculated, and target visitor is determined according to the residence time
Selection time of the family to the end article；
According to the selection time, the sales performance information of the end article is generated, the sales performance information is deposited
In the end article information for entering acquisition.
Above computer storage medium, the computer program of storage, by realizing step as above, so as to pass through figure
As acquiring selection time of the identification record target customer to end article, and according to the selection time of target customer, in conjunction with selection
The target customer that the feature of time represents is special to the sale of various different classes of end articles to the feedback information of end article
Sign is analyzed, and the sales performance information of corresponding end article is generated, and is effectively promoted to merchandise sales situation information extraction
Diversity promotes the accuracy of the sales information of the end article of acquisition.
The present invention also provides a kind of vending machine, the vending machine includes camera and the processing that is connect with the camera
The step of device, the processor executes the shopping saving system method of the automatic vending machine described in any embodiment as above.
Above-mentioned vending machine only acquires the information pair of the sales volume and sale type of commodity compared to traditional shopping saving system
Commodity carry out sales performance information extraction, and the vending machine of the application passes through figure when the merchandise news to vending machine is acquired
As acquiring selection time of the identification record target customer to end article, and according to the selection time of target customer, in conjunction with selection
The target customer that the feature of time represents is special to the sale of various different classes of end articles to the feedback information of end article
Sign is analyzed, and the sales performance information of corresponding end article is generated, and is effectively promoted to merchandise sales situation information extraction
Diversity promotes the accuracy of the sales information of the end article of acquisition.
Description of the drawings
Fig. 1 is the applied environment figure of the shopping saving system method of automatic vending machine in one embodiment；
Fig. 2 is the flow diagram of the shopping saving system method of automatic vending machine in one embodiment；
Fig. 3 is the flow diagram of the shopping saving system method of automatic vending machine in another embodiment；
Fig. 4 is the flow diagram of the sales performance information generation step of end article in one embodiment；
Fig. 5 is target customer in one embodiment to the flow diagram of the selection time obtaining step of end article；
Fig. 6 is the flow diagram that similarity parameter calculates step in one embodiment；
Fig. 7 is the structure diagram of the image capturing system of automatic vending machine in an application example；
Fig. 8 is the flow diagram of the shopping saving system method of automatic vending machine in an application example；
Fig. 9 is the structure diagram of the shopping saving system device of automatic vending machine in one embodiment；
Figure 10 is the structural schematic diagram of automatic vending machine in one embodiment.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the present invention, not
For limiting the present invention.
The shopping saving system method of automatic vending machine provided by the invention can be applied to application ring as shown in Figure 1
In border.Wherein, camera 110, shelf 11 front region of the camera towards automatic vending machine are installed on automatic vending machine 10
Image Acquisition is carried out, camera 110 connect with the processor 120 inside automatic vending machine, and camera 110 is by the automatic selling of shooting
Image data in front of cargo aircraft is transmitted to processor, the image data that processor processing receives, identification and acquisition automatic vending machine
Objects ahead client 20 to the end article 12 on the shelf 11 of automatic vending machine selection the time data, to end article 12
Information be acquired.
In one embodiment, as shown in Fig. 2, a kind of shopping saving system method of automatic vending machine is provided, with this
Method is applied to illustrate for the processor in Fig. 1, includes the following steps：
S210 obtains the image before the automatic vending machine of shooting, target customer is identified from described image.
Wherein, target customer refers to the personage occurred before automatic vending machine, as long as the personage occurred before automatic vending machine is special
Sign meets specific identification condition, can determine that the personage to have the behavioural characteristic of concern, example to made merchandise of automatic vending machine
The shelf direction for such as identifying personage's facial orientation automatic vending machine then can be determined that the personage is target customer.
In this step, processor can obtain the image before the automatic vending machine of shooting by camera, from the figure
The target customer in image is identified by image recognition algorithm as in.
S220 identifies the end article of target customer's concern according to described image.
Wherein, in a variety of commodity placed on the shelf for the automatic vending machine that end article refers to, target customer concern
Type commodity.If such as have beverage, snacks and paper handkerchief etc. on current shelf, pass through image recognition to current goal client pass
The commodity of note are the beverage on shelf, then beverage is end article.
In this step, processor carries out the end article of analysis and identification target customer's concern according to the image of acquisition.
S230 calculates residence time of the target customer before automatic vending machine, and is determined according to the residence time
Selection time of the target customer to the end article.
Wherein, the target customer that the residence time refers to enters and leaves the time of the predetermined areas before automatic vending machine
Difference, it refers to the time of concern behavior of the target customer to end article to select the time.
In this step, processor calculates residence time of the target customer before automatic vending machine, and according to described
Residence time determines selection time of the target customer to the end article.
S240 generates the sales performance information of the end article, the sales performance is believed according to the selection time
In the end article information of breath deposit acquisition.
Wherein, sales performance information is the evaluation information to the sales situation of the end article, such as the target quotient
The information whether product be in great demand or attract clients etc..
In this step, according to determining target customer to the selection time of the end article, analysis generates processor
The sales performance information of the end article, will be in the end article information of sales performance information deposit acquisition.
The shopping saving system method of above-mentioned automatic vending machine only acquires commodity compared to traditional shopping saving system
The information of sales volume and sale type carries out sales performance information extraction to commodity, and the said program of the application passes through Image Acquisition
Identification record target customer is to selection time of end article, and according to the selection time of target customer, in conjunction with the selection time
The target customer that feature represents carries out the sales performance of various different classes of end articles the feedback information of end article
Analysis, generates the sales performance information of corresponding end article, effectively promotes the diversity to merchandise sales situation information extraction,
Promote the accuracy of the sales information of the end article of acquisition.
In one embodiment, described when determining selection of the target customer to the end article according to the residence time
Between the step of after, further include：Obtain the sales volume data of the end article；It is described according to the selection time, described in generation
The step of sales performance information of end article includes：According to the selection time and sales volume data, the end article is generated
Sales performance information.
In one embodiment, as shown in figure 3, providing a kind of shopping saving system method of automatic vending machine, including
Following steps：
S310 obtains the image before the automatic vending machine of shooting, target customer is identified from described image.
S320 identifies the end article of target customer's concern according to described image.
S330 calculates residence time of the target customer before automatic vending machine, and is determined according to the residence time
Selection time of the target customer to the end article.
S340 obtains the sales volume data of the end article；
Wherein, sales volume data can be the number of the set period of time such as sales volume of this month or this season end article
According to the data can be pre-stored in vending machine memory and read, and can also be the target that real-time reception server is sent
The sales volume data of commodity.
S350 generates the sales performance information of the end article according to the selection time and sales volume data；
S360, will be in the end article information of sales performance information deposit acquisition.
The technical solution of above-described embodiment, except through acquisition image recording target customer to the selection of end article when
Between it is outer, also further read the sales volume data of end article, integration objective user when time to the selection temporal characteristics of end article,
And the sales volume data of current goal commodity, sales situation evaluation analysis is carried out to end article, generates corresponding sales performance
Information further promotes diversification and the accuracy of shopping saving system.
In one embodiment, as shown in figure 4, according to the selection time and sales volume data described in S350, described in generation
The sales performance information of end article includes：
S351, when the selection time is without departing from first time threshold, it is not attract to generate and mark the end article
The sales performance information of client；
S352, when the sales volume of the selection time beyond first time threshold and the end article is not up to sales volume threshold value
When, it is to attract clients but sales performance information that sales volume is bad to generate and mark the end article.
S353, when the sales volume of the selection time beyond first time threshold and the end article reaches predetermined sales volume
When, it is to attract clients and sell measured sales performance information to generate and mark the end article.
The technical solution of above-described embodiment, according to target customer to the selection time of end article and the pin of end article
Data are measured, classification of assessment are carried out to the sales situation of end article, by the selection temporal information of end article and end article pair
The Attraction Degree information association of client, by between the current sales volume information of end article and specified sales volume difference and end article it is smooth
End article is divided in the sale evaluating characteristic classification of corresponding classification, generates corresponding sales performance by pin degree information association
Information carries out accurately classification of assessment to end article feature, the sales information of commodity is intuitively known convenient for businessman, with to mesh
Mark the sales tactics adjusting and optimizing of commodity.
In one embodiment, in above-mentioned steps S351 when the selection time is without departing from first time threshold, it is raw
Before the step of marking the end article to be the sales performance information not attracted clients, further include：
S354 abandons the information of the selection time when the selection time is without departing from second time threshold；Wherein,
The second time threshold is less than first time threshold.
When recording selection time of the target customer to end article, if the selection time of record is too short, the secondary selection
The record of time is likely to invalid data, such as client is only to pass by the vending machine and by the capture of camera short time
It arrives, and there is no the commodity on actual concern shelf by client.A second time threshold is arranged in the technical solution of above-described embodiment
Value rejects the selection temporal information less than the target customer of the second time threshold to selecting the information of time to screen,
Invalid selection time record can be screened out, the accuracy extracted to target customer's housing choice behavior time is promoted.
In one embodiment, the step of identifying the end article of target customer's concern according to described image described in S220 is wrapped
It includes：
S221 obtains the shooting image in different monitoring region；Wherein, each monitoring area and a kind of end article shape
At one-to-one relationship；
Wherein, each monitoring area forms one-to-one relationship with a kind of end article, refers to each prison
Control area monitoring range, if target customer falls into the range, the target customer can be determined that for the end article into
Row concern.Such as can be end article for each classification, target customer's face characteristic such as eyes delimited,
Pay close attention to the regional extent for the camera site being likely to be at when the end article.Division for monitoring area can be to one
The image of camera acquisition carries out region division, can also be the image for acquiring different zones respectively by multiple cameras, again
Either two ways combination.
S222, the image obtained to the monitoring of each monitoring area carry out target signature identification, determine the prison that the target is fallen into
Region is controlled, the end article of target customer's concern is determined according to the monitoring area that the target is fallen into.
Wherein, it when multiple monitoring areas recognize target customer's feature, can be fallen by algorithm identification decision target
The one or more monitoring area ranges entered.
When being recorded to the selection time of end article to target customer, one has problem to be solved is how to sentence
Determining specifically which or which kind of the end article of existing customer concern can select to lead to as possible solution
Image recognition operation is crossed, the feature of the target customer and end article in image are extracted, to judge current goal client selection
End article, but this method has the defect of operation complexity.And the technical solution of the above embodiment of the present invention, it proposes for every
A kind of end article is corresponded by dividing monitoring area range with all kinds of end articles, according to the target of image recognition
The monitoring area that client falls into, the corresponding end article for differentiating target customer concern, this method is simple and is easily achieved, can be with
Effectively promote the efficiency of operation identification.
In one embodiment, stop before automatic vending machine as shown in figure 5, calculating the target customer described in S230
The time is stayed, and the step of determining selection time of the target customer to the end article according to the residence time includes：
S231 carries out target identification to the video frame images of acquisition, automatic vending is fallen into recognizing the target customer
When setting regions range before machine, corresponding frame image is included in the target classification, and target customer described in start recording
Residence time；
S232, calculated for subsequent obtain the frame image in target customer and target classification in frame image in target
Whether the similarity parameter of client is in threshold range, if so, the frame image is included in the target classification；
If S233 stops the stop to the target customer recognize the target customer beyond setting regions range
Time records, obtain residence time of the target customer of record as the target customer to the selection of the end article when
Between.
When the residence time to target customer carrying out timing, if counted according only to the character features of the client of acquisition
When, it is understood that there may be the case where multiple target customers continuously occur, such as custom queueing occurs, the residence time of different target client
Entered in the primary residence time by error count, causes to target stay time misregister.The technical solution of above-described embodiment,
According to the acquisition sequential of acquisition frame image, similarity identification sorting of operation, the phase that will continuously occur are carried out to the frame image of acquisition
Like degree, multiframe target customer is classified as a kind of progress timing in threshold range, can effectively distinguish the different mesh occurred in image
Client is marked, and timing respectively is carried out to different target customers, promotes the accuracy to target customer's residence time timing.
In one embodiment, the target customer in the frame image that calculated for subsequent described in S232 obtains and target point
The step of similarity parameter of the target customer in frame image in class includes：
S2321 obtains the frame image picture number corresponding with target object in the frame image in target classification subsequently obtained
According to the characteristic point information of the target object is obtained from described image data respectively, obtains fisrt feature point set and second
Set of characteristic points；
S2322 is obtained according to the information of the feature point set between fisrt feature point set and second feature point set
Two-way similarity distance determines the similarity that target is identified in the two framings image according to the two-way similarity distance.
The technical solution of above-described embodiment, by extracting the target customer in the frame image subsequently obtained and target point
The fisrt feature point set and second feature point set of the characteristic point information of target customer in frame image this two groups of images in class,
The two-way similarity distance between fisrt feature point set and second feature point set is calculated, fisrt feature point set and second are obtained
The information of the maximum mismatch degree of set of characteristic points, determines the similarity that target is identified in two framing images, can be simple and high
The extraction of effect ground compares the similarity of target customer in two groups of images.
Further, as shown in fig. 6, obtaining the frame image and mesh subsequently obtained in one embodiment, described in S2321
The corresponding image data of target customer in frame image in mark classification, obtains the target customer from described image data respectively
Characteristic point information, the step of obtaining fisrt feature point set and second feature point set includes：
S2321a knows the frame image subsequently obtained with the frame image in target classification according to the gray-scale intensity value of image
Other target customer carries out shape segmentations, obtains the shaped wheel profile of the target customer, and movement is obtained to the image of successive frame
The shaped wheel profile for calculating and obtaining is compared as drop shadow curve in region；
S2321b calculates the center of gravity of drop shadow curve's area image, converts drop shadow curve to using the center of gravity as origin
Point set, the information for obtaining the point set is the characteristic point information of target customer, obtains fisrt feature point set and second feature point
Set.
Wherein, fisrt feature point set is combined into the set of the characteristic point of target customer in the frame image subsequently obtained, and second is special
Sign point set is combined into the set of the characteristic point of target customer in target classification.
The technical solution of above-described embodiment calculates center of gravity by the drop shadow curve of target customer's feature outlines of extraction
The characteristic point being converted into point set extraction image carries out operation, can simplify operational data, avoid to the entire feature of target customer
The pixel in region carries out operation, and the problem that efficiency is low caused by operand is huge and system loading is heavy promotes operation efficiency.
In one embodiment, as shown in fig. 6, according to the information of the feature point set described in S2322, it is special to obtain first
Sign point set and second feature point set between two-way similarity distance include：
S2322a is obtained each in second feature point set respectively for each characteristic point in fisrt feature point set
The minimum range of a characteristic point and this feature point chooses the maximum value in each minimum range, is fisrt feature point set
Unidirectional similarity distance relative to second feature point set；
Wherein, fisrt feature point set indicates as follows relative to the unidirectional similarity distance of second feature point set：
In above formula, H is fisrt feature point set, and G is second feature point set, and h is the feature in fisrt feature point set
Point, g are the characteristic point in second feature point set, and d (H, G) fisrt feature point sets are relative to the unidirectional of second feature point set
Similarity distance.
D (H, G) is not the actual distance of two point sets, but in set G with certain point h in set HiDistance it is minimum
gjDistance | | hi- gj | | it is ranked up, d (H, G) is maximum value therein.
S2322b is obtained each in fisrt feature point set respectively for each characteristic point in second feature point set
The minimum range of a characteristic point and this feature point chooses the maximum value in each minimum range, is second feature point set
Unidirectional similarity distance relative to fisrt feature point set；
Wherein, second feature point set indicates as follows relative to the unidirectional similarity distance of fisrt feature point set：
In above formula, H is fisrt feature point set, and G is second feature point set, and h is the feature in fisrt feature point set
Point, g are the characteristic point in second feature point set, and d (G, H) second feature point sets are relative to the unidirectional of fisrt feature point set
Similarity distance.
D (G, H) is not the actual distance of two point sets, but in set H with certain point g in set GjDistance it is minimum
hiDistance | | gj-hi| | it is ranked up, d (G, H) is maximum value therein.
S2322c obtains unidirectional similarity distance and second feature of the fisrt feature point set relative to second feature point set
Point set is fisrt feature point set and second feature relative to the higher value in the unidirectional similarity distance of fisrt feature point set
Two-way similarity distance between point set.
Wherein, the two-way similarity distance is obtained according to following formula：
D (H, G)=max (d (H, G), d (G, H))
Two-way similarity distance D (H, G) is unidirectional similarity distance d (H, G) and the greater in d (G, H), and D (H, G) is described
The maximum mismatch degree of the set of characteristic points of two images.
The technical solution of above-described embodiment, by the unidirectional similarity distance between two groups of image feature point sets of calculating
Higher value, as the similarity of two groups of image feature point set sums, wherein each spy that unidirectional similarity distance Expressive Features point is concentrated
The information for levying the mismatch degree of the position relationship of point, by each characteristic point in one of calculating set relative to another
Characteristic point therein progress minimum distance match is corresponded to similitude, and obtained by the minimum range of any one characteristic point in set
The minimum range between similitude two-by-two is taken, then obtains the maximum value in each minimum range, two group pictures are extracted by distance operation
The information of maximum mismatch degree between the characteristic point of picture, operation mode are simple, it is easy to accomplish, it can effectively promote operation effect
Rate.
It should be understood that although each step in the flow chart of Fig. 2-6 is shown successively according to the instruction of arrow,
These steps are not that the inevitable sequence indicated according to arrow executes successively.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-6
Part steps may include that either these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can either the sub-step of other steps or at least part in stage be in turn or alternately with other steps
It executes.
In order to enable the shopping saving system method of the automatic vending machine of the embodiment of the present invention is more clearly understood, below with
One is specifically illustrated the shopping saving system method of the automatic vending machine of the present invention using example.
The present invention applies the shopping saving system method of exemplary automatic vending machine, and it is exemplary to can be applied to present invention application
In the shopping saving system system of automatic vending machine, the shopping saving system system of the automatic vending machine acquires visitor using camera
The image of the buying behavior at family, and classified to the identification of the image progress similar purpose of acquisition by similar recognizer.
As shown in fig. 7, the present invention in the shopping saving system system of exemplary automatic vending machine using being mounted with image and adopt
Collecting system 700, image capturing system 700 include image capture module 710, data processing module 720 and system feedback model
730.Wherein, image capture module 710 acquires the image before automatic vending machine by camera, matches in data processing module 720
The program for having set similar recognizer carries out target identification to the client in image, to the target customer that identifies into row information
Sort out, further analyzes the selection time of client and the end article of corresponding selection.
As shown in figure 8, the present invention carries out similitude identification to client, client's single purchase commodity behavior is quickly recognized
Select the time.It is more than the specified selection time when the image data similarity of continuous acquisition is more than threshold value and continuous acquisition time
Under the conditions of, system starts to carry out customer data the data processing of next step, represents client using first frame image and records visitor
Finally buy the selection time of commodity behavior in family.In conjunction with acquisition user to the selection time of end article and end article
Merchandise sales situation is divided into 3 kinds by sales volume：Commodity attract clients and sales volume is good, commodity attract clients but sales volume is bad or quotient
Product do not attract clients.
When the image data similarity of the image data currently acquired and current comparison set is less than threshold value, system will be remembered
Record the buying behavior time span of previous client；And present image is set as the second client, increases a customer data collection newly and merges
Reset similar parameter, the then identification similar to new customer data set progress of next frame image.
When the set continuous acquisition time, which is less than system nominal, selects the time, system will abandon the set.
The present invention applies the shopping saving system method of exemplary automatic vending machine, when camera collects each user couple
The data of the selection time of commodity are simultaneously fed back in server, can subsequently be carried out according to the selection time analysis customer priorities of acquisition
The maximization of sale benefit is realized in the adjustment of merchandise sales strategy.
In one embodiment, as shown in figure 9, providing a kind of shopping saving system device of automatic vending machine, including：
Target customer's identification module 910, the image before automatic vending machine for obtaining shooting, identifies from described image
Go out target customer；
End article matching module 920, the end article for identifying target customer's concern according to described image；
Time recording module 930 is selected, for calculating residence time of the target customer before automatic vending machine, and root
Selection time of the target customer to the end article is determined according to the residence time；
Shopping saving system module 950, for according to the selection time, generating the sales performance letter of the end article
Breath, will be in the end article information of sales performance information deposit acquisition.
The shopping saving system device of above-mentioned automatic vending machine only acquires commodity compared to traditional shopping saving system
The information of sales volume and sale type carries out sales performance information extraction to commodity, and the said program of the application passes through Image Acquisition
Identification record target customer is to selection time of end article, and according to the selection time of target customer, in conjunction with the selection time
The target customer that feature represents carries out the sales performance of various different classes of end articles the feedback information of end article
Analysis, generates the sales performance information of corresponding end article, effectively promotes the diversity to merchandise sales situation information extraction,
Promote the accuracy of the sales information of the end article of acquisition.
In one embodiment, the shopping saving system device of the automatic vending machine further includes：
Sales volume acquisition module 940, the sales volume data for obtaining the end article；
The shopping saving system module 950 is further used for according to the selection time and sales volume data, described in generation
The sales performance information of end article.
In one embodiment, the shopping saving system module 950 be further used for when the selection time without departing from
When first time threshold, it is the sales performance information not attracted clients to generate and mark the end article；When the selection time
When sales volume beyond first time threshold and the end article is not up to sales volume threshold value, it is to inhale to generate and mark the end article
Draw client but the bad sales performance information of sales volume；When selection time is beyond first time threshold and the end article
When sales volume reaches predetermined sales volume, it is to attract clients and sell measured sales performance information to generate and mark the end article.
In one embodiment, the shopping saving system module 950 is additionally operable to when the selection time is without departing from second
When time threshold, the information of the selection time is abandoned；Wherein, the second time threshold is less than first time threshold.
In one embodiment, the end article matching module 920 includes：
Multizone image collection module 921, the shooting image for obtaining different monitoring region；Wherein, each prison
It controls region and forms one-to-one relationship with a kind of end article；
Commodity determining module 922 is paid close attention to, the image for being obtained to the monitoring of each monitoring area carries out target signature identification, really
The monitoring area that the fixed target is fallen into determines target customer's concern according to the monitoring area that the target is fallen into
End article.
In one embodiment, the selection time recording module 930 includes：
Timing module 931 is originated, target identification is carried out for the video frame images to acquisition, is recognizing the target visitor
When family falls into the setting regions range before automatic vending machine, corresponding frame image is included in the target classification, and start recording
The residence time of the target customer；
Similarity comparison module 932 is used for the target customer in the frame image that calculated for subsequent obtains and target classification
In frame image in target customer similarity parameter whether in threshold range, if so, the frame image is included in institute
It states in target classification；
Timing module 933 is terminated, if when for recognizing the target customer beyond setting regions range, stopping to described
Residence time of target customer records, and obtains residence time of the target customer of record as the target customer to the target
The selection time of commodity.
In one embodiment, the similarity comparison module 932 includes：
Feature point extraction module 9321, for obtaining the frame image subsequently obtained and target in the frame image in target classification
The corresponding image data of object, the characteristic point information of the target object is obtained from described image data, obtains first respectively
Set of characteristic points and second feature point set；
Similarity calculation module 9322, for according to the information of the feature point set, obtaining fisrt feature point set and the
Two-way similarity distance between two set of characteristic points determines in the two framings image according to the two-way similarity distance and identifies mesh
Target similarity.
In one embodiment, in similarity calculation module 9322 fisrt feature point set relative to second feature point set
Unidirectional similarity distance indicate it is as follows：
In above formula, H is fisrt feature point set, and G is second feature point set, and h is the feature in fisrt feature point set
Point, g are the characteristic point in second feature point set, and d (H, G) fisrt feature point sets are relative to the unidirectional of second feature point set
Similarity distance.
Unidirectional similarity distance of the second feature point set relative to fisrt feature point set in similarity calculation module 9322
It indicates as follows：
In above formula, H is fisrt feature point set, and G is second feature point set, and h is the feature in fisrt feature point set
Point, g are the characteristic point in second feature point set, and d (G, H) second feature point sets are relative to the unidirectional of fisrt feature point set
Similarity distance.
Two-way similarity distance described in similarity calculation module 9322 is obtained according to following formula：
D (H, G)=max (d (H, G), d (G, H))
In one embodiment, the feature point extraction module 9321 includes：
Drop shadow curve extraction module 9321a, for according to the gray-scale intensity value of image to the frame image and mesh that subsequently obtain
The target customer identified in frame image in mark classification carries out shape segmentations, obtains the shaped wheel profile of the target customer, right
The image of successive frame obtains moving region and the shaped wheel profile for calculating and obtaining is compared as drop shadow curve；
Feature point set acquisition module 9321b, the center of gravity for calculating drop shadow curve's area image, by drop shadow curve with
The center of gravity is that origin is converted into point set, and the information for obtaining the point set is the characteristic point information of target customer, obtains fisrt feature
Point set and second feature point set.
The specific restriction of shopping saving system device about automatic vending machine may refer to above for automatic vending
The restriction of the shopping saving system method of machine, details are not described herein.In the shopping saving system device of above-mentioned automatic vending machine
Modules can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware
Or independently of in the processor in computer equipment, can also in a software form be stored in the memory in computer equipment,
The corresponding operation of the above modules is executed in order to which processor calls.
The shopping saving system device of the automatic vending machine of the present invention and the merchandise news of the automatic vending machine of the present invention are adopted
Set method correspond, above-mentioned automatic vending machine shopping saving system method embodiment illustrate technical characteristic and its have
Beneficial effect suitable for the embodiment of the shopping saving system device of automatic vending machine, hereby give notice that.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor are realized described in any embodiment as above certainly when executing computer program
The step of shopping saving system method of dynamic vending machine.
Above computer equipment, when processor executes program, by realizing step as above, so as to be adopted by image
Collect selection time of the identification record target customer to end article, and according to the selection time of target customer, in conjunction with the selection time
The target customer that represents of feature to the feedback information of end article, to the sales performances of various different classes of end articles into
Row analysis, generates the sales performance information of corresponding end article, is effectively promoted to the various of merchandise sales situation information extraction
Property, promote the accuracy of the sales information of the end article of acquisition.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step of shopping saving system method of automatic vending machine described in any embodiment as above when being executed by processor.
Above computer readable storage medium storing program for executing, the computer program of storage, by realizing step as above, so as to logical
Selection time of the Image Acquisition identification record target customer to end article is spent, and according to the selection time of target customer, in conjunction with
Feedback information of the target customer that the feature of time represents to end article is selected, to the pin of various different classes of end articles
It sells feature to be analyzed, generates the sales performance information of corresponding end article, effectively promoted and merchandise sales situation information is carried
The diversity taken promotes the accuracy of the sales information of the end article of acquisition.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein,
Any reference to memory, storage, database or other media used in each embodiment provided by the present invention,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
The present invention also provides a kind of vending machines, as shown in Figure 10, the vending machine 100 include camera 1010 and with it is described
The processor 1020 that camera 1010 connects, the processor 1020 execute the automatic vending machine described in any embodiment as above
The step of shopping saving system method.
Above-mentioned vending machine only acquires the information pair of the sales volume and sale type of commodity compared to traditional shopping saving system
Commodity carry out sales performance information extraction, and the vending machine of the application passes through figure when the merchandise news to vending machine is acquired
As acquiring selection time of the identification record target customer to end article, and according to the selection time of target customer, in conjunction with selection
The target customer that the feature of time represents is special to the sale of various different classes of end articles to the feedback information of end article
Sign is analyzed, and the sales performance information of corresponding end article is generated, and is effectively promoted to merchandise sales situation information extraction
Diversity promotes the accuracy of the sales information of the end article of acquisition.
Each technical characteristic of above example can be combined arbitrarily, to keep description succinct, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield is all considered to be the range of this specification record.
Several embodiments of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Range.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of shopping saving system method of automatic vending machine, the method includes：
The image before the automatic vending machine of shooting is obtained, target customer is identified from described image；
The end article of target customer's concern is identified according to described image；
Residence time of the target customer before automatic vending machine is calculated, and target customer couple is determined according to the residence time
The selection time of the end article；
According to the selection time, the sales performance information of the end article is generated, sales performance information deposit is adopted
In the end article information of collection.
2. the shopping saving system method of automatic vending machine according to claim 1, which is characterized in that described in the basis
After residence time determines the step of selection time of the target customer to the end article, further include：
Obtain the sales volume data of the end article；
It is described according to the selection time, the step of sales performance information for generating the end article includes：
According to the selection time and sales volume data, the sales performance information of the end article is generated.
3. the shopping saving system method of automatic vending machine according to claim 1, which is characterized in that described in the basis
Selection time and sales volume data, the sales performance information for generating the end article include：
When the selection time is without departing from first time threshold, it is the sale not attracted clients to generate and mark the end article
Characteristic information；
When the sales volume of the selection time beyond first time threshold and the end article is not up to sales volume threshold value, mark is generated
Remember that the end article is to attract clients but sales performance information that sales volume is bad；
When the sales volume of the selection time beyond first time threshold and the end article reaches predetermined sales volume, label is generated
The end article is to attract clients and sell measured sales performance information.
4. the shopping saving system method of automatic vending machine according to claim 1, which is characterized in that described in the basis
Selection time and sales volume data, the sales performance information for generating the end article further include：
When the selection time is without departing from first time threshold, the information of the selection time is abandoned；Wherein, described second when
Between threshold value be less than first time threshold.
5. the shopping saving system method of automatic vending machine according to claim 1, which is characterized in that described in the basis
Image recognition target customer concern end article the step of include：
Obtain the shooting image in different monitoring region；Wherein, each monitoring area forms an a pair with a kind of end article
It should be related to；
The image obtained to the monitoring of each monitoring area carries out target signature identification, determines the monitoring area that the target is fallen into, root
The end article of target customer's concern is determined according to the monitoring area that the target is fallen into.
6. the shopping saving system method of automatic vending machine according to claim 1, which is characterized in that described in the calculating
Residence time of the target customer before automatic vending machine, and determine target customer to the end article according to the residence time
The selection time the step of include：
Target identification, the setting before recognizing the target customer and falling into automatic vending machine are carried out to the video frame images of acquisition
When regional extent, corresponding frame image is included in the target classification, and the residence time of target customer described in start recording；
The phase of target customer and the target customer in the frame image in target classification in the frame image that calculated for subsequent obtains
Like degree parameter whether in threshold range, if so, the frame image is included in the target classification；
If recognize the target customer beyond setting regions range, stop recording the residence time of the target customer,
The residence time of the target customer of acquisition record is as the target customer to the selection time of the end article.
7. the shopping saving system method of automatic vending machine according to claim 1, which is characterized in that the calculated for subsequent obtains
The frame image in target customer and target classification in frame image in target customer similarity parameter the step of wrap
It includes：
The frame image image data corresponding with target object in the frame image in target classification subsequently obtained is obtained, respectively from institute
The characteristic point information for obtaining the target object in image data is stated, fisrt feature point set and second feature point set are obtained；
According to the information of the feature point set, obtain between fisrt feature point set and second feature point set it is two-way it is similar away from
From, according to the two-way similarity distance determine in the two framings image identify target similarity；Wherein, described two-way similar
Distance is obtained according to following formula：
D (H, G)=max (d (H, G), d (G, H))
Wherein,
In above formula, H is fisrt feature point set, and G is second feature point set, and D (H, G) is that fisrt feature point set and second are special
The two-way similarity distance between point set is levied, d (H, G) fisrt feature point sets are relative to the unidirectional similar of second feature point set
Distance, d (G, H) are unidirectional similarity distance of the second feature point set relative to fisrt feature point set.
8. the shopping saving system method of automatic vending machine according to claim 2, which is characterized in that described to obtain subsequently
The frame image of acquisition image data corresponding with target customer in the frame image in target classification, respectively from described image data
The characteristic point information for obtaining the target customer, the step of obtaining fisrt feature point set and second feature point set include：
According to the gray-scale intensity value of image to the frame image that subsequently obtains and the target visitor that is identified in the frame image in target classification
Family carries out shape segmentations, obtains the shaped wheel profile of the target customer, and obtaining moving region to the image of successive frame compares
To calculating the shaped wheel profile obtained as drop shadow curve；
The center of gravity for calculating drop shadow curve's area image converts drop shadow curve to point set by origin of the center of gravity, obtains institute
The information for stating point set is the characteristic point information of target customer, obtains fisrt feature point set and second feature point set.
9. a kind of shopping saving system device of automatic vending machine, which is characterized in that described device includes：
Target customer's identification module, the image before automatic vending machine for obtaining shooting, identifies target from described image
Client；
End article matching module, the end article for identifying target customer's concern according to described image；
Time recording module is selected, for calculating residence time of the target customer before automatic vending machine, and according to described
Residence time determines selection time of the target customer to the end article；
Shopping saving system module, for according to the selection time, the sales performance information of the end article being generated, by institute
In the end article information for stating the deposit acquisition of sales performance information.
10. a kind of vending machine, which is characterized in that the vending machine includes camera and the processor that is connect with the camera,
The processor executes the step of shopping saving system method such as automatic vending machine described in any item of the claim 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810327007.2A CN108648338B (en) | 2018-04-12 | 2018-04-12 | Commodity information acquisition method and device for vending machine and vending machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810327007.2A CN108648338B (en) | 2018-04-12 | 2018-04-12 | Commodity information acquisition method and device for vending machine and vending machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108648338A true CN108648338A (en) | 2018-10-12 |
| CN108648338B CN108648338B (en) | 2021-01-12 |
Family
ID=63745918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810327007.2A Active CN108648338B (en) | 2018-04-12 | 2018-04-12 | Commodity information acquisition method and device for vending machine and vending machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108648338B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109447756A (en) * | 2018-10-31 | 2019-03-08 | 李义 | A kind of unattended supermarket shopping method and system |
| CN111626201A (en) * | 2020-05-26 | 2020-09-04 | 创新奇智(西安)科技有限公司 | Commodity detection method and device and readable storage medium |
| CN111667012A (en) * | 2020-06-10 | 2020-09-15 | 创新奇智(广州)科技有限公司 | Classification result correction method and device, correction equipment and readable storage medium |
| CN111935229A (en) * | 2020-07-10 | 2020-11-13 | 北京云迹科技有限公司 | Intelligent container pushing method and device and electronic equipment |
| WO2023070844A1 (en) * | 2021-10-25 | 2023-05-04 | 广州广电运通金融电子股份有限公司 | Intelligent design method for personalized discount coupon, and electronic apparatus and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894536A (en) * | 2016-03-30 | 2016-08-24 | 中国农业大学 | Method and system for analyzing livestock behaviors on the basis of video tracking |
| CN106776619A (en) * | 2015-11-20 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for determining the attribute information of destination object |
| CN107016004A (en) * | 2016-01-28 | 2017-08-04 | 百度在线网络技术（北京）有限公司 | Image processing method and device |
| CN107229921A (en) * | 2017-06-09 | 2017-10-03 | 济南大学 | Dynamic gesture identification method based on Hausdorff distances |
| CN206546607U (en) * | 2017-03-14 | 2017-10-10 | 帮团成都电子商务有限责任公司 | A kind of automatic vending machine and retail kiosk |
| CN107493319A (en) * | 2017-07-18 | 2017-12-19 | 上海千帆科技股份有限公司 | A kind of intelligent interaction Multimedia System and its implementation |
| CN107798560A (en) * | 2017-10-23 | 2018-03-13 | 武汉科技大学 | A kind of retail shop's individual character advertisement intelligent method for pushing and system |
-
2018
- 2018-04-12 CN CN201810327007.2A patent/CN108648338B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776619A (en) * | 2015-11-20 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for determining the attribute information of destination object |
| CN107016004A (en) * | 2016-01-28 | 2017-08-04 | 百度在线网络技术（北京）有限公司 | Image processing method and device |
| CN105894536A (en) * | 2016-03-30 | 2016-08-24 | 中国农业大学 | Method and system for analyzing livestock behaviors on the basis of video tracking |
| CN206546607U (en) * | 2017-03-14 | 2017-10-10 | 帮团成都电子商务有限责任公司 | A kind of automatic vending machine and retail kiosk |
| CN107229921A (en) * | 2017-06-09 | 2017-10-03 | 济南大学 | Dynamic gesture identification method based on Hausdorff distances |
| CN107493319A (en) * | 2017-07-18 | 2017-12-19 | 上海千帆科技股份有限公司 | A kind of intelligent interaction Multimedia System and its implementation |
| CN107798560A (en) * | 2017-10-23 | 2018-03-13 | 武汉科技大学 | A kind of retail shop's individual character advertisement intelligent method for pushing and system |
Non-Patent Citations (1)
| Title |
|---|
| 刘波等: "基于射线轮廓点匹配的生猪红外与可见光图像自动配准", 《农业工程学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109447756A (en) * | 2018-10-31 | 2019-03-08 | 李义 | A kind of unattended supermarket shopping method and system |
| CN111626201A (en) * | 2020-05-26 | 2020-09-04 | 创新奇智(西安)科技有限公司 | Commodity detection method and device and readable storage medium |
| CN111626201B (en) * | 2020-05-26 | 2023-04-28 | 创新奇智(西安)科技有限公司 | Commodity detection method, commodity detection device and readable storage medium |
| CN111667012A (en) * | 2020-06-10 | 2020-09-15 | 创新奇智(广州)科技有限公司 | Classification result correction method and device, correction equipment and readable storage medium |
| CN111935229A (en) * | 2020-07-10 | 2020-11-13 | 北京云迹科技有限公司 | Intelligent container pushing method and device and electronic equipment |
| WO2023070844A1 (en) * | 2021-10-25 | 2023-05-04 | 广州广电运通金融电子股份有限公司 | Intelligent design method for personalized discount coupon, and electronic apparatus and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108648338B (en) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108648338A (en) | The shopping saving system method, apparatus and vending machine of automatic vending machine | |
| Chen et al. | Multimodal object detection via probabilistic ensembling | |
| US11335092B2 (en) | Item identification method, system and electronic device | |
| CN104732413B (en) | A kind of intelligent personalized video ads method for pushing and system | |
| RU2769888C2 (en) | System for identifying fresh products for a retail trade cash terminal | |
| Liu et al. | A smart unstaffed retail shop based on artificial intelligence and IoT | |
| Nam et al. | Pest detection on traps using deep convolutional neural networks | |
| Noh et al. | A new framework for background subtraction using multiple cues | |
| CN108171207A (en) | Face identification method and device based on video sequence | |
| US8498454B2 (en) | Optimal subspaces for face recognition | |
| CN109086873A (en) | Training method, recognition methods, device and the processing equipment of recurrent neural network | |
| CN110175590A (en) | A kind of commodity recognition method and device | |
| US11599983B2 (en) | System and method for automated electronic catalogue management and electronic image quality assessment | |
| US20080175447A1 (en) | Face view determining apparatus and method, and face detection apparatus and method employing the same | |
| CN111222870B (en) | Settlement method, device and system | |
| CN106874922B (en) | Method and device for determining service parameters | |
| Gothai et al. | Design features of grocery product recognition using deep learning | |
| CN113468914A (en) | Method, device and equipment for determining purity of commodities | |
| CN111242094B (en) | Commodity identification method, intelligent container and intelligent container system | |
| CN110929668A (en) | Commodity detection method and device based on unmanned goods shelf | |
| Korhonen | Assessing personally perceived image quality via image features and collaborative filtering | |
| CN116452636A (en) | Target tracking-based dynamic commodity identification method and related device for unmanned sales counter | |
| WO2021214880A1 (en) | Processing device, processing method, and program | |
| CN108875503A (en) | Method for detecting human face, device, system, storage medium and capture machine | |
| CN110781752A (en) | Object identification method for dynamic visual intelligent cabinet under multi-class scene |
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 |