CN109166007A - A kind of Method of Commodity Recommendation and its device based on automatic vending machine - Google Patents
A kind of Method of Commodity Recommendation and its device based on automatic vending machine Download PDFInfo
- Publication number
- CN109166007A CN109166007A CN201810964683.0A CN201810964683A CN109166007A CN 109166007 A CN109166007 A CN 109166007A CN 201810964683 A CN201810964683 A CN 201810964683A CN 109166007 A CN109166007 A CN 109166007A
- Authority
- CN
- China
- Prior art keywords
- user
- shopping
- recommendations
- vending machine
- commodity
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F7/00—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus
- G07F7/08—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus by coded identity card or credit card or other personal identification means
- G07F7/10—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus by coded identity card or credit card or other personal identification means together with a coded signal, e.g. in the form of personal identification information, like personal identification number [PIN] or biometric data
-
- 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
-
- 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
- G07F9/02—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus
- G07F9/026—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus for alarm, monitoring and auditing in vending machines or means for indication, e.g. when empty
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Human Computer Interaction (AREA)
- Computer Security & Cryptography (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)
Abstract
The present invention provides a kind of Method of Commodity Recommendation and its device based on automatic vending machine, if user is to have authenticated user, obtains the authentication information of user the method comprise the steps that authenticating to user；History purchaser record is obtained according to the authentication information of the user；Determine the corresponding Recommendations of user；According to Recommendations, product display zone corresponding with Recommendations is determined；Also, the corresponding LED light bright light in product display zone is controlled, to prompt user to buy the Recommendations in product display zone.The present invention realizes the frequent purchase for user or the intelligent recommendation of the corresponding Recommendations of habit point of interest, directly the product display zone of the corresponding Recommendations of user is carried out to light LED light prompt, the lookup of the Recommendations of Habit Buying is provided convenience for user, improve shopping efficiency, shopping-time is saved, user experience is improved.
Description
Technical field
The present invention relates to automatic vending machine technical fields, more specifically to a kind of commodity based on automatic vending machine
Recommended method and its device.
Background technique
Substance circulating is the most basic element of human society.Retail trade is directly facing the open of consumer's sale
The important means that relevant industries (hereinafter referred to as retail trade or retailer) circulate as material present needs to employ a large amount of
Cashier realize the dealing work of commodity, cashier counts consumer's purchase piece by piece, statistics is completed
Afterwards, it completes to pay jointly with consumer.
And automatic vending machine, then it solves the artificial defect for counting and manually settling accounts of retail trade, is a kind of towards disappearing
The self-service of expense person, Automatic-settlement sell mode.The product of the selected commodity of user can be counted by the selection of user
Kind type and total value complete payment process so that user settles accounts.But in based on open automatic vending machine, use
In the shopping process of family, observation selection is carried out one by one in numerous commodity that user can only be displayed in automatic vending machine, for certainly
Commodity in dynamic vending machine are checked one by one, can just select the commodity of user's needs, the kind of display goods is more, makes to user
At to choose the time longer, cause user to do shopping low efficiency, can not select in a short time often buying or needs
Commodity.
In short, current existing automatic vending machine, can only manually be carried out by user to all commodity in automatic vending machine
It is observed one by one, the commodity of user's needs could be selected from large number of display goods, user is can not achieve and exists
Commodity that user often buys or needs are found in short time, are led to user's shopping low efficiency, are wasted the plenty of time, influence
The shopping-time of other consumers, poor user experience.
Summary of the invention
In view of this, the present invention provides a kind of Method of Commodity Recommendation based on automatic vending machine and its device is existing to solve
The deficiency of technology.
To solve the above problems, the present invention provides a kind of Method of Commodity Recommendation based on automatic vending machine, comprising:
User is authenticated, if the user is to have authenticated user, obtains the authentication information of the user；
Based on historical purchase data library, the institute in the historical purchase data library is obtained according to the authentication information of the user
State the corresponding history purchaser record of user；
The corresponding Recommendations of the user are determined according to the history purchaser record and the authentication information；
According to the Recommendations, product display zone corresponding with the Recommendations is determined；Also,
The corresponding LED light bright light in the product display zone is controlled, to prompt the user to the product display zone
The interior Recommendations are bought.
Preferably, described " the corresponding LED light bright light in the product display zone to be controlled, to prompt the user to institute
The Recommendations stated in product display zone are bought " after, further includes:
Receive the shopping enabled instruction generated by user shopping the first infrared sensor of gesture trigger；
According to the shopping enabled instruction, the current shopping items taken to the user are identified, according to identification
As a result judge whether the current shopping items are the Recommendations；
If the current shopping items are the Recommendations, the corresponding product display zone of the Recommendations is closed
LED light.
It is preferably, described that " according to the shopping enabled instruction, the current shopping items taken to the user are known
Not, judge whether the current shopping items are the Recommendations according to recognition result " include:
According to the shopping enabled instruction, the shopping continuous shooting image of the shopping gesture of the user is acquired；
Extract the key frame in the shopping continuous shooting image；
Outline identification is carried out to each key frame, obtaining in key frame includes shopping gesture and shopping gesture crawl
The current shopping items gesture profile；
The corresponding gesture screenshot of each key frame is obtained according to the gesture profile；
The gesture screenshot is identified based on commodity identification model trained in advance, judged according to recognition result described in
Whether the current shopping items in gesture screenshot are the Recommendations.
Preferably, described " user to be authenticated, if the user is to have authenticated user, obtains recognizing for the user
Demonstrate,prove information " before, further includes:
The corresponding commodity display image in each product display zone is acquired as control image；
Described " according to the shopping enabled instruction, the current shopping items taken to the user are identified, according to
Recognition result judges whether the current shopping items are the Recommendations " include:
It receives corresponding with the product display zone heavy by the product display zone current shopping items triggering of taking
Force snesor and the weight change signal generated acquire the current old of the product display zone according to the weight change signal
Column image；
The current display image is compared with control display image, the user is confirmed according to comparison result
It takes the current shopping items of the product display zone；
If the user has taken, the current shopping items of the product display zone, obtain the product display zone
Corresponding commodity display information and the corresponding Recommendations information of the Recommendations；
If the commodity display information is consistent with the Recommendations information, determine that the current shopping items are described
Recommendations.
Preferably, described " the corresponding LED light bright light in the product display zone to be controlled, to prompt the user to institute
The Recommendations stated in product display zone are bought " after, further includes:
Commodity in automatic vending machine described in real-time detection identify the end article of user's crawl；
If the end article of user's crawl is returned in the automatic vending machine, the end article is judged
Whether it is returned to preset corresponding with the end article and puts area；
If the end article is not put back into described preset and puts area, controls described preset and put the corresponding LED light in area
It reports an error, and the end article is returned to by described preset by user described in voice prompting and puts area.
Preferably, described " user to be authenticated, if the user is to have authenticated user, obtains recognizing for the user
Demonstrate,prove information " include:
It receives the user and triggers the shopping that the second infrared sensor generates into the shopping area of the automatic vending machine
Enabled instruction；
Acquire the authentication image of the user；
The facial area in the authentication image is positioned, also, extracts the face feature information of the facial area；
Identify whether judge the user to the face feature information using face recognition model trained in advance
To have authenticated user；
If the user is to have authenticated user, the authentication information of the user is obtained.
Preferably, described " to receive the user into the shopping area of the automatic vending machine and trigger the second infrared sensing
After the shopping enabled instruction that device generates ", further includes:
According to the shopping enabled instruction, the whole body images of user are acquired；
Based on the whole body images of the user, limbs joint point of the user in the whole body images is constructed；
It shows the person model constructed based on the limbs joint point, prompts the user according to the limb of the person model
Body movement is imitated；
The echomotism image of the user is obtained, and described imitate is extracted according to the limbs joint of user point and is moved
Make the feature vector in image；
If described eigenvector and the limb action of the person model match, determine that the user is recognized by living body
Card.
In addition, to solve the above problems, being wrapped the present invention also provides a kind of device for recommending the commodity based on automatic vending machine
Include: authentication module obtains module and determining module；
The authentication module, if the user is to have authenticated user, obtains the user for authenticating to user
Authentication information；
The acquisition module is gone through according to the acquisition of the authentication information of the user for being based on historical purchase data library
The corresponding history purchaser record of the user in history purchase database；
The determining module, for determining that the user is corresponding according to the history purchaser record and the authentication information
Recommendations；
The determining module is also used to determine commodity display corresponding with the Recommendations according to the Recommendations
Area；Also,
The corresponding LED light bright light in the product display zone is controlled, to prompt the user to the product display zone
The interior Recommendations are bought.
In addition, to solve the above problems, the present invention also provides a kind of user terminal, including memory and processor, institute
Memory is stated for storing the commercial product recommending program based on automatic vending machine, the processor operation is described to be based on automatic vending machine
Commercial product recommending program so that the user terminal executes the Method of Commodity Recommendation as described above based on automatic vending machine.
In addition, to solve the above problems, the present invention also provides a kind of computer readable storage medium, it is described computer-readable
The commercial product recommending program based on automatic vending machine, the commercial product recommending program based on automatic vending machine are stored on storage medium
It is realized when being executed by processor and such as weighs the Method of Commodity Recommendation described above based on automatic vending machine.
A kind of Method of Commodity Recommendation and its device based on automatic vending machine provided by the invention.Wherein, the present invention is mentioned
The method of confession according to the history purchaser record in the authentication information of user by determining and using after confirmation user is to have authenticated user
The corresponding Recommendations in family, and prompt by the bright light of LED light in the product display zone of Recommendations, with prompt
User carries out the purchase to Recommendations.The present invention realizes in open shopping environment, and user is purchased based on history
The recommendation of the Recommendations of record is bought, that is, realize the frequent purchase for user or is accustomed to the corresponding Recommendations of point of interest
Intelligent recommendation, to directly carry out a little the product display zone of the corresponding Recommendations of user in shopping process in user
Bright LED light prompt, provides convenience the lookup of the Recommendations of Habit Buying for user, improves shopping effect
Rate saves shopping-time, improves user experience, avoid as the long low efficiency of shopping-time shadow caused by other consumers
It rings.
Detailed description of the invention
Fig. 1 is the hardware running environment being related to the present invention is based on the Method of Commodity Recommendation example scheme of automatic vending machine
Structural schematic diagram；
Fig. 2 is that the present invention is based on the flow diagrams of the Method of Commodity Recommendation first embodiment of automatic vending machine；
Fig. 3 is that the present invention is based on the flow diagrams of the Method of Commodity Recommendation second embodiment of automatic vending machine；
Fig. 4 is that the present invention is based on the flow diagrams of the Method of Commodity Recommendation 3rd embodiment of automatic vending machine；
Fig. 5 is that the present invention is based on the flow diagrams of the Method of Commodity Recommendation fourth embodiment of automatic vending machine；
Fig. 6 is that the present invention is based on the flow diagrams of the 5th embodiment of Method of Commodity Recommendation of automatic vending machine；
Fig. 7 is that the present invention is based on the flow diagrams of the Method of Commodity Recommendation sixth embodiment of automatic vending machine；
Fig. 8 is that the present invention is based on the functional block diagrams of the device for recommending the commodity of automatic vending machine.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, in which the same or similar labels are throughly indicated same or like
Element or element with the same or similar functions.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include one or more of the features.In the description of the present invention, the meaning of " plurality " is two or more,
Unless otherwise specifically defined.
In the present invention unless specifically defined or limited otherwise, term " installation ", " connected ", " connection ", " fixation " etc.
Term shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integral；It can be mechanical connect
It connects, is also possible to be electrically connected；It can be directly connected, can also can be in two elements indirectly connected through an intermediary
The interaction relationship of the connection in portion or two elements.It for the ordinary skill in the art, can be according to specific feelings
Condition understands the concrete meaning of above-mentioned term in the present invention.
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 is the structural schematic diagram of the hardware running environment for the terminal that the embodiment of the present invention is related to.
The PC being set in automatic counter machine that the terminal of that embodiment of the invention can be is also possible to smart phone, plate electricity
The packaged types terminal devices such as brain, E-book reader, MP3 player, MP4 player, portable computer.In addition it is also possible to
The computer hardware device being had by automatic counter machine itself.
As shown in Figure 1, the terminal may include: processor 1001, such as CPU, network interface 1004, user interface
1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing the connection communication between these components.
User interface 1003 may include display screen, input unit such as keyboard, remote controler, and optional user interface 1003 can also include
Standard wireline interface and wireless interface.Network interface 1004 optionally may include standard wireline interface and wireless interface (such as
WI-FI interface).Memory 1005 can be high speed RAM memory, be also possible to stable memory, such as magnetic disk storage.
Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.
In addition, terminal includes image capture device, it is specifically as follows camera, camera etc..
In addition, terminal further includes infrared sensing equipment, judge to the Shopping Behaviors to user.
In addition, terminal further includes gravity sensitive equipment, to the quality to the commodity in automatic vending machine carry out in real time or
The monitoring of timing.
Optionally, terminal can also include RF (Radio Frequency, radio frequency) circuit, sensor, voicefrequency circuit,
WiFi module etc..In addition, mobile terminal can also configure gyroscope, barometer, hygrometer, thermometer, infrared sensor etc.
Other sensors, details are not described herein.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal shown in Fig. 1, may include ratio
More or fewer components are illustrated, certain components or different component layouts are perhaps combined.
As shown in Figure 1, as may include operating system, number in a kind of memory 1005 of computer readable storage medium
According to interface control program, network attachment procedure and commercial product recommending program based on automatic vending machine.
A kind of Method of Commodity Recommendation and its device based on automatic vending machine provided by the invention.Wherein, the method is real
The frequent purchase for user or the intelligent recommendation of the corresponding Recommendations of habit point of interest are showed, to do shopping in user
In the process, directly the product display zone of the corresponding Recommendations of user is carried out lighting LED light prompt, is user for practising
The lookup of the Recommendations of inertia purchase provides convenience, and improves shopping efficiency, saves shopping-time, improves user's body
It tests, avoids as the influence caused by other consumers of the long low efficiency of shopping-time.
Embodiment 1:
Referring to Fig. 2, first embodiment of the invention provides a kind of Method of Commodity Recommendation based on automatic vending machine, comprising:
Step S10, authenticates user, if the user is to have authenticated user, obtains the certification letter of the user
Breath；
Above-mentioned, the Method of Commodity Recommendation based on automatic vending machine provided by the present embodiment can be adapted for open
The places such as shopping environment, such as market, supermarket, i.e., unattended, user can carry out cargo of freely taking.In the present embodiment,
It can be open automatic vending machine, after user starts shopping, the cabinet door of automatic vending machine is opened, and user carries out to inside
Cargo is directly taken, and automatic vending machine is identified by Shopping Behaviors, purchase of the image capture device to user and
Statistics realizes the final clearing of the purchased commodity for user.
It is above-mentioned, the verification process of user, the as login process of user.It carries out doing shopping it using automatic vending machine in user
Before, it first has to authenticate the identity of user, to determine whether user is to have authenticated user.
Above-mentioned, the verification process of user can start the certification of the progress to user for when user triggers shopping instruction,
Such as user starts to initiate shopping instruction or user by mobile phone to certainly by the system on manual operation automatic vending machine
Dynamic vending machine barcode scanning, realizes the shopping instruction etc. that sets out, in addition it is also possible to enter into the shopping cog region of automatic vending machine in user
When domain, the image capture device of automatic vending machine automatically starts user to carry out face recognition.
Above-mentioned, authentication information is user after verification process, the information corresponding to the user that system is got, wherein can
To include that the image of user, user's face feature, age of user, User ID, user contact details, user's gender etc. characterization are used
The information of family unique identities prestored, or after active user authenticates as new user, the new information of filling.
Step S20 is based on historical purchase data library, obtains the historical purchase data according to the authentication information of the user
The corresponding history purchaser record of the user in library；
It is above-mentioned, historical purchase data library, to preserve user information and the bought inventory records corresponding relationship of user
Database.Wherein it is possible to include the range of goods, merchandise classification, time buying, quantity purchase etc. information of user's purchase, into
One step, count above- mentioned information by system, according to preset weight information, the shopping point of interest of user can be obtained,
Shopping high frequency time commodity etc..
Step S30 determines the corresponding Recommendations of the user according to the history purchaser record and the authentication information；
Above-mentioned, Recommendations count the recommendation quotient recommended out for history purchaser record corresponding with the authentication information of user
Product can buy commodity for the high frequency time of user, can also be with the commodity etc. of single purchase before user.For example, user is 3 times led to
It crosses automatic vending machine and has purchased mineral water, then according to the history purchaser record of user, the Recommendations of generation are mineral water.
Step S40 determines product display zone corresponding with the Recommendations according to the Recommendations；Also, it controls
The corresponding LED light bright light in the product display zone, to prompt the user to the recommendation in the product display zone
Commodity are bought.
Above-mentioned, each commodity has the product display zone of fixed difference according to the difference of classification, in order to distinguish commodity
And user is convenient to choose different classes of commodity, different commodity be set to different product display zones it
In.For example, being sales counter in automatic vending machine, multiple cells separated by partition, each cell are equipped in sales counter
For a product display zone.
It is above-mentioned, according to Recommendations, confirm corresponding product display zone, i.e. confirmation Recommendations position, into
And by LED light carry out bright light, carry out for user, the Recommendations are prompted, in order to user to Recommendations into
Row purchase.
Method provided by the present embodiment by confirmation user be authenticated user after, according in the authentication information of user
History purchaser record determine the corresponding Recommendations of user, and refer to by LED in the product display zone of Recommendations
Show the bright light prompt of lamp, to prompt user to carry out the purchase to Recommendations.The present embodiment is realized in open shopping ring
In border, the recommendation of the Recommendations for user based on history purchaser record is realized for the frequent purchase of user or habit
The intelligent recommendation of the used corresponding Recommendations of point of interest, thus carried out in shopping process in user, it is directly corresponding to user to push away
The product display zone for recommending commodity carries out lighting LED light prompt, is lookup of the user for the Recommendations of Habit Buying
It provides convenience, improves shopping efficiency, save shopping-time, improve user experience, avoid since shopping-time is long-acting
Rate is low to be influenced caused by other consumers.
Embodiment 2:
Referring to Fig. 3, second embodiment of the invention provides a kind of Method of Commodity Recommendation based on automatic vending machine, based on above-mentioned
First embodiment shown in Fig. 2, the step S40 " control the corresponding LED light bright light in the product display zone, with prompt
The user buys the Recommendations in the product display zone " after, further includes:
Step S50 receives the shopping enabled instruction generated by user shopping the first infrared sensor of gesture trigger；
Above-mentioned, the first infrared sensor is set in automatic vending machine the position that can perceive user's shopping gesture, stretches in user
Hand or limbs protrude into a shopping area of automatic vending machine, sensor perception shopping gesture, and generate shopping enabled instruction.
Above-mentioned, after determining the corresponding Recommendations of user and prompt accordingly, user starts to do shopping, and passes through
Infrared sensor progress identifies the shopping movement of user and gesture, triggers the process of shopping.
Step S60, according to the shopping enabled instruction, the current shopping items taken to the user are identified,
Judge whether the current shopping items are the Recommendations according to recognition result；
It is above-mentioned, after user sets out sensor, shopping enabled instruction is generated, and then know to the commodity that user takes
Not.Current shopping items are currently based on the commodity that the shopping enabled instruction grabs by user, carry out to the current shopping items
Identification, to judge whether the commodity are Recommendations.
Specifically, recognition methods can be to judge to recommend quotient by image-recognizing method or weight change method
Whether product are selected.
Step S70 closes the corresponding commodity of the Recommendations if the current shopping items are the Recommendations
The LED light of display area.
It is above-mentioned, in the present embodiment, after user sets out generation shopping enabled instruction, the current shopping taken to user
Commodity are identified, to judge whether current shopping items are exactly Recommendations, if so, closing corresponding conduct
The LED light recommending indicative function and lighting, indicates that the Recommendations have been taken by user, family can be used definitely to do shopping
End article, so that user is clearly known that Recommendations have been taken, reduce unnecessary prompt information, did shopping for user
Journey provides convenient.
Embodiment 3:
Referring to Fig. 4, third embodiment of the invention provides a kind of Method of Commodity Recommendation based on automatic vending machine, based on above-mentioned
Second embodiment shown in Fig. 3, and the step S60 " according to the shopping enabled instruction, the current purchase taken to the user
Object commodity are identified, judge whether the current shopping items are the Recommendations according to recognition result " include:
Step S61 acquires the shopping continuous shooting image of the shopping gesture of the user according to the shopping enabled instruction；
Above-mentioned, continuous shooting image of doing shopping can be the still image of continuous shooting, or dynamic GIF cardon or video
File.Specifically, taking the continuous shooting image of cargo for user.
Continuous shooting image can for Fixed Time Interval carry out Image Acquisition still image, time interval such as 1/
The frequency of 2S, or image is opened in take away the stage continuous shooting ten of cargo of user.
Step S62 extracts the key frame in the shopping continuous shooting image；
Above-mentioned, key frame is converted for shopping continuous shooting image, and extracts key frame therein.Wherein key frame can be with
It is further in order to be carried out to the commodity wherein grabbed for the frame in shopping continuous shooting image including the grabbed commodity of user
Identification.
Step S63 carries out outline identification to each key frame, and obtaining in key frame includes shopping gesture and the shopping
The gesture profile of the current shopping items of gesture crawl；
It is above-mentioned, it determines in key frame, the shopping gesture of user and the profile of shopping items.
It should be noted that profile testing method has two classes at present, one kind is detected using traditional edge detection operator
Objective contour, another kind of is to extract the mathematical model that can be used from human visual system to complete objective contour detection.At this
In embodiment, obtain the current shopping items including shopping gesture and the shopping gesture crawl using edge detection
Gesture profile.
Step S64 obtains the corresponding gesture screenshot of each key frame according to the gesture profile；
It is above-mentioned, the screenshot based on gesture profile in each key frame is got, further screenshot can be identified, significantly
Reduce computer for the workload of image recognition, improves recognition efficiency, reduce useless noise impurity for image recognition
Influence.
Step S65 identifies the gesture screenshot based on commodity identification model trained in advance, according to recognition result
Judge whether the current shopping items in the gesture screenshot are the Recommendations.
It is above-mentioned, specific identification process, which may include:, to be identified for shopping continuous shooting image
S1, extracts the key frame of continuous shooting crawl image, and constructs the corresponding timestamp of each key frame；
S2 carries out Threshold Segmentation Algorithm to the key frame continuous in time and is split, obtains bianry image；Its
In include:
S2-1 obtains HSV image for continuous key frame is converted into hsv color space in time described in each frame；
S2-2 carries out histogram analysis to the HSV image, obtains threshold range corresponding with the HSV image；
S2-3 will be set as 1 in pixel of the pixel value of tri- dimensions of H, S, V in the threshold range, will be
H, pixel of the pixel value of tri- dimensions of S, V not all in the threshold range is set as 0, obtains described two after the segmentation
It is worth image.
S3 does not grab the hand images of commodity drawing of seeds as a comparison with user gathered in advance, to after the segmentation two
Value image is compared, and to outline in all key frames, has the figure for the end article for being different from the comparison drawing of seeds
Picture obtains the Target key frames with the commodity.
S4 identifies the Target key frames by artificial neural network trained in advance, obtains the target and closes
The kind and quantity of included commodity in key frame.
Embodiment 4:
Referring to Fig. 5, fourth embodiment of the invention provides a kind of Method of Commodity Recommendation based on automatic vending machine, based on above-mentioned
Second embodiment shown in Fig. 3, the step S10 " authenticate user, if the user is to have authenticated user, obtain
Before the authentication information of the user ", further includes:
Step S80 acquires the corresponding commodity display image in each product display zone as control image；
It is above-mentioned, before user authenticates, Image Acquisition is carried out for each product display zone in automatic vending machine,
Commodity display image corresponding to each product display zone is collected, as control image.Control image can acquire a figure
Picture can also acquire multiple images of different angle.
The step S60 " according to the shopping enabled instruction, know by the current shopping items taken to the user
Not, judge whether the current shopping items are the Recommendations according to recognition result " include:
Step S66 is received and is taken the current shopping items triggering and the product display zone by the product display zone
Corresponding gravity sensor and the weight change signal generated acquires the product display zone according to the weight change signal
Current display image；
Above-mentioned, each product display zone is equipped with a corresponding gravity sensor, obtains the quotient in real time by gravity sensor
The weight value of the commodity of product display area, can real-time perception commodity take, put during weight change, i.e., weight gain variable signal.
After shopping items are taken out by product display zone, gross mass changes, and corresponding gravity sensor is triggered, according to institute
The weight of the shopping items of reduction generates a weight change signal.
It is above-mentioned, currently display image, for after user takes commodity to the corresponding product display zone of the commodity taken into
The image of row acquisition.
The current display image is compared with control display image, is confirmed according to comparison result by step S67
The user takes the current shopping items of the product display zone；
It is above-mentioned, it is compared by the way that current display image is displayed image with control, to confirm that user has taken commodity
The commodity of display area, i.e., current shopping items.
Step S68, if the user has taken, the current shopping items of the product display zone, obtain the quotient
The corresponding commodity display information in product display area and the corresponding Recommendations information of the Recommendations；
Step S69 determines the current shopping quotient if the commodity display information is consistent with the Recommendations information
Product are the Recommendations；
It is above-mentioned, by obtaining the commodity display information and the corresponding Recommendations information of Recommendations of current shopping items,
And then compare commodity display information and Recommendations information, if the two is consistent, i.e., range of goods in commodity display information with
Range of goods in Recommendations information is identical, then determines current shopping items for Recommendations, is not otherwise Recommendations.It is logical
Gravity sensing technology is crossed, is identified to whether commodity are taken, and then whether the current shopping items of contrast judgement are to recommend quotient
Product improve recognition efficiency to substantially increase the accuracy identified for commodity, provide for the shopping process of user
Convenience.
Embodiment 5:
Referring to Fig. 6, fifth embodiment of the invention provides a kind of Method of Commodity Recommendation based on automatic vending machine, based on above-mentioned
First embodiment shown in Fig. 2, the step S40 " control the corresponding LED light bright light in the product display zone, with prompt
The user buys the Recommendations in the product display zone " after, further includes:
Step S90, the commodity in automatic vending machine described in real-time detection, identifies the end article of user's crawl；
It is above-mentioned, during user grabs commodity, pass through the corresponding quotient of grasping movement of the image recognition technology to user
Product are identified that is, user has grabbed end article.The product features of the end article can be obtained in identification process, carried out
It saves, in order to carry out the identifying and judgeing for the end article of a step.
Step S100 judges institute if the end article of user crawl is returned in the automatic vending machine
It states end article and whether is returned to and corresponding with the end article default put area；
It is above-mentioned, if user returns goods for the end article, i.e., the end article is put back into automatic vending machine,
Then judge whether the commodity are placed go back to corresponding correct position, it is as default to put area.
Above-mentioned, default area of putting is preset region corresponding with commodity, and the commodity of each type are corresponding to be set
It is equipped with one and default puts area.
Step S110 controls described preset and puts area pair if the end article is not put back into described preset and puts area
The LED light answered reports an error, and the end article is returned to described preset by user described in voice prompting and puts area.
It is above-mentioned, if the end article is placed into the position of mistake by user, i.e., it is not placed to preset and puts area, then lead to
Cross it is default put the corresponding LED light in area and report an error, prompt user's end article to there is the case where placing errors present, and
Correctly default put in area is prevented by voice prompting user.In the present embodiment, it takes end article in user
Afterwards, exist due to the case where user takes by mistake or does not meet user demand, need user to return goods at this time, but due to automatic selling
Cargo aircraft be it is open, the commodity of each type are corresponding have it is corresponding default puts area, if will be moved back when being returned goods due to user
The end article of goods places the position of mistake, then will appear the situation of position confusion, for the shopping process of the user and other
The shopping process of user causes influence；By utilizing image recognition technology, commodity taken to user are measured in real time, and are known
Not Chu user crawl end article, and further user return goods when, compare whether the position that user is placed is default
It puts area to be judged, if placing mistake, the mistake of user is placed by LED light and voice prompting and is reported
Mistake, and prompt user to place the commodity and put in area to correctly default, to be realized pair by the monitoring of automatic vending machine
It is put in the classification of commodity in cabinet, identification is monitored for the return of goods behavior of user, and carry out accordingly if error
It reports an error, to be to keep classifying in automatic vending machine putting orderly indirectly, is provided convenience for the shopping process of user.
Embodiment 6:
Referring to Fig. 7, sixth embodiment of the invention provides a kind of Method of Commodity Recommendation based on automatic vending machine, based on above-mentioned
First embodiment shown in Fig. 2, the step S10 " authenticate user, if the user is to have authenticated user, obtain
The authentication information of the user " includes:
Step S120 receives the user into the shopping area of the automatic vending machine and triggers the life of the second infrared sensor
At shopping enabled instruction；
It is above-mentioned, the second infrared sensor, whether to enter the sensor that shopping area is perceived for user.Shopping area
Domain is the region that the user based on automatic vending machine setting carries out shopping selection commodity, after user enters the shopping area, touching
The second infrared sensor is sent out, shopping enabled instruction is generated.
Step S130 acquires the authentication image of the user；
When user enters shopping area, according to the authentication image of shopping enabled instruction acquisition user.Specifically, authentication image
It can be whole body images, half body image or face-image.
In addition, the optimization processing for authentication image can be carried out after step S130, for example, being carried out pair to authentication image
It is improved than degree, and is converted to binary grayscale image.
Step S140 positions the facial area in the authentication image, also, extracts the facial characteristics of the facial area
Information；
It is above-mentioned, authentication image is identified, facial area therein is oriented, and extracts facial characteristics letter therein
Breath, for example, eye feature, eye spacing, supercilium feature, mouth feature, shape of face feature etc..
Step S150 identifies the face feature information using face recognition model trained in advance, judges institute
State whether user is to have authenticated user；
Step S160 obtains the authentication information of the user if the user is to have authenticated user.
It is above-mentioned, face feature information is identified, user is authenticated based on the authentication image, if the user passes through
It crosses and is identified as having authenticated user, then obtain the corresponding authentication information of user.Wherein authentication information can be to be stored in cloud service
The corresponding information of user in device.
The step S120 " receives the user into the shopping area of the automatic vending machine and triggers the second infrared sensing
After the shopping enabled instruction that device generates ", further includes:
Step S170 acquires the whole body images of user according to the shopping enabled instruction；
It is above-mentioned, the whole body images of user are acquired, whole body images are image of the complete display user from head to foot, to
Carry out limb action tracking.
In the present embodiment, the bone tracking technique based on kinect, identifies the movement of user.
It is above-mentioned, it should be noted that kinect is a kind of 3D body-sensing video camera (exploitation code name " Project Natal "),
It has imported the functions such as instant dynamic capture, image identification, microphone input, speech recognition, community interactive simultaneously.
It is above-mentioned, it should be noted that bone tracer technique is the core technology of Kinect, it can be with accurate calibration human body
20 key points, and real-time tracing can be carried out to the position of this 20 points.Using this technology, can develop various based on body
Feel the application of human-computer interaction.Currently, the bone API in Kinect for Windows SDK can be provided in front of Kinect
The location information of at most two people, the three-dimensional coordinate information including detailed posture and skeleton point.In addition, Kinect for
Windows SDK can at most support 20 skeleton points.Data object type is provided in the form of skeletal frame, and each frame at most may be used
To save 20 points.
Kinect skeleton data stream can provide the three-dimensional coordinate of 20 artis of Whole Body, and it is effective that people is in Kinect
Data acquisition region in, the corresponding coordinate of the artis also can be with the movement of people, time changing, the coordinate of different movements
Data are different, therefore coordinate data can be used to further characterization and act.But these primary coordinate datas can not be straight
It connects for describing action model, it is necessary to carry out conversion and be characterized.
Step S180 is constructed limbs of the user in the whole body images and is closed based on the whole body images of the user
Node；
In the present embodiment, it needs to save and track, the limbs joint point in human limb, by being known according to image
The three-dimensional coordinate of the extremities joint point of the user is not determined.Because in shopping process, need to identify be user four limbs
Movement, by the major beat of people, that is, may recognize that the action behavior of people.And then according to the different Shopping Behaviors of people, carry out
Corresponding prompt.
Step S190 is shown the person model constructed based on the limbs joint point, prompts the user according to the people
The limb action of object model is imitated；
Step S200 obtains the echomotism image of the user, and is extracted according to the limbs joint of user point
Feature vector in the echomotism image；
Step S210 determines the user if described eigenvector and the limb action of the person model match
Pass through living body authentication.
It is above-mentioned, in the present embodiment, a person model corresponding to the user is shown by display screen, passes through the bone of kinect
Bone tracking technique prompts user to carry out echopraxis according to the movement of person model, tracks when based on bone, identifies that user does
It is corresponding with person model out to act, then it can determine that user is living body, pass through living body authentication.In the present embodiment, to user's
In verification process, to guarantee the shopping process of user and the safety of process of exchange, by the bone tracking technique based on kinect,
The movement of user is identified, after making movement corresponding with person model by user, so that it is determined that user is living body, i.e.,
By living body authentication, user is placed by, by certification, guaranteeing the safety of the transaction of user using substitutes such as photo, images
Property.
In addition, the present invention also provides a kind of devices for recommending the commodity based on automatic vending machine with reference to Fig. 8, comprising: certification mould
Block 10 obtains module 20 and determining module 30；
The authentication module 10, if the user is to have authenticated user, obtains the use for authenticating to user
The authentication information at family；
The acquisition module 20, for being based on historical purchase data library, according to the acquisition of the authentication information of the user
The corresponding history purchaser record of the user in historical purchase data library；
The determining module 30, for determining that the user is corresponding according to the history purchaser record and the authentication information
Recommendations；
The determining module 30 is also used to determine that commodity corresponding with the Recommendations are old according to the Recommendations
Arrange area；Also, the corresponding LED light bright light in the product display zone is controlled, to prompt the user to the commodity display
The Recommendations in area are bought.
In addition, the present invention also provides a kind of user terminal, including memory and processor, the memory is for storing
Commercial product recommending program based on automatic vending machine, the processor run the commercial product recommending program based on automatic vending machine with
The user terminal is set to execute the Method of Commodity Recommendation as described above based on automatic vending machine.
In addition, being stored on the computer readable storage medium the present invention also provides a kind of computer readable storage medium
There is the commercial product recommending program based on automatic vending machine, when the commercial product recommending program based on automatic vending machine is executed by processor
The Method of Commodity Recommendation described above based on automatic vending machine is such as weighed in realization.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of Method of Commodity Recommendation based on automatic vending machine characterized by comprising
User is authenticated, if the user is to have authenticated user, obtains the authentication information of the user；
Based on historical purchase data library, the use in the historical purchase data library is obtained according to the authentication information of the user
The corresponding history purchaser record in family；
The corresponding Recommendations of the user are determined according to the history purchaser record and the authentication information；
According to the Recommendations, product display zone corresponding with the Recommendations is determined；Also,
The corresponding LED light bright light in the product display zone is controlled, to prompt the user in the product display zone
The Recommendations are bought.
2. as described in claim 1 based on the Method of Commodity Recommendation of automatic vending machine, which is characterized in that described " to control the quotient
The corresponding LED light bright light in product display area, with prompt the user to the Recommendations in the product display zone into
After row purchase ", further includes:
Receive the shopping enabled instruction generated by user shopping the first infrared sensor of gesture trigger；
According to the shopping enabled instruction, the current shopping items taken to the user are identified, according to recognition result
Judge whether the current shopping items are the Recommendations；
If the current shopping items are the Recommendations, the LED of the corresponding product display zone of the Recommendations is closed
Indicator light.
3. as claimed in claim 2 based on the Method of Commodity Recommendation of automatic vending machine, which is characterized in that described " according to the purchase
Object enabled instruction, the current shopping items taken to the user identify, judge the current purchase according to recognition result
Whether object commodity are the Recommendations " include:
According to the shopping enabled instruction, the shopping continuous shooting image of the shopping gesture of the user is acquired；
Extract the key frame in the shopping continuous shooting image；
Outline identification is carried out to each key frame, obtains the institute including shopping gesture and the shopping gesture crawl in key frame
State the gesture profile of current shopping items；
The corresponding gesture screenshot of each key frame is obtained according to the gesture profile；
The gesture screenshot is identified based on commodity identification model trained in advance, the gesture is judged according to recognition result
Whether the current shopping items in screenshot are the Recommendations.
4. as claimed in claim 2 based on the Method of Commodity Recommendation of automatic vending machine, which is characterized in that
Before described " being authenticated to user, if the user is to have authenticated user, obtain the authentication information of the user ",
Further include:
The corresponding commodity display image in each product display zone is acquired as control image；
It is described that " according to the shopping enabled instruction, the current shopping items taken to the user are identified, according to identification
As a result judge whether the current shopping items are the Recommendations " include:
It receives and triggers gravity biography corresponding with the product display zone by the product display zone current shopping items of taking
Sensor and the weight change signal generated acquire the current planogram of the product display zone according to the weight change signal
Picture；
The current display image is compared with control display image, confirms that the user takes according to comparison result
The current shopping items of the product display zone；
It is corresponding to obtain the product display zone for the current shopping items of the product display zone if the user has taken
Commodity display information and the corresponding Recommendations information of the Recommendations；
If the commodity display information is consistent with the Recommendations information, determine that the current shopping items are the recommendation
Commodity.
5. as described in claim 1 based on the Method of Commodity Recommendation of automatic vending machine, which is characterized in that described " to control the quotient
The corresponding LED light bright light in product display area, with prompt the user to the Recommendations in the product display zone into
After row purchase ", further includes:
Commodity in automatic vending machine described in real-time detection identify the end article of user's crawl；
If the end article of user's crawl is returned in the automatic vending machine, whether the end article is judged
It is returned to preset corresponding with the end article and puts area；
If the end article is not put back into described preset and puts area, controls the default corresponding LED light in area of putting and carry out
It reports an error, and the end article is returned to by described preset by user described in voice prompting and puts area.
6. as described in claim 1 based on the Method of Commodity Recommendation of automatic vending machine, which is characterized in that described " to be carried out to user
Certification obtains the authentication information of the user if the user is to have authenticated user " include:
It receives the user and triggers the shopping starting that the second infrared sensor generates into the shopping area of the automatic vending machine
Instruction；
Acquire the authentication image of the user；
The facial area in the authentication image is positioned, also, extracts the face feature information of the facial area；
Identify judge whether the user is to the face feature information using face recognition model trained in advance
Authenticate user；
If the user is to have authenticated user, the authentication information of the user is obtained.
7. as claimed in claim 6 based on the Method of Commodity Recommendation of automatic vending machine, which is characterized in that described " to receive the use
Trigger the shopping enabled instruction that the second infrared sensor generates in the shopping area that family enters the automatic vending machine " after, also wrap
It includes:
According to the shopping enabled instruction, the whole body images of user are acquired；
Based on the whole body images of the user, limbs joint point of the user in the whole body images is constructed；
It shows the person model constructed based on the limbs joint point, prompts the user dynamic according to the limbs of the person model
It is imitated；
The echomotism image of the user is obtained, and the echomotism figure is extracted according to the limbs joint of user point
Feature vector as in；
If described eigenvector and the limb action of the person model match, determine that the user passes through living body authentication.
8. a kind of device for recommending the commodity based on automatic vending machine characterized by comprising authentication module, obtain module and really
Cover half block；
The authentication module, if the user is to have authenticated user, obtains recognizing for the user for authenticating to user
Demonstrate,prove information；
The acquisition module obtains the history according to the authentication information of the user and purchases for being based on historical purchase data library
Buy the corresponding history purchaser record of the user in database；
The determining module, for determining the corresponding recommendation of the user according to the history purchaser record and the authentication information
Commodity；
The determining module is also used to determine product display zone corresponding with the Recommendations according to the Recommendations；And
And
The corresponding LED light bright light in the product display zone is controlled, to prompt the user in the product display zone
The Recommendations are bought.
9. a kind of user terminal, which is characterized in that including memory and processor, the memory is for storing based on automatic
The commercial product recommending program of vending machine, the processor run the commercial product recommending program based on automatic vending machine so that the use
Family terminal is executed as described in any one of claim 1-7 based on the Method of Commodity Recommendation of automatic vending machine.
10. a kind of computer readable storage medium, which is characterized in that be stored on the computer readable storage medium based on certainly
The commercial product recommending program of dynamic vending machine, is realized when the commercial product recommending program based on automatic vending machine is executed by processor as weighed
Benefit requires the Method of Commodity Recommendation described in any one of 1-7 based on automatic vending machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810964683.0A CN109166007A (en) | 2018-08-23 | 2018-08-23 | A kind of Method of Commodity Recommendation and its device based on automatic vending machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810964683.0A CN109166007A (en) | 2018-08-23 | 2018-08-23 | A kind of Method of Commodity Recommendation and its device based on automatic vending machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109166007A true CN109166007A (en) | 2019-01-08 |
Family
ID=64896386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810964683.0A Pending CN109166007A (en) | 2018-08-23 | 2018-08-23 | A kind of Method of Commodity Recommendation and its device based on automatic vending machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109166007A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448233A (en) * | 2019-01-09 | 2019-03-08 | 盈奇科技（深圳）有限公司 | A kind of new type vending machine splicing body |
| CN109754522A (en) * | 2019-01-09 | 2019-05-14 | 盈奇科技（深圳）有限公司 | A kind of automatic vending machine splicing linkage display control method |
| CN110188695A (en) * | 2019-05-30 | 2019-08-30 | 北京百度网讯科技有限公司 | Shopping acts decision-making technique and device |
| CN110378215A (en) * | 2019-06-12 | 2019-10-25 | 北京大学 | Purchase analysis method based on first person shopping video |
| CN110674786A (en) * | 2019-09-30 | 2020-01-10 | 联想(北京)有限公司 | Processing method and device |
| CN110705377A (en) * | 2019-09-12 | 2020-01-17 | 创新奇智(合肥)科技有限公司 | Unmanned container order judgment auxiliary scheme based on user purchase mode |
| CN111260447A (en) * | 2020-02-11 | 2020-06-09 | 深圳前海达闼云端智能科技有限公司 | Commodity recommendation method and device for vending robot |
| CN111861589A (en) * | 2020-08-06 | 2020-10-30 | 中国农业大学 | Intelligent commodity recommending system and intelligent commodity recommending method for vending machine |
| CN111882751A (en) * | 2020-07-04 | 2020-11-03 | 青岛和成源精密科技有限公司 | Intelligent cabinet of selling goods |
| CN111882365A (en) * | 2020-08-06 | 2020-11-03 | 中国农业大学 | Intelligent commodity recommendation system and method for efficient self-service vending machine |
| CN111967943A (en) * | 2020-08-20 | 2020-11-20 | 渭南双盈未来科技有限公司 | Intelligent shopping system |
| CN112102025A (en) * | 2020-07-10 | 2020-12-18 | 齐喝彩(上海)管理咨询有限公司 | Remote purchase method and system for unmanned vending machine |
| CN112508592A (en) * | 2019-09-13 | 2021-03-16 | 东芝泰格有限公司 | Area migration prediction device and storage medium |
| CN112927055A (en) * | 2021-04-01 | 2021-06-08 | 山西慧虎健康科技有限公司 | Intelligent retail service method and system for accurately recommending related commodities |
| CN113222702A (en) * | 2021-05-19 | 2021-08-06 | 齐喝彩(上海)人工智能科技有限公司 | Beverage recipe recommendation method and system for automatic beverage machine |
| CN113208430A (en) * | 2021-05-31 | 2021-08-06 | 齐喝彩(上海)人工智能科技有限公司 | Beverage proportioning data management method and system for automatic beverage dispenser |
| CN113450176A (en) * | 2020-10-22 | 2021-09-28 | 齐喝彩(上海)管理咨询有限公司 | Remote purchase selection pushing method and system for unmanned vending machine |
| CN113761347A (en) * | 2021-02-25 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Commodity recommendation method, commodity recommendation device, storage medium and commodity recommendation system |
| CN115965324A (en) * | 2023-03-16 | 2023-04-14 | 浙江天柜科技有限公司 | Commodity selling method and system based on vending machine |
| CN117314576A (en) * | 2023-10-12 | 2023-12-29 | 南京软迅科技有限公司 | Visual data processing method for intelligent park |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750274A (en) * | 2011-01-04 | 2012-10-24 | 张越峰 | Field intelligent guide service system and method with preliminary human thinking |
| CN104038799A (en) * | 2014-05-21 | 2014-09-10 | 南京大学 | Three-dimensional television-oriented gesture manipulation method |
| CN104598867A (en) * | 2013-10-30 | 2015-05-06 | 中国艺术科技研究所 | Automatic evaluation method of human body action and dance scoring system |
| CN105976230A (en) * | 2016-05-23 | 2016-09-28 | 北京小米移动软件有限公司 | Processing method and apparatus for shopping request |
| CN107134053A (en) * | 2017-04-19 | 2017-09-05 | 石道松 | Intelligence is sold goods shops |
| CN107247759A (en) * | 2017-05-31 | 2017-10-13 | 深圳正品创想科技有限公司 | A kind of Method of Commodity Recommendation and device |
| CN107507017A (en) * | 2017-07-07 | 2017-12-22 | 阿里巴巴集团控股有限公司 | Shopping guide method and device under a kind of line |
| CN108108976A (en) * | 2017-12-29 | 2018-06-01 | 深圳正品创想科技有限公司 | The method and device that brush face is paid in a kind of unmanned shop |
| CN108171172A (en) * | 2017-12-27 | 2018-06-15 | 惠州Tcl家电集团有限公司 | Self-help shopping method, self-service sale device and computer readable storage medium |
| CN108198052A (en) * | 2018-03-02 | 2018-06-22 | 北京京东尚科信息技术有限公司 | User's free choice of goods recognition methods, device and intelligent commodity shelf system |
| CN108346050A (en) * | 2018-03-29 | 2018-07-31 | 深圳正品创想科技有限公司 | A kind of method, apparatus creating user account and unmanned shop |
-
2018
- 2018-08-23 CN CN201810964683.0A patent/CN109166007A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750274A (en) * | 2011-01-04 | 2012-10-24 | 张越峰 | Field intelligent guide service system and method with preliminary human thinking |
| CN104598867A (en) * | 2013-10-30 | 2015-05-06 | 中国艺术科技研究所 | Automatic evaluation method of human body action and dance scoring system |
| CN104038799A (en) * | 2014-05-21 | 2014-09-10 | 南京大学 | Three-dimensional television-oriented gesture manipulation method |
| CN105976230A (en) * | 2016-05-23 | 2016-09-28 | 北京小米移动软件有限公司 | Processing method and apparatus for shopping request |
| CN107134053A (en) * | 2017-04-19 | 2017-09-05 | 石道松 | Intelligence is sold goods shops |
| CN107247759A (en) * | 2017-05-31 | 2017-10-13 | 深圳正品创想科技有限公司 | A kind of Method of Commodity Recommendation and device |
| CN107507017A (en) * | 2017-07-07 | 2017-12-22 | 阿里巴巴集团控股有限公司 | Shopping guide method and device under a kind of line |
| CN108171172A (en) * | 2017-12-27 | 2018-06-15 | 惠州Tcl家电集团有限公司 | Self-help shopping method, self-service sale device and computer readable storage medium |
| CN108108976A (en) * | 2017-12-29 | 2018-06-01 | 深圳正品创想科技有限公司 | The method and device that brush face is paid in a kind of unmanned shop |
| CN108198052A (en) * | 2018-03-02 | 2018-06-22 | 北京京东尚科信息技术有限公司 | User's free choice of goods recognition methods, device and intelligent commodity shelf system |
| CN108346050A (en) * | 2018-03-29 | 2018-07-31 | 深圳正品创想科技有限公司 | A kind of method, apparatus creating user account and unmanned shop |
Non-Patent Citations (1)
| Title |
|---|
| 蒋可心: ""智能视频监控系统中若干生物特征识别研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448233A (en) * | 2019-01-09 | 2019-03-08 | 盈奇科技（深圳）有限公司 | A kind of new type vending machine splicing body |
| CN109754522A (en) * | 2019-01-09 | 2019-05-14 | 盈奇科技（深圳）有限公司 | A kind of automatic vending machine splicing linkage display control method |
| CN110188695A (en) * | 2019-05-30 | 2019-08-30 | 北京百度网讯科技有限公司 | Shopping acts decision-making technique and device |
| CN110188695B (en) * | 2019-05-30 | 2021-09-07 | 北京百度网讯科技有限公司 | Shopping action decision method and device |
| CN110378215A (en) * | 2019-06-12 | 2019-10-25 | 北京大学 | Purchase analysis method based on first person shopping video |
| CN110378215B (en) * | 2019-06-12 | 2021-11-02 | 北京大学 | Shopping analysis method based on first-person visual angle shopping video |
| CN110705377A (en) * | 2019-09-12 | 2020-01-17 | 创新奇智(合肥)科技有限公司 | Unmanned container order judgment auxiliary scheme based on user purchase mode |
| CN112508592A (en) * | 2019-09-13 | 2021-03-16 | 东芝泰格有限公司 | Area migration prediction device and storage medium |
| CN112508592B (en) * | 2019-09-13 | 2024-11-08 | 东芝泰格有限公司 | Region transfer prediction device and storage medium |
| CN110674786A (en) * | 2019-09-30 | 2020-01-10 | 联想(北京)有限公司 | Processing method and device |
| CN111260447A (en) * | 2020-02-11 | 2020-06-09 | 深圳前海达闼云端智能科技有限公司 | Commodity recommendation method and device for vending robot |
| CN111882751A (en) * | 2020-07-04 | 2020-11-03 | 青岛和成源精密科技有限公司 | Intelligent cabinet of selling goods |
| CN112102025A (en) * | 2020-07-10 | 2020-12-18 | 齐喝彩(上海)管理咨询有限公司 | Remote purchase method and system for unmanned vending machine |
| CN111861589A (en) * | 2020-08-06 | 2020-10-30 | 中国农业大学 | Intelligent commodity recommending system and intelligent commodity recommending method for vending machine |
| CN111861589B (en) * | 2020-08-06 | 2024-01-26 | 中国农业大学 | Intelligent commodity recommendation system and intelligent recommendation method for self-service vending machine |
| CN111882365B (en) * | 2020-08-06 | 2024-01-26 | 中国农业大学 | Intelligent commodity recommendation system and method for efficient self-service vending machine |
| CN111882365A (en) * | 2020-08-06 | 2020-11-03 | 中国农业大学 | Intelligent commodity recommendation system and method for efficient self-service vending machine |
| CN111967943A (en) * | 2020-08-20 | 2020-11-20 | 渭南双盈未来科技有限公司 | Intelligent shopping system |
| CN113450176A (en) * | 2020-10-22 | 2021-09-28 | 齐喝彩(上海)管理咨询有限公司 | Remote purchase selection pushing method and system for unmanned vending machine |
| CN113761347A (en) * | 2021-02-25 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Commodity recommendation method, commodity recommendation device, storage medium and commodity recommendation system |
| CN112927055A (en) * | 2021-04-01 | 2021-06-08 | 山西慧虎健康科技有限公司 | Intelligent retail service method and system for accurately recommending related commodities |
| CN113222702A (en) * | 2021-05-19 | 2021-08-06 | 齐喝彩(上海)人工智能科技有限公司 | Beverage recipe recommendation method and system for automatic beverage machine |
| CN113208430A (en) * | 2021-05-31 | 2021-08-06 | 齐喝彩(上海)人工智能科技有限公司 | Beverage proportioning data management method and system for automatic beverage dispenser |
| CN115965324A (en) * | 2023-03-16 | 2023-04-14 | 浙江天柜科技有限公司 | Commodity selling method and system based on vending machine |
| CN117314576A (en) * | 2023-10-12 | 2023-12-29 | 南京软迅科技有限公司 | Visual data processing method for intelligent park |
| CN117314576B (en) * | 2023-10-12 | 2024-04-02 | 南京软迅科技有限公司 | Visual data processing method for intelligent park |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109166007A (en) | A kind of Method of Commodity Recommendation and its device based on automatic vending machine | |
| CN108694779B (en) | Goods returning method and device for open type vending machine | |
| CN109035629A (en) | A kind of shopping settlement method and device based on open automatic vending machine | |
| US11638490B2 (en) | Method and device for identifying product purchased by user and intelligent shelf system | |
| US11393213B2 (en) | Tracking persons in an automated-checkout store | |
| CN108830251A (en) | Information correlation method, device and system | |
| CN108921645A (en) | A kind of commodity purchasing determination method, device and user terminal | |
| US11023908B2 (en) | Information processing apparatus for performing customer gaze analysis | |
| CN108985861A (en) | A kind of shopping clearing control method and device based on open shopping environment | |
| CN104885111B (en) | Control method for displaying sales information on information terminal | |
| RU2739542C1 (en) | Automatic registration system for a sales outlet | |
| US20150039458A1 (en) | Method and system for automated retail checkout using context recognition | |
| US10628695B2 (en) | Fast item identification for checkout counter | |
| CN109241883B (en) | Goods returning control method and device based on vending machine | |
| CN109767258A (en) | Intelligent shopping guide method and device based on eyes image identification | |
| CN109243112A (en) | A kind of open environment shopping control method and device | |
| CN108960132A (en) | The purchasing method and its device of commodity in a kind of open automatic vending machine | |
| CN109191196A (en) | A kind of Method of Commodity Recommendation based on user characteristics, device and user terminal | |
| CN108831017A (en) | Intelligent goods selling equipment and method | |
| CN112215167B (en) | Intelligent store control method and system based on image recognition | |
| CN109002782A (en) | A kind of commodity purchasing method, apparatus and user terminal based on automatic vending machine | |
| KR20190104282A (en) | Method and mobile terminal for providing information based on image | |
| CN109556695A (en) | Weighing method, weighing device, self-service cabinet and self-service method | |
| CN109034980B (en) | Collocation commodity recommendation method and device and user terminal | |
| CN109840503A (en) | A kind of method and device of determining information |
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: 20190108 |