CN110490698A - A kind of unmanned misplaced detection method and device of store shelf article - Google Patents
A kind of unmanned misplaced detection method and device of store shelf article Download PDFInfo
- Publication number
- CN110490698A CN110490698A CN201910709187.5A CN201910709187A CN110490698A CN 110490698 A CN110490698 A CN 110490698A CN 201910709187 A CN201910709187 A CN 201910709187A CN 110490698 A CN110490698 A CN 110490698A
- Authority
- CN
- China
- Prior art keywords
- misplaced
- user
- article
- shelf
- behavior
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/52—Weighing apparatus combined with other objects, e.g. furniture
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/20—Point-of-sale [POS] network systems
- G06Q20/208—Input by product or record sensing, e.g. weighing or scanner processing
-
- 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]
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
Abstract
The embodiment of the present application discloses a kind of misplaced detection method of unmanned store shelf article, device, electronic equipment and storage medium.The described method includes: the behavior of user is tracked and identified to user in real time after user chooses region by authentication entrance；When the behavior for recognizing user is misplaced behavior, determines the corresponding position of the misplaced behavior, trigger the misplaced verifying of corresponding position shelf；Result based on the misplaced verifying carries out user's shopping list statistics and corresponding shelf contents statistics.Technical solution provided by the embodiments of the present application, pass through misplaced Activity recognition and carries out misplaced verifying, the situation of change of corresponding position shelf contents is determined according to misplaced verification result, and user's shopping list statistics and corresponding shelf contents inventory statistics are carried out according to the situation of change of shelf contents, so that shopping goods check and shelf contents check it is more accurate, it avoids mistake from deducting fees, and then optimizes user's shopping experience.
Description
Technical field
The invention relates to computer recognition detection technical field more particularly to a kind of unmanned store shelf articles
Misplaced detection method and device.
Background technique
Currently, with the development of science and technology, intelligence retail, unmanned retail are also gradually being widely used in life.Nothing
People convenience store is an emerging application product under the field.It is whole in shopping process that unmanned convenience store is often referred to user
The purchase of article can be completed without the participation of attendant.After user enters unmanned convenience store, independently choosing for article is carried out,
Article can voluntarily leave convenience store after selecting, and system background can be automatically performed the clearing of article.
Existing unmanned convenience store mainly determines that user selects during operation by the weight detecting on unmanned shelf
Which commodity is purchased, as the clearing deducted fees according to progress corresponding goods.But user can exist and take when buying goods
Play the case where article is put back to again.Commodity may be put into the position of mistake when putting back to commodity by user, thus will lead to shelf
The problem of article statistics and user's shopping cart inventory mistake of statistics, and then lead to mistake of deducting fees, influence the shopping experience of user.
Summary of the invention
The embodiment of the present application provides a kind of misplaced detection method of unmanned store shelf article, device, electronic equipment and deposits
Storage media can be avoided because of shelf contents mistake of statistics and user's shopping cart inventory mistake of statistics caused by misplaced, optimize user
Shopping experience.
In a first aspect, the embodiment of the present application provides a kind of unmanned misplaced detection method of store shelf article, comprising:
After user chooses region by authentication entrance, the behavior of user is tracked and identified to user in real time；
When the behavior for recognizing user is misplaced behavior, the corresponding position of the misplaced behavior is determined, trigger corresponding position
Set the misplaced verifying of place's shelf；
Result based on the misplaced verifying carries out user's shopping list statistics and corresponding shelf contents statistics.
Further, misplaced verify includes:
Determine that corresponding position shelf are abnormal with the presence or absence of weight gain based on the misplaced behavior.
Further, described that user's shopping list statistics and corresponding shelf contents are carried out according to the result of the misplaced verifying
Statistics, comprising:
If it is abnormal to there is weight gain in corresponding position shelf, it is determined that this time shelf weight change is non-order operation, user
Shopping list does not count the non-order operation, and updates the weight change of corresponding position shelf；
If there is no weight gain exception, the misplaced behavior erroneous judgements for corresponding position shelf.
Further, abnormal if there is weight gain in the corresponding position shelf, it is determined that this time shelf weight change is
Non- order operation, user's shopping list do not count the non-order operation, and update corresponding position shelf weight change it
Afterwards, further includes:
Misplaced article is put back into correct position according to the weight gain abnormal prompt user or operation personnel.
Further, the behavior of the identification user is that misplaced behavior includes:
It identifies that the article of user takes out operation, determines that the taking-up operates corresponding first position；
The correspondence article of identification user puts back to operation, and the corresponding second position of operation is put back to described in determination；
It is whether consistent with the second position to compare the first position, if the first position and the second position are not
Unanimously, it is determined that it is misplaced behavior that the correspondence article of user, which puts back to operation,.
Further, the behavior of the identification user is that misplaced behavior includes:
The article of identification user puts back to operation, determines the classification for putting back to article；
The corresponding position that operation is put back to described in determination identifies the classification of the original article in the corresponding position；
Whether classification and the original goods categories that article is put back to described in comparison are consistent, if the classification for putting back to article
It is inconsistent with the classification of original article, it is determined that it is misplaced behavior that the article of the user, which puts back to operation,.
Further, described after user chooses region by authentication entrance, user is tracked and known in real time
In the behavior of other user, by entrance guard device detect user whether enter described in choose region, and detected according to entrance guard device
User enter behavior triggering usertracking identification events, start in real time to track user and identify the behavior of user.
In second aspect, the embodiment of the present application provides a kind of unmanned misplaced detection device of store shelf article, comprising:
Module is tracked and identified, for tracking in real time to user after user chooses region by authentication entrance
And identify the behavior of user；
Misplaced authentication module, for determining pair of the misplaced behavior when the behavior for recognizing user is misplaced behavior
Position is answered, the misplaced verifying of corresponding position shelf is triggered；
Statistical module carries out user's shopping list statistics and corresponding shelf contents for the result based on the misplaced verifying
Statistics.
In the third aspect, the embodiment of the present application provides a kind of electronic equipment, comprising:
Memory and one or more processors；
The memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the unmanned misplaced detection method of store shelf article as described in relation to the first aspect.
In fourth aspect, the embodiment of the present application provides a kind of storage medium comprising computer executable instructions, described
Computer executable instructions by computer processor when being executed for executing unmanned store shelf as described in relation to the first aspect
The misplaced detection method of article.
The embodiment of the present application enters the behavior for choosing the user in region by real-time tracking identification, and preliminary identification judgement is used
Family whether there is misplaced behavior, and carry out misplaced verifying according to the misplaced behavior recognized, determine corresponding position according to verification result
The situation of change of place's shelf contents is set, and user's shopping list statistics and corresponding shelf are carried out according to the situation of change of shelf contents
List of articles statistics so that shopping goods check and shelf contents are checked more accurate, avoid mistake from deducting fees, and then optimize
User's shopping experience.
Detailed description of the invention
Fig. 1 is a kind of flow chart for unmanned misplaced detection method of store shelf article that the embodiment of the present application one provides；
Fig. 2 is the process for the unmanned misplaced detection method of store shelf article of another kind that the embodiment of the present application two provides
Figure；
Fig. 3 is the process for the unmanned misplaced detection method of store shelf article of another kind that the embodiment of the present application three provides
Figure；
Fig. 4 is the process for the unmanned misplaced detection method of store shelf article of another kind that the embodiment of the present application four provides
Figure；
Fig. 5 is a kind of structural frames for unmanned misplaced detection device of store shelf article that the embodiment of the present application five provides
Figure；
Fig. 6 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present application six provides.
Specific embodiment
It is specifically real to the application with reference to the accompanying drawing in order to keep the purposes, technical schemes and advantages of the application clearer
Example is applied to be described in further detail.It is understood that specific embodiment described herein is used only for explaining the application,
Rather than the restriction to the application.It also should be noted that illustrating only for ease of description, in attached drawing related to the application
Part rather than full content.It should be mentioned that some exemplary realities before exemplary embodiment is discussed in greater detail
It applies example and is described as the processing or method described as flow chart.Although operations (or step) are described as sequence by flow chart
Processing, but many of these operations can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of operations
It can be rearranged.The processing can be terminated when its operations are completed, be not included in attached drawing it is also possible to have
Additional step.The processing can correspond to method, function, regulation, subroutine, subprogram etc..
The unmanned misplaced detection scheme of store shelf article provided by the present application, it is intended to by the mistake for identifying and verifying user
Clearance is to carry out shelf contents statistics and user's shopping cart inventory statistics to avoid separately through image recognition or weight detecting
The case where erroneous judgement of appearance, it is ensured that deduct fees correct.Relative to existing using in the enterprising crudely-made articles frame weight detecting of unmanned shelf
Mode can not detect misplaced behavior of the user during choosing.When user is when choosing, picking up article then can be in user
Corresponding article is counted in shopping cart inventory.Certainly, the case where user's " picking up " " puts back to " again often has, if for this purpose, user picks up
Article is placed back into original position again, then counts without user's shopping cart inventory.But the article that user will choose during choosing
There is misplaced situation often in the operation put back to, makes that the goods that article in situ is placed at other positions should be put back to originally
On frame.And article original position shelf are in when carrying out weight detecting, discovery reduces the weight of respective articles, then clear in user's shopping cart
It is single to count corresponding article；When shelf at the misplaced position of article carry out weight detecting, the total amount of discovery weight gain respective articles, then
Corresponding weight is increased to the article at the position on shelf contents inventory.This results in user's shopping list to count and correspond to goods
The problem of frame article mistake of statistics.For this purpose, providing the unmanned misplaced detection method of store shelf article of the embodiment of the present application, lead to
The behavior for crossing real-time tracking identification user, to identify the misplaced behavior of user, and verifies misplaced behavior, avoids identifying
Mistake so that shelf contents statistics and user's shopping cart inventory statistics are correct, and then avoids mistake of deducting fees.
Implement one:
Fig. 1 gives a kind of process of unmanned misplaced detection method of store shelf article of the offer of the embodiment of the present application one
Scheme, the unmanned misplaced detection method of store shelf article provided in the present embodiment can be misplaced by unmanned store shelf article
Detection device executes, which can be realized by way of software and/or hardware,
The unmanned misplaced detection device of store shelf article can be two or more physical entities and constitute, and be also possible to a physics
Entity is constituted.In general, the unmanned misplaced detection device of store shelf article can be computer.
Following with the unmanned misplaced detection device of store shelf article is to execute the unmanned misplaced detection of store shelf article
For the main body of method, it is described.Referring to Fig.1, which specifically includes:
S110, user by authentication enter choose region after, user is tracked in real time and identifies user's
Behavior.
Illustratively, in unmanned convenience store operation scene, each user for being prepared to enter into unmanned convenience store is carried out
Authentication, by confirm user identity and with the account of deducting fees of user identity binding, user is chosen convenient for subsequent
Article carries out operation of deducting fees.Unmanned convenience store chooses setting entrance guard device at zone inlet, detects user by entrance guard device
Whether into unmanned convenience store choose region, and is entered behavior triggering usertracking identification according to the user that entrance guard device detects
Event starts the behavior for tracking and identifying user to user in real time.Entrance guard device can be infrared inductor, camera
Equal hardware devices.
In choosing in region for unmanned convenience store, several shelf are set, places article on shelf, is chosen for user.In
Each article being corresponded on shelf, corresponding Weight detecting device being set, Weight detecting device, which specifically can be, to be arranged in every class object
The bottom of product, for accepting the weighing sensor of article.Weighing sensor real-time detection corresponds to the weight information of article, when nobody
When the misplaced detection device of store shelf article detects that weighing sensor weight information changes, indicate that shelf occur at this time
Weight change.This corresponding weight change, it may be possible to caused by user takes out the commodity at corresponding shelf, be also possible to run people
Caused by member places article, user can also be during shopping goods, misplace shelf weight change caused by operation.For
This, needs to identify the misplaced behavior of user by camera.In conjunction with the misplaced behavior of user recognized, further according to correspondence
Shelf weight detecting at position finally carries out user's shopping cart inventory statistics according to verification result to carry out misplaced behavior verifying
And shelf contents statistics.
Several cameras are set in unmanned convenience store, on the one hand camera is used to track user and identifies the row of user
For on the other hand for shooting the real-time condition of article on each position shelf.When being tracked to user and Activity recognition,
The target tracking algorism based on convolutional neural networks can be used, real-time tracking is carried out to user, using behavior act recognizer and
Algorithm of target detection determines the misplaced behavior of user.Unmanned convenience store pre-establishes a target following model, target following
Model can based on Siamese_fc single goal tracing algorithm establish, subsequently through target following model to user carry out in real time with
Track.And the movement of article is put back to by identification user, and whether the article put back to belongs to corresponding shelf to determine user and be
No being detected as the identification of behavior act and article is existing compared with mature technology there are misplaced behavior, seldom repeats here.
S120, when the behavior for recognizing user is misplaced behavior, determine the corresponding position of the misplaced behavior, triggering pair
Answer the misplaced verifying of shelf at position.
Identification based on above-mentioned S110 to misplaced behavior, when recognizing user there are when misplaced behavior, then according to user with
When track identifies, there are the misplaced correspondence shelf locations of article, carry out the misplaced verifying at the shelf location.It is this time misplaced to ensure
The identification of behavior is correct.When carrying out misplaced verifying, misplaced verifying is carried out by the weight detecting of corresponding position shelf.Pass through weight
Whether the Item Weight that amount detection operation detects on shelf at this time increases weight, and increases weight if corresponding to Item Weight at shelf at this time, then
Misplaced verification result is that user definitely has misplaced behavior；And if corresponded at shelf at this time and Item Weight weight gain do not occur,
Then think that misplaced behavior has misjudgement at this time.
S130, the result based on the misplaced verifying carry out user's shopping list statistics and corresponding shelf contents statistics.
Finally, according to it is above-mentioned it is misplaced verify it is obtaining as a result, carry out user's shopping list statistics and corresponding shelf contents
Statistics.Before this, when user unmanned convenience store choose region carry out article choose when, take out corresponding article and then can
Corresponding article is counted on user's shopping list, later, when detect user put back to article operation be misplaced behavior when, this
Although when the shelf located in situ of the article do not detect that user puts back to article, since user has put back to the correlation chosen at this time
Article can then be corresponded to and be modified on user's shopping list, and the corresponding article on shopping list is deleted, without system
Meter.And the article of corresponding shelf is counted, relevant article is taken out when user chooses, the article statistics of corresponding shelf then subtracts
The article of few corresponding weight.When on user's misplaced article to a certain shelf, although then weight increases at the shelf, due to
The correspondence article to increase weight at this time is not belonging to the shelf, then the article statistics on the shelf is constant.
Optionally, it is contemplated that increased by the weight of the shelf contents at misplaced article, be for the ease of subsequent determining user
The no article chosen on the shelf avoids statistics chaotic.The shelf contents of the position can also be counted and increase misplaced article
Weight.In this way, subsequent when user is from shopping goods on this shelf, Weight detecting device detects how much weight reduced,
It can then determine user has taken what article on the shelf away.
It is above-mentioned, the behavior for choosing the user in region is entered by real-time tracking identification, whether preliminary identification judges user
There are misplaced behaviors, and carry out misplaced verifying according to the misplaced behavior recognized, determine corresponding position goods according to verification result
The situation of change of frame article, and it is clear according to the situation of change of shelf contents progress user's shopping list statistics and corresponding shelf contents
Single statistics so that shopping goods check and shelf contents are checked more accurate, avoid mistake from deducting fees, and then optimize user's purchase
Object is tested.
Embodiment two:
On the basis of the above embodiments, Fig. 2 is the unmanned store shelf object of another kind that the embodiment of the present application two provides
The flow chart of the misplaced detection method of product.With reference to Fig. 2, the unmanned misplaced detection method tool of store shelf article provided in this embodiment
Body includes:
S210, user by authentication enter choose region after, user is tracked in real time and identifies user's
Behavior；
S221, it identifies that the article of user takes out operation, determines that the taking-up operates corresponding first position；
S222, it identifies that the correspondence article of user puts back to operation, the corresponding second position of operation is put back to described in determination；
Whether S223, the comparison first position and the second position are consistent, if the first position and described second
Position is inconsistent, it is determined that it is misplaced behavior that the correspondence article of user, which puts back to operation,；
S224, the corresponding position for determining the misplaced behavior trigger the misplaced verifying of corresponding position shelf；
S230, the result based on the misplaced verifying carry out user's shopping list statistics and corresponding shelf contents statistics.
Illustratively, the embodiment of the present application first passes through action recognition model knowledge when carrying out the detection of the misplaced behavior of user
The article of other user takes out operation and article puts back to operation.By pre-establishing, article takes out Activity recognition model and article is put back to
Activity recognition model, when carrying out model foundation, a large amount of obtain includes to take out object manipulation and put back to object manipulation respectively
Action trail image is trained to obtain above-mentioned two Activity recognition model based on convolutional neural networks.It is taken later based on article
Trip is that identification model and article put back to Activity recognition model and carry out the article of real-time detection user and take out operation and article puts back to behaviour
Make.What article took out that Activity recognition model and article put back to Activity recognition model establishes principle and existing behavior act identification model
It is similar, not as the main improvement of the embodiment of the present application, seldom repeat here.
Operation is taken out according to the consumer articles recognized and article puts back to operation, determines what user took out and put back to respectively
Two positions compare whether two positions are consistent, if two position consistencies, it is correct that user puts back to operation by image；If root
It is inconsistent that two positions are compared according to image, then it is assumed that there are misplaced behaviors by user.Misplaced verifying need to be carried out according to misplaced behavior, with
Determine the whether misplaced relative article of user.
By above scheme it is found that the embodiment of the present application is taken out by establishing article, puts back to action recognition model, known with acting
Other model takes out identifying the article of user and puts back to operation, then corresponding with two images of operation are put back to by comparing taking-up
Whether shelf location unanimously carrys out preliminary judgement user with the presence or absence of misplaced behavior.It can quickly identify user with the presence or absence of latent
It is misplaced because, without carrying out the target detection of misplaced article, subsequent misplaced verifying and correlation are quickly carried out convenient for equipment
The statistics of inventory.
Embodiment three:
On the basis of the above embodiments, Fig. 3 is the unmanned store shelf object of another kind that the embodiment of the present application three provides
The flow chart of the misplaced detection method of product.With reference to Fig. 3, the unmanned misplaced detection method tool of store shelf article provided in this embodiment
Body includes:
S310, user by authentication enter choose region after, user is tracked in real time and identifies user's
Behavior；
S321, it identifies that the article of user puts back to operation, determines the classification for putting back to article；
The corresponding position that operation is put back to described in S322, determination, identifies the classification of the original article in the corresponding position；
Whether classification and the original goods categories that article is put back to described in S323, comparison are consistent, if described put back to article
Classification and original article classification it is inconsistent, it is determined that it is misplaced behavior that the article of the user, which puts back to operation,；
S324, the corresponding position for determining the misplaced behavior trigger the misplaced verifying of corresponding position shelf；
S330, the result based on the misplaced verifying carry out user's shopping list statistics and corresponding shelf contents statistics.
Illustratively, the embodiment of the present application first passes through action recognition model knowledge when carrying out the detection of the misplaced behavior of user
The article of other user puts back to operation.Activity recognition model is put back to by pre-establishing article, when carrying out model foundation, by big
It includes the action trail image for putting back to object manipulation that amount, which obtains, is trained to obtain article based on convolutional neural networks and puts back to row
For identification model.Activity recognition model is put back to based on article later and puts back to operation come the article of real-time detection user.
Operation, the classification for the article that detection user puts back to are put back to according to the consumer articles recognized.Basis puts back to behaviour simultaneously
The corresponding position of work detects the classification of original article on the position shelf.In the article and original article that progress user puts back to
Detection when, using the algorithm of target detection based on convolutional neural networks two images are carried out with the identification of goods categories, according to
The goods categories information in two images recognized is compared, that is, can determine user with the presence or absence of misplaced operation.
Specifically, the target detection identification basis of article pre-establishes corresponding target detection model.Establish target detection
When model, it is trained to obtain mesh as sample data set by obtaining the image of a large amount of corresponding articles based on convolutional neural networks
Detection model is marked, carries out the identification of goods categories to above-mentioned image subsequently through target detection model.Target detection model is specific
It can be YOLOv3 target detection model, existing algorithm of target detection has very much, and do not fix restriction herein.
By above scheme it is found that the embodiment of the present application puts back to action recognition model and article target identification by establishing article
Model identifies that the article of user puts back to operation by action recognition model, then two figures are determined by Model of Target Recognition
As whether corresponding article is consistent, carry out preliminary judgement user with the presence or absence of misplaced behavior.Accurate use can be recognized with this
Whether the goods categories that family is put back to belong to corresponding shelf.Ensure that the misplaced behavior of the user of preliminary judgement is accurate.
Example IV:
On the basis of the above embodiments, Fig. 4 is the unmanned store shelf object of another kind that the embodiment of the present application four provides
The flow chart of the misplaced detection method of product.With reference to Fig. 4, the unmanned misplaced detection method tool of store shelf article provided in this embodiment
Body includes:
S410, user by authentication enter choose region after, user is tracked in real time and identifies user's
Behavior；
S420, when the behavior for recognizing user is misplaced behavior, determine the corresponding position of the misplaced behavior, triggering pair
Answer the misplaced verifying of shelf at position；
S431, judge that corresponding position shelf are abnormal with the presence or absence of weight gain；
There is weight gain exception in S4321~S4322, corresponding position shelf, it is determined that this time shelf weight change is non-orders
Single operation, user's shopping list does not count the non-order operation, and updates the weight change of corresponding position shelf；Corresponding position
Setting place's shelf, there is no weight gain exception, the then misplaced behavior erroneous judgements；
S433, misplaced article is put back to by correct position according to the weight gain abnormal prompt user or operation personnel.
Illustratively, the embodiment of the present application is when carrying out misplaced verifying, according to the mistake of the Weight detecting device of corresponding shelf
Verification result is put, if user definitely has misplaced behavior, then according to the misplaced behavior, carries out the statistics of related inventory.At this time
Since user has put back to the relative article chosen, then it can correspond to and modify on user's shopping list, it will be on shopping list
Corresponding article is deleted, without statistics.And the article of corresponding shelf is counted, it can be as needed without misplaced article weight
It measures increased statistics or the shelf contents statistics of corresponding position is increased to the weight of misplaced article.And if being tied according to misplaced verifying
Fruit determines that there is no weight gain exceptions at corresponding shelf, then it is assumed that carrying out the misplaced behavior of user that image recognition determines before is to miss
Sentence operation, therefore, the statistics without related inventory.
Later, abnormal according to the weight gain at the correspondence shelf of confirmation, further demonstrate the misplaced behavior of user.In order to keep away
Article that fault-avoidance is put influences the statistics of user's shopping list statistics and shelf contents inventory when subsequent user is chosen, need and
When prompt user or operation personnel come handle this weight gain exception, misplaced article is put back into original position, avoids misplaced article shadow
Ring the normal operation of unmanned convenience store.
By above scheme it is found that the embodiment of the present application is kept away by carrying out real-time prompting to the verified misplaced behavior of user
Exempt from the misplaced normal operation for influencing unmanned convenience store of article, advanced optimizes the shopping experience of user.
Embodiment five:
On the basis of the above embodiments, Fig. 5 is a kind of unmanned store shelf article that the embodiment of the present application five provides
The structural schematic diagram of misplaced detection device.With reference to Fig. 5, the unmanned misplaced detection device of store shelf article provided in this embodiment
It specifically includes: tracking and identifying module 51, misplaced authentication module 52, statistical module 53.
Wherein, track and identify module 51 for user by authentication entrance choose region after, in real time to user into
Line trace and the behavior for identifying user；
Misplaced authentication module 52 is used to determine pair of the misplaced behavior when the behavior for recognizing user is misplaced behavior
Position is answered, the misplaced verifying of corresponding position shelf is triggered；
Statistical module 53 carries out user's shopping list statistics and corresponding shelf object for the result based on the misplaced verifying
Product statistics.
It is above-mentioned, the behavior for choosing the user in region is entered by real-time tracking identification, whether preliminary identification judges user
There are misplaced behaviors, and carry out misplaced verifying according to the misplaced behavior recognized, determine corresponding position goods according to verification result
The situation of change of frame article, and it is clear according to the situation of change of shelf contents progress user's shopping list statistics and corresponding shelf contents
Single statistics so that shopping goods check and shelf contents are checked more accurate, avoid mistake from deducting fees, and then optimize user's purchase
Object is tested.
The unmanned misplaced detection device of store shelf article that the embodiment of the present application five provides can be used for executing above-mentioned reality
The unmanned misplaced detection method of store shelf article for applying the offer of example one, has corresponding function and beneficial effect.
Embodiment six:
The embodiment of the present application six provides a kind of electronic equipment, which includes: processor 61, memory 62, leads to
Believe module 63, input unit 64 and output device 65.The quantity of processor can be one or more in the electronic equipment, should
The quantity of memory in electronic equipment can be one or more.The processor 61 of the electronic equipment, memory 62, communication
Module 63, input unit 64 and output device 65 can be connected by bus or other modes.
Memory 62 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, the corresponding program of the unmanned misplaced detection method of store shelf article as described in the application any embodiment refer to
Order/module is (for example, track and identify module, misplaced authentication module, statistics in the unmanned misplaced detection device of store shelf article
Module).Memory 62 can mainly include storing program area and storage data area, wherein storing program area can storage program area,
Application program needed at least one function；Storage data area, which can be stored, uses created data etc. according to equipment.In addition,
Memory may include high-speed random access memory, can also include nonvolatile memory, and a for example, at least disk is deposited
Memory device, flush memory device or other non-volatile solid state memory parts.In some instances, memory can further comprise phase
The memory remotely located for processor, these remote memories can pass through network connection to equipment.The reality of above-mentioned network
Example includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Communication module 63 is for carrying out data transmission.
Processor 61 is by running software program, instruction and module stored in memory, thereby executing equipment
The above-mentioned unmanned misplaced detection method of store shelf article is realized in various function application and data processing.
Input unit 64 can be used for receiving the number or character information of input, and generate with the user setting of equipment and
The related key signals input of function control.Output device 64 may include that display screen etc. shows equipment.
The unmanned store shelf article that the electronic equipment of above-mentioned offer can be used for executing the offer of above-described embodiment one is misplaced
Detection method has corresponding function and beneficial effect.
Embodiment seven:
The embodiment of the present application also provides a kind of storage medium comprising computer executable instructions, and the computer is executable
Instruction when being executed by computer processor for executing a kind of unmanned misplaced detection method of store shelf article, this nobody just
The sharp misplaced detection method of shop shelf contents includes: through authentication into after choosing region, in real time to user's progress in user
Track and identify the behavior of user；When the behavior for recognizing user is misplaced behavior, the correspondence position of the misplaced behavior is determined
It sets, triggers the misplaced verifying of corresponding position shelf；Result based on the misplaced verifying carry out user's shopping list statistics and
Corresponding shelf contents statistics.
Storage medium --- any various types of memory devices or storage equipment.Term " storage medium " is intended to wrap
It includes: install medium, such as CD-ROM, floppy disk or magnetic tape equipment；Computer system memory or random access memory, such as
DRAM, DDR RAM, SRAM, EDO RAM, Lan Basi (Rambus) RAM etc.；Nonvolatile memory, such as flash memory, magnetic medium
(such as hard disk or optical storage)；Register or the memory component of other similar types etc..Storage medium can further include other
Memory of type or combinations thereof.In addition, storage medium can be located at program in the first computer system being wherein performed,
Or can be located in different second computer systems, second computer system is connected to the by network (such as internet)
One computer system.Second computer system can provide program instruction to the first computer for executing." storage is situated between term
Matter " may include may reside in different location (such as by network connection different computer systems in) two or
More storage mediums.Storage medium can store the program instruction that can be performed by one or more processors and (such as implement
For computer program).
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present application
The unmanned misplaced detection method of store shelf article that executable instruction is not limited to the described above, it is any to can also be performed the application
Relevant operation in the unmanned misplaced detection method of store shelf article provided by embodiment.
The misplaced detection device of unmanned store shelf article, storage medium and the electronic equipment provided in above-described embodiment can
The unmanned misplaced detection method of store shelf article provided by the application any embodiment is executed, not in the above-described embodiments in detail
The technical detail described to the greatest extent, reference can be made to the unmanned misplaced detection side of store shelf article provided by the application any embodiment
Method.
The technical principle that above are only the preferred embodiment of the application and used.The application is not limited to spy described here
Determine embodiment, various significant changes, readjustment and the substitution being able to carry out for a person skilled in the art are not departing from
The protection scope of the application.Therefore, although being described in further detail by above embodiments to the application, this Shen
Above embodiments please be not limited only to, can also include other more equivalence enforcements in the case where not departing from the application design
Example, and scope of the present application is determined by the scope of the claims.
Claims (10)
1. a kind of unmanned misplaced detection method of store shelf article characterized by comprising
After user chooses region by authentication entrance, the behavior of user is tracked and identified to user in real time；
When the behavior for recognizing user is misplaced behavior, determines the corresponding position of the misplaced behavior, trigger corresponding position
The misplaced verifying of shelf；
Result based on the misplaced verifying carries out user's shopping list statistics and corresponding shelf contents statistics.
2. the unmanned misplaced detection method of store shelf article according to claim 1, which is characterized in that described misplaced to test
Card includes:
Determine that corresponding position shelf are abnormal with the presence or absence of weight gain based on the misplaced behavior.
3. the unmanned misplaced detection method of store shelf article according to claim 2, which is characterized in that described according to institute
The result for stating misplaced verifying carries out user's shopping list statistics and corresponding shelf contents statistics, comprising:
If it is abnormal to there is weight gain in corresponding position shelf, it is determined that this time shelf weight change is non-order operation, user's shopping
Inventory does not count the non-order operation, and updates the weight change of corresponding position shelf；
If there is no weight gain exception, the misplaced behavior erroneous judgements for corresponding position shelf.
4. the unmanned misplaced detection method of store shelf article according to claim 3, which is characterized in that if described right
Shelf at position are answered to there is weight gain exception, it is determined that this time shelf weight change is non-order operation, and user's shopping list is not united
The non-order operation is counted, and after updating the weight change of corresponding position shelf, further includes:
Misplaced article is put back into correct position according to the weight gain abnormal prompt user or operation personnel.
5. the unmanned misplaced detection method of store shelf article according to claim 1, which is characterized in that the identification is used
The behavior at family is that misplaced behavior includes:
It identifies that the article of user takes out operation, determines that the taking-up operates corresponding first position；
The correspondence article of identification user puts back to operation, and the corresponding second position of operation is put back to described in determination；
It is whether consistent with the second position to compare the first position, if the first position and the second position are different
It causes, it is determined that it is misplaced behavior that the correspondence article of user, which puts back to operation,.
6. the unmanned misplaced detection method of store shelf article according to claim 1, which is characterized in that the identification is used
The behavior at family is that misplaced behavior includes:
The article of identification user puts back to operation, determines the classification for putting back to article；
The corresponding position that operation is put back to described in determination identifies the classification of the original article in the corresponding position；
Whether classification and the original goods categories that article is put back to described in comparison are consistent, if the classification for putting back to article and institute
The classification for stating original article is inconsistent, it is determined that it is misplaced behavior that the article of the user, which puts back to operation,.
7. the unmanned misplaced detection method of store shelf article according to claim 1, which is characterized in that described in user
Entered after choosing region by authentication, in the behavior for user being tracked and being identified in real time user, passes through entrance guard device
Detection user chooses region described in whether entering, and is known according to the user that entrance guard device detects behavior triggering usertracking of entering
Other event starts the behavior for tracking and identifying user to user in real time.
8. a kind of unmanned misplaced detection device of store shelf article characterized by comprising
Module is tracked and identified, for user being tracked and being known in real time after user chooses region by authentication entrance
The behavior of other user；
Misplaced authentication module, for determining the correspondence position of the misplaced behavior when the behavior for recognizing user is misplaced behavior
It sets, triggers the misplaced verifying of corresponding position shelf；
Statistical module carries out user's shopping list statistics and corresponding shelf contents system for the result based on the misplaced verifying
Meter.
9. a kind of electronic equipment characterized by comprising
Memory and one or more processors；
The memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The existing unmanned misplaced detection method of store shelf article as claimed in claim 1.
10. a kind of storage medium comprising computer executable instructions, which is characterized in that the computer executable instructions by
For executing the unmanned misplaced detection side of store shelf article as claimed in claim 1 when computer processor executes
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910709187.5A CN110490698A (en) | 2019-08-01 | 2019-08-01 | A kind of unmanned misplaced detection method and device of store shelf article |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910709187.5A CN110490698A (en) | 2019-08-01 | 2019-08-01 | A kind of unmanned misplaced detection method and device of store shelf article |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110490698A true CN110490698A (en) | 2019-11-22 |
Family
ID=68549031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910709187.5A Withdrawn CN110490698A (en) | 2019-08-01 | 2019-08-01 | A kind of unmanned misplaced detection method and device of store shelf article |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110490698A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739091A (en) * | 2020-03-24 | 2020-10-02 | 北京京东乾石科技有限公司 | Article replacement detection method, device, equipment and medium |
| CN112309031A (en) * | 2020-09-17 | 2021-02-02 | 北京京东乾石科技有限公司 | Unmanned container mixed discharge detection method, device, equipment and readable storage medium |
| CN115311830A (en) * | 2021-01-19 | 2022-11-08 | 东芝泰格有限公司 | Informing device and informing method |
-
2019
- 2019-08-01 CN CN201910709187.5A patent/CN110490698A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739091A (en) * | 2020-03-24 | 2020-10-02 | 北京京东乾石科技有限公司 | Article replacement detection method, device, equipment and medium |
| CN112309031A (en) * | 2020-09-17 | 2021-02-02 | 北京京东乾石科技有限公司 | Unmanned container mixed discharge detection method, device, equipment and readable storage medium |
| CN112309031B (en) * | 2020-09-17 | 2022-06-07 | 北京京东乾石科技有限公司 | Unmanned container mixed discharge detection method, device, equipment and readable storage medium |
| CN115311830A (en) * | 2021-01-19 | 2022-11-08 | 东芝泰格有限公司 | Informing device and informing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109840504B (en) | Article taking and placing behavior identification method and device, storage medium and equipment | |
| CN107451816B (en) | Method and device for realizing offline transaction | |
| US10192408B2 (en) | Registry verification for a mechanized store using radio frequency tags | |
| US20200202163A1 (en) | Target positioning system and target positioning method | |
| CN108806074B (en) | Shopping information generation method and device and storage medium | |
| US10943128B2 (en) | Constructing shopper carts using video surveillance | |
| CN109979130A (en) | A kind of commodity automatic identification and clearing sales counter, method and system | |
| US8429016B2 (en) | Generating an alert based on absence of a given person in a transaction | |
| CN110490698A (en) | A kind of unmanned misplaced detection method and device of store shelf article | |
| CN108171172A (en) | Self-help shopping method, self-service sale device and computer readable storage medium | |
| CN107392614B (en) | Method and device for realizing offline transaction | |
| CN110866429A (en) | Missed scanning identification method and device, self-service cash register terminal and system | |
| CN112466035B (en) | Commodity identification method, device and system based on vision and gravity sensing | |
| CN111263224B (en) | Video processing method and device and electronic equipment | |
| CN111079478B (en) | Unmanned goods shelf monitoring method and device, electronic equipment and system | |
| CN110050284A (en) | Register system in a kind of automatic shop | |
| CN110490516A (en) | A kind of unmanned store shelf article detection method and device | |
| CN110490515A (en) | Unmanned store shelf article detection method, device, computer and storage medium | |
| CN110490697A (en) | Unmanned convenience store's settlement method, device, computer and storage medium | |
| CN107688980A (en) | A kind of unattended intelligent purchase method and unattended intelligent purchase system | |
| CN109523694A (en) | A kind of retail trade system and method based on commodity detection | |
| CN111507792A (en) | Self-service shopping method, computer readable storage medium and system | |
| CN110473065A (en) | Unmanned convenience store user virtual shopping inventory display methods and device | |
| CN110443946A (en) | Vending machine, the recognition methods of type of goods and device | |
| JP7318753B2 (en) | Information processing program, information processing method, and information processing apparatus |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191122 |
|
| WW01 | Invention patent application withdrawn after publication |