CN117727149A - Intelligent goods shelf anti-theft system and anti-theft method - Google Patents

Abstract

The invention discloses an intelligent goods shelf anti-theft system and an anti-theft method, wherein the method comprises the following steps: responding to the induction signal of the human body induction module, and acquiring the appearance characteristic information of the user by using the shelf monitoring module; acquiring goods taking information through a goods sensing module; collecting stay information of a user through a global monitoring module, determining time-dependent identity information of the user according to the stay information and the appearance characteristic information, and constructing a mapping relation between the time-dependent identity information and goods taking information; determining a checkout completion result of the user through a checkout cashing module; if the user finishes checkout, determining a matching result of checkout information and goods taking information corresponding to the user; if the matching result is that the matching fails, generating first alarm information. The method enables the store owner to master the behavior of the user in the unmanned selling store in real time, effectively prevents theft and loss, and realizes reliable unmanned selling.

Description

Intelligent goods shelf anti-theft system and anti-theft method

Technical Field

The invention relates to the technical field of unmanned vending control, in particular to an intelligent goods shelf anti-theft system and an anti-theft method.

Background

At present, along with the development of technologies such as mobile payment, internet of things and the like and the habit change of consumers, the retail industry has an unattended function of providing 24 hours for convenience stores. After the user enters the store to select the required goods, self-service checkout can be performed, and then the user can conveniently and quickly leave the store directly. The types of packages of goods in the unmanned convenience store are in the forms of boxes, bottles, bags, bulk and the like. For part of the packed and boxed goods packages, a hook hole is reserved on the package so as to be hung and displayed on a hook goods shelf for facilitating the customer to take. However, in an unmanned sales environment, a store owner cannot know the taking condition of a user in a store on goods on a goods shelf in real time, so that the storage quantity and the sales condition of the goods in the store at present cannot be controlled in real time, and only a certain time is needed to go to the spot for counting, thereby causing low efficiency of sales management; meanwhile, the store owner cannot effectively avoid the situation that the user leaves the store without checking out after taking the goods, and loss is easy to cause.

Disclosure of Invention

The embodiment of the invention provides an intelligent goods shelf anti-theft system and an intelligent goods shelf anti-theft method. Aims to solve the problems that in the prior art, a store owner who does not sell a store can not quickly learn the selling condition of goods, so that the store management efficiency is low and the anti-theft can not be effectively carried out.

In a first aspect, an embodiment of the present invention provides an intelligent shelf anti-theft system, including a shelf main body module, provided with a plurality of hangers, each of the hangers being respectively used for hanging a plurality of goods; the goods sensing modules are connected to the hanging racks in the goods shelf main body module in a one-to-one correspondence manner, and are used for sensing the goods and determining goods taking information of the goods when the corresponding goods are hung into or separated from the goods shelf main body module; the human body sensing module is arranged at the front end of the goods shelf main body module and is used for sensing a user positioned in front of the goods shelf main body module; the goods shelf monitoring module is used for further monitoring the hooking condition or the detachment condition of each goods on the goods shelf main body module and acquiring the appearance characteristic information of the user; the global monitoring module is used for monitoring the goods shelf main body module and the check-out condition of the goods and acquiring the stay information of the user; the checkout and cashing module is used for acquiring checkout information corresponding to the user; and the central processing module is in communication connection with the goods induction module, the human body induction module, the goods shelf monitoring module, the global monitoring module and the checkout and cashing module and is used for acquiring the hanging or separating condition of goods on the goods shelf main body module and the checkout condition of the goods.

In a second aspect, an embodiment of the present invention further provides an intelligent shelf anti-theft method, which is applied to the central processing module in the intelligent shelf anti-theft system according to the first aspect, where the method includes:

responding to the induction signal of the human body induction module, starting the shelf monitoring module to record the video of the shelf main body module and collect the appearance characteristic information of the user positioned in front of the shelf main body module;

acquiring goods taking information of goods taken by the user in the current goods shelf main body module through the goods sensing module;

collecting the stay information of the user through a global monitoring module, determining the aging identity information of the user according to the stay information and the appearance characteristic information, and constructing a mapping relation between the aging identity information and the goods taking information; wherein the stay information at least comprises stay time of the user and stay identification area;

determining a checkout completion result of the user through a checkout cashing module according to the aging identity information and the goods taking information;

if the checkout completion result of the user is completed, determining checkout information of the user through a checkout cashing module, and determining a matching result of the checkout information and goods taking information corresponding to the user;

If the matching result is that the matching fails, generating first alarm information;

and if the matching result is that the matching is successful, generating purchase completion information.

Based on the anti-theft system and the corresponding anti-theft method provided by the embodiment of the invention, the intelligent goods shelf anti-theft system provided by the embodiment of the invention can acquire the situation that goods are taken out or put back by a user in real time by arranging the goods induction module; through goods shelf monitoring module and global monitoring module, can acquire the appearance characteristic information of the user who is purchasing goods at present and the stay information of user before goods shelf main part module in real time to confirm the goods information of taking of user on goods shelf main part module through stay information, bind goods information and user's ageing identity information, and then can grasp the behavior trend of user in unmanned selling the shop in real time, and then ensure the effective management of shop owner to the shop sales. Meanwhile, the check-out and cashing module is used for comparing the goods taking information and the check-out information of the user, so that the situation that the user does not check out and leaves the unmanned selling shop can be effectively prevented, further, theft prevention is effectively carried out, loss is avoided, and reliable unmanned selling is achieved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an intelligent shelf anti-theft system and an application scenario thereof provided by an embodiment of the present invention;

FIG. 2 is a schematic flow chart of an intelligent shelf anti-theft method provided by an embodiment of the invention;

FIG. 3 is a schematic diagram of a first sub-process of the intelligent shelf anti-theft method according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a second sub-flowchart of an intelligent shelf anti-theft method according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a third sub-flowchart of an intelligent shelf anti-theft method according to an embodiment of the present invention;

fig. 6 is a schematic diagram of a fourth sub-flowchart of an intelligent shelf anti-theft method according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

Referring to fig. 1, as shown in fig. 1, an embodiment of the present invention provides an intelligent shelf anti-theft system, which may be disposed in a vending shop and at least includes the following modules: the shelf main body module 10 is provided with a plurality of hanging frames 11, and each hanging frame 11 is used for hanging a plurality of goods; the plurality of goods sensing modules 20 are connected to each hanger 11 in the goods shelf main body module 10 in a one-to-one correspondence manner, and are used for sensing the goods and determining the goods taking information of the goods when the corresponding goods are hung into the goods shelf main body module 10 or are separated from the goods shelf main body module 10; the human body sensing module 30 is arranged at the front end of the shelf main body module 10 and is used for sensing a user positioned in front of the shelf main body module 10; the shelf monitoring module 40 is configured to further monitor a hooking condition or a detachment condition of each item on the shelf main body module 10, and obtain appearance characteristic information of the user; the global monitoring module 50 is configured to monitor the checkout conditions of the goods and the shelf main module 10, and obtain the residence information of the user; the checkout and cashing module 60 is configured to obtain checkout information corresponding to the user; the central processing module 70 is communicatively connected to the goods sensing module 20, the human body sensing module 30, the goods shelf monitoring module 40, the global monitoring module 50 and the checkout module 60, and is configured to obtain a hanging situation or a separating situation of the goods on the goods shelf main body module 10 and a checkout situation of the goods.

In the present embodiment, the central processing module 70 may be a module capable of information acquisition and processing, such as a server, an intelligent processing terminal, or the like. The central processing module 70 can receive various data from the goods sensing module 20, the human body sensing module 30, the shelf monitoring module 40, the global monitoring module 50 and the checkout module 60, and issue control instructions to the respective modules after processing the various data, or obtain various information according to the various data.

The shelf main body module 10 is an independent display structure for hanging goods, on which a plurality of hanging frames 11 are arranged, and each outer package of the goods is provided with a hanging hole through which the hanging frame 11 can pass, and further, the goods can be hung on the hanging frame 11 through the hanging hole. The front end of the shelf main body module 10 may have a plurality of racks 11 arranged in parallel, and for a single rack 11, a plurality of articles hung on the rack 11 are the same article. Before the store owner or the store clerk hangs the goods on the hangers 11, information such as the type, model, price, storage quantity and the like of the goods to be hung on each hanger 11 can be predetermined, and the goods can be hung on the corresponding hanger 11 according to the information. For acquiring the goods in real time and separating from the hanging rack 11 or being put back to the hanging rack 11, the goods sensing modules 20 can be independently arranged on each hanging rack 11, and the goods sensing modules 20 can be in a structural form such as an infrared sensor which can sense the movement of the goods. The article sensing module 20 is actually provided at the head end of each hanger 11, and the article needs to be hung into the hanger 11 from the head end of the hanger 11 or taken down from the head end of the hanger 11. Therefore, when a user or a power source takes goods from the hanger 11 or puts the goods into the hanger 11 again, the goods sensing module 20 on the corresponding hanger 11 can sense the condition that the goods are taken or put back in real time, but does not sense when the goods are stationary. Specifically, when the article moves from the head end to the tail end of the hanger 11, it can be determined that the article is put back into the hanger 11, and when the article moves from the tail end to the head end of the hanger 11, it can be determined that the article is taken out of the hanger 11.

It can be appreciated that when a clerk performs a loading or unloading operation on the goods, or when a user takes the goods off the hanger 11 or puts the goods back on the hanger 11, the central processing module 70 can record the taking-out condition or the putting-back condition of the goods according to the sensing condition of the shelf sensing module, and update the storage condition of the goods according to the taking-out condition or the putting-back condition, so that the clerk can learn the sales condition of the current goods in real time. To bind the item pickup information to the user, the shelf monitor module 40 and the global monitor module 50 may be provided at the same time. The shelf monitor module 40 may be a camera disposed on the shelf main body module 10, which can record each hanger 11 on the front end of the shelf monitor module 40 and the goods on the hanger 11, and acquire the face image of the user in front of the shelf, so as to extract the appearance characteristic information of the user from the face image. In order to improve the efficiency and accuracy of user identification, a human body sensing module 30 may be additionally arranged in front of the shelf main body module 10, the human body sensing module 30 may be in a structural form of an infrared sensor, when the distance between the user and the corresponding shelf main body module 10 is smaller than a preset distance threshold, the human body sensing module 30 is triggered, and at this time, the shelf monitoring module 40 records and identifies images in front of the shelf. Meanwhile, the global monitoring modules 50 can be arranged at various positions in the store, and each global monitoring module 50 can acquire a global image of the store. The identification area corresponding to each shelf main body module 10 can be preset corresponding to each global monitoring module 50, and meanwhile, the checkout identification area corresponding to each checkout receipt module 60 can also be preset, when a user is located in each identification area or checkout identification area, the central processing module 70 can acquire the shelf main body module 10 corresponding to the identification area where the user is located or the checkout receipt module 60 corresponding to the checkout identification area through the global monitoring module 50, so that the location of the user is determined, and the goods taking information of the location is bound with the user according to the location of the user, so that effective management of the goods and the user is realized.

Wherein a plurality of shelf monitor modules 40 may be provided to accommodate a larger number of shelf body modules 10. It will be appreciated that since the goods sensing module 20 has no recognition function, when a user puts goods back into the hanger 11 and is sensed by the goods sensing module 20, the goods sensing module 20 cannot recognize the kind of the goods currently put back. When a user enters an unmanned selling shop provided with the intelligent goods shelf anti-theft system, the user needs to authorize the shop to acquire the external feature information.

Corresponding to the intelligent shelf anti-theft system, the embodiment of the invention also provides an intelligent shelf anti-theft method which is applied to the central processing module in the shelf anti-theft system, referring to fig. 2, as shown in fig. 2, the method comprises the following steps:

s110, responding to the induction signal of the human body induction module, starting the shelf monitoring module to record the video of the shelf main body module and collecting the appearance characteristic information of the user positioned in front of the shelf main body module.

The central processing module 70 may determine that a user stands in front of the shelf main body module 10 corresponding to the human body sensing module 30 at this time when the sensing signal of the human body sensing module 30 is obtained, and may start the shelf monitoring module 40 on the shelf main body module 10 corresponding to the human body sensing module 30 to perform image acquisition on the user at this time. After capturing a plurality of facial images of the user, the user's appearance characteristic information may be captured by a preset face recognition algorithm and given an acquisition time to determine when the user stands in front of the shelf main body module 10. Meanwhile, if the user stays in front of the shelf main body module 10 for a certain time, the starting and ending time points of the time period can be determined by the first acquisition time of the first time of the appearance characteristic information and the second acquisition time of the last time of the appearance characteristic information acquired by the shelf monitoring module 40.

S120, acquiring goods taking information of goods taken by the user in the current goods shelf main body module through the goods sensing module; the goods taking information at least comprises a goods shelf main body module corresponding to the goods and induction time when the goods are taken.

The sensing information of the goods sensing modules 20 can generate goods taking information of corresponding goods, and each goods sensing module 20 only senses the goods of the corresponding hanger 11, so that the corresponding goods taking information can be in one-to-one correspondence with the goods sensing modules 20.

In one embodiment, referring to FIG. 3, step S120 may include the following steps S121-S123:

s121, determining the current goods induction module which inducts that the goods are taken out as a first target goods induction module, and determining induction time of the first target goods induction module.

S123, determining name information and price information of the goods according to the goods storage information corresponding to the first target goods sensing module, and updating the goods storage information; the goods storage information at least comprises goods corresponding to the goods and stock quantity.

S123, combining the updated goods storage information, the updated name information, the updated price information, the updated sensing time and the updated goods main body module corresponding to the first target goods sensing module into the goods taking information.

In this embodiment, the central processing module 70 stores the goods storage information corresponding to each hanger 11, and the goods storage information corresponding to a single hanger 11 also directly corresponds to the goods sensing module 20 on the hanger 11. Therefore, when the first article sensing module 20 senses that the article is taken out, the central processing module 70 may update the article storage information corresponding to the hanger 11 according to the hanger 11 corresponding to the first article sensing module 20. Specifically, if the first article sensing module 20 senses that the first number of articles are taken out from the hanger 11, the inventory number in the article storage information corresponding to the hanger 11 may be decremented and updated, and the inventory number is the first number. Meanwhile, the information of the name information, the price information and the like corresponding to the goods are also included in the goods storage information, when the first goods sensing module 20 senses that the goods are taken out, the central processing module 70 can also simultaneously acquire the name information and the price information of the goods, and record the sensing time of taking out the goods, so that the goods taking information can be bound with a user by utilizing the sensing time in the subsequent process. Finally, the article storage information, the name information, the price information, the sensing time and the article main body module corresponding to the first article sensing module 20 may be combined into the article taking information uniquely corresponding to the article to be taken out, so as to determine the original storage position of the article. It can be seen that while the goods are being taken, the store owner can acquire the taking situation and the stock situation of the goods in real time through the terminal communicating with the central processing module 70. The central processing module 70 may also determine the number of items currently being taken but not checked out for real-time theft risk management.

S130, collecting stay information of the user through a global monitoring module, determining aging identity information of the user according to the stay information and the appearance characteristic information, and constructing a mapping relation between the aging identity information and the goods taking information; wherein the stay information at least comprises stay time of the user and stay identification area.

The global monitoring module 50 can identify the user image in the shop panoramic image through a preset identification algorithm such as a confidence level identification algorithm, and determine the shelf main body module 10 where the user is currently located according to the identification area where the user image is located, namely determine the stay identification area of the user; at the same time, the time that the user remains in front of the shelf body module 10 where the user is currently located can also be determined, thereby determining the residence time of the user. The dwell time and dwell identification area may then be used together as a set of dwell information for the user to indicate that the user is staying in front of a certain shelf body module 10 for a certain period of time. Then, since the article taking information also includes the article taking time, a mapping relationship can be established between the article taking information and the user in the residence time, so as to determine the taking condition of the user on the article in the current shelf main body module 10.

In one embodiment, referring to fig. 4, step S130 may specifically include the following steps:

s131, determining a stay identification area where the user is located and stay time of the user in the stay identification area through the global monitoring module, and taking the stay identification area and the stay time as the stay information.

Since each shelf body module 10 is divided into respective unique identification areas in the image captured by the global monitoring module 50, when a user is located in an identification area in front of a certain shelf body module 10, the global monitoring module 50 can determine a stay identification area of the user, and establish a binding relationship between the stay identification area and the shelf body module 10, and record the stay time of the user in the stay identification area, where the stay time includes a start time point and an end time point, and the two time points correspond to the time when the user enters the identification area and leaves the identification area, respectively. The stay identification area and the stay time may then be used as stay information for the user. It will be appreciated that the global monitoring module 50 cannot confirm the identity of the user and therefore first generates a stay message for the identity to be claimed.

And S132, determining the last acquired appearance characteristic information of the target shelf main body module corresponding to the stay identification area and the shelf monitoring module corresponding to the target shelf main body module.

The central processing module 70 may then acquire the last acquired appearance characteristic information (i.e., the present appearance characteristic information) in the stay identification area, and may then determine the identity of the user to whom the appearance characteristic information corresponds.

S133, determining the stay information and the last acquired appearance characteristic information as aging identity information of the user.

After the appearance characteristic information is obtained, the stay information of the identity to be claimed can be bound with the user with the appearance characteristic information so as to confirm the aging identity information of the user.

And S134, mapping each item taking information with the sensing time within the residence time in the target goods shelf main body module to the item taking information corresponding to the user so as to construct a mapping relation between the aging identity information corresponding to the user and the item taking information.

Then, the item taken in the dwell time corresponding to the aged identity information of the user may be determined to be the item taken by the user. And then, mapping the information of each article in the residence time to the time-lapse identity information of the user, so as to realize the information binding of the user and the fetched articles.

In this embodiment, by determining the residence information of the user and the goods taken in the residence time, the goods taking information and the aging identity information of the user can be effectively bound, so that the user and the goods taken by the user can be effectively tracked, and an effective anti-theft effect is achieved.

In one embodiment, step S134 further includes the following steps:

if the global monitoring module identifies that the user with the aging identity information is located in a stay identification area corresponding to another shelf main body module, determining a first acquisition time of the shelf monitoring module in the other shelf main body module to the appearance characteristic information corresponding to the user;

determining a second acquisition time for the user to leave the identified area of the other shelf body module;

if the appearance characteristic information corresponding to another user does not exist in the time period from the first acquisition time to the second acquisition time, the goods taking information corresponding to the other goods shelf main body module in the time period from the first acquisition time to the second acquisition time and the aging identity information of the user are constructed into a mapping relation.

In this embodiment, when the global monitoring module 50 identifies that the user is located in the residence identification area corresponding to another shelf main body module 10, it is necessary to determine the residence time of the user in the residence identification area corresponding to the shelf main body module 10, at this time, the residence time of the user may be further determined by the first acquisition time and the second acquisition time acquired by the shelf monitoring module 40, and if no other user's appearance characteristic information is identified between the first acquisition time and the second acquisition time, the item taking information in the residence time may be added to the item taking information of the currently identified user, so as to implement updating of the item taking information of the user. If the appearance characteristic information corresponding to another user exists in the time period from the first acquisition time to the second acquisition time, the article taking information corresponding to the articles taken by each customer in the overlapping time period of the residence time before the shelf main body module 10 can be mapped to the aging identity information of each user at the same time, and when each user in the overlapping time period has completed checkout, the intersection of all the article information in the checkout information of each user is confirmed, and if each article taking information corresponding to each article taken in the overlapping time period exists in the intersection of all the article information, it can be determined that no user checkout occurs. Specifically, for example, the user a and the user B are simultaneously acquired the appearance characteristic information in the time period from the first acquisition time to the second acquisition time, and the article taking information of the article C exists in the overlapping time period identified by the user a and the user B, then the article taking information of the article C is simultaneously mapped into the aging identity information of the user a and the user B, after the user a and the user B are determined to finish checkout, the union set of the article information in the checkout information of the user a and the user B can be acquired, and if the article taking information of the article C exists in the union set, it can be determined that the phenomenon that the checkout is not left occurs. If the goods taking information of the C goods does not exist, the information of the appearance characteristics of the A user and the B user can be tracked, so that effective theft prevention is realized.

In an embodiment, referring to fig. 5, the following steps S1301-S1309 may be further included after step S130:

s1301, determining whether a second target goods sensing module sensing that goods are put back exists; if yes, go to step S1302; if not, it is determined that the article has been removed.

If an article sensing module 20 senses that an article is placed, it can be determined that the user does not select the article at this time, and the article is desired to be placed back on the hanger 11. The item sensing module 20 may be identified as a second item sensing module 20 at this time. However, there may be a case where the user puts the article into another hanger 11 different from the hanger 11 where the article is originally hung. To avoid cluttering the display of the article in this case, it is necessary to determine whether the article is placed into the correct hanger 11.

S1302, when only the goods taking information corresponding to the current goods shelf main body module where the user is located exists in the goods taking information corresponding to the user, acquiring first sensing time when the second target goods sensing module senses that the goods are put back, and acquiring second sensing time when the last sensing time senses that the goods are taken out.

When the goods taking information corresponding to the user only corresponds to the goods taking information of the current goods shelf main body module 10 where the user is located, the first goods sensing module 20 and the second goods sensing module 20 representing the moment are located on the same goods shelf main body module 10, and the user only takes the goods from the current goods shelf main body module 10 where the user is located. When the shelf monitoring module 40 in the current shelf main body module 10 acquires the appearance characteristic information of the user, or when the user is identified by the global monitoring module 50 to be located in the identification area of the current shelf main body module 10, the central processing module 70 can automatically determine all the goods taking information corresponding to the user according to the aging identity information of the user. Therefore, it is required to acquire the second sensing time of the first article sensing module 20 that the article is taken out last time in the current shelf main body module 10, and acquire the first sensing time of the second article sensing module 20 that the article is put back, and further determine whether the article put back again belongs to the shelf main body module 10 through the time interval between the first sensing time and the second sensing time, so as to prevent the occurrence of the situation that the user takes the article in another shelf main body module 10 but is not successfully recorded. The first article sensing module 20 that senses that the article is taken out last time may also be the article sensing module 20 corresponding to the article that is taken out last time in the article taking information corresponding to the user.

S1303, determining whether the difference between the first sensing time and the second sensing time is smaller than a preset time difference; if yes, go to step S1304; if not, go to step S1308.

If the difference between the first sensing time and the second sensing time is greater than or equal to the preset time difference, it means that the user is likely to take the commodity from another shelf main body module 10 and then place the commodity into the current shelf main body module 10, and the commodity taking information is not recorded successfully, and at this time, the first commodity placement error risk information needs to be sent to the store owner to prompt the store owner that the condition that the commodity is mixed between different shelf main body modules 10 may exist.

S1304, judging whether the number of the appearance characteristic information acquired by the shelf monitoring module in a time period from the second sensing time to the first sensing time is greater than one; if yes, go to step S1309; if not, step S1305 is executed.

Then, it is necessary to determine whether there are other users present in front of the current shelf main body module 10 between the first sensing time and the second sensing time. If there are different users, it cannot be determined which user is placing the item back to the current shelf body module 10 at this time, and the central processing module 70 needs to send a second item placement error risk message to the store owner to prompt the store owner that there may be an item confusion. In addition, when the number of the obtained appearance characteristic information is greater than one, the article taking information of the user corresponding to each appearance characteristic information can be obtained, and if only one of the users has the article taking information corresponding to the current shelf main body module 10, then the article which is put back at present can be determined as the article which is taken out last time; if there are a plurality of users having the goods taking information corresponding to the current goods shelf main body module 10, the sensing time corresponding to each of the goods taking information corresponding to the current goods shelf main body module 10 is acquired, and the goods taking information corresponding to the sensing time nearest to the first sensing time is determined as the last fetched goods.

S1305 determines that the item currently being returned is the item that was last removed.

If only one user is located in the current shelf body module 10 during the first sensing time and the second sensing time, it can be determined that the returned item is the item that was last taken out.

S1306, determining whether the second target goods sensing module is different from the first target goods sensing module which senses that the goods are taken out last time; if yes, go to step S1307; if not, determining that the goods are correctly placed back.

If the second article sensing module 20 sensing that the article is put back and the first article sensing module 20 sensing that the article is taken out last time are not the same modules, it may be determined that the article is put on the wrong hanger 11. If the second goods sensing module 20 is the same as the first goods sensing module 20, it can be determined that the user correctly puts the goods back on the hanging rack 11 which is originally hung.

S1307, generate first article placement error alert information.

If the goods are placed in error, a first goods placement error alarm message needs to be generated, and the message is mainly used for prompting the store owner that the goods are hung on the wrong hanging rack 11 on the current goods shelf main body module 10 at the moment, and the correct hanging rack 11 corresponding to the goods is also located on the current goods shelf main body module 10.

S1308, first article placement error risk information is generated.

The first item placement error risk information is used to alert the store owner that there may be an item confusion between different shelf body modules 10.

S1309, second item placement error risk information is generated.

The second item placement error risk information is used to alert the store owner that item confusion may exist.

In this embodiment, by determining the difference of the sensing time and the number of the appearance characteristic information, it is able to effectively determine whether the goods are placed on the wrong hanger 11 when the user only takes the goods on the current shelf main body module 10 and puts the goods back again, thereby effectively performing management on the placement of the goods. In addition, if there are a plurality of goods taking information of the current goods shelf main body module 10 corresponding to the user currently located in front of the current goods shelf main body module 10, then early warning information may be sent to the store owner, so as to prevent the user from hanging the goods of the same goods shelf main body module 10 onto the first goods sensing module 20 which senses that the goods are taken out last time, but the goods and the first goods sensing module 20 do not correspond to each other, and the situation corresponding to another goods sensing module 20 occurs.

In an embodiment, referring to fig. 6, the following steps S210-S240 may be further included after step S130:

s210, determining whether a second target goods sensing module sensing that goods are put back exists; if yes, go to step S220; if not, it is determined that the article has been removed.

If an article sensing module 20 senses that an article is placed, it can be determined that the user does not select the article at this time, and the article is desired to be placed back on the hanger 11. The item sensing module 20 may be identified as a second item sensing module 20 at this time. However, there may be a case where the user takes the article at each of the plurality of shelf body modules 10 and then puts the article into another article body module different from the article body module in which the article was originally hung. To avoid cluttering the display of the item in this situation, it is necessary to determine whether the item is placed into the correct item body module.

S220, when the goods taking information corresponding to the user exists in the goods taking information corresponding to the plurality of different goods shelf main body modules, acquiring the goods taking information of the goods taken by the user in each goods shelf main body module; each shelf main body module comprises a current shelf main body module where the user is located and other shelf main body modules where the user is not located.

When a user has taken a number of items from each of a plurality of different shelf body modules 10, then the item currently returned on behalf of the user may originate from the current shelf body module 10 or from the remaining shelf body modules 10. At this time, the shelf main body module 10 corresponding to each item taking information in the item taking information corresponding to the user needs to be acquired.

S230, determining whether target goods taking information corresponding to a first target goods sensing module in the current goods shelf main body module exists in the goods taking information; if yes, go to step S240, if no, go to step S250.

After the goods shelf main body module 10 corresponding to each piece of goods taking information in the goods taking information corresponding to the user is obtained, each goods shelf main body module 10 of the goods taken by the user can be compared and matched with the current goods shelf main body module 10.

S240, when the second target goods sensing module is different from each first target goods sensing module corresponding to the target goods taking information, generating second goods placement error warning information.

If there is a current shelf body module 10 in each of the shelf body modules 10 that the user has taken the item, it means that the item currently returned by the user is likely to be located in the current shelf body module 10. At this time, if the second goods sensing module 20 is different from each first goods sensing module 20 corresponding to all the users, it may be determined that there is a certain placement error condition of the goods that are currently placed back, and the second goods placement error alarm information is used to prompt the store owner that the goods are placed on the wrong hanger 11, as to how to determine whether the goods are originally located in the current goods shelf main body module 10 or the rest of the goods shelf main body modules 10, it may be determined that the sensing time is located in the current goods shelf main body module 10 before the second sensing time of the first goods sensing module 20 that senses that the goods are taken out last time by acquiring each sensing time corresponding to the goods taking information corresponding to the users, and it may be determined that the goods are originally located in the current goods shelf main body module 10 if only corresponds to the current goods shelf main body module 10; if there is a correspondence between the current shelf body module 10 and a number of remaining shelf body modules 10, it may be determined that the item is likely to be from the remaining shelf body modules 10, and at this time, early warning information needs to be sent to the store owner to indicate that the store owner may have the item of the remaining shelf body modules 10 placed in the current shelf body module 10.

S250, generating third goods placement error warning information.

If the current shelf main body module 10 does not exist in the respective shelf main body modules 10 for taking the goods, it can be directly determined that the goods put back do not belong to the current shelf main body module 10, and at this time, the third goods placement error warning information is used for prompting the store owner that the goods are placed on the wrong shelf main body module 10.

In this embodiment, by acquiring each shelf main body module 10 corresponding to each item taking information corresponding to the user, it is possible to effectively and comprehensively determine whether the user puts the item in the wrong shelf main body module 10, and prompt the store owner to manage in time. It can be understood that the image recognition algorithm of the added goods can also be used to directly utilize the goods shelf monitoring module 40 to obtain the goods images on each hanging frame 11, and directly perform recognition analysis on the goods images to determine whether different goods are hung on one hanging frame 11. The above steps provided by the embodiment of the invention are simplified steps which do not need to rely on the goods image recognition algorithm.

And S140, determining a checkout completion result of the user through a checkout and cashing module according to the aging identity information and the goods taking information.

The aging identity information and the goods taking information are mapped and matched with each other, and further, after the user performs the checkout operation on the checkout cashing module 60, the checkout information generated by the checkout cashing module 60 can be compared with the goods taking information to determine whether the user with the corresponding aging identity information finishes checkout of all goods.

In one embodiment, the step S140 may specifically include the following steps:

determining an identification frame corresponding to the user through the global monitoring module;

if the global monitoring module obtains that the identification frame corresponding to the user is located in a checkout identification area where the checkout receipt module is located, determining first time when the user corresponding to the identification frame enters the checkout identification area and second time when the user corresponding to the identification frame leaves the checkout identification area, and determining the checkout receipt module corresponding to the checkout identification area;

if the checkout information exists in the checkout module corresponding to the checkout identification area in the time period from the first time to the second time, determining that the checkout completion result of the user is completed;

and if the checkout information does not exist in the time period from the first time to the second time by the checkout cashing module corresponding to the checkout identification area, determining that the checkout completion result of the user is incomplete.

In this embodiment, since a plurality of checkout modules 60 are provided, the user can check at any one of the checkout modules 60, and at this time, the global monitoring module 50 needs to acquire the checkout identification area where the user checks out to determine the checkout module 60 where the user checks out, and then when it is determined that the user leaves the checkout identification area, the checkout information of the corresponding checkout module 60 can be acquired, and if there is checkout information in the period between the first time and the second time where the user stays, it can be determined that the checkout information is the checkout information of the corresponding user. If the checkout information does not exist in the time period, it may be determined that the user has not completed checkout, and if the global monitoring module 50 does not recognize that the user is located in the identification area corresponding to any shelf main body module 10 or the checkout identification area corresponding to the checkout and receipts module 60, it is determined that the user leaves the store without any checkout operation, and at this time, an alarm message needs to be sent to the store owner to prompt the store owner that the user leaves the store without payment.

And S150, if the checkout completion result of the user is completed, determining checkout information of the user through a checkout and cashing module, and determining a matching result of the checkout information and goods taking information corresponding to the user.

If the user has finished checkout, further judging whether the user checks all the goods, and at the moment, matching the checkout information with the goods taking information corresponding to the user to determine whether the checkout information contains all the goods taking information.

In one embodiment, the step S150 may specifically include the following steps:

acquiring all checked-out goods information contained in the check-out information of the user;

matching each checked-out article information with each article taking information corresponding to the user respectively;

if the checked-out goods information corresponds to the goods taking information corresponding to the user one by one, determining that the matching result is successful;

if the goods taking information does not correspond to the checked goods information, determining that the matching result is failed.

In this embodiment, if the respective article taking information corresponds to the respective checked-out article information in the check-out information one by one, it may be determined that the matching result is successful, and at this time, the user leaves the store without checking out; if there are some pieces of the article taking information in the article taking information, which cannot correspond to any piece of the checked-out article information in the individual piece of the checked-out article information, it can be determined that the user leaves without checking out at this time. The checked-out goods information includes the names of checked-out goods, the positions of the shelf main body modules 10 and the number of checked-out identical goods, so that matching with the taking information of each goods is facilitated.

And S160, if the matching result is that the matching fails, generating first alarm information.

If the matching result is that the matching is failed, the first alarm information is used for reminding a store owner that the customer carries unpaid commodity to leave.

And S170, if the matching result is that the matching is successful, generating purchase completion information.

If the matching result is successful, the purchase completion information is used for prompting the store owner that the user completes a normal purchase.

Therefore, based on the anti-theft system and the anti-theft method thereof provided by the embodiment of the invention, the intelligent goods shelf anti-theft system provided by the embodiment of the invention can acquire the situation that goods are taken out or put back by a user in real time by arranging the goods sensing module; through goods shelves monitoring module and global monitoring module, can acquire the appearance characteristic information of the user who is purchasing goods at present and the stay information of user before goods shelves main part module in real time to confirm the goods information of taking of user on goods shelves main part module through stay information, bind goods information and user's ageing identity information, and then can grasp the behavior trend of user in unmanned selling the shop in real time, and then improve the management efficiency of shop owner to the shop sales. Meanwhile, the check-out and cashing module compares the goods taking information and the check-out information of the user, so that the situation that the user does not check out and leaves the unmanned selling shop can be effectively prevented, and further theft prevention and loss prevention are effectively carried out.

While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims (10)

1. An intelligent shelf anti-theft system, comprising:

the goods shelf main body module is provided with a plurality of hanging frames, and each hanging frame is used for hanging a plurality of goods;

the goods sensing modules are connected to the hanging racks in the goods shelf main body module in a one-to-one correspondence manner, and are used for sensing the goods and determining goods taking information of the goods when the corresponding goods are hung into or separated from the goods shelf main body module;

the human body sensing module is arranged at the front end of the goods shelf main body module and is used for sensing a user positioned in front of the goods shelf main body module;

the goods shelf monitoring module is used for further monitoring the hooking condition or the detachment condition of each goods on the goods shelf main body module and acquiring the appearance characteristic information of the user;

The global monitoring module is used for monitoring the goods shelf main body module and the check-out condition of the goods and acquiring the stay information of the user;

the checkout and cashing module is used for acquiring checkout information corresponding to the user;

and the central processing module is in communication connection with the goods induction module, the human body induction module, the goods shelf monitoring module, the global monitoring module and the checkout and cashing module and is used for acquiring the hanging or separating condition of goods on the goods shelf main body module and the checkout condition of the goods.

2. An intelligent shelf anti-theft method applied to a central processing module in an intelligent shelf anti-theft system according to claim 1, characterized in that the method comprises:

responding to the induction signal of the human body induction module, starting the shelf monitoring module to record the video of the shelf main body module and collect the appearance characteristic information of the user positioned in front of the shelf main body module;

acquiring goods taking information of goods taken by the user in the current goods shelf main body module through the goods sensing module; the goods taking information at least comprises a goods shelf main body module corresponding to the goods and induction time when the goods are taken;

Collecting the stay information of the user through a global monitoring module, determining the aging identity information of the user according to the stay information and the appearance characteristic information, and constructing a mapping relation between the aging identity information and the goods taking information; wherein the stay information at least comprises stay time of the user and stay identification area;

determining a checkout completion result of the user through a checkout cashing module according to the aging identity information and the goods taking information;

if the checkout completion result of the user is completed, determining checkout information of the user through a checkout cashing module, and determining a matching result of the checkout information and goods taking information corresponding to the user;

if the matching result is that the matching fails, generating first alarm information;

and if the matching result is that the matching is successful, generating purchase completion information.

3. The intelligent shelf theft prevention method according to claim 2, wherein the acquiring, by the item sensing module, item taking information of the item taken by the user in the current shelf main body module comprises:

determining the goods induction module which is currently induced to take out the goods as a first target goods induction module, and determining the induction time of the first target goods induction module;

Determining name information and price information of the goods according to the goods storage information corresponding to the first target goods sensing module, and updating the goods storage information; the goods storage information at least comprises a goods shelf main body module and stock quantity corresponding to goods;

and combining the updated goods storage information, the updated name information, the updated price information, the updated sensing time and the updated goods main body module corresponding to the first target goods sensing module into the goods taking information.

4. The intelligent shelf theft prevention method according to claim 3, wherein after the collecting the residence information of the user by the global monitoring module, determining the aging identity information of the user according to the residence information and the appearance characteristic information and constructing the mapping relationship between the aging identity information and the goods taking information, further comprises:

if a second target goods sensing module for sensing that goods are put back exists, when only goods taking information corresponding to the current goods shelf main body module where the user is located exists in goods taking information corresponding to the user, acquiring first sensing time for the second target goods sensing module to sense that the goods are put back, and acquiring second sensing time for the first target goods sensing module for sensing that the goods are taken out last time;

If the difference value between the first sensing time and the second sensing time is smaller than a preset time difference value, judging whether the number of the appearance characteristic information acquired by the shelf monitoring module in a time period from the second sensing time to the first sensing time is larger than one;

if the number of the appearance characteristic information is equal to one, determining that the goods which are put back currently are the goods which are taken out last time;

and if the second target goods sensing module is different from the first target goods sensing module which senses that the goods are taken out last time, generating first goods placement error warning information.

5. The intelligent shelf theft prevention method according to claim 3, wherein after the collecting the residence information of the user by the global monitoring module, determining the aging identity information of the user according to the residence information and the appearance characteristic information and constructing the mapping relationship between the aging identity information and the goods taking information, further comprises:

if a second target goods sensing module for sensing goods to be put back exists, when goods taking information corresponding to a plurality of different goods shelf main body modules exists in the goods taking information corresponding to the user, acquiring all the goods taking information of the goods taken by the user in all the goods shelf main body modules; each shelf main body module comprises a current shelf main body module where the user is located and other shelf main body modules where the user is not located;

If the object article taking information corresponding to each first object article sensing module in the current goods shelf main body module exists in the article taking information, generating second article placement error warning information when the second object article sensing module is different from the first object article sensing module corresponding to the object article taking information.

6. The intelligent shelf anti-theft method according to claim 5, wherein if there is a second target article sensing module that senses that an article is put back, when article taking information corresponding to a plurality of different shelf main body modules exists in the article taking information corresponding to the user, acquiring each article taking information of the article taken by the user in each of the shelf main body modules, further comprises:

and if the target goods taking information corresponding to the first target goods sensing module in the current goods shelf main body module does not exist in the goods taking information, generating third goods placement error warning information.

7. The intelligent shelf theft prevention method according to claim 2, wherein collecting the stay information of the user through a global monitoring module, determining the aging identity information of the user according to the stay information and the appearance characteristic information, and constructing the mapping relationship between the aging identity information and the goods taking information, comprises:

Determining a stay identification area where the user is located and stay time of the user in the stay identification area through the global monitoring module, and taking the stay identification area and the stay time as the stay information;

determining the last acquired appearance characteristic information of a target goods shelf main body module corresponding to the stay identification area and a goods shelf monitoring module corresponding to the target goods shelf main body module;

determining the stay information and the last acquired appearance characteristic information as aging identity information of a user;

and mapping each item taking information with the sensing time within the residence time in the target goods shelf main body module to the item taking information corresponding to the user so as to construct a mapping relation between the aging identity information corresponding to the user and the item taking information.

8. The intelligent shelf theft prevention method according to claim 7, wherein after mapping the article taking information corresponding to the target shelf main body module in the residence time to the article taking information corresponding to the user to construct the mapping relationship between the aging identity information corresponding to the user and the article taking information, further comprising:

If the global monitoring module identifies that the user with the aging identity information is located in a stay identification area corresponding to another shelf main body module, determining a first acquisition time of the shelf monitoring module in the other shelf main body module to the appearance characteristic information corresponding to the user;

determining a second acquisition time for the user to leave the identified area of the other shelf body module;

if the appearance characteristic information corresponding to another user does not exist in the time period from the first acquisition time to the second acquisition time, the goods taking information corresponding to the other goods shelf main body module in the time period from the first acquisition time to the second acquisition time and the aging identity information of the user are constructed into a mapping relation.

9. The intelligent shelf theft prevention method according to claim 2, wherein the determining, by a checkout receipt module, a checkout completion result of the user according to the aging identity information and the goods taking information comprises:

determining an identification frame corresponding to the user through the global monitoring module;

if the global monitoring module obtains that the identification frame corresponding to the user is located in a checkout identification area where the checkout receipt module is located, determining first time when the user corresponding to the identification frame enters the checkout identification area and second time when the user corresponding to the identification frame leaves the checkout identification area, and determining the checkout receipt module corresponding to the checkout identification area;

If the checkout information exists in the checkout module corresponding to the checkout identification area in the time period from the first time to the second time, determining that the checkout completion result of the user is completed;

and if the checkout information does not exist in the time period from the first time to the second time by the checkout cashing module corresponding to the checkout identification area, determining that the checkout completion result of the user is incomplete.

10. The intelligent shelf theft prevention method according to claim 2, wherein if the checkout completion result of the user is completed, determining checkout information of the user through a checkout and cashing module, and determining a matching result of the checkout information and goods taking information corresponding to the user, comprises:

acquiring all checked-out goods information contained in the check-out information of the user;

matching each checked-out article information with each article taking information corresponding to the user respectively;

if the checked-out goods information corresponds to the goods taking information corresponding to the user one by one, determining that the matching result is successful;

If the goods taking information does not correspond to the checked goods information, determining that the matching result is failed.