A shelf management method, device, computer equipment and computer program product
By setting up detectors and image sensors on the shelves to automatically identify and manage goods, the problems of inefficiency and error-prone management of shelves are solved, and more efficient and accurate cargo management is achieved.
Patent Information
- Application Number
- CN202411557596.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-01
- Publication Date
- 2025-04-01
AI Technical Summary
In the prior art, there are problems of error-prone and inefficient management of goods on shelves manually.
When the detector detects moving objects on the shelf, the image sensor is triggered to collect images, determine the target cargo and target person, and manage them based on their data, including updates of inventory information.
Real-time monitoring of shelf goods is achieved, the efficiency and accuracy of goods management is improved, and manual errors and labor intensity are reduced.
Smart Images
Figure CN119741466A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of Internet of Things, and in particular, relates to a shelf management method, device, computer equipment and computer program product. Background Art
[0002] For managers of large supermarkets, shelf management is a crucial part of their daily operations. In an environment with large customer flow and fast circulation of goods, effective shelf management can not only ensure the timely supply of goods and meet customer needs, but also avoid inventory backlogs and reduce unnecessary cost losses. However, in the existing shelf management technology, manual inventory and monitoring of goods have technical problems such as low efficiency and easy errors. Summary of the invention
[0003] The embodiments of the present application provide a shelf management method, apparatus, computer equipment and computer program product, which can solve the technical problems in the prior art of manually managing goods on shelves, which are prone to errors and inefficient.
[0004] In a first aspect, the present application provides a shelf management method, the method comprising:
[0005] When the detector detects that there is a moving object on the shelf, the image sensor is triggered to collect images in the direction of the moving object to obtain image collection results;
[0006] Determining target goods and target persons from the image acquisition results;
[0007] The relevant data of the target goods are managed according to the target goods and the target person, wherein the relevant data of the target goods at least includes the inventory information of the target goods.
[0008] In particular, the method further comprises:
[0009] When the identity type of the target person is a customer type, receiving settlement information of the target person transmitted by the first terminal;
[0010] Determining whether the target goods have been settled according to the settlement information;
[0011] When the settlement of the target goods is completed, the inventory of the target goods is updated.
[0012] In particular, after determining whether the target goods have been settled according to the settlement information, the method further includes:
[0013] In the case that the target goods have not been settled, a first prompt message is sent to the second terminal, the first prompt message indicates that the target goods have not been settled, and the first prompt message includes appearance feature information of the target person.
[0014] In particular, after determining the target goods and the target person from the image acquisition results, the method further includes:
[0015] Establishing a key-value pair relationship between the target goods and the target person, and storing the key-value pair relationship in a cache database;
[0016] Generate shopping cart information of the target person based on the key-value pair relationship, and send the shopping cart information to a user terminal of the target person;
[0017] When the settlement of the target goods is completed, the step of updating the inventory of the target goods comprises:
[0018] When the settlement of the target goods is completed, the key-value pair relationship is removed from the cache database, and the inventory of the target goods is updated.
[0019] In particular, the method further comprises:
[0020] Performing face recognition on the target person to obtain the identity type of the target person;
[0021] In the case that the target person is a first type of user, historical shopping information of the target person is obtained, and commodity recommendation information of the target person is generated based on the historical shopping information.
[0022] When the target person is a second type of user, a second prompt message is sent to the second terminal.
[0023] In particular, the method further comprises:
[0024] Controlling the shelf management device to move on the guide rail of the shelf, and calling the image sensor to photograph each cargo area on the shelf to obtain image photographing results of each cargo area;
[0025] Managing the cargo area according to the image shooting results to monitor the cargo status of the shelf in real time;
[0026] Wherein, the image sensor is arranged on the shelf management device, and the shelf management device is arranged on the guide rail.
[0027] In a second aspect, the present application also provides a shelf management device, the device comprising an image sensor, a detector, an image processing unit and a control unit;
[0028] The detector is used to detect moving objects on the shelf;
[0029] The image sensor is used to collect images in the direction of the moving object to obtain image collection results;
[0030] The image processing unit is used to determine the target goods and the target person from the image acquisition result;
[0031] The control unit is used to manage the relevant data of the target goods according to the target goods and the target person, wherein the relevant data of the target goods at least includes the inventory information of the target goods.
[0032] In a third aspect, the present application further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.
[0033] In a fourth aspect, the present application further provides a computer program product, comprising a computer program, wherein when the computer program is run, the method of the first aspect is executed.
[0034] The beneficial effects of the present application are that it can monitor the status of goods on the shelves in real time. When a moving object is detected on the shelf, the image sensor is triggered to capture images in the direction of the moving object. By analyzing the image capture results to manage the relevant data of the goods, the efficiency and accuracy of goods management can be greatly improved, and manual errors and labor intensity can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0036] Figure 1 It is a flowchart provided by the first embodiment of the shelf management method of the present application;
[0037] Figure 2 It is a schematic diagram of the structure of an embodiment of the shelf management device of the present application in a specific implementation;
[0038] Figure 3 This is another flowchart provided by the first embodiment of the shelf management method of the present application;
[0039] Figure 4It is a flow chart of the second embodiment of the shelf management method of the present application;
[0040] Figure 5 It is a flow chart of the third embodiment of the shelf management method of the present application;
[0041] Figure 6 A schematic block diagram of a shelf management device provided in an embodiment of the present application;
[0042] Figure 7 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0044] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "multiple" is two or more.
[0045] For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0046] Embodiment 1
[0047] like Figure 1 As shown, the shelf of the embodiment of the present application can be equipped with a shelf management device, and the shelf management device can be set on the guide rail of the shelf (refer to Figure 2 ), the shelf of the present application may be a shelf for placing goods in a supermarket, or an unmanned vending machine displayed in other public places such as warehouses, libraries and shopping malls; the execution subject of the shelf management method may be the shelf management device itself, or other computer equipment, and the shelf management method includes steps S10-S30:
[0048] Step S10: When the detector detects that there is a moving object on the shelf, the image sensor is triggered to collect images in the direction of the moving object to obtain image collection results.
[0049] It should be noted that the embodiment of the present application takes the shelf management device as an example of the execution subject of the shelf management method; the shelf management device of the embodiment of the present application includes an image sensor, a detector, an image processing unit and a control unit.
[0050] In a specific implementation, the shelf management device of the embodiment of the present application can be an electronic device integrating multiple functions, which can integrate at least a camera, a detector, a pyroelectric infrared sensor, a power supply unit, a processor, a memory and other functional components to improve the efficiency and accuracy of shelf management.
[0051] In the embodiment of the present application, a pyroelectric infrared sensor (Passive Infra-Rey, PIR) can be used as the detector, which is mainly used to detect the movement of heat sources on the shelves. In the embodiment of the present application, the detector can be used to detect whether the goods on the shelves are taken away by people (such as customers and shelf managers). When the movement of heat sources on the shelves is detected, the image sensor is triggered to collect images in the direction of the heat sources.
[0052] The camera (i.e., image sensor) is a core component of the shelf management device and can be used to capture images or videos of the shelf and its surrounding environment. When the detector detects the presence of a moving object on the shelf, the processor can control the camera to capture images in the direction of the moving object to obtain image capture results.
[0053] Step S20, determining the target goods and the target person from the image acquisition results.
[0054] Specifically, the processor of the shelf management device integrates an image processing unit and a control unit. The image processing unit can call an image recognition algorithm to identify and process the information of the target goods moving on the shelf, and then obtain specific information such as the category and price of the target goods; at the same time, the image processing unit can call an image recognition algorithm to identify the person who makes the target goods move, and determine the target person who takes the target goods from the shelf.
[0055] In addition, the image processing unit can also call a face recognition algorithm to perform face recognition on the target person, and then determine the identity type of the target person, and the identity type can at least include a customer type and a shelf manager type.
[0056] In some other embodiments, the shelf management device is also equipped with an indicator light, which is used to provide visual indications, such as shelf status, warnings, operation prompts, etc., and can also be linked with cameras and detectors. For example, when the detector and image processing unit cooperate to detect an abnormality, the indicator light will light up red to attract attention. The shelf management device can also be equipped with a speaker, which can be used to provide sound prompts or warnings to convey information to relevant personnel, and can be linked with the indicator light and detector to achieve sound and light alarms.
[0057] Step S30: managing relevant data of the target goods according to the target goods and the target customers, wherein the relevant data of the target goods at least includes inventory information of the target goods.
[0058] In a specific implementation, the control unit of the shelf management device is used to receive signals from functional components such as image sensors and detectors, and the control unit is responsible for the management of relevant data of the goods on the entire shelf, such as data processing, storage, transmission, and communication with external terminal devices; the relevant data of the target goods may at least include inventory information of the goods, such as the increase or decrease of inventory, whether it is out of stock, or whether there are other categories of goods that are mistakenly placed in the goods area where the target goods are located.
[0059] The beneficial effects of the embodiments of the present application are that the situation of goods on the shelves can be monitored in real time. When the detector detects the presence of a moving object on the shelf, the image sensor is triggered to capture images in the direction of the moving object. The relevant data of the goods is managed by analyzing the image capture results, which can greatly improve the efficiency and accuracy of goods management and reduce manual errors and labor intensity.
[0060] Further, in some embodiments, taking the identity type of the target person as a customer type as an example, step S30 may further include steps S31-S32:
[0061] Step S31, receiving the settlement information of the target person transmitted by the first terminal.
[0062] It is understandable that the first terminal can be an external terminal device that is communicatively connected to the shelf management device. Taking a supermarket as an example, the first terminal can be a cashier terminal device used by the supermarket cashier when working at the cashier counter; after the customer (target person) takes the goods from different shelves, he or she usually takes the goods to the cashier counter for settlement and payment.
[0063] Step S32: judging whether the settlement of the target goods has been completed according to the settlement information, the control unit of the shelf management device can judge and manage the inventory of the target goods according to the settlement information fed back by the first terminal:
[0064] When the settlement of the target goods is completed, step S331 "update the inventory of the target goods" is executed. It can be understood that after the target customer (target person) completes the checkout of the target goods at the checkout counter, it is equivalent to the supermarket selling one piece of the target goods, and the shelf management device updates the inventory of the product in the database; the database can be located in the local memory of the shelf management device, and the database can also be deployed on the background server. If the database is deployed on the background server, the control unit will initiate a database access request to the background server to obtain the inventory of the product in the database to update the inventory of the product in the database (that is, when one piece of the target goods is sold, the inventory of the target goods is reduced by one), and synchronize the inventory update result to the database.
[0065] In the case where the target goods have not been settled, step S332 "sending a first prompt message to the second terminal" is executed. It is understandable that if the customer takes the goods from the shelf but does not complete the checkout of the goods at the checkout counter, it means that the customer did not pay for the goods in the end. The following situations may exist: the customer does not want to buy the goods after taking them from the shelf, and does not return the target goods to the shelf, but puts them in other corners of the supermarket; or the customer may put the goods in his or her clothes pocket and want to take them out of the supermarket. The above-mentioned behavior of the customer will bring a lot of inconvenience to the management staff and ultimately cause economic losses to the supermarket. In this regard, when the shelf management device determines that the target goods have not been settled, it will send a first prompt message to the second terminal, and the second terminal is a mobile terminal (such as a smart phone) carried by the shelf manager; wherein the second terminal has the function of receiving information sent to it by the shelf management device in real time; and the first prompt message indicates that the target goods have been taken away but not checked out, and the first prompt message may also include the appearance feature information of the customer (target person). After receiving the first prompt message transmitted by the shelf management device, the manager can obtain the news that the target goods have not been checked out in the first time. At the same time, the manager can find the customer in the supermarket through the customer's appearance feature information, and ask the customer where the target goods taken from the shelf but not checked out are left, which can reduce the economic loss of the supermarket.
[0066] Embodiment 2
[0067] Based on the first embodiment of the above shelf management method, a related method of the second embodiment is proposed. In this embodiment, reference is made to Figure 4 The shelf management method further includes steps S11-S13:
[0068] Step S11, performing face recognition on the target person to obtain the identity type of the target person;
[0069] In an embodiment of the present application, the identity types may include at least a first type of user (member customer), a second type of user (blacklist customer) and a third type of user (manager); both the first type of user and the second type of user belong to the customer type, and the third type of user belongs to the supermarket administrator type. In this embodiment, the first type of user is a member customer, the second type of user is a "blacklist customer", and the third type of user is a supermarket manager; the information of these three different identity type users will be pre-stored in the database to facilitate the subsequent shelf management device to call the face recognition algorithm to identify the customer identity and the supermarket manager identity.
[0070] If a customer wants to become a member of a supermarket, he or she can register as a member customer by using a smart phone. During the registration process, the customer can fill in the basic personal data information on the registration declaration page, and then the basic data information of the customer is written into the database, and the identity type of the customer is set to the first type (member customer), and a registration identifier is assigned to the customer, and the assigned registration identifier is bound and associated with the basic data information of the user, and the basic data information at least includes the personal avatar information picture.
[0071] After obtaining the head portrait information picture uploaded by the customer, the backend server will perform denoising and normalization on the collected facial image to improve the image quality. Then, a specific algorithm (such as convolutional neural network, etc.) is used to extract a representative standard feature vector from the facial image; the standard feature vector of the target person will then be stored in the database.
[0072] In the specific implementation process of shelf management device for shelf monitoring, the image processing unit of the shelf management device can call the face recognition algorithm to make the target goods produce the movement of the person for face recognition, and the specific recognition process includes: after taking the facial image of the person, extracting its feature vector; comparing the newly extracted feature vector to be tested with the existing standard feature vector in the database, and specifically using distance measurement and other methods to judge the similarity. If an existing standard feature vector with a high degree of similarity to the feature vector to be tested is found, it means that the person has a data record in the database, and then the identity type of the person can be obtained; if an existing standard feature vector that is sufficiently similar to the feature vector to be tested is not found, it is determined that the person has no information stored in the database.
[0073] Step S12, when the target person is a first type of user, obtain the target person's historical shopping information, and generate product recommendation information for the target person based on the historical shopping information.
[0074] It is understandable that if the identity type of User A is a first type of user (member customer), after A successfully registers as a member customer of the mall, the bill for each purchase of goods in the supermarket will be retained in the database as a historical shopping record; and when the shelf management device calls the face recognition algorithm to identify that the identity type of the target person (User A) is a first type of user (member customer), it will obtain User A's historical shopping information, and determine User A's needs and preferences based on the historical shopping information. The shelf management device generates product recommendation information for User A based on User A's historical shopping information, thereby providing more personalized services and recommendations for the target person (User A).
[0075] In a specific implementation, the shelf management device can push the generated commodity recommendation information to the user terminal device of the member customer or the terminal display screen inside the convenience store for display, so that the member customer can view the recommendation information;
[0076] For example, if user A registers membership information using the supermarket mini-program application that comes with instant messaging software (such as WeChat and QQ), the shelf management device can push the generated product recommendation information to the supermarket mini-program application that comes with the instant messaging software for user A to check.
[0077] Alternatively, if user A happens to have a terminal device with a display function at the location of the shopping mall, the shelf management device can push the generated product recommendation information to the terminal display screen very close to user A so that user A can check it.
[0078] The embodiments of the present application can help merchants better understand customer needs and preferences, thereby providing more personalized services and recommendations.
[0079] Step S13: When the target person is a second type of user, a second prompt message is sent to the second terminal.
[0080] As another case, when the shelf management device calls the face recognition algorithm to identify the target person's identity type as a second type of user (blacklisted customer), it will send a second prompt message to the supermarket manager's second terminal. The second prompt message is an early warning message used to remind the supermarket manager that there may be hidden dangers.
[0081] Specifically, if there have been incidents of goods being stolen or being carried away privately by customers in a supermarket, the supermarket's cameras or other monitoring equipment will record the facial profile information of these "illegal users"; or if the situation in step S32 of the above-mentioned embodiment 1 has occurred, that is, the customer has not checked out and paid for the goods or returned the goods to the shelf after taking them away, but has placed them randomly, the customer's identity information will also be set as a second-type user (it should be noted that in the database system of this embodiment, a user can be configured as two identity types at the same time, that is, the user identity type can include both a second-type user and a first-type user). If the shelf management device determines that a customer with an identity type of the second type has taken the goods from the shelf, the shelf management device will immediately send a second prompt message to the second terminal carried by the supermarket manager to prompt the supermarket manager to pay attention to this second-type user to prevent the goods from being abandoned by the customer in other corners of the supermarket or being carried out of the supermarket, which can effectively assist the supermarket manager in making effective security measures.
[0082] In other embodiments, the second terminal may be a mobile terminal used by a supermarket manager that has a corresponding relationship with the number of the shelf in the database, and the supermarket manager with the second terminal is responsible for maintaining the goods on the shelf. After the shelf management device of the shelf identifies that an "illegal user" has taken away the goods on the shelf, the shelf management device sends a second prompt message to the second terminal of the supermarket manager of the shelf, so that the supermarket manager can better manage and maintain the goods on the shelf for which he is responsible.
[0083] In addition, in some other embodiments, after the step S20 of determining the target goods and the target person from the image acquisition results, a function of creating a shopping cart for the customer may be further included, and the specific method includes:
[0084] Step A1, establishing a key-value pair relationship between the target goods and the target person, and storing the key-value pair relationship in a cache database;
[0085] Step A2, generating the shopping cart information of the target person based on the key-value pair relationship, and sending the shopping cart information to the user terminal of the target person;
[0086] Step A3, when the settlement of the target goods is completed, the key-value pair relationship is removed from the cache database, and the inventory of the target goods is updated.
[0087] It is understandable that after determining the target person who takes the target goods from the shelf, the shelf management device will create a "virtual shopping cart" for the target person, and send this "virtual shopping cart" to the application of the user terminal device of the target person (such as the supermarket applet that comes with the instant messaging software mentioned in the above content), and the "virtual shopping cart" can be stored through a cache database (such as Redis); that is, after the customer (target person) takes a product from the shelf, the shelf management device on the shelf where the product is taken will transmit the taken target product to the cache database (that is, the "virtual shopping cart"), and the customer can open the user terminal to view which goods and commodities he has selected in the supermarket, so that it is convenient for the customer to trace his pickup record in the supermarket; and once the customer goes to the checkout counter to settle the taken goods and commodities, the system will remove the key-value pair relationship from the cache database (that is, "empty the shopping cart"), and update the remaining inventory of the target goods that the customer has checked out in the supermarket; this not only facilitates the customer's shopping experience, but also ensures the correctness of the shelf inventory data management.
[0088] Embodiment 3
[0089] Based on the above-mentioned embodiment 2, embodiment 3 is proposed. The shelf management device of the embodiment of the present application is arranged on the guide rail of the shelf, and the shelf management device has a self-moving function. The shelf management device can move along the guide rail at preset time intervals (for example, every two hours), and during the movement, the image sensor is called to shoot and scan the positions of each cargo area on the shelf, thereby obtaining the image scanning results of each cargo area, and then the cargo status of the shelf can be monitored in real time; in the specific implementation, refer to Figure 5 The shelf management device implements real-time monitoring of the shelves by executing the following steps:
[0090] Step S41, at every preset time interval, the control unit of the shelf management device controls the shelf management device to move on the guide rail of the shelf, and calls the image sensor to shoot each cargo area on the shelf to obtain image shooting results of each cargo area;
[0091] Step S42: managing the cargo area according to the image shooting result.
[0092] Specifically, each cargo area on the shelf will be affixed with a corresponding cargo label. When the shelf management device moves to the corresponding position of each cargo area, it uses the image sensor to capture images of each commodity placed in the cargo area, and calls the cargo recognition algorithm to identify the cargo information of each commodity placed in the cargo area. The cargo information may include the name, specification, and price of the cargo.
[0093] In the specific implementation, the shelf manager of the supermarket will input the cargo information of different types of goods into the database in advance, including uploading the external shape and packaging image information of the goods; after obtaining the external shape and packaging image information uploaded by the shelf manager, the backend server will pre-process the external shape and packaging image information, including cropping, scaling, denoising, contrast enhancement and other operations, so that the image is more suitable for subsequent processing. Then, image processing algorithms or algorithms based on deep learning can be used to extract the characteristics of the goods, such as shape, color, texture and other features. Next, the extracted features can be further processed and modeled, such as constructing feature vectors or feature maps; finally, the built model can be trained using a machine learning training model or a deep learning training model, such as using a large number of known goods images and labels for training, so that the model learns the characteristic patterns of different goods, and finally obtains the standard model of goods and the standard feature data of goods, and the standard model of goods and the standard feature data of goods will be stored in the database.
[0094] In the process of the shelf management device moving along the guide rail at preset time intervals, the shelf management device calls the goods recognition algorithm to recognize the goods information of each target goods placed in the target goods area. Specifically, the recognition process includes: if there are goods in the target goods area to which the shelf management device moves, sub-step 421 is executed. When the image sensor captures the external shape and packaging image information of the target goods, the target goods to be tested features are extracted, and the goods standard model or goods standard feature data corresponding to the target goods area in the database is determined, and the target goods to be tested features are matched with the goods standard model or goods standard feature data trained in the database. If the match is successful, it means that all goods currently placed in the target goods area meet the specifications, that is, there is no situation where other goods are misplaced in the goods area. However, if the match is unsuccessful, it means that there are other categories of goods in the goods currently placed in the target goods area (for example, a customer may take away a certain product and then do not want to buy it, and then misplace it in a goods area that does not correspond to the goods). At this time, a third prompt information needs to be sent to the second terminal of the supermarket manager. The third prompt information indicates that there are misplaced goods on the shelf, so as to prompt the supermarket manager to reclassify the misplaced goods.
[0095] Of course, in the process of the shelf management device moving along the guide rail at preset time intervals, if the image sensor captures that there are no goods in the target cargo area, the processing unit, after determining the cargo label on the target cargo area, executes step S422 to send a fourth prompt message to the second terminal of the supermarket manager. The fourth prompt message indicates that the target cargo area on the shelf is out of stock, so as to prompt the supermarket manager to replenish the goods corresponding to the cargo label.
[0096] Embodiment 4
[0097] Combination of the above-mentioned embodiment 1 with embodiment 2 and embodiment 3 Figures 1 to 5 The unmanned vehicle driving control method of the embodiment of the present application is described in detail. Figure 6 to Figure 7 The shelf management device provided in the embodiment of the present application is described in detail.
[0098] Figure 6 This is a schematic block diagram of a shelf management device 600 provided in an embodiment of the present application. The shelf management device 600 includes:
[0099] The detector 61 is used to detect moving objects on the shelf;
[0100] The image sensor 62 is used to collect images in the direction of the moving object to obtain image collection results;
[0101] The image processing unit 63 is used to determine the target goods and the target person from the image acquisition result;
[0102] The control unit 64 is used to manage the relevant data of the target goods according to the target goods and the target person, wherein the relevant data of the target goods at least includes the inventory information of the target goods.
[0103] Specifically, the detector 61 can use a pyroelectric infrared sensor, which is mainly used to detect the movement of the heat source on the shelf, and then detect whether the goods on the shelf are taken away by people (such as customers and shelf managers). When the movement of the heat source on the shelf is detected, the image sensor 62 is triggered to collect images in the direction of the heat source. The image sensor 62 can be connected to the image processing unit 63 and the control unit 64 in a wireless or wired manner.
[0104] The image processing unit 63 and the control unit 64 may be integrated circuits built into a processor chip of the shelf management device 600 .
[0105] It should be noted that Figure 6 The schematic structural diagram of the shelf management device 600 provided in the embodiment of the present application is shown in FIG. Figure 6 More components are added or expanded on the basis of the shelf management device 600 shown, for example, the shelf management device 600 may also include components such as a power supply unit, an indicator light, and a speaker. The power supply unit can provide power support for the shelf management device 600; the speaker is used to issue an alarm or voice prompt; the indicator light: is used to indicate the working status of the image sensor 62, such as power on, shooting, face recognition, etc.
[0106] In a specific implementation, each component in the shelf management device 600 can be connected to an internal processor chip via cables or wirelessly to form a complete system.
[0107] The shelf management device 600 of the embodiment of the present application can be arranged on the guide rail of the shelf (such as Figure 2 As shown), the control unit 64 can control the shelf management device 600 to move on the guide rail to realize the function of automatically monitoring and managing the goods on the shelf, so as to improve the efficiency and accuracy of shelf management.
[0108] In addition, the shelf management device 600 may also have a built-in network communication module, which can be connected to the network via wired or wireless means to achieve remote monitoring and management. For example, it can communicate remotely with the customer terminal equipment of the aforementioned embodiment, the terminal display screen inside the public place, the second terminal of the supermarket manager, and the first terminal of the checkout counter through the wired network module.
[0109] Embodiment 5
[0110] Figure 7 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be the above Figure 6 The shelf management device shown can of course also be other devices capable of executing Figure 1 The terminal device of the shelf management method shown, for example, in some other embodiments, the shelf of the supermarket includes a camera and a detector; the detector is linked to the camera: when the detector detects the presence of a moving object on the shelf, it triggers the camera to capture an image in the direction of the moving object, and then the camera transmits the image capture result to the processor of the computer device of this embodiment to execute subsequent method steps such as "determining the target goods and target customers from the image capture results; managing the relevant data of the target goods according to the target goods and the target customers".
[0111] like Figure 7 As shown, the computer device 700 includes a processor 701, a memory 702, a communication interface 703 and a bus 704. The processor 701, the memory 702 and the communication interface 703 communicate via the bus 704, or other means such as wireless transmission. The memory 702 is used to store instructions, and the processor 701 is used to execute the instructions stored in the memory 702. The memory 702 stores program code 6021, and the processor 701 can call the computer program 7021 stored in the memory 702 to execute Figure 1 The shelf management method shown.
[0112] It should be understood that in the embodiment of the present application, the processor 701 may be a CPU, and the processor 701 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.
[0113] The memory 702 may include a read-only memory and a random access memory, and provide instructions and data to the processor 701. The memory 702 may also include a non-volatile random access memory. The memory 702 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus random access memory (DR RAM).
[0114] In addition to the data bus, the bus 704 may also include a power bus, a control bus, and a status signal bus. Figure 7 Various buses are labeled as bus 704.
[0115] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid state drive (SSD).
[0116] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A shelf management method, characterized in that: The method comprises: When the detector detects that there is a moving object on the shelf, the image sensor is triggered to collect images in the direction of the moving object to obtain image collection results; Determining target goods and target persons from the image acquisition results; The relevant data of the target goods are managed according to the target goods and the target person, wherein the relevant data of the target goods at least includes the inventory information of the target goods.
2. The method according to claim 1, characterized in that The method further comprises: When the identity type of the target person is a customer type, receiving settlement information of the target person transmitted by the first terminal; Determining whether the target goods have been settled according to the settlement information; When the settlement of the target goods is completed, the inventory of the target goods is updated.
3. The method according to claim 2, characterized in that After determining whether the target goods have been settled according to the settlement information, the method further includes: In the case that the target goods have not been settled, a first prompt message is sent to the second terminal, the first prompt message indicates that the target goods have not been settled, and the first prompt message includes appearance feature information of the target person.
4. The method according to claim 2, characterized in that After determining the target goods and the target person from the image acquisition results, the method further includes: Establishing a key-value pair relationship between the target goods and the target person, and storing the key-value pair relationship in a cache database; Generate shopping cart information of the target person based on the key-value pair relationship, and send the shopping cart information to a user terminal of the target person; When the settlement of the target goods is completed, the step of updating the inventory of the target goods comprises: When the settlement of the target goods is completed, the key-value pair relationship is removed from the cache database, and the inventory of the target goods is updated.
5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Performing face recognition on the target person to obtain the identity type of the target person; When the target person is a user of the first type, acquiring historical shopping information of the target person, and generating commodity recommendation information of the target person based on the historical shopping information; When the target person is a second type of user, a second prompt message is sent to the second terminal.
6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Controlling the shelf management device to move on the guide rail of the shelf, and calling the image sensor to photograph each cargo area on the shelf to obtain image photographing results of each cargo area; Managing the cargo area according to the image shooting results to monitor the cargo status of the shelf in real time; Wherein, the image sensor is arranged on the shelf management device, and the shelf management device is arranged on the guide rail.
7. The method according to claim 6, characterized in that The method further comprises: When the image sensor captures the external shape and packaging image information of the target goods, extracting the features to be measured of the target goods; The features to be tested of the target goods are matched with the goods standard model or goods standard feature data that have been trained in the database. If the match is unsuccessful, a third prompt message is sent to the second terminal, and the third prompt message indicates that there are goods and commodities that are placed in a disorderly manner on the shelf.
8. A shelf management device, characterized in that: The device comprises an image sensor, a detector, an image processing unit and a control unit; The detector is used to detect moving objects on the shelf; The image sensor is used to collect images in the direction of the moving object to obtain image collection results; The image processing unit is used to determine the target goods and the target person from the image acquisition result; The control unit is used to manage the relevant data of the target goods according to the target goods and the target person, wherein the relevant data of the target goods at least includes the inventory information of the target goods.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer program product, characterized in that The invention comprises a computer program, which, when executed, enables the method according to any one of claims 1 to 7 to be performed.