Mobile terminal-based system and method for shopping by scanning codes in stores

Abstract

This application provides a mobile-based in-store QR code shopping system and method. By redirecting the existing QR codes or barcodes on products, the system uses a local area network to direct them to a redirection server, completing product identification. The redirection server then sends the product information back to the mobile client, allowing customers to complete the purchase through the mobile client. This saves customers time at checkout, improves the shopping experience, and avoids the labor of re-applying QR codes to all products, as well as the repeated application of QR codes to similar products. This significantly saves economic and labor costs, reduces paper usage, and is beneficial to environmental protection.

Description

Technical Field

[0001] This application relates to the field of e-shopping technology, and in particular to a mobile-based in-store QR code shopping system and method. Background Technology

[0002] The statements in this section are merely background information related to this application and do not necessarily constitute prior art.

[0003] In large shopping malls, the surge in foot traffic during evening rush hours and holidays overwhelms the mall's staffing capacity, forcing customers to find their desired items themselves, thus increasing shopping time. Furthermore, the large quantity and variety of goods purchased by customers in large malls lead to lengthy checkout times, and the limited capacity of manual checkout often results in queues, further increasing shopping time and diminishing the shopping experience.

[0004] In some shopping malls, automatic checkout machines have been put into use, but customers still need to pay for each item one by one. In situations with a large flow of people, they still need to queue and wait, which limits the effectiveness of the products. Summary of the Invention

[0005] To address the aforementioned issues, this application proposes a mobile-based in-store QR code shopping system and method.

[0006] This application provides a mobile-based in-store QR code shopping method, including: redirecting the original QR code and / or barcode of the product based on the mall's local area network, and the redirection server receiving the product identification information sent by the mobile client after connecting to the mall's local area network and scanning the code; The redirection server searches for product information based on product identification information and sends it back to the mobile client. The mobile client connects to the shopping backend, and the user operates the mobile client to perform shopping operations. The redirection server receives product identification information and navigation requests sent by the mobile client via QR code scanning, confirms the product location based on the product location fingerprint database, and determines whether the product has been moved. If so, send a nearby QR code scanning request to the mobile client, receive feedback information from the mobile client, redirect the server to use the feedback information to perform repeated positioning, and send the repeated positioning result and the location fingerprint information of the target product in the navigation request to the mobile client. If not, the location fingerprint information of the scanned product and the target product in the navigation request will be sent to the mobile client; The mobile client navigates the route based on a pre-stored map and received location fingerprint information.

[0007] Preferably, when the mobile client scans a QR code and / or barcode, it connects to the mall's local area network by default. When the mobile client receives the product information or location fingerprint information, it disconnects from the mall's local area network by default.

[0008] Preferably, the mobile client can enable continuous scanning mode, which is connected to the mall's local area network by default. When no scanning operation is performed after a preset time period T, the mobile client disconnects from the mall's local area network.

[0009] Preferably, when the mobile client receives product information, it adds the corresponding product to the shopping cart by default.

[0010] Preferably, the specific method for the redirection server to determine whether a product has been moved includes: Method A: S101: The redirection server controls the AP and / or CPE modules in the mall's local area network to send fixed-frequency verification pulses to the mobile client, calculates the number of verification pulses received by the mobile client within a preset time period T_1, sorts them from least to most, and selects the first N pulse sources as the positioning signal transmission points, where N is determined by the positioning algorithm. S102: Calculate the location of the mobile client according to the positioning algorithm. If the error between the calculated location and the location of the corresponding product in the product location fingerprint database is less than the preset threshold value P, it is determined that the product has not been moved; otherwise, it is determined that the product has been moved. Method B: S201: The redirection server obtains customer ID information from the mobile client, retrieves the customer recognition image from the preset customer image database based on the customer ID information, searches for the product location fingerprint based on the product recognition information, and retrieves the camera closest to the product location fingerprint from the mall monitoring system to identify and search for the customer. If the customer is identified within the preset area Zone of the corresponding product location fingerprint, it is determined that the product has not been moved; otherwise, it is determined that the product has been moved.

[0011] Preferably, the specific method for the redirection server to perform repeated location includes: Method D: The user scans the QR code or barcode of the product around the original product using a mobile client, uploads the product identification information, and the redirection server searches the product location fingerprint database based on the product identification information, and uses the corresponding location fingerprint as the duplicate location result; Method E: The user takes an image of the surrounding products of the product being scanned via a mobile client and uploads it; The redirection server segments the image, separating the image of individual products from the QR code or barcode image; The segmented product images are recognized and the QR codes or barcodes are parsed in parallel to obtain the product recognition information of surrounding products. The product location fingerprint database is searched to obtain the location fingerprints of surrounding products. Outliers in the location fingerprints are removed, and one of the remaining location fingerprints is randomly selected as the duplicate localization result.

[0012] Preferably, the process also includes factory verification of the purchased goods, the specific method of which is as follows: The mobile client generates a comprehensive verification QR code for the purchased goods, and the factory verification device scans the comprehensive verification QR code to obtain a list of goods to be verified; The factory inspection device acquires top images, side images, and overall weight of the purchased goods; Image recognition and visual positioning are performed on the top image and side image of the product, respectively. A first recognition list is obtained based on the top image, and several second recognition lists are obtained based on the side image. The elements of the first recognition list and the second recognition list include the confirmed product and the similar product sublist. Based on the visual positioning results of each product, the confirmed products in the second identification list are used to confirm the similar product sublist elements with the same position in the first identification list; The elements in the first identification list are identified. If there is no similar product sublist in the first identification list, the product list to be verified is matched and verified with the first identification list. If there is at least one similar product sublist in the first identification list, substitute the elements of each similar product sublist into the first identification list to generate several third identification lists. Calculate the weight of the products in each third identification list. Use the third identification list whose weight difference from the total weight of the purchased products is less than a preset value as the verification list. If any verification list matches the list of products to be verified, the verification is successful.

[0013] This application also provides a mobile-based in-store QR code shopping system, including: a mobile client, a local area network subsystem, a redirection server, and a shopping backend server; The mobile client is set up on a mobile terminal and includes a shopping interface, a QR code scanning module, and a route navigation module. The local area network subsystem includes a local area network constructed from several AP modules and CPE modules installed within the shopping mall; The redirection server connects to the mobile client via a local area network subsystem and has a product location fingerprint database. The shopping backend server is equipped with a product sales platform that connects to the mobile client's broadband internet to complete the purchase and settlement of goods.

[0014] Preferably, the redirection server further includes a first image recognition module, a customer portrait database, and a product image database; It also includes a monitoring system, which comprises several surveillance cameras installed within the shopping mall.

[0015] Preferably, it also includes a factory verification device; The factory verification device includes a base and a transparent frame embedded in the top of the base. An electronic scale is installed at the bottom of the transparent frame. A first acquisition camera is installed above the top of the base. A second acquisition camera is installed inside the base relative to the four sides of the transparent frame. A QR code scanner and a display are installed on the top of the base. A controller electrically connected to the first acquisition camera, the second acquisition camera, the QR code scanner, the display, and the electronic scale is embedded inside the base. A second image recognition module is installed in the controller.

[0016] Compared with the prior art, the beneficial effects of this application are as follows: This application redirects the existing QR codes or barcodes on products, using a local area network to direct them to a redirection server for product identification. The redirection server then sends the product information back to the mobile client, allowing customers to complete the purchase through the mobile client. This saves customers time at checkout, improves the shopping experience, and avoids the labor of re-applying QR codes to all products, as well as the repeated application of QR codes to similar products. This significantly saves economic and labor costs, reduces paper usage, and is beneficial to environmental protection.

[0017] This application establishes a product location fingerprint database, which, in conjunction with a mobile client scanning a QR code or barcode to identify the product, accurately determines the location of the mobile client. Combined with a map within the mobile client, it enables precise navigation to the target product, saving customers time in searching for goods and thus reducing overall shopping time and improving the shopping experience.

[0018] This application uses a product displacement judgment algorithm to correct the product position fingerprint, preventing the product position fingerprint from becoming invalid due to customer movement of the product, which would lead to inaccurate or failed navigation, thus improving the effectiveness of the product navigation in this application.

[0019] In the product displacement judgment algorithm of this application, the customer's image is recognized by the first image recognition module and the customer image database set in the redirection server. The whole process is in the local area network, which avoids the exposure of the customer's image privacy to the broadband Internet and reduces the risk of privacy leakage. Attached Figure Description

[0020] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an undue limitation of this application.

[0021] Figure 1 This is a schematic diagram of the method flow of this application. Figure 2 This is a schematic diagram of the system composition of this application. Figure 3 This is a schematic diagram of the factory verification device of this application.

[0022] In the picture: 1. Base, 2. Transparent frame, 3. First acquisition camera, 4. Second acquisition camera, 5. Electronic scale. Detailed Implementation

[0023] The present application will be further described below with reference to the accompanying drawings and embodiments.

[0024] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this disclosure. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms “comprising” and / or “including” are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0025] In this disclosure, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are merely relational terms determined for the convenience of describing the structural relationship of the various components or elements in this disclosure, and do not specifically refer to any component or element in this disclosure, nor should they be construed as limiting this disclosure. Example 1

[0026] like Figures 1 to 3 As shown, this application provides a mobile-based in-store QR code shopping system, including: a mobile client, a local area network subsystem, a redirection server, and a shopping backend server; The mobile client is set up on a mobile terminal and includes a shopping interface, a QR code scanning module, and a route navigation module. The local area network subsystem includes a local area network constructed from several AP modules and CPE modules installed within the shopping mall; The redirection server connects to the mobile client via a local area network subsystem and has a product location fingerprint database. The shopping backend server is equipped with a product sales platform that connects to the mobile client's broadband internet to complete the purchase and settlement of goods.

[0027] Users connect to the mall's local area network via a mobile client, scan the existing QR code or barcode on the product, and send the product identification information to the redirection server. The redirection server then uses the product identification information to find the product information and sends it back to the mobile client. The mobile client then connects to the shopping backend, and the user operates the mobile client to make purchases.

[0028] The redirection server receives product identification information and navigation requests sent by the mobile client via QR code scanning. Based on the product location fingerprint database, it confirms the product location and sends the location fingerprint information of the scanned product and the target product in the navigation request to the mobile client. The mobile client performs path navigation based on the pre-stored map and the received location fingerprint information.

[0029] Preferably, the pre-stored map can be a 3D virtual map.

[0030] Preferably, the redirection server also includes a first image recognition module, a customer portrait database, and a product image database.

[0031] Preferably, the system also includes a monitoring system, which includes several surveillance cameras installed in the shopping mall.

[0032] The first image recognition module, the customer facial database, and the monitoring system are used to determine whether the product has been moved. When the redirection server receives the product recognition information and navigation request sent by the mobile client through scanning, and confirms the product location based on the product location fingerprint database, it determines whether the product has been moved. The specific method is as follows: The redirection server obtains customer ID information from the mobile client, retrieves customer recognition images from a preset customer image database based on the customer ID information, searches for product location fingerprints based on product recognition information, and retrieves the camera closest to the product location fingerprint from the mall monitoring system to identify and search for the customer. If the customer is identified within the preset zone of the corresponding product location fingerprint, it is determined that the product has not been moved; otherwise, it is determined that the product has been moved.

[0033] Preferably, the system further includes an outgoing verification device, which includes a base 1 and a transparent frame 2 embedded in the top of the base 1. An electronic scale 5 is provided at the bottom of the transparent frame 2. A first acquisition camera 3 is provided above the top of the base 1. Second acquisition cameras 4 are respectively provided inside the base 1 relative to the four sides of the transparent frame 2. A QR code scanner is provided on the top of the base 1. A controller electrically connected to the first acquisition camera 3, the second acquisition camera 4, the QR code scanner, and the electronic scale 5 is embedded inside the base 1. A second image recognition module is provided in the controller.

[0034] The controller is a computer device, and the tray of the electronic scale 5 is placed at the bottom of the transparent frame 2.

[0035] The exit verification device is used to verify the goods purchased by the user when the user leaves the store. The specific verification method is as follows: The mobile client generates a comprehensive verification QR code for the purchased goods, and the QR code scanner of the factory verification device scans the comprehensive verification QR code to obtain the list of goods to be verified; The user places the purchased item in the transparent frame 2, and the controller acquires the top image, side image, and overall weight of the purchased item through the first acquisition camera 3, the second acquisition camera 4, and the electronic scale 5. The second image recognition module performs image recognition and visual localization on the top and side images of the product, respectively. It obtains a first recognition list based on the top image and several second recognition lists based on the side images. The elements of the first and second recognition lists include confirmed products and sub-lists of similar products. Based on the visual positioning results of each product, the confirmed products in the second identification list are used to confirm the similar product sublist elements in the same position in the first identification list. For example, if the first identification list contains elements {a1, a2, a3}, and the second identification list contains a2 in the same position as elements {a1, a2, a3}, then a2 is used to replace elements {a1, a2, a3}. The elements in the first identification list are identified. If there is no similar product sublist in the first identification list, the product list to be verified is matched and verified with the first identification list. If at least one similar product sublist exists in the first identification list, substitute the elements of each similar product sublist into the first identification list to generate several third identification lists. For example, if the elements in the first identification list are {b1,b2,{a1,a2,a3}}, then three third identification lists will be generated: {b1,b2,a1}, {b1,b2,a2}, and {b1,b2,a3}. Calculate the weight of the products in each third identification list. The third identification list whose weight difference from the total weight of the purchased products is less than a preset value will be used as a verification list. If any verification list matches the list of products to be verified, the verification passes.

[0036] Since the products overlap within the transparent frame 2, the first acquisition camera 3 and the second acquisition camera 4 may only capture partial images of the products. As a result, when identifying them, there may be multiple products that match the corresponding partial images. The similar product sublist is a list of multiple possible matching products for the same image.

[0037] The results of the matching verification are displayed on the screen. Example 2

[0038] Based on Example 1, this application also provides a mobile-based in-store QR code shopping method, including the following steps: Based on the mall's local area network, the original QR codes and / or barcodes of the products are redirected. The redirection server receives the product identification information sent by the mobile client after it connects to the mall's local area network and scans the code. The redirection server searches for product information based on product identification information and sends it back to the mobile client. The mobile client connects to the shopping backend, and the user operates the mobile client to perform shopping operations. The redirection server receives product identification information and navigation requests sent by the mobile client via QR code scanning, confirms the product location based on the product location fingerprint database, and determines whether the product has been moved. If so, send a nearby QR code scanning request to the mobile client, receive feedback information from the mobile client, redirect the server to use the feedback information to perform repeated positioning, and send the repeated positioning result and the location fingerprint information of the target product in the navigation request to the mobile client. If not, the location fingerprint information of the scanned product and the target product in the navigation request will be sent to the mobile client; The mobile client navigates the route based on a pre-stored map and received location fingerprint information.

[0039] The method of this application redirects the original QR code or barcode on the product, using a local area network to direct it to a redirection server to complete the product identification. The redirection server then feeds the product information back to the mobile client, and the mobile client completes the purchase, saving the customer's checkout time. At the same time, by setting up a product location fingerprint database, in conjunction with the mobile client scanning the QR code or barcode to identify the product, the location of the mobile client can be accurately determined. Combined with the map set in the mobile client, accurate navigation to the target product can be achieved.

[0040] Preferably, when the mobile client scans a QR code and / or barcode, it connects to the mall's local area network by default. When the mobile client receives the product information or location fingerprint information, it disconnects from the mall's local area network by default.

[0041] Disconnecting the mall's local area network in a timely manner allows mobile clients to connect to the shopping backend server promptly to purchase goods, and also prevents interference with the mobile terminal's ability to receive messages or calls.

[0042] Furthermore, a continuous scanning mode can be enabled on the mobile client, which connects to the mall's local area network by default. If no scanning operation is performed after a preset time period T, the mobile client disconnects from the mall's local area network.

[0043] Preferably, when the mobile client receives product information, it adds the corresponding product to the shopping cart by default. The shopping cart is a functional module of the shopping interaction interface, which is present in conventional shopping software and will not be described in detail in this application. Adding the corresponding product to the shopping cart by default facilitates the user's purchase operation.

[0044] Specifically, the methods used by the redirection server to determine whether a product has been moved include: Method A: S101: The redirection server controls the AP and / or CPE modules in the mall's local area network to send fixed-frequency verification pulses to the mobile client, calculates the number of verification pulses received by the mobile client within a preset time period T_1, sorts them from least to most, and selects the first N pulse sources as the positioning signal transmission points, where N is determined by the positioning algorithm. S102: Calculate the location of the mobile client according to the positioning algorithm. If the error between the calculated location and the location of the corresponding product in the product location fingerprint database is less than the preset threshold value P, it is determined that the product has not been moved; otherwise, it is determined that the product has been moved. Method B: S201: The redirection server obtains customer ID information from the mobile client, retrieves the customer recognition image from the preset customer image database based on the customer ID information, searches for the product location fingerprint based on the product recognition information, and retrieves the camera closest to the product location fingerprint from the mall monitoring system to identify and search for the customer. If the customer is identified within the preset area Zone of the corresponding product location fingerprint, it is determined that the product has not been moved; otherwise, it is determined that the product has been moved.

[0045] In step S101, the more verification pulses received, the farther the transmitter is from the mobile client. Selecting a distant AP and / or CPE module as the positioning base station helps to increase the transmission time of the positioning signal and reduce the impact of the operation delay of the positioning signal at the transmitter and receiver on the positioning accuracy. AP refers to Access Point, and CPE refers to Customer Premises Equipment. Both are access devices in a wireless network. The positioning algorithm can be either TOA (Time of Arrival) or TDOA (Time Difference of Arrival) positioning algorithms.

[0046] This application may use method A or method B or a combination of both to determine whether the goods have been moved.

[0047] Specifically, the methods for redirecting servers to perform repeated location tracking include: Method D: The user scans the QR code or barcode of the product around the original product using a mobile client, uploads the product identification information, and the redirection server searches the product location fingerprint database based on the product identification information, and uses the corresponding location fingerprint as the duplicate location result; Method E: The user takes an image of the surrounding products of the product being scanned via a mobile client and uploads it; The redirection server segments the image, separating the image of individual products from the QR code or barcode image; The segmented product images are recognized and the QR codes or barcodes are parsed in parallel to obtain the product recognition information of surrounding products. The product location fingerprint database is searched to obtain the location fingerprints of surrounding products. Outliers in the location fingerprints are removed, and one of the remaining location fingerprints is randomly selected as the duplicate localization result.

[0048] In method E, the segmented product images are identified and the QR codes or barcodes are parsed in parallel. This helps to avoid the differences in images collected by different mobile terminals and facilitates the identification of as much product identification information as possible from the surrounding products. The outlier value refers to a few observations or location points that deviate significantly from most data points in a given dataset. Removing outliers from the location fingerprint is to prevent the presence of products taken from elsewhere among the surrounding products.

[0049] Use either method D or method E for duplicate location, with method E being the preferred option.

[0050] Preferably, this method also includes a factory verification of the purchased goods, the specific method of which is as follows: The mobile client generates a comprehensive verification QR code for the purchased goods, and the factory verification device scans the comprehensive verification QR code to obtain a list of goods to be verified; The factory inspection device acquires top images, side images, and overall weight of the purchased goods; Image recognition and visual positioning are performed on the top image and side image of the product, respectively. A first recognition list is obtained based on the top image, and several second recognition lists are obtained based on the side image. The elements of the first recognition list and the second recognition list include the confirmed product and the similar product sublist. Based on the visual positioning results of each product, the confirmed products in the second identification list are used to confirm the similar product sublist elements with the same position in the first identification list; The elements in the first identification list are identified. If there is no similar product sublist in the first identification list, the product list to be verified is matched and verified with the first identification list. If there is at least one similar product sublist in the first identification list, substitute the elements of each similar product sublist into the first identification list to generate several third identification lists. Calculate the weight of the products in each third identification list. Use the third identification list whose weight difference from the total weight of the purchased products is less than a preset value as the verification list. If any verification list matches the list of products to be verified, the verification is successful.

[0051] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0052] While the specific embodiments of this application have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of this application. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of this application are still within the scope of protection of this application.

Claims

1. A mobile-based in-store QR code shopping method, characterized in that, include: Based on the mall's local area network, the original QR codes and / or barcodes of the products are redirected. The redirection server receives the product identification information sent by the mobile client after it connects to the mall's local area network and scans the code. The redirection server searches for product information based on product identification information and sends it back to the mobile client. The mobile client connects to the shopping backend, and the user operates the mobile client to perform shopping operations. The redirection server receives product identification information and navigation requests sent by the mobile client via QR code scanning, confirms the product location based on the product location fingerprint database, and determines whether the product has been moved. If so, send a nearby QR code scanning request to the mobile client, receive feedback information from the mobile client, redirect the server to use the feedback information to perform repeated positioning, and send the repeated positioning result and the location fingerprint information of the target product in the navigation request to the mobile client. If not, the location fingerprint information of the scanned product and the target product in the navigation request will be sent to the mobile client; The mobile client navigates the route based on a pre-stored map and received location fingerprint information.

2. The in-store QR code shopping method based on mobile terminal according to claim 1, characterized in that: When a mobile client scans a QR code or barcode, it connects to the mall's local area network by default. When the mobile client receives product information or location fingerprint information, it disconnects from the mall's local area network by default.

3. The in-store QR code shopping method based on mobile terminal according to claim 2, characterized in that: The mobile client can enable continuous scanning mode, which connects to the mall's local area network by default. If no scanning operation is performed after a preset time period T, the mobile client will disconnect from the mall's local area network.

4. The in-store QR code shopping method based on mobile terminal according to claim 1, characterized in that: Once the mobile client receives product information, it will add the corresponding product to the shopping cart by default.

5. The in-store QR code shopping method based on mobile terminal according to claim 1, characterized in that: The specific methods used by the redirection server to determine whether a product has been moved include: Method A: S101: The redirection server controls the AP and / or CPE modules in the mall's local area network to send fixed-frequency verification pulses to the mobile client, calculates the number of verification pulses received by the mobile client within a preset time period T_1, sorts them from least to most, and selects the first N pulse sources as the positioning signal transmission points, where N is determined by the positioning algorithm. S102: Calculate the location of the mobile client according to the positioning algorithm. If the error between the calculated location and the location of the corresponding product in the product location fingerprint database is less than the preset threshold value P, it is determined that the product has not been moved; otherwise, it is determined that the product has been moved. Method B: S201: The redirection server obtains customer ID information from the mobile client, retrieves the customer recognition image from the preset customer image database based on the customer ID information, searches for the product location fingerprint based on the product recognition information, and retrieves the camera closest to the product location fingerprint from the mall monitoring system to identify and search for the customer. If the customer is identified within the preset area Zone of the corresponding product location fingerprint, it is determined that the product has not been moved; otherwise, it is determined that the product has been moved.

6. The in-store QR code shopping method based on a mobile terminal according to any one of claims 1 or 5, characterized in that: Specific methods for redirecting servers to perform repeated location tracking include: Method D: The user scans the QR code or barcode of the product around the original product using a mobile client, uploads the product identification information, and the redirection server searches the product location fingerprint database based on the product identification information, and uses the corresponding location fingerprint as the duplicate location result; Method E: The user takes an image of the surrounding products of the product being scanned via a mobile client and uploads it; The redirection server segments the image, separating the image of individual products from the QR code or barcode image; The segmented product images are recognized and the QR codes or barcodes are parsed in parallel to obtain the product recognition information of surrounding products. The product location fingerprint database is searched to obtain the location fingerprints of surrounding products. Outliers in the location fingerprints are removed, and one of the remaining location fingerprints is randomly selected as the duplicate localization result.

7. The in-store QR code shopping method based on mobile terminal according to claim 1, characterized in that: This also includes verification of the purchased goods before they leave the factory, the specific methods of which are as follows: The mobile client generates a comprehensive verification QR code for the purchased goods, and the factory verification device scans the comprehensive verification QR code to obtain a list of goods to be verified; The factory inspection device acquires top images, side images, and overall weight of the purchased goods; Image recognition and visual positioning are performed on the top image and side image of the product, respectively. A first recognition list is obtained based on the top image, and several second recognition lists are obtained based on the side image. The elements of the first recognition list and the second recognition list include the confirmed product and the similar product sublist. Based on the visual positioning results of each product, the confirmed products in the second identification list are used to confirm the similar product sublist elements with the same position in the first identification list; The elements in the first identification list are identified. If there is no similar product sublist in the first identification list, the product list to be verified is matched and verified with the first identification list. If there is at least one similar product sublist in the first identification list, substitute the elements of each similar product sublist into the first identification list to generate several third identification lists. Calculate the weight of the products in each third identification list. Use the third identification list whose weight difference from the total weight of the purchased products is less than a preset value as the verification list. If any verification list matches the list of products to be verified, the verification is successful.

8. A mobile-based in-store QR code shopping system, characterized in that: include: Mobile client, LAN subsystem, redirection server, shopping backend server; The mobile client is set up on a mobile terminal and includes a shopping interface, a QR code scanning module, and a route navigation module. The local area network subsystem includes a local area network constructed from several AP modules and CPE modules installed within the shopping mall; The redirection server connects to the mobile client via a local area network subsystem and has a product location fingerprint database. The shopping backend server is equipped with a product sales platform that connects to the mobile client's broadband internet to complete the purchase and settlement of goods.

9. The mobile terminal-based in-store QR code shopping system according to claim 8, characterized in that: The redirection server is also equipped with a first image recognition module, a customer portrait database, and a product image database; It also includes a monitoring system, which comprises several surveillance cameras installed within the shopping mall.

10. The mobile terminal-based in-store QR code shopping system according to claim 8, characterized in that: It also includes a factory verification device; The factory verification device includes a base (1) and a transparent frame (2) embedded on the top of the base (1). An electronic scale (5) is provided at the bottom of the transparent frame (2). A first acquisition camera (3) is provided above the top of the base (1). A second acquisition camera (4) is provided inside the base (1) relative to the four sides of the transparent frame (2). A QR code scanner and a display are provided on the top of the base (1). A controller is embedded inside the base (1) and electrically connected to the first acquisition camera (3), the second acquisition camera (4), the QR code scanner, the display, and the electronic scale (5). A second image recognition module is provided in the controller.

Images