Unmanned retail system for identifying commodities through videos

Abstract

The invention relates to the technical field of unmanned retail commodity identification, in particular to an unmanned retail system for identifying commodities through videos. The operation system comprises a user code scanning unit, a user credit score retrieval unit, a retail electromechanical mortise lock opening unit, a camera video recording unit, a retail electromechanical mortise lock closing unit, a camera stopping unit, a video processing unit, a data transmission unit, an automatic identification unit, a settlement unit and the like. After a user scans a code through a mobile phone and recognizes the code through a system, whether the retail electromechanical mortise lock is opened or not is determined according to the credit score of the user, if yes, a camera starts video recording, the user takes a commodity, and the camera photographs the taken commodity and stores the commodity locally; after the set unlocking time is up, the retail electromechanical mortise lock is closed, and the camera stops; the video is processed / compressed into an effective video, and the effective video is uploaded to a server through an LOT data transmission box; the automatic identification unit performs first system automatic identification, enters the settlement unit after successful identification, and performs manual identification and settlement by the background after failed identification. And deducting the credit score of the user if the user does not carry out settlement.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned retail commodity identification, and in particular to an unmanned retail system for identifying commodities through video. Background Art

[0002] With the popularity of vending machines, there are many spring-based vending machines on the market. Spring machines are large in size, the number of goods they can hold is limited, and replenishment requires the goods to be placed one by one according to the slots before they can be used normally, which is cumbersome and time-consuming.

[0003] The present invention provides a system for identifying commodities by video, which can reduce the cumbersome replenishment of traditional machines and the waiting time for shipment. It can open the door to take the goods, take away and close the door for automatic settlement without waiting, thus greatly increasing the user-friendly experience. Summary of the invention

[0004] The main purpose of the present invention is to provide an unmanned retail system for identifying commodities through video, so as to effectively solve the problems raised in the background technology.

[0005] To achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an unmanned retail system for identifying commodities through video, comprising a camera assembly installed on a retail machine, a retail machine electrical latch assembly, a retail machine temperature control system, a LOT data transmission box, a power supply system and a cloud system; its operating system comprises a user code scanning unit, a user credit score retrieval unit, a retail machine electrical latch opening and camera recording unit, a retail machine electrical latch closing and camera stopping unit, a video processing unit, a data transmission unit, an automatic identification unit and a settlement unit;

[0006] The user first scans the code with a mobile phone. After identification, the system determines whether the user's credit score is below the preset threshold. If it is, the door will be refused and a text prompt will be given. Otherwise, the retail machine's electrical lock will pop open, the camera will start recording, and the user will take the product. The camera will take a photo of the product and save it locally.

[0007] The operating system presets the unlocking time in advance. When the set time is reached, the retail machine's electrical lock closes and the camera stops; the video processing unit processes / compresses the video into a valid video, and the data transmission unit uploads it to the server through the LOT data transmission box; the automatic identification unit automatically identifies the type, unit price, and quantity for the first time, and enters the settlement unit after successful identification. The system calculates the total price based on the identification result and automatically deducts the corresponding fees from the mobile phone WeChat or Alipay; if the identification fails, the background will perform manual identification and send the pricing result to the settlement unit for settlement.

[0008] Preferably, the user credit score retrieval unit is connected to a banking system, and the user credit score adopts the credit score of the banking system.

[0009] Preferably, if the user fails to settle the account for some reason, his / her bank system credit score will be deducted.

[0010] The present invention collects video streams through a camera and transmits them to a 4G module in the form of H264 encoding format, and transmits the compressed video files to a server through video compression technology for commodity identification. If the algorithm fails to identify the product, it will enter an abnormal order, and the manual background can perform secondary identification until the order is closed after the identification is completed. It mainly solves the problems of the cumbersomeness, instability, and long time of selling in traditional vending machines. For example, spring vending machines need to wait for a long time before the goods can be shipped, and gravity-sensing vending machines are subject to greater limitations and cannot place multiple different types of SKUs on the same tray. With this solution, you can scan the code to open the door -> take away the goods -> close the door to settle the bill. It is simple and clear, without unnecessary waiting and cumbersome operations.

[0011] The beneficial effects of the present invention are: reducing the cumbersome replenishment of traditional machines and reducing the waiting time for shipment. The door can be opened to take the goods, and the door can be closed for automatic settlement after taking them away, without waiting, which greatly increases the user-friendly experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Attached Figure 1 This is a framework diagram of the operating system of the present invention.

[0013] Attached Figure 2 This is a diagram of the system composition of the present invention. DETAILED DESCRIPTION

[0014] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0015] Attached Figure 1 , 2 As shown, an unmanned retail system for identifying commodities through video includes a camera component installed on a retail machine, a retail machine electrical latch component, a retail machine temperature control system, a LOT data transmission box, a power supply system, and a cloud system; its operating system includes a user code scanning unit, a user credit score retrieval unit, a retail machine electrical latch opening and camera recording unit, a retail machine electrical latch closing and camera stopping unit, a video processing unit, a data transmission unit, an automatic identification unit, and a settlement unit;

[0016] The user first scans the code with a mobile phone. After identification, the system determines whether the user's credit score is below the preset threshold. If it is, the door will be refused and a text prompt will be given. Otherwise, the retail machine's electrical lock will pop open, the camera will start recording, and the user will take the product. The camera will take a photo of the product and save it locally.

[0017] The operating system presets the unlocking time in advance. When the set time is reached, the retail machine's electrical lock closes and the camera stops; the video processing unit processes / compresses the video into a valid video, and the data transmission unit uploads it to the server through the LOT data transmission box; the automatic identification unit automatically identifies the type, unit price, and quantity for the first time, and enters the settlement unit after successful identification. The system calculates the total price based on the identification result and automatically deducts the corresponding fees from the mobile phone WeChat or Alipay; if the identification fails, the background will perform manual identification and send the pricing result to the settlement unit for settlement.

[0018] The user credit score retrieval unit is connected to the banking system, and the user credit score adopts the credit score of the banking system.

[0019] If the user fails to settle the account for some reason, his / her bank system credit score will be deducted.

[0020] The present invention collects video streams through a camera and transmits them to a 4G module in the form of H264 encoding format, and transmits the compressed video files to a server through video compression technology for commodity identification. If the algorithm fails to identify the product, it will enter an abnormal order, and the manual background can perform secondary identification until the order is closed after the identification is completed. It mainly solves the problems of the cumbersomeness, instability, and long time of selling in traditional vending machines. For example, spring vending machines need to wait for a long time before the goods can be shipped, and gravity-sensing vending machines are subject to greater limitations and cannot place multiple different types of SKUs on the same tray. With this solution, you can scan the code to open the door -> take away the goods -> close the door to settle the bill. It is simple and clear, without unnecessary waiting and cumbersome operations.

[0021] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An unmanned retail system for identifying commodities through video, characterized in that: It includes a camera component installed on the retail machine, a retail machine electrical latch component, a retail machine temperature control system, a LOT data transmission box, a power supply system and a cloud system; its operating system includes a user code scanning unit, a user credit score retrieval unit, a retail machine electrical latch opening and camera recording unit, a retail machine electrical latch closing and camera stopping unit, a video processing unit, a data transmission unit, an automatic identification unit and a settlement unit; The user first scans the code with a mobile phone. After identification, the system determines whether the user's credit score is below the preset threshold. If it is, the door will be refused and a text prompt will be given. Otherwise, the retail machine's electrical lock will pop open, the camera will start recording, and the user will take the product. The camera will take a photo of the product and save it locally. The operating system presets the unlocking time in advance. When the set time is reached, the retail machine's electrical lock closes and the camera stops; the video processing unit processes / compresses the video into a valid video, and the data transmission unit uploads it to the server through the LOT data transmission box; the automatic identification unit automatically identifies the type, unit price, and quantity for the first time, and enters the settlement unit after successful identification. The system calculates the total price based on the identification result and automatically deducts the corresponding fee from WeChat or Alipay on the mobile phone; If the recognition fails, the background will perform manual recognition and send the pricing result to the settlement unit for settlement.

2. The unmanned retail system for identifying commodities through video according to claim 1, characterized in that: The user credit score retrieval unit is connected to the banking system, and the user credit score adopts the credit score of the banking system.

3. The unmanned retail system for identifying commodities through video according to claim 1, characterized in that: If the user fails to settle the account for some reason, his / her bank system credit score will be deducted.

Images