Commodity return identification method

Abstract

The invention discloses a commodity return identification method, and the method comprises the steps: carrying out the centralized processing of the same type of commodities needing to be returned, and carrying out the photographing of the same type of commodities needing to be returned, and obtaining an image of a commodity allowed to be returned; the images of the goods allowed to be returned are recognized through the AI, the remaining storage day number information of the returned goods is obtained, the AI obtains the position information of the goods needing to be returned to the corresponding goods shelf for storage at present based on the remaining storage day number information of the returned goods, and the goods are returned to the corresponding goods shelf for storage based on the position information. A conveying line is controlled to convey the returned commodities to a specified commodity temporary storage area, and the commodities in the temporary storage area are unloaded manually or unloaded through a robot according to the sizes and the weights of the commodities; according to the system and the method, the labor and efficiency in the sorting link, the goods returning difficulty and the like are optimized, the camera is additionally arranged to obtain the image of the returned goods, the production date and shelf life information in the image of the returned goods is automatically extracted by adopting the AI, the goods returning error rate is reduced, and the operation is more efficient.

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to a commodity return identification method. Background Art

[0002] At present, warehouses must verify the production date and remaining shelf life of returned goods, determine whether the returned goods are eligible for secondary sales based on the remaining shelf life of the returned goods, implement different return processes according to the remaining shelf life of each product, and centrally handle the same type of goods with similar or identical remaining shelf life. The specific processing method is to manually enter the shelf life of the goods and calculate the time, then sort and transport them. The entire return process is mostly manual. The degree of automation is low. In order to ensure the efficiency of the operation, the company relies heavily on skilled workers, which leads to low labor efficiency. In addition, multiple operators are required to complete the process, which will lead to redundant personnel.

[0003] Therefore, it is necessary to propose further solutions to solve the above technical problems. Summary of the invention

[0004] The present invention provides a commodity return identification method to solve the above technical problems.

[0005] The object of the present invention is achieved through the following technical solution: a commodity return identification method, comprising the following steps:

[0006] S1: Obtain the goods that need to be returned and manually classify the goods;

[0007] S2: Acquire the same type of goods that need to be returned, take photos of the same type of goods that need to be returned, and obtain images of goods that are allowed to be returned;

[0008] S3: AI pre-processes the collected product images, including obtaining the remaining storage days of the returned product in the returned product image, and obtaining the location information of the corresponding shelf where the returned product needs to be stored;

[0009] S4: AI determines the number of days to store returned goods:

[0010] If the number of days for storage is greater than or equal to the preset time threshold, information on allowing the product to enter the warehouse is generated, and S5 is performed;

[0011] If the storage days are less than the preset time threshold, then the product damage report information is generated and S6 is performed;

[0012] If the number of days of storage cannot be identified, manual identification information is generated, and S7 is performed;

[0013] S5: Based on the information about the allowed goods entering the warehouse, the conveyor line conveys the allowed goods to the temporary storage area, instructs the robot to put the allowed goods into the corresponding return material frame, and conveys them to the corresponding storage rack for storage;

[0014] S6: Based on the damaged commodity information, the conveyor line conveys the damaged commodity to the commodity temporary storage area, instructs the robot to put the damaged commodity into a corresponding damaged material frame, and conveys the damaged material frame to a corresponding shelf for storage;

[0015] S7: Based on the manual identification information, the conveyor line transports the returned goods to the temporary storage area, instructs the robot to put the goods with the manually entered storage days into the corresponding return material frame, and transports the return material frame to the corresponding sorting operation table. The operator identifies the goods placed on the sorting operation table and put into the return material frame, and manually enters the identified storage days into the server, and then proceeds to S4.

[0016] In one embodiment disclosed in the present application, in S3, the number of days the returned product can be stored in the returned product image is obtained, including: AI extracts information from the collected product image to identify the production date and shelf life of the product, and analyzes and compares the production date, shelf life and today's date to determine the remaining number of days the product can be stored.

[0017] In one embodiment disclosed in the present application, in S1, different types of goods that need to be returned are obtained for scanning and detection, including: performing label scanning and detection on different types of goods that need to be returned to obtain label scanning information about each returned product; analyzing the label scanning information to obtain production-related feature information of the different types of returned products; performing screening and classification based on the production-related feature information to determine the type of goods that need to be returned, wherein the production-related feature information of the returned products includes shape, size and weight information of the returned products.

[0018] In one embodiment disclosed in the present application, based on the type of the goods that need to be returned, the goods of the same type that need to be returned are placed in the same area, and the S2 operation is performed on the goods in the area.

[0019] In one embodiment disclosed in the present application, the label is a one-dimensional barcode or a two-dimensional code or a three-dimensional logo or a digital code.

[0020] The beneficial technical effects achieved by the present invention are:

[0021] The present invention optimizes the use of manpower and efficiency in the sorting process, the difficulty of returning goods, etc., adds a camera to obtain images of returned goods, adopts AI to automatically extract the production date and shelf life information in the images of returned goods, and automatically enters the production date and shelf life information into the computer server. Then AI compares the production date and shelf life information entered into the computer server with the return date of the day, and can quickly determine the remaining storage days of the returned goods and accurately determine the storage location of the goods. There is no need to calculate the date manually, the error rate is low, and more than 80% of manpower can be saved. It also makes the operation more efficient, which is 2 times higher than the original processing capacity. At the same time, the return operation is completed by robots, which reduces the difficulty of returning goods.

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the warehousing process of a commodity return identification method provided by the present invention. DETAILED DESCRIPTION

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] See also Figure 1 , Figure 1 A method for identifying product returns is provided in an embodiment of the present invention. The method for identifying product returns comprises the following steps:

[0026] S1: Obtain the goods that need to be returned and manually classify the goods;

[0027] S2: Obtain the same type of goods that need to be returned, take photos of the same type of goods that need to be returned, and obtain images of goods that are allowed to be returned.

[0028] S3: AI pre-processes the collected product images, including obtaining the remaining storage days of the returned product in the returned product image, and obtaining the location information of the corresponding shelf where the returned product needs to be stored;

[0029] S4: AI determines the number of days to store returned goods:

[0030] If the number of days for storage is greater than or equal to the preset time threshold, information on allowing the product to enter the warehouse is generated, and S5 is performed;

[0031] If the number of storage days is less than the preset time threshold, then the product damage report information is generated and S6 is performed;

[0032] If the number of days of storage cannot be identified, manual identification information is generated, and S7 is performed;

[0033] S5: Based on the information about the allowed goods entering the warehouse, the conveyor line conveys the allowed goods to the temporary storage area, instructs the robot to put the allowed goods into the corresponding return material frame, and conveys them to the corresponding storage rack for storage;

[0034] S6: Based on the damaged commodity information, the conveyor line conveys the damaged commodity to the commodity temporary storage area, instructs the robot to put the damaged commodity into a corresponding damaged material frame, and conveys the damaged material frame to a corresponding shelf for storage;

[0035] S7: Based on the manual identification information, the conveyor line conveys the returned goods to the temporary storage area, instructs the robot to put the goods with the manually entered storage days into the corresponding return material frame, and conveys the return material frame to the corresponding sorting operation table. The operator identifies the goods placed on the sorting operation table and put into the return material frame, and manually enters the identified storage days into the server, and then proceeds to S4.

[0036] In one embodiment disclosed in the present application, in S3, the number of days the returned product can be stored in the returned product image is obtained, including: AI extracts information from the collected product image to identify the production date and shelf life of the product, and analyzes and compares the production date, shelf life and today's date to determine the remaining number of days the product can be stored.

[0037] In one embodiment disclosed in the present application, in S1, different types of goods that need to be returned are obtained for scanning and detection, including: performing label scanning and detection on different types of goods that need to be returned to obtain label scanning information about each returned product; analyzing the label scanning information to obtain production-related feature information of the different types of returned products; performing screening and classification based on the production-related feature information to determine the type of goods that need to be returned, wherein the production-related feature information of the returned products includes shape, size and weight information of the returned products.

[0038] In one embodiment disclosed in the present application, based on the type of the goods that need to be returned, the goods of the same type that need to be returned are placed in the same area, and the S2 operation is performed on the goods in the area.

[0039] In one embodiment disclosed in the present application, the label is a one-dimensional barcode or a two-dimensional code or a three-dimensional logo or a digital code.

[0040] From the above, it can be seen that the types of returned goods in the present invention are classified according to the size and weight of the goods. For returned goods whose size or weight exceeds the preset value, they are manually put into the material frame, and for goods whose size and weight are within the preset value, they are directly put into the material frame for transportation, and then the AGV machine automatically puts them into the material frame, which greatly reduces the labor intensity of workers.

[0041] Furthermore, AI is used to automatically extract the production date and shelf life information from the image of the returned goods, and automatically enter the production date and shelf life information into the computer server. Then, by comparing the production date and shelf life information entered into the computer server with the return date of the day, AI can quickly determine the remaining storage days of the returned goods and accurately determine the storage location of the goods. There is no need to manually calculate the date, the error rate is low, and more than 80% of manpower can be saved. It also makes the operation more efficient, increasing the original processing capacity by 2 times4, and reducing the difficulty of returning goods: the return operation is completed by robots.

[0042] The above is a detailed introduction to a commodity return identification method provided by an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the core idea of ​​the present invention. At the same time, for those skilled in the art, according to the ideas and methods of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

[0043] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying commodity returns, characterized in that: The steps include: S1: Obtain the goods that need to be returned, classify them manually, and store the same type of goods that need to be returned together; S2: Obtain the same type of goods that need to be returned, take photos of the same type of goods that need to be returned, and obtain images of goods that are allowed to be returned. S3: AI pre-processes the collected product images, including obtaining the remaining storage days of the returned products; S4: AI makes a judgment based on the storage days of the returned goods, and obtains the location information of the corresponding shelf where the returned goods need to be stored: If the remaining storage days are greater than or equal to the preset time threshold, information on allowing the product to enter the warehouse is generated, and S5 is performed; If the remaining storage days are less than the preset time threshold, then the product damage report information is generated and S6 is performed; If the remaining storage days cannot be identified, manual identification information is generated, and S7 is performed; S5: Based on the information about the allowed goods entering the warehouse, the conveyor line conveys the allowed goods to the temporary storage area, instructs the robot to put the allowed goods into the corresponding return material frame, and conveys them to the corresponding storage rack for storage; S6: Based on the damaged commodity information, the conveyor line conveys the damaged commodity to the commodity temporary storage area, instructs the robot to put the damaged commodity into a corresponding damaged material frame, and conveys the damaged material frame to a corresponding shelf for storage; S7: Based on the manual identification information, the conveyor line transports the returned goods to the temporary storage area, instructs the robot to put the goods with the manually entered storage days into the corresponding return material frame, and transports the return material frame to the corresponding sorting operation table. The operator identifies the goods placed on the sorting operation table and put into the return material frame, and manually enters the identified storage days into the server, and then proceeds to S4.

2. A commodity return identification method according to claim 1, characterized in that: In S3, the number of days for the returned product to be stored in the returned product image is obtained, including: AI extracts information from the collected product image to identify the production date and shelf life of the product, and automatically enters the production date and shelf life into the computer server. The computer server analyzes and compares the production date and the shelf life with the return date of the day, generates information on the remaining number of days for the product to be stored, and sends it to AI.

3. A commodity return identification method according to claim 1, characterized in that: In S1, different types of goods that need to be returned are obtained for scanning and detection, including: performing label scanning and detection on different types of goods that need to be returned to obtain label scanning information about each returned product; analyzing the label scanning information to obtain production-related feature information of the different types of returned products; screening and classification based on the production-related feature information to determine the type of goods that need to be returned, wherein the production-related feature information of the returned products includes shape, size and weight information of the returned products.

4. A commodity return identification method according to claim 3, characterized in that: Based on the type of the goods that need to be returned, the goods of the same type that need to be returned are placed in the same area, and the S2 operation is performed on the goods in the area.

5. A commodity return identification method according to claim 4, characterized in that: The label is a one-dimensional barcode or a two-dimensional code or a three-dimensional logo or a digital code.

Images