Intelligent logistics sorting methods, devices, terminals and storage media

Abstract

This application discloses an intelligent logistics sorting method, apparatus, terminal, and storage medium, relating to the field of logistics sorting. Based on a multi-faceted scanning system, this application includes multiple industrial camera groups and inlet and outlet photoelectric sensors. The method includes retrieving flight information from a warehouse management system and obtaining large package allocation information from a logistics distribution system. Upon receiving an inlet photoelectric sensor signal, the camera groups are controlled to acquire images of the cargo boxes and record information. The acquired images undergo barcode decoding and OCR recognition, and are fused and matched with flight information. Upon receiving information from the outlet photoelectric sensor, photoelectric verification is performed. After successful verification, the master order number and large package number are output for sorting. This application achieves the technical effects of efficiently and accurately sorting logistics cargo boxes, reducing sorting errors, and improving the efficiency and accuracy of logistics sorting.

Description

Technical Field

[0001] This application relates to the field of automated logistics sorting technology, and in particular to an intelligent logistics sorting method, device, terminal and storage medium. Background Technology

[0002] In today's highly competitive market environment, with the rapid development of e-commerce and express delivery industries, the importance of logistics sorting is becoming increasingly prominent, and the performance of logistics sorting systems has become one of the key factors for enterprises to enhance their competitiveness.

[0003] In the field of logistics sorting, various technologies are commonly used to solve problems such as parcel sorting and information acquisition. Cross-belt sorters are a common type, consisting of a conveyor belt, a parcel feeding platform, sorting carts, a barcode reading system, and a parcel dropping system. By utilizing the coordinated operation of the conveyor belt and sorting carts, it can efficiently handle the sorting and transportation of large quantities of parcels.

[0004] However, existing logistics sorting systems have many shortcomings. The parcel sorting process requires significant manual intervention, such as manually adjusting parcel placement to ensure the waybill is facing upwards, which undoubtedly increases labor costs. Furthermore, traditional sorting systems are inefficient when dealing with complex orders or large volumes of parcels, failing to meet the rapidly growing demands of the e-commerce and express delivery industries. Simultaneously, existing systems are inadequate in information processing, failing to effectively integrate barcode and OCR information, resulting in low matching accuracy. Moreover, they are insufficient in automatically matching flight information, requiring manual intervention and increasing the error rate. Additionally, traditional systems can only identify partial information about the boxes, failing to comprehensively acquire all key information on the boxes, and lack a verification mechanism, resulting in insufficient ability to detect erroneous boxes. Existing volume measurement systems also lack precision, failing to meet the requirements of high-precision sorting. Furthermore, the systems face difficulties in integrating with other systems such as WMS, leading to low efficiency in data sharing and process collaboration. Summary of the Invention

[0005] In order to improve the efficiency and accuracy of logistics sorting, this application provides an intelligent logistics sorting method, device, terminal and storage medium.

[0006] Firstly, this application provides an intelligent logistics sorting method, which adopts the following technical solution:

[0007] A smart logistics sorting method based on a multi-faceted scanning system, the multi-faceted scanning system comprising multiple industrial camera groups arranged in a preset scanning area, wherein an inlet photoelectric sensor and an outlet photoelectric sensor are respectively provided at the inlet and outlet of the scanning area, the method comprising the following steps:

[0008] Retrieve flight information from a pre-established warehouse management system, including the master manifest number and package number for all cargo containers;

[0009] When the first photoelectric trigger signal is received from the entrance photoelectric sensor, all the industrial camera groups are controlled to acquire images of the cargo box passing through the entrance photoelectric sensor to obtain the first acquired image, and the first photoelectric trigger information is recorded.

[0010] Based on the first acquired image, barcode decoding and OCR recognition are performed. The obtained barcode decoding information and OCR recognition information are fused and matched with the retrieved flight information to obtain the corresponding master order number and the large package number.

[0011] When the second photoelectric trigger information recorded by the exit photoelectric sensor is received, photoelectric verification is performed in conjunction with the second photoelectric trigger information. After the photoelectric verification is passed, the master order number and the large package number are output for sorting.

[0012] By adopting the above technical solution, flight information can be automatically retrieved from the warehouse management system and package allocation information can be obtained from the logistics distribution system. The industrial camera group is triggered by the entrance photoelectric sensor to collect images of the cargo box. After barcode decoding and OCR recognition, the information is fused and matched to obtain the master order number and package number. Then, photoelectric verification is performed by the exit photoelectric sensor, and finally, the information is output for sorting. This realizes the automation of logistics sorting, reduces manual intervention, and improves sorting efficiency. It also improves the accuracy of flight information matching through information fusion matching and photoelectric verification. Furthermore, it can obtain key information such as barcodes and OCR text of the cargo box at one time. The coordinated work of each step realizes an integrated process from information acquisition to sorting.

[0013] Preferably, the step of retrieving flight information from a pre-established warehouse management system, wherein the flight information includes the master manifest number and package number of all cargo containers, specifically includes the following steps:

[0014] Based on the flight number, the corresponding flight information is retrieved from the database of the pre-established warehouse management system. The flight information includes the master bill of lading number and the package number of all cargo containers. Each flight includes several master bill of lading numbers, and each master bill of lading number includes several package numbers. Each cargo container has a unique corresponding package number.

[0015] Based on the flight number, obtain the package allocation information and transportation plan from the pre-established logistics allocation system;

[0016] By adopting the above technical solution, the master order number and package number of all cargo boxes can be accurately retrieved from the warehouse management system database based on the flight number. At the same time, package allocation information and transportation plans can be obtained from the logistics distribution system, providing comprehensive and accurate flight-related information for subsequent sorting, thereby improving the efficiency and accuracy of logistics sorting.

[0017] Preferably, when the first photoelectric trigger signal emitted by the entrance photoelectric sensor is received, controlling all the industrial camera groups to acquire images of the cargo box passing through the entrance photoelectric sensor to obtain a first acquired image, and recording the first photoelectric trigger information, specifically includes the following steps:

[0018] When the entrance photoelectric sensor is blocked by the passing cargo box, the entrance photoelectric sensor emits a first photoelectric trigger signal;

[0019] When the first photoelectric trigger signal is received, a temporary cargo box number is generated for the cargo box and a first-in-first-out queue is maintained. The temporary cargo box number is stored in the first-in-first-out queue and the first photoelectric trigger information is recorded. The first photoelectric trigger information includes the temporary cargo box number and the current cargo box entry timestamp.

[0020] Based on the first photoelectric trigger signal, the industrial camera group is controlled to continuously acquire images of each side of the cargo box in the scanning area, thereby obtaining multiple first acquired images;

[0021] The temporary cargo container number is bound to the first acquired image.

[0022] By adopting the above technical solution, when the entrance photoelectric sensor is blocked by the cargo box and emits the first photoelectric trigger signal, the system can receive the signal in a timely manner, generate a temporary cargo box number, maintain the first-in-first-out queue, store the number in the queue, and record the first photoelectric trigger information including the entry timestamp. Furthermore, the system can control the industrial camera group to continuously acquire images from all sides of the cargo box, obtaining multiple first-capture images, and bind the temporary cargo box number to the images. This achieves accurate recording of cargo box information and comprehensive image acquisition, providing an accurate and complete data foundation for subsequent barcode decoding, OCR recognition, information fusion matching, and sorting operations, thereby improving the accuracy and efficiency of intelligent logistics sorting.

[0023] Preferably, a spatial coordinate system is established in the scanning area. When the image is acquired, the industrial camera group in the scanning area continuously takes high-speed photos of the six sides of the cargo box. The industrial camera group includes industrial cameras located in the positive X-axis direction, negative X-axis direction, positive Y-axis direction, negative Y-axis direction, positive Z-axis direction, and negative Z-axis direction of the spatial coordinate system. Among them, the industrial camera located in the negative Z-axis direction is a bottom scanning camera. The bottom scanning camera is located below the conveyor belt transporting the cargo box. A reflector is set in the field of view of the bottom scanning camera, and the reflector faces the gap between the two conveyor belts.

[0024] By adopting the above technical solution, a spatial coordinate system is established in the scanning area, enabling the industrial camera group to continuously take high-speed pictures of all six sides of the cargo box. Combined with the bottom scanning camera located below the conveyor belt with a reflector facing the gap of the conveyor belt, image information of all sides of the cargo box can be comprehensively acquired, improving the comprehensiveness of information acquisition and thus improving the accuracy of flight information matching.

[0025] Preferably, the step of performing barcode decoding and OCR recognition based on the first acquired image, and fusing and matching the obtained barcode decoding information, OCR recognition information, and retrieved flight information to obtain the corresponding master order number and the large package number, specifically includes the following steps:

[0026] Based on the first acquired image, determine whether there is only one cargo box when entering the scanning area. If so, extract the cargo box label based on the first acquired image to obtain the current cargo box label.

[0027] The barcode of the cargo container is decoded to obtain barcode decoding information, and multiple first-collected images are OCR recognized to obtain OCR recognition information. The barcode decoding information includes the master order number, the large package number and the flight number, and the OCR recognition information includes the shipping and receiving address and the item description.

[0028] Based on the preset BERT model, entity extraction is performed on the OCR recognition information to obtain semantic features. The semantic similarity between the semantic features and the preset semantic fields of the flight information is calculated. The semantic similarity values ​​that exceed the semantic matching threshold are filtered and summarized into a candidate matching set.

[0029] Structured character data of each flight information is extracted from the candidate matching set, and the edit distance matching algorithm is used to calculate the edit distance between the flight information and the corresponding character data in the barcode decoding information. The flight information with the smallest edit distance and less than the edit distance threshold is selected as the final matching result.

[0030] If multiple records have the same edit distance, then a second sort is performed based on the semantic similarity, and the record with the highest semantic similarity is selected as the final matching result.

[0031] By adopting the above technical solution, it is possible to determine whether there is only one cargo box in the first acquired image, ensuring that subsequent processing is done on a single cargo box and avoiding interference from multiple cargo boxes. Through waybill extraction, barcode decoding, and OCR recognition, key information such as cargo box barcode, master order number, package number, flight number, shipping and receiving address, and item description can be obtained. By using the BERT model to extract entities and calculate semantic similarity for the OCR-recognized information, combined with the edit distance matching algorithm, flight information with a high degree of matching with the barcode decoding information can be selected. Even if there are multiple data with the same edit distance, the final matching result can be obtained by combining semantic similarity for secondary sorting, which improves the accuracy of flight information matching and achieves effective fusion and matching of cargo box information and flight information.

[0032] Preferably, when the second photoelectric trigger information recorded by the exit photoelectric sensor is received, the photoelectric verification is performed in conjunction with the second photoelectric trigger information, specifically including the following steps:

[0033] When the exit photoelectric sensor is blocked by the passing cargo box, the system receives the second photoelectric trigger signal emitted by the exit photoelectric sensor and generates the second photoelectric trigger information, which includes the current timestamp of the cargo box being removed.

[0034] The industrial camera group is controlled to acquire images of the current cargo box, resulting in a second acquired image;

[0035] Take out the temporary container number that was first stored in the queue from the head of the first-in-first-out queue, and find and obtain the master order number and the large package number that are bound to the temporary container number based on the taken-out temporary container number, as sorting information to be output;

[0036] The first acquired image and the second acquired image are compared for similarity, and an image matching score is calculated.

[0037] Calculate the time difference between the removal timestamp in the second photoelectric triggering information and the entry timestamp in the first photoelectric triggering information, and determine whether the time difference is within a preset reasonable time threshold range;

[0038] If the image matching score exceeds the preset matching confidence value and the time difference ΔT is within the reasonable time threshold range, the photoelectric verification passes and the sorting information to be output is output to the logistics distribution system; otherwise, arbitration verification is performed, and if the arbitration verification fails, the return operation of the cargo box is triggered.

[0039] By adopting the above technical solution, the similarity of images captured by inlet and outlet photoelectric sensors, as well as the time difference calculation and verification between the second and first photoelectric trigger information, can effectively determine the status of the cargo box and realize photoelectric verification. When the verification fails, arbitration verification is performed and a return operation is triggered when necessary, which improves the accuracy and reliability of cargo box sorting and reduces the occurrence of incorrect sorting.

[0040] Preferably, after continuously acquiring multiple first images from each side of the cargo box, the following steps are further included:

[0041] The depth information of multiple first-captured images acquired by the industrial camera group is analyzed in real time. When the distance between multiple cargo boxes is continuously lower than a preset distance threshold, it is determined that a collision event has occurred between the multiple cargo boxes. The multiple cargo boxes are recorded as a collision cargo box group and the collision timestamp is recorded.

[0042] Obtain the temporary container numbers of all containers in the collision container group, and denote them as the collision number set;

[0043] For each cargo box in the collision number set, the face where the cargo box label is located and its two-dimensional coordinates on the current face are identified and extracted from the first acquired image corresponding to the cargo box, and a first position fingerprint is generated;

[0044] Extract the latest frame of the first acquired image after the collision timestamp and before the cargo box group leaves the scanning area, identify and extract the face of the current cargo box label of each cargo box and the two-dimensional coordinates on the current face, and generate a second position fingerprint;

[0045] If all the cargo container labels are successfully identified and the second location fingerprint has a unique match with the first location fingerprint, the collision number set in the first-in-first-out queue is maintained, and the first-in-first-out queue is updated according to the matching result.

[0046] If there is a situation where the cargo container waybill cannot be identified or the matching relationship is not unique, the collision number set will be removed from the first-in-first-out queue, and the return operation of the cargo container group will be triggered.

[0047] By adopting the above technical solution, the depth information of the images captured by the industrial camera group can be analyzed in real time, and the collision event of the cargo box can be determined in a timely manner and the relevant information can be recorded. The first position fingerprint and the second position fingerprint can be generated to accurately determine whether the collision has caused the loss of the cargo box identity. Based on the judgment result, the queue order can be maintained or the reflow operation can be triggered, which ensures the accuracy of the cargo box information and the reliability of the sorting process, reduces sorting errors caused by the loss of cargo box identity due to collision, and improves the accuracy and efficiency of logistics sorting.

[0048] Secondly, this application provides an intelligent logistics sorting device, which adopts the following technical solution:

[0049] The information retrieval module is used to retrieve flight information from a pre-established warehouse management system. The flight information includes the master bill of lading number and package number of all cargo containers.

[0050] The image acquisition module is used to control all the industrial camera groups to acquire images of the cargo box passing through the entrance photoelectric sensor when it receives the first photoelectric trigger signal emitted by the entrance photoelectric sensor, and to record the first photoelectric trigger information.

[0051] The information fusion and matching module is used to perform barcode decoding and OCR recognition based on the first acquired image, and to fuse and match the obtained barcode decoding information, OCR recognition information and the retrieved flight information to obtain the corresponding master order number and the large package number;

[0052] The photoelectric verification module is used to perform photoelectric verification in conjunction with the second photoelectric trigger information recorded by the exit photoelectric sensor when it receives the second photoelectric trigger information. After the photoelectric verification is passed, the main order number and the large package number are output for sorting.

[0053] Thirdly, this application provides a terminal that adopts the following technical solution:

[0054] A terminal includes a memory and a processor, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the intelligent logistics sorting method as described above.

[0055] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0056] A computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the intelligent logistics sorting method as described above.

[0057] In summary, this application includes at least one of the following beneficial technical effects:

[0058] (1) This application can automatically retrieve flight information from the warehouse management system, and combine the information obtained by barcode decoding and OCR recognition to perform fusion matching, thereby obtaining key information such as barcodes and OCR text on the boxes at one time, and achieving comprehensive information acquisition;

[0059] (2) This application reduces manual intervention through automated processes and improves sorting efficiency by using photoelectric sensors at the inlet and outlet to perform image acquisition, counting, and verification.

[0060] (3) This application improves the accuracy of flight information matching through information fusion matching technology and photoelectric verification and other multiple verification mechanisms. Attached Figure Description

[0061] Figure 1 This is a flowchart of an intelligent logistics sorting method;

[0062] Figure 2 This is a structural diagram of an intelligent logistics sorting device. Detailed Implementation

[0063] This application provides an intelligent logistics sorting method, device, terminal, and storage medium. To make the purpose, technical solution, and advantages of this application clearer, the implementation methods of this application will be further described in detail below.

[0064] The following describes in further detail an embodiment of an intelligent logistics sorting method of this application, with reference to the accompanying drawings.

[0065] This embodiment of an intelligent logistics sorting method is based on a multi-faceted scanning system. The multi-faceted scanning system includes multiple industrial camera groups set in a preset scanning area P2. An entrance photoelectric sensor and an exit photoelectric sensor are respectively set at the entrance and exit of the scanning area P2.

[0066] A spatial coordinate system is established in the scanning area. During image acquisition, the industrial camera group in the scanning area continuously takes high-speed photos of the six sides of the cargo box.

[0067] The industrial camera group includes industrial cameras located in the positive X-axis direction, negative X-axis direction, positive Y-axis direction, negative Y-axis direction, positive Z-axis direction, and negative Z-axis direction of the spatial coordinate system.

[0068] The industrial camera located in the negative Z-axis direction is a bottom-scan camera. It is positioned below the conveyor belt of the transport container, and a reflector is positioned within its field of view, facing the gap between the two conveyor belts. Specifically, the camera in the positive Z-axis direction photographs the top surface of the container vertically downwards.

[0069] A camera positioned vertically upwards along the negative Z-axis captures images of the bottom of the cargo container. Because the conveyor belt obstructs the view, this camera is a bottom-scan camera; it is mounted below the conveyor belt and observes the bottom of the container through a reflector facing the gap between the two belts.

[0070] The cameras are positioned horizontally facing each other along the positive and negative X-axis to capture images of the two sides of the cargo box.

[0071] The camera on the positive Y-axis is positioned at the end of the aisle, facing the entrance, to photograph the front of the cargo container.

[0072] The camera on the negative Y-axis is positioned at the beginning of the passageway, facing the exit, to photograph the back of the cargo container.

[0073] All cameras are equipped with bar lights and diffusers to ensure that images with uniform lighting and no overexposure of highlights are obtained under any ambient light conditions.

[0074] This setup ensures comprehensive image capture of all six sides of the cargo box.

[0075] like Figure 1 As shown, the method of this application includes the following steps:

[0076] S1. Retrieve flight information from the pre-established warehouse management system. The flight information includes the master manifest number and package number of all containers. The specific steps are as follows:

[0077] S11. Retrieve the corresponding flight information from the pre-established warehouse management system database based on the flight number. The flight information includes the master bill of lading number and the package number of all cargo containers. Each flight includes several master bill of lading numbers, and each master bill of lading number includes several package numbers. Each cargo container has a unique corresponding package number.

[0078] The warehouse management system can be a common WMS system, storing cargo container information related to flights. The database used can be a relational database, such as MySQL or Oracle, or a non-relational database, such as MongoDB.

[0079] S12. Based on the flight number, obtain the package allocation information and transportation plan from the pre-established logistics allocation system. The logistics allocation system manages the allocation of packages.

[0080] In this embodiment, information retrieval is a scheduled task that performs incremental data synchronization every minute. First, it queries the WMS system's database using the flight information table (flight_info) to retrieve all records for scheduled departure times within the next two hours. Each flight record includes a flight number (flight_number), a master waybill number (master_waybill_number), and its status. For each master waybill number, it then queries its associated package information table (packages) to obtain all house waybill numbers associated with that master waybill number.

[0081] This embodiment employs a dual-verification mechanism to ensure data consistency: First, it checks the format of the master order number, with a standard format such as 2 letters + 10 numbers. Second, it verifies whether each package number exists in the TMS loading list. If inconsistencies are found between the WMS and TMS data, such as a package number not existing in the TMS, the record will be marked as pending confirmation and will not be added to the matching database. Simultaneously, an alarm will be triggered to notify the administrator.

[0082] S2. Upon receiving the first photoelectric trigger signal from the entrance photoelectric sensor, control all industrial camera groups to acquire images of the cargo box passing through the entrance photoelectric sensor, obtain the first acquired image, and record the first photoelectric trigger information. The entrance photoelectric sensor can be a through-beam photoelectric sensor, which blocks the light when the cargo box passes by, thereby emitting a trigger signal. Specifically, the steps are as follows:

[0083] S21. When the entrance photoelectric sensor is blocked by a passing cargo box, the entrance photoelectric sensor emits a first photoelectric trigger signal.

[0084] S22. When the first photoelectric trigger signal is received, a temporary cargo box number is generated and a first-in-first-out queue is maintained. The temporary cargo box number is stored in the first-in-first-out queue and the first photoelectric trigger information is recorded. The first photoelectric trigger information includes the temporary cargo box number and the current cargo box entry timestamp.

[0085] The system maintains a First-In-First-Out (FIFO) queue, which stores all temporary container numbers in the order in which containers pass through the entrance. Whenever a temporary container number is generated for a container by the photoelectric sensor at the entrance, that temporary container number is immediately pushed to the end of the queue.

[0086] S23. Based on the first photoelectric trigger signal, the industrial camera group in the scanning area is controlled to continuously acquire images of each side of the cargo box in the scanning area, and multiple first acquired images are obtained.

[0087] S24. Bind the temporary cargo container number to the first acquired image.

[0088] In one specific implementation, when the inlet photoelectric sensor is triggered, the PLC sends a rising edge signal to the image server. A daemon process on the server listens for this signal and, upon capturing it, immediately performs the following operations:

[0089] Generate a temporary cargo box number, record the first photoelectric trigger information, including the temporary number and the entry timestamp accurate to milliseconds, and store it as a data object in the Redis cache.

[0090] All industrial camera groups can be triggered to acquire data synchronously via GPIO ports or Gigabit Ethernet.

[0091] Each set of photos captured by the camera group (six photos per set, one for each side) is immediately uploaded to the file server, and a new record in the database is created that strongly associates the temporary cargo box number with the URL paths of these six image files.

[0092] S3. Based on the first acquired image, perform barcode decoding and OCR recognition, and fuse and match the obtained barcode decoding information and OCR recognition information with the retrieved flight information to obtain the corresponding master order number and package number. The specific steps include the following:

[0093] S31. Based on the first acquired image, determine whether there is only one cargo box when entering the scanning area. If so, extract the cargo box label based on the first acquired image to obtain the cargo box label for the current cargo box.

[0094] In this embodiment, the determination of whether there is only one cargo box when entering the scanning area is based on the first acquired image. Specifically, it is determined whether there is only one cargo box in the image at this time based on the first acquired image corresponding to the cargo box's entry timestamp. If not, all cargo boxes that enter the scanning area at the same time are returned.

[0095] S32. Decode the barcode on the cargo container waybill to obtain barcode decoding information, and perform OCR recognition on multiple first-captured images to obtain OCR recognition information. The barcode decoding information includes the master order number, package number, and flight number, and the OCR recognition information includes the shipping and receiving addresses and item descriptions.

[0096] S33. Based on the preset BERT model, entity extraction is performed on the OCR recognition information to obtain semantic features. The semantic similarity between the semantic features and the preset semantic fields of flight information is calculated. Semantic similarity exceeding the semantic matching threshold is selected and summarized into a candidate matching set.

[0097] In this embodiment, the BERT model is a pre-trained language model used for effective semantic understanding and feature extraction of text.

[0098] From the full text identified by OCR, key entities such as [DEST:PEK] (Destination Beijing Capital International Airport) and [MAWB:1234567890] are extracted using a pre-trained BERT model.

[0099] Calculate the semantic similarity between the destination field extracted by OCR and the destination code in the WMS flight information. For example, the destination field "Beijing Capital" and the destination code "PEK".

[0100] In this embodiment, all text is projected into BERT's 768-dimensional vector space, and cosine similarity is calculated. This embodiment sets a semantic matching threshold of 0.85, filtering out all flight records with similarity higher than this value to form a candidate matching set A.

[0101] S34. Extract the structured character data of each flight information from the candidate matching set, use the edit distance matching algorithm to calculate the edit distance between the flight information and the corresponding character data in the barcode decoding information, and select the flight information with the smallest edit distance that is less than the edit distance threshold as the final matching result.

[0102] The edit distance matching algorithm used in this embodiment is the Levenshtein distance algorithm. The edit distance between the master order number and package number identified by OCR and the corresponding number in the WMS is calculated and normalized. Normalized distance = edit distance / field length.

[0103] In this embodiment, the edit distance threshold is set to 0.2, and all records with a normalized distance lower than this value are filtered out to form a candidate matching set B.

[0104] The intersection of candidate sets A and B is taken as the final candidate set. The final candidate set usually contains only one record, which is the final matching result. If the intersection is empty or there are multiple records, the union is taken to form the final candidate set.

[0105] For each record in the final candidate set, a comprehensive confidence score is calculated: Comprehensive confidence score = 0.6 × semantic similarity + 0.4 × (1 - normalized distance). The record with the highest score exceeding 0.75 is selected as the final matching result.

[0106] S35. If there are multiple records with the same edit distance, then the semantic similarity is used for secondary sorting, and the record with the highest semantic similarity is selected as the final matching result.

[0107] S4. In a specific implementation, after continuously acquiring multiple first acquired images of each side of the cargo box, a collision detection and processing step is further included, specifically including the following steps:

[0108] S41. Analyze the depth information of multiple first-capture images collected by the industrial camera group in real time. When it is detected that the distance between multiple boxes is continuously lower than the preset distance threshold, determine that a collision event has occurred between multiple boxes, record the multiple boxes as a collision box group and record the collision timestamp.

[0109] The depth information analysis in this embodiment is achieved through binocular vision technology, which can accurately determine the distance between cargo boxes.

[0110] As the cargo box moves through the scanning area, the system analyzes the depth map point cloud data generated by the camera in real time. It determines collisions by calculating the minimum distance between adjacent cargo boxes. If the distance is less than 5cm for 5 consecutive frames (100ms), a collision event is determined to have occurred. The numbers of the two cargo boxes involved are marked and recorded in the collision event record table.

[0111] S42. Obtain the temporary container numbers of all containers in the collision container group, and denote them as the collision number set.

[0112] S43. For each cargo box in the collision number set, identify and extract the face where the cargo box label is located and the two-dimensional coordinates on the current face from the first acquired image corresponding to the cargo box, and generate the first position fingerprint.

[0113] S44. Extract the latest frame of the first acquired image after the collision timestamp and before the cargo box group leaves the scanning area, identify and extract the face where the current cargo box label is located and the two-dimensional coordinates on the current face of each cargo box, and generate the second position fingerprint;

[0114] S45. If all cargo container waybills are successfully identified and the fingerprint at the second position has a unique match with the fingerprint at the first position, it is determined that the collision did not cause identity loss. The collision number set in the first-in-first-out queue is maintained, and the first-in-first-out queue is updated according to the matching result.

[0115] S46. If there are cases where the cargo container waybill cannot be identified or the matching relationship is not unique, remove the collision number set from the first-in-first-out queue and trigger the return operation of the cargo container group.

[0116] The implementation principle of this embodiment is as follows: Collision detection and handling steps are added, further improving the stability and reliability of the logistics sorting system. It can promptly detect collisions between cartons and determine whether identification has been lost based on the location information of the shipping label after a collision. Cargo groups with lost identification are returned to their original locations, preventing incorrect sorting.

[0117] In one specific implementation, if the temporary number of the cargo container is marked as being involved in a collision, assuming the two colliding cargo containers are numbered M456 and N123, the recovery procedure is initiated:

[0118] A: Retrieve the first location fingerprint of the waybill generated when each box in the collision box group enters the warehouse from the cache. For example: M456: ('top', 0.2, 0.8); N123: ('side', 0.5, 0.5).

[0119] B: Extract the latest clear image frame from the continuously acquired video stream, after the collision occurs and before the exit is triggered.

[0120] C: Attempt to identify the waybill for each cargo box in this frame image and generate a second location fingerprint. If successful, for example, if the current cargo box's side unit is found to be ('side', 0.5, 0.5), then match it with the first fingerprint to confirm that the current cargo box's true identity is N123.

[0121] D: If a match is successful, update the queue order based on the current position of the cargo box, and swap the temporary number of the cargo box that is closer to the exit sensor to the front of the queue.

[0122] E: If a match fails, the collision ID set of the involved collision box group will be deleted from the collision event log table, and the entire collision box group will be forced to reflow. Reasons for match failure include not finding a unique match or surface occlusion.

[0123] The condition for determining that the matching fails due to the occlusion of the label is that when the visible area or visibility of the label area in all views is less than the preset visibility threshold, a reflow is directly triggered.

[0124] Wherein, visibility = (number of pixels per current face) / (number of reference pixels per pre-stored face).

[0125] S5. When the second photoelectric trigger information recorded by the exit photoelectric sensor is received, photoelectric verification is performed in conjunction with the second photoelectric trigger information. After the photoelectric verification is passed, the master order number and the large package number are output for sorting. The specific steps include the following:

[0126] S51. The exit photoelectric sensor also adopts a through-beam photoelectric sensor. When the exit photoelectric sensor is blocked by a passing cargo box, it receives the second photoelectric trigger signal emitted by the exit photoelectric sensor and generates the second photoelectric trigger information, which includes the current timestamp of the cargo box being removed.

[0127] S52: Control the industrial camera group to acquire images of the current cargo box and obtain a second acquired image;

[0128] S53. Take out the temporary box number that was first stored in the current queue from the head of the first-in-first-out queue. Find and obtain the master order number and package number that are bound to the temporary box number based on the retrieved temporary box number, and use them as sorting information to be output.

[0129] When the exit photoelectric sensor is triggered, the system retrieves the oldest temporary container number from the head of the first-in-first-out queue. This number is then considered the temporary container number for the currently departing container.

[0130] S54. Compare the similarity between the first and second acquired images and calculate the image matching score.

[0131] In one specific implementation, ORB feature points and their feature descriptors are extracted from the first acquired image and the second acquired image;

[0132] Feature point matching is performed using the K-nearest neighbor algorithm, and a ratio test is applied to select high-quality matching pairs. The image matching score is the ratio of the number of high-quality matching pairs to the total number of feature points.

[0133] S55. Calculate the time difference between the removal timestamp in the second photoelectric trigger information and the entry timestamp in the first photoelectric trigger information, and determine whether the time difference is within the preset reasonable time threshold range.

[0134] Calculate the time difference ΔT = T2 - T1, and set a reasonable time threshold range based on the conveyor belt speed and the scanning area length. For example, if the conveyor belt speed is 0.5 m / s, the scanning area length is 2 m, and the theoretical transit time is 4 seconds, a reasonable time threshold range can be set to [3.5, 5] seconds.

[0135] S56. If the image matching score exceeds the preset matching confidence value and the time difference ΔT is within a reasonable time threshold range, the photoelectric verification passes and the sorting information to be output is sent to the logistics distribution system; otherwise, arbitration verification is performed. If the arbitration verification fails, the return operation of the cargo box is triggered.

[0136] In one specific implementation, if the image matching score is lower than the preset matching confidence value, arbitration verification is performed, a backup matching strategy is activated, and visual features of the non-waybill area of ​​the cargo box are extracted for secondary matching.

[0137] Match the current second acquired image with the first acquired images bound to the subsequent temporary container numbers in the first-in-first-out queue;

[0138] If a match is found with the image of the Nth number in the queue, it is inferred that the boxes numbered from the head of the queue to the (N-1)th number are the held boxes, the current exit box is the box with the Nth number, the corresponding sorting information is output and the first-in-first-out queue is updated.

[0139] If the match still does not occur, the arbitration verification fails, triggering the return of the corresponding cargo container.

[0140] In another specific implementation, if ΔT exceeds a preset time threshold, multi-box collisions may occur, triggering arbitration verification.

[0141] Query the collision event record table to determine whether the current temporary cargo container number is recorded in the current collision event record table;

[0142] If the temporary container number is recorded in the collision event, and the time difference between the collision timestamp and the removal timestamp does not exceed the preset collision time tolerance value, the arbitration verification passes, the photoelectric verification is deemed to pass, and the updated sorting information is output; otherwise, the corresponding container return is triggered.

[0143] If the temporary container number is not recorded in the collision event or the time difference between the collision timestamp and the removal timestamp exceeds the preset collision time tolerance value, the arbitration verification will fail, and the photoelectric verification will ultimately be deemed to have failed, triggering a reflow operation.

[0144] In one specific implementation, after the cargo box passes the exit photoelectric sensor, it passes through a camera used to acquire the volume of the cargo box. The camera summarizes the length, width, and height information of the cargo box into the cargo box sorting information, which facilitates the palletizing in the subsequent transportation process.

[0145] S57. Combining the large package number, master order number, and previously obtained large package allocation information and transportation plan from the current cargo box sorting information, allocate transportation for cargo boxes that have successfully passed the verification.

[0146] By using a multi-faceted scanning system to comprehensively capture images of cargo containers, obtaining their barcode and OCR information, and then fusing and matching this information with retrieved flight data, along with photoelectric verification, the accuracy and efficiency of logistics sorting are greatly improved. This avoids the high costs and low efficiency associated with manual intervention and also solves the problems of insufficient information fusion and low automation in existing systems.

[0147] Based on the same inventive concept described above, this application also discloses an intelligent logistics sorting device, such as... Figure 2 As shown, it includes the following modules:

[0148] The information retrieval module is used to retrieve flight information from a pre-established warehouse management system. The flight information includes the master bill of lading number and package number of all cargo containers.

[0149] The image acquisition module is used to control all industrial camera groups to acquire images of the cargo box passing through the entrance photoelectric sensor when it receives the first photoelectric trigger signal from the entrance photoelectric sensor, and to record the first photoelectric trigger information.

[0150] The information fusion and matching module is used to perform barcode decoding and OCR recognition based on the first acquired image, and to fuse and match the obtained barcode decoding information, OCR recognition information and retrieved flight information to obtain the corresponding master order number and package number.

[0151] The photoelectric verification module is used to perform photoelectric verification when it receives the second photoelectric trigger information recorded by the exit photoelectric sensor. After the photoelectric verification is passed, it outputs the master order number and the large package number for sorting.

[0152] In a specific feasible implementation, the information retrieval module includes the following units:

[0153] The first information retrieval unit is used to retrieve the corresponding flight information from the database of the pre-established warehouse management system based on the flight number. The flight information includes the master bill of lading number and the package number of all cargo containers. Each flight includes several master bill of lading numbers, and each master bill of lading number includes several package numbers. Each cargo container has a unique corresponding package number.

[0154] The second information retrieval unit is used to obtain package allocation information and transportation plans from a pre-established logistics allocation system based on the flight number.

[0155] In one specific implementation scheme, the image acquisition module includes the following units:

[0156] The first image acquisition unit is used to make the entrance photoelectric sensor emit a first photoelectric trigger signal when the entrance photoelectric sensor is blocked by a passing cargo box;

[0157] The second image acquisition unit is used to generate a temporary cargo box number and maintain a first-in-first-out queue when it receives the first photoelectric trigger signal. It stores the temporary cargo box number in the first-in-first-out queue and records the first photoelectric trigger information, which includes the temporary cargo box number and the current cargo box entry timestamp.

[0158] The third image acquisition unit is used to control the industrial camera group to continuously acquire images of each side of the cargo box in the scanning area based on the first photoelectric trigger signal, and obtain multiple first acquired images.

[0159] Bind the temporary cargo container number to the first captured image.

[0160] In a specific feasible implementation, the information fusion and matching module includes the following units:

[0161] The first information fusion and matching unit is used to determine whether there is only one cargo box when entering the scanning area based on the first acquired image. If so, the cargo box label is extracted based on the first acquired image to obtain the cargo box label for the current cargo box.

[0162] The second information fusion and matching unit is used to decode the barcode on the cargo container waybill to obtain barcode decoding information and to perform OCR recognition on multiple first-captured images to obtain OCR recognition information. The barcode decoding information includes the master order number, the large package number and the flight number, and the OCR recognition information includes the shipping and receiving addresses and the item description.

[0163] The third information fusion and matching unit is used to extract semantic features from OCR recognition information based on the preset BERT model, calculate the semantic similarity between the semantic features and the preset semantic fields of flight information, filter out the semantic similarity exceeding the semantic matching threshold and summarize them into a candidate matching set.

[0164] The fourth information fusion matching unit is used to extract the structured character data of each flight information from the candidate matching set, calculate the edit distance between the flight information and the corresponding character data in the barcode decoding information using the edit distance matching algorithm, and select the flight information with the smallest edit distance and less than the edit distance threshold as the final matching result.

[0165] The fifth information fusion and matching unit is used to perform a secondary sorting based on semantic similarity if there are multiple data with the same edit distance, and select the record with the highest semantic similarity as the final matching result.

[0166] In one specific implementation scheme, the photoelectric verification module includes the following units:

[0167] The first photoelectric verification unit is used to receive the second photoelectric trigger signal emitted by the exit photoelectric sensor and generate the second photoelectric trigger information when the exit photoelectric sensor is blocked by the passing cargo box. The second photoelectric trigger information includes the current timestamp of the cargo box being removed.

[0168] The second photoelectric verification unit is used to control the industrial camera group to acquire images of the current cargo box and obtain the second acquired image; it retrieves the temporary cargo box number that was stored first in the current queue from the head of the first-in-first-out queue, and finds and obtains the master order number and package number bound to the temporary cargo box number based on the retrieved temporary cargo box number as sorting information to be output.

[0169] The third photoelectric verification unit is used to compare the similarity of the first acquired image and the second acquired image, calculate the image matching score, calculate the time difference between the move-out timestamp in the second photoelectric trigger information and the enter timestamp in the first photoelectric trigger information, and determine whether the time difference is within the preset reasonable time threshold range.

[0170] The fourth photoelectric verification unit is used to verify that if the image matching score exceeds the preset matching confidence value and the time difference ΔT is within a reasonable time threshold range, the photoelectric verification passes and the sorting information to be output is sent to the logistics distribution system; otherwise, arbitration verification is performed, and if the arbitration verification fails, the return operation of the cargo box is triggered.

[0171] In one specific implementation, the device further includes a collision detection module, comprising the following units:

[0172] The first collision detection unit is used to analyze the depth information of multiple first-capture images collected by the industrial camera group in real time. When it is detected that the distance between multiple boxes is continuously lower than the preset distance threshold, it determines that a collision event has occurred between multiple boxes, records the multiple boxes as a collision box group and records the collision timestamp; obtains the temporary box number of all boxes in the collision box group, and records it as the collision number set.

[0173] The second collision detection unit is used to identify and extract the face where the cargo box label is located and the two-dimensional coordinates on the current face from the first acquired image corresponding to each cargo box in the collision number set, and generate a first position fingerprint.

[0174] The third collision detection unit is used to extract the latest frame of the first acquired image after the collision timestamp and before the cargo box group leaves the scanning area, identify and extract the face where the current cargo box label is located and the two-dimensional coordinates on the current face of each cargo box, and generate a second position fingerprint.

[0175] The fourth collision detection unit is used to maintain the collision number set in the first-in-first-out queue and update the first-in-first-out queue according to the matching result if all cargo container waybills are successfully identified and the second position fingerprint has a unique matching relationship with the first position fingerprint; if there is a case where the cargo container waybill cannot be identified or the matching relationship is not unique, the collision number set is removed from the first-in-first-out queue and the return operation of the cargo container group is triggered.

[0176] Based on the same inventive concept described above, this application also discloses a terminal, including a memory and a processor. The memory stores at least one instruction, at least one program, code set, or instruction set. The at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the intelligent logistics sorting method described above.

[0177] Based on the same inventive concept described above, this application also discloses a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the intelligent logistics sorting method described above.

[0178] The steps described in this invention are not necessarily to be performed in the strict order indicated by the reference numerals in the accompanying drawings. The order of the steps may be adjusted, changed, or performed in parallel as needed. Unless the dependencies between steps are explicitly stated (e.g., step S3 requires the result of step S2), the sequence numbers should not be interpreted as a strict restriction on the order.

[0179] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media capable of storing program code.

[0180] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. An intelligent logistics sorting method, characterized in that, Based on a multi-faceted scanning system, the multi-faceted scanning system includes multiple industrial camera groups arranged in a preset scanning area. An inlet photoelectric sensor and an outlet photoelectric sensor are respectively installed at the inlet and outlet of the scanning area. The method includes the following steps: Retrieve flight information from a pre-established warehouse management system, including the master manifest number and package number for all cargo containers; When the first photoelectric trigger signal emitted by the entrance photoelectric sensor is received, all the industrial camera groups are controlled to acquire images of the cargo box passing through the entrance photoelectric sensor to obtain a first acquired image, and the first photoelectric trigger information is recorded. Specifically, When the entrance photoelectric sensor is blocked by the passing cargo box, the entrance photoelectric sensor emits a first photoelectric trigger signal; When the first photoelectric trigger signal is received, a temporary cargo box number is generated for the cargo box and a first-in-first-out queue is maintained. The temporary cargo box number is stored in the first-in-first-out queue and the first photoelectric trigger information is recorded. The first photoelectric trigger information includes the temporary cargo box number and the current cargo box entry timestamp. Based on the first photoelectric trigger signal, the industrial camera group is controlled to continuously acquire images of each side of the cargo box in the scanning area, thereby obtaining multiple first acquired images; Bind the temporary cargo box number to the first acquired image; Based on the first acquired image, barcode decoding and OCR recognition are performed. The obtained barcode decoding information and OCR recognition information are fused and matched with the retrieved flight information to obtain the corresponding master order number and the large package number. When the second photoelectric trigger information recorded by the exit photoelectric sensor is received, photoelectric verification is performed in conjunction with the second photoelectric trigger information. After the photoelectric verification is passed, the master order number and the large package number are output for sorting.

2. The intelligent logistics sorting method according to claim 1, characterized in that, The step of retrieving flight information from a pre-established warehouse management system, including the master manifest number and package number of all cargo containers, specifically includes the following steps: Based on the flight number, the corresponding flight information is retrieved from the database of the pre-established warehouse management system. The flight information includes the master bill of lading number and the package number of all cargo containers. Each flight includes several master bill of lading numbers, and each master bill of lading number includes several package numbers. Each cargo container has a unique corresponding package number. Based on the flight number, obtain package allocation information and transportation plan from the pre-established logistics allocation system.

3. The intelligent logistics sorting method according to claim 1, characterized in that: A spatial coordinate system is established in the scanning area. During image acquisition, the industrial camera group in the scanning area continuously takes high-speed photos of the six sides of the cargo box. The industrial camera group includes industrial cameras located in the positive X-axis, negative X-axis, positive Y-axis, negative Y-axis, positive Z-axis, and negative Z-axis directions of the spatial coordinate system. The industrial camera located in the negative Z-axis direction is a bottom scanning camera. The bottom scanning camera is located below the conveyor belt transporting the cargo box. A reflector is set within the field of view of the bottom scanning camera, and the reflector faces the gap between the two conveyor belts.

4. The intelligent logistics sorting method according to claim 2, characterized in that, The step of performing barcode decoding and OCR recognition based on the first acquired image, and then fusing and matching the obtained barcode decoding information, OCR recognition information, and retrieved flight information to obtain the corresponding master order number and the large package number, specifically includes the following steps: Based on the first acquired image, determine whether there is only one cargo box when entering the scanning area. If so, extract the cargo box label based on the first acquired image to obtain the current cargo box label. The barcode of the cargo container is decoded to obtain barcode decoding information, and multiple first-collected images are OCR recognized to obtain OCR recognition information. The barcode decoding information includes the master order number, the large package number and the flight number, and the OCR recognition information includes the shipping and receiving address and the item description. Based on the preset BERT model, entity extraction is performed on the OCR recognition information to obtain semantic features. The semantic similarity between the semantic features and the preset semantic fields of the flight information is calculated. The semantic similarity values ​​that exceed the semantic matching threshold are filtered and summarized into a candidate matching set. Structured character data of each flight information is extracted from the candidate matching set, and the edit distance matching algorithm is used to calculate the edit distance between the flight information and the corresponding character data in the barcode decoding information. The flight information with the smallest edit distance and less than the edit distance threshold is selected as the final matching result. If multiple records have the same edit distance, then a second sort is performed based on the semantic similarity, and the record with the highest semantic similarity is selected as the final matching result.

5. The intelligent logistics sorting method according to claim 2, characterized in that, When the second photoelectric trigger information recorded by the exit photoelectric sensor is received, photoelectric verification is performed in conjunction with the second photoelectric trigger information, specifically including the following steps: When the exit photoelectric sensor is blocked by the passing cargo box, the system receives the second photoelectric trigger signal emitted by the exit photoelectric sensor and generates the second photoelectric trigger information, which includes the current timestamp of the cargo box being removed. The industrial camera group is controlled to acquire images of the current cargo box, resulting in a second acquired image; Take out the temporary container number that was first stored in the queue from the head of the first-in-first-out queue, and find and obtain the master order number and the large package number that are bound to the temporary container number based on the taken-out temporary container number, as sorting information to be output; The first acquired image and the second acquired image are compared for similarity, and an image matching score is calculated. Calculate the time difference between the removal timestamp in the second photoelectric triggering information and the entry timestamp in the first photoelectric triggering information, and determine whether the time difference is within a preset reasonable time threshold range; If the image matching score exceeds the preset matching confidence value and the time difference ΔT is within the reasonable time threshold range, then the photoelectric verification is passed, and the sorting information to be output is output to the logistics distribution system. Otherwise, an arbitration verification is performed. If the arbitration verification fails, the return operation of the cargo box is triggered.

6. The intelligent logistics sorting method according to claim 4, characterized in that, After continuously acquiring multiple first images from each side of the cargo box, the following steps are also included: The depth information of multiple first-captured images acquired by the industrial camera group is analyzed in real time. When the distance between multiple cargo boxes is continuously lower than a preset distance threshold, it is determined that a collision event has occurred between the multiple cargo boxes. The multiple cargo boxes are recorded as a collision cargo box group and the collision timestamp is recorded. Obtain the temporary container numbers of all containers in the collision container group, and denote them as the collision number set; For each cargo box in the collision number set, the face where the cargo box label is located and its two-dimensional coordinates on the current face are identified and extracted from the first acquired image corresponding to the cargo box, and a first position fingerprint is generated; Extract the latest frame of the first acquired image after the collision timestamp and before the cargo box group leaves the scanning area, identify and extract the face of the current cargo box label of each cargo box and the two-dimensional coordinates on the current face, and generate a second position fingerprint; If all the cargo container labels are successfully identified and the second location fingerprint has a unique match with the first location fingerprint, the collision number set in the first-in-first-out queue is maintained, and the first-in-first-out queue is updated according to the matching result. If there is a situation where the cargo container waybill cannot be identified or the matching relationship is not unique, the collision number set will be removed from the first-in-first-out queue, and the return operation of the cargo container group will be triggered.

7. An intelligent logistics sorting device, characterized in that, Based on the intelligent logistics sorting method according to claim 1, the device includes the following modules: The information retrieval module is used to retrieve flight information from a pre-established warehouse management system. The flight information includes the master bill of lading number and package number of all cargo containers. The image acquisition module is used to control all industrial camera groups to acquire images of the cargo box passing through the entrance photoelectric sensor when a first photoelectric trigger signal is received from the entrance photoelectric sensor, and to record the first photoelectric trigger information. Specifically, when the entrance photoelectric sensor is blocked by the passing cargo box, the entrance photoelectric sensor emits the first photoelectric trigger signal; when the first photoelectric trigger signal is received, a temporary cargo box number is generated and a first-in-first-out queue is maintained. The temporary cargo box number is stored in the first-in-first-out queue and the first photoelectric trigger information is recorded, including the temporary cargo box number and the current cargo box entry timestamp; based on the first photoelectric trigger signal, the industrial camera groups are controlled to continuously acquire images of each side of the cargo box in the scanning area to obtain multiple first acquired images; the temporary cargo box number is bound to the first acquired images. The information fusion and matching module is used to perform barcode decoding and OCR recognition based on the first acquired image, and to fuse and match the obtained barcode decoding information, OCR recognition information and the retrieved flight information to obtain the corresponding master order number and the large package number; The photoelectric verification module is used to perform photoelectric verification in conjunction with the second photoelectric trigger information recorded by the exit photoelectric sensor when it receives the second photoelectric trigger information. After the photoelectric verification is passed, the main order number and the large package number are output for sorting.

8. A terminal, characterized in that, The system includes a memory and a processor, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the intelligent logistics sorting method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The readable storage medium stores at least one instruction, at least one program, code set, or instruction set, which is loaded and executed by a processor to implement the intelligent logistics sorting method as described in any one of claims 1 to 6.

Images