Logistics distribution handover management method and device, equipment and storage medium

Abstract

The invention relates to the technical field of logistics, in particular to a logistics distribution handover management method, device and equipment and a storage medium. The logistics distribution handover management method comprises the following steps: predicting a cargo handover list by using a risk prediction model to obtain an error risk, and outputting an alarm according to the error risk; comparing the cargo handover list with the loading cargo list, outputting a first comparison result, and binding the bar code of the to-be-loaded cargo with the carrier vehicle information; comparing the unloaded cargo list with the loaded cargo list, outputting a second comparison result, and adopting a preset responsibility judgment rule to judge an error responsibility party according to the second comparison result; and outputting a processing method to the responsible party by adopting a preset error processing rule according to an error condition in the second comparison result. According to the invention, full-link monitoring and early warning are carried out on loading and unloading links in logistics, errors in a cargo handover process can be effectively reduced, and the logistics efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of logistics technology, and in particular to a logistics distribution and handover management method, apparatus, equipment, and storage medium. Background Technology

[0002] Against the backdrop of rapid e-commerce development and exponential growth in logistics volume, the efficiency and management accuracy of cargo handover between distribution centers in the logistics network directly affect the smoothness of the entire logistics chain and cost control. Due to the lack of objective, real-time, and closed-loop data records, when discrepancies occur during handover, liability determination often relies on the recollections and evidence presented by each party, a process rife with subjective assumptions and finger-pointing. This leads to difficulties in assigning responsibility, lengthy dispute resolution cycles, increased management and coordination costs for enterprises, and directly higher expenses for abnormal claims due to the unclear definition of liability. Discrepancies in cargo quantity (such as shortages or excesses) typically only become apparent through manual inventory checks after all unloading operations are completed, or even later in the process. This process heavily relies on manual verification, resulting in low efficiency and a high error rate, failing to enable real-time detection and on-site intervention for anomalies, and missing optimal remedial opportunities. Furthermore, the lack of statistical data means that targeted measures have not been developed for many recurring error-prone stages, leading to frequent problems. Summary of the Invention

[0003] In view of the shortcomings of the prior art, the purpose of this invention is to provide a logistics distribution and handover management method, device, equipment and storage medium, which aims to solve the technical problems in the prior art where it is difficult to quickly identify the responsible party for errors in the goods handover process of logistics distribution centers, and where some nodes repeatedly make mistakes that are difficult to eliminate.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of this invention provides a logistics distribution and handover management method, comprising the following steps: obtaining a goods handover list; using a risk prediction model to predict the goods handover list to obtain error risks; and outputting warnings based on the error risks; obtaining barcodes of all goods to be loaded to form a loading goods list; comparing the goods handover list with the loading goods list to output a first comparison result; and binding the barcodes of the goods to be loaded with the carrier vehicle information; obtaining barcodes of all goods to be unloaded to form an unloading goods list; comparing the unloading goods list with the loading goods list to output a second comparison result; using preset responsibility determination rules to determine the party responsible for the error based on the second comparison result; and using preset error handling rules to output a handling method to the responsible party based on the error situation in the second comparison result.

[0005] Optionally, in a first implementation of the first aspect of the present invention, the step of obtaining the goods handover list and using a risk prediction model to predict the goods handover list to obtain error risks, and outputting warnings based on the error risks, specifically includes: obtaining historical goods handover data, which includes information on the shipping distribution center and personnel, information on the carrier vehicles and personnel, information on the receiving distribution center and personnel, shipping time, receiving time, and handover error records; cleaning the historical goods handover data and extracting key features to form a dataset; constructing a risk prediction model based on the XGBoost algorithm and training the XGBoost algorithm using the dataset; using the risk prediction model to predict the goods handover list to obtain error risks, and outputting warnings based on the error risks.

[0006] Optionally, in the second implementation of the first aspect of the present invention, the step of cleaning historical cargo handover data and extracting key features to form a dataset specifically includes: cleaning historical cargo handover data to obtain preprocessed data; using the LightGBM algorithm to select features with a high correlation to errors from the preprocessed data and sorting the features according to their weights; selecting features with weights greater than a preset threshold as key features according to a preset threshold, and forming a dataset based on the key features.

[0007] Optionally, in a third implementation of the first aspect of the present invention, the step of using a risk prediction model to predict the goods handover list to obtain error risks and outputting warnings based on the error risks specifically includes: using a risk prediction model to predict the goods handover list to obtain error risks, wherein the error risks include multiple predicted error nodes and their error risk probabilities; constructing error prevention rules, formulating preventive measures based on historical error nodes, and periodically collecting feedback data to optimize the preventive measures; and matching the predicted error nodes with the error prevention rules to obtain preventive measure suggestions corresponding to the predicted error nodes.

[0008] Optionally, in the fourth implementation of the first aspect of the present invention, the step of obtaining all barcodes of goods to be loaded, forming a loading goods list, comparing the goods handover list with the loading goods list, outputting a first comparison result, and binding the barcodes of goods to be loaded with the carrier vehicle information specifically includes: obtaining all barcodes of goods to be loaded, verifying the validity of the barcodes of goods to be loaded, forming a loading goods list from all the verified barcodes of goods to be loaded; comparing the goods handover list with the loading goods list, outputting a first comparison result; binding the barcodes of goods to be loaded with the carrier vehicle information, obtaining the delivery address of the goods based on the barcodes of the goods to be loaded, and determining whether the goods match the transportation plan of the carrier vehicle based on the delivery address, and outputting a matching result.

[0009] Optionally, in the fifth implementation of the first aspect of the present invention, the step of binding the barcode of the goods to be loaded with the information of the carrier vehicle, obtaining the delivery address of the goods based on the barcode of the goods to be loaded, and determining whether the transportation plan of the goods matches the transportation plan of the carrier vehicle based on the delivery address, and outputting the matching result, specifically includes: binding the barcode of the goods to be loaded with the information of the carrier vehicle, obtaining the delivery address of the goods based on the barcode of the goods to be loaded; using a pre-built route generation algorithm to generate a predicted transportation route based on the address of the shipping distribution center and the delivery address of the goods, wherein the predicted transportation route includes multiple predicted transit nodes; obtaining the vehicle transportation plan based on the carrier vehicle information, extracting the transportation nodes in the vehicle transportation plan; comparing the transportation nodes in the vehicle transportation plan with multiple predicted transit nodes to determine whether there are overlapping nodes, and outputting the judgment result.

[0010] Optionally, in the sixth implementation of the first aspect of the present invention, the step of adopting a preset error handling rule and outputting a processing method to the responsible party based on the error situation in the second comparison result specifically includes: setting error handling rules; for the error situation of extra goods, obtaining the delivery address of the goods according to the goods barcode, rescheduling the delivery plan, and sending a prompt message to the dispatching distribution center and transportation personnel; for the error situation of missing goods, sending a prompt message to the dispatching distribution center and transportation personnel; and using the preset error handling rule to output a processing method to the responsible party based on the error situation in the second comparison result.

[0011] A second aspect of the present invention provides a logistics distribution and handover management device, comprising: a risk prediction module for acquiring a goods handover list, using a risk prediction model to predict the goods handover list to obtain error risks, and outputting warnings based on the error risks; a first comparison module for acquiring all barcodes of goods to be loaded, forming a loading goods list, comparing the goods handover list with the loading goods list, outputting a first comparison result, and binding the barcodes of goods to be loaded with the carrier vehicle information; a second comparison module for acquiring all barcodes of goods to be unloaded, forming an unloading goods list, comparing the unloading goods list with the loading goods list, outputting a second comparison result, and using preset responsibility determination rules to determine the party responsible for the error based on the second comparison result; and a processing module for using preset error handling rules to output a processing method to the responsible party based on the error situation in the second comparison result.

[0012] Optionally, in the first implementation of the second aspect of the present invention, the risk prediction module includes: a data acquisition unit, used to acquire historical cargo handover data, the historical cargo handover data including information on dispatching and distribution centers and personnel, information on carrier vehicles and personnel, information on receiving and distribution centers and personnel, dispatch time, receiving time, and handover error records; a feature unit, used to clean the historical cargo handover data and extract key features to form a dataset; a construction unit, used to construct a risk prediction model based on the XGBoost algorithm, using the dataset to train the XGBoost algorithm; and a prediction unit, used to use the risk prediction model to predict the cargo handover list to obtain error risks, and output warnings based on the error risks.

[0013] Optionally, in a second implementation of the second aspect of the present invention, the feature unit includes: a cleaning subunit, used to clean historical cargo handover data to obtain preprocessed data; a filtering subunit, used to use the LightGBM algorithm to filter out features with high correlation to errors from the preprocessed data and sort the features according to their weights; and a selection subunit, used to select features with weights greater than a preset threshold as key features and form a dataset based on the key features.

[0014] Optionally, in a third implementation of the second aspect of the present invention, the prediction unit includes: a prediction subunit, used to use a risk prediction model to predict the goods handover list to obtain error risks, wherein the error risks include multiple predicted error nodes and their error risk probabilities; an optimization subunit, used to construct error prevention rules, formulate preventive measures according to historical error nodes, and periodically collect feedback data to optimize the preventive measures; and a matching subunit, used to match the predicted error nodes with the error prevention rules to obtain preventive measure suggestions corresponding to the predicted error nodes.

[0015] Optionally, in a fourth implementation of the second aspect of the present invention, the first comparison module includes: an inspection unit, configured to acquire all barcodes of goods to be loaded, inspect the validity of the barcodes of goods to be loaded, and form a loading goods list from all qualified barcodes of goods to be loaded; a comparison unit, configured to compare the goods handover list with the loading goods list and output a first comparison result; and a judgment unit, configured to bind the barcodes of goods to be loaded with the information of the carrier vehicle, acquire the delivery address of the goods based on the barcodes of the goods to be loaded, and determine whether the goods match the transportation plan of the carrier vehicle based on the delivery address, and output a matching result.

[0016] Optionally, in a fifth implementation of the second aspect of the present invention, the judgment unit includes: a binding subunit, used to bind the barcode of the goods to be loaded to the information of the carrier vehicle, and obtain the delivery address of the goods based on the barcode of the goods to be loaded; a generation subunit, used to generate a predicted transportation route based on the address of the shipping distribution center and the delivery address of the goods using a pre-built route generation algorithm, wherein the predicted transportation route includes multiple predicted transit nodes; an extraction subunit, used to obtain the vehicle transportation plan based on the information of the carrier vehicle, and extract the transportation nodes in the vehicle transportation plan; and a judgment subunit, used to compare the transportation nodes in the vehicle transportation plan with the multiple predicted transit nodes to determine whether there are overlapping nodes, and output the judgment result.

[0017] Optionally, in a sixth implementation of the second aspect of the present invention, the processing module includes: a setting unit, configured to set error handling rules, and in the event of an error involving extra goods, obtain the delivery address of the goods based on the goods barcode, rearrange the delivery plan, and send a notification message to the dispatching distribution center and the transportation personnel; a notification unit, configured to send a notification message to the dispatching distribution center and the transportation personnel in the event of an error involving missing goods; and a processing unit, configured to use preset error handling rules to output a processing method to the responsible party based on the error in the second comparison result.

[0018] A third aspect of the present invention provides a logistics distribution and handover management device, including a memory and at least one processor, wherein the memory stores computer-readable instructions; the at least one processor invokes the computer-readable instructions in the memory to execute the various steps of the logistics distribution and handover management method described above.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the various steps of the logistics distribution and handover management method described above.

[0020] Beneficial Effects: This invention provides a logistics distribution and handover management method. The method first obtains a goods handover list and uses a risk prediction model to predict the error risk based on this list. Warnings are then issued based on the error risk, thus preventing potential errors in advance and reducing the probability of early-stage errors. Next, by obtaining the barcodes of all goods to be loaded, a loading list is formed. The goods handover list is compared with the loading list, and a first comparison result is output. This automatic comparison before shipment reduces shipping errors, and the barcodes of the goods to be loaded are bound to the carrier vehicle information. Next, by acquiring the barcodes of all unloaded goods, an unloaded goods list is generated. This list is then compared with the loading goods list, and a second comparison result is output. By also comparing the results at the receiving end, operational standards and automatic data acquisition are ensured, facilitating rapid determination of responsibility for errors. Subsequently, preset responsibility determination rules are used to determine the responsible party based on the second comparison result, resulting in automatic responsibility assessment and significantly shortening the dispute resolution cycle. Finally, by employing preset error handling rules, based on the error situation in the second comparison result, a handling method is output to the responsible party to quickly resolve the error and improve overall operational efficiency. Attached Figure Description

[0021] Figure 1 This is a first flowchart of a logistics distribution and handover management method provided in an embodiment of the present invention; Figure 2 This is a second flowchart of the logistics distribution and handover management method provided in an embodiment of the present invention; Figure 3 This is a third flowchart of the logistics distribution and handover management method provided in an embodiment of the present invention; Figure 4 This is a fourth flowchart of the logistics distribution and handover management method provided in this embodiment of the invention; Figure 5 A fifth flowchart of the logistics distribution and handover management method provided in this embodiment of the invention; Figure 6 The sixth flowchart of the logistics distribution and handover management method provided in the embodiments of the present invention; Figure 7 The seventh flowchart of the logistics distribution and handover management method provided in the embodiments of the present invention; Figure 8 A schematic diagram of a logistics distribution and handover management device provided in an embodiment of the present invention; Figure 9 This is another structural schematic diagram of the logistics distribution and handover management device provided in an embodiment of the present invention; Figure 10 A schematic diagram of the structure of the logistics distribution and handover management equipment provided in an embodiment of the present invention. Detailed Implementation

[0022] This invention provides a method, apparatus, equipment, and storage medium for logistics distribution and handover management. First, the invention acquires a goods handover list, analyzes it using a risk prediction model to determine the error risk level, and simultaneously outputs warning information, thereby preventing potential errors and reducing the probability of early operational mistakes. Then, it collects barcodes of all goods to be loaded to generate a loading goods list, automatically compares it with the goods handover list, and outputs the first comparison result, reducing errors in the shipping process and simultaneously binding the barcodes of goods to be loaded with the carrier vehicle information. Next, it acquires barcodes of all goods to be unloaded to form an unloading goods list, compares it with the loading goods list, and outputs the second comparison result. This dual verification at the receiving end ensures standardized operation and automatic data collection, providing a basis for rapid liability determination. Then, based on preset liability determination rules and the second comparison result, it determines the party responsible for the error, achieving automatic liability determination to shorten the dispute resolution cycle. Finally, based on preset error handling rules, it outputs corresponding handling solutions to the responsible party for specific errors in the second comparison result, quickly resolving errors and improving the overall efficiency of logistics distribution and handover operations.

[0023] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 The first embodiment of the logistics distribution and handover management method in this invention includes: S101. Obtain the goods handover list, use a risk prediction model to predict the goods handover list to obtain the error risk, and output a warning based on the error risk; S102. Obtain all barcodes of goods to be loaded, form a loading list, compare the goods handover list with the loading list, output the first comparison result, and bind the barcodes of goods to be loaded with the carrier vehicle information; S103. Obtain all unloaded goods barcodes, form an unloaded goods list, compare the unloaded goods list with the loaded goods list, output the second comparison result, and use the preset responsibility determination rules to determine the party responsible for the error based on the second comparison result; S104. Using preset error handling rules, output the handling method to the responsible party based on the error situation in the second comparison result.

[0025] In this embodiment, to reduce the occurrence of errors, a risk prediction model is used to predict the upcoming goods handover scenario. The goods handover list details the handover time, quantity, type of goods, and related information such as the personnel involved. The risk prediction model predicts the probability of errors based on the contents of the goods handover list. For example, the risk of errors is high when the quantity of goods is large; the risk of errors is high when the proportion of small-volume goods is high; and the risk of errors is high when goods are shipped and handed over at night or in the early morning. Based on the predictions provided by the risk prediction model, managers can make timely personnel adjustments, increase supervision and assistance for the shift, and reduce the occurrence of errors.

[0026] During the loading process, in addition to obtaining the cargo handover list, the system also needs to obtain the barcodes of all goods to be loaded to form a loading cargo list. Through this step, operators are required to scan each item to be loaded to check whether the goods are complete. If there are any shortages or excesses, they will be recorded in the first comparison result, allowing operators to identify problems in a timely manner. All barcodes of goods to be loaded will eventually be linked to the carrier vehicle information to form a traceability system for the transportation process, in case any goods are lost during transportation.

[0027] In the unloading process at the distribution center, the system needs to acquire all unloaded goods barcodes to form an unloading goods list. By comparing the unloading goods list with the loading goods list, it can provide real-time alerts for "excess" or "short" goods, quickly and accurately outputting "short" and "excess" lists. If errors occur after the loading process has been completed and confirmed, it may indicate problems in the transportation process, or errors or omissions during unloading scanning. Specifically, business rules can be translated into computer-executable logic. These rules include: Rule 1: Goods on the "loading list" but not on the "unloading list" are defined as "short." If unloading is missed at the unloading distribution center, the responsible party is the unloading distribution center; if loading scanning was performed at the loading distribution center but the goods were not actually loaded, the responsible party is the loading distribution center. Rule 2: Goods not on the "loading list" but appearing on the "unloading list" are defined as "excess." If loading is missed at the loading distribution center, the responsible party is the loading distribution center. Rule 3: If the tracking number barcode cannot be scanned, the responsible party is "Distribution Center A" (determined to be due to damaged label or missing header). Distribution Center A is the shipping distribution center A.

[0028] After quickly identifying the responsible party, this embodiment automatically generates corresponding solutions for the responsible party and the point of error to improve efficiency. This reduces the overall time spent on investigation, communication, and follow-up.

[0029] Please see Figure 2 The second embodiment of the logistics distribution and handover management method in this invention includes: S201. Obtain historical cargo handover data, which includes information on dispatching and distribution centers and personnel, information on carrier vehicles and personnel, information on receiving and distribution centers and personnel, dispatch time, receiving time, and handover error records; S202. Clean the historical cargo handover data and extract key features to form a dataset; S203. Construct a risk prediction model based on the XGBoost algorithm and train the XGBoost algorithm using a dataset. S204. Use a risk prediction model to predict the cargo handover list in order to obtain the error risk, and output warnings based on the error risk.

[0030] In this embodiment, to ensure the reliability of the output results after model training, the collection of raw data must cover key information of the handover scenario. Input feature-related data includes: personnel information of all parties, types of goods handed over, handover time, handover location (e.g., transport vehicle, shipping distribution center, receiving distribution center), and historical handover records. Output label-related data clearly defines the result of each handover record, indicating whether there was an error and the type of error, serving as labels for model learning. To improve model performance, the data also needs to be cleaned, and the most useful features for risk prediction extracted and filtered. For example, if shipping time, receiving time, and personnel information are highly influential factors, they are included as key features.

[0031] The processed dataset is divided into three categories for model training, parameter tuning, and performance validation, respectively, to ensure the model's generalization ability. Specifically, 70% of the dataset can be selected as the training set, 15% as the validation set, and 15% as the test set.

[0032] When building risk prediction models, the XGBoost algorithm can more accurately capture the complex patterns of risk scenarios and handle various problems with real-world data. In handover error risk prediction scenarios, the patterns of error occurrence are often not simple linear relationships but are related to multiple different factors, and the characteristics of the XGBoost algorithm can effectively deal with such complex patterns.

[0033] After building the risk prediction model, inputting the goods handover list into it will yield error risk prediction results. When outputting error risk results, the risk prediction model will provide the error probability and its cause for different error types. Based on historical data, the model will capture common characteristics of error scenarios to provide prediction results. When the error risk probability is too high, the system will issue a warning to the relevant management personnel.

[0034] Please see Figure 3 The third embodiment of the logistics distribution and handover management method in this invention includes: S301. Clean the historical cargo handover data to obtain preprocessed data; S302. The LightGBM algorithm is used to select features with a high correlation to errors from the preprocessed data and sort the features according to their weights. S303. Based on a preset threshold, select features with weights greater than the threshold as key features, and form a dataset using the key features.

[0035] In this embodiment, in order to eliminate redundant features and select the core factors that truly affect handover errors from multiple original features, and to avoid noise features interfering with model learning, the feature importance quantification mechanism of the LightGBM algorithm is used to deeply explore the intrinsic relationship between each feature and the "handover error" result. With feature contribution (weight) as the core indicator, the core factors that truly drive handover risk are accurately identified and selected, effectively eliminating meaningless redundant features and interfering noise features, avoiding irrelevant information from misleading model learning, and allowing the subsequent risk prediction model to focus on high-value feature dimensions, thus consolidating the foundation for prediction accuracy.

[0036] By eliminating redundant features to achieve reasonable simplification of feature dimensions, the amount of training data and computational complexity of subsequent risk prediction models are significantly reduced. This not only significantly shortens the model training cycle and reduces resource consumption caused by redundant computation, but also improves the efficiency of model iteration and optimization, facilitating rapid model deployment and parameter tuning. Furthermore, high-dimensional redundant features can easily lead to the model overlearning local noise in historical data rather than core risk patterns. Simplifying dimensions through feature selection effectively constrains model complexity, reduces the risk of overfitting, and allows the model to focus more on learning the general patterns between features and cross-risks.

[0037] LightGBM's output feature weights clearly quantify the impact of each factor on handover errors and clarify the priority ranking of core risk factors. This not only provides an objective and quantifiable basis for key feature selection but also provides precise guidance for subsequent business process optimization (such as targeted control of high-weight risk factors).

[0038] Please see Figure 4 The fourth embodiment of the logistics distribution and handover management method in this invention includes: S401. A risk prediction model is used to predict the goods handover list in order to obtain the error risk, wherein the error risk includes multiple predicted error nodes and their error risk probabilities; S402. Build error prevention rules, formulate preventive measures based on historical error nodes, and collect feedback data regularly to optimize preventive measures; S403. Match the predicted error nodes with the error prevention rules to obtain the corresponding preventive measures suggestions for the predicted error nodes.

[0039] In this embodiment, the risk prediction model calculates the potential error risks and possible causes during shift handover based on historical data. For example, the error risk probability at the shipping and distribution center is 25%, which may be caused by employee A working the night shift; the error risk probability in the transportation process is 5%, which may be caused by the night shift; and the error risk probability in the transportation process is 10%, which may be caused by the night shift. The direct indication that employee A is a likely cause of errors suggests a strong correlation between employee A and the occurrence of errors in historical data.

[0040] Once error risks are predicted using risk prediction models, managers can develop targeted remedial measures. For example, if employee A has a high error rate during the night shift, shift adjustments can reduce the problem. Similarly, if a shift carries many small-volume items, increasing the risk of errors, additional staff can be added for inspection and handling. Regularly collecting data after implementing these measures, and monitoring whether the error risk probability or the recent number of errors has decreased, reflects the effectiveness of the measures and allows for continuous optimization of preventative measures.

[0041] Furthermore, to enhance management automation, the system in this embodiment can automatically provide preventative measures. By pre-determining error prevention rules, when the error risk probability of a certain node exceeds a threshold, corresponding suggestions are directly output. For example, if the error risk probability of the distribution center exceeds the threshold, and the possible cause is employee A working the night shift, then a suggestion to adjust employee A's shift schedule is output.

[0042] Please see Figure 5 The fifth embodiment of the logistics distribution and handover management method in this invention includes: S501. Obtain all barcodes of goods to be loaded, verify the validity of the barcodes, and generate a loading list of all qualified barcodes. S502. Compare the goods handover list with the loading goods list and output the first comparison result; S503. Bind the barcode of the goods to be loaded to the information of the carrier vehicle, obtain the delivery address of the goods based on the barcode of the goods to be loaded, and determine whether the transportation plan of the goods and the carrier vehicle matches based on the delivery address, and output the matching result.

[0043] When obtaining barcodes for goods to be loaded, operators use handheld barcode scanners, fixed barcode recognition devices, or mobile terminals to scan the unique identification barcodes on the outer packaging of each item.

[0044] In this embodiment, the validity check of the barcodes for goods to be loaded includes verifying the correct number of digits and format. Any blank or invalid barcodes are displayed in the first comparison result. Based on the company's preset barcode rules, the system determines whether the number of digits obtained from the scan meets the standard. For example, if the company specifies that the logistics traceability code is 18 digits, the system automatically intercepts barcodes with "number of digits ≠ 18" and deems them invalid. Format verification: The system checks whether the barcode's character format conforms to the rules, including "character type" (e.g., whether it contains only numbers, or allows letter + number combinations) and "character constraints at specific positions" (e.g., the 7th digit is fixed as "0" for regular goods, "1" for special cold chain goods, and "2" for incorrect format). Finally, the system automatically generates a structured loading list from all the verified barcodes in the scanning order, containing various key information. The goods handover list generated by the system serves as the benchmark for determining whether the goods are complete. If all barcodes in the loading list can be found in the goods handover list with completely matching records, they are marked as "matched and qualified." If any content is missing or extra, a notification will be displayed in the first comparison result.

[0045] Next, the barcode of the goods to be loaded is linked to the information of the transport vehicle to solve the problem of mismatch between goods and vehicles. By linking and verifying the goods information with the vehicle's travel plan, it is ensured that the "destination" or transit point of the goods to be loaded matches the "transportation route" of the transport vehicle, fundamentally preventing goods from being loaded into the wrong vehicle.

[0046] Please see Figure 6 The sixth embodiment of the logistics distribution and handover management method in this invention includes: S601. Bind the barcode of the goods to be loaded to the information of the carrier vehicle, and obtain the delivery address of the goods based on the barcode of the goods to be loaded; S602. A pre-built route generation algorithm is used to generate a predicted transportation route based on the address of the shipping distribution center and the delivery address of the goods. The predicted transportation route includes multiple predicted nodes. S603. Obtain the vehicle transportation plan based on the carrier vehicle information, and extract the transportation nodes in the vehicle transportation plan; S604. Compare the transportation nodes in the vehicle transportation plan with multiple predicted route nodes to determine if there are any overlapping nodes, and output the judgment result.

[0047] In this embodiment, by matching the expected transportation route of the goods with the transportation plan of the carrier vehicle, it can be determined whether the goods have been loaded onto the wrong vehicle. Specifically, the route generation algorithm in the system is constructed based on the layout of the enterprise's distribution centers and the enterprise's internal habitual transportation route planning. After obtaining the delivery address of the goods, the system generates its subsequent expected transportation route based on the current location of the goods. The expected transportation route will include multiple predicted transit nodes, such as passing through distribution center A and distribution center B. The system also has carrier vehicle information, including the vehicle transportation plan for this shipment. If the vehicle transportation plan includes distribution center A or distribution center B, it means that the vehicle will pass through distribution center A or distribution center B for loading and unloading, which matches the transit nodes of the goods, so it is considered that there is no wrong loading. Through this embodiment, route deviations can be detected before loading, avoiding the discovery of incorrect goods allocation at the next node. This is especially beneficial for time-sensitive or fragile goods such as fresh produce and home appliances, significantly reducing customer complaints or goods losses caused by delays. This also helps avoid occasional errors in cargo loading and allocation within the system.

[0048] Please see Figure 7 The seventh embodiment of the logistics distribution and handover management method in this invention includes: S701. Set error handling rules. In the event of an error involving multiple shipments, obtain the delivery address of the goods based on the goods barcode, reschedule the delivery plan, and send a notification message to the distribution center and transportation personnel. S702. In the event of a shortage of goods, a notification message shall be sent to the distribution center and transportation personnel at the point of shipment; S703. Using preset error handling rules, based on the error situation in the second comparison result, output the handling method to the responsible party.

[0049] In this embodiment, when an error occurs during the receiving process, i.e., the second comparison result shows that the unloading goods list and the loading goods list do not completely match, the system matches the various situations according to preset error handling rules and directly outputs the handling method. Specifically, for the error of extra goods, the second comparison result lists the extra goods, and the responsibility will be attributed to the dispatching distribution center. The dispatching distribution center will be notified, and at the same time, the system will reschedule the wrongly dispatched goods for delivery and send them directly from the receiving distribution center, without returning the process to the responsible party, thus reducing the goods transportation time.

[0050] When an error occurs where goods are missing, the second comparison result lists the list of missing goods, and a prompt message is sent to the distribution center and the transportation personnel for shipping. For this situation, since the previous distribution center has confirmed that there are no errors during loading, the responsibility will be attributed to the transportation link. Additionally, for cases where incomplete matching occurs due to unclear barcodes or inability to scan the barcodes, the second comparison result will also indicate which goods' barcodes have not been recognized, along with a note on the accurate quantity of goods. In this case, the responsibility will also be attributed to the transportation link, and there may be problems with the goods' packaging being damaged during transportation.

[0051] Through the preset error handling rules, the system can automatically determine responsibility and provide problem prompts for different situations, reducing communication costs and outputting judgment data information with clear responsible parties without manual intervention.

[0052] The above described the logistics distribution transfer management method in the embodiments of the present invention. Next, the logistics distribution transfer management device in the embodiments of the present invention will be described. Please refer to Figure 8 , an embodiment of the logistics distribution transfer management device in the embodiments of the present invention includes: A risk prediction module 10, configured to obtain a goods transfer list, use a risk prediction model to predict the goods transfer list to obtain an error risk, and output a warning according to the error risk; A first comparison module 20, configured to obtain all barcodes of goods to be loaded, form a list of goods to be loaded onto the vehicle, compare the goods transfer list with the list of goods to be loaded onto the vehicle, output a first comparison result, and bind the barcodes of the goods to be loaded with the information of the carrier vehicle; A second comparison module 30, configured to obtain all barcodes of goods unloaded from the vehicle, form a list of goods unloaded from the vehicle, compare the list of goods unloaded from the vehicle with the list of goods to be loaded onto the vehicle, output a second comparison result, and use a preset responsibility determination rule to determine the responsible party for the error according to the second comparison result; A processing module 40, configured to use a preset error handling rule to output a processing method to the responsible party according to the error situation in the second comparison result.

[0053] Please refer to Figure 9 , an embodiment of the logistics distribution transfer management device in the embodiments of the present invention includes: A risk prediction module 10, configured to obtain a goods transfer list, use a risk prediction model to predict the goods transfer list to obtain an error risk, and output a warning according to the error risk; A first comparison module 20, configured to obtain all barcodes of goods to be loaded, form a list of goods to be loaded onto the vehicle, compare the goods transfer list with the list of goods to be loaded onto the vehicle, output a first comparison result, and bind the barcodes of the goods to be loaded with the information of the carrier vehicle; The second comparison module 30 is used to acquire all unloaded goods barcodes, form an unloaded goods list, compare the unloaded goods list with the loaded goods list, output the second comparison result, and use preset responsibility determination rules to determine the party responsible for the error based on the second comparison result. The processing module 40 is used to output a processing method to the responsible party based on the error situation in the second comparison result, according to the preset error handling rules. In this embodiment, the risk prediction module 10 includes: Data acquisition unit 11 is used to acquire historical cargo handover data, which includes information on the dispatching and distribution center and personnel, information on the carrier vehicle and personnel, information on the receiving and distribution center and personnel, dispatch time, receiving time, and handover error records. Feature unit 12 is used to clean historical cargo handover data and extract key features to form a dataset; Building unit 13 is used to build a risk prediction model based on the XGBoost algorithm, using a dataset to train the XGBoost algorithm. Prediction unit 14 is used to use a risk prediction model to predict the goods handover list in order to obtain the error risk, and output a warning based on the error risk; In this embodiment, the feature unit 12 includes: The cleaning subunit 121 is used to clean historical cargo handover data to obtain preprocessed data. The filtering subunit 122 is used to use the LightGBM algorithm to filter out features that are highly correlated with errors from the preprocessed data and sort the features according to their weights. Select subunit 123, which is used to select features with weights greater than a preset threshold as key features, and form a dataset with the key features; In this embodiment, the prediction unit 14 includes: The prediction subunit 141 is used to use a risk prediction model to predict the goods handover list in order to obtain the error risk, which includes multiple prediction error nodes and their error risk probabilities. The optimization subunit 142 is used to build error prevention rules, formulate preventive measures according to historical error nodes, and collect feedback data regularly to optimize the preventive measures. Matching subunit 143 is used to match the predicted error node with the error prevention rule to obtain the corresponding prevention measure suggestion for the predicted error node; In this embodiment, the first comparison module 20 includes: Inspection unit 21 is used to acquire all barcodes of goods to be loaded, inspect the validity of the barcodes of goods to be loaded, and form a loading list of all qualified barcodes of goods to be loaded. Comparison unit 22 is used to compare the goods handover list with the loading goods list and output the first comparison result; Judgment unit 23 is used to bind the barcode of the goods to be loaded to the information of the carrier vehicle, obtain the delivery address of the goods based on the barcode of the goods to be loaded, and determine whether the transportation plan of the goods and the carrier vehicle matches based on the delivery address, and output the matching result. In this embodiment, the determination unit 23 includes: Binding subunit 231 is used to bind the barcode of the goods to be loaded to the information of the carrier vehicle, and to obtain the delivery address of the goods based on the barcode of the goods to be loaded; The generation subunit 232 is used to generate a predicted transportation route based on the address of the shipping distribution center and the delivery address of the goods using a pre-built route generation algorithm. The predicted transportation route includes multiple predicted transit nodes. Extraction subunit 233 is used to obtain the vehicle transportation plan based on the carrier vehicle information and extract the transportation nodes in the vehicle transportation plan; The judgment subunit 234 is used to compare the transportation nodes in the vehicle transportation plan with multiple predicted route nodes to determine whether there are overlapping nodes and output the judgment result. In this embodiment, the processing module 40 includes: Setting unit 41 is used to set error handling rules. In the event of an error where multiple goods are shipped, the delivery address of the goods is obtained based on the goods barcode, the delivery plan is rearranged, and a prompt message is sent to the distribution center and transportation personnel. The notification unit 42 is used to send notification information to the distribution center and transportation personnel in case of a shortage of goods. Processing unit 43 is used to output a processing method to the responsible party based on the error situation in the second comparison result, according to preset error handling rules.

[0054] The logistics distribution and handover management device of this invention achieves pre-emptive risk prevention and post-error handling efficiency optimization through closed-loop control of the entire logistics distribution and handover process. First, by acquiring the goods handover list, it performs in-depth analysis using a risk prediction model to generate error risk levels and simultaneously push warning information, predicting potential risk points in advance and avoiding possible operational oversights, thus reducing the probability of early errors from the source. Then, it collects the barcodes of all goods to be loaded to generate a loading goods list. The system automatically compares the loading list with the goods handover list, outputting the first comparison result to reduce errors in the shipping process, and simultaneously completing the unique binding of the barcodes of the goods to be loaded with the carrier vehicle information to ensure traceability. Upon entering the unloading stage, it collects the barcodes of all unloaded goods to generate an unloading goods list, which is then compared with the loading goods... The manifest undergoes a second comparison and outputs the second comparison result. Through dual verification of the manifest and the physical goods at the receiving end, the operational process is ensured to be standardized, and the handover data is automatically collected, laying a data foundation for rapid determination of responsibility. Then, based on the preset responsibility determination rules and the second comparison result, the party responsible for the error is automatically identified, replacing the traditional manual responsibility determination mode and significantly shortening the dispute resolution cycle. Finally, based on the preset error handling rules, the appropriate handling solution is accurately pushed to the responsible party for the specific problem scenario in the second comparison result, realizing a rapid closed-loop resolution of error problems and comprehensively improving the overall operational efficiency of logistics distribution and handover.

[0055] The above describes the logistics distribution and handover management device in the embodiments of the present invention from the perspective of modular functional entities. The following describes the logistics distribution and handover management equipment in the embodiments of the present invention from the perspective of hardware processing.

[0056] Figure 10 This is a schematic diagram of a logistics distribution and handover management device 900 provided in an embodiment of the present invention. The logistics distribution and handover management device 900 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 910 (e.g., one or more processors) and a memory 920, and one or more storage media 930 (e.g., one or more mass storage devices) storing application programs 933 or data 932. The memory 920 and storage media 930 can be temporary or persistent storage. The program stored in the storage media 930 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the logistics distribution and handover management device 900. Furthermore, the processor 910 may be configured to communicate with the storage media 930 and execute the series of instruction operations in the storage media 930 on the logistics distribution and handover management device 900 to implement the steps of the logistics distribution and handover management methods provided in the above-described method embodiments.

[0057] The logistics distribution and handover management device 900 may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input / output interfaces 960, and / or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 10 The illustrated structure of the logistics distribution and handover management equipment does not constitute a limitation on the logistics distribution and handover management equipment. It may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0058] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of a logistics distribution and handover management method.

[0059] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the device or apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0060] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0061] It is understood that those skilled in the art can make equivalent substitutions or modifications to the technical solution and inventive concept of the present invention, and all such substitutions or modifications should fall within the protection scope of the appended claims.

Claims

1. A logistics distribution and handover management method, characterized in that, Includes the following steps: Obtain the goods handover list, use a risk prediction model to predict the goods handover list to obtain the error risk, and output warnings based on the error risk; Obtain all barcodes of goods to be loaded, generate a loading list, compare the goods handover list with the loading list, output the first comparison result, and bind the barcodes of goods to be loaded with the carrier vehicle information; Obtain all unloaded goods barcodes to form an unloaded goods list. Compare the unloaded goods list with the loaded goods list and output a second comparison result. Use preset responsibility determination rules to determine the party responsible for the error based on the second comparison result. Using preset error handling rules, based on the error situation in the second comparison result, the handling method is output to the responsible party.

2. The logistics distribution and handover management method according to claim 1, characterized in that, The process of obtaining the goods handover list involves using a risk prediction model to predict the risks of errors in the goods handover list, and then outputting warnings based on these risks. Specifically, this includes: Obtain historical cargo handover data, which includes information on dispatching and distribution centers and personnel, information on carrier vehicles and personnel, information on receiving and distribution centers and personnel, dispatch time, receiving time, and records of handover errors; The historical cargo handover data is cleaned and key features are extracted to form a dataset; A risk prediction model is constructed based on the XGBoost algorithm and trained using a dataset. A risk prediction model is used to predict the risk of errors in the goods handover list, and warnings are output based on the risk of errors.

3. The logistics distribution and handover management method according to claim 2, characterized in that, The process of cleaning historical cargo handover data and extracting key features to form a dataset specifically includes: Clean the historical cargo handover data to obtain preprocessed data; The LightGBM algorithm is used to select features with a high correlation to errors from the preprocessed data and sort the features according to their weights. Based on a preset threshold, features with weights greater than the threshold are selected as key features, and a dataset is formed using these key features.

4. The logistics distribution and handover management method according to claim 2, characterized in that, The aforementioned risk prediction model is used to predict the cargo handover list to obtain the error risk, and warnings are output based on the error risk, specifically including: A risk prediction model is used to predict the cargo handover list in order to obtain the error risk, which includes multiple predicted error nodes and their error risk probabilities; Develop error prevention rules, formulate preventive measures based on historical error points, and regularly collect feedback data to optimize preventive measures; The predicted error nodes are matched with error prevention rules to obtain corresponding preventive measures suggestions for the predicted error nodes.

5. The logistics distribution and handover management method according to claim 1, characterized in that, The process of acquiring all barcodes of goods to be loaded, forming a loading list, comparing the goods handover list with the loading list, outputting the first comparison result, and binding the barcodes of goods to be loaded with the carrier vehicle information specifically includes: Obtain all barcodes of goods to be loaded, verify the validity of the barcodes, and compile a loading list of all qualified barcodes. Compare the goods handover list with the loading goods list and output the first comparison result; The system binds the barcode of the cargo to be loaded to the information of the carrier vehicle, obtains the delivery address of the cargo based on the barcode, and determines whether the cargo and the carrier vehicle's transportation plan match based on the delivery address, and outputs the matching result.

6. The logistics distribution and handover management method according to claim 5, characterized in that, The process of binding the barcode of the goods to be loaded with the information of the carrier vehicle, obtaining the delivery address of the goods based on the barcode, determining whether the goods match the transportation plan of the carrier vehicle based on the delivery address, and outputting the matching result includes: The barcode of the cargo to be loaded is linked to the information of the carrier vehicle, and the delivery address of the cargo is obtained based on the barcode of the cargo to be loaded. A pre-built route generation algorithm is used to generate a projected transportation route based on the address of the shipping distribution center and the delivery address of the goods. The projected transportation route includes multiple predicted nodes. Obtain the vehicle transportation plan based on the carrier vehicle information, and extract the transportation nodes in the vehicle transportation plan; The transportation nodes in the vehicle transportation plan are compared with multiple predicted route nodes to determine if there are any overlapping nodes, and the judgment result is output.

7. The logistics distribution and handover management method according to claim 1, characterized in that, The method employs preset error handling rules and outputs a handling method to the responsible party based on the error situation in the second comparison result, specifically including: Set error handling rules. In the event of an error such as multiple shipments, obtain the delivery address of the goods based on the goods barcode, reschedule the delivery plan, and send a notification message to the distribution center and transportation personnel. In the event of a shortage of goods, a notification message will be sent to the distribution center and transportation personnel. Using preset error handling rules, based on the error situation in the second comparison result, the handling method is output to the responsible party.

8. A logistics distribution and handover management device, characterized in that, include: The risk prediction module is used to obtain the goods handover list, use a risk prediction model to predict the goods handover list to obtain the error risk, and output warnings based on the error risk. The first comparison module is used to obtain the barcodes of all goods to be loaded, form a loading list, compare the goods handover list with the loading list, output the first comparison result, and bind the barcodes of the goods to be loaded with the carrier vehicle information. The second comparison module is used to obtain the barcodes of all unloaded goods, form an unloaded goods list, compare the unloaded goods list with the loaded goods list, output the second comparison result, and use preset responsibility determination rules to determine the party responsible for the error based on the second comparison result. The processing module is used to output the processing method to the responsible party based on the error situation in the second comparison result, according to the preset error handling rules.

9. A logistics distribution and handover management device, characterized in that, It includes a memory and at least one processor, wherein the memory stores computer-readable instructions; The at least one processor invokes the computer-readable instructions in the memory to perform the steps of the logistics distribution and handover management method as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer-readable instructions thereon, characterized in that, When the computer-readable instructions are executed by a processor, they implement the various steps of the logistics distribution and handover management method as described in any one of claims 1-7.

Images