Early warning method, device and equipment for card sorting of express panel turnover machine and storage medium

Abstract

The invention relates to the technical field of logistics, in particular to an express delivery panel turnover machine sorting card early warning method, device and equipment and a storage medium, historical scanning data is analyzed by utilizing a machine learning algorithm, a normal scanning data model is constructed according to an analysis result, scanning data of a top scanning camera on express delivery numbers are collected in real time, and the scanning data are acquired; scanning data are preprocessed, the preprocessed scanning data are input into a normal scanning data model and compared with a preset scanning frequency threshold value, a preset scanning time interval threshold value and a preset model deviation rate threshold value, when a comparison result meets a preset clamping rule, an early warning signal is triggered, repeated data processing is reduced, and the accuracy of data processing is improved. According to the method, the data reliability and stability are enhanced, the cost is reduced, the operation cost is reduced, express item number information in early warning related detailed information is recognized, express items corresponding to the express item number information are marked as abnormal items, card items can be rapidly processed, normal sorting is guaranteed, the operation efficiency is improved, logistics delay is prevented, and the customer satisfaction degree is improved.

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to an express delivery flip machine sorting card early warning method, device, equipment and storage medium. Background Art

[0002] Currently, cross-pallet machines are a common device used in the express delivery sorting process in the logistics industry. The workflow involves manually placing parcels on the pallet of the pallet machine. A top-scanning camera on a loop line identifies the parcel and queries the slot. Upon arrival at the destination, the pallet flips down, sorting the parcel to the designated slot. However, due to the uncertainty of manual placement, parcels often get placed between two pallets, causing them to become stuck. These stuck parcels are constantly photographed by the cameras on the loop line, and the system continuously queries the slots, resulting in a large number of repeated scans and returns for the same order number, reducing data reliability and stability. Furthermore, the pallet appears to have been dropped according to procedure, but the actual parcel remains unsorted. This severely impacts the efficiency and accuracy of logistics sorting, increases the system's processing burden and operating costs, and causes logistics delays and reduced customer satisfaction. Summary of the Invention

[0003] In order to overcome the shortcomings of the existing technology, the purpose of the present invention is to provide an express flip machine sorting card warning method, device, equipment and storage medium that enhances data reliability and stability, reduces repeated data processing, reduces hardware consumption, reduces operating costs, can quickly process cards, ensure normal sorting, improve operational efficiency, prevent logistics delays, and improve customer satisfaction.

[0004] The first aspect of the present invention provides an express turntable sorting card early warning method, comprising: using a machine learning algorithm to analyze historical scanning data to obtain analysis results, and constructing a normal scanning data model based on the analysis results; collecting the scanning data of the express delivery number by the top scanning camera in real time, preprocessing the scanning data to obtain preprocessed scanning data; inputting the preprocessed scanning data into the normal scanning data model and comparing it with a preset scanning frequency threshold, a scanning time interval threshold, and a model deviation rate threshold to obtain a comparison result; when the comparison result meets the preset card rule, a warning signal is triggered, and warning-related detailed information is recorded; identifying the express delivery number information in the warning-related detailed information, and marking the express delivery corresponding to the express delivery number information as an abnormal item.

[0005] Optionally, in a first implementation method of the first aspect of the present invention, the historical scanning data is analyzed using a machine learning algorithm to obtain analysis results, and a normal scanning data model is constructed based on the analysis results, including: obtaining historical scanning data, and extracting data features of the historical scanning data to obtain data feature set samples; dividing the data feature set samples into training set samples, validation set samples, and test set samples; constructing a normal scanning data model, and training the normal scanning data model using the training set samples; and tuning and evaluating the normal scanning data model using the validation set samples and the test set samples, respectively.

[0006] Optionally, in a second implementation method of the first aspect of the present invention, the real-time collection of the scanning data of the express delivery number by the top scanning camera and the pre-processing of the scanning data to obtain pre-processed scanning data include: real-time collection of the scanning data of the express delivery number by the top scanning camera; data cleaning of the scanning data to obtain scan cleaning data; filling missing values in the scan cleaning data to obtain scan filling data; and format conversion of the scan filling data based on a preset target standard format to obtain pre-processed scanning data.

[0007] Optionally, in a third implementation of the first aspect of the present invention, the pre-processed scan data is input into the normal scan data model and compared with a preset scan frequency threshold, a scan time interval threshold, and a model deviation rate threshold to obtain a comparison result, including: inputting the pre-processed scan data into the normal scan data model; comparing the pre-processed scan data with the scan frequency threshold preset in the normal scan data model to obtain first comparison information; comparing the pre-processed scan data with the scan time interval threshold preset in the normal scan data model to obtain second comparison information; comparing the pre-processed scan data with the model deviation rate threshold preset in the normal scan data model to obtain third comparison information; integrating the first comparison information, the second comparison information, and the third comparison information to obtain a comparison result.

[0008] Optionally, in a fourth implementation method of the first aspect of the present invention, when the comparison result meets the preset card rules, an early warning signal is triggered and early warning related detailed information is recorded, including: when the comparison result meets the preset card rules, an early warning signal is triggered; early warning related detailed information is recorded, the early warning related detailed information is encrypted, and early warning related detailed encrypted information is obtained; and the early warning related detailed encrypted information is uploaded to the blockchain.

[0009] Optionally, in the fifth implementation method of the first aspect of the present invention, the identification of the express delivery number information in the warning-related detailed information and marking the express delivery corresponding to the express delivery number information as an abnormal item include: identifying the express delivery number information in the warning-related detailed information; marking the express delivery corresponding to the express delivery number information as an abnormal item; suspending subsequent scanning and grid query operations on the abnormal item, and locking the data related to the abnormal item.

[0010] Optionally, in a sixth implementation method of the first aspect of the present invention, after identifying the express delivery number information in the warning-related detailed information and marking the express delivery corresponding to the express delivery number information as an abnormal delivery, it also includes: evaluating the severity of the problem and the scope of impact of the abnormal delivery to obtain a problem evaluation result, and analyzing the current equipment operation status of the turnover machine, the equipment operation status including pallet position information and express delivery distribution information; generating a processing recommendation strategy corresponding to the abnormal delivery based on the equipment operation status and the problem evaluation result, the processing recommendation strategy is one of manually checking the card position, adjusting the express delivery position and re-sorting; sending the processing recommendation strategy to the management terminal; creating a listener, and using the listener to monitor the execution status information of the processing recommendation strategy; when the listener monitors the execution status information, obtaining the current execution status information; analyzing the rationality of the threshold setting and the strategy setting based on the execution status information to obtain an analysis result; optimizing and adjusting the scanning frequency threshold, the scanning time interval threshold, the model deviation rate threshold and the processing recommendation strategy based on the analysis result.

[0011] The second aspect of the present invention provides an express turntable sorting card warning device, comprising: an analysis and construction module, used to analyze historical scanning data using a machine learning algorithm to obtain analysis results, and construct a normal scanning data model based on the analysis results; a collection and processing module, used to collect the scanning data of the express delivery number by the top scanning camera in real time, pre-process the scanning data, and obtain pre-processed scanning data; an input comparison module, used to input the pre-processed scanning data into the normal scanning data model and compare it with a preset scanning frequency threshold, a scanning time interval threshold, and a model deviation rate threshold to obtain a comparison result; a trigger recording module, used to trigger an early warning signal when the comparison result meets the preset card rule, and record early warning related detailed information; an identification and marking module, used to identify the express delivery number information in the early warning related detailed information, and mark the express delivery corresponding to the express delivery number information as an abnormal item.

[0012] Optionally, in a first implementation method of the second aspect of the present invention, the analysis and construction module includes: an acquisition and extraction unit for acquiring historical scanning data and extracting data features of the historical scanning data to obtain data feature set samples; a division unit for dividing the data feature set samples into training set samples, validation set samples and test set samples; a construction training unit for constructing a normal scanning data model and training the normal scanning data model using the training set samples; a tuning and evaluation unit for tuning and evaluating the normal scanning data model using the validation set samples and the test set samples, respectively.

[0013] Optionally, in a second implementation of the second aspect of the present invention, the collection and processing module includes: a collection unit, used to collect the scanning data of the express delivery number by the top scanning camera in real time; a cleaning unit, used to perform data cleaning on the scanning data to obtain scanning cleaning data; a filling unit, used to fill missing values in the scanning cleaning data to obtain scanning filling data; and a conversion unit, used to perform format conversion on the scanning filling data based on a preset target standard format to obtain preprocessed scanning data.

[0014] Optionally, in a third implementation of the second aspect of the present invention, the input comparison module includes: an input unit for inputting the preprocessed scan data into the normal scan data model; a first comparison unit for comparing the preprocessed scan data with the normal scan data through a scan frequency threshold preset in the normal scan data model to obtain first comparison information; a second comparison unit for comparing the preprocessed scan data with the scan time interval threshold preset in the normal scan data model to obtain second comparison information; a third comparison unit for comparing the preprocessed scan data with the model deviation rate threshold preset in the normal scan data model to obtain third comparison information; and an integration unit for integrating the first comparison information, the second comparison information and the third comparison information to obtain a comparison result.

[0015] Optionally, in a fourth implementation of the second aspect of the present invention, the trigger recording module includes: a trigger unit, which is used to trigger a warning signal when the comparison result meets the preset card rules; a recording encryption unit, which is used to record warning-related detailed information, encrypt the warning-related detailed information, and obtain warning-related detailed encrypted information; and an uploading unit, which is used to upload the warning-related detailed encrypted information to the blockchain.

[0016] Optionally, in the fifth implementation of the second aspect of the present invention, the identification and marking module includes: an identification unit for identifying the express delivery number information in the warning-related detailed information; a marking unit for marking the express delivery corresponding to the express delivery number information as an abnormal item; a pause and locking unit for suspending subsequent scanning and grid query operations on the abnormal item, and locking the abnormal item-related data.

[0017] Optionally, in the sixth implementation method of the second aspect of the present invention, it also includes: an evaluation and analysis module, which is used to evaluate the severity and impact scope of the problem of the abnormal part, obtain the problem evaluation result, and analyze the current equipment operation status of the turnover machine, wherein the equipment operation status includes pallet position information and express distribution information; a generation module, which is used to generate a processing recommendation strategy corresponding to the abnormal part based on the equipment operation status and the problem evaluation result, and the processing recommendation strategy is one of manually checking the card position, adjusting the express position and re-sorting; a sending module, which is used to send the processing recommendation strategy to the management terminal; a creation monitoring module, which is used to create a listener and use the listener to monitor the execution status information of the processing recommendation strategy; an acquisition module, which is used to obtain the current execution status information when the listener monitors the execution status information; an analysis module, which is used to analyze the rationality of the threshold setting and the strategy setting according to the execution status information to obtain the analysis result; an optimization and adjustment module, which is used to optimize and adjust the scanning frequency threshold, the scanning time interval threshold, the model deviation rate threshold and the processing recommendation strategy according to the analysis result.

[0018] The third aspect of the present invention provides an express flip machine sorting card piece warning device, which includes: a memory and at least one processor, wherein the memory stores instructions; at least one processor calls the instructions in the memory to enable the express flip machine sorting card piece warning device to execute each step of the express flip machine sorting card piece warning method described above.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed by a processor, implement the various steps of any of the above-mentioned express turntable sorting card warning methods.

[0020] In the technical solution of the present invention, historical scanning data is analyzed by utilizing a machine learning algorithm to obtain analysis results, a normal scanning data model is constructed based on the analysis results, scanning data of express delivery numbers by a top scanning camera is collected in real time, the scanning data is preprocessed to obtain preprocessed scanning data, the preprocessed scanning data is input into the normal scanning data model and compared with a preset scanning frequency threshold, a scanning time interval threshold, and a model deviation rate threshold to obtain a comparison result. When the comparison result meets the preset card piece rules, an early warning signal is triggered, and detailed information related to the early warning is recorded, thereby enhancing data reliability and stability, reducing duplicate data processing, reducing hardware consumption, and reducing operating costs. The express delivery number information in the early warning related detailed information is identified, and the express delivery number information corresponding to the express delivery number information is marked as an abnormal piece. The card piece can be quickly processed to ensure normal sorting, improve operational efficiency, prevent logistics delays, and improve customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A first flow chart of the express delivery flip machine card sorting early warning method provided by an embodiment of the present invention;

[0022] Figure 2 A second flow chart of the express delivery flip machine card sorting early warning method provided by an embodiment of the present invention;

[0023] Figure 3 A third flow chart of the express delivery flip machine card sorting early warning method provided by an embodiment of the present invention;

[0024] Figure 4 A fourth flow chart of the express delivery flip machine card sorting early warning method provided by an embodiment of the present invention;

[0025] Figure 5 A schematic diagram of a structure of an early warning device for sorting card parts on a courier flip machine provided by an embodiment of the present invention;

[0026] Figure 6 Another structural diagram of the express delivery flip machine sorting card early warning device provided by an embodiment of the present invention;

[0027] Figure 7 A schematic structural diagram of the express delivery flip machine sorting card early warning device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The present invention provides an express delivery flip machine sorting card early warning method, device, equipment and storage medium, which enhances data reliability and stability, reduces repeated data processing, reduces hardware consumption, and reduces operating costs. It can quickly process cards, ensure normal sorting, improve operational efficiency, prevent logistics delays, and enhance customer satisfaction.

[0029] The terms "first," "second," "third," "fourth," and the like (if any) in the description and claims of the present invention and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatus.

[0030] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 In one embodiment of the present invention, an early warning method for sorting card pieces by an express turntable machine includes:

[0031] 101. Use machine learning algorithms to analyze historical scan data, obtain analysis results, and build a normal scan data model based on the analysis results;

[0032] In this embodiment, a supervised learning or unsupervised learning algorithm can be selected based on the characteristics of the historical scanning data. The historical scanning data is analyzed using a machine learning algorithm to obtain analysis results. Through the analysis results, it can be evaluated which features are most important in distinguishing normal from abnormal scans. For example, features such as scanning frequency and time interval may be key factors, and a normal scanning data model is constructed based on the analysis results.

[0033] 102. Collecting scan data of the express delivery number from the top scanning camera in real time, pre-processing the scan data to obtain pre-processed scan data;

[0034] In this embodiment, the scan data of the express delivery order number by the top scanning camera is collected in real time, and the scan data is processed for missing values, outliers, duplicate data is eliminated, and the format is unified to obtain pre-processed scan data.

[0035] 103. Input the pre-processed scan data into a normal scan data model and compare it with a preset scan frequency threshold, a scan time interval threshold, and a model deviation rate threshold to obtain a comparison result;

[0036] In this embodiment, the pre-processed scan data will serve as the input of the normal scanning data model, including information such as the express delivery number, scanning time, scanning frequency, and scanning equipment. After obtaining the model output result, it is necessary to compare the result with the preset threshold to determine whether the scanning behavior meets expectations. The scanning frequency threshold refers to the maximum or minimum number of express deliveries scanned in a unit of time (such as per minute or per hour). For example, if the scanning frequency is higher than a certain threshold, it may indicate that there is a fault in the equipment or the data is scanned abnormally. The scanning time interval threshold refers to the maximum or minimum limit of the time interval between two scans. The actual scanning time interval calculated by the model is compared with the preset scanning time interval threshold. The model deviation rate threshold represents the difference between the scanning data predicted by the model and the actual data. The model prediction result is compared with the actual scanning data to calculate the deviation rate. The model output is a comparison result. The comparison result is a classification (such as normal or abnormal) or a numerical value (such as an abnormality score, predicted scanning frequency, etc.) for each data point.

[0037] 104. When the comparison result meets the preset card rules, an early warning signal is triggered and detailed information related to the early warning is recorded;

[0038] In this embodiment, when the comparison result meets the preset card rules, for example: the scanning frequency threshold is set to that the same order number cannot be scanned more than 3 times within 1 minute. During a certain period of time, the system monitors that the order number of express A was scanned 4 times within 50 seconds, which exceeds the scanning frequency threshold. The scanning time interval threshold is set to at least 10 seconds between two adjacent scans. Express B was scanned again within 5 seconds after the first scan, which does not meet the time interval requirement. The constructed normal scanning data model shows that the average time interval for normal scanning of a certain type of small package is 15-20 seconds. However, in actual monitoring, the scanning time interval of such small package C is only 8 seconds on average, and the deviation rate from the model exceeds the set 20%, which triggers an early warning signal and records the relevant early warning detailed information.

[0039] 105. Identify the express shipment number information in the warning-related detailed information and mark the shipment corresponding to the express shipment number information as an abnormal shipment;

[0040] In this embodiment, all relevant data are extracted from the warning-related detailed information, including fields related to the express delivery, such as express delivery number information, scanning time information, equipment number information, etc. Once the express delivery number is identified, the express delivery corresponding to the express delivery number information is marked as an abnormal item.

[0041] In an embodiment of the present invention, historical scanning data is analyzed by utilizing a machine learning algorithm to obtain analysis results, a normal scanning data model is constructed based on the analysis results, scanning data of express delivery numbers by a top scanning camera is collected in real time, the scanning data is preprocessed to obtain preprocessed scanning data, the preprocessed scanning data is input into the normal scanning data model and compared with a preset scanning frequency threshold, a scanning time interval threshold, and a model deviation rate threshold to obtain a comparison result. When the comparison result meets the preset card piece rule, an early warning signal is triggered, and detailed information related to the early warning is recorded, thereby enhancing data reliability and stability, reducing duplicate data processing, reducing hardware consumption, and reducing operating costs. The express delivery number information in the early warning related detailed information is identified, and the express delivery number information corresponding to the express delivery number information is marked as an abnormal piece. The card piece can be quickly processed to ensure normal sorting, improve operational efficiency, prevent logistics delays, and improve customer satisfaction.

[0042] See also Figure 2 The second embodiment of the express flip machine sorting card early warning method in the embodiment of the present invention includes:

[0043] 201. Obtain historical scanning data, extract data features of the historical scanning data, and obtain a data feature set sample;

[0044] In this embodiment, historical scanning data is obtained. Historical scanning data refers to all the express parcel records that have been scanned in the system. These records contain information about each express parcel, such as scanning time, scanning equipment, express parcel number, etc. From the obtained historical scanning data, data features that are helpful for analysis are identified to obtain a data feature set sample.

[0045] 202. Divide the data feature set samples into training set samples, validation set samples, and test set samples;

[0046] In this embodiment, the data feature set samples are divided into training set samples, validation set samples and test set samples in proportion. For example, the training set samples account for 70%-80%, the validation set samples account for 10%-15%, and the test set samples account for 10%-15%.

[0047] 203. Construct a normal scanning data model, and train the normal scanning data model using training set samples;

[0048] In this embodiment, according to the task objectives of the normal scan data model, a suitable machine learning algorithm, such as a classification algorithm and a clustering algorithm, can be selected, the normal scan data model is constructed according to the selected algorithm, and the normal scan data model is trained using training set samples.

[0049] 204. Use validation set samples and test set samples to tune and evaluate the normal scan data model respectively;

[0050] In this embodiment, the main function of the validation set samples is to adjust the model's hyperparameters, select the optimal model configuration, and ensure that the model does not overfit. When training the model, the main goal of tuning is to find an optimal set of hyperparameters. The function of the test set samples is to perform a final evaluation of the model and verify the model's performance on completely unseen data. After the model is trained and tuned on the training set and validation set, the test set is used for the final evaluation.

[0051] 205. Real-time collection of top-scanning camera scanning data on express delivery numbers;

[0052] In this embodiment, the top-scanning camera is generally an efficient camera or laser scanning device, which is mainly used to scan barcodes, QR codes or other identification information on express parcels, such as order numbers. The top-scanning camera is located above the conveyor belt to automatically identify and read the labels of passing express parcels, and collect the scanning data of the express parcel order numbers by the top-scanning camera in real time.

[0053] 206. Clean the scanned data to obtain scan cleaned data;

[0054] In this embodiment, the scanned data is first deduplicated to exclude records in which the same express delivery number appears multiple times. If the scanned data contains content that does not conform to the expected format, for example, the length of the delivery number does not match, the characters do not meet the requirements, etc., it needs to be eliminated or repaired. There may be some abnormal data caused by equipment failure, damaged barcodes, lighting problems, etc., such as unrecognizable characters and incomplete delivery numbers. These data need to be identified and repaired or deleted to obtain scanned cleaned data.

[0055] 207. Fill missing values in the scanned cleaned data to obtain scanned filled data;

[0056] In this embodiment, it is identified which fields of the scanned and cleaned data have missing values, and a filling strategy is determined. The filling strategy includes constant filling, filling based on historical data, filling based on inference of other fields, and filling based on a machine learning model. According to the selected filling strategy, the missing values in the scanned data are filled to obtain scanned and filled data.

[0057] 208. Based on a preset target standard format, convert the scanned filling data into a format to obtain pre-processed scanned data;

[0058] In this embodiment, the target standard format is clarified, the field names of the scanned data are matched with the field names of the target standard format, and the format of the scanned fill data is converted based on the preset target standard format to obtain pre-processed scanned data.

[0059] In the embodiment of the present invention, through a systematic process, features are effectively extracted from historical data and a model is established, thereby ensuring efficient training, tuning and evaluation of the model. This process also involves the continuous collection and processing of real-time data, ensuring the integrity and consistency of the data, and ensuring the accuracy of subsequent analysis and application. At the same time, data cleaning, missing value filling and format conversion can improve data quality, ensuring that the model can be applied efficiently and accurately in a real-time environment, and has strong adaptability and operability.

[0060] See also Figure 3 The third embodiment of the express delivery flip machine sorting card early warning method in the embodiment of the present invention includes:

[0061] 301. Inputting the pre-processed scan data into a normal scan data model;

[0062] In this embodiment, the pre-processed scan data that has been processed through steps such as data cleaning, format conversion, and missing value filling is used as input for the normal scan data model data analysis.

[0063] 302. Compare the pre-processed scan data with the scan frequency threshold preset in the normal scan data model to obtain first comparison information;

[0064] In this embodiment, by comparing with the preset scanning frequency threshold, it is determined whether the data meets the set standard. By comparing the difference between the actual data and the preset threshold, possible abnormal values, errors or inconsistencies in the data can be identified, and the comparison results are generated into the first comparison information to provide data basis for further analysis.

[0065] 303. Compare the pre-processed scan data with the scan time interval threshold preset in the normal scan data model to obtain second comparison information;

[0066] In this embodiment, by comparing the time difference between the preset time interval threshold and the actual scanning data, it is determined whether the data collection is performed according to the preset time interval. By comparing the actual time interval of the scanning data with the preset time interval threshold, those abnormal situations that exceed the predetermined range are found, and the comparison results are used to generate second comparison information.

[0067] 304. Compare the pre-processed scan data with the model deviation rate threshold preset in the normal scan data model to obtain third comparison information;

[0068] In this embodiment, by comparing the preset model deviation rate threshold with the actual scanning data deviation, it is ensured that the scanning data is within the predetermined deviation range. By calculating the deviation of the scanning data and comparing it with the preset deviation threshold, those data with excessive deviation are found, and the results of the deviation comparison are used to generate third comparison information.

[0069] 305. Integrate the first comparison information, the second comparison information, and the third comparison information to obtain a comparison result;

[0070] In this embodiment, the first comparison information, the second comparison information, and the third comparison information are integrated to obtain a comparison result. As long as one of the comparison information is unqualified, the preset card rule is met.

[0071] 306. When the comparison result meets the preset card rules, an early warning signal is triggered;

[0072] In this embodiment, when the comparison result meets the preset card rules, an early warning signal is triggered, and a red warning sign, flashing prompt, etc. are displayed on the data monitoring interface to remind the operator to pay attention. If the early warning signal is serious or involves important data, the system can send text messages or emails to notify relevant personnel.

[0073] 307. Record the warning-related detailed information, encrypt the warning-related detailed information, and obtain the warning-related detailed encrypted information;

[0074] In this embodiment, the pre-warning related detailed information is recorded, and the warning related detailed information includes the triggering rules, abnormal data, timestamp, etc., and a suitable encryption algorithm is selected to encrypt the warning related detailed information to obtain the warning related detailed encrypted information.

[0075] 308. Upload the detailed encrypted information related to the warning to the blockchain;

[0076] In this embodiment, the detailed encrypted information related to the early warning is submitted to the blockchain through a smart contract or transaction record. Specifically, the encrypted detailed encrypted information related to the early warning and the corresponding hash value are created as part of the transaction, and the detailed encrypted information related to the early warning and the hash value are digitally signed. Data processing and verification are performed through the smart contract to ensure that the uploaded data complies with certain rules and formats, and the transaction containing the encrypted early warning information and the digital signature is broadcast to the blockchain network.

[0077] 309. Identify the express shipment number information in the detailed information related to the warning;

[0078] In this embodiment, the express delivery number information in the warning-related detailed information is identified. The express delivery number information is a unique number used to identify a specific express delivery in logistics or transportation.

[0079] 310. Mark the express shipment corresponding to the express shipment number as an abnormal shipment;

[0080] In this embodiment, once the system identifies the express shipment number information in the warning-related detailed information, the system will update the status of the express shipment corresponding to the express shipment number information to "abnormal shipment".

[0081] 311. Suspend subsequent scanning and grid query operations on abnormal items, and lock the relevant data of abnormal items;

[0082] In this embodiment, suspending the slot query operation means stopping further queries and operations on the slots where the abnormal items are located during the warehousing and distribution process. This operation ensures that when handling abnormal items, the slot status will not be changed incorrectly or operated unintentionally. Locking the relevant data of abnormal items is a key step in protecting the information of express items that have been marked as abnormal, ensuring that all relevant data will not be tampered with or misoperated during the exception handling process.

[0083] In the embodiments of the present invention, multi-level and multi-dimensional comparison and integration are used to effectively compare scanned data with preset thresholds, ensuring accurate identification of abnormal data and timely triggering of early warnings. This refined comparison and processing process not only enhances the accuracy of early warnings but also ensures the security and immutability of data through blockchain technology. In addition, the system can automatically identify and lock abnormal items to prevent them from affecting subsequent operations, thereby improving the efficiency of overall operations and the transparency of data processing.

[0084] See also Figure 4 The fourth embodiment of the express delivery flip machine sorting card early warning method in the embodiment of the present invention includes:

[0085] 401. Evaluate the severity and impact of the abnormal item, obtain the problem assessment results, and analyze the current equipment operating status of the pallet turnover machine, which includes pallet location information and express delivery distribution information;

[0086] In this embodiment, the severity and impact scope of the problems of abnormal parts are evaluated. Specifically, the abnormal parts are classified according to the problem category (such as transportation damage, system mislabeling, packaging damage, etc.), and their severity is evaluated according to their impact. The rating system can include minor, medium and severe. The problem evaluation results are obtained, and the current equipment operating status of the turnover machine is analyzed. The equipment operating status includes pallet position information and express distribution information.

[0087] 402. Generate a corresponding handling strategy for the abnormal item based on the equipment operating status and the problem assessment results. The handling strategy is one of manually checking the location of the stuck item, adjusting the location of the item, and re-sorting.

[0088] In this embodiment, a processing recommendation strategy corresponding to the abnormal parts is generated based on the equipment operating status and problem assessment results. The processing recommendation strategy is one of manually checking the position of the stuck parts, adjusting the position of the express parts and re-sorting. The purpose of manually checking the position of the stuck parts is to confirm whether the express parts have an abnormality in the sorting path of the flip machine, or are stuck in a certain part of the equipment. Manual inspection can help quickly discover problems and take targeted measures. The purpose of adjusting the position of the express parts is to ensure that the express parts can correctly enter the subsequent sorting process or transportation path.

[0089] 403. Send the processing suggestion strategy to the management terminal;

[0090] In this embodiment, the processing suggestion strategy is sent to the management terminal via email or message queue. After receiving the processing suggestion, the management personnel confirm it and take corresponding measures according to the feedback information.

[0091] 404. Create a listener and use the listener to monitor the execution status of the recommended strategy.

[0092] In this embodiment, a listener is created and a trigger mechanism is set so that an immediate response can be made when execution status information occurs.

[0093] 405. When the listener listens to the execution status information, it obtains the current execution status information;

[0094] In this embodiment, the listener needs to start running in the system and monitor the execution process of the target policy. When the listener listens to the execution status information, the current execution status information is obtained.

[0095] 406. Analyze the rationality of the threshold setting and the strategy setting based on the execution status information to obtain an analysis result;

[0096] In this embodiment, the rationality of the threshold setting and the policy setting is analyzed based on the execution status information, and the deficiencies in the threshold setting are identified by comparing the actual execution with the predetermined target to obtain the analysis result.

[0097] 407. Optimize and adjust the scanning frequency threshold, scanning time interval threshold, model deviation rate threshold, and processing suggestion strategy based on the analysis results;

[0098] In this embodiment, deficiencies in the threshold settings are determined based on the analysis results, and the scanning frequency threshold, scanning time interval threshold, model deviation rate threshold, and processing suggestion strategy are optimized and adjusted.

[0099] In the embodiments of the present invention, efficient handling of exceptions is ensured through systematic evaluation, policy formulation, and execution monitoring. First, by assessing the severity and scope of the problem, as well as analyzing the operating status of the equipment, targeted processing strategies can be accurately formulated. Then, the execution process ensures the effective implementation of the strategy through real-time monitoring and feedback mechanisms, and optimizes and adjusts it according to the actual execution situation when necessary, thereby enhancing the flexibility and responsiveness of the system. Overall, this process effectively improves the accuracy and timeliness of exception handling and optimizes resource allocation and equipment operation.

[0100] The above describes the express turn-over machine sorting card early warning method in the embodiment of the present invention. The following describes the express turn-over machine sorting card early warning device in the embodiment of the present invention. Figure 5 In one embodiment of the present invention, an early warning device for sorting card pieces of a courier flip machine includes:

[0101] An analysis and construction module 501 is used to analyze historical scan data using a machine learning algorithm to obtain analysis results and construct a normal scan data model based on the analysis results;

[0102] The collection and processing module 502 is used to collect the scan data of the express delivery number by the top scanning camera in real time, pre-process the scan data, and obtain pre-processed scan data;

[0103] An input comparison module 503 is used to input the pre-processed scan data into the normal scan data model and compare it with a preset scan frequency threshold, a scan time interval threshold, and a model deviation rate threshold to obtain a comparison result;

[0104] The trigger recording module 504 is used to trigger an early warning signal and record detailed information related to the early warning when the comparison result meets the preset card rules;

[0105] The identification and marking module 505 is used to identify the express delivery number information in the warning-related detailed information and mark the express delivery corresponding to the express delivery number information as an abnormal delivery.

[0106] In this embodiment, historical scanning data is analyzed by utilizing a machine learning algorithm to obtain analysis results, a normal scanning data model is constructed based on the analysis results, scanning data of express delivery numbers by a top scanning camera is collected in real time, the scanning data is preprocessed to obtain preprocessed scanning data, the preprocessed scanning data is input into the normal scanning data model and compared with a preset scanning frequency threshold, a scanning time interval threshold, and a model deviation rate threshold to obtain a comparison result. When the comparison result meets the preset card rule, an early warning signal is triggered, and detailed information related to the early warning is recorded to enhance data reliability and stability, reduce duplicate data processing, reduce hardware consumption, and reduce operating costs. The express delivery number information in the early warning related detailed information is identified, and the express delivery number information corresponding to the express delivery number information is marked as an abnormal item. The card can be processed quickly to ensure normal sorting, improve operational efficiency, prevent logistics delays, and improve customer satisfaction.

[0107] See also Figure 6 Another embodiment of the express delivery flip machine sorting card early warning device in the embodiment of the present invention includes:

[0108] An analysis and construction module 501 is used to analyze historical scan data using a machine learning algorithm to obtain analysis results and construct a normal scan data model based on the analysis results;

[0109] The collection and processing module 502 is used to collect the scan data of the express delivery number by the top scanning camera in real time, pre-process the scan data, and obtain pre-processed scan data;

[0110] An input comparison module 503 is used to input the pre-processed scan data into the normal scan data model and compare it with a preset scan frequency threshold, a scan time interval threshold, and a model deviation rate threshold to obtain a comparison result;

[0111] The trigger recording module 504 is used to trigger an early warning signal and record detailed information related to the early warning when the comparison result meets the preset card rules;

[0112] Identification and marking module 505, used to identify the express shipment number information in the warning-related detailed information and mark the express shipment corresponding to the express shipment number information as an abnormal shipment;

[0113] In this embodiment, the analysis and construction module 501 includes: an acquisition and extraction unit 5011, which is used to acquire historical scanning data and extract data features of the historical scanning data to obtain data feature set samples; a division unit 5012, which is used to divide the data feature set samples into training set samples, verification set samples and test set samples; a construction training unit 5013, which is used to construct a normal scanning data model and train the normal scanning data model using the training set samples; a tuning and evaluation unit 5014, which is used to tune and evaluate the normal scanning data model using the verification set samples and the test set samples respectively.

[0114] In this embodiment, the collection and processing module 502 includes: a collection unit 5021, which is used to collect the scanning data of the express delivery number by the top scanning camera in real time; a cleaning unit 5022, which is used to clean the scan data to obtain scan cleaning data; a filling unit 5023, which is used to fill missing values in the scan cleaning data to obtain scan filling data; a conversion unit 5024, which is used to convert the format of the scan filling data based on a preset target standard format to obtain pre-processed scan data.

[0115] In this embodiment, the input comparison module 503 includes: an input unit 5031, used to input the preprocessed scan data into the normal scan data model; a first comparison unit 5032, used to compare the preprocessed scan data with the normal scan data model through a scan frequency threshold preset in the normal scan data model to obtain first comparison information; a second comparison unit 5033, used to compare the preprocessed scan data with the scan time interval threshold preset in the normal scan data model to obtain second comparison information; a third comparison unit 5034, used to compare the preprocessed scan data with the model deviation rate threshold preset in the normal scan data model to obtain third comparison information; an integration unit 5035, used to integrate the first comparison information, the second comparison information and the third comparison information to obtain a comparison result.

[0116] In this embodiment, the trigger recording module 504 includes: a trigger unit 5041, which is used to trigger an early warning signal when the comparison result meets the preset card rules; a recording encryption unit 5042, which is used to record early warning related detailed information, encrypt the early warning related detailed information, and obtain early warning related detailed encrypted information; an upload unit 5043, which is used to upload the early warning related detailed encrypted information to the blockchain.

[0117] In this embodiment, the identification and marking module 505 includes: an identification unit 5051, which is used to identify the express delivery number information in the warning-related detailed information; a marking unit 5052, which is used to mark the express delivery corresponding to the express delivery number information as an abnormal item; a pause and lock unit 5053, which is used to pause subsequent scanning and grid query operations on abnormal items, and lock the data related to the abnormal items.

[0118] In this embodiment, it also includes: an evaluation and analysis module 506, which is used to evaluate the severity and impact range of the problem of abnormal parts, obtain problem evaluation results, and analyze the current equipment operation status of the turnover machine, where the equipment operation status includes pallet position information and express distribution information; a generation module 507, which is used to generate a processing recommendation strategy corresponding to the abnormal parts based on the equipment operation status and problem evaluation results, where the processing recommendation strategy is one of manually checking the card position, adjusting the express position, and re-sorting; a sending module 508, which is used to send the processing recommendation strategy to the management terminal; a creation monitoring module 509, which is used to create a listener and use the listener to monitor the execution status information of the processing recommendation strategy; an acquisition module 510, which is used to obtain the current execution status information when the listener monitors the execution status information; an analysis module 511, which is used to analyze the rationality of the threshold setting and the strategy setting based on the execution status information to obtain the analysis results; an optimization and adjustment module 512, which is used to optimize and adjust the scanning frequency threshold, the scanning time interval threshold, the model deviation rate threshold, and the processing recommendation strategy based on the analysis results.

[0119] above Figure 5 and Figure 6 The express flip machine sorting card warning device in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The express flip machine sorting card warning device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0120] Figure 7 : This is a schematic structural diagram of an express flip machine sorting card early warning device provided by an embodiment of the present invention. The express flip machine sorting card early warning device 600 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (for example, one or more processors) and a memory 620, and one or more storage media 630 (for example, one or more mass storage devices) storing application programs 633 or data 632. Among them, the memory 620 and the storage medium 630 can be temporary storage or permanent storage. The program stored in the storage medium 630 may include one or more modules (not shown in the figure), each of which may include a series of instruction operations in the express flip machine sorting card early warning device 600. Furthermore, the processor 610 can be configured to communicate with the storage medium 630, and execute a series of instruction operations in the storage medium 630 on the express flip machine sorting card early warning device 600 to implement the steps of the express flip machine sorting card early warning method provided by the above-mentioned method embodiments.

[0121] The express card sorting machine early warning device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input and output interfaces 660, and / or one or more operating systems 631, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be understood by those skilled in the art that Figure 7 The structure of the express flip machine sorting card warning device shown does not constitute a limitation on the express flip machine sorting card warning device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0122] 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. The computer-readable storage medium stores instructions. When the instructions are run on a computer, the computer executes the steps of the express flip machine sorting card warning method.

[0123] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0124] If the integrated unit is implemented in the form of 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 is essentially 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc., various media that can store program code.

[0125] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for early warning of card sorting by an express turntable, characterized in that: include: Analyze historical scan data using a machine learning algorithm to obtain analysis results, and construct a normal scan data model based on the analysis results; collecting scan data of the express delivery number from the top scanning camera in real time, and preprocessing the scan data to obtain preprocessed scan data; Inputting the pre-processed scan data into the normal scan data model and comparing it with a preset scan frequency threshold, a scan time interval threshold, and a model deviation rate threshold to obtain a comparison result; When the comparison result meets the preset card rules, an early warning signal is triggered and detailed information related to the early warning is recorded; Identify the express shipment number information in the warning-related detailed information, and mark the express shipment corresponding to the express shipment number information as an abnormal shipment.

2. The express turntable sorting card early warning method according to claim 1 is characterized in that: The method of analyzing the historical scan data using a machine learning algorithm to obtain analysis results and constructing a normal scan data model based on the analysis results includes: Acquire historical scanning data, and extract data features of the historical scanning data to obtain a data feature set sample; Dividing the data feature set samples into training set samples, validation set samples and test set samples; Constructing a normal scan data model, and training the normal scan data model using the training set samples; The normal scan data model is tuned and evaluated using the validation set samples and the test set samples respectively.

3. The express delivery flip machine sorting card early warning method according to claim 1 is characterized in that: The real-time collection of scan data of the express delivery number by the top scanning camera and pre-processing of the scan data to obtain pre-processed scan data include: Real-time collection of top-scan camera scanning data on express delivery numbers; performing data cleaning on the scan data to obtain scan cleaned data; Filling missing values in the scanned cleaned data to obtain scanned filled data; Based on a preset target standard format, the scanned filling data is format converted to obtain pre-processed scanned data.

4. The express delivery flip machine sorting card early warning method according to claim 1 is characterized in that: The inputting the pre-processed scan data into the normal scan data model and comparing it with a preset scan frequency threshold, a scan time interval threshold, and a model deviation rate threshold to obtain a comparison result includes: inputting the pre-processed scan data into the normal scan data model; Obtaining first comparison information by comparing the pre-processed scan data with the scan frequency threshold preset in the normal scan data model; Obtaining second comparison information by comparing the scan time interval threshold preset in the normal scan data model with the pre-processed scan data; Obtain third comparison information by comparing the pre-processed scan data with the model deviation rate threshold preset in the normal scan data model; The first comparison information, the second comparison information, and the third comparison information are integrated to obtain a comparison result.

5. The express delivery flip machine sorting card early warning method according to claim 1 is characterized in that: When the comparison result meets the preset card rules, an early warning signal is triggered and detailed information related to the early warning is recorded, including: When the comparison result meets the preset card rules, an early warning signal is triggered; Recording warning-related detailed information, encrypting the warning-related detailed information, and obtaining warning-related detailed encrypted information; Upload the detailed encrypted information related to the warning to the blockchain.

6. The express delivery flip machine sorting card early warning method according to claim 1 is characterized in that: The identifying the express shipment number information in the warning-related detailed information and marking the express shipment corresponding to the express shipment number information as an abnormal shipment includes: Identify the express shipment number information in the detailed information related to the warning; Mark the express shipment corresponding to the express shipment number information as an abnormal shipment; Suspend subsequent scanning and grid query operations on the abnormal part, and lock the relevant data of the abnormal part.

7. The express delivery flip machine sorting card early warning method according to claim 1, characterized in that: After identifying the express shipment number information in the warning-related detailed information and marking the express shipment corresponding to the express shipment number information as an abnormal shipment, the method further includes: Assess the severity and impact of the abnormal item, obtain a problem assessment result, and analyze the current equipment operating status of the pallet turnover machine, including pallet position information and express delivery distribution information; Generate a recommended handling strategy for the abnormal item based on the equipment operating status and the problem assessment result, wherein the recommended handling strategy is one of manually checking the location of the item, adjusting the location of the item, and re-sorting the item; Sending the processing suggestion strategy to the management terminal; Creating a listener, and using the listener to monitor the execution status information of the processing suggestion strategy; When the listener listens to the execution status information, it obtains the current execution status information; Analyzing the rationality of threshold settings and strategy settings based on the execution status information to obtain analysis results; The scanning frequency threshold, the scanning time interval threshold, the model deviation rate threshold, and the processing suggestion strategy are optimized and adjusted according to the analysis results.

8. An early warning device for sorting card parts of an express delivery flip machine, characterized in that: include: An analysis and construction module is used to analyze historical scan data using a machine learning algorithm to obtain analysis results, and to construct a normal scan data model based on the analysis results; A collection and processing module is used to collect the scan data of the express delivery number by the top scanning camera in real time, and pre-process the scan data to obtain pre-processed scan data; An input comparison module, configured to input the pre-processed scan data into the normal scan data model and compare the data with a preset scan frequency threshold, a scan time interval threshold, and a model deviation rate threshold to obtain a comparison result; A trigger recording module is used to trigger an early warning signal and record detailed information related to the early warning when the comparison result meets the preset card rules; The identification and marking module is used to identify the express delivery number information in the warning-related detailed information and mark the express delivery corresponding to the express delivery number information as an abnormal delivery.

9. An express delivery flip machine sorting card early warning device, characterized in that: The express turntable sorting card early warning device comprises: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors calls the instructions in the memory to enable the express flip machine sorting card early warning device to execute each step of the express flip machine sorting card early warning method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the express turnover machine sorting card early warning method as described in any one of claims 1-7 are implemented.

Images