M10 system barcode mistake proofing system

Abstract

The application discloses an M10 system bar code mistake proofing system and relates to the technical field of industrial internet of things.The M10 system bar code mistake proofing system comprises a bar code scanning module, a sensor module, an article bar code state binding module and an article state anomaly judgment module.The bar code scanning module is used for scanning a bar code and recording corresponding process information when the bar code is scanned, and bar code data and process data are generated respectively.The sensor module comprises various sensors and is used for collecting category state data of articles in different categories of processes in the order of bar code data collection, and article state data is generated.The M10 system bar code mistake proofing system can automatically compare article state data with state data of corresponding bar codes of previous processes when each bar code is scanned, so that quick judgment of whether the state of articles corresponding to the bar code is abnormal can be realized, and the bar code scanning mistake proofing mechanism is more delicate.

Description

Technical Field

[0001] This invention relates to the field of industrial Internet of Things (IoT) technology, specifically to the M10 system barcode error prevention system. Background Technology

[0002] The M10 system refers to an unattended industrial scanning system. In manufacturing, product tracking and management are crucial for ensuring production efficiency and product quality. Traditional product tracking methods rely on manual recording and verification, which are prone to errors and inefficient. With the widespread adoption of barcode technology, barcode systems are widely used for product tracking and management. However, existing barcode systems are typically used only for tracking a single stage, lacking a full-process barcode verification mechanism. This leads to information gaps or errors between multiple stages of product development. Existing technology, with publication number CN118469504A, discloses a production error-proofing system and method based on MES (Manufacturing Execution System) for automotive manufacturing process control. It includes: a station monitoring module, a vehicle-material coordination module, a standardized operation management module, a barcode verification module, and an MES server. The station monitoring module monitors the station status of vehicles and determines whether the passing vehicles match the production plan. The vehicle-material coordination module adjusts the material supply and actual production material supply matching, and collects material supply station information. The standardized operation management module displays vehicle information and automatically switches display content, obtaining progress information from production data. The barcode verification module identifies part barcodes and distinguishes part types. The MES server communicates with the station monitoring module, vehicle-material coordination module, standardized operation management module, and barcode verification module, collecting real-time production data for real-time analysis and evaluation. Real-time analysis and evaluation of the production process based on real-time data enables tracking of the entire vehicle production cycle.

[0003] However, during the product verification process, errors in transportation and assembly may cause problems with the product itself. Simply checking the barcode cannot guarantee the accuracy of the product verification. For example, some materials may be lost during loading or transportation, resulting in a reduction in product weight; the product may be damaged during transportation and assembly due to bumps or assembly processes. Therefore, it is also necessary to inspect and verify the materials themselves when checking the barcode. Summary of the Invention

[0004] The purpose of this invention is to provide an M10 system barcode error prevention system to address the aforementioned shortcomings in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an M10 system barcode error prevention system, comprising the following modules:

[0006] The barcode scanning module is used to scan barcodes and record the corresponding process information during the barcode scanning process, and generate barcode data accordingly. and process data p represents the p-th barcode scanned, and u represents the u-th process;

[0007] The sensor module includes multiple sensors used to collect category status data of items in different processes, following the order of barcode data collection. Generate item status data o represents the o-th category state;

[0008] The item barcode status binding module is used to collect and combine the barcode data, process data and item status data to generate comprehensive item data.

[0009] The item status anomaly judgment module is used to perform similarity analysis on the item status data of the current process and the previous process based on the comprehensive item data, judge whether the item status is abnormal, and generate item status judgment data.

[0010] The barcode item anomaly type analysis module is used to perform anomaly type analysis processing on the item's comprehensive data and anomaly type item comprehensive feature data when the item's status is abnormal, and generate item process anomaly type analysis data.

[0011] The barcode error prevention management module is used to construct barcode error prevention management data and perform barcode error prevention management information feedback operations based on the barcode error prevention management data.

[0012] Furthermore, the barcode scanning module generates barcode data and process data, including the following steps:

[0013] S11. Scan the barcode information using the barcode scanning module to generate a barcode data set. , , This represents the p-th barcode data, where the barcode is generated according to the set barcode rules and associated with the corresponding item information entered into the database, such as the item's category, production date, name, specifications, batch number, etc.

[0014] S12. Generate a process data set by collecting the process information corresponding to the barcode scanning module. , , This represents the u-th process data corresponding to the p-th barcode. The process data can be bound to the ID of the barcode scanning module of each process by setting the process data. The process data corresponding to the barcode data can be generated by searching for the process data corresponding to the ID of the barcode scanning module that generated the barcode data.

[0015] Furthermore, the sensor module generates item status data, including the following steps:

[0016] S21. Using multiple sensors to scan barcode data The system collects item status information in each process sequentially, generating an item status data set. , This represents the item status data corresponding to the p-th barcode and the u-th process. , , This represents the o-th category status data corresponding to the u-th process of the p-th barcode; for example, the weight data of the item can be collected by a gravity sensor, the temperature information of the item can be collected by a temperature sensor, the humidity information of the item can be collected by a humidity sensor, and the high-definition image information of the item can be collected by a high-definition camera sensor, etc.

[0017] Furthermore, the item barcode status binding module generates comprehensive item data, including the following steps:

[0018] S31. Collect and combine the corresponding barcode data, process data, and item status data according to the order of the process data to generate comprehensive item data. In other words, the comprehensive data of an item includes the item's barcode data, its process data, and the status data of various items within that process; among these, the comprehensive item data... The further extension is as follows:

[0019] .

[0020] Furthermore, the item status anomaly judgment module determines whether the item status is abnormal, including the following steps:

[0021] S41, Based on comprehensive item data For category status o and barcode data Same barcode data Process data and category status data The corresponding data is collected and combined to generate O comprehensive datasets for each item category. ,in, , ;

[0022] S42, Comprehensive data set for a single category of items Category status data Standardization processing is performed to generate categorically standardized data. Standardized comprehensive dataset of item categories Further standardization processing also includes the analysis of category status data. Perform vectorization, missing value handling, normalization, etc.

[0023] S43. Standardized comprehensive data set of the items for a single category based on cosine similarity. In the comprehensive data of item categories, the last process data Corresponding category standardized data The similarity to the average value of the standardized category data corresponding to all the previous process data is calculated to generate the current similarity data of the item's single category comprehensive data. , The calculation formula is as follows:

[0024] ;

[0025] and They represent respectively to and The Euclidean norm is used for calculation;

[0026] S43. Determine the comprehensive data set of the single category of the item. Current similarity data for each item category If the similarity is less than the set threshold, then the item status judgment data is processed. Output item status error; otherwise, output item status judgment data. The output item is in normal condition.

[0027] Furthermore, the barcode item anomaly type analysis module generates item process anomaly type analysis data, including the following steps:

[0028] S51. Collect the status characteristic data of items of various categories under different anomaly types, and generate status characteristic data of anomaly type items. , , This represents the item status feature data corresponding to the q-th anomaly type of the p-th barcode, where... , This represents the status feature data of the item with the qth anomaly type when it is associated with the pth barcode, and the status feature data of the item with the 0th category.

[0029] S52. If the item status is abnormal, obtain the corresponding process data when the item status is abnormal. In the abnormal type of item status feature data Comprehensive data on search and corresponding items Corresponding process data Corresponding item status data Status data of each category Category state feature data for feature matching Generate item process anomaly type analysis data, including the following steps:

[0030] S521. Comprehensive data of the item Process data when item status is abnormal Corresponding item status data Status data of each category in Extract and generate abnormal item status data. , This represents the o-th type of exception status data corresponding to the u-th process of the p-th barcode;

[0031] S522, Regarding the abnormal type of item status feature data and abnormal item status data Standardization processing is performed to generate standardized data on the status characteristics of abnormal items. Standardized data on abnormal item status ;

[0032] S523. Initialize algorithm parameters, based on the standardized data of the abnormal type item state characteristics. n anomaly type search particles are randomly generated in the search space. , Indicates the i-th anomaly type search particle in The location inside, This represents the position of the i-th anomaly type search particle in the o-th category state. The initialization algorithm parameters include the initial maximum number of iterations T and the inertia weight. Individual learning factor Global learning factor random numbers , The range of values , and They represent Minimum and maximum values, initial particle velocity ;

[0033] S524. Calculate the search particle for each anomaly type based on the fitness function. The fitness value, wherein the fitness function is equal to the fitness value of the anomaly type search particle. Standardized data on abnormal item status The reciprocal of the cosine similarity plus 1;

[0034] S525, Search for particles for each anomaly type The position with the minimum fitness value in the historical iterations is taken as the optimal position of the individual. Search for particles of all abnormal types The position with the smallest fitness value in the historical iterations is taken as the global optimum. ;

[0035] S526, Search for particles for each anomaly type The particle velocity is updated using the following formula:

[0036] ,

[0037] ,

[0038] Where t is the current iteration number, This represents the particle velocity of the i-th anomaly type search particle in the o-th category state. This represents the position of the i-th anomaly type search particle in the o-th category state. express The best historical position Indicates all The globally optimal position, The inertia weight decreases with the number of iterations. For individual learning factors, The global learning factor is a random number. ;

[0039] S527, based on updated particle velocity Search for particles for each anomaly type Update the position and calculate the fitness value. The updated formula is as follows:

[0040] ,

[0041] ,

[0042] ,

[0043] in, Indicates will Limited to and Between, if greater than Then take If less than Then take ;

[0044] S528, Search for particles based on each updated anomaly type The fitness value is used to update the individual's optimal position. and global optimal position ;

[0045] S529. Determine if the maximum number of iterations T has been reached. If so, output the globally optimal position. Corresponding category state feature data Generate data on abnormal item processing types. If not, return to S526.

[0046] Furthermore, the barcode error prevention management module constructs barcode error prevention management data and performs barcode error prevention management information feedback operations based on the barcode error prevention management data, including the following steps:

[0047] S61. Comprehensive data of the item Item status judgment data Analysis data on abnormal types of items in the process Collect and combine data to generate barcode error prevention management data K = ( , , );

[0048] S62, if the item status judgment data in the barcode error prevention management data K... If the item's status is determined to be normal, the error prevention management data K is recorded, and the item process anomaly type analysis data is then generated. It is a null value;

[0049] S63, if the item status judgment data in the barcode error prevention management data K... If an item's status is determined to be abnormal, the barcode error prevention management data K is fed back to the system administrator. Further, comprehensive data about the item can be analyzed. Item status judgment data The corresponding process for judging anomalies Data groups are specially marked, such as highlighted, or extracted and displayed separately, so that system administrators can quickly find the barcode information corresponding to the anomaly. Process data and item status data .

[0050] 1. Compared with the prior art, the M10 system barcode error prevention system provided by the present invention, by setting up a barcode scanning module, a sensor module, an item barcode status binding module, and an item status anomaly judgment module, can bind the barcode data with multiple status data of the item corresponding to the barcode during each barcode scan. This allows the system to automatically compare the item status data with the status data of the corresponding barcode in the previous process after each barcode scan and item status data collection. This enables rapid judgment of whether the item status corresponding to the barcode is abnormal, allowing the system to detect items during barcode scanning error prevention.

[0051] 2. Compared with the prior art, the M10 system barcode error prevention system provided by the present invention, by setting up a barcode item anomaly type analysis module and a barcode error prevention management module, can analyze the type of anomaly after the item corresponding to the barcode has an anomaly, and provide feedback to the system administrator to remind them, so that the administrator can quickly understand the anomaly type and status data of the abnormal item, and verify and process the abnormal item. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0053] Figure 1 A system structure block diagram provided for embodiments of the present invention;

[0054] Figure 2 A diagram illustrating the system implementation steps provided in this embodiment of the invention. Detailed Implementation

[0055] To enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0056] Exemplary embodiments will be described more fully below with reference to the accompanying drawings; however, these exemplary embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will enable those skilled in the art to fully understand the scope of this disclosure.

[0057] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0058] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0059] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. As used herein, the singular forms “a” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded.

[0060] The embodiments described herein can be described with reference to plan views and / or cross-sectional views using the ideal schematic diagrams of this disclosure. Therefore, the example illustrations can be modified according to manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to those shown in the drawings, but include modifications to configurations formed based on manufacturing processes. Therefore, the areas illustrated in the drawings are schematic in nature, and the shapes of the areas shown in the figures illustrate specific shapes of areas of an element, but are not intended to be limiting.

[0061] Please see Figure 1 The M10 system barcode error prevention system includes the following modules:

[0062] The barcode scanning module is used to scan barcodes and record the corresponding process information when scanning barcodes, generating barcode data and process data respectively;

[0063] The sensor module includes multiple sensors used to collect category status data of the item in different processes according to the barcode data collection sequence, and generate item status data; in each process, the sensor module is installed together with the barcode scanning module so that the item status is collected while barcode scanning is being performed.

[0064] The item barcode status binding module is used to collect and combine barcode data, process data and item status data to generate comprehensive item data;

[0065] The item status anomaly judgment module is used to perform similarity analysis on the item status data of the current process and the previous process based on the comprehensive item data, judge whether the item status is abnormal, and generate item status judgment data.

[0066] The barcode item anomaly type analysis module is used to perform anomaly type analysis and processing corresponding to the item's comprehensive data based on the item's comprehensive data and the item's anomaly type comprehensive feature data when the item's status is abnormal, and to generate item process anomaly type analysis data.

[0067] The barcode error prevention management module is used to build barcode error prevention management data and perform barcode error prevention management information feedback operations based on the barcode error prevention management data.

[0068] Please see Figure 2 The M10 system barcode error prevention system provided by this invention is implemented through the following steps:

[0069] S1. The barcode scanning module generates barcode data and process data, including the following steps:

[0070] S11. Scan the barcode information using the barcode scanning module to generate a barcode data set. , p represents the p-th barcode scanned. This represents the p-th barcode data, where the barcode is generated according to the set barcode rules and associated with the corresponding item information entered into the database, such as the item's category, production date, name, specifications, batch number, etc.

[0071] S12. Generate a process data set by collecting the process information corresponding to the barcode scanning module. , , u represents the u-th process, This represents the u-th process data corresponding to the p-th barcode. The process data can be bound to the ID of the barcode scanning module of each process by setting the process data. The process data corresponding to the barcode data can be generated by searching for the process data corresponding to the ID of the barcode scanning module that generated the barcode data.

[0072] S2. The sensor module generates item status data, including the following steps:

[0073] S21. Using multiple sensors to scan barcode data The system collects item status information in each process sequentially, generating an item status data set. , This represents the item status data corresponding to the p-th barcode and the u-th process. , , o represents the o-th category state, This represents the o-th category status data corresponding to the u-th process of the p-th barcode; for example, the weight data of the item can be collected by a gravity sensor, the temperature information of the item can be collected by a temperature sensor, the humidity information of the item can be collected by a humidity sensor, and the high-definition image information of the item can be collected by a high-definition camera sensor, etc.

[0074] S3. The item barcode status binding module generates comprehensive item data, including the following steps:

[0075] S31. Collect and combine the corresponding barcode data, process data, and item status data according to the order of the process data to generate comprehensive item data. In other words, the comprehensive data of an item includes the item's barcode data, its process data, and the status data of various items within that process; among these, the comprehensive item data... The further extension is as follows:

[0076] .

[0077] S4. The item status anomaly detection module determines whether the item status is abnormal, including the following steps:

[0078] S41, Based on comprehensive item data For category status o and barcode data Same barcode data Process data and category status data The corresponding data is collected and combined to generate O comprehensive datasets for each item category. ,in, , ;

[0079] S42, Comprehensive data set for a single category of items Category status data Standardization processing is performed to generate categorically standardized data. Standardized comprehensive dataset of item categories Further standardization processing also includes the analysis of category status data. Perform vectorization, missing value handling, normalization, etc.

[0080] S43. Standardized comprehensive dataset for single-category items based on cosine similarity. In the comprehensive data of item categories, the last process data Corresponding category standardized data The similarity to the average value of the standardized category data corresponding to all the previous process data is calculated to generate the current similarity data of the item's single category comprehensive data. , The calculation formula is as follows:

[0081] ;

[0082] and They represent respectively to and The Euclidean norm is used for calculation;

[0083] S43. Determine the comprehensive data set of a single item category. Current similarity data for each item category If the similarity is less than the set threshold, then the item status judgment data is processed. Output item status error; otherwise, output item status judgment data. The output item is in normal condition.

[0084] S5, the barcode item anomaly type analysis module generates item process anomaly type analysis data, including the following steps:

[0085] S51. Collect the status characteristic data of items of various categories under different anomaly types, and generate status characteristic data of anomaly type items. , , This represents the item status feature data corresponding to the q-th anomaly type of the p-th barcode, where... , This represents the status feature data of the item with the qth anomaly type when it is associated with the pth barcode, and the status feature data of the item with the 0th category.

[0086] S52. If the item status is abnormal, obtain the corresponding process data when the item status is abnormal. In the abnormal type item status feature data Comprehensive data on search and corresponding items Corresponding process data Corresponding item status data Status data of each category Category state feature data for feature matching Generate item process anomaly type analysis data, including the following steps:

[0087] S521, Comprehensive data on items Process data when item status is abnormal Corresponding item status data Status data of each category in Extract and generate abnormal item status data. , This represents the o-th type of exception status data corresponding to the u-th process of the p-th barcode;

[0088] S522, Status characteristic data of abnormal type items and abnormal item status data Standardization processing is performed to generate standardized data on the status characteristics of abnormal items. Standardized data on abnormal item status ;

[0089] S523. Initialize algorithm parameters, standardize data on the state characteristics of abnormal items. n anomaly type search particles are randomly generated in the search space. , Indicates the i-th anomaly type search particle in The location inside, This represents the position of the i-th anomaly type search particle in the o-th category state. The initialization algorithm parameters include the initial maximum number of iterations T and the inertia weight. Individual learning factor Global learning factor random numbers , The range of values , and They represent Minimum and maximum values, initial particle velocity ;

[0090] S524. Calculate the search particle for each anomaly type based on the fitness function. The fitness value, the fitness function is equal to the anomaly type search particle Standardized data on abnormal item status The reciprocal of the cosine similarity plus 1;

[0091] S525, Search for particles for each anomaly type The position with the minimum fitness value in the historical iterations is taken as the optimal position of the individual. Search for particles of all abnormal types The position with the smallest fitness value in the historical iterations is taken as the global optimum. ;

[0092] S526, Search for particles for each anomaly type The particle velocity is updated using the following formula:

[0093] ,

[0094] ,

[0095] Where t is the current iteration number, This represents the particle velocity of the i-th anomaly type search particle in the o-th category state. This represents the position of the i-th anomaly type search particle in the o-th category state. express The best historical position Indicates all The globally optimal position, The inertia weight decreases with the number of iterations. For individual learning factors, The global learning factor is a random number. ;

[0096] S527, based on updated particle velocity Search for particles for each anomaly type Update the position and calculate the fitness value. The updated formula is as follows:

[0097] ,

[0098] ,

[0099] ,

[0100] in, Indicates will Limited to and Between, if greater than Then take If less than Then take ;

[0101] S528, Search for particles based on each updated anomaly type The fitness value is used to update the individual's optimal position. and global optimal position ;

[0102] S529. Determine if the maximum number of iterations T has been reached. If so, output the globally optimal position. Corresponding category state feature data Generate data on abnormal item processing types. If not, return to S526.

[0103] S6. The barcode error prevention management module constructs barcode error prevention management data and performs barcode error prevention management information feedback operations based on the barcode error prevention management data, including the following steps:

[0104] S61, Comprehensive data on items Item status judgment data Analysis data on abnormal types of items in the process Collect and combine data to generate barcode error prevention management data K = ( , , );

[0105] S62, If the item status judgment data in the barcode error prevention management data K If the item's status is determined to be normal, the barcode error prevention management data K is recorded, and the item's process anomaly type analysis data is then generated. It is a null value;

[0106] S63, If the item status judgment data in the barcode error prevention management data K If an item's status is determined to be abnormal, the barcode error prevention management data K is fed back to the system administrator. Further, comprehensive data on the item can be analyzed. Item status judgment data The corresponding process for judging anomalies Data groups are specially marked, such as highlighted, or extracted and displayed separately, so that system administrators can quickly find the barcode information corresponding to the anomaly. Process data and item status data .

[0107] In one embodiment, if the barcode error prevention management data K contains comprehensive item data... China lacks Data group, i.e. The number of data sets is not the same as the total data for the corresponding items. If the maximum number is U, it indicates that the corresponding item is lost or missed scanning; if barcode information exists... Not in the corresponding item comprehensive data If it is in the middle, it means that other items have entered the process.

[0108] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. The M10 system barcode error prevention system, characterized in that: Includes the following modules: The barcode scanning module is used to scan barcodes and record the corresponding process information when scanning barcodes, generating barcode data and process data respectively; The sensor module includes various sensors used to collect category status data of items in different categories at each stage of the process, according to the order of barcode data collection, and generate item status data; The item barcode status binding module is used to collect and combine the barcode data, process data and item status data to generate comprehensive item data. The item status anomaly judgment module is used to perform similarity analysis on the item status data of the current process and all previous processes based on the comprehensive item data, judge whether the item status is abnormal, and generate item status judgment data. The barcode item anomaly type analysis module is used to perform anomaly type analysis processing on the item's comprehensive data and anomaly type item comprehensive feature data when the item's status is abnormal, and generate item process anomaly type analysis data. The barcode error prevention management module is used to construct barcode error prevention management data and perform barcode error prevention management information feedback operations based on the barcode error prevention management data, including the following steps: S61. Collect and combine the comprehensive data of the item, the item status judgment data, and the item process abnormality type analysis data to generate barcode error prevention management data; S62. If the item status judgment data in the barcode error prevention management data determines that the item status is normal, then the barcode error prevention management data is recorded. S63. If the item status judgment data in the barcode error prevention management data determines that the item status is abnormal, then the barcode error prevention management data is fed back to the system administrator.

2. The M10 system barcode error prevention system according to claim 1, characterized in that: The barcode scanning module generates barcode data and process data, including the following steps: S11. Scan the barcode information using the barcode scanning module to generate barcode data to form a barcode data set; S12. By collecting the process information corresponding to the barcode scanning module, process data is generated to form a process data set.

3. The M10 system barcode error prevention system according to claim 1, characterized in that: The sensor module generates item status data, including the following steps: S21. Collect the status information of the items in each process through multiple sensors in the order of barcode data, and generate an item status data set.

4. The M10 system barcode error prevention system according to claim 1, characterized in that: The item barcode status binding module generates comprehensive item data, including the following steps: S31. Collect and combine the corresponding barcode data, process data and item status data according to the order of process data to generate comprehensive item data.

5. The M10 system barcode error prevention system according to claim 1, characterized in that: The item status anomaly detection module determines whether an item's status is abnormal, including the following steps: S41. Based on the comprehensive data of items, collect and combine barcode data, process data and category status data that have the same category status and barcode data to generate multiple comprehensive data sets of single category items. S42. Standardize the category status data in the single-category comprehensive dataset of items to generate standardized category data and standardized single-category comprehensive dataset of items. S43. Based on cosine similarity, calculate the similarity between the category-standardized data corresponding to the last process data and the average of the category-standardized data corresponding to all previous process data in the item single-category standardized comprehensive data set, and generate the current similarity data of the item single-category comprehensive data. S44. Determine whether the current similarity data of each item in the single-category comprehensive data set is less than the set similarity threshold. If yes, the item status judgment data outputs that the item status is abnormal; otherwise, the item status judgment data outputs that the item status is normal.

6. The M10 system barcode error prevention system according to claim 1, characterized in that: The barcode item anomaly type analysis module generates item process anomaly type analysis data, including the following steps: S51. Collect the status feature data of each category of items under various abnormal types, and generate the status feature data of abnormal type items; S52. If the item status is abnormal, obtain the process data corresponding to the abnormal item status, search for category status feature data in the abnormal item status feature data that matches the category status data features in the item status data corresponding to the process data in the corresponding comprehensive item data, and generate item process abnormality type analysis data, including the following steps: S521. Extract the status data of each category from the item status data corresponding to the process data when the item status is abnormal in the comprehensive item data, and generate abnormal item status data. S522. Standardize the abnormal type item status feature data and abnormal item status data to generate abnormal type item status feature standardized data and abnormal item status standardized data. S523. Initialize algorithm parameters, based on the standardized data of the abnormal type item state characteristics. n anomaly type search particles are randomly generated in the search space. , Indicates the i-th anomaly type search particle in The location inside, This represents the position of the i-th anomaly type search particle in the o-th category state, where o = 1, 2, ..., O; S524. Calculate the search particle for each anomaly type based on the fitness function. The fitness value, wherein the fitness function is equal to the fitness value of the anomaly type search particle. The reciprocal of the cosine similarity to the standardized data of abnormal item status plus 1; S525, Search for particles for each anomaly type The position with the minimum fitness value in the historical iterations is taken as the optimal position of the individual. Search for particles of all abnormal types The position with the smallest fitness value in the historical iterations is taken as the global optimum. ; S526, Search for particles for each anomaly type The particle velocity is updated using the following formula: ， ， Where t is the current iteration number, This represents the particle velocity of the i-th anomaly type search particle in the o-th category state. This represents the position of the i-th anomaly type search particle in the o-th category state. express The best historical position Indicates all The globally optimal position, The inertia weight decreases with the number of iterations. For individual learning factors, The global learning factor is a random number. ; S527, based on updated particle velocity Search for particles for each anomaly type Update the position and calculate the fitness value. The updated formula is as follows: ， ， ， in, Indicates will Limited to and Between, if greater than Then take If less than Then take ; S528, Search for particles based on each updated anomaly type The fitness value is used to update the individual's optimal position. and global optimal position ; S529. Determine if the maximum number of iterations T has been reached. If so, output the globally optimal position. The corresponding category status feature data is used to generate item flow anomaly type analysis data; otherwise, return S526.

Images