Product barcode correction method and system combined with timing analysis

Abstract

The application discloses a product barcode correction method and system combined with time sequence analysis, and belongs to the technical field of automatic identification. The method comprises the following steps: configuring a scanner at station 0 to scan a product barcode; using a health score network to perform health scoring on a real-time scanning image, establishing a product barcode score value, and obtaining a time sequence position of a corresponding product; performing score value discrimination on the product barcode score value; if the score value discrimination result is a result lower than a preset score threshold, the corresponding product is identified as a weak barcode, and a station skipping correction instruction is triggered; station complement code adaptive identification is performed according to the station skipping correction instruction; a complement code station is selected based on an adaptive optimization result, product information calling based on the time sequence position is performed by using the complement code station, and complement code processing is performed on the corresponding product according to a product information calling result. The application solves the technical problems of unstable product barcode identification quality, inability to dynamically adjust a correction strategy, high barcode error rate and low correction efficiency in the prior art.

Description

Technical Field

[0001] This invention relates to the field of automated identification technology, specifically to a product barcode correction method and system that incorporates time-series analysis. Background Technology

[0002] Barcode technology, as a crucial information identification method in the manufacturing and retail industries, has a critical impact on product traceability, inventory management, and production efficiency due to its reliability and accuracy. In practical applications, barcodes are read by scanning devices. However, limitations in barcode printing quality, scanning equipment performance, and the complexity of the production environment can easily lead to identification errors or missing information during the reading process, affecting the integrity of data collection. To address this issue, researching automatic correction technologies for barcode information has become an important direction for ensuring data consistency throughout the entire product lifecycle.

[0003] Existing barcode correction methods typically rely on fixed rules or simple algorithms, offering limited remediation capabilities for barcode information. In the initial stages of product barcode scanning, scanners often fail to recognize or misinterpret barcodes due to issues such as barcode damage or unclear printing. Current solutions cannot dynamically adjust correction strategies or fully integrate production line timing information, resulting in missing barcode data for some products and severely impacting the accuracy and timeliness of subsequent product data processing. Therefore, a solution combining timing analysis and intelligent correction mechanisms is urgently needed to reduce barcode recognition error rates and improve production process efficiency. Summary of the Invention

[0004] This application provides a product barcode correction method and system that combines time-series analysis, aiming to solve the technical problems in the prior art of unstable product barcode recognition quality and inability to dynamically adjust correction strategies, resulting in high barcode error rates and low correction efficiency.

[0005] In view of the above problems, this application provides a product barcode correction method and system that combines time series analysis.

[0006] The first aspect disclosed in this application provides a product barcode correction method incorporating time-series analysis. This method includes configuring a scanner at station 0 to scan product barcodes and establish a real-time scan image; configuring a health scoring network, using the health scoring network to perform a health score on the real-time scan image, establishing a product barcode score, and obtaining the time-series position of the corresponding product; performing a score determination on the product barcode score, and if the score determination result is lower than a preset score threshold, then identifying the corresponding product as a weak barcode and triggering a station-skipping correction instruction; performing station-scanning code adaptation identification based on the station-skipping correction instruction, establishing an adaptation optimization result; selecting a code-scanning station based on the adaptation optimization result, using the code-scanning station to retrieve product information based on the time-series position, and performing corresponding product code-scanning processing based on the product information retrieval result.

[0007] Another aspect of this application discloses a product barcode correction system incorporating time-series analysis. This system includes a real-time scan image creation module for configuring a scanner at station 0 to scan product barcodes and create a real-time scan image; a scoring module for configuring a health scoring network, using the health scoring network to perform a health score on the real-time scan image, creating a product barcode scoring score, and obtaining the time-series position of the corresponding product; a score discrimination module for discriminating the product barcode scoring score; if the score discrimination result is lower than a preset scoring threshold, the corresponding product is identified as a weak barcode, and a station-skipping correction command is triggered; an adaptation optimization result creation module for performing station-level code replacement adaptation identification based on the station-skipping correction command and creating an adaptation optimization result; and a code replacement processing module for selecting a code replacement station based on the adaptation optimization result, using the code replacement station to retrieve product information based on the time-series position, and performing code replacement processing on the corresponding product based on the product information retrieval result.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By employing a product barcode correction method that incorporates time-series analysis, including configuring scanners to create real-time scan images, using a health scoring network for scoring, determining barcode quality and triggering skip-station correction commands, selecting supplementary code stations based on adaptation optimization results, and performing supplementary code processing, this approach solves the technical problems of unstable product barcode recognition quality and the inability to dynamically adjust correction strategies in existing technologies, resulting in high barcode error rates and low correction efficiency. This achieves the technical effects of improving barcode recognition accuracy, optimizing the correction process, and increasing production efficiency.

[0010] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0011] Figure 1 A flowchart illustrating a product barcode correction method incorporating time-series analysis is provided for embodiments of this application.

[0012] Figure 2 A schematic diagram of the structure of a product barcode correction system incorporating time-series analysis is provided for embodiments of this application.

[0013] Figure labeling: Real-time scan image creation module 11, scoring value creation module 12, score discrimination module 13, adaptation optimization result creation module 14, two's complement processing module 15. Detailed Implementation

[0014] The overall concept of the technical solution provided in this application is as follows:

[0015] This application provides a product barcode correction method and system that incorporates time-series analysis. First, the barcode is scanned at station 0 to create a real-time image. A health scoring network is used to evaluate the barcode quality, generating a score and making a judgment. Barcodes below a preset threshold are marked as weak barcodes, triggering a station-skipping correction command. Subsequently, the optimal barcode correction station is selected through load and delay analysis of the replacement station, and product information is retrieved to complete the barcode correction operation.

[0016] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0017] Example 1, as Figure 1 As shown in the embodiments of this application, a product barcode correction method combining time series analysis is provided, the method comprising:

[0018] Step S100: Configure a scanner at station 0 to scan product barcodes and create a real-time scan image.

[0019] Specifically, station 0 refers to the first station on the production line, typically used for initialization processes such as barcode scanning or product information entry, marking the starting point of the production process. A scanner is a barcode recognition device that uses optical technology to scan barcodes and interpret them into digital signals, which are then transmitted to the data processing system. Common types of scanners include laser barcode scanners, linear imaging scanners, and 2D image scanners.

[0020] A high-precision barcode scanner is installed at station 0 of the production line. By configuring parameters such as the light source, focal length, and photosensitive element, it can quickly capture barcode images of each product passing through the production line. Specifically, the scanner is fixedly mounted above the conveyor belt at station 0. The distance between the scanner and the product surface, the scanning angle, and the light source intensity are adjusted to optimally cover the product's barcode area. When a product on the conveyor belt passes through station 0, the sensor detects that the product has entered the scanning area, and the scanner immediately triggers the image capture operation, acquiring the barcode image and transmitting it to the back-end system in real time. The barcode image transmitted by the scanner is processed by a built-in algorithm, including noise reduction, contrast enhancement, barcode area cropping, and image tilt angle correction, for subsequent health scoring and recognition.

[0021] By configuring a high-precision barcode scanner at station 0 and creating barcode scanning images in real time, the real-time status image of the barcode can be captured efficiently and accurately, providing a reliable data foundation for subsequent health scoring and correction operations.

[0022] Step S200: Configure the health scoring network, use the health scoring network to perform health scoring on the real-time scanned image, establish product barcode scoring scores, and obtain the time sequence position of the corresponding product.

[0023] Specifically, the health scoring network is a deep learning-based artificial neural network used to analyze barcode image quality, assess the barcode's health status (such as clarity, integrity, and contrast), and provide a numerical score. The product barcode score is a numerical indicator derived from the health scoring network analysis results, used to quantify the quality of the barcode image; a higher score indicates a better barcode health status. The temporal position refers to the product's sequential arrangement on the production line, recording the order in which the product passes through scanning stations.

[0024] A health scoring model based on convolutional neural networks (CNNs), such as deep learning models built with TensorFlow or PyTorch, is used to automatically extract barcode features (e.g., edge sharpness, contrast, and continuity) from real-time scanned images and output a score. The real-time scanned images are then input into the health scoring network, which uses convolutional layers to extract key image features (e.g., smoothness, straightness, and continuity of barcode lines). The network labels blurred areas of the barcode and calculates their impact weights. Based on the extracted features, the health scoring network uses a weighted model to calculate a comprehensive score and saves the result to the product database. Simultaneously, the system records the production sequence position of each product and maps it one-to-one with the barcode score. The product's sequence position is updated in real-time on the production line for subsequent station skipping correction operations.

[0025] By introducing a health scoring network, the system can accurately identify the quality of barcode images and generate a numerical score for each product. Combined with the product's temporal position, the system can quickly identify weak barcodes and plan correction paths. Overall, this step significantly improves the automation level of barcode scanning and the reliability of data processing, laying the foundation for subsequent process optimization.

[0026] Step S300: The product barcode score is judged. If the score is lower than the preset score threshold, the corresponding product is marked as a weak barcode and a station skipping correction command is triggered.

[0027] Specifically, weak barcodes refer to barcodes with scores below a preset scoring threshold, typically due to issues such as blurred edges, breaks, discontinuities, or insufficient contrast, resulting in substandard barcode quality. A skip-station correction instruction is a system-generated command that, once a barcode is marked as weak, instructs the production line to skip its current station and proceed to a designated replacement station to perform barcode correction.

[0028] After obtaining the product barcode score, the system compares it with a preset scoring threshold. If the score is lower than the threshold, it is determined to be a weak barcode; if the score is higher than or equal to the threshold, it is determined to be a normal barcode and no correction is needed. For products determined to have weak barcodes, a skip-station correction instruction is generated, instructing the production line to skip the current station and proceed to the designated supplementary barcode station.

[0029] By using score discrimination, weak barcode identification, and triggering skip station correction instructions, the system can quickly filter out barcodes that need correction and accurately guide them to the appropriate replacement station, thereby improving the automation level of the production line and the efficiency of barcode correction.

[0030] Step S400: Perform station position complementation identification according to the station jump correction instruction, and establish the adaptation optimization result.

[0031] Specifically, barcode replacement and adaptation identification refers to dynamically evaluating and selecting the most suitable station for barcode replacement correction based on the actual status of each station in the production line (such as workload and delay time). The optimization result refers to calculating and selecting an optimal station by combining station load analysis and delay constraints, ensuring that the replacement operation achieves the best balance between production efficiency and accuracy. Delay time refers to the additional time required for the product to complete the replacement correction, including flow delay time and queue delay time caused by queuing or station transmission. Constraints refer to the maximum allowable range of load and delay time, used to filter available replacement stations.

[0032] The system receives a station skipping correction command, identifies the barcode product requiring replacement and its current station position, and retrieves the replacement station position information database. It then analyzes all potential replacement stations on the production line, including load analysis and delay time calculation. Based on the production line's maximum load and delay time limits, stations meeting the constraints are selected. Among these stations, the one with the lightest load and shortest delay time is chosen as the replacement station. The optimization results are output, including the optimal station number, estimated delay time, and replacement operation time.

[0033] By combining station-skipping correction commands with station-position complement code adaptation and recognition, the system can dynamically adjust barcode correction strategies to ensure the efficiency and stability of the production line. This method makes full use of production line resources, avoids resource waste and production delays caused by random station selection, achieves high efficiency and intelligence in barcode complement code correction, and improves the overall production quality management level.

[0034] Step S500: Select the complement code station position based on the adaptation optimization result, use the complement code station position to call product information based on the time sequence position, and perform corresponding product complement code processing according to the product information call result.

[0035] Specifically, the time sequence position refers to the order in which products are arranged on the production line. It is used to track the production status and flow information of each product, ensuring the correspondence between product information retrieval and barcode replacement processing. Product information retrieval refers to the system retrieving product-related information from the database based on the time sequence position, including the product number, barcode image, and its health score, to guide barcode replacement correction. Barcode replacement processing refers to the correction or regeneration of the barcode at the replacement station based on the results of the product information retrieval, such as barcode reprinting, error correction, or information completion.

[0036] The system determines the target barcode replacement station based on the optimization results and controls a conveyor belt or robotic arm to deliver the product to that station. During transmission, the system synchronously updates the product's temporal position to ensure consistency between the replacement operation and product information. Upon arrival at the replacement station, the system extracts specific product-related information from the database based on the temporal position, including: product number and barcode image; health score; and identified barcode defect types (e.g., blurriness, discontinuity). Based on the retrieved product information, the replacement station processes the barcode using a preset correction mechanism, including: barcode reprinting: regenerating a clear barcode using a barcode printer and covering the old barcode; optical error correction: correcting blurry or broken barcode lines using laser engraving; and rescanning: for barcodes that fail to be read, re-identifying the barcode by optimizing the scanning angle or adjusting the light source. Specifically, the replacement station can be configured with a high-precision barcode printer (such as the Zebra series), laser engraving equipment, or a high-resolution scanner, combined with image processing software (such as OpenCV) to achieve efficient barcode replacement. After the barcode replacement process is completed, the system records the results of the replacement operation, including the barcode status before and after the correction, the correction time, and other information, so as to facilitate subsequent traceability and process optimization.

[0037] By selecting the barcode replacement station based on the optimization results and calling product information for replacement processing, the system can ensure the accuracy and efficiency of barcode correction operations while reducing manual intervention. It can not only dynamically allocate replacement tasks but also perform personalized correction operations for specific problems, significantly improving the level of automation and the reliability of barcode data.

[0038] Furthermore, the step of using the health scoring network to perform health scoring on the real-time scanned image and establishing a product barcode score includes: using the positioning preprocessing layer of the health scoring network to perform attention positioning on the real-time scanned image and establish attention positioning results; extracting edge contours from the attention positioning results and scoring edge smoothness based on the edge contour extraction results to generate a first score result; scoring edge straightness based on the edge contour extraction results to establish a second score result; scoring edge continuity based on the edge contour extraction results to establish a third score result; identifying the contrast between the attention positioning results and the background of the real-time scanned image to establish a fourth score result; and establishing a product barcode score based on the first score result, the second score result, the third score result, and the fourth score result.

[0039] Specifically, the localization preprocessing layer, the first layer in the health scoring network, is used to identify the region of interest in the barcode image and remove background parts irrelevant to the barcode, thereby improving the accuracy and efficiency of subsequent feature analysis. Edge smoothness scoring calculates the smoothness of the barcode based on the angle changes of the barcode lines; a high score indicates smooth barcode lines without abrupt changes. Edge straightness scoring evaluates the straightness of the barcode lines, quantifying whether the barcode possesses good straightness through the coefficient of determination of linear fitting. Edge continuity scoring measures whether there are breaks or gaps in the barcode lines; a high score indicates no obvious interruptions in the barcode lines.

[0040] After the barcode image is input into the health scoring network, the localization preprocessing layer first identifies the region of interest (ROI) of the barcode. This process is achieved through a sliding window combined with convolution operations. For example, OpenCV's image segmentation algorithm is used to separate the barcode region from the background. The edge lines of the barcode are extracted using the Canny edge detection method, and a contour image is generated. The contour extraction results provide the basis for subsequent scoring. Example: For a blurry barcode, the contour extraction identifies most of the lines, but breakpoints and blurry areas still exist. The contour lines are analyzed, the angle changes between adjacent points on the lines are calculated, and a score is given based on the smoothness of the changes. Barcodes with smaller angle changes score higher. Linear regression is used to fit the contour lines, and the coefficient of determination is calculated to quantify the straightness. The higher the fitting accuracy, the higher the score. The number of contour breakpoints and the maximum gap length are detected, and the breakage is quantified into a score. Barcodes with fewer gaps and better continuity score higher.

[0041] The contrast is quantified and scored by analyzing the difference in grayscale values ​​between the barcode area and the background. For example, the difference in the mean grayscale values ​​between the barcode area and the background is calculated. A barcode score is generated by combining scores for smoothness, linearity, continuity, and contrast, weighted according to a specific ratio. For example, smoothness accounts for 30%, linearity for 25%, continuity for 25%, and contrast for 20%.

[0042] By utilizing a health scoring network to perform multi-dimensional analysis of real-time scanned images, the system can accurately and comprehensively assess barcode quality and generate scientific scores, providing a basis for subsequent corrective actions. Overall, this step significantly improves the reliability of barcode recognition and the level of automation on the production line.

[0043] Furthermore, the first scoring result is calculated as follows:

[0044] ;

[0045] ;

[0046] in, Characterizes edge smoothness score, Characterizing the average angle change between edge points, The threshold for characterizing edge angle changes Represents the total number of points on the same straight line. Represents any point on the current line. Characterizing the first Point to number The direction angle of the point, Characterizing the first Point to number The direction angle of the point.

[0047] Specifically, the edge smoothness score is a rating used to evaluate the smoothness of barcode edge lines. A higher score indicates a smoother edge, more uniform lines, and better quality. Average angle variation refers to the average angle variation between adjacent lines on the barcode edge, reflecting the smoothness of the lines. Small angle variations indicate smooth line connections. The edge angle variation threshold is a benchmark value used to measure smoothness, usually a preset standard, indicating the range within which lines can be considered smooth. Direction angle refers to the direction between points on the edge line, used to describe the trend of the barcode lines. Total number of points refers to the total number of points on the edge lines, representing the length and complexity of the barcode lines.

[0048] First, extract the coordinates of all points along the edge of the barcode. , ), calculate the direction angle of each pair of adjacent points. , specifically: If the lines are smooth, the changes in these directional angles will be very small; if the lines are not smooth, the directional angles will change significantly. Then, the changes in directional angles at all adjacent points are statistically analyzed to calculate the average angle change along the barcode edge. The smaller this average value, the smoother the lines. Based on the statistically analyzed angle change values, this is compared to a set smoothness standard to generate a score. The score typically ranges from 0 to 100; a higher score indicates smoother barcode lines.

[0049] By scoring edge smoothness, the system can quantify the quality of barcode lines, especially when the barcode is broken or uneven due to printing blur or smudges, the score will drop significantly. This scoring mechanism can effectively identify barcodes that need correction, thereby improving the accuracy of barcode scanning.

[0050] Furthermore, the second scoring result is calculated as follows:

[0051] ;

[0052] ;

[0053] in, Characterizing the linearity score of the edge. The coefficient of determination of the fitted line representing the edge points. The minimum standard for characterizing the coefficient of determination. Characterizes the predicted values ​​on the fitted line. Characterizing the average of all points value, Characterizing the first The actual ordinate value of the point.

[0054] Specifically, the edge straightness score is used to evaluate whether the barcode edge lines exhibit good straight-line characteristics. A higher score indicates that the barcode lines are closer to a straight line, and the better the quality. The coefficient of determination is a statistical measure of the degree of fit between the fitted straight line and the actual edge points. The closer the value is to 1, the closer the edge point distribution is to a straight line, and the better the fit. The minimum standard for the coefficient of determination is a threshold used to measure whether the fitting result meets the minimum requirements for straightness.

[0055] The least squares method is used to fit a straight line to the extracted edge points, generating the equation of the fitted line based on the actual ordinates of the edge points. and the predicted value of the fitted straight line ,calculate The calculation and the set minimum standard The comparisons are used to generate a linearity score for the edge. The score ranges from 0 to 100, with a score closer to 100 indicating better linearity.

[0056] Edge straightness scoring effectively identifies line curvature issues caused by poor printing quality or damage by evaluating the overall trend of the barcode edges to ensure they are nearly straight. This scoring method is crucial for barcode recognition quality. Automating this method can also reduce manual intervention, improve production efficiency, and enhance the reliability of barcode recognition.

[0057] Furthermore, the third scoring result is calculated as follows:

[0058] ;

[0059] ;

[0060] in, Characterizing edge continuity score, Characterizes the maximum gap length in the edge profile. Characterizes the maximum allowable gap length threshold. Characterizing the first The actual x-coordinate of the point, Characterizing the first The actual x-coordinate of the point, Characterizing the first The actual ordinate value of the point.

[0061] Specifically, the edge continuity score measures whether the barcode edge lines are continuous, without obvious breaks or gaps. A higher score indicates more continuous edge lines and better barcode quality. The maximum gap length refers to the maximum distance between adjacent points on the barcode edge line, representing the severity of edge breaks or gaps. A smaller value indicates a smaller gap and more continuous edge. The maximum allowable gap length threshold is a preset standard used to determine whether there are unacceptable gaps on the edge. If... If the value exceeds this threshold, it indicates that the barcode quality is poor.

[0062] Calculate the distance between each pair of adjacent points sequentially, using the Pythagorean theorem based on the coordinates of the two points. Record the distances between all points to find the maximum distance (i.e., the maximum gap length). Find the maximum gap length between all pairs of points. and compare it with the maximum allowable gap length threshold. Compare them. If Exceeding the threshold indicates poor continuity of the barcode edges, requiring a correction process to be triggered. A score is calculated based on the ratio of the gap length to the threshold. The score ranges from 0 to 100, with a higher score for smaller maximum gaps.

[0063] By calculating edge continuity scores, the system can accurately assess the integrity of barcode edges and automatically detect breaks and gaps. Combined with the scoring results, it can quickly determine whether the barcode needs correction, avoiding scan failures due to barcode defects.

[0064] Further, the score discrimination of the product barcode score value includes: if the score discrimination result meets the preset score threshold, a normal transfer instruction is generated; and the transfer process of the corresponding product is executed according to the normal transfer instruction.

[0065] Specifically, after receiving the barcode score value, it is compared with the preset score threshold. If the score value is greater than or equal to the threshold, the barcode is regarded as qualified; if it is lower than the threshold, it is marked as a weak barcode that needs to be corrected. For example: the set score threshold of the system is 80, the score of barcode A is 85, and it is judged as qualified; the score of barcode B is 75, and it is marked as a weak barcode.

[0066] For the barcodes determined to be qualified, the system automatically generates a normal transfer instruction and sends it to the control module of the conveyor belt or production equipment through an industrial communication protocol. This instruction may include the product number, barcode score value, and target station information. After receiving the normal transfer instruction, production equipment (such as a conveyor belt or a manipulator) starts the corresponding operation to smoothly transfer the product to the next station. The operating state of the equipment is monitored in real time by sensors to ensure that the transfer process is error-free. While the system executes the transfer process, the score value and transfer instruction are recorded in the database for subsequent analysis and quality traceability.

[0067] Through the score discrimination of the score value and the generation and execution of the normal transfer instruction, the system can achieve rapid screening and efficient processing of barcode quality, greatly improving the automation level of the production line and the accuracy of barcode transfer.

[0068] Further, the position complement code adaptation recognition according to the skip station correction instruction to establish an adaptation optimization result includes: performing a complement code load analysis of the execution position to establish a load constraint, where the complement code load analysis includes continuous load analysis and temporary window load analysis; obtaining the delay time of the position complement code to establish a delay constraint, where the delay time includes transfer delay time and complement code queue delay time; and performing position complement code adaptation optimization according to the load constraint and the delay constraint to generate an adaptation optimization result.

[0069] Specifically, continuous load analysis refers to evaluating the average workload of a station under stable operating conditions. Temporary window load analysis refers to analyzing the additional load on a station due to sudden tasks within a specific time period. Flow delay time refers to the time it takes for a product to be transferred from the current station to the replenishment station, determined by the conveyor belt speed and transmission distance. Replenishment queue delay time refers to the delay time incurred by products waiting in queues at the replenishment station. Load constraint refers to the upper limit of load set by the system based on the production line's operating capacity; if the current load of a station exceeds this threshold, it is considered ineligible. Delay constraint refers to the upper limit of delay time set by the system; if the flow delay time or queue delay time of a station exceeds this limit, that station is excluded.

[0070] The system receives barcode correction instructions, analyzes the product information requiring barcode replacement at a different station and its location, and initiates a station status assessment process. The real-time data acquisition module assesses the current workload of all candidate barcode replacement stations: calculating the average workload currently being processed by each station. For example, station 1's current continuous load is 70%. The system also analyzes load fluctuations caused by short-term task backlogs over a certain period, such as station 2's temporary load reaching 85%.

[0071] The flow delay time is calculated by sensors collecting data on conveyor belt speed and transmission distance. The replenishment queue delay time is calculated by the number of products in the queue and the processing speed. Station flow information is collected in real time by a PLC controller and sensors. The load and delay time of all candidate stations are compared with preset constraints, and stations exceeding the limits are eliminated. Among the stations that meet the conditions, the system calculates the optimal replenishment station based on the principles of minimizing load and delay time, and generates a specific replenishment scheme. The optimization results are sent to the production equipment, controlling the conveyor belt or robotic arm to deliver the product to the optimal replenishment station, and the replenishment operation is monitored in real time.

[0072] By combining station-skipping correction commands with station-position complement code adaptation and recognition, the system achieves intelligent scheduling and optimization of production line resources. This method can dynamically select the optimal station position to perform barcode correction, significantly reducing production line delays and resource waste. It not only improves barcode correction efficiency but also provides technical support for intelligent management of the entire production process.

[0073] In summary, the product barcode correction method combining time-series analysis provided in this application has the following technical effects:

[0074] 1. The barcode correction method combining time-series analysis significantly improves the accuracy of barcode recognition and the integrity of production data by dynamically adjusting scanning, scoring, and correction strategies. Real-time monitoring of barcode health status ensures that quality issues are detected and addressed promptly, reducing barcode loss rates and optimizing production efficiency. It is particularly suitable for automated production lines with high precision requirements.

[0075] 2. By employing a health scoring network to perform multi-dimensional analysis of barcode images (such as smoothness, linearity, and continuity), a refined quality assessment method is provided. This method can comprehensively identify barcode defect types, reduce misjudgments caused by traditional single scoring indicators, and improve the reliability and scientific rigor of barcode health scoring.

[0076] 3. By using score-based discrimination and generating normal transmission instructions, the system can automatically screen and process barcode quality, preventing unqualified barcodes from entering subsequent processes. This mechanism improves the automation level of the production line, reduces manual intervention, ensures the smooth flow of high-quality products, and optimizes overall production efficiency.

[0077] Example 2, based on the same inventive concept as the product barcode correction method combining time-series analysis in the foregoing examples, such as... Figure 2 As shown in the embodiment of this application, a product barcode correction system incorporating time-series analysis is provided. This system includes:

[0078] The real-time scanning image establishment module 11 is used to configure a scanner at station 0 to scan product barcodes and establish a real-time scanning image; the scoring value establishment module 12 is used to configure a health scoring network, use the health scoring network to perform health scoring on the real-time scanning image, establish a product barcode scoring value, and obtain the time sequence position of the corresponding product; the score discrimination module 13 is used to discriminate the product barcode scoring value, and if the score discrimination result is lower than a preset scoring threshold, the corresponding product is identified as a weak barcode and a station skipping correction instruction is triggered; the adaptation optimization result establishment module 14 is used to perform station code supplementation adaptation identification according to the station skipping correction instruction and establish an adaptation optimization result; the code supplementation processing module 15 is used to select a code supplementation station based on the adaptation optimization result, use the code supplementation station to perform product information retrieval based on the time sequence position, and perform corresponding product code supplementation processing according to the product information retrieval result.

[0079] Furthermore, the scoring module 12 is also used to perform the following steps: using the positioning preprocessing layer of the health scoring network to perform attention positioning of the real-time scanned image and establish attention positioning results; extracting edge contours from the attention positioning results and scoring edge smoothness based on the edge contour extraction results to generate a first scoring result; scoring edge straightness based on the edge contour extraction results to establish a second scoring result; scoring edge continuity based on the edge contour extraction results to establish a third scoring result; performing contrast recognition between the attention positioning results and the background of the real-time scanned image to establish a fourth scoring result; and establishing a product barcode scoring value based on the first scoring result, the second scoring result, the third scoring result, and the fourth scoring result.

[0080] Furthermore, the scoring module 12 is also used to perform the following steps:

[0081] ;

[0082] ;

[0083] in, Characterizes edge smoothness score, Characterizing the average angle change between edge points, The threshold for characterizing edge angle changes Represents the total number of points on the same straight line. Represents any point on the current line. Characterizing the first Point to number The direction angle of the point, Characterizing the first Point to number The direction angle of the point.

[0084] Furthermore, the scoring module 12 is also used to perform the following steps:

[0085] ;

[0086] ;

[0087] in, Characterizing the linearity score of the edge. The coefficient of determination of the fitted line representing the edge points. The minimum standard for characterizing the coefficient of determination. Characterizes the predicted values ​​on the fitted line. Characterizing the average of all points value, Characterizing the first The actual ordinate value of the point.

[0088] Furthermore, the scoring module 12 is also used to perform the following steps:

[0089] ;

[0090] ;

[0091] in, Characterizing edge continuity score, Characterizes the maximum gap length in the edge profile. Characterizes the maximum allowable gap length threshold. Characterizing the first The actual x-coordinate of the point, Characterizing the first The actual x-coordinate of the point, Characterizing the first The actual ordinate value of the point.

[0092] Furthermore, the score discrimination module 13 is also used to perform the following steps: if the score discrimination result is a result that meets the preset scoring threshold, then a normal transfer instruction is generated; and the transfer processing of the corresponding product is performed according to the normal transfer instruction.

[0093] Furthermore, the adaptation optimization result establishment module 14 is also used to perform the following steps: perform station complement load analysis and establish load constraints, wherein the complement load analysis includes continuous load analysis and temporary window load analysis; obtain the station complement delay time and establish delay constraints, wherein the delay time includes flow delay time and complement queue delay time; perform station complement adaptation optimization according to the load constraints and the delay constraints, and generate adaptation optimization results.

[0094] In summary, any step of the method described above can be stored as a computer instruction or program in an unrestricted computer memory, and can be called and identified by an unrestricted computer processor to implement any method in the embodiments of this application, without any additional restrictions.

[0095] Furthermore, the "first" or "second" mentioned above may not only represent a sequential relationship, but may also represent a specific concept, and / or refer to the individual or collective selection of multiple elements. Clearly, those skilled in the art can make various modifications and variations to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A product barcode correction method combining time-series analysis, characterized in that, The method includes: A scanner is configured at station 0 to scan product barcodes and create a real-time scan image. Configure a health scoring network, use the health scoring network to score the health of the real-time scanned image, establish a product barcode scoring score, and obtain the time sequence position of the corresponding product. The product barcode score is evaluated. If the score is lower than the preset score threshold, the corresponding product is marked as a weak barcode and a station skipping correction command is triggered. Based on the station jump correction instruction, perform station complementation and identification, and establish adaptation optimization results; Based on the adaptation optimization result, a complement code station is selected, and the product information based on the time sequence position is called using the complement code station. The product complement code processing is performed according to the product information call result. The step of using the health scoring network to perform health scoring on the real-time scanned image and establishing a product barcode scoring score includes: The preprocessing layer of the health scoring network is used to perform attention localization of the real-time scanned image, and attention localization results are established. The focus positioning result is used to extract edge contours, and the edge smoothness is scored based on the edge contour extraction result to generate a first score result; Based on the edge contour extraction results, edge straightness is scored, and a second scoring result is established; Based on the edge contour extraction results, an edge continuity score is performed to establish a third score result; The contrast between the focus positioning result and the background of the real-time scanned image is identified to establish a fourth scoring result; A product barcode scoring score is established based on the first scoring result, the second scoring result, the third scoring result, and the fourth scoring result.

2. The product barcode correction method combining time-series analysis as described in claim 1, characterized in that, The first scoring result is calculated as follows: ; ; in, Characterizes edge smoothness score, Characterizing the average angle change between edge points, The threshold for characterizing edge angle changes Represents the total number of points on the same straight line. Represents any point on the current line. Characterizing the first Point to number The direction angle of the point, Characterizing the first Point to number The direction angle of the point.

3. The product barcode correction method combining time-series analysis as described in claim 2, characterized in that, The second scoring result is calculated as follows: ; ; in, Characterizing the linearity score of the edge. The coefficient of determination of the fitted line representing the edge points. The minimum standard for characterizing the coefficient of determination. Characterizes the predicted values ​​on the fitted line. Characterizing the average of all points value, Characterizing the first The actual ordinate value of the point.

4. The product barcode correction method combining time-series analysis as described in claim 3, characterized in that, The third scoring result is calculated as follows: ; ; in, Characterizing edge continuity score, Characterizes the maximum gap length in the edge profile. Characterizes the maximum allowable gap length threshold. Characterizing the first The actual x-coordinate of the point, Characterizing the first The actual x-coordinate of the point, Characterizing the first The actual ordinate value of the point.

5. The product barcode correction method combining time-series analysis as described in claim 1, characterized in that, The process of determining the score for the product barcode includes: If the score determination result meets the preset scoring threshold, a normal transmission instruction is generated; The corresponding product is processed according to the normal transfer instruction.

6. The product barcode correction method combining time-series analysis as described in claim 1, characterized in that, The step of performing position complementation adaptation identification based on the skip-station correction instruction and establishing adaptation optimization results includes: Perform complement load analysis on the station and establish load constraints. The complement load analysis includes continuous load analysis and temporary window load analysis. The delay time of obtaining the station complement code is used to establish delay constraints, wherein the delay time includes the flow delay time and the complement code queue delay time; Based on the load constraints and the delay constraints, station complement adaptation optimization is performed to generate adaptation optimization results.

7. A product barcode correction system incorporating time-series analysis, characterized in that: The system for performing the method according to any one of claims 1 to 6 includes: The real-time scan image creation module is used to configure a scanner at station 0 to scan product barcodes and create a real-time scan image. The scoring value establishment module is used to configure the health scoring network, use the health scoring network to perform health scoring on the real-time scanned image, establish product barcode scoring values, and obtain the time sequence position of the corresponding product. The score discrimination module is used to discriminate the score of the product barcode. If the score discrimination result is lower than the preset score threshold, the corresponding product is identified as a weak barcode and a station skipping correction instruction is triggered. The adaptation optimization result establishment module is used to perform station complement code adaptation identification according to the station jump correction instruction and establish the adaptation optimization result. The complement code processing module is used to select the complement code position based on the adaptation optimization result, use the complement code position to call product information based on the time sequence position, and perform corresponding product complement code processing according to the product information call result.

Images