Batch chart printing task optimization method and system based on intelligent merging

Abstract

The invention discloses a batch chart printing task optimization method and system based on intelligent merging. According to the method, a chart task data packet is analyzed in real time, an element distribution matrix is constructed, regional color gradation compensation parameters are dynamically calculated in combination with the reflectivity of a printing medium, and a color gradation compensation vector is generated. And clustering the compensation vectors by adopting a hierarchical clustering algorithm to realize self-adaptive combination of the chart printing tasks, and generating a color gradation calibration curve matched with medium characteristics. Through task merging decision and parameter optimization closed loop, the problem of color deviation caused by medium difference in batch printing of nautical charts is solved, and the frequency of repeated calibration of equipment is reduced. Through the intelligent task merging and dynamic calibration technology, the printing efficiency and color consistency are remarkably improved, the printing cost is reduced, and the method is suitable for large-scale high-precision chart printing requirements in the fields of navigation, surveying and mapping and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of printing optimization, and particularly to an optimization method and system for batch nautical chart printing tasks based on intelligent merging. Background Art

[0002] As an indispensable important information carrier during navigation, the printing quality and production efficiency of nautical charts are directly related to navigation safety and navigation accuracy. Traditional nautical chart printing usually adopts the Print-On-Demand (POD) mode, which can perform personalized printing according to user needs. However, the existing nautical chart printing process still faces many challenges when dealing with batches.

[0003] Firstly, the content of nautical charts is complex, including multiple levels such as vector graphics, raster images, nautical symbols, and text annotations. Traditional printing methods are difficult to achieve precise color level control for different regions, resulting in low color restoration of printed products on different media and affecting the final navigation effect. Secondly, current nautical chart printing tasks are often processed independently, and the similarity between tasks is not fully utilized for optimization, resulting in inefficient task allocation and color management during the production process.

[0004] In addition, since nautical charts cover different geographical regions, there are significant differences in the content density of each nautical chart. Traditional printing methods do not perform intelligent compensation based on the element distribution characteristics of nautical charts, and problems such as printing color deviation, detail loss, or overexposure are likely to occur. At the same time, the existing printing task arrangements are relatively scattered, lacking a systematic merging strategy, resulting in low utilization rate of printing equipment, increased production costs, and time overhead.

[0005] With the development of intelligent technologies, it has become a trend in the industry to optimize the nautical chart printing process using image processing, machine learning, and intelligent scheduling methods. Especially by intelligently merging batch nautical chart printing tasks, not only can the printing quality be improved, but also task scheduling can be optimized, production efficiency can be increased, and costs can be reduced. Therefore, there is an urgent need for an optimization method and system for batch nautical chart printing tasks based on intelligent merging to achieve precise color control, intelligent task allocation, and efficient printing management. Summary of the Invention

[0006] To solve at least one of the above technical problems, the present invention proposes an optimization method and system for batch nautical chart printing tasks based on intelligent merging.

[0007] In the first aspect of the present invention, an optimization method for batch nautical chart printing tasks based on intelligent merging is provided, including: Real-time obtaining a nautical chart printing task data packet of a user, performing layer parsing on each data packet, extracting nautical chart elements, and constructing a nautical chart element distribution matrix; Analyze the chart element distribution matrix, identify the density of chart elements in each area of the chart, calculate the printing color level compensation parameters for each area of the chart in combination with the detected value of the reflectivity of the printing medium, and generate a color level compensation vector for each chart printing task; Perform a clustering operation on the color level compensation vectors of each chart printing task based on the hierarchical clustering algorithm to obtain a clustering result, and merge the chart printing tasks according to the clustering result to construct a chart printing task combination; Generate a color level calibration curve for the chart printing task combination, and optimize the chart printing task according to the color level calibration curve.

[0008] In this solution, the chart printing task data packet of the user is obtained in real time, each data packet is subjected to layer parsing, chart elements are extracted, and a chart element distribution matrix is constructed. Specifically: Construct a chart printing management system based on the B / S architecture, receive the chart printing order data placed by the user within a preset time period in real time according to the chart printing management system, extract the chart PDF file of the chart printing order data, and construct a chart printing task data packet; Convert each chart in the chart printing task data packet into a grayscale image, extract contour features from the grayscale image based on the Canny edge detection algorithm to generate a binary edge image, construct a Hough parameter space and a target geometric feature equation for the target geometric features of the chart, and accumulate votes for the binary edge image in the Hough parameter space according to the target geometric feature equation; When the accumulation voting in the Hough parameter space is completed, filter out the local peak points in the accumulation voting result, map the local peak points to the original image space and determine the corresponding geometric feature parameters, convert the geometric feature parameters into vector graphic coordinate data, and generate a vector layer containing chart elements such as straight lines, broken lines or polygons; Traverse each pixel in the grayscale image and the neighborhood pixels in the preset direction and spacing of each pixel, count the frequency of the appearance of the preset gray level combination, generate a gray level co-occurrence matrix, calculate the texture feature values according to the gray level co-occurrence matrix, the texture feature values include contrast, energy value, entropy value, map the texture feature values to the original image space, and generate a raster layer containing the chart texture features; Construct a standard nautical symbol database, construct a nautical symbol recognition model based on a convolutional neural network, import the nautical symbols in the standard nautical symbol database into the recognition model for training, and extract nautical symbols and text from each chart in the chart printing task data packet based on the trained complete nautical symbol recognition model and the preset text recognition model to generate a marked layer of the chart; The chart elements are extracted based on the vector layer, raster layer and annotation layer of the chart, and the position information of the chart elements is determined. The chart element distribution matrix is constructed based on the position information of the chart elements and sea area elements.

[0009] In this solution, the chart element distribution matrix is analyzed to identify the density of chart elements in each area of the chart. The printing color scale compensation parameters of each area of the chart are calculated in combination with the reflectivity detection value of the printing medium to generate the color scale compensation vector for each chart printing task. Specifically, The chart element distribution matrix is evenly divided into grid units of a preset size, and the coverage area ratio, number of navigation symbols and text density of the vector graphic coordinates and chart texture features in each grid unit are counted according to the chart element distribution matrix to obtain the initial density information of the chart elements in each grid unit; Selecting a Gaussian kernel function as the kernel function of the kernel density estimation algorithm, setting a smoothing bandwidth parameter of the kernel density estimation algorithm, performing a weighted sum calculation on the initial density information of the chart elements of each grid cell according to the kernel density estimation algorithm, constructing a continuous density distribution model, and calculating the density value of each grid cell; Normalizing the density value of each grid cell to within a preset value range, presetting a chart element density classification threshold based on the normalized density value, performing chart element density classification on each grid cell of the chart according to the preset chart element density classification threshold, and determining the chart element density of each grid cell; Obtain the reflectivity detection value of the chart printing medium, construct a preset reflectivity-compensation coefficient mapping table, and match the corresponding basic compensation coefficient according to the range of the reflectivity detection value, where the reflectivity detection value and the basic compensation coefficient are positively correlated; According to the results of the density division of the chart elements, different density level areas are mapped to the preset compensation weight gradient intervals. For each grid unit, the color scale compensation correction amount is calculated by the linear superposition formula according to the basic compensation coefficient of the density level to which it belongs and the matching gradient weight. According to the color scale compensation correction amount of each grid unit, a compensation parameter matrix with the same dimension as the chart element distribution matrix is generated. The compensation parameter matrix is expanded into a one-dimensional sequence by row and normalized, and the color scale compensation vector is output.

[0010] In this solution, the hierarchical clustering algorithm is used to cluster the color scale compensation vector of each nautical chart printing task to obtain a clustering result. The nautical chart printing tasks are merged according to the clustering result to construct a nautical chart printing task combination, specifically: Calculating the Euclidean distance between the color scale compensation vectors of each nautical chart printing task based on a hierarchical clustering algorithm, setting an initial clustering distance threshold, and performing initial clustering grouping on the color scale compensation vectors according to the Euclidean distance and the initial clustering distance threshold; Calculate the mean vector of all color level compensation vectors within each initial clustering group as the color level compensation reference vector for this group; Obtain the maximum color level compensation processing capacity of the POD printer, add up the color level compensation reference vectors of each initial clustering group and the color level compensation vectors of all chart printing tasks within the group to obtain the total color level compensation of the current group; Determine whether the total color level compensation exceeds the maximum color level compensation processing capacity. If the total color level compensation of the current group exceeds the maximum color level compensation processing capacity, reduce the initial clustering distance threshold, recalculate the Euclidean distance and iteratively execute clustering grouping until the total color level compensation of all groups is not greater than the maximum color level compensation processing capacity; When there are still over-standard groups with a total color level compensation greater than the maximum color level compensation processing capacity after the iteration times reach the preset upper limit, perform a dispersion analysis on the color level compensation vectors of the over-standard groups, calculate the standard deviation of the color level compensation vectors within the group. If the standard deviation is greater than the preset dispersion threshold, split the over-standard group into multiple sub-groups and assign independent printing batch numbers to each sub-group; Generate a hierarchical chart printing task combination according to the final clustering grouping result and sub-groups. Each task group contains chart printing tasks with the same batch number.

[0011] In this solution, generating a color level calibration curve for the chart printing task combination and optimizing the chart printing task according to the color level calibration curve specifically includes: Generate an initial calibration curve based on the color level compensation vectors of each group in the chart printing task combination. After performing a trial print through the printing device, collect the reflectivity distribution data and actual color level values of the printing medium; Perform a cross-analysis on the reflectivity distribution data and the chart element density data, and calculate the compensation correlation index between the reflectivity deviation and density of each region; Generate a surface reflectivity-density correction coefficient for the printing medium according to the compensation correlation index, and perform a secondary allocation of the compensation parameters in the initial calibration curve based on this coefficient; Input the compensation parameters after the secondary allocation into the color level drift prediction model, and calculate the color level drift coefficient by combining the color difference between the actual color level value and the target value; When the color level drift coefficient exceeds the preset threshold, construct an inverse compensation matrix based on the reflectivity-density correction coefficient, and correct the compensation parameters in the color level calibration curve through the inverse compensation matrix; If the corrected color level drift coefficient still exceeds the threshold, extract the redundant compensation parameters not used in the chart printing task combination, establish a compensation parameter buffer area, and call the buffer area parameters for superimposed compensation according to the gradient change of the color level drift coefficient to generate the final color level calibration curve; Perform a printing operation on the user's nautical chart printing task according to the final color level calibration curve.

[0012] In this solution, performing a printing operation on the user's nautical chart printing task according to the final color level calibration curve specifically includes: Generate color conversion parameters matching the POD printing device according to the final color level calibration curve, input the parameters into the color management module of the third-party printing management software, and drive the printer to perform color level calibration; Extract the nautical chart PDF file corresponding to the task from the nautical chart information and PDF file library, call the rasterization engine to perform layer-by-layer parsing on the PDF file, and perform rasterization processing on the nautical chart content in combination with the calibrated color level parameters; Select the printing medium type according to the printing task type. If it is the central task type, use the preset long paper roll or short paper roll for printing. If it is the user order type, automatically adapt the printing parameters according to the printer type configured by the user; When performing POD printing, perform rotation and white edge addition processing on the nautical chart PDF file based on the non-cutting standard. After printing, for the printed products of the central task type, compare the printed products with the standard symbols in the nautical chart information database through the system automatic verification module to generate an inspection report. If the inspection passes, store the version information in the database and mark it as the releasable state; For user order tasks, if the user does not have a POD printer, generate a logistics tracking code and bind the order information, and ship the printed products by express. If the user has a printer, push the calibrated nautical chart PDF file to the user's printer through the network for direct output.

[0013] The second aspect of the present invention also provides an optimized system for batch nautical chart printing tasks based on intelligent merging. The system includes: a memory and a processor. The memory includes an optimized method program for batch nautical chart printing tasks based on intelligent merging. When the optimized method program for batch nautical chart printing tasks based on intelligent merging is executed by the processor, the following steps are implemented: Obtain the nautical chart printing task data packets of the user in real time, perform layer-by-layer parsing on each data packet, extract nautical chart elements, and construct a nautical chart element distribution matrix; Analyze the nautical chart element distribution matrix, identify the density of nautical chart elements in each area of the nautical chart, calculate the printing color level compensation parameters for each area of the nautical chart in combination with the reflectivity detection value of the printing medium, and generate a color level compensation vector for each nautical chart printing task; Perform a clustering operation on the color level compensation vectors of each nautical chart printing task based on the hierarchical clustering algorithm to obtain a clustering result, and merge the nautical chart printing tasks according to the clustering result to construct a nautical chart printing task combination; Generate a color level calibration curve for the combined chart printing tasks, and optimize the chart printing tasks according to the color level calibration curve.

[0014] The present invention discloses an optimization method and system for batch chart printing tasks based on intelligent merging. The method includes real-time parsing of chart task data packets and constructing an element distribution matrix, dynamically calculating regional color level compensation parameters in combination with the reflectivity of the printing medium, and generating a color level compensation vector. The hierarchical clustering algorithm is used to cluster the compensation vectors to achieve adaptive merging of chart printing tasks and generate a color level calibration curve that matches the characteristics of the medium. Through the closed-loop of task merging decision-making and parameter optimization, the problem of color deviation caused by medium differences in batch chart printing is solved, and the frequency of repeated calibration of equipment is reduced. The present invention significantly improves printing efficiency and color consistency, reduces printing costs, and is applicable to the large-volume and high-precision chart printing requirements in the fields of navigation, surveying and mapping, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Shows a flowchart of an optimization method for batch chart printing tasks based on intelligent merging according to the present invention; Figure 2 Shows a flowchart of generating a color level compensation vector for each chart printing task according to the present invention; Figure 3 Shows a flowchart of performing a printing operation on a user's chart printing task according to the present invention; Figure 4 Shows a block diagram of an optimization system for batch chart printing tasks based on intelligent merging according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0017] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention may be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0018] Figure 1 Shows a flowchart of an optimization method for batch chart printing tasks based on intelligent merging according to the present invention.

[0019] As Figure 1 shown, the first aspect of the present invention provides an optimization method for batch chart printing tasks based on intelligent merging, including: S102. Obtain the chart printing task data packet of the user in real time, perform layer parsing on each data packet, extract chart elements, and construct a chart element distribution matrix; S104. Analyze the chart element distribution matrix, identify the density of chart elements in each area of the chart, calculate the printing color level compensation parameters for each area of the chart in combination with the detection value of the reflectivity of the printing medium, and generate a color level compensation vector for each chart printing task; S106. Perform a clustering operation on the color level compensation vectors of each chart printing task based on the hierarchical clustering algorithm to obtain a clustering result, merge the chart printing tasks according to the clustering result, and construct a chart printing task combination; S108. Generate a color level calibration curve for the chart printing task combination, and optimize the chart printing task according to the color level calibration curve.

[0020] It should be noted that by obtaining the chart printing task data packet of the user in real time and performing layer parsing on each data packet, the chart elements can be accurately extracted and a chart element distribution matrix can be constructed, so as to comprehensively master the content structure and layout characteristics of the chart. Through the analysis of the chart element distribution matrix, the density of elements in each area of the chart can be identified, and the printing color level compensation parameters can be calculated in combination with the detection value of the reflectivity of the printing medium, so as to effectively optimize the color performance of different areas and reduce the color deviation problem caused by medium differences. Performing a clustering operation on the color level compensation vectors of each chart printing task based on the hierarchical clustering algorithm enables tasks with similar color level compensation requirements to be reasonably merged, thereby optimizing the printing resource allocation and improving the efficiency and consistency of batch printing. Constructing a chart printing task combination according to the clustering result can not only reduce the frequency of color adjustment of the printing machine, but also reduce the waste of printing consumables, thereby improving production efficiency. Finally, by generating a color level calibration curve and optimizing the chart printing task according to this calibration curve, the color reproduction of the printed product is more accurate, the adaptability and navigation readability of the chart on different printing media are improved, and the actual application effect and service life of the chart are ensured.

[0021] According to the embodiment of the present invention, the obtaining the chart printing task data packet of the user in real time, performing layer parsing on each data packet, extracting chart elements, and constructing a chart element distribution matrix is specifically as follows: Construct a chart printing management system based on the B / S architecture, receive the chart printing order data placed by the user within a preset time period in real time according to the chart printing management system, extract the chart PDF file of the chart printing order data, and construct a chart printing task data packet; Convert each chart in the chart printing task data packet into a grayscale image, extract contour features from the grayscale image based on the Canny edge detection algorithm to generate a binary edge image, construct a Hough parameter space and a target geometric feature equation for the target geometric features of the chart, and accumulate votes for the binary edge image in the Hough parameter space according to the target geometric feature equation; When the accumulation voting in the Hough parameter space is completed, filter out the local peak points in the accumulation voting results, map the local peak points to the original image space and determine the corresponding geometric feature parameters, convert the geometric feature parameters into vector graphic coordinate data, and generate a vector layer containing chart elements such as straight lines, broken lines or polygons; Traverse each pixel in the grayscale image and the neighborhood pixels with a preset direction and spacing for each pixel, count the frequency of the occurrence of the preset gray level combination to generate a gray level co-occurrence matrix, calculate the texture feature values according to the gray level co-occurrence matrix, the texture feature values include contrast, energy value, entropy value, map the texture feature values to the original image space, and generate a raster layer containing the chart texture features; Construct a standard nautical symbol database, build a nautical symbol recognition model based on a convolutional neural network, import the nautical symbols in the standard nautical symbol database into the recognition model for training, and extract nautical symbols and text from each chart in the chart printing task data packet based on the trained nautical symbol recognition model and a preset text recognition model to generate a labeled layer of the chart; Extract chart elements according to the vector layer, raster layer, and labeled layer of the chart, determine the position information of the chart elements, and construct a chart element distribution matrix according to the position information of the chart elements and sea area elements.

[0022] It should be noted that the target geometric features mainly refer to the common geometric structures in nautical charts, such as straight lines, broken lines, polygons, arcs, etc. These geometric features are usually used to represent waterways, boundaries, bathymetric lines and other navigation information. The Hough parameter space is a space that converts the geometric features in an image into a parameter representation. Through this space, the problem of detecting straight lines or curves in an image can be transformed into the problem of detecting points in the parameter space. For example, a straight line can usually be represented by the polar coordinate equation ρ = xcosθ + ysinθ. The target geometric feature equation is a mathematical expression used to describe these target geometric features, such as the straight line equation, the circle equation, the polygon boundary equation, etc. By performing cumulative voting on the binary edge image in the Hough parameter space, the position and shape of the geometric features in the image can be detected. The original image space refers to the original pixel coordinate system of the nautical chart, that is, the two-dimensional image representation of the nautical chart in the computer, where each pixel point has a specific coordinate value. The cumulative voting is, for example, when detecting a straight line, calculating all possible combinations of ρ and θ through the polar coordinate parameter equation and updating the accumulator matrix. The feature parameters include straight line parameters (length, direction angle, starting and ending point coordinates, distance from the origin), broken line parameters (sequence of vertex coordinates, number of line segments, trend of inflection angle change), polygon parameters (vertex coordinates, number of sides, area, perimeter), arc parameters (center coordinates, radius, starting angle, ending angle, arc length); nautical chart elements include vector layer elements (coastline, waterway boundary, bathymetric line, restricted navigation area / hazardous area boundary, dock / anchorage, lighthouse / buoy position), raster layer elements (terrain shadow, water depth color scale, substrate type), annotation layer elements (navigation symbols, place name annotations, waterway numbers, navigation warnings).

[0023] Figure 2 Fig. shows the flow chart of generating the color scale compensation vector for each nautical chart printing task of the present invention.

[0024] According to an embodiment of the present invention, the analysis of the nautical chart element distribution matrix, identifying the density of nautical chart elements in each area of the nautical chart, calculating the printing color scale compensation parameters for each area of the nautical chart in combination with the detected value of the reflectivity of the printing medium, and generating the color scale compensation vector for each nautical chart printing task are specifically as follows: S202, uniformly divide the nautical chart element distribution matrix into grid cells of a preset size, and according to the nautical chart element distribution matrix, count the coverage area ratio of vector graphic coordinates and nautical chart texture features, the number of navigation symbols and the text density in each grid cell to obtain the initial density information of nautical chart elements in each grid cell; S204, select the Gaussian kernel function as the kernel function of the kernel density estimation algorithm, set the smoothing bandwidth parameter of the kernel density estimation algorithm, perform weighted summation calculation on the initial density information of nautical chart elements in each grid cell according to the kernel density estimation algorithm, construct a continuous density distribution model, and calculate the density value of each grid cell; S206, normalizing the density value of each grid cell to within a preset value range, presetting a chart element density classification threshold based on the normalized density value, and performing chart element density classification on each grid cell of the chart according to the preset chart element density classification threshold to determine the chart element density of each grid cell; It should be noted that because the visual appearance of printed color gradations is affected by both the density of chart elements and the reflectivity of the printing medium, dynamic adjustment of color gradation compensation parameters is required during the printing process to ensure balanced print quality. Sparse areas: Due to the small number of chart elements and the large amount of blank space, the printing process is easily affected by the reflectivity of the printing medium. High reflectivity can easily lead to too light colors and loss of detail. Therefore, the color gradation compensation value should be appropriately increased, that is, the color gradation density should be increased to enhance contrast. Medium-dense areas: These areas have relatively uniform element distribution and are relatively less affected by reflectivity. Therefore, the color gradation compensation value is calculated according to the standard to ensure balanced print color. High-dense areas: Due to the dense distribution of chart elements and the strong black-white contrast, low reflectivity of the printing medium may result in too dark colors and blurred details. Therefore, the color gradation compensation value should be appropriately reduced to ensure clear color gradations. Ultra-dense areas: These areas typically contain a large number of nautical symbols, geographic boundaries, or dense terrain features. If the printing color gradation is too high, the symbols and lines may become blurred. Therefore, the color gradation density should be further reduced, and nonlinear adjustment strategies can be applied to maintain printed details.

[0025] S208, obtaining a reflectivity detection value of the chart printing medium, constructing a preset reflectivity-compensation coefficient mapping table, and matching a corresponding basic compensation coefficient according to the interval of the reflectivity detection value, wherein the reflectivity detection value and the basic compensation coefficient are positively correlated; S210, based on the result of the density division of the nautical chart elements, the different density level areas are mapped to the preset compensation weight gradient intervals respectively. For each grid cell, the color scale compensation correction amount is calculated by the linear superposition formula according to the basic compensation coefficient of the density level to which it belongs and the matching gradient weight. Based on the color scale compensation correction amount of each grid cell, a compensation parameter matrix with the same dimension as the nautical chart element distribution matrix is generated. The compensation parameter matrix is expanded into a one-dimensional sequence by row and normalized, and the color scale compensation vector is output.

[0026] It should be noted that different printing media (such as different types of paper or special coating materials) have different light reflection characteristics, and the color performance of printing is closely related to the reflectivity of the medium. For example, on a medium with a high reflectivity, certain colors may appear lighter, while a medium with a low reflectivity may absorb more colors, making the printing effect darker. Therefore, by measuring the reflectivity of the medium and using a preset reflectivity-compensation coefficient mapping table, a basic compensation coefficient can be matched for each medium. Since the higher the reflectivity, the higher the required compensation, the two are positively correlated. This step provides a global adjustment benchmark for color level compensation. Different regions of the nautical chart contain different densities of elements. For example, the port area may have a large number of nautical symbols, markings, and complex lines, while the open sea area may only contain a small number of bathymetric lines. The color information in the dense area is more, and it is more likely to be affected by color accumulation, detail blurring, or color distortion during the printing process. Therefore, it is necessary to apply different degrees of color level compensation to regions with different densities according to the division results of the nautical chart element density. Map the density levels of each region to a preset compensation weight gradient interval: the high-density region corresponds to a larger compensation weight, while the low-density region has a smaller compensation weight. Calculate the color level compensation correction amount for each grid cell: combine the basic compensation coefficient of this region (obtained by matching the medium reflectivity) and the compensation weight corresponding to this region (determined by the density), and use a linear superposition formula to calculate the color level compensation correction amount to ensure appropriate color adjustment for different regions. Generate a compensation parameter matrix: The color level compensation correction amounts of all grid cells form a matrix, which has the same dimension as the nautical chart element distribution matrix, so that the color adjustment of each region can be applied specifically. Since the numerical range of the color level compensation correction amount may fluctuate greatly, in order to ensure the comparability of the compensation parameters between different nautical chart tasks, finally, the compensation parameter matrix needs to be expanded into a one-dimensional sequence by rows and normalized (for example, scaled to the interval [0,1] or [-1,1]). The finally obtained color level compensation vector can comprehensively reflect the color level compensation requirements of the nautical chart under different media and different regions, providing a standardized data basis for subsequent printing task optimization and task merging.

[0027] According to an embodiment of the present invention, clustering operations are performed on the color level compensation vectors of each nautical chart printing task based on the hierarchical clustering algorithm to obtain a clustering result, and the nautical chart printing tasks are merged according to the clustering result to construct a nautical chart printing task combination, specifically: Calculate the Euclidean distance between the color level compensation vectors of each nautical chart printing task based on the hierarchical clustering algorithm, set an initial clustering distance threshold, and perform initial clustering grouping on the color level compensation vectors according to the Euclidean distance and the initial clustering distance threshold; Calculate the mean vector of all color level compensation vectors within each initial clustering group as the color level compensation reference vector for this group; Obtain the maximum color level compensation processing amount of the POD printer, accumulate the color level compensation reference vectors of each initial clustering group with the color level compensation vectors of all chart printing tasks within the group to obtain the total color level compensation of the current group; Determine whether the total color level compensation exceeds the maximum color level compensation processing amount. If the total color level compensation of the current group exceeds the maximum color level compensation processing amount, reduce the initial clustering distance threshold, recalculate the Euclidean distance and iteratively perform clustering grouping until the total color level compensation of all groups is not greater than the maximum color level compensation processing amount; When there are still over-standard groups with a color level compensation amount greater than the maximum color level compensation processing amount after the number of iterations reaches the preset upper limit, perform a dispersion analysis on the color level compensation vectors of the over-standard groups, calculate the standard deviation of the color level compensation vectors within the group. If the standard deviation is greater than the preset dispersion threshold, split the over-standard group into multiple sub-groups and assign independent printing batch numbers to each sub-group; Generate a hierarchical chart printing task combination according to the final clustering grouping results and sub-groups. Each task group contains chart printing tasks with the same batch number.

[0028] It should be noted that in the batch chart printing task, due to the differences in the color level compensation requirements of different charts, it may lead to unbalanced distribution of printing tasks, thereby affecting the printing efficiency and quality. For example, the color level compensation requirements of some chart tasks are too high, which may exceed the processing capacity of the POD (print on demand) printer, resulting in color overload, uneven printing, or degradation of equipment performance. While the color level compensation requirements of some chart tasks are relatively low, which may cause waste of printing resources. Therefore, the Euclidean distance between the color level compensation vectors of each chart printing task is calculated using the hierarchical clustering algorithm, and an initial clustering distance threshold is set to ensure that similar tasks can be clustered into the same group. This can ensure that the chart printing tasks within the same group have similar color level compensation requirements. Secondly, the mean vector of all color level compensation vectors within each initial clustering group is calculated as the color level compensation reference vector for this group, and the total color level compensation is further calculated. The purpose of this step is to measure the overall color level compensation requirements of each task group to ensure that it does not exceed the maximum color level compensation processing capacity of the POD printer. If the total color level compensation of a certain task group exceeds the processing capacity of the device, the clustering parameters need to be adjusted to narrow the clustering distance threshold until the total color level compensation of all task groups is within the processable range of the device. This ensures that the device will not cause a decline in printing quality due to overload. When the clustering adjustment still cannot solve the overload problem, that is, some task groups still exceed the maximum color level compensation processing amount, it is necessary to further analyze the dispersion degree of the color level compensation vectors within the group. If the standard deviation of the color level compensation vectors within the group is large, it indicates that the distribution of the color level compensation requirements of the chart tasks within this task group is relatively dispersed and is not suitable for being processed in the same printing batch. It is necessary to split this group into multiple sub-groups and assign independent printing batch numbers to each sub-group to ensure that tasks with different color level requirements can be accurately compensated and printed. This can not only optimize the printing process and improve production efficiency, but also ensure the color consistency of the charts within the same batch, avoiding uneven quality of printed products due to different color level compensations.

[0029] According to an embodiment of the present invention, generating a color level calibration curve for the chart printing task combination and optimizing the chart printing task according to the color level calibration curve specifically includes: Generating an initial calibration curve based on the color level compensation vectors of each group in the chart printing task combination. After performing a trial print through the printing device, collect the reflectivity distribution data of the printing medium and the actual color level values of the printed charts. Perform cross-analysis on the reflectivity distribution data and the chart element density data, and calculate the compensation correlation index between the reflectivity deviation and the density of each area. Generate a surface reflectivity-density correction coefficient for the printing medium according to the compensation correlation index, and perform secondary allocation of the compensation parameters in the initial calibration curve based on this coefficient. Input the compensated parameters after secondary allocation into the color level drift prediction model, and calculate the color level drift coefficient by combining the color difference between the actual color level value and the target value. When the color level drift coefficient exceeds the preset threshold, construct an inverse compensation matrix based on the reflectivity-density correction coefficient, and correct the compensated parameters in the color level calibration curve through the inverse compensation matrix. If the corrected color level drift coefficient still exceeds the threshold, extract the unused redundant compensated parameters in the chart printing task combination, establish a compensated parameter buffer, and call the buffer parameters for superposition compensation according to the gradient change of the color level drift coefficient to generate the final color level calibration curve. Perform a printing operation on the user's chart printing task according to the final color level calibration curve.

[0030] It should be noted that in the field of marine surveying and mapping, nautical charts must accurately present the color gradation differences of different elements (such as water depth gradients and reef markers). During the printing process, differences in the reflectivity of the printing medium (due to the paper's ink absorption characteristics or changes in ambient temperature and humidity) can interact with the density distribution of chart elements. Directly applying fixed compensation parameters can lead to color gradation distortion due to deviations between the medium properties and the theoretical model, affecting the accuracy of navigational information interpretation. This claim achieves dynamic optimization through the following steps: First, an initial calibration curve is generated as a basic compensation scheme, but the actual effect must be verified through trial printing (by obtaining reflectivity distribution data from printed samples using an optical scanning device). Spatial correlation analysis is then performed between the measured data and the density distribution of chart elements, and a compensation correlation index is calculated (using statistical correlation analysis to quantify the strength of the correlation between reflectivity deviation and element density). Based on this, a reflectivity-density correction coefficient is generated (by establishing a dynamic mapping model between medium properties and compensation parameters), and the initial compensation parameters are then redistributed to adapt to the differences in medium properties. The color scale drift prediction model (a time-series prediction model trained based on historical printing data) is used to predict the color scale deviation trend after compensation. When the predicted value exceeds the safety threshold, the reverse compensation matrix (a set of reverse adjustment parameters generated through matrix operations) dynamically corrects the compensation direction. The redundant compensation buffer mechanism (a dynamic backup library of unused compensation parameters) uses a gradient matching strategy to call backup parameters for superimposed compensation, ultimately generating an adaptive calibration curve that takes into account both media characteristics and element distribution. The redundant compensation parameters refer to a set of backup adjustment parameters that are pre-reserved during the printing color scale calibration process. Their essence is to provide additional correction margin for dynamic color scale deviations through over-design. In printing task optimization scenarios, due to the superposition effect of densely distributed chart elements (such as the cumulative effect of ink diffusion when multiple high-density areas are printed adjacently) or local mutations in the reflectivity of the printing medium (such as color scale jumps caused by uneven ink absorption of paper), relying solely on the initial calibration parameters may not be able to fully cover the nonlinear color differences in actual printing. To this end, when generating the initial compensation parameters, the system will reserve a portion of the compensation parameters that are not directly allocated as redundant reserves through parameter decomposition technology (such as decomposing the compensation vector into basic components and high-frequency detail components according to frequency domain characteristics) or based on historical data prediction models.

[0031] Figure 3 The flowchart of the present invention showing the printing operation of the user's nautical chart printing task.

[0032] According to an embodiment of the present invention, the printing operation of the user's nautical chart printing task according to the final color scale calibration curve is specifically performed as follows: S302, generating color conversion parameters matching the POD printing device based on the final color scale calibration curve, inputting the parameters into a color management module of a third-party print management software, and driving the printer to perform color scale calibration; S304. Extract the chart PDF file corresponding to the task from the chart information and PDF file library, call the rasterization engine to perform layer-by-layer parsing on the PDF file, and perform rasterization processing on the chart content in combination with the calibrated color level parameters; S306. Select the print medium type according to the printing task type. If it is the central task type, use the preset long paper roll or short paper roll for printing. If it is the user order type, automatically adapt the printing parameters according to the printer type configured by the user; S308. When performing POD printing, perform rotation and white edge addition processing on the chart PDF file based on the non-cutting standard. After printing, for the printed products of the central task type, compare the printed products with the standard symbols in the chart information database through the system automatic verification module to generate an inspection report. If the inspection passes, store the version information in the database and mark it as the releasable state; S310. For the user order type tasks, if the user does not have a POD printer, generate a logistics tracking code and bind the order information, and send the printed products by express. If the user has a printer, push the calibrated chart PDF file to the user's printer through the network for direct output.

[0033] It should be noted that the third-party printing management software refers to a professional printing control software platform independent of the chart printing optimization system, which usually includes a color management module, a print task queue management module, and a device driver interface, and is used to implement color parameter parsing, print job scheduling, and hardware control functions. The rasterization engine refers to the core processing module that converts the vector-format chart PDF file into a pixelated raster image (such as TIFF or JPG format) recognizable by the printing device. Its technical process includes: parsing the mixed structure of the vector graphic layer (such as the isobath described by Bezier curves), text layer (nautical identification annotations), and raster layer (seafloor terrain map) in the PDF file, performing geometric transformation and rasterization reconstruction on each layer element according to the resolution parameters of the target printer (such as 1200×1200dpi), and at the same time mapping the color level calibration parameters to the CMYK / Lab color value calculation of each pixel point (such as adjusting the inkjet volume of a specific ink channel according to the calibration curve).

[0034] Figure 4 Shows a block diagram of an optimized system for batch chart printing tasks based on intelligent merging according to the present invention.

[0035] In a second aspect of the present invention, an optimized system 4 for batch chart printing tasks based on intelligent merging is also provided. The system includes: a memory 41 and a processor 42. The memory includes a program for an optimized method for batch chart printing tasks based on intelligent merging. When the program for the optimized method for batch chart printing tasks based on intelligent merging is executed by the processor, the following steps are implemented: Obtain the chart printing task data packets of users in real time, perform layer parsing on each data packet, extract chart elements, and construct a chart element distribution matrix; Analyze the chart element distribution matrix, identify the density of chart elements in each area of the chart, calculate the printing color level compensation parameters for each area of the chart in combination with the detected value of the reflectivity of the printing medium, and generate a color level compensation vector for each chart printing task; Perform a clustering operation on the color level compensation vectors of each chart printing task based on the hierarchical clustering algorithm to obtain a clustering result, and merge the chart printing tasks according to the clustering result to construct a chart printing task combination; Generate a color level calibration curve for the chart printing task combination, and optimize the chart printing task according to the color level calibration curve.

[0036] The present invention discloses an optimization method and system for batch chart printing tasks based on intelligent merging. This method constructs an element distribution matrix by real-time parsing of chart task data packets, dynamically calculates regional color level compensation parameters in combination with the reflectivity of the printing medium, and generates a color level compensation vector. The hierarchical clustering algorithm is used to cluster the compensation vectors to achieve the adaptive merging of chart printing tasks and generate a color level calibration curve that matches the characteristics of the medium. Through the closed-loop of task merging decision and parameter optimization, the problem of color deviation caused by medium differences in batch chart printing is solved, and the frequency of repeated calibration of equipment is reduced. The present invention significantly improves printing efficiency and color consistency, reduces printing costs through intelligent task merging and dynamic calibration technologies, and is applicable to the large-scale high-precision chart printing requirements in the fields of navigation, surveying and mapping, etc.

[0037] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be electrical, mechanical, or other forms.

[0038] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they may be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0039] In addition, each functional unit in the embodiments of the present invention may be entirely integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the above-mentioned integrated unit may be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0040] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks and other various media that can store program codes.

[0041] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art, 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 causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks, or optical disks and other various media that can store program codes.

[0042] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, and all of them should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An optimization method for batch chart printing tasks based on intelligent merging, characterized in that, It includes the following steps: Obtain the chart printing task data packets of the user in real time, perform layer parsing on each data packet, extract chart elements, and construct a chart element distribution matrix; Analyze the chart element distribution matrix, identify the density of chart elements in each area of the chart, calculate the printing color level compensation parameters for each area of the chart in combination with the detected value of the reflectivity of the printing medium, and generate a color level compensation vector for each chart printing task; Perform clustering operations on the color level compensation vectors of each chart printing task based on the hierarchical clustering algorithm, obtain the clustering results, merge the chart printing tasks according to the clustering results, and construct a chart printing task combination; Generate a color level calibration curve for the chart printing task combination, and optimize the chart printing task according to the color level calibration curve.

2. The optimized method for batch chart printing tasks based on intelligent merging according to claim 1, wherein, The step of obtaining the chart printing task data packets of the user in real time, performing layer parsing on each data packet, extracting chart elements, and constructing a chart element distribution matrix is specifically as follows: Construct a chart printing management system based on the B / S architecture, receive the chart printing order data placed by the user within a preset time period in real time according to the chart printing management system, extract the chart PDF file of the chart printing order data, and construct a chart printing task data packet; Convert each chart in the chart printing task data packet into a grayscale image, extract contour features from the grayscale image based on the Canny edge detection algorithm, generate a binary edge image, construct a Hough parameter space and a target geometric feature equation for the target geometric features of the chart, and accumulate votes for the binary edge image in the Hough parameter space according to the target geometric feature equation; When the accumulation voting in the Hough parameter space is completed, filter out the local peak points in the accumulation voting results, map the local peak points to the original image space and determine the corresponding geometric feature parameters, convert the geometric feature parameters into vector graphic coordinate data, and generate a vector layer containing chart elements such as straight lines, broken lines, or polygons; Traverse each pixel in the grayscale image and the neighborhood pixels in the preset direction and spacing of each pixel, count the frequency of the appearance of the preset gray level combination, generate a gray level co-occurrence matrix, calculate the texture feature values according to the gray level co-occurrence matrix, the texture feature values include contrast, energy value, entropy value, map the texture feature values to the original image space, and generate a raster layer containing the chart texture features; Construct a standard nautical symbol database, construct a nautical symbol recognition model based on a convolutional neural network, import the nautical symbols in the standard nautical symbol database into the recognition model for training, and extract nautical symbols and text from each chart in the chart printing task data packet based on the trained complete nautical symbol recognition model and the preset text recognition model, and generate a marked layer of the chart; Extract chart elements according to the vector layer, raster layer, and marked layer of the chart, determine the position information of the chart elements, and construct a chart element distribution matrix according to the position information of the chart elements and sea area elements.

3. The optimized method for batch chart printing tasks based on intelligent merging according to claim 1, wherein The chart element distribution matrix is analyzed to identify the density of chart elements in each area of the chart, and the printing color scale compensation parameters of each area of the chart are calculated in combination with the print medium reflectivity detection value to generate the color scale compensation vector for each chart printing task, specifically: The chart element distribution matrix is evenly divided into grid units of a preset size, and the coverage area ratio, number of navigation symbols and text density of the vector graphic coordinates and chart texture features in each grid unit are counted according to the chart element distribution matrix to obtain the initial density information of the chart elements in each grid unit; Selecting a Gaussian kernel function as the kernel function of the kernel density estimation algorithm, setting a smoothing bandwidth parameter of the kernel density estimation algorithm, performing a weighted sum calculation on the initial density information of the chart elements of each grid cell according to the kernel density estimation algorithm, constructing a continuous density distribution model, and calculating the density value of each grid cell; Normalizing the density value of each grid cell to within a preset value range, presetting a chart element density classification threshold based on the normalized density value, performing chart element density classification on each grid cell of the chart according to the preset chart element density classification threshold, and determining the chart element density of each grid cell; Obtain the reflectivity detection value of the chart printing medium, construct a preset reflectivity-compensation coefficient mapping table, and match the corresponding basic compensation coefficient according to the range of the reflectivity detection value, where the reflectivity detection value and the basic compensation coefficient are positively correlated; According to the results of the density division of the chart elements, different density level areas are mapped to the preset compensation weight gradient intervals. For each grid unit, the color scale compensation correction amount is calculated by the linear superposition formula according to the basic compensation coefficient of the density level to which it belongs and the matching gradient weight. According to the color scale compensation correction amount of each grid unit, a compensation parameter matrix with the same dimension as the chart element distribution matrix is generated. The compensation parameter matrix is expanded into a one-dimensional sequence by row and normalized, and the color scale compensation vector is output.

4. A method for optimizing batch chart printing tasks based on intelligent merging according to claim 1, characterized in that The hierarchical clustering algorithm is used to perform a clustering operation on the color scale compensation vector of each nautical chart printing task to obtain a clustering result. The nautical chart printing tasks are merged according to the clustering result to construct a nautical chart printing task combination, specifically: Calculating the Euclidean distance between the color scale compensation vectors of each nautical chart printing task based on a hierarchical clustering algorithm, setting an initial clustering distance threshold, and performing initial clustering grouping on the color scale compensation vectors according to the Euclidean distance and the initial clustering distance threshold; Calculate the mean vector of all color scale compensation vectors in each initial cluster group as the color scale compensation reference vector of the group; Obtain the maximum color scale compensation processing capacity of the POD printer, and add the color scale compensation reference vector of each initial cluster group with the color scale compensation vectors of all chart printing tasks in the group to obtain the total color scale compensation capacity of the current group; Determine whether the total color level compensation amount exceeds the maximum color level compensation processing amount. If the total color level compensation amount of the current grouping exceeds the maximum color level compensation processing amount, reduce the initial clustering distance threshold, recalculate the Euclidean distance, and iteratively execute clustering grouping until the total color level compensation amounts of all groupings are not greater than the maximum color level compensation processing amount; When there are still over-standard groupings with a color level compensation amount greater than the maximum color level compensation processing amount when the number of iterations reaches the preset upper limit, perform a dispersion analysis on the color level compensation vectors of the over-standard groupings, calculate the standard deviation of the intra-group color level compensation vectors. If the standard deviation is greater than the preset dispersion threshold, split the over-standard groupings into multiple sub-groupings, and assign independent printing batch numbers to each sub-grouping; Generate a hierarchical chart printing task combination based on the final clustering grouping results and sub-groupings. Each task group contains chart printing tasks with the same batch number.

5. A method for optimizing batch chart printing tasks based on intelligent merging according to claim 1, characterized in that Generate a color level calibration curve for the chart printing task combination, and optimize the chart printing task according to the color level calibration curve. Specifically: Generate an initial calibration curve based on the color level compensation vectors of each grouping in the chart printing task combination. After performing a trial print through the printing device, collect the reflectance distribution data and actual color level values of the printing medium; Perform a cross-analysis on the reflectance distribution data and the chart element density data, and calculate the compensation correlation index of the reflectance deviation and density for each region; Generate a surface reflectance-density correction coefficient for the printing medium based on the compensation correlation index, and perform a secondary allocation of the compensation parameters in the initial calibration curve based on this coefficient; Input the compensated parameters after the secondary allocation into the color level drift prediction model, and calculate the color level drift coefficient by combining the color difference between the actual color level value and the target value; When the color level drift coefficient exceeds the preset threshold, construct a reverse compensation matrix based on the reflectance-density correction coefficient, and correct the compensation parameters in the color level calibration curve through the reverse compensation matrix; If the corrected color level drift coefficient still exceeds the threshold, extract the unused redundant compensation parameters in the chart printing task combination, establish a compensation parameter buffer area, and call the buffer area parameters for superposition compensation according to the gradient change of the color level drift coefficient to generate the final color level calibration curve; Perform a printing operation on the user's chart printing task according to the final color level calibration curve.

6. The optimized method for batch chart printing tasks based on intelligent merging according to claim 5, wherein, The printing operation on the user's chart printing task according to the final color level calibration curve is specifically: Generate color conversion parameters matching the POD printing device according to the final color level calibration curve, input the parameters into the color management module of the third-party printing management software, and drive the printer to perform color level calibration; Extract the chart PDF file corresponding to the task from the chart information and PDF file library, call the rasterization engine to perform layer-by-layer parsing on the PDF file, and perform rasterization processing on the chart content in combination with the calibrated color level parameters; Select the printing medium type according to the printing task type. If it is the central task type, use a preset long paper roll or short paper roll for printing. If it is the user order type, automatically adapt the printing parameters according to the printer type configured by the user; When performing POD printing, rotate the chart PDF file and add white margins based on the non-cutting standard. After printing, for the printed products of the central task class, compare the printed products with the standard symbols in the chart information database through the system's automatic verification module to generate an inspection report. If the inspection passes, store the version information in the database and mark it as the issuable state; For user order tasks, if the user does not have a POD printer, generate a logistics tracking code and bind the order information, and execute express delivery for the printed products. If the user has a printer, push the calibrated chart PDF file to the user's printer through the network for direct output.

7. An optimized system for batch nautical chart printing tasks based on intelligent merging, characterized in that, The batch chart printing task optimization system based on intelligent merging includes a storage and a processor. The storage includes a program for the method of optimizing batch chart printing tasks based on intelligent merging. When the program for the method of optimizing batch chart printing tasks based on intelligent merging is executed by the processor, the following steps are implemented: Obtain the user's chart printing task data packets in real time, perform layer parsing on each data packet, extract chart elements, and construct a chart element distribution matrix; Analyze the chart element distribution matrix, identify the density of chart elements in each area of the chart, calculate the printing color level compensation parameters for each area of the chart in combination with the detected value of the reflectance of the printing medium, and generate a color level compensation vector for each chart printing task; Perform a clustering operation on the color level compensation vectors of each chart printing task based on the hierarchical clustering algorithm to obtain a clustering result, and merge the chart printing tasks according to the clustering result to construct a chart printing task combination; Generate a color level calibration curve for the chart printing task combination, and optimize the chart printing task according to the color level calibration curve.

Images