Digital printing automatic sample adjusting method and system

Abstract

This invention provides an automated digital printing sample adjustment method and system, including a sample adjustment client that imports a preset pattern file to be printed and performs similarity matching calculations with a local process database or a cloud process database on a cloud server. The local process data and the cloud process database store historical process scenario data examples. The sample adjustment client retrieves examples that meet the similarity criteria, corrects the data, and sends it to the digital printing machine terminal. The digital printing machine terminal drives the digital printing machine to print and saves the process scenario data that meets the finished product effect criteria to the local or cloud process database. The cloud server also communicates remotely with service engineers to manually set process scenario parameters. By storing and managing the printing difference parameters of all digital printing equipment, when a customer adjusts a sample, the system automatically matches and retrieves similar historical examples and makes corrections, improving the sampling efficiency of digital printing plants.

Description

Technical Field

[0001] This invention belongs to the field of intelligent management technology for digital printing machines, and particularly relates to an automated sample adjustment method and system for digital printing. Background Technology

[0002] Digital printing uses a computer-aided design (CAD) system to control the printhead, directly spraying dye onto the fabric. This eliminates the need for traditional plate-making processes, enabling a fully digital process from pattern input to production. Low sample adjustment efficiency is a major challenge currently facing the textile digital printing industry. At present, digital printing factories mainly rely on experienced sample adjusters to perform trial-and-error sampling for customer orders. This involves receiving a customer sample, printing a test sample on a digital printing machine, and then visually comparing the customer's sample with the test sample to observe color differences. The sample adjuster then returns to the computer color matching software to adjust the pattern and correct the color difference based on past experience. The process is repeated until the customer's order requirements are met.

[0003] The prior art patent with publication number CN120612306A discloses a method and system for image quality detection of a digital printing machine. The method includes the following steps: determining first state information and second state information; sending change information to the inkjet mechanism based on the comparative analysis of the first and second state information, whereby the change information is used to indicate the second state information; connecting the trained prediction model to the drawing mechanism, inputting a pattern, and reconstructing and outputting the pattern of the digital printing machine through region analysis; establishing an initial prediction model, using a BP neural network to establish a relationship model between printing pressure, squeegee speed, ink viscosity, squeegee angle, and ink transfer rate, and combining state estimation to train and update the prediction model to achieve real-time correction of the inkjet mechanism and reduce the misjudgment rate; and further performing targeted analysis on color features and contour features to improve the output image quality. Summary of the Invention

[0004] In existing manual sample adjustment methods, the printing parameters of each printing machine may differ due to variations in mechanical precision and installation. Sample adjustment technicians must make targeted fine-tuning adjustments based on the current equipment status during sampling. When customers place repeat orders, or when mass production is required after sample confirmation, the sampling machine may differ from the production machine. This necessitates special adjustments for each machine involved in production, ensuring that each machine's samples meet the customer's requirements. All of these situations rely heavily on the experience and skill of the sample adjustment technician, making efficiency difficult to guarantee. This contradicts the market trend of small-batch, fast-response printing, limiting the flexibility of digital printing equipment compared to traditional printing for small orders, and exacerbating the recruitment and labor costs for digital printing factories.

[0005] To solve the above-mentioned technical problems, the technical solution provided by the present invention is: an automated digital printing sample adjustment method, comprising the following steps: S1. Import the preset pattern file to be printed into the sample adjustment client and perform similarity matching calculation with historical cases in the local process database; S2. Filter out historical cases with similarity greater than the preset threshold A, select the process scene data of the case with the highest similarity, correct the data, and output it to the digital printing machine terminal. S3. The digital printing machine terminal drives the digital printing machine to print based on the corrected process scene data parameters and judges the finished product effect. S4. If the finished product meets the requirements, record the process scenario data and save it to the local process database; if the finished product does not meet the requirements, return to S2 to re-correct the process scenario deviation details.

[0006] Specifically, data correction includes equipment difference data correction based on the deviation data of each digital printing machine stored in the sample client, and process scene deviation detail correction based on the process feature parameters of the preset pattern file.

[0007] Specifically, if there are no historical cases with a similarity greater than the preset threshold A in the local process database in S2, then a similarity matching calculation is performed with the historical cases in the cloud process database in the cloud server. The process scene data of the historical case with the largest similarity greater than the threshold A is retrieved, the equipment difference data is corrected, and the process scene deviation details are corrected according to the preset pattern file. Finally, the data is output to the digital printing machine terminal.

[0008] Specifically, if there are no historical cases with a similarity greater than the preset threshold A in the local process database of S2, and there are also no historical cases with a similarity greater than the preset threshold A in the cloud server, the cloud server communicates remotely with the service engineer to manually intervene in setting the process scenario parameters and output them to the digital printing machine terminal.

[0009] Specifically, S4 counts the number of times the finished product does not meet the requirements, resulting in the need to correct the details of the process scene deviation. If the number of consecutive modifications exceeds the preset threshold, a manual intervention request is sent to the cloud server. The cloud server communicates remotely with the service engineer, who then manually intervenes to set the process scene parameters and outputs them to the digital printing machine terminal.

[0010] Specifically, if process scenario data is retrieved from the cloud process database in S2 and the final printed product of the digital printing machine meets the requirements after data correction, the cloud server performs a similarity judgment on all case data in the cloud process database and the process scenario data after this printing correction; if there is no case data in the cloud process database with a similarity greater than the preset threshold B, the process scenario data after this printing correction is saved to the cloud process database.

[0011] Specifically, when importing the preset pattern file to be printed in S1, the process features are quantified into specific parameters and matched with the process scenario parameters of historical cases based on similarity.

[0012] Specifically, process characteristics include material characteristics, processing technology type, and customer quality requirement level; material characteristics include ink type, fabric type, and component ratio.

[0013] Specifically, during similarity matching calculation, different similarity scores are assigned to different types of process scenario features in historical cases, with a total similarity score of 100. The similarity scores of various process scenario features in historical cases are assigned based on the degree of difference between the historical cases and the quantified process feature parameters. The sum of the similarity scores of various process scenario features is used as the overall similarity score of the historical case. The threshold A for similarity matching calculation is set to 80 points, and the threshold B is set to 90 points.

[0014] An automated digital printing sample adjustment system, using the aforementioned automated digital printing sample adjustment method, includes a sample adjustment client that imports a preset pattern file to be printed and performs similarity matching calculations with a local process database or a cloud process database on a cloud server; the local process data and the cloud process database store historical process scene data cases; the sample adjustment client retrieves cases that meet the similarity standard, corrects the data, and sends it to the digital printing machine terminal; the digital printing machine terminal drives the digital printing machine to print and saves the process scene data that meets the finished product effect standard to the local or cloud process database; the cloud server also communicates remotely with service engineers to manually set process scene parameters.

[0015] The beneficial effects of this invention are: it stores and manages the printing difference parameters of all digital printing equipment; when customers request samples, it automatically matches similar process scenarios of previous orders through local databases and cloud databases, and intelligently corrects equipment differences and process scenario deviations to quickly request samples for customer orders, realizing experience management and reuse, thereby greatly improving the sampling efficiency of digital printing factories and reducing the dependence on skilled sample-making technicians. Attached Figure Description

[0016] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0017] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0018] Example 1: An automated sample preparation method for digital printing, such as Figure 1 As shown, it includes the following steps: S1. Import the preset pattern file to be printed into the sample adjustment client and perform similarity matching calculation with historical cases in the local process database; S2. Filter out historical cases with similarity greater than the preset threshold A, select the process scene data of the case with the highest similarity, correct the data, and output it to the digital printing machine terminal. S3. The digital printing machine terminal drives the digital printing machine to print based on the corrected process scene data parameters and judges the finished product effect. S4. If the finished product meets the requirements, record the process scenario data and save it to the local process database; if the finished product does not meet the requirements, return to S2 to re-correct the process scenario deviation details.

[0019] Data correction involves two parts. First, due to differences in mechanical precision and installation, the printing parameters of each printing machine may vary. Therefore, digital printing requires equipment deviation data correction based on the deviation data of each digital printing machine, which is pre-stored in the sample adjustment client. Second, it also requires detailed correction of process scenario deviations based on the process feature parameters of the preset pattern file. This involves adjusting the process scenario data parameters of the most similar historical cases in the database to match the preset pattern file required by the customer. In traditional digital printing, differences in mechanical precision and installation lead to different printing parameter settings for each printing machine. The sample adjustment technician makes targeted fine-tuning based on the current equipment status during sampling. When customers place repeat orders or when mass production is required after sample confirmation, the sampling machine may differ from the production machine, requiring special adjustment for each machine involved in production, and ensuring that the samples from each machine meet the customer's sample requirements. All of the above situations require operation based on the experience and condition of the sample adjustment technician, which is inefficient and contradicts the market trend of small-batch, fast-response printing. This limits the flexibility of digital printing equipment compared to traditional printing for small orders and also increases the recruitment and labor costs for digital printing factories. This embodiment automates the sample adjustment process by storing the calibration data of the target digital printing machine in the sample adjustment client in advance, automatically correcting equipment difference data, and refining process scenario deviations based on previously stored historical cases. This automates the sample adjustment process, improves the efficiency of digital printing, and reduces reliance on skilled sample adjustment technicians.

[0020] If the process scenario data in S2 is retrieved from the cloud-based process database, and the final printed product from the digital printing machine meets the requirements after data correction, then the cloud server performs a similarity assessment between the corrected process scenario data and all previously stored case data in the cloud-based process database. If no case data with a similarity greater than 90% exists in the cloud-based process database, the corrected process scenario data is saved to the cloud-based process database. The purpose is to enrich the cloud-based process database by storing different printing data as samples. If the similarity is too high, it is not necessary to save it repeatedly. Therefore, the similarity threshold for this assessment is relatively high, generally around 90% in practice.

[0021] When importing a preset pattern file to be printed in S1, the process features are quantified into specific parameters and matched with the process scenario parameters of historical cases based on similarity.

[0022] Process characteristics include material characteristics, processing technology type, and customer quality requirement level; material characteristics include ink type, fabric type, and component ratio.

[0023] When calculating similarity matching, different similarity scores are assigned to different types of process scenario features in historical cases, with a total similarity score of 100. The similarity scores of various process scenario features in historical cases are assigned based on the degree of difference between the historical cases and the quantified process feature parameters. The sum of the similarity scores of various process scenario features is used as the overall similarity score of the historical case. The threshold for similarity matching calculation is set at 80 points, and the similarity threshold for the cloud process database to determine whether to update the case is set at 90 points.

[0024] This embodiment also provides an automated digital printing sample adjustment system. Using the above-described automated digital printing sample adjustment method, the system includes a sample adjustment client that imports a preset pattern file to be printed and performs a similarity matching calculation with a local process database or a cloud process database on a cloud server. The local process data and the cloud process database store historical process scenario data cases. The sample adjustment client retrieves cases that meet the similarity criteria, corrects the data, and sends it to the digital printing machine terminal. The digital printing machine terminal drives the digital printing machine to print and saves the process scenario data that meets the finished product effect criteria to the local or cloud process database. The cloud server also communicates remotely with service engineers to manually set process scenario parameters.

[0025] In practice, after processing the pattern file to be printed using image processing software such as PS or AI on a PC, the user imports the pattern file into the sample adjustment client software. The user then sets process scenario features such as ink, pre- and post-processing technology type, fabric type, composition ratio, and customer quality requirement level in the sample adjustment client software. The sample adjustment client software then identifies whether there are scenarios with a similarity of ≥80% in the local database based on the input process scenario features. If the input latest customer order scenario has a one-to-one overlap with existing cases in the local database, it will be judged and a corresponding score will be obtained (total score 100).

[0026] If the sum of the scores for all factors is ≥80, then the similarity between the customer order factory scenario and existing cases in the process library is considered to be ≥80%, and there may be more than one case. The software filters the existing cases according to the similarity score and selects the print data with the highest similarity. This print data is then added to the equipment deviation data (which needs to be set in advance according to the equipment and entered into the sample adjustment client software). Based on the specific differences of the previously judged factors, deviation corrections are made for the process scenarios with differences (e.g., if there are differences in the colors of each color in the color gamut, the color difference is corrected according to the order color; the specific correction value needs to be obtained through testing in advance and entered into the sample adjustment client software). Then, the print data is transmitted to the digital printing machine terminal, which receives the print data and starts printing. The process begins with printing a sample. After printing, the digital printing machine's built-in standard light source vision recognition system identifies the printed sample and judges the difference between it and the original image. If the sample meets the requirements, the process scenario is recorded, and the data is returned to the sample adjustment client database and simultaneously uploaded to the cloud process database. If the sample does not meet the requirements, the specific color deviation is recorded, and the information is returned to the sample adjustment client. This process involves judging the number of failures. If there are fewer than 3 failures, the process scenario deviation details are corrected again, and the printing process is repeated. If there are 3 or more failures, the information is directly fed back to the cloud server. The cloud server prompts that manual intervention is required and sends a message to the mobile phone of the service engineer at the nearest service point in the customer's factory for remote or on-site assistance. The service engineer records the scenario characteristic parameters and the solution process parameters in the cloud process database.

[0027] If there are no historical cases with a similarity greater than 80% (i.e., no cases whose total score for all factors is ≥80) in the local process database of S2, and there are also no historical cases with a similarity greater than 80% in the cloud server, the cloud server will request manual assistance from the service engineer (in the specific implementation process, messages can be sent via SMS or a preset contact application), establish remote communication with the service engineer, and the service engineer will manually intervene according to the customer's requirements, manually adjust the parameter settings of the digital process scenario, and output them to the digital printing machine terminal.

[0028] S4 will count the number of times process scene deviation details are corrected. If the finished product does not meet the requirements multiple times during the printing process of a product, resulting in multiple corrections of process scene deviation details, and the number of consecutive corrections exceeds 3, a manual intervention request will be sent to the cloud server. The cloud server will communicate remotely with the service engineer to manually intervene, set the process scene parameters, and output them to the digital printing machine terminal.

[0029] In the specific implementation process, if the sum of the final scores of all factors is less than 80 points, the sample adjustment terminal sends a request to the cloud server for case support from the cloud process database. The cloud server performs scenario matching in the solution library and executes scenario similarity judgment (the judgment rules and methods are the same as those of the sample adjustment terminal). The most similar case is selected according to the similarity score, and the data is output to the sample adjustment client software for looping. After success, the cloud server compares the order data and automatically determines whether the case in the process library needs to be updated. If not (similarity exceeds 90%), the process ends. If it is needed, the case is updated to the cloud server scenario library. If there are no scenario cases with similarity ≥ 80% in the cloud server's process scenario library, the information is directly fed back to the cloud server. The cloud server prompts that manual intervention is required and sends a message to the mobile phone of the service engineer corresponding to the nearest service point in the customer's factory for remote or on-site assistance. The service engineer records the scenario feature parameters and solution process parameters in the cloud process library.

[0030] Example 2: An automated sample preparation method for digital printing, comprising the following steps: S1. Import the preset pattern file to be printed into the sample adjustment client and perform similarity matching calculation with historical cases in the local process database; S2. Filter out historical cases with similarity greater than the preset threshold A, select the process scene data of the case with the highest similarity, correct the data, and output it to the digital printing machine terminal. S3. The digital printing machine terminal drives the digital printing machine to print based on the corrected process scene data parameters and judges the finished product effect. S4. If the finished product meets the requirements, record the process scenario data and save it to the local process database; if the finished product does not meet the requirements, return to S2 to re-correct the process scenario deviation details.

[0031] Data correction involves two parts. First, due to differences in mechanical precision and installation, the printing parameters of each printing machine may vary. Therefore, digital printing requires equipment deviation data correction based on the deviation data of each digital printing machine, which is pre-stored in the sample adjustment client. Second, it also requires detailed correction of process scenario deviations based on the process feature parameters of the preset pattern file. This involves adjusting the process scenario data parameters of the most similar historical cases in the database to match the preset pattern file required by the customer. In traditional digital printing, differences in mechanical precision and installation lead to different printing parameter settings for each printing machine. The sample adjustment technician makes targeted fine-tuning based on the current equipment status during sampling. When customers place repeat orders or when mass production is required after sample confirmation, the sampling machine may differ from the production machine, requiring special adjustment for each machine involved in production, and ensuring that the samples from each machine meet the customer's sample requirements. All of the above situations require operation based on the experience and condition of the sample adjustment technician, which is inefficient and contradicts the market trend of small-batch, fast-response printing. This limits the flexibility of digital printing equipment compared to traditional printing for small orders and also increases the recruitment and labor costs for digital printing factories. This embodiment automates the sample adjustment process by storing the calibration data of the target digital printing machine in the sample adjustment client in advance, automatically correcting equipment difference data, and refining process scenario deviations based on previously stored historical cases. This automates the sample adjustment process, improves the efficiency of digital printing, and reduces reliance on skilled sample adjustment technicians.

[0032] If there are no historical cases with a similarity greater than 80% in the local process database of S2, and there are also no historical cases with a similarity greater than 80% in the cloud server, the cloud server will request manual assistance from the service engineer (in the specific implementation process, messages can be sent via SMS or a preset contact application), establish remote communication with the service engineer, and the service engineer will manually intervene according to the customer's requirements, manually adjust the digital process scenario parameter settings, and output them to the digital printing machine terminal.

[0033] S4 will count the number of times process scene deviation details are corrected. If the finished product does not meet the requirements multiple times during the printing process of a product, resulting in multiple corrections of process scene deviation details, and the number of consecutive corrections exceeds 3, a manual intervention request will be sent to the cloud server. The cloud server will communicate remotely with the service engineer to manually intervene, set the process scene parameters, and output them to the digital printing machine terminal.

[0034] If the process scenario data in S2 is retrieved from the cloud-based process database, and the final printed product from the digital printing machine meets the requirements after data correction, then the cloud server performs a similarity assessment between the corrected process scenario data and all previously stored case data in the cloud-based process database. If no case data with a similarity greater than 90% exists in the cloud-based process database, the corrected process scenario data is saved to the cloud-based process database. The purpose is to enrich the cloud-based process database by storing different printing data as samples. If the similarity is too high, it is not necessary to save it repeatedly. Therefore, the similarity threshold for this assessment is relatively high, generally around 90% in practice.

[0035] When importing a preset pattern file to be printed in S1, the process features are quantified into specific parameters and matched with the process scenario parameters of historical cases based on similarity.

[0036] Process characteristics include material characteristics, processing technology type, and customer quality requirement level; material characteristics include ink type, fabric type, and component ratio.

[0037] When calculating similarity matching, different similarity scores are assigned to different types of process scenario features in historical cases, with a total similarity score of 100. The similarity scores of various process scenario features in historical cases are assigned based on the degree of difference between the historical cases and the quantified process feature parameters. The sum of the similarity scores of various process scenario features is used as the overall similarity score of the historical case. The threshold for similarity matching calculation is set at 80 points, and the similarity threshold for the cloud process database to determine whether to update the case is set at 90 points.

[0038] This embodiment also provides an automated digital printing sample adjustment system. Using the above-described automated digital printing sample adjustment method, the system includes a sample adjustment client that imports a preset pattern file to be printed and performs a similarity matching calculation with a local process database or a cloud process database on a cloud server. The local process data and the cloud process database store historical process scenario data cases. The sample adjustment client retrieves cases that meet the similarity criteria, corrects the data, and sends it to the digital printing machine terminal. The digital printing machine terminal drives the digital printing machine to print and saves the process scenario data that meets the finished product effect criteria to the local or cloud process database. The cloud server also communicates remotely with service engineers to manually set process scenario parameters.

[0039] In practice, after processing the pattern file to be printed using image processing software such as PS or AI on a PC, the user imports the pattern file into the sample adjustment client software. The user then sets process scenario features such as ink, pre- and post-processing technology type, fabric type, composition ratio, and customer quality requirement level in the sample adjustment client software. The sample adjustment client software then identifies whether there are scenarios with a similarity of ≥80% in the local database based on the input process scenario features. If the input latest customer order scenario has a one-to-one overlap with existing cases in the local database, it will be judged and a corresponding score will be obtained (total score 100).

[0040] If the sum of the scores for all factors is ≥80, then the similarity between the customer order factory scenario and existing cases in the process library is considered to be ≥80%, and there may be more than one case. The software filters the existing cases according to the similarity score and selects the print data with the highest similarity. This print data is then added to the equipment deviation data (which needs to be set in advance according to the equipment and entered into the sample adjustment client software). Based on the specific differences of the previously judged factors, deviation corrections are made for the process scenarios with differences (e.g., if there are differences in the colors of each color in the color gamut, the color difference is corrected according to the order color; the specific correction value needs to be obtained through testing in advance and entered into the sample adjustment client software). Then, the print data is transmitted to the digital printing machine terminal, which receives the print data and starts printing. The process begins with printing a sample. After printing, the digital printing machine's built-in standard light source vision recognition system identifies the printed sample and judges the difference between it and the original image. If the sample meets the requirements, the process scenario is recorded, and the data is returned to the sample adjustment client database and simultaneously uploaded to the cloud process database. If the sample does not meet the requirements, the specific color deviation is recorded, and the information is returned to the sample adjustment client. This process involves judging the number of failures. If there are fewer than 3 failures, the process scenario deviation details are corrected again, and the printing process is repeated. If there are 3 or more failures, the information is directly fed back to the cloud server. The cloud server prompts that manual intervention is required and sends a message to the mobile phone of the service engineer at the nearest service point in the customer's factory for remote or on-site assistance. The service engineer records the scenario characteristic parameters and the solution process parameters in the cloud process database.

[0041] If the sum of the final scores for all factors is less than 80 points, the sample adjustment terminal sends a request to the cloud server for case support from the cloud process database. The cloud server performs scenario matching in the solution library and executes scenario similarity determination (the determination rules and methods are the same as those for the sample adjustment terminal). It selects the most similar case based on the similarity score and outputs the data to the sample adjustment client software for looping. After successful processing, the cloud server compares the order data and automatically determines whether to update the case in the process library. If not (similarity exceeding 90%), the process ends; otherwise, the case is updated to the cloud server's scenario library. If the cloud server's process scenario library also lacks a scenario case with a similarity ≥ 80%, the information is directly fed back to the cloud server. The cloud server prompts for manual intervention, sends a message to the mobile phone of the service engineer at the nearest service point in the customer's factory, and provides remote or on-site assistance. The service engineer records the scenario characteristic parameters and solution process parameters in the cloud process library.

[0042] Table 2 As shown in Table 2 above, in this embodiment, the similarity score is based on eight factors: consistency of fabric type, consistency of main fabric components, consistency of fabric component proportion, similarity of color gamut distribution of unit cycle pattern, consistency of pre-processing, consistency of ink type, consistency of post-processing, and customer requirement level.

[0043] Table 3 Table 3 above shows an example of similarity calculation for process scene features between existing cases in the process database and the printed patterns in the input customer orders. The difference in color gamut similarity for unit loop patterns is judged by a total difference of 28% per color, resulting in a score of 2 (rounded down to the nearest integer).

[0044] This embodiment can aggregate a large number of customer cases through a cloud server to solve specific customer scenario problems; this embodiment can integrate and manage the differences between equipment in the factory, and automatically correct deviations according to the equipment conditions during printing; it can also digitize human experience data, realize experience management and reuse, significantly improve the efficiency of sample adjustment and subsequent mass production, and reduce dependence on human labor.

Claims

1. An automated sample preparation method for digital printing, characterized in that, Includes the following steps: S1. Import the preset pattern file to be printed into the sample adjustment client and perform similarity matching calculation with historical cases in the local process database; S2. Filter out historical cases with similarity greater than the preset threshold A, select the process scene data of the case with the highest similarity, correct the data, and output it to the digital printing machine terminal. S3. The digital printing machine terminal drives the digital printing machine to print based on the corrected process scene data parameters and judges the finished product effect. S4. If the finished product meets the requirements, record the process scenario data and save it to the local process database; if the finished product does not meet the requirements, return to S2 to re-correct the process scenario deviation details.

2. The automated digital printing sample preparation method according to claim 1, characterized in that, Data correction includes equipment difference data correction based on the deviation data of each digital printing machine stored in the sample client, and process scene deviation detail correction based on the process feature parameters of the preset pattern file.

3. The automated digital printing sample preparation method according to claim 1, characterized in that, If there are no historical cases with a similarity greater than the preset threshold A in the local process database in S2, then a similarity matching calculation is performed with the historical cases in the cloud process database in the cloud server. The process scene data of the historical case with the largest similarity greater than the threshold A is retrieved, the equipment difference data is corrected, and the process scene deviation details are corrected according to the preset pattern file. Finally, the data is output to the digital printing machine terminal.

4. The automated digital printing sample preparation method according to claim 1 or 3, characterized in that, If there are no historical cases with a similarity greater than the preset threshold A in the local process database in S2, and there are also no historical cases with a similarity greater than the preset threshold A in the cloud server, the cloud server communicates remotely with the service engineer to manually intervene in setting the process scenario parameters and output them to the digital printing machine terminal.

5. The automated digital printing sample preparation method according to claim 1, characterized in that, In S4, the number of times the finished product does not meet the requirements and the process scene deviation details need to be corrected is counted. If the number of consecutive modifications exceeds the preset threshold, a manual intervention request is sent to the cloud server. The cloud server communicates remotely with the service engineer, and the manual intervention sets the process scene parameters and outputs them to the digital printing machine terminal.

6. The automated digital printing sample preparation method according to claim 3, characterized in that, If the process scenario data is retrieved from the cloud process database in S2 and the final printed product of the digital printing machine meets the requirements after data correction, the cloud server will perform a similarity judgment on all case data in the cloud process database and the process scenario data after this printing correction; if there is no case data in the cloud process database with a similarity greater than the preset threshold B, the process scenario data after this printing correction will be saved to the cloud process database.

7. The automated digital printing sample preparation method according to claim 1, characterized in that, When importing a preset pattern file to be printed in S1, the process features are quantified into specific parameters and matched with the process scenario parameters of historical cases based on similarity.

8. The automated digital printing sample preparation method according to claim 7, characterized in that, Process characteristics include material characteristics, processing technology type, and customer quality requirement level; Material characteristics include ink type, fabric type, and component ratio.

9. The automated digital printing sample preparation method according to claim 7, characterized in that, When calculating similarity matching, different similarity scores are assigned to different types of process scenario features in historical cases, with a total similarity score of 100. The similarity scores of various process scenario features in historical cases are assigned based on the degree of difference between the historical cases and the quantified process feature parameters. The sum of the similarity scores of various process scenario features is used as the overall similarity score of the historical case. The threshold A for similarity matching calculation is set to 80 points, and the threshold B is set to 90 points.

10. An automated digital printing sample preparation system, using the automated digital printing sample preparation method according to any one of claims 1-9, characterized in that, This includes a sample adjustment client that imports preset pattern files to be printed and performs similarity matching calculations with the local process database or the cloud process database on the cloud server; the local process data and the cloud process database store historical process scenario data cases; The sample client retrieves cases that meet the similarity standard, corrects the data, and sends them to the digital printing machine terminal; the digital printing machine terminal drives the digital printing machine to print and saves the process scene data that meets the finished product effect to the local or cloud process database; the cloud server also communicates remotely with service engineers to manually set process scene parameters.

Images