A method, process, system, product and medium for batch printing product dispensing

Abstract

The application provides a batch-printed product sub-packaging method, process, system, product and medium, and relates to the technical field of image recognition. Label information of a current packaging bag is acquired, specific requirements corresponding to each packaging bag can be clearly and definitely determined, then, the unit weight of the printed product and the unit weight of the current packaging bag are used to calculate the theoretical total weight of the printed product in the current packaging bag, and the floating weight is determined according to the required number of printed products, the theoretical weight range is determined based on the floating weight and the theoretical total weight, these features cooperate with each other, finally, the weight information of the current packaging bag is acquired, and the number is rechecked according to whether the weight information is located in the theoretical weight range, through comparison between the actual weight and the theoretical range, whether the number is accurate can be quickly located, the disadvantage that previous errors need to be rechecked is avoided, the rechecking efficiency is improved, the sub-packaging progress is steadily promoted, and the accuracy and timeliness of sub-packaging are improved as a whole.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image recognition, in particular to a batch-printed product packaging method, process, system, product and medium. BACKGROUND

[0002] In the field of education, batch-printed products such as test papers and exercise books have clear distribution requirements. They need to be packaged according to different regions, schools, and specific classes, etc., to ensure accurate supply to the corresponding use scenarios. For example, different-sized primary schools have different numbers of classes, and the number of students in each class is not the same. For example, A Primary School has a total of 4 classes, with 28 students in A1, 32 students in A2, 31 students in A3, and 25 students in A4. B Primary School has a total of 3 classes, with 22 students in B1, 32 students in B2, and 28 students in B3. Moreover, many times these test papers need to be sealed and transported to designated locations such as examination rooms, so after printing, they need to be sealed and packaged according to the class situation, which is an important link to ensure the normal development of teaching-related activities.

[0003] Currently, for the packaging of batch-printed products, especially for test papers that require high confidentiality, if it is found that the number of test papers in one test paper bag is incorrect during review, all previously packaged test paper bags need to be rechecked, which is extremely time-consuming and labor-intensive, seriously affecting the overall packaging progress. SUMMARY

[0004] The present application provides a batch-printed product packaging method, process, system, product and medium, which can quickly locate the accuracy of the number and avoid the disadvantage of rechecking all when there is an error, thereby improving the review efficiency.

[0005] In a first aspect, the present application provides a batch-printed product packaging method, comprising: obtaining label information of a current packaging bag; the label information includes school, class, required number of printed products, and printed product subject information; conveying corresponding printed products to the current packaging bag according to the label information; after the conveying is completed, calculating the theoretical total weight of the printed products in the current packaging bag according to the unit weight of the printed products and the unit weight of the current packaging bag; determining a floating weight according to the required number of printed products, and determining a theoretical weight range based on the floating weight and the theoretical total weight; obtaining weight information of the current packaging bag, and performing number review according to whether the weight information is located in the theoretical weight range; according to the printed product subject information, extracting a pre-stored printed product electronic template to obtain template feature information of the printed product; obtaining images of the printed product according to a preset sampling ratio; and obtaining actual feature information of the images of the printed product; calculating a consistency score of the template feature information and the actual feature information; and performing content review according to whether the consistency score is higher than a preset score threshold.

[0006] By adopting the technical solution, the label information of the current packaging bag is acquired, the specific requirements corresponding to each packaging bag are clear and definite, and a foundation is laid for subsequent accurate sub-packaging. Then, the theoretical total weight of the printing products in the current packaging bag is calculated according to the unit weight of the printing products and the unit weight of the current packaging bag, and the floating weight is determined according to the required number of printing products, the theoretical weight range is determined based on the floating weight and the theoretical total weight, these features cooperate with each other to determine a reasonable range based on objective weight data and quantity requirements, finally the weight information of the current packaging bag is acquired, and the quantity is rechecked according to whether the weight information is located in the theoretical weight range, through comparison between the actual weight and the theoretical range, whether the quantity is accurate can be quickly located, the disadvantage that previous errors need to be rechecked is avoided, the rechecking efficiency is improved, the sub-packaging progress is ensured to steadily advance, and the accuracy and timeliness of sub-packaging are overall improved. Meanwhile, whether the printing products are placed incorrectly is further judged according to the consistency between the comparison template feature information and the actual feature.

[0007] In combination with some embodiments of the first aspect, in some embodiments, after the step of acquiring the weight information of the current packaging bag and rechecking the quantity according to whether the weight information is located in the theoretical weight range; after the quantity rechecking succeeds, the historical packaging bag of the same kind of the current packaging bag is determined according to the printing product subject information; the historical weight information of the historical packaging bag is acquired; the calculated product weight of the printing products is calculated according to the weight difference value and the quantity difference value; the quantity difference value is the difference between the required number of printing products of the current packaging bag and the required number of printing products of the historical packaging bag; the weight difference value is the difference between the weight information of the current packaging bag and the historical weight information; the average value of all the calculated product weights is updated to the unit weight of the printing products; and the updated unit weight of the printing products is used for quantity rechecking of the next packaging bag.

[0008] By adopting the technical scheme, after the quantity rechecking succeeds, the historical packaging bag of the same kind of the current packaging bag is determined according to the subject information of the printed product, and the same kind of packaging bag is screened out with the help of the subject information, so that subsequent comparison and analysis are facilitated. The historical weight information of the historical packaging bag is obtained, the quantity difference is the difference between the required printed product quantity of the current packaging bag and the required printed product quantity of the historical packaging bag, and the weight difference is the difference between the weight information of the current packaging bag and the difference between the historical weight information. The two sets of differences are used to accurately quantify the difference. Then, the calculated product weight of the printed product is calculated according to the weight difference and the quantity difference, and a more accurate product weight is obtained based on rigorous calculation. The average value of all the calculated product weights is updated to the unit weight of the printed product. The updated unit weight of the printed product is used for quantity rechecking of the next packaging bag. By updating the unit weight, the subsequent packaging bag can be based on a more accurate weight standard during quantity rechecking, and the weight deviation caused by human factors, material technology and other factors can be gradually corrected, so that the quantity rechecking is more accurate, and the reliability of the weight-based split operation is improved.

[0009] In combination with some embodiments of the first aspect, in some embodiments, after the step of calculating the calculated product weight of the printed product according to the weight difference and the quantity difference, the method further comprises: substituting the historical weight information and the corresponding calculated product weight into a linear relationship model, the slope of the linear relationship model being the calculated product weight, and the intercept of the linear relationship model being the calculated packaging bag weight; updating the weight information of the current packaging bag with the average value of all the calculated packaging bag weights; and using the updated weight information of the current packaging bag for quantity rechecking of the next packaging bag.

[0010] By adopting the technical scheme, the historical weight information and the corresponding calculated product weight are substituted into a linear relationship model, the slope of the linear relationship model is the calculated product weight, and the intercept of the linear relationship model is the calculated packaging bag weight. The historical data and the current calculation result are deeply integrated and analyzed by using the linear relationship model, and the reasonable value of the packaging bag weight is mined. Then, the weight information of the current packaging bag is updated with the average value of all the calculated packaging bag weights. The updated weight information of the current packaging bag is used for quantity rechecking of the next packaging bag. By updating the weight information of the current packaging bag, the next round of quantity rechecking work has a more accurate weight reference, effectively compensating for the deviation between the actual weight and the preset weight, and continuously optimizing the weight-based split operation.

[0011] In some embodiments of the first aspect, according to the subject information of the printed product, the pre-stored electronic template of the printed product is extracted, the template feature information of the printed product is obtained, the image of the printed product is obtained according to a preset sampling ratio, and the actual feature information of the image of the printed product is obtained. The consistency score of the template feature information and the actual feature information is calculated. According to whether the consistency score is higher than a preset score threshold, the content review step is performed, which specifically includes: extracting the pre-stored electronic template of the printed product according to the subject information of the printed product; extracting the first feature information of the cover in the electronic template of the printed product; and recording the first position information of the first feature information; based on a preset region size, a plurality of second feature information is randomly extracted in the electronic template of the printed product, and a plurality of corresponding second position information is recorded; the image of the printed product is obtained according to a preset sampling ratio; the third feature information of the image of the printed product is obtained according to the first position information; it is judged whether the first feature information is consistent with the third feature information; if consistent, a second position information that has not been used is randomly selected, and the fourth feature information of the image of the printed product is obtained; it is judged whether the second feature information is consistent with the fourth feature information; if consistent, the step of randomly selecting a second position information that has not been used and obtaining the fourth feature information of the image of the printed product is returned.

[0012] By adopting the above technical solution, according to the subject information of the printed product, the pre-stored electronic template of the printed product is extracted, the template feature information of the printed product is obtained, the representative feature information is extracted from the electronic template; and the first position information of the first feature information is recorded; based on a preset region size, a plurality of second feature information is randomly extracted in the electronic template of the printed product, and a plurality of corresponding second position information is recorded, the key features and positions are accurately positioned, and the comparison range is reduced. The image of the printed product is obtained according to a preset sampling ratio; the third feature information of the image of the printed product is obtained according to the first position information, the image features are compared according to the corresponding positions, and if consistent, a second position information that has not been used is randomly selected, and the fourth feature information of the image of the printed product is obtained; it is judged whether the second feature information is consistent with the fourth feature information; if consistent, the step of randomly selecting a second position information that has not been used and obtaining the fourth feature information of the image of the printed product is returned. In this way, the step-by-step verification and cyclic judgment mode avoids indiscriminate comparison of all image data, reduces the amount of feature comparison data, speeds up the comparison speed, makes the content review link efficient, ensures that the distribution work can be promoted on time, and ensures that the teaching materials are timely and accurately distributed to the classes.

[0013] In some embodiments of the first aspect, before the step of determining the theoretical weight range based on the floating weight and the theoretical total weight, the method further comprises: determining a target interval in a preset floating table according to the number of required printed products; the preset floating table comprises a plurality of intervals with a range from small to large, and the corresponding threshold of the interval is from large to small; adjusting the floating weight according to the threshold corresponding to the target interval; after the step of determining the theoretical weight range based on the floating weight and the theoretical total weight, the method further comprises: obtaining a cumulative weight deviation, the cumulative weight deviation being the sum of the difference between the theoretical total weight and the weight information of different packaging bags; and adjusting the theoretical weight range according to the cumulative weight deviation.

[0014] By adopting the above technical solution, the target interval in the preset floating table is determined according to the number of required printed products; the preset floating table comprises a plurality of intervals with a range from small to large, and the corresponding threshold of the interval is from large to small; the floating weight is adjusted according to the threshold corresponding to the target interval, the appropriate interval is accurately positioned in the preset floating table according to the number, and then the floating weight is adjusted accordingly, so that the determination of the floating weight is more scientific and reasonable, and randomness is avoided. After determining the theoretical weight range based on the floating weight and the theoretical total weight, the cumulative weight deviation is obtained, the cumulative weight deviation being the sum of the difference between the theoretical total weight and the weight information of different packaging bags; and the theoretical weight range is adjusted according to the cumulative weight deviation, the theoretical weight range is adjusted by using the cumulative deviation feedback, and the two-way optimization makes the theoretical weight range more suitable for the actual situation, effectively preventing the problem of quantity misjudgment caused by the simple accumulation of the floating weight leading to a too large range.

[0015] In some embodiments of the first aspect, the step of calculating the consistency score of the template feature information and the actual feature information specifically comprises: calculating a similarity score of geometric features in the template feature information and the actual feature information; calculating a similarity score of visual features in the template feature information and the actual feature information; and weighting and synthesizing the similarity scores of the geometric features and the visual features to obtain the consistency score.

[0016] By adopting the above technical solution, the similarity score of geometric features in the template feature information and the actual feature information is calculated, the similarity degree of the two is measured from the geometric angle, and the consistency in shape, structure and the like can be accurately captured. The similarity score of visual features in the template feature information and the actual feature information is calculated from the visual presentation level, such as color, texture and the like, to judge the similarity in two dimensions.

[0017] In a second aspect, the application provides a batch-printed product packaging process, comprising: attaching label information to a packaging bag; the label information comprising a school, a class, a required number of printed products, and subject information of the printed products; transporting the packaging bag to the outlet of a printing device one by one by a rotating device; setting a counting device and a scanning and identifying device at the outlet; sending corresponding label information to a host after the scanning and identifying device obtains the label information on the current packaging bag; controlling the counting device and the printing device to deliver corresponding printed products to the packaging bag by the host; determining a floating weight according to the required number of printed products, and determining a theoretical weight range based on the floating weight and a theoretical total weight; moving the current packaging bag to a review area by the rotating device, obtaining weight information of the current packaging bag, and performing quantity review according to whether the weight information is located in the theoretical weight range; in the review device, extracting a pre-stored electronic template of the printed product according to the subject information of the printed product, and obtaining template feature information of the printed product; in the review device, obtaining an image of the printed product according to a preset sampling ratio, and obtaining actual feature information of the image of the printed product; in the review device, calculating a consistency score of the template feature information and the actual feature information; performing content review according to whether the consistency score is higher than a preset score threshold; if the review is correct, sealing the packaging bag; and centrally stacking the sealed current packaging bag according to the school in the label information.

[0018] In a third aspect, the application provides a batch-printed product packaging system, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program code, the computer program code comprising computer instructions, and the one or more processors are configured to invoke the computer instructions to enable the batch-printed product packaging system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0019] In a fourth aspect, the application provides a computer program product comprising instructions, which, when executed on a batch-printed product packaging system, enable the batch-printed product packaging system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0020] In a fifth aspect, the application provides a computer-readable storage medium comprising instructions, which, when executed on a batch-printed product packaging system, enable the batch-printed product packaging system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0021] The one or more technical solutions provided in the embodiments of the application have at least the following technical effects or advantages:

[0022] 1、Obtain the label information of the current packaging bag, which can clearly and explicitly indicate the specific requirements of each packaging bag, laying the foundation for subsequent precise dispensing. Then, calculate the theoretical total weight of the printing products in the current packaging bag according to the unit weight of the printed product and the unit weight of the current packaging bag, and determine the floating weight according to the required number of printing products. Based on the floating weight and the theoretical total weight, determine the theoretical weight range. These features work together to determine a reasonable range based on objective weight data and quantity requirements. Finally, obtain the weight information of the current packaging bag, and perform quantity review based on whether the weight information is within the theoretical weight range. By comparing the actual weight with the theoretical range, it can quickly determine whether the quantity is accurate, avoiding the disadvantage of having to recheck everything when there is an error in the past, improving the review efficiency, ensuring the steady progress of dispensing, and overall improving the accuracy and timeliness of dispensing. At the same time, according to the consistency of the comparison template feature information and the actual features, further judge whether the printing products are placed incorrectly.

[0023] 2、After successful quantity review, determine the historical packaging bag of the same kind of the current packaging bag according to the subject information of the printing product, and use the subject information to filter out similar packaging bags for subsequent comparison and analysis. Obtain the historical weight information of the historical packaging bag, the quantity difference is the difference between the required number of printing products of the current packaging bag and the required number of printing products of the historical packaging bag; the weight difference is the difference between the weight information of the current packaging bag and the difference between the historical weight information, and use the two sets of differences to accurately quantify the difference. Then calculate the calculated product weight of the printing product according to the weight difference and the quantity difference, and obtain a more realistic product weight based on rigorous calculation. Update the unit weight of the printing product with the average value of all calculated product weights; the updated unit weight of the printing product is used for quantity review of the next packaging bag. By updating the unit weight, the subsequent packaging bag can be based on a more accurate weight standard when performing quantity review, gradually correcting the weight deviation caused by human factors, material technology and other factors, making the quantity review more accurate and improving the reliability of the weight-based dispensing operation.

[0024] 3. According to the printed product subject information, extract the pre-stored printed product electronic template, obtain the template feature information of the printed product, first extract the representative feature information from the electronic template; and record the first position information of the first feature information; based on the pre-set area size, randomly extract a plurality of second feature information in the printed product electronic template, and record a plurality of corresponding second position information, accurately locate the key features and positions, and narrow the comparison range. Obtain the image of the printed product according to the pre-set sampling ratio; obtain the third feature information of the image of the printed product according to the first position information, compare the image features according to the corresponding positions, and if they are consistent, randomly select an unused second position information to obtain the fourth feature information of the image of the printed product; judge whether the second feature information is consistent with the fourth feature information; if consistent, return to the step of randomly selecting an unused second position information to obtain the fourth feature information of the image of the printed product. This step-by-step verification and cyclic judgment mode avoids indiscriminate comparison of all image data, reduces the amount of feature comparison data, speeds up the comparison speed, makes the content review link efficient, ensures that the packaging work can be on schedule, and ensures that the teaching materials are timely and accurately distributed to the classes. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 is a flowchart of the product packaging method in batches printed in the embodiment of the present application;

[0026] Figure 2 is another flowchart of the product packaging method in batches printed in the embodiment of the present application;

[0027] Figure 3 is a specific flowchart of steps S106 to S108 in the embodiment of the present application;

[0028] Figure 4 is another flowchart of the product packaging method in batches printed in the embodiment of the present application;

[0029] Figure 5 is a schematic diagram of an exemplary hardware structure of the product packaging system in batches printed in the embodiment of the present application. DETAILED DESCRIPTION

[0030] The terms used in the following embodiments of the present application are only for the purpose of describing the specific embodiments, and are not intended to be limiting to the present application. As used in the specification and the appended claims of the present application, the singular forms "a," "an," "the," "said," "upper," and "this" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms used in this specification and / or the appended claims are intended to describe the particular embodiments and not to limit the application.

[0031] The terms first, second, etc. are used only for descriptive purposes and do not connote or imply relative importance or imply a quantity of the indicated technical features. Thus, features defined with the terms first, second, etc. can explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, the meaning of multiple is two or more, unless otherwise specified.

[0032] Please refer to Figure 1 , Figure 1 is a flowchart of a product dispensing method in batch printing in the embodiments of the present application;

[0033] S101, obtaining label information of a current packaging bag; the label information includes a school, a class, a required number of printed products, and subject information of the printed products;

[0034] Among them, the current packaging bag represents a packaging container for containing printed products that is being processed, such as a common paper test paper bag, a cowhide data bag, etc., which is used to load the required printed products of the corresponding class, facilitating subsequent transportation and distribution.

[0035] In some embodiments, labels with two-dimensional codes or bar codes are provided on the packaging bags, and the labels have pre-stored label information; a code scanning device is used to scan the two-dimensional code or bar code, and a terminal system connected to the code scanning device automatically analyzes the school, class, required number of printed products, and subject information of the printed products contained therein; the analyzed information is directly stored into a dispensing management database for subsequent dispensing process, which is not limited here.

[0036] S102, delivering corresponding printed products to the current packaging bag according to the label information;

[0037] Among them, the printed products refer to various paper materials such as test papers, exercise books, and teaching materials produced through batch printing processes.

[0038] In some embodiments, according to the label information obtained in step S101, such as knowing that 50 copies of English test papers are required for Class 2 of Grade 3 of B Primary School, the automatic delivery device will go to the area where the English test papers are stored, select the corresponding 50 copies of test papers, and then deliver these printed products into the current packaging bag through a conveyor belt or other transportation methods, to ensure that the printed products loaded are completely consistent with the requirements of the label information, providing an accurate basis for subsequent review and other operations.

[0039] S103, calculating a theoretical total weight of the printed products in the current packaging bag according to the unit weight of the printed products and the unit weight of the current packaging bag after the delivery is completed;

[0040] The unit weight of the printed product refers to a single printed product, which can be measured in advance by a weighing device and recorded. The unit weight of the current packaging bag refers to the weight of the packaging bag being processed at present, which can also be measured by a weighing device.

[0041] In some embodiments, the weight of a single printed product is measured by an electronic scale, and recorded as the unit weight of the printed product. The empty current packaging bag is placed on the same electronic scale to obtain its unit weight, which is recorded. The number of printed products in the current packaging bag is counted, and the number is multiplied by the unit weight of the printed product, and then the unit weight of the current packaging bag is added to obtain the theoretical total weight.

[0042] S104, determining a floating weight according to the required number of printed products, and determining a theoretical weight range based on the floating weight and the theoretical total weight;

[0043] In some embodiments, a floating weight value is obtained, which is determined according to the required number of printed products and past experience or a pre-set standard. The estimated floating weight value is added to and subtracted from the calculated theoretical total weight to obtain the lower limit value and the upper limit value of the theoretical weight range. The lower limit value and the upper limit value are recorded to form the theoretical weight range, which is used for subsequent comparison.

[0044] S105, obtaining the weight information of the current packaging bag, and performing quantity review according to whether the weight information is located in the theoretical weight range;

[0045] Specifically, the weighing device is used to weigh the packaging bag that has already been filled with printed products to obtain the actual weight information. Then, the actual weight information is compared with the theoretical weight range determined in step S104. If the actual weight is within the range, it is preliminarily judged that the number of printed products filled is correct. If it is not within the range, it means that there may be an error in the number of printed products filled, and further investigation is needed to complete the review of the number of printed products and ensure the accuracy of the packaging of each packaging bag.

[0046] S106, extracting a pre-stored printed product electronic template according to the printed product subject information to obtain template feature information of the printed product;

[0047] The pre-stored printed product electronic template refers to a standard electronic document stored in advance in a computer system or a database, which is made according to different printed product subjects and contains information such as ideal style, format, layout and content framework of the corresponding printed product.

[0048] Specifically, first, according to the subject information of the printed product in the current packaging bag, such as an English test paper, then accurately find and extract the corresponding English test paper pre-stored electronic template from the database storing a plurality of electronic templates, and then extract the template characteristic information such as the font format of the title, the layout style of the specific question type, and the fixed logo pattern on the test paper from the electronic template through special image recognition and text analysis software tools. These information is sorted out to prepare for the comparison with the characteristics of the actual printed product, so as to check whether the content of the printed product is accurate.

[0049] S107, according to the preset sampling ratio, obtaining the image of the printed product; and obtaining the actual characteristic information of the image of the printed product;

[0050] Specifically, first, according to the preset sampling ratio, using a scanner or a high-definition camera and other image acquisition devices, the corresponding number of printed products are scanned or photographed page by page, and the image of the printed product is obtained. Then, using image analysis software, the images are processed to extract actual characteristic information such as the clarity of the text, whether there are missing words, whether the lines of the chart are complete, and whether the color is accurate. These actual characteristic information is sorted out for subsequent comparison with the template characteristic information obtained before, to determine whether the content of the printed product meets the standard requirements.

[0051] It should be noted that in some embodiments, there is a more efficient operation mode, that is, the related operations are carried out simultaneously during the execution of step S102. Specifically, when the corresponding printed product is conveyed to the current packaging bag, the image of the printed product can be obtained simultaneously using the corresponding device, and the actual characteristic information can be extracted therefrom. In this way, the time can be fully utilized, and the collection of part of the subsequent required characteristic information can be carried out in advance while completing the basic task of product conveying, thereby improving the efficiency of the overall work flow. At the same time, it has the effect of reducing the process.

[0052] S108, calculating the consistency score of the template characteristic information and the actual characteristic information; and performing content review according to whether the consistency score is higher than the preset score threshold.

[0053] Specifically, the extracted template characteristic information and the actual characteristic information are compared one by one, such as comparing whether the font and size of the text are consistent, whether the shape, position and content of the chart are consistent, etc. Then, using a special similarity calculation algorithm, the comparison of each characteristic is quantitatively scored, for example, the text characteristic matching degree is high, and the chart characteristic is also mostly matched, so a relatively high consistency score is obtained according to the algorithm rule. Then, the score is compared with the preset score threshold, if the consistency score is higher than the preset score threshold, it means that the content of the current sampled printed product meets the standard requirements as a whole, and the content review is passed.

[0054] In some specific embodiments, the input template feature information and the actual feature information, the system automatically uses image recognition and text analysis technology, etc., to comprehensively compare the multi-dimensions of geometric features, visual features, etc., of the two, and generate feature difference information.

[0055] It can be seen that obtaining the label information of the current packaging bag can clearly and explicitly specify the specific requirements corresponding to each packaging bag, laying a foundation for subsequent accurate sub-packaging. Then, the theoretical total weight of the printing product in the current packaging bag is calculated according to the unit weight of the printing product and the unit weight of the current packaging bag, and the floating weight is determined according to the required number of printing products, and the theoretical weight range is determined based on the floating weight and the theoretical total weight. These features cooperate with each other to determine a reasonable range based on objective weight data and quantity requirements. Finally, the weight information of the current packaging bag is obtained, and the quantity is rechecked according to whether the weight information is located in the theoretical weight range. Through the comparison between the actual weight and the theoretical range, it can quickly locate whether the quantity is accurate, avoiding the disadvantage of rechecking all the previous errors, improving the rechecking efficiency, ensuring the steady progress of sub-packaging, and overall improving the accuracy and timeliness of sub-packaging. At the same time, according to the consistency of the compared template feature information and the actual feature, whether the printing product is placed incorrectly is further judged.

[0056] In some specific embodiments, step S108 specifically includes: S1081, calculating the similarity score of the geometric features in the template feature information and the actual feature information;

[0057] Specifically, the geometric feature related content is first extracted from the template feature information, such as arranging the shape parameters of each graphic in the electronic template, the position coordinates of each part, and other geometric information, and the corresponding geometric feature information on the actual printing product is also extracted from the actual feature information. Then, a special geometric feature comparison algorithm (such as a shape matching algorithm, a spatial position relationship comparison algorithm, etc.) is used to align and compare the geometric features of the template and the actual geometric features one by one. For example, compare two triangular patterns to see if their side length ratios and angle sizes are similar. Finally, according to the calculation logic of the algorithm, a score representing the similarity of the geometric features of the two is obtained, which can intuitively reflect the degree of fit of the actual printing product in terms of geometric features with the standard template, providing part of the basis for subsequent comprehensive judgment of the accuracy of the printing product content.

[0058] S1082, calculating the similarity score of the visual features in the template feature information and the actual feature information;

[0059] Specifically, first, the visual feature related content such as the color coding of the text, the texture pattern of the graph, etc. is extracted from the template feature information, and the visual feature of the actual printed product is also obtained from the actual feature information, such as the color value of the actual text, the actual texture details of the graph, etc. Then, a special visual feature comparison algorithm (such as a color similarity algorithm based on color space distance calculation, a texture feature matching algorithm, an image clarity evaluation algorithm, etc.) is used to compare the visual features of the template and the actual visual features in detail. For example, compare the color of the text to see if the distance in the color space is close (the smaller the distance, the more similar the color); compare the texture of the graph to see if the pattern, density, etc. are consistent, etc. Finally, according to the calculation logic of the algorithm, a score reflecting the similarity of the visual features of the two is obtained, which can intuitively reflect the closeness of the actual printed product in visual presentation to the standard template, and provide another dimension basis for subsequent comprehensive judgment.

[0060] S1083, the geometric feature similarity score and the visual feature similarity score are weighted and synthesized to obtain a consistency score.

[0061] It can be seen that the similarity score of the geometric features in the template feature information and the actual feature information measures the similarity of the two from the geometric angle, and can accurately capture the consistency of the shape, structure, etc. The similarity score of the visual features in the template feature information and the actual feature information judges the similarity from the visual presentation level, such as color, texture, etc. Two dimensions are evaluated respectively.

[0062] In actual use, due to the combined influence of human operation errors and material process characteristics and other factors, the actual weight of the input packaging bag and the printed product often deviates from the preset weight. This deviation interferes with the accuracy of related sub-packaging operations such as quantity review based on weight information.

[0063] Please refer to Figure 2 , Figure 2 is another flowchart of the product sub-packaging method in the embodiments of the present application;

[0064] After step S105, it further includes:

[0065] S201, after the quantity review is successful, the historical packaging bag of the same kind as the current packaging bag is determined according to the subject information of the printed product.

[0066] In some embodiments, the printing product subject information of the current packaging bag is input as a retrieval condition in the system to initiate a query instruction; the system automatically filters all historical packaging bag records conforming to the subject information from the stored past dispensing data, which contain detailed information of the packaging bag such as number, weight, quantity, etc.; the system generates a historical packaging bag list according to the filtered records, and can be associated with the warehouse management system to locate the specific storage location of the historical packaging bag in the warehouse, facilitating subsequent acquisition of its weight information, etc.

[0067] S202, acquire historical weight information of the historical packaging bag;

[0068] S203, calculate the calculated product weight of the printing product according to the weight difference value and the quantity difference value; the quantity difference value is the difference between the required printing product quantity of the current packaging bag and the required printing product quantity of the historical packaging bag; the weight difference value is the difference between the weight information of the current packaging bag and the historical weight information;

[0069] Specifically, first, according to the weight information of the current packaging bag and the historical packaging bag, the weight of the current packaging bag is subtracted from the weight of the historical packaging bag to calculate the weight difference value; then, according to the required printing product quantity of the two, the required quantity of the current packaging bag is subtracted from the required quantity of the historical packaging bag to obtain the quantity difference value. Then, the weight difference value is divided by the quantity difference value.

[0070] S204, update the unit weight of the printing product with the average value of all calculated product weights; the updated unit weight of the printing product is used for quantity review of the next packaging bag.

[0071] Specifically, first, all the calculated product weights obtained through step S203 are collected, and then the average value of all the calculated product weights is calculated by using the average value method. Next, this average value is used as the new unit weight of the printing product to replace the original unit weight value, and the updated unit weight of the printing product can more accurately reflect the actual situation. After that, when performing quantity review and other related dispensing operations on the next packaging bag, the calculation and judgment will be based on this updated and more accurate unit weight, thereby improving the accuracy of the dispensing operation based on weight judgment and reducing dispensing errors caused by weight deviation.

[0072] It can be seen that after the quantity review is successful, the historical packaging bag of the same kind of the current packaging bag is determined according to the subject information of the printed product, and the same kind of packaging bag is screened out with the help of the subject information, so as to facilitate subsequent comparison and analysis. The historical weight information of the historical packaging bag is obtained, the quantity difference is the difference between the required printed product quantity of the current packaging bag and the required printed product quantity of the historical packaging bag; the weight difference is the difference between the weight information of the current packaging bag and the difference between the historical weight information, and the two sets of differences are used to accurately quantify the difference. Then, according to the weight difference and the quantity difference, the calculated product weight of the printed product is calculated, and a more accurate product weight is obtained based on rigorous calculation. The average value of all the calculated product weights is updated to the unit weight of the printed product; the updated unit weight of the printed product is used for quantity review of the next packaging bag. Through updating the unit weight, the subsequent packaging bag can be based on a more accurate weight standard when performing quantity review, and gradually correct the weight deviation caused by human factors, material process and other factors, so that the quantity review is more accurate, and the reliability of the weight judgment based on the quantity review is improved.

[0073] After step S203, it further includes:

[0074] S205, the historical weight information and the corresponding calculated product weight are substituted into a linear relationship model, the slope of the linear relationship model is the calculated product weight, and the intercept of the linear relationship model is used as the calculated packaging bag weight;

[0075] Specifically, the historical weight information of each historical packaging bag collected and sorted is extracted in turn, and the corresponding calculated product weight value calculated before is correspondingly good. Then, these data are substituted into the set linear relationship model, that is, the calculated product weight is used as the slope of the model, according to the principle of linear relationship and the corresponding mathematical calculation method (such as the straight line equation can be determined by a point and a slope on the straight line, and then the intercept is solved by the historical weight information point), the intercept is calculated, and the value of the intercept is the calculated packaging bag weight. Thus, the linear relationship model can be used to deeply mine the related information of the packaging bag weight, and provide a basis for further optimizing the weight judgment of the current packaging bag.

[0076] S206, the average value of all the calculated packaging bag weights is updated to the weight information of the current packaging bag; the updated weight information of the current packaging bag is used for quantity review of the next packaging bag.

[0077] Specifically, all the calculated packaging bag weight values obtained through step S205 are collected, and then an average value of all the calculated packaging bag weights is obtained by using an average value calculation method, such as a calculator or a special data processing software. Then, the average value is used as the new weight information of the current packaging bag to replace the original recorded weight information of the current packaging bag, and the updated weight information of the current packaging bag can more accurately reflect the actual weight. Subsequently, when the next packaging bag is subjected to quantity review and other related sub-packaging operations, the calculation and judgment are based on the updated and more accurate weight information of the current packaging bag, thereby further improving the accuracy of the weight-based sub-packaging operation and reducing the sub-packaging errors caused by the weight deviation of the packaging bag.

[0078] It can be seen that the historical weight information and the corresponding calculated product weight are introduced into the linear relationship model, the slope of the linear relationship model is the calculated product weight, and the intercept of the linear relationship model is the calculated packaging bag weight. The linear relationship model is used to deeply integrate and analyze the historical data and the current calculation results, and the reasonable value of the packaging bag weight is mined. Then, the average value of all the calculated packaging bag weights is used to update the weight information of the current packaging bag. The updated weight information of the current packaging bag is used for quantity review of the next packaging bag. By updating the weight information of the current packaging bag, the next round of quantity review work has a more accurate weight reference, effectively compensates for the deviation between the actual weight and the preset weight, and continuously optimizes the weight-based sub-packaging operation.

[0079] In actual use, especially in scenarios involving a large number of test paper bags, the feature comparison link is time-consuming and inefficient due to the large amount of data to be compared. This not only slows down the overall progress of the sub-packaging work, but also may affect the timely and accurate distribution of subsequent teaching materials and other printed products to the corresponding classes.

[0080] Please refer to Figure 3 , Figure 3 is a specific flowchart of steps S106 to S108 in the embodiment of the present application;

[0081] S106 to S108 specifically include:

[0082] S301, extracting the pre-stored electronic template of the printed product according to the subject information of the printed product;

[0083] S302, extracting the first feature information of the cover in the electronic template of the printed product; and recording the first position information of the first feature information;

[0084] Specifically, the extracted electronic template of the printed product is opened by using a special image recognition software or a document editing tool, and then the cover part of the template is focused on. By using the feature extraction function of the software, the first feature information such as the font format (Songti, bold, etc.), the font size (such as two font sizes), the color (such as red), and the shape, size, and coordinate position in the page of the specific pattern (such as the school logo) of the cover title is recognized and extracted. At the same time, by using the positioning function of the software, the specific first position information of the first feature information on the cover page is accurately recorded. The feature information and the corresponding position information are sorted out to provide clear reference content for subsequent feature comparison with the actual printed product image.

[0085] It should be noted that the cover, as the primary display surface of the printed product presented to the user, often contains many key elements with high recognition and representativeness.

[0086] S303, randomly extracting a plurality of second feature information in the electronic template of the printed product based on a preset area size, and recording a plurality of corresponding second position information;

[0087] Specifically, first, the area size is determined according to the pre-set area size, such as determining a rectangular preset area. Then, in the electronic template of the printed product, a plurality of such areas are randomly determined at different positions of the template by using the random selection function (which can be based on a random number generation algorithm to determine the starting coordinates of the selection) of the software. For each selected area, the image recognition and text analysis functions are used to extract the second feature information such as the special layout of the text and the local details of the chart. At the same time, the positioning function of the software is used to accurately record the corresponding second position information of each second feature information in the template. The second feature information and the corresponding position information are sorted out one by one to further enrich the feature information content used for comparison, and to more comprehensively check the content accuracy of the printed product.

[0088] S304, obtaining an image of the printed product according to a preset sampling ratio;

[0089] S305, obtaining third feature information of the image of the printed product according to the first position information;

[0090] Specifically, first, the first position information recorded in step S302 is called from the previously sorted electronic template related information, and then the image content at the corresponding position is found on the image of the printed product by using the positioning and recognition functions of the image processing software with the position information as a guide, and the third feature information such as the actual font, font size, color of the text, and the actual shape, size, etc. of the pattern are extracted, and the third feature information is sorted out, so as to compare with the first feature information in the electronic template in the next step, and check whether the actual printed product meets the requirements of the standard template in terms of cover key features.

[0091] S306, judge whether the first feature information is consistent with the third feature information;

[0092] Specifically, the first feature information and the third feature information sorted out previously are extracted, and then each corresponding feature item is compared, such as comparing the font of the title to see if they are both Songti; comparing the font size to see if they are both No. 2; and then comparing the color to see if they are all red, etc. In this way, the features of text, patterns, etc. are compared one by one in detail. According to the actual situation, a certain error allowance range can be set, for example, a small color difference is allowed in color, and if all the features are consistent within the allowed range, it is determined that the first feature information is consistent with the third feature information; if one or more features are inconsistent beyond the allowed range, it is determined that the two are inconsistent, so as to preliminarily judge whether the actual printed product meets the requirements of the standard template in the cover part, and provide a basis for further feature comparison.

[0093] If not consistent, the content review fails.

[0094] If consistent, S307, randomly select a second position information that has not been used, and obtain the fourth feature information of the image of the printed product;

[0095] Specifically, after it is determined that the first feature information is consistent with the third feature information, further comparison of other features is needed to ensure the accuracy of the content of the printed product. At this time, by checking all the second position information recorded previously, the second position information that has not been used is selected, and then one of the second position information that has not been used is selected by using a random selection method (which can be assisted by a random number generator tool), and then the corresponding position on the image of the printed product is found by using the image processing software with the position information as a guide, and the fourth feature information such as text layout details and chart specific styles is extracted from the position, and the fourth feature information is extracted, so as to prepare for the comparison with the second feature information in the electronic template in the next step, so as to gradually expand the comparison range and more comprehensively check whether the content of the printed product meets the standard requirements.

[0096] S308, judge whether the second feature information is consistent with the fourth feature information or not;

[0097] Specifically, the second feature information and the fourth feature information previously extracted and arranged are extracted first, and then each corresponding feature item is compared, such as whether the word spacing and line spacing are consistent for the text layout feature, and whether the line thickness and color filling are consistent for the chart feature, and so on. According to such an order, different types of features are compared one by one in detail. A certain error allowance range can also be set according to actual conditions, for example, the line thickness is allowed to have a slight difference, and so on. If all the features are consistent within the allowed range, it is determined that the second feature information is consistent with the fourth feature information. If one or more features are inconsistent beyond the allowed range, it is determined that the two are inconsistent. In this way, it is further judged whether the actual printed product meets the requirements of the standard template in other areas except the cover, thereby providing a basis for subsequent operations such as whether to continue in-depth comparison.

[0098] If consistent, return to step S108.

[0099] If inconsistent, the content review fails.

[0100] It can be seen that according to the subject information of the printed product, the pre-stored electronic template of the printed product is extracted, the template feature information of the printed product is obtained, the representative feature information is extracted from the electronic template first; the first position information of the first feature information is recorded; a plurality of second feature information is randomly extracted in the electronic template of the printed product based on the preset area size, and a plurality of corresponding second position information is recorded, so as to accurately locate the key features and positions and reduce the comparison range. The image of the printed product is obtained according to the preset sampling ratio; the third feature information of the image of the printed product is obtained according to the first position information, the image features are compared according to the corresponding positions, and if consistent, a second position information not used is randomly selected to obtain the fourth feature information of the image of the printed product. Whether the second feature information is consistent with the second feature information is judged; if consistent, return to the step of randomly selecting a second position information not used to obtain the fourth feature information of the image of the printed product. In this way, the verification and cyclic judgment are gradually carried out, avoiding indiscriminate comparison of all image data, reducing the amount of feature comparison, speeding up the comparison, making the content review link efficient, ensuring that the packaging work can be promoted on time, and ensuring that the teaching materials are accurately distributed to the classes in time.

[0101] In actual use, if the total floating weight is simply accumulated to determine the theoretical weight range, it is easy to result in a too wide theoretical weight range, and thus the actual printed product quantity error is incorrectly determined as correct. This situation will undoubtedly seriously affect the accuracy of the quantity of the packaged product.

[0102] Please refer to Figure 4 , Figure 4 is another flowchart of the product packaging method in batches printing in the embodiments of the present application;

[0103] Before step S104, further comprising:

[0104] S401, determining a target interval in a preset floating table according to the required number of printed products; the preset floating table includes a plurality of intervals ranging from small to large, and the threshold values corresponding to the intervals range from large to small;

[0105] Among them, the preset floating table is a data table prepared in advance, which contains a plurality of intervals arranged in order from small to large. Each interval corresponds to a specific threshold value, and these threshold values show a rule from large to small, like a standard reference table divided into different levels, which is used to accurately locate the appropriate range interval according to different product quantity conditions.

[0106] Specifically, the current required number of printed products is input in the system interface, and a query instruction is initiated; secondly, the system automatically searches in the stored floating table data, quickly locates the corresponding target interval through algorithm comparison (such as judging whether the number is within the range of each interval), and then feeds back the detailed information of the target interval (including the range of the interval, the corresponding threshold value, etc.) in the form of data to the operation interface, and stores the target interval information in the related parameter configuration of the current packaging task, which is convenient for subsequent process calling.

[0107] S402, adjusting the floating weight according to the threshold value corresponding to the target interval;

[0108] Specifically, first find the threshold value corresponding to the target interval determined in step S401 from the preset floating table, and then adjust the originally initially set or default floating weight according to this threshold value, such as directly using the threshold value as the new floating weight, or adjusting the threshold value and the original floating weight in a certain proportion, etc., to obtain the adjusted floating weight value.

[0109] S403, obtaining the cumulative weight deviation, which is the sum of the differences between the theoretical total weight of different packaging bags and the weight information;

[0110] Specifically, first, the relevant weight data of each packaging bag that has completed the sub-packaging is collected, that is, the theoretical total weight of each packaging bag (which can be found from the previous calculation record) and the actually measured weight information (which can be obtained by checking the weighing record or re-weighing) are obtained. Then, for each packaging bag, the difference between the theoretical total weight and the weight information is calculated. Then, the sum of the differences of all the packaging bags is calculated by adding up the differences, and the final cumulative weight deviation value is obtained by calculating by a calculator or a special data processing software. This value can provide key data support for subsequent judgment of whether the theoretical weight range is reasonable and how to adjust.

[0111] S404, adjusting the theoretical weight range according to the cumulative weight deviation.

[0112] In some embodiments, a fixed positive deviation adjustment value is set, and when the cumulative weight deviation is positive, the upper limit of the theoretical weight range is increased by the fixed value each time. That is, whenever there is a cumulative weight deviation, no matter how large the deviation value is, as long as it is positive, the upper limit of the theoretical weight range is increased by a preset value.

[0113] Similarly, a fixed negative deviation adjustment value is set, and when the cumulative weight deviation is negative, the lower limit of the theoretical weight range is decreased by the fixed value each time. That is, as long as there is a negative cumulative weight deviation, the lower limit of the theoretical weight range is decreased by a preset value.

[0114] In other embodiments, the ratio of the cumulative weight deviation to the current theoretical total weight is calculated, and then this ratio coefficient is multiplied by the initial upper limit and lower limit of the theoretical weight range respectively to obtain the adjustment amount of the upper limit and lower limit, and the upper limit and lower limit of the theoretical weight range are adjusted.

[0115] It can be seen that the target interval in the preset floating table is determined according to the required number of printed products; the preset floating table includes a plurality of intervals with increasing ranges, and the threshold values corresponding to the intervals decrease from large to small; the floating weight is adjusted according to the threshold value corresponding to the target interval, and the floating weight is adjusted according to the number to accurately locate the appropriate interval in the preset floating table, so that the determination of the floating weight is more scientific and reasonable, and the randomness is avoided. After determining the theoretical weight range based on the floating weight and the theoretical total weight, the cumulative weight deviation is obtained, which is the sum of the differences between the theoretical total weight and the weight information of different packaging bags; the theoretical weight range is adjusted according to the cumulative weight deviation, the theoretical weight range is adjusted by using the cumulative deviation feedback, and the two-way optimization makes the theoretical weight range more suitable for the actual situation, effectively preventing the problem of number misjudgment caused by simply adding the floating weight to make the range too large.

[0116] The following describes an example product sub-packaging system 500 for batch printing provided by an embodiment of the present application. Figure 5Fig. 1 is a schematic diagram of an exemplary hardware structure of a batch-printed product dispensing system 500 provided by embodiments of the present application.

[0117] In some embodiments, the batch-printed product dispensing system 500 is a computer device or includes a computer device in the batch-printed product dispensing system 500. The computer device includes a processor, a memory, and a network interface connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store data. The network interface of the computer device is configured to communicate with other terminals or servers outside through a network connection. In some embodiments, the network interface can be a wired network interface, and in some embodiments, the network interface can also be a wireless network interface. The computer program is executed by the processor to implement the method in the embodiments of the present application.

[0118] Those skilled in the art can understand that Figure 5 The structure shown in FIG. 1 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0119] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit the present application; even though the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0120] In the above-described embodiments, according to the context, the term when can be interpreted as meaning if or after or in response to determining or in response to detecting. Similarly, according to the context, the phrase when determining or if detecting (a stated condition or event) can be interpreted as meaning if determining or in response to determining or when detecting or in response to detecting (a stated condition or event).

[0121] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk) and the like.

[0122] Those of ordinary skill in the art understand that all or part of the processes in the above embodiments can be implemented by a computer program to instruct the relevant hardware, which can be stored in a computer readable storage medium. The program can include the processes of the above method embodiments when executed. The aforementioned storage medium includes ROM or random access memory (RAM), magnetic disk or optical disk, and various media that can store program codes.

Claims

1. A method of dispensing a batch-printed product, characterized by, The method comprises the following steps: acquiring label information of a current packaging bag; the label information comprises a school, a class, a required number of printed products, and subject information of the printed products; delivering corresponding printed products to the current packaging bag according to the label information; after the delivery is completed, calculating a theoretical total weight of the printed products in the current packaging bag according to a unit weight of the printed products and a unit weight of the current packaging bag; determining a floating weight according to the required number of printed products, and determining a theoretical weight range based on the floating weight and the theoretical total weight; acquiring weight information of the current packaging bag, and performing quantity review according to whether the weight information is located in the theoretical weight range; after the quantity review is successful, determining historical packaging bags of the same kind of the current packaging bag according to the subject information of the printed products; acquiring historical weight information of the historical packaging bags; calculating a calculated product weight of the printed products according to a weight difference value and a quantity difference value; the quantity difference value is a difference between the required number of printed products of the current packaging bag and the required number of printed products of the historical packaging bags; the weight difference value is a difference between the weight information of the current packaging bag and the historical weight information; updating an average value of all the calculated product weights to the unit weight of the printed products; the updated unit weight of the printed products is used for quantity review of a next packaging bag; according to the subject information of the printed products, extracting a pre-stored electronic template of the printed products, and acquiring template feature information of the printed products; acquiring images of the printed products according to a preset sampling ratio; and acquiring actual feature information of the images of the printed products; calculating a consistency score of the template feature information and the actual feature information; and performing content review according to whether the consistency score is higher than a preset score threshold.

2. The method of claim 1, wherein, After the step of calculating the calculated product weight of the printed products according to the weight difference value and the quantity difference value, the method further comprises the following steps: substituting the historical weight information and the corresponding calculated product weight into a linear relationship model; a slope of the linear relationship model is the calculated product weight, and an intercept of the linear relationship model is used as a calculated packaging bag weight; updating an average value of all the calculated packaging bag weights to the weight information of the current packaging bag; and the updated weight information of the current packaging bag is used for quantity review of a next packaging bag.

3. The method of claim 1, wherein, According to the subject information of the printed products, extracting a pre-stored electronic template of the printed products, and acquiring template feature information of the printed products; acquiring images of the printed products according to a preset sampling ratio; and acquiring actual feature information of the images of the printed products; calculating a consistency score of the template feature information and the actual feature information; The step of performing content review according to whether the consistency score is higher than a preset score threshold specifically comprises the following steps: extracting the pre-stored electronic template of the printed products according to the subject information of the printed products; extracting first feature information of a cover in the electronic template of the printed products; and recording first position information of the first feature information; extracting a plurality of second feature information randomly in the electronic template of the printed product based on a preset area size, and recording a plurality of corresponding second position information; acquiring an image of the printed product according to a preset sampling ratio; acquiring third feature information of the image of the printed product according to the first position information; judging whether the first feature information is consistent with the third feature information; if consistent, randomly selecting one unused second position information to acquire fourth feature information of the image of the printed product; judging whether the second feature information is consistent with the fourth feature information; if consistent, returning to the step of randomly selecting one unused second position information to acquire fourth feature information of the image of the printed product.

4. The method of claim 1, wherein, Before the step of determining the theoretical weight range based on the floating weight and the theoretical total weight, the method further comprises: determining a target interval in a preset floating table according to the required number of printed products; the preset floating table comprises a plurality of intervals with ranges from small to large, and the threshold values corresponding to the intervals are from large to small; adjusting the floating weight according to the threshold value corresponding to the target interval; After the step of determining the theoretical weight range based on the floating weight and the theoretical total weight, the method further comprises: acquiring a cumulative weight deviation, which is the sum of the differences between the theoretical total weight and the weight information of different packaging bags; adjusting the theoretical weight range according to the cumulative weight deviation.

5. The method of claim 1, wherein, The step of calculating the consistency score of the template feature information and the actual feature information specifically comprises: calculating a similarity score of geometric features in the template feature information and the actual feature information; calculating a similarity score of visual features in the template feature information and the actual feature information; weighting and synthesizing the geometric feature similarity score and the visual feature similarity score to obtain the consistency score.

6. A batch printed product dispensing system, comprising: The batch-printed product packaging system comprises one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code comprising computer instructions, and the one or more processors invoke the computer instructions to enable the batch-printed product packaging system to perform the method of any one of claims 1-5.

7. A computer program product comprising instructions, characterized in that, When the computer program product is run on the batch-printed product packaging system, the computer program product enables the batch-printed product packaging system to perform the method of any one of claims 1-5.

8. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are run on the batch-printed product packaging system, the instructions enable the batch-printed product packaging system to perform the method of any one of claims 1-5.

Images