Methods, devices, electronic devices, and storage media for identifying and adding adhesive to tobacco packaging.

By automatically identifying and matching the codes on glue buckets using image recognition technology, the problem of low glue addition accuracy in tobacco packaging has been solved, achieving accuracy in glue addition and traceability of the production process.

CN123071990APending Publication Date: 2026-11-10CHINA TOBACCO ZHEJIANG IND CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611312529.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-27
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

In the existing technology, the accuracy of glue addition during the tobacco rolling process is low, mainly relying on manual operation, which leads to errors in glue application and makes it difficult to distinguish between different types of glue.

Method used

Image recognition technology is used to obtain the code image on the glue bucket. The image recognition algorithm is used to extract the glue code information and match it with the preset standard glue information. The glue container is then controlled to accurately add glue and the operation process information is recorded.

Benefits of technology

It improves the accuracy of glue addition, avoids errors caused by human factors, and ensures the quality stability and production efficiency of the tobacco rolling process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123071990A_ABST
    Figure CN123071990A_ABST
Patent Text Reader

Abstract

This application relates to a method, apparatus, electronic device, and storage medium for identifying and adding adhesive to tobacco packaging. The method includes: acquiring image information of an adhesive code on an adhesive container; identifying the image information using an image recognition algorithm to obtain the adhesive code information; matching the adhesive code information with preset standard adhesive information, and determining whether the adhesive code information and the standard adhesive information are consistent based on the matching result; if the matching result is consistent, opening the adhesive container to perform adhesive addition; and recording the adhesive addition process information. By acquiring the code image on the adhesive container and automatically identifying and comparing it, and controlling the opening and closing of the adhesive container based on the comparison result, accurate adhesive addition is achieved, improving the accuracy of adhesive addition during the tobacco packaging process.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tobacco roll wrapping glue image recognition, in particular to a tobacco roll wrapping glue recognition and adding method and device, an electronic device and a storage medium. BACKGROUND

[0002] In the tobacco industry, glue is a key auxiliary material in the process of cigarette rolling, filter tipping and packaging forming. The correct addition of glue can directly affect the quality stability and production efficiency of the cigarette product.

[0003] However, the current glue adding process still mainly relies on manual operation. The operator manually selects a glue bucket for addition according to a production task list or experience. Since different brands and specifications of cigarette products correspond to different types of glue, and the appearance of the glue bucket is similar, only the text or code on the barrel body is used for identification. In actual production, human negligence may lead to incorrect glue selection, resulting in low accuracy of glue addition in the tobacco rolling process.

[0004] To address the problem of low accuracy of glue addition in the related art, there is currently no effective solution. SUMMARY

[0005] A tobacco roll wrapping glue recognition and adding method, device, electronic device and storage medium are provided in the present embodiment to solve the problem of low accuracy of glue addition in the related art.

[0006] In a first aspect, a tobacco roll wrapping glue recognition and adding method is provided in the present embodiment, comprising:

[0007] Obtaining image information of a glue code on a glue bucket;

[0008] Identifying the image information by an image recognition algorithm to obtain glue code information;

[0009] Matching the glue code information with preset standard glue information, and determining whether the glue code information is consistent with the standard glue information according to a matching result;

[0010] If the matching result is determined to be consistent, opening a switch of a glue container to perform glue addition;

[0011] Recording operation process information of the glue addition.

[0012] In some embodiments, the obtaining of the image information of the glue code on the glue bucket comprises:

[0013] Obtaining original image information of the glue code on the glue bucket;

[0014] The original image information is subjected to denoising and contrast enhancement preprocessing to obtain the enhanced image information.

[0015] In some embodiments, the step of identifying the image information using an image recognition algorithm to obtain glue code information includes:

[0016] The edge contours of the glue code in the image information are extracted using an edge detection algorithm;

[0017] Based on the edge contour, the characters of the glue code are separated using character segmentation technology;

[0018] The image features of each separated character are extracted to obtain the glue code information.

[0019] In some embodiments, matching the glue code information with preset standard glue information and determining whether the glue code information and the standard glue information are consistent based on the matching result includes:

[0020] The image features are used as the feature vector to be identified;

[0021] Calculate the cosine similarity between the feature vector to be identified and the standard feature vectors of each glue in the preset standard glue information;

[0022] When the cosine similarity is greater than or equal to a preset similarity threshold, the glue code information is determined to be consistent with the standard glue information; otherwise, the glue code information is determined to be inconsistent with the standard glue information.

[0023] In some embodiments, the method for identifying and adding adhesive to tobacco rolls further includes:

[0024] When the matching result determines that the glue code information is inconsistent with the standard glue information, a closing command is sent to the electronically controlled valve to close the switch of the glue container and trigger the alarm device to issue a warning message.

[0025] In some embodiments, recording the process information of adding the adhesive includes:

[0026] Record the glue code information of the glue bucket corresponding to the glue addition operation, the timestamp of the glue addition operation, and the cumulative number of glue additions within a preset statistical period.

[0027] In some embodiments, the method for identifying and adding adhesive to tobacco rolls further includes:

[0028] Based on the preset analysis cycle, the recorded glue addition process information is analyzed to obtain the actual addition time interval and / or actual addition frequency.

[0029] When the actual addition time interval exceeds the preset normal time interval threshold range, and / or the actual addition frequency exceeds the preset normal frequency threshold range, it is determined that there is an abnormality in the glue addition process, and an early warning notification is output.

[0030] Secondly, this embodiment provides a tobacco roll adhesive identification and addition device, including: an information acquisition module, an information comparison module, and an information recording module; wherein:

[0031] The information acquisition module is used to acquire image information of the glue code on the glue bucket; and to identify the image information using an image recognition algorithm to obtain the glue code information.

[0032] The information comparison module is used to match the glue code information with preset standard glue information, and determine whether the glue code information and the standard glue information are consistent based on the matching result; if the matching result is consistent, the glue container is turned on to add glue.

[0033] The information recording module is used to record information about the process of adding the adhesive.

[0034] Thirdly, this embodiment provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the tobacco roll adhesive identification and addition method described in the first aspect.

[0035] Fourthly, this embodiment provides a storage medium storing a computer program that, when executed by a processor, implements the steps of the tobacco roll adhesive identification and addition method described in the first aspect.

[0036] Compared with related technologies, the method, apparatus, electronic device, and storage medium for identifying and adding adhesive in tobacco packaging provided in this embodiment are as follows: First, the method acquires image information of the adhesive code on the adhesive container; second, it identifies the image information using an image recognition algorithm to obtain the adhesive code information; next, it matches the adhesive code information with preset standard adhesive information and determines whether the adhesive code information and standard adhesive information are consistent based on the matching result; further, if the matching result is consistent, it opens the adhesive container to perform adhesive addition; finally, it records the information of the adhesive addition process. By acquiring the code image on the adhesive container and performing automatic identification and comparison, and controlling the opening and closing of the adhesive container based on the comparison result, accurate adhesive addition is achieved, improving the accuracy of adhesive addition during the tobacco packaging process.

[0037] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0038] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0039] Figure 1 This is a hardware structure block diagram of a terminal for a tobacco roll adhesive identification and addition method according to an embodiment of this application;

[0040] Figure 2 This is a flowchart of a method for identifying and adding adhesive to tobacco rolls according to an embodiment of this application;

[0041] Figure 3 This is a flowchart of a method for identifying and adding adhesive to tobacco rolls according to another embodiment of this application;

[0042] Figure 4 This is a structural block diagram of a tobacco roll adhesive identification and addition device according to an embodiment of this application. Detailed Implementation

[0043] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0044] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these” used in this application do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to these processes, methods, products, or devices. Words such as “connected,” “linked,” and “coupled” used in this application are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. Normally, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," "third," etc., used in this application are merely to distinguish similar objects and do not represent a specific order of objects.

[0045] The method embodiments provided in this example can be executed on a terminal, computer, or similar electronic device with a certain computing power. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of a terminal for a tobacco roll adhesive identification and addition method according to an embodiment of this application. Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0046] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the tobacco roll adhesive identification and addition method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0047] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0048] This embodiment provides a method for identifying and adding adhesive to tobacco rolls. Figure 2 This is a flowchart of a method for identifying and adding adhesive to tobacco rolls according to an embodiment of this application, as follows: Figure 2 As shown, the process includes the following steps:

[0049] Step S210: Obtain image information of the glue code on the glue bucket.

[0050] Before the glue addition process begins, an industrial camera or high-definition camera positioned on the side or top of the glue container can capture images of the glue code affixed to the glue bucket. This glue code can be a barcode or a character code, containing data uniquely identifying the glue type, model, batch, or formulation information. During image acquisition, the glue bucket is placed within the field of view of the industrial camera or high-definition camera, or a conveyor transports the glue bucket to the image acquisition station. The system automatically focuses and captures an image of the area containing the code on the glue bucket according to preset acquisition parameters, obtaining raw image data containing the glue code.

[0051] Step S220: Image information is identified using an image recognition algorithm to obtain glue code information.

[0052] After receiving the raw image data containing the glue code, preprocessing can be performed to improve image quality and highlight code features. After preprocessing, since the glue code is a character code type, edge detection algorithms can be used to detect edges in the enhanced image, extracting the edge contours of each character in the glue code. Based on the extracted edge contours, character segmentation techniques are used to separate the characters of the glue code, allowing each character to be output independently. For each separated character, its shape features and stroke features are extracted. The extracted shape features and stroke features are combined to form a feature vector to be recognized. This feature vector is the glue code information identified from the image information.

[0053] Step S230: Match the glue code information with the preset standard glue information, and determine whether the glue code information and the standard glue information are consistent based on the matching result.

[0054] Specifically, the pre-defined standard adhesive information is stored in a standard code feature library. This library contains pre-collected standard code data corresponding to each model and batch of qualified adhesives, with each standard code data stored as a standard feature vector. During matching, the feature vector to be identified, extracted from the image information, is compared one by one with each standard feature vector in the standard code feature library, and the similarity between the feature vector to be identified and each standard feature vector is calculated. For example, the similarity calculation can use a cosine similarity algorithm, which measures the degree of similarity between the feature vector to be identified and the standard feature vectors by calculating the cosine of the angle between them in high-dimensional space.

[0055] Step S240: If the matching result is determined to be consistent, turn on the glue container to add glue.

[0056] After calculating the similarity between the feature vector to be identified and each standard feature vector, the maximum similarity value is taken as the matching result, and this maximum similarity value is compared with a preset similarity threshold. If the maximum similarity value is greater than or equal to the preset threshold, the matching result between the current glue code information and the standard glue information is determined to be consistent. When the matching result is consistent, an allow-to-add command is sent to the intelligent glue container control center. After receiving the allow-to-add command, the intelligent glue container control center sends an opening command to the electronically controlled valve of the glue container. The electronically controlled valve executes the opening action according to the received opening command, allowing the glue in the glue container to be transported through the pipeline to the glue application device of the tobacco packaging equipment, thereby performing the glue addition operation.

[0057] Step S250: Record the information on the process of adding glue.

[0058] Each time glue is added, the system automatically records the following information: the glue code of the glue container used, the timestamp of the addition, the cumulative frequency of additions within a preset statistical period, operator information, and the matching result. This information is stored in a relational database as a structured table for easy data retrieval, statistics, and management.

[0059] Compared to other technologies, the addition of glue in tobacco packaging still relies heavily on manual operation. Operators manually identify and select the glue containers to be added from the glue storage area based on production orders or past experience. However, different brands and specifications of cigarette products correspond to different glue formulations, and the glue containers have very similar appearances. Operators can only distinguish them by the text labels or codes on the surface of the containers. In actual production, human factors such as visual fatigue, worn labels, or misjudgment due to experience can easily lead to low accuracy in glue addition during the tobacco packaging process.

[0060] Steps S210 to S250 involve: first, acquiring the image information of the glue code on the glue container; second, recognizing the image information using an image recognition algorithm to obtain the glue code information; next, matching the glue code information with preset standard glue information, and determining whether the glue code information and standard glue information are consistent based on the matching result; further, if the matching result is consistent, opening the glue container to add glue; and finally, recording the glue adding process. By acquiring the code image on the glue container and automatically recognizing and comparing it, and controlling the opening and closing of the glue container based on the comparison result, errors in glue dispensing caused by human factors such as visual fatigue, label wear, or experience-based misjudgment due to manual judgment are prevented. This solves the problem of difficulty in distinguishing different types of glue due to their similar appearance, thereby improving the accuracy of glue dispensing.

[0061] Optionally, in one embodiment, obtaining image information of the glue code on the glue bucket includes: obtaining the original image information of the glue code on the glue bucket; performing image preprocessing operations such as denoising and contrast enhancement on the original image information to obtain enhanced image information.

[0062] After obtaining the original image information containing the glue code, image preprocessing is performed on the received original image information. Specifically, the original image information can be denoised using a mean filtering algorithm to remove noise interference introduced during image acquisition and transmission. Furthermore, the denoised image can be contrast-enhanced using a histogram equalization algorithm, stretching the image's grayscale distribution range to make the grayscale difference between the glue code area and the background area more obvious, thereby highlighting the code features and obtaining the enhanced image information.

[0063] By denoising and contrast enhancement of the original images of the glue code, image noise was effectively eliminated and the grayscale difference between the code and the background was highlighted, thus improving image quality and providing a clear and reliable image data foundation for subsequent feature extraction and recognition. This improved the accuracy and stability of glue code recognition.

[0064] In addition, in one embodiment, the glue code information is obtained by recognizing the image information using an image recognition algorithm, including: extracting the edge contour of the glue code in the image information using an edge detection algorithm; separating the characters of the glue code based on the edge contour using character segmentation technology; and extracting the image features of each separated character to obtain the glue code information.

[0065] First, edge detection algorithms are used to detect edges in the enhanced image information. By calculating the gradient magnitude and direction of pixels in the image, the edge contour information of each character in the glue code is identified and extracted. Then, based on the projection distribution of the edge contours in the horizontal and vertical directions, the boundary position of each character is determined, and adjacent characters in the glue code are segmented one by one, allowing each character to be output independently. Finally, for each segmented independent character, shape features and stroke features are extracted. Shape features include geometric attributes such as the aspect ratio and duty cycle of the character, used to describe the overall shape and contour information of the character; stroke features include structural attributes such as the stroke width, stroke direction, and distribution of stroke intersections, used to describe the stroke composition and detailed features of the character. The extracted shape features and stroke features of each character are combined to form a feature vector to be identified, which is the glue code information identified from the image information.

[0066] By using edge detection, character segmentation, and character image feature extraction, the structured feature information of glue codes can be accurately extracted from the image of glue codes, providing reliable data support for subsequent code comparison and glue verification.

[0067] In one embodiment, matching the adhesive code information with preset standard adhesive information and determining whether the adhesive code information and the standard adhesive information are consistent based on the matching result includes:

[0068] The image features are used as the feature vector to be identified; the cosine similarity between the feature vector to be identified and the standard feature vector of each glue in the preset standard glue information is calculated; when the cosine similarity is greater than or equal to the preset similarity threshold, the glue code information is determined to be consistent with the standard glue information; otherwise, the glue code information is determined to be inconsistent with the standard glue information.

[0069] Specifically, the image features extracted from the glue code image are used as the feature vector to be identified. This feature vector is used to characterize the graphic structure information of the glue code on the glue container to be added. The feature vector to be identified is compared with the standard feature vectors of each glue in the preset standard glue information. The standard glue information is stored in a standard code feature library, which pre-includes the standard code data corresponding to each model and batch of qualified glue. Each standard code data is stored in the form of a standard feature vector. Subsequently, the similarity between the feature vector to be identified and each standard feature vector is calculated. The similarity calculation uses the cosine similarity algorithm, and the formula is:

[0070] ;

[0071] Where A and B are the feature vector of the code to be identified and the feature vector of the standard code, respectively, and n is the feature dimension. According to the cosine similarity algorithm formula, the similarity between the feature vector to be identified and the standard feature vector is measured by calculating the cosine value of the angle between them in high-dimensional space. The cosine similarity value ranges from 0 to 1, and the closer the value is to 1, the more similar the two vectors are.

[0072] When the cosine similarity between the feature vector to be identified and a standard feature vector is greater than or equal to a preset similarity threshold, the current glue code information is determined to be consistent with the standard glue information, indicating that the glue to be added is the correct glue, and subsequent glue addition operations are allowed. When the cosine similarity between the feature vector to be identified and the standard feature vector is less than the preset similarity threshold, the current glue code information is determined to be inconsistent with the standard glue information, indicating that the glue to be added does not match the standard glue, and there may be an error in glue selection. After the matching determination is completed, the determination result is sent to the intelligent glue container control module for subsequent glue addition control decisions.

[0073] By converting the image features of the glue code to be identified into feature vectors and comparing them with the pre-set standard feature vectors using cosine similarity, accurate matching and judgment of glue codes are achieved, effectively improving the reliability of glue recognition.

[0074] In one embodiment, the above-mentioned method for identifying and adding adhesive to tobacco rolls may further include: when the matching result determines that the adhesive code information is inconsistent with the standard adhesive information, sending a closing command to the electronically controlled valve to close the switch of the adhesive container and triggering an alarm device to issue a warning message.

[0075] When the matching result determines that the glue code information is inconsistent with the standard glue information, a shut-off command is sent to the electrically controlled valve of the glue container. The valve, upon receiving the command, remains closed or switches to the closed state, cutting off the glue delivery path. The current glue container no longer supplies glue to the glue application device of the tobacco packaging equipment, preventing incorrect glue from being added to the production process. Simultaneously, an audible and visual alarm is activated to alert on-site operators, and a message is displayed on the equipment's human-machine interface, clearly informing operators that the current glue container is incompatible with the production task. Furthermore, this abnormal event can be simultaneously transmitted and stored in a database for later querying and traceability.

[0076] By disabling the glue addition and alarm mechanism, incorrect addition can be promptly blocked and operators notified when glue codes are inconsistent. This effectively avoids product quality incidents caused by incorrect glue usage and ensures the correctness of glue addition and product quality stability during the tobacco packaging process.

[0077] In one embodiment, the process information of adding glue is recorded, including: recording the glue code information of the glue bucket corresponding to the glue adding operation, the timestamp of the glue adding operation, and the cumulative number of times the glue adding operation is performed within a preset statistical period.

[0078] During or after each glue addition operation, the glue code information of the glue container corresponding to this glue addition operation, the timestamp of this glue addition operation, and the cumulative number of glue additions within a preset statistical period are linked and recorded. The glue code information is the code data of the current glue container obtained through image recognition, used to identify the type, model, and batch source of the glue used in this addition. The timestamp is the specific date and time of this addition operation, automatically generated by the system clock. The cumulative number of additions is the cumulative number of times the glue container has successfully performed glue addition operations from the start time of the preset statistical period to the current time, reflecting the frequency of glue use and consumption rate. The above glue code information, timestamp of this glue addition operation, and cumulative number of additions within the preset statistical period are linked and stored in a database in the form of a structured data table, with each record corresponding to one complete glue addition operation event.

[0079] By recording glue code information, timestamps, and cumulative addition times, the system achieves digital storage of information for the entire process of each bucket of glue from identification to addition, providing a data foundation for subsequent glue usage traceability, production data statistical analysis, and abnormal behavior monitoring.

[0080] In addition, in one embodiment, the above-mentioned method for identifying and adding adhesive to tobacco rolls may further include: analyzing the recorded adhesive addition process information according to a preset analysis period to obtain the actual addition time interval and / or the actual addition frequency; when the actual addition time interval exceeds a preset normal time interval threshold range, and / or the actual addition frequency exceeds a preset normal frequency threshold range, determining that there is an abnormality in the adhesive addition process, and outputting a warning notification.

[0081] According to a preset analysis cycle (e.g., hourly, per shift, or daily), all glue addition records within that analysis cycle are read from the database. The difference between the timestamps of two adjacent addition operations is calculated to obtain the actual time interval between each addition. Simultaneously, the total number of glue addition operations within the analysis cycle is counted as the actual addition frequency. The calculated actual addition time interval is compared with a preset normal time interval threshold range, and the actual addition frequency is compared with a preset normal frequency threshold range. The normal time interval threshold range and normal frequency threshold range are preset based on the glue consumption pattern under normal production rhythm. When the actual addition time interval exceeds the preset normal time interval threshold range, and / or the actual addition frequency exceeds the preset normal frequency threshold range, an anomaly is determined in the current glue addition process, potentially indicating glue omissions, duplicate additions, or abnormal glue consumption. An automatic warning notification is then issued. For example, the warning notification sends SMS and / or email notifications to preset staff to remind relevant management personnel to promptly investigate the problem.

[0082] By periodically analyzing and identifying anomalies in the glue addition process, abnormal situations can be detected in a timely manner and proactive warnings can be issued, effectively improving the level of intelligence in production management and the efficiency of anomaly response.

[0083] Figure 3 This is a flowchart of a method for identifying and adding adhesive to tobacco rolls, according to another embodiment of this application. Figure 3 As shown, the method for identifying and adding adhesive to tobacco rolls includes the following steps:

[0084] Step S301: Collect the original image information of the glue code on the glue bucket;

[0085] Step S302: Denoise and contrast enhancement are performed on the original image information to obtain enhanced image information;

[0086] Step S303: Extract the edge contours of the glue code from the enhanced image information;

[0087] Step S304: Based on the edge contour, the characters of the glue code are separated using character segmentation technology;

[0088] Step S305: Extract the shape features and stroke features of each separated character and combine them to form the feature vector to be identified;

[0089] Step S306: Compare the feature vector to be identified with each standard feature vector in the preset standard glue information, and calculate the cosine similarity.

[0090] Step S307: Determine whether the cosine similarity is greater than or equal to the preset similarity threshold. If the cosine similarity is greater than or equal to the preset similarity threshold, it is determined to be consistent, and step S308 is executed. Otherwise, it is determined to be inconsistent, and step S309 is executed.

[0091] Step S308: When the match is determined, an opening command is sent to the electric control valve to open the glue container and perform glue addition.

[0092] Step S309: When an inconsistency is determined, a closing command is sent to the electrically controlled valve to close the switch of the glue container and trigger the alarm device to issue a warning message.

[0093] Step S310: Store the glue code information, timestamp, and cumulative number of additions in the database in the form of a structured data table;

[0094] Step S311: When it is determined that there is an abnormality in the glue addition process, a notification is sent to the preset personnel.

[0095] Steps S301 to S311 above involve collecting the code image on the glue bucket and automatically identifying and comparing it. The opening and closing of the glue container is controlled based on the comparison results, which avoids the problem of errors caused by manual operation and improves the accuracy of glue addition. At the same time, by recording the addition process information and combining it with big data analysis to realize abnormal early warning, the entire glue addition process is traceable and intelligently controlled, ensuring the stability of tobacco cigarette production quality.

[0096] Figure 4 This is a structural block diagram of a tobacco roll adhesive identification and addition device 40 according to an embodiment of this application, as shown below. Figure 4As shown, the tobacco roll glue identification and addition device 40 includes: an information acquisition module 42, an information comparison module 44, and an information recording module 46; wherein: the information acquisition module 42 is used to acquire image information of the glue code on the glue container; and to identify the image information using an image recognition algorithm to obtain the glue code information; the information comparison module 44 is used to match the glue code information with preset standard glue information, and to determine whether the glue code information and the standard glue information are consistent based on the matching result; if the matching result is consistent, the glue container is turned on to perform glue addition; the information recording module 46 is used to record the glue addition operation process information.

[0097] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0098] This embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0099] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0100] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0101] S1, Obtain the image information of the glue code on the glue bucket;

[0102] S2, uses an image recognition algorithm to identify image information and obtain glue code information;

[0103] S3, match the glue code information with the preset standard glue information, and determine whether the glue code information and the standard glue information are consistent based on the matching result;

[0104] S4, If the matching result is determined to be consistent, turn on the glue container to add glue;

[0105] S5 records the process information of adding glue.

[0106] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0107] Furthermore, in conjunction with the tobacco pack adhesive identification and addition method provided in the above embodiments, this embodiment can also provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the tobacco pack adhesive identification and addition methods described in the above embodiments.

[0108] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0109] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0110] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0111] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0112] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method for identifying and adding adhesive to tobacco rolls, characterized in that, include: Obtain the image information of the glue code on the glue bucket; The image information is identified using an image recognition algorithm to obtain glue code information; The glue code information is matched with preset standard glue information, and the matching result is used to determine whether the glue code information and the standard glue information are consistent. If the matching result is determined to be consistent, turn on the glue container to add glue; The process information of adding the adhesive is recorded.

2. The method for identifying and adding adhesive to tobacco rolls according to claim 1, characterized in that, The process of obtaining the image information of the glue code on the glue bucket includes: Obtain the original image information of the glue code on the glue bucket; The original image information is subjected to denoising and contrast enhancement preprocessing to obtain the enhanced image information.

3. The method for identifying and adding adhesive to tobacco rolls according to claim 1, characterized in that, The step of identifying the image information using an image recognition algorithm to obtain glue code information includes: The edge contours of the glue code in the image information are extracted using an edge detection algorithm; Based on the edge contour, the characters of the glue code are separated using character segmentation technology; The image features of each separated character are extracted to obtain the glue code information.

4. The method for identifying and adding adhesive to tobacco rolls according to claim 3, characterized in that, The step of matching the glue code information with preset standard glue information and determining whether the glue code information and the standard glue information are consistent based on the matching result includes: The image features are used as the feature vector to be identified; Calculate the cosine similarity between the feature vector to be identified and the standard feature vectors of each glue in the preset standard glue information; When the cosine similarity is greater than or equal to a preset similarity threshold, the glue code information is determined to be consistent with the standard glue information; otherwise, the glue code information is determined to be inconsistent with the standard glue information.

5. The method for identifying and adding adhesive to tobacco rolls according to claim 1, characterized in that, The method for identifying and adding adhesive to tobacco rolls also includes: When the matching result determines that the glue code information is inconsistent with the standard glue information, a closing command is sent to the electronically controlled valve to close the switch of the glue container and trigger the alarm device to issue a warning message.

6. The method for identifying and adding adhesive to tobacco rolls according to claim 1, characterized in that, The recording of the process information for adding the adhesive includes: Record the glue code information of the glue bucket corresponding to the glue addition operation, the timestamp of the glue addition operation, and the cumulative number of glue additions within a preset statistical period.

7. The method for identifying and adding adhesive to tobacco rolls according to claim 1, characterized in that, The method for identifying and adding adhesive to tobacco rolls also includes: Based on the preset analysis cycle, the recorded glue addition process information is analyzed to obtain the actual addition time interval and / or actual addition frequency. When the actual addition time interval exceeds the preset normal time interval threshold range, and / or the actual addition frequency exceeds the preset normal frequency threshold range, it is determined that there is an abnormality in the glue addition process, and an early warning notification is output.

8. A device for identifying and adding adhesive to tobacco rolls, characterized in that, include: The module includes an information acquisition module, an information comparison module, and an information recording module; among which: The information acquisition module is used to acquire image information of the glue code on the glue bucket; and to identify the image information using an image recognition algorithm to obtain the glue code information. The information comparison module is used to match the glue code information with preset standard glue information, and determine whether the glue code information and the standard glue information are consistent based on the matching result; if the matching result is consistent, the glue container is turned on to add glue. The information recording module is used to record information about the process of adding the adhesive.

9. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the tobacco roll adhesive identification and addition method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the tobacco roll adhesive identification and addition method according to any one of claims 1 to 7.