Tobacco equipment evaluation method and device, computer equipment and storage medium

Abstract

The invention relates to a tobacco equipment evaluation method and device, computer equipment and a storage medium, and the method comprises the steps: determining the product defect information of a tobacco product according to the product image information of the tobacco product; and determining defect trend prediction information of the tobacco product according to the product defect information and the equipment operation information of the associated equipment for manufacturing the tobacco product. And determining an evaluation result of the associated equipment according to the defect trend prediction information, the product defect information and the equipment operation information. According to the method, the product defect information of the tobacco product is determined based on the product image information. In addition, the defect area prediction information of the tobacco product can be obtained based on the product defect information, and finally the evaluation result of the associated equipment is determined based on the defect trend prediction information, the product defect information and the equipment operation information, so that the root of the defect of the tobacco product is determined, and the operation efficiency and the product quality of the production line are effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of tobacco equipment, and in particular to a tobacco equipment evaluation method, apparatus, computer equipment, and storage medium. Background Art

[0002] In the modern cigarette manufacturing process, the stability of related tobacco equipment and product quality control are crucial.

[0003] Current production lines rely heavily on visual inspection equipment to identify potential product defects during the production process, enabling them to immediately reject substandard products. However, with increasing production demands and consumers demanding higher quality cigarettes, traditional inspection methods can only simply identify tobacco product quality and fail to address the root cause. Summary of the Invention

[0004] Based on this, it is necessary to provide a tobacco equipment evaluation method, device, computer equipment and storage medium that can evaluate tobacco equipment and improve tobacco product quality and production efficiency in response to the above technical problems.

[0005] In a first aspect, the present application provides a tobacco device evaluation method. The method comprises:

[0006] determining product defect information of the tobacco product based on product image information of the tobacco product;

[0007] Determining tobacco product defect trend prediction information based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products;

[0008] Determine the evaluation results of related equipment based on defect trend prediction information, product defect information and equipment operation information.

[0009] In one embodiment, determining tobacco product defect trend prediction information based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products includes:

[0010] Determine the defect type of tobacco products based on product image information and product defect information using a defect analysis model;

[0011] Defect trend prediction information of tobacco products is determined through a trend prediction model based on defect types and equipment operation information of associated equipment for manufacturing tobacco products.

[0012] In one embodiment, determining an evaluation result of an associated device based on defect trend prediction information, product defect information, and device operation information includes:

[0013] Determine target defect information for tobacco products based on defect trend prediction information and product defect information;

[0014] Determine the evaluation results of associated equipment based on target defect information and equipment operation information.

[0015] In one embodiment, determining an evaluation result of an associated device based on target defect information and device operation information includes:

[0016] Determine the evaluation results of associated equipment based on target defect information, equipment operation information and knowledge graph model.

[0017] Among them, the knowledge graph model includes the knowledge graph model of each associated device; the knowledge graph model of each associated device includes each fault type corresponding to the associated device and the associated information of each fault type; the associated information includes at least one of associated components, component operation information, component parameter information and product impact information.

[0018] In one embodiment, the associated information also includes fault repair information;

[0019] Accordingly, based on the target defect information, equipment operation information and knowledge graph model, the evaluation results of the associated equipment are determined, including:

[0020] Determine the predicted fault information and fault repair information of the associated equipment based on the knowledge graph model, target defect information, and equipment operation information;

[0021] Generates evaluation results of associated devices based on predicted fault information and fault repair information.

[0022] In one embodiment, generating an evaluation result of associated devices based on the predicted fault information and the fault repair information includes:

[0023] An evaluation result of the associated equipment is generated based on the predicted fault information, the fault repair information, and the defect type of the tobacco product.

[0024] In one embodiment, determining product defect information of a tobacco product based on product image information of the tobacco product includes:

[0025] Determining the presence of product defects in tobacco products based on product image information of tobacco products;

[0026] When the product defect existence condition is that a defect exists, product defect information of the tobacco product is determined.

[0027] In a second aspect, the present application also provides a tobacco equipment evaluation device. The device includes:

[0028] A first determining module is configured to determine product defect information of the tobacco product based on product image information of the tobacco product;

[0029] a second determining module, configured to determine defect trend prediction information of tobacco products based on the product defect information and equipment operation information of associated equipment for manufacturing tobacco products;

[0030] The third determination module is used to determine the evaluation results of the associated equipment based on the defect trend prediction information, product defect information and equipment operation information.

[0031] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the following steps are performed:

[0032] determining product defect information of the tobacco product based on product image information of the tobacco product;

[0033] Determining tobacco product defect trend prediction information based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products;

[0034] Determine the evaluation results of related equipment based on defect trend prediction information, product defect information and equipment operation information.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0036] determining product defect information of the tobacco product based on product image information of the tobacco product;

[0037] Determining tobacco product defect trend prediction information based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products;

[0038] Determine the evaluation results of related equipment based on defect trend prediction information, product defect information and equipment operation information.

[0039] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

[0040] determining product defect information of the tobacco product based on product image information of the tobacco product;

[0041] Determining tobacco product defect trend prediction information based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products;

[0042] Determine the evaluation results of related equipment based on defect trend prediction information, product defect information and equipment operation information.

[0043] The above-mentioned tobacco equipment evaluation method, device, computer equipment and storage medium determine the product defect information of tobacco products based on the product image information of tobacco products. Determine the defect trend prediction information of tobacco products based on the product defect information and the equipment operation information of the associated equipment used to manufacture tobacco products. Determine the evaluation results of the associated equipment based on the defect trend prediction information, product defect information and equipment operation information. This application can not only determine the product defect information of tobacco products based on product image information. It can also obtain the defect area prediction information of the tobacco product based on the product defect information, and finally determine the evaluation results of the associated equipment based on the defect trend prediction information, product defect information and equipment operation information, and then determine the root cause of the defects in the tobacco products. It can not only detect product defects in a timely manner, but also quickly locate the associated equipment corresponding to the defects, effectively improving the operating efficiency and product quality of the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A diagram illustrating the application environment of the tobacco equipment evaluation method provided in this embodiment;

[0045] Figure 2 A schematic flow chart of the first tobacco equipment evaluation method provided in this embodiment;

[0046] Figure 3 A schematic diagram of a process for determining defect trend prediction information of tobacco products provided in this embodiment;

[0047] Figure 4 A schematic diagram of the principle of the analysis device provided in this embodiment;

[0048] Figure 5 A schematic diagram of a process for determining an evaluation result of an associated device provided in this embodiment;

[0049] Figure 6 A schematic flow chart of a second tobacco equipment evaluation method provided in this embodiment;

[0050] Figure 7 A structural block diagram of a tobacco equipment evaluation device provided in this embodiment;

[0051] Figure 8 This is a diagram of the internal structure of the computer device provided in this embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0053] The tobacco equipment evaluation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the acquisition device is responsible for collecting product image information of tobacco products generated by each associated device. The collected product image information is then sent to the evaluation device. The evaluation device determines product defect information based on the tobacco product image information and determines defect trend prediction information for the tobacco product based on the product defect information and the equipment operation information of the associated equipment that manufactures the tobacco product. Finally, the evaluation device determines the evaluation results for the associated devices based on the defect trend prediction information, product defect information, and equipment operation information. The evaluation device can send the evaluation results to a display device, which can then display the evaluation results to the user. The evaluation device can be a control host, a server, or other device with evaluation capabilities. The server can be implemented as a standalone server or a server cluster consisting of multiple servers. The acquisition device can be a collector, which obtains product image information of tobacco products using an image detection device. The display device can be a display or other device with display capabilities.

[0054] In one embodiment, Figure 2 As shown, a tobacco device evaluation method is provided, which is applied to Figure 1 The following steps are used as an example to describe the evaluation device in the example:

[0055] S201 : Determine product defect information of the tobacco product based on product image information of the tobacco product.

[0056] Tobacco products refer to tobacco-related products generated or processed using associated equipment. Product image information refers to image information of tobacco products, which can be generated using image detection equipment (e.g., webcams, high-definition cameras, etc.). Product defect information refers to descriptions of tobacco product defects, such as inconsistent tobacco length, excessive moisture content, or surface stains.

[0057] As an optional implementation of the embodiment of the present application, product image information of tobacco products is input into an image analysis tool, and the image analysis tool outputs product defect information of the tobacco products. The image analysis tool can be a neural network model trained based on sample data of tobacco products.

[0058] Another optional implementation method of the embodiment of the present application is to determine the presence of product defects of tobacco products based on the product image information of tobacco products. When the presence of product defects is a defect, the product defect information of the tobacco products is determined. Specifically, an image analysis tool is used to determine the presence of product defects of tobacco products based on the product image information of tobacco products. When the presence of product defects is a defect, the product defect information of the tobacco products is determined. When in use, the product image information of the tobacco products is input into the image analysis tool, and the image analysis tool first performs a "rough inspection" on the product image information to detect the presence of product defects of the tobacco products. When the presence of product defects is a defect, a further "detailed inspection" is performed to detect and output the product defect information of the tobacco products.

[0059] S202 : Determine defect trend prediction information of tobacco products based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products.

[0060] Associated equipment refers to equipment related to tobacco product manufacturing, such as blade slicers, rehumidification equipment, conveyor belts, and fans. Equipment operation information refers to the operating information of associated equipment. Defect trend prediction information refers to forecasts of product defect trends, such as defect probability trends, defect quantity trends, and defect severity trends.

[0061] Optionally, the associated equipment operating information includes operating information of a blade slicer, a rehumidification device, a conveyor belt device, and a fan device. The blade slicer operating information includes slicing speed, tool wear status, operating temperature, etc.; the rehumidification device operating information includes water application amount, humidity change curve, etc.; the conveyor belt operating information includes vibration frequency, transmission speed, etc.; and the fan operating information includes air volume, vibration amplitude, and temperature, etc.

[0062] Optionally, in this embodiment, product defect information and equipment operation information of associated equipment for manufacturing tobacco products are input into a prediction model, and the prediction model outputs defect trend prediction information of tobacco products; wherein the prediction model can be a trained neural network model.

[0063] S203: Determine evaluation results of associated equipment based on defect trend prediction information, product defect information, and equipment operation information.

[0064] Optionally, the evaluation result in this embodiment includes at least one of product defect information, defect development trend, fault-related equipment, fault type, and maintenance suggestion.

[0065] As an optional implementation of the present application, defect trend prediction information, product defect information, and equipment operation information are input into an analysis device, which then outputs an evaluation result of the associated equipment. The analysis device can be an AI agent or a trained neural network model.

[0066] In this embodiment, product defect information of tobacco products is determined based on product image information of tobacco products. Defect trend prediction information of tobacco products is determined based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products. Evaluation results of associated equipment are determined based on defect trend prediction information, product defect information, and equipment operation information. This application not only determines product defect information of tobacco products based on product image information. It also obtains defect area prediction information of the tobacco products based on product defect information. Finally, based on defect trend prediction information, product defect information, and equipment operation information, it determines evaluation results of associated equipment, and then determines the root cause of defects in tobacco products. This not only allows timely discovery of product defects, but also allows rapid location of associated equipment corresponding to the defects, effectively improving the operating efficiency of the production line and product quality.

[0067] In one embodiment, in order to more quickly determine defect trend prediction information, such as Figure 3 As shown, an optional implementation in S202 includes:

[0068] S301 , determining the defect type of the tobacco product according to the product image information and the product defect information through a defect analysis model.

[0069] The defect analysis model is used to analyze tobacco product defects. The defect type refers to the type of product defect information, such as uneven tobacco, abnormal tobacco moisture, surface contamination, etc.

[0070] Optionally, the defect analysis model in this embodiment may use the YOLOv5 (You Only Look Once, fifth edition) model. The YOLOv5 model can locate and classify defects in images in a very short time and is particularly suitable for processing large amounts of image data in industrial scenarios.

[0071] Optionally, in this embodiment, Figure 4 As shown, product image information and product defect information are input into a defect analysis model, which then outputs the tobacco product defect type. Specifically, the defect analysis model determines candidate tobacco product defect information based on the product image information, compares the candidate defect information with the product defect information, obtains common defect information, and determines the tobacco product defect type based on the common defect information.

[0072] Optionally, in addition to determining the defect type, the defect analysis model in this embodiment can also output a defect report, which includes the defect type and corresponding defect information. For example, uneven slicing: Inconsistent lengths of tobacco slices lead to uneven filling of subsequent cigarette products, affecting combustion performance. Abnormal tobacco humidity: Excessive or insufficient humidity directly affects the burning speed of tobacco and the smoking experience. Surface contamination: Foreign matter or stains mixed into the tobacco surface affect the product's appearance quality.

[0073] S302 , determining defect trend prediction information of tobacco products according to defect types and equipment operation information of associated equipment for manufacturing tobacco products through a trend prediction model.

[0074] Among them, the trend prediction model refers to a prediction model for the trend development of product defects in the future period.

[0075] Optionally, the trend prediction model in this embodiment can be an LSTM (Long Short-Term Memory) prediction model. The LSTM prediction model is suitable for processing time series data and can effectively predict trends in device status changes. By inputting device operating data from multiple time points, the system can accurately predict the future status of the device.

[0076] Optionally, in this implementation, Figure 4 As shown, the defect type and equipment operation information of the related equipment for manufacturing tobacco products are input into the trend prediction model, and the trend prediction model outputs defect trend prediction information of the tobacco products.

[0077] It should be noted that after the evaluation results are given, users can provide feedback and suggestions on the evaluation results based on artificial intelligence analysis models or expert experience, and can optimize the defect analysis model and / or trend prediction model in the analysis equipment based on the feedback suggestions to make the subsequent output results more accurate.

[0078] In this embodiment, a defect analysis model is used to determine the tobacco product defect type based on product image information and product defect information. A trend prediction model is used to determine tobacco product defect trend prediction information based on the defect type and equipment operating information related to tobacco product manufacturing. This embodiment allows for more accurate and rapid determination of defect trend prediction information.

[0079] In one embodiment, in order to make the evaluation result more accurate, Figure 5 As shown, an optional implementation of S203 includes:

[0080] S501: Determine target defect information of tobacco products based on defect trend prediction information and product defect information.

[0081] The target defect information refers to the defect information determined based on the defect trend prediction information and product defect information.

[0082] Optionally, the defect trend prediction information in this embodiment includes defect type, defect description information and future defect trend. On this basis, an optional implementation method for determining the target defect information of tobacco products based on the defect trend prediction information and product defect information is to determine the defect union information based on the defect description information and product defect information. The defect union information, defect type and future defect trend are used as target defect information. In this embodiment, an optional implementation method for determining the defect union information based on the defect description information and product defect information is to use the union of the defect description information and the product defect information as the initial union information, pre-process the initial union information, and obtain the defect union information. Among them, the preprocessing method includes removing noise data, for example, eliminating invalid features.

[0083] S502: Determine the evaluation results of the associated equipment according to the target defect information and the equipment operation information.

[0084] Optionally, the evaluation results in this embodiment include but are not limited to defect reports, maintenance suggestions, faulty equipment, fault types, etc.

[0085] In this embodiment, an optional implementation method for determining the evaluation results of associated devices based on target defect information and device operation information is to determine the evaluation results of associated devices based on target defect information, device operation information and a knowledge graph model.

[0086] Among them, the knowledge graph model includes the knowledge graph model of each associated device; the knowledge graph model of each associated device includes each fault type corresponding to the associated device and the associated information of each fault type; the associated information includes at least one of associated components, component operation information, component parameter information and product impact information. In this embodiment, the construction of the knowledge graph model first requires modeling each device in the silk-making workshop, including the component structure of the equipment, the configuration of various sensors, the relevant information obtained by the sensors, historical maintenance records, etc. The knowledge graph can not only record the current status of the equipment, but also model its failure mode. For example:

[0087] Knowledge graph model for a blade slicer: This model includes detailed information about multiple components, including blades, conveyor belts, and motors. It also includes data interfaces for blade wear and vibration sensors. Furthermore, the graph includes historical maintenance records, past failure types, and the impact of these failures on the product.

[0088] A knowledge graph model for moisture recovery equipment: This graph model includes a relationship diagram of equipment components such as water pumps, humidifiers, and fans, as well as information about their associated humidity sensors and temperature control modules. This information allows the system to quickly determine whether humidity control anomalies are caused by a water pump failure or a humidifier issue.

[0089] Optionally, the knowledge graph model in this embodiment may also include a knowledge graph model at the process level. In addition to the information at the equipment level, this application also needs to model the overall process flow of the silk-making workshop to obtain a process knowledge graph model. By modeling the process flow, the evaluation equipment can understand the key equipment and process parameters of each production stage and the impact of these parameters on the quality of the final product. This multi-level knowledge graph design enables the evaluation to make judgments from a more comprehensive perspective when analyzing defects and equipment failures.

[0090] In this embodiment, an optional implementation method for determining the evaluation results of associated devices based on target defect information, device operation information, and a knowledge graph model is that the associated information also includes fault repair information. Based on this, predicted fault information and fault repair information for the associated devices are determined based on the knowledge graph model, target defect information, and device operation information. Based on the predicted fault information and fault repair information, an evaluation result for the associated devices is generated. Specifically, the target defect information and device operation information are matched with the various fault types in the knowledge graph model of each associated device, as well as the associated information corresponding to each fault type, to obtain the faulty device and the corresponding fault prediction information. The predicted fault information includes the fault type and fault development trend. Based on the fault type and the knowledge graph model of the faulty device, fault repair information is determined. Fault repair information refers to repair recommendations for the fault type of the faulty device. For example, if the faulty device is a blade slicer and the fault type is a blade fault, the fault repair information includes detailed instructions for each step of blade removal, cleaning, replacement, and commissioning, making it easier for maintenance personnel to follow standard procedures.

[0091] It should be noted that the knowledge graph model can also form optimization or modification suggestions based on the evaluation results, and optimize or modify the knowledge graph model based on the optimization or modification suggestions.

[0092] Building on the above-mentioned embodiment, an alternative implementation for generating an assessment result for associated devices based on predicted fault information and fault remediation information in this embodiment is to generate an assessment result for associated devices based on the predicted fault information, fault remediation information, and tobacco product defect types. In other words, the assessment report contains at least the predicted fault information, fault remediation information, and tobacco product defect types, allowing users to clearly understand production line fault conditions and product defects, and intuitively understand fault remediation recommendations.

[0093] In this embodiment, target defect information for tobacco products is determined based on defect trend prediction information and product defect information. Predicted fault information and fault remediation information for associated equipment are determined based on a knowledge graph model, target defect information, and equipment operation information. Finally, assessment results for associated equipment are generated based on the predicted fault information, remediation information, and tobacco product defect types. This embodiment not only increases the accuracy of equipment assessment results but also allows users to clearly understand production line fault conditions and product defects, and intuitively access fault remediation recommendations.

[0094] In one embodiment, Figure 6 As shown, an optional implementation of the tobacco device evaluation method is:

[0095] S601: Determine whether there are product defects of the tobacco product based on product image information of the tobacco product.

[0096] S602: When the product defect existence condition is that the product defect exists, determine product defect information of the tobacco product.

[0097] S603: Determine the defect type of the tobacco product based on the product image information and the product defect information using a defect analysis model.

[0098] S604 , determining defect trend prediction information of tobacco products according to the defect type and equipment operation information of associated equipment for manufacturing tobacco products through a trend prediction model.

[0099] S605 , determining target defect information of the tobacco product based on the defect trend prediction information and the product defect information.

[0100] S606: Determine predicted fault information and fault repair information for associated devices based on the knowledge graph model, target defect information, and device operation information. The knowledge graph model includes knowledge graph models for each associated device; each associated device's knowledge graph model includes each fault type corresponding to the associated device and associated information for each fault type; and the associated information includes at least one of associated components, component operation information, component parameter information, and product impact information.

[0101] S607: Generate an evaluation result of the associated device based on the predicted fault information, the fault repair information, and the defect type of the tobacco product.

[0102] This application determines the product defect information of tobacco products based on the product image information of tobacco products. Determines the defect trend prediction information of tobacco products based on the product defect information and the equipment operation information of the associated equipment for manufacturing tobacco products. Determines the evaluation results of the associated equipment based on the defect trend prediction information, product defect information and equipment operation information. This application not only determines the product defect information of tobacco products based on product image information. It also obtains the defect area prediction information of the tobacco product based on the product defect information, and finally determines the evaluation results of the associated equipment based on the defect trend prediction information, product defect information and equipment operation information, and then determines the root cause of the defects in the tobacco products. It can not only detect product defects in a timely manner, but also quickly locate the associated equipment corresponding to the defects, effectively improving the operating efficiency of the production line and product quality.

[0103] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0104] Based on the same inventive concept, embodiments of the present application also provide a tobacco equipment evaluation device for implementing the aforementioned tobacco equipment evaluation method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more tobacco equipment evaluation device embodiments provided below can be found in the above-described limitations of the tobacco equipment evaluation method and will not be further elaborated here.

[0105] In one embodiment, Figure 7 As shown, a tobacco equipment evaluation device 1 is provided, comprising: a first determination module 10, a second determination module 20 and a third determination module 30, wherein:

[0106] A first determining module 10 is configured to determine product defect information of the tobacco product based on product image information of the tobacco product;

[0107] A second determining module 20 is configured to determine defect trend prediction information of tobacco products based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products;

[0108] The third determination module 30 is used to determine the evaluation results of the associated equipment based on the defect trend prediction information, product defect information and equipment operation information.

[0109] In one embodiment, the Figure 7 The second determining module is further specifically configured to:

[0110] Determine the defect type of tobacco products based on product image information and product defect information using a defect analysis model;

[0111] Defect trend prediction information of tobacco products is determined through a trend prediction model based on defect types and equipment operation information of associated equipment for manufacturing tobacco products.

[0112] In one embodiment, the Figure 7 The third determining module is further specifically configured to:

[0113] Determine target defect information for tobacco products based on defect trend prediction information and product defect information;

[0114] Determine the evaluation results of associated equipment based on target defect information and equipment operation information.

[0115] In one embodiment, the Figure 7 The third determining module is further specifically configured to:

[0116] Determine the evaluation results of associated equipment based on target defect information, equipment operation information and knowledge graph model.

[0117] Among them, the knowledge graph model includes the knowledge graph model of each associated device; the knowledge graph model of each associated device includes each fault type corresponding to the associated device and the associated information of each fault type; the associated information includes at least one of associated components, component operation information, component parameter information and product impact information.

[0118] In one embodiment, the associated information also includes fault repair information; on this basis, Figure 6 The third determining module is further specifically configured to:

[0119] Determine the predicted fault information and fault repair information of the associated equipment based on the knowledge graph model, target defect information, and equipment operation information;

[0120] Generates evaluation results of associated devices based on predicted fault information and fault repair information.

[0121] In one embodiment, the Figure 7 The third determining module is further specifically configured to:

[0122] An evaluation result of the associated equipment is generated based on the predicted fault information, the fault repair information, and the defect type of the tobacco product.

[0123] In one embodiment, the Figure 7 The first determination module is further specifically configured to:

[0124] Determining the presence of product defects in tobacco products based on product image information of tobacco products;

[0125] When the product defect existence condition is that a defect exists, product defect information of the tobacco product is determined.

[0126] Each module in the tobacco device evaluation device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0127] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used 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 the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store tobacco device-related data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a tobacco device evaluation method is implemented.

[0128] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0129] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0130] determining product defect information of the tobacco product based on product image information of the tobacco product;

[0131] Determining tobacco product defect trend prediction information based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products;

[0132] Determine the evaluation results of related equipment based on defect trend prediction information, product defect information and equipment operation information.

[0133] In one embodiment, when the processor executes the computer program, the processor further implements the following steps: determining defect trend prediction information of the tobacco product based on the product defect information and equipment operation information of associated equipment for manufacturing the tobacco product, including:

[0134] Determine the defect type of tobacco products based on product image information and product defect information using a defect analysis model;

[0135] Defect trend prediction information of tobacco products is determined through a trend prediction model based on defect types and equipment operation information of associated equipment for manufacturing tobacco products.

[0136] In one embodiment, when the processor executes the computer program, the processor further implements the following steps: determining an evaluation result of the associated device based on the defect trend prediction information, the product defect information, and the device operation information, including:

[0137] Determine target defect information for tobacco products based on defect trend prediction information and product defect information;

[0138] Determine the evaluation results of associated equipment based on target defect information and equipment operation information.

[0139] In one embodiment, when the processor executes the computer program, the processor further implements the following steps: determining an evaluation result of the associated device based on the target defect information and the device operation information, including:

[0140] Determine the evaluation results of associated equipment based on target defect information, equipment operation information and knowledge graph model.

[0141] Among them, the knowledge graph model includes the knowledge graph model of each associated device; the knowledge graph model of each associated device includes each fault type corresponding to the associated device and the associated information of each fault type; the associated information includes at least one of associated components, component operation information, component parameter information and product impact information.

[0142] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the associated information further includes fault repair information;

[0143] Accordingly, based on the target defect information, equipment operation information and knowledge graph model, the evaluation results of the associated equipment are determined, including:

[0144] Determine the predicted fault information and fault repair information of the associated equipment based on the knowledge graph model, target defect information, and equipment operation information;

[0145] Generates evaluation results of associated devices based on predicted fault information and fault repair information.

[0146] In one embodiment, when the processor executes the computer program, the processor further implements the following steps: generating an evaluation result of the associated device based on the predicted fault information and the fault repair information, including:

[0147] An evaluation result of the associated equipment is generated based on the predicted fault information, the fault repair information, and the defect type of the tobacco product.

[0148] In one embodiment, when the processor executes the computer program, the processor further implements the following steps: determining product defect information of the tobacco product based on the product image information of the tobacco product, including:

[0149] Determining the presence of product defects in tobacco products based on product image information of tobacco products;

[0150] When the product defect existence condition is that a defect exists, product defect information of the tobacco product is determined.

[0151] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0152] determining product defect information of the tobacco product based on product image information of the tobacco product;

[0153] Determining tobacco product defect trend prediction information based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products;

[0154] Determine the evaluation results of related equipment based on defect trend prediction information, product defect information and equipment operation information.

[0155] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining defect trend prediction information of tobacco products based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products, including:

[0156] Determine the defect type of tobacco products based on product image information and product defect information using a defect analysis model;

[0157] Defect trend prediction information of tobacco products is determined through a trend prediction model based on defect types and equipment operation information of associated equipment for manufacturing tobacco products.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining an evaluation result of the associated device based on the defect trend prediction information, the product defect information, and the device operation information, including:

[0159] Determine target defect information for tobacco products based on defect trend prediction information and product defect information;

[0160] Determine the evaluation results of associated equipment based on target defect information and equipment operation information.

[0161] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining an evaluation result of the associated device based on the target defect information and the device operation information, including:

[0162] Determine the evaluation results of associated equipment based on target defect information, equipment operation information and knowledge graph model.

[0163] Among them, the knowledge graph model includes the knowledge graph model of each associated device; the knowledge graph model of each associated device includes each fault type corresponding to the associated device and the associated information of each fault type; the associated information includes at least one of associated components, component operation information, component parameter information and product impact information.

[0164] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: the associated information further includes fault repair information;

[0165] Accordingly, based on the target defect information, equipment operation information and knowledge graph model, the evaluation results of the associated equipment are determined, including:

[0166] Determine the predicted fault information and fault repair information of the associated equipment based on the knowledge graph model, target defect information, and equipment operation information;

[0167] Generates evaluation results of associated devices based on predicted fault information and fault repair information.

[0168] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: generating an evaluation result of the associated device based on the predicted fault information and the fault repair information, including:

[0169] An evaluation result of the associated equipment is generated based on the predicted fault information, the fault repair information, and the defect type of the tobacco product.

[0170] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining product defect information of the tobacco product based on the product image information of the tobacco product, including:

[0171] Determining the presence of product defects in tobacco products based on product image information of tobacco products;

[0172] When the product defect existence condition is that a defect exists, product defect information of the tobacco product is determined.

[0173] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0174] determining product defect information of the tobacco product based on product image information of the tobacco product;

[0175] Determining tobacco product defect trend prediction information based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products;

[0176] Determine the evaluation results of related equipment based on defect trend prediction information, product defect information and equipment operation information.

[0177] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining defect trend prediction information of tobacco products based on product defect information and equipment operation information of associated equipment for manufacturing tobacco products, including:

[0178] Determine the defect type of tobacco products based on product image information and product defect information using a defect analysis model;

[0179] Defect trend prediction information of tobacco products is determined through a trend prediction model based on defect types and equipment operation information of associated equipment for manufacturing tobacco products.

[0180] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining an evaluation result of the associated device based on the defect trend prediction information, the product defect information, and the device operation information, including:

[0181] Determine target defect information for tobacco products based on defect trend prediction information and product defect information;

[0182] Determine the evaluation results of associated equipment based on target defect information and equipment operation information.

[0183] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining an evaluation result of the associated device based on the target defect information and the device operation information, including:

[0184] Determine the evaluation results of associated equipment based on target defect information, equipment operation information and knowledge graph model.

[0185] Among them, the knowledge graph model includes the knowledge graph model of each associated device; the knowledge graph model of each associated device includes each fault type corresponding to the associated device and the associated information of each fault type; the associated information includes at least one of associated components, component operation information, component parameter information and product impact information.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: the associated information further includes fault repair information;

[0187] Accordingly, based on the target defect information, equipment operation information and knowledge graph model, the evaluation results of the associated equipment are determined, including:

[0188] Determine the predicted fault information and fault repair information of the associated equipment based on the knowledge graph model, target defect information, and equipment operation information;

[0189] Generates evaluation results of associated devices based on predicted fault information and fault repair information.

[0190] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: generating an evaluation result of the associated device based on the predicted fault information and the fault repair information, including:

[0191] An evaluation result of the associated equipment is generated based on the predicted fault information, the fault repair information, and the defect type of the tobacco product.

[0192] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining product defect information of the tobacco product based on the product image information of the tobacco product, including:

[0193] Determining the presence of product defects in tobacco products based on product image information of tobacco products;

[0194] When the product defect existence condition is that a defect exists, product defect information of the tobacco product is determined.

[0195] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0196] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0197] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A tobacco equipment evaluation method, characterized in that: The method comprises: determining product defect information of the tobacco product based on product image information of the tobacco product; determining defect trend prediction information of the tobacco product based on the product defect information and equipment operation information of associated equipment for manufacturing the tobacco product; An evaluation result of the associated device is determined based on the defect trend prediction information, the product defect information, and the device operation information.

2. The method according to claim 1, characterized in that The determining of defect trend prediction information of the tobacco product based on the product defect information and equipment operation information of associated equipment for manufacturing the tobacco product includes: determining, by a defect analysis model, a defect type of the tobacco product based on the product image information and the product defect information; Defect trend prediction information of the tobacco product is determined by a trend prediction model according to the defect type and equipment operation information of associated equipment for manufacturing the tobacco product.

3. The method according to claim 1, characterized in that Determining the evaluation result of the associated device according to the defect trend prediction information, the product defect information, and the device operation information includes: determining target defect information of the tobacco product based on the defect trend prediction information and the product defect information; An evaluation result of the associated device is determined according to the target defect information and the device operation information.

4. The method according to claim 3, characterized in that Determining an evaluation result of the associated device according to the target defect information and the device operation information includes: Determining an evaluation result of the associated device based on the target defect information, the device operation information, and the knowledge graph model; Among them, the knowledge graph model includes the knowledge graph model of each associated device; the knowledge graph model of each associated device includes each fault type corresponding to the associated device and the associated information of each fault type; the associated information includes at least one of associated components, component operation information, component parameter information and product impact information.

5. The method according to claim 4, characterized in that The associated information also includes fault repair information; Accordingly, determining the evaluation result of the associated device according to the target defect information, the device operation information, and the knowledge graph model includes: Determining predicted fault information and fault repair information of the associated device based on the knowledge graph model, the target defect information, and the device operation information; An evaluation result of the associated device is generated according to the predicted fault information and the fault repair information.

6. The method according to claim 5, characterized in that Generating an evaluation result of the associated device according to the predicted fault information and the fault repair information includes: An evaluation result of the associated device is generated according to the predicted fault information, the fault repair information, and the defect type of the tobacco product.

7. The method according to claim 1, characterized in that The determining of product defect information of the tobacco product based on product image information of the tobacco product includes: determining, based on product image information of the tobacco product, whether a product defect exists in the tobacco product; When the product defect existence condition is that a defect exists, product defect information of the tobacco product is determined.

8. A tobacco equipment evaluation device, characterized in that: include: A first determining module, configured to determine product defect information of the tobacco product based on product image information of the tobacco product; a second determining module, configured to determine defect trend prediction information of the tobacco product based on the product defect information and equipment operation information of associated equipment for manufacturing the tobacco product; The third determination module is used to determine the evaluation result of the associated device according to the defect trend prediction information, the product defect information and the device operation information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the tobacco device evaluation method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the tobacco device evaluation method according to any one of claims 1 to 7 are implemented.

Images