Digital Twin-Based Tobacco Leaf Sorting and Grading Management Method and System

Abstract

This application relates to a tobacco leaf sorting and grading management method, device, computer device, storage medium, and computer program product based on digital twin. The method includes: creating digital twin models of tobacco leaves and preset sorting and grading equipment; obtaining the event content obtained during sorting and grading; calling an event trigger program and transmitting the event content to the event trigger program. After the event trigger program obtains the event content, it reads the event trigger conditions corresponding to the event content and determines whether the event content is triggered based on the event content and the event trigger conditions; if the event is triggered, it calls the event consumption program corresponding to the event content for processing, and generates a data processing completion event after completion. By using an event-driven architecture with this method, the tobacco leaf grading management system can quickly respond and update the model when data changes, improving the real-time performance, scalability, and reliability of the system, while simplifying the system integration and maintenance work.

Description

Technical Field

[0001] The present application relates to the technical field of tobacco leaf sorting, and particularly to a method, device, equipment and storage medium for tobacco leaf sorting and grading management based on digital twin. Background Art

[0002] Tobacco leaf grading is a basic task in the tobacco industry when purchasing tobacco. Since the quality of tobacco leaves varies, the mixed use of ungraded tobacco leaves of good and bad quality will inevitably lead to a reduction in their use value, resulting in a waste of resources and a significant reduction in economic benefits. Only through reasonable grading and the adoption of scientific formulations for different grades of tobacco leaves can cigarettes of different requirements be produced. Therefore, the purpose of grading is to separate tobacco leaves of different qualities so that each grade and each bundle of tobacco leaves have relatively consistent quality, which is of great significance in the tobacco acquisition stage.

[0003] For a long time, most tobacco leaf grading methods have been manual grading methods, which are processes of dividing tobacco leaf grades by visual inspection, manual touch, nose smelling, etc. according to certain tobacco leaf grading factors. The ultimate goal of tobacco leaf grading is to define the internal and external qualities of tobacco leaf grades.

[0004] However, the current tobacco leaf grading mostly uses manual methods, relying too much on the subjective feelings and personal judgments of grading personnel, and there are limitations such as long time consumption and lack of unified standards. Improving the accuracy, objectivity and reliability of tobacco leaf grading through new technologies has become an urgent need for tobacco production enterprises. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for tobacco leaf sorting and grading management based on digital twin that can improve the sorting efficiency of tobacco leaves.

[0006] In a first aspect, the present application provides a method for tobacco leaf sorting and grading management based on digital twin. The method includes:

[0007] Create digital twin models of tobacco leaves and preset sorting and grading equipment, where the digital twin models at least include tobacco leaves and simulation equipment corresponding to the sorting and grading equipment, and the simulation equipment is used to simulate data collection of the sorting and grading equipment;

[0008] Obtain the event content obtained during sorting and grading, where the event content at least includes data collection of tobacco leaves;

[0009] Call the event trigger program and transmit the event content to the event trigger program. After the event trigger program obtains the event content, read the event trigger conditions corresponding to the event content, and determine whether the event content is triggered based on the event content and the event trigger conditions;

[0010] If an event is triggered, call the event consumption program corresponding to the event content for processing, and generate a data processing completion event after completion.

[0011] In one embodiment, when the event consumption program is data processing, obtain the tobacco leaf data detected by the preset sorting and grading equipment;

[0012] Call the data trigger program and transmit the tobacco leaf data to the event trigger program, and the event trigger program obtains the tobacco leaf data;

[0013] Read that the event trigger condition corresponding to the tobacco leaf data is that the sorting and grading equipment performs data collection operations;

[0014] Based on the tobacco leaf data and the data collection operation of the sorting and grading equipment, call the data processing event to process the collected data until a data processing completion event is generated after the data processing event is completed.

[0015] In one embodiment, when the event consumption program is model update, receive the data processing completion event;

[0016] Obtain the updated tobacco leaf data, and the updated tobacco data is the tobacco leaf data obtained after the tobacco leaf data detected by the sorting and grading equipment is processed;

[0017] Construct an incremental digital model based on the updated tobacco leaf data and perform incremental training;

[0018] Fuse the incremental digital model with the digital twin model and generate an updated twin model.

[0019] In one embodiment, when the event consumption program is anomaly detection, obtain the tobacco leaf data;

[0020] Compare the tobacco leaf data with the preset standard change range;

[0021] If the tobacco leaf data is outside the preset standard change range, obtain the detection environment data related to the tobacco leaf data;

[0022] If the detection environment data is within the preset standard environment range, generate an anomaly detection event.

[0023] In one embodiment, calling the data processing event to process the collected data includes:

[0024] Statistical data processing event for the processing time of the collected data;

[0025] If the processing time is outside the critical time, extract the regional information corresponding to the tobacco leaf data;

[0026] Based on the regional information, perform the same processing operation on the collected data and generate accelerated processing data;

[0027] When the processing time is within the critical time, perform secondary verification processing on the accelerated processing data;

[0028] If the error between the verification data and the accelerated processing data is within the preset range, replace the corresponding accelerated processing data with the verification data;

[0029] If the error between the verification data and the accelerated processing data is outside the preset range, generate an anomaly detection event.

[0030] In one of the embodiments, the acceleration stability of different regions is statistically analyzed, and the acceleration stability is the error between the verification data corresponding to the target region and the accelerated processing data;

[0031] Based on the acceleration stability, preferentially process the tobacco leaf data corresponding to the region with high acceleration stability;

[0032] Perform optimization operations on the data processing of the regions with low acceleration stability;

[0033] If the acceleration stability of the optimized region is within the preset improvement range, preferentially process the tobacco leaf data corresponding to the region with high acceleration stability according to the acceleration stability;

[0034] If the acceleration stability of the optimized region is outside the preset improvement range, process the tobacco leaf data corresponding to the target region in the order of the lowest priority.

[0035] In a second aspect, the present application also provides a tobacco leaf sorting and grading management device based on digital twin. The device includes:

[0036] A digital model construction module, configured to create digital twin models of tobacco leaves and preset sorting and grading equipment, where the digital twin models at least include tobacco leaves and simulation equipment corresponding to the sorting and grading equipment, and the simulation equipment is used to simulate data collection of the sorting and grading equipment;

[0037] An event configuration module, configured to obtain the event content obtained during sorting and grading, where the event content at least includes data collection of tobacco leaves;

[0038] A data processing module, configured to call an event trigger program and transmit the event content to the event trigger program. After the event trigger program obtains the event content, it reads the event trigger conditions corresponding to the event content and determines whether the event content is triggered based on the event content and the event trigger conditions;

[0039] A completed event module, configured to, if the event is triggered, call an event consumption program corresponding to the event content for processing, and generate a data processing completed event after completion.

[0040] In a third aspect, the present application also 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 implemented:

[0041] Create a digital twin model of tobacco leaves and a preset sorting and grading device. The digital twin model at least includes tobacco leaves and a simulation device corresponding to the sorting and grading device. The simulation device is used to simulate the data collection of the sorting and grading device;

[0042] Obtain the event content obtained during sorting and grading. The event content at least includes the data collection of tobacco leaves;

[0043] Call an event trigger program and transmit the event content to the event trigger program. After the event trigger program obtains the event content, it reads the event trigger conditions corresponding to the event content and determines whether the event content is triggered based on the event content and the event trigger conditions;

[0044] If the event is triggered, call the event consumption program corresponding to the event content for processing, and generate a data processing completion event after completion.

[0045] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0046] Create a digital twin model of tobacco leaves and a preset sorting and grading device. The digital twin model at least includes tobacco leaves and a simulation device corresponding to the sorting and grading device. The simulation device is used to simulate the data collection of the sorting and grading device;

[0047] Obtain the event content obtained during sorting and grading. The event content at least includes the data collection of tobacco leaves;

[0048] Call an event trigger program and transmit the event content to the event trigger program. After the event trigger program obtains the event content, it reads the event trigger conditions corresponding to the event content and determines whether the event content is triggered based on the event content and the event trigger conditions;

[0049] If the event is triggered, call the event consumption program corresponding to the event content for processing, and generate a data processing completion event after completion.

[0050] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0051] Create a digital twin model of tobacco leaves and a preset sorting and grading device. The digital twin model at least includes tobacco leaves and a simulation device corresponding to the sorting and grading device, and the simulation device is used to simulate the data collection of the sorting and grading device;

[0052] Obtain the event content obtained during sorting and grading. The event content at least includes the data collection of tobacco leaves;

[0053] Call the event trigger program and transmit the event content to the event trigger program. After the event trigger program obtains the event content, it reads the event trigger conditions corresponding to the event content and determines whether the event content is triggered based on the event content and the event trigger conditions;

[0054] If the event is triggered, call the event consumption program corresponding to the event content for processing, and generate a data processing completion event after completion.

[0055] The above-mentioned tobacco leaf sorting and grading management method, device, computer device, storage medium and computer program product based on digital twin create a digital twin model of tobacco leaves and a preset sorting and grading device. The digital twin model at least includes tobacco leaves and a simulation device corresponding to the sorting and grading device, and the simulation device is used to simulate the data collection of the sorting and grading device; obtain the event content obtained during sorting and grading. The event content at least includes the data collection of tobacco leaves; call the event trigger program and transmit the event content to the event trigger program. After the event trigger program obtains the event content, it reads the event trigger conditions corresponding to the event content and determines whether the event content is triggered based on the event content and the event trigger conditions; if the event is triggered, call the event consumption program corresponding to the event content for processing, and generate a data processing completion event after completion. By adopting the above method, this application makes real-time updates and decisions through an event-driven architecture. During the sorting and grading of tobacco leaves, when new tobacco leaf data is collected, a data collection event is immediately generated and sent. After receiving the event, the event consumer immediately starts processing the data and updating the model, realizing real-time grading decision-making and response; when the tobacco leaf harvest season comes, the data collection volume increases sharply, and the high load can be coped with by increasing the number of event consumers to ensure that the system can efficiently process a large amount of data. During non-peak periods, the number of consumers can be reduced to save resources; simplified system integration, the data collection device, data processing service and model update service communicate through standardized event messages without having to understand each other's internal implementation, simplifying the system integration and maintenance work; by using the event-driven architecture, the tobacco leaf grading management system can quickly respond and update the model when the data changes, improving the real-time performance, scalability and reliability of the system, and at the same time simplifying the system integration and maintenance work. Description of the Drawings

[0056] Figure 1It is an application environment diagram of a tobacco leaf sorting and grading management method based on digital twin in an embodiment;

[0057] Figure 2 It is a flowchart of a tobacco leaf sorting and grading management method based on digital twin in an embodiment;

[0058] Figure 3 It is a structural block diagram of a tobacco leaf sorting and grading management device based on digital twin in an embodiment;

[0059] Figure 4 It is an internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0060] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] The tobacco leaf sorting and grading management method based on digital twin provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be integrated on the server, or placed in the cloud or other network servers. Among them, the terminal can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0062] In one embodiment, as Figure 2 shown, taking the application of this method to the Figure 1 terminal as an example for description, it can be understood that this method can also be applied to the server, and can also be applied to a system including the terminal and the server, and is realized through the interaction between the terminal and the server. In this embodiment, this method includes the following steps:

[0063] Step 202, create digital twin models of tobacco leaves and preset sorting and grading equipment.

[0064] Among them, digital twin technology can simulate the operating state, behavior and performance of a physical entity by creating a virtual model of the physical entity, and can monitor the state of the physical entity in real time for predictive maintenance and optimization.

[0065] Building a digital twin model includes physical entity modeling and virtual sensor modeling. Physical entity modeling: Create digital twin models of tobacco leaves and related equipment, including physical characteristics, operating parameters, and operating status. Virtual sensor: Configure virtual sensors in the digital twin model to simulate data collection by physical sensors. The digital twin model includes at least tobacco leaves and simulation equipment corresponding to the sorting and grading equipment, and the simulation equipment is used to simulate data collection by the sorting and grading equipment.

[0066] Step 204, obtain the event content obtained during sorting and grading.

[0067] Among them, in the embodiments of the present invention, the event publisher specifically refers to the tobacco leaf sorting and grading system. Of course, this method can also be used on other devices, and the embodiments of the present invention do not specifically limit it.

[0068] It means that the information sending of the tobacco leaf sorting and grading system has the following characteristics:

[0069] There are many types of information to be sent, the information differences are large, and the sending quantities and the lengths of single-piece information of various types of information vary greatly;

[0070] The method of the present invention is a tobacco leaf sorting and grading management method based on digital twin, so as to meet the above requirements sent by the tobacco leaf sorting and grading system in the event-driven architecture.

[0071] Step 206, call the event trigger program and transmit the event content to the event trigger program.

[0072] Among them, after the event trigger program obtains the event content, it reads the event trigger conditions corresponding to the event content, and determines whether the event content is triggered based on the event content and the event trigger conditions; if the event is triggered, it calls the event consumption program corresponding to the event content for processing, and generates a data processing completion event after completion; if the event is not triggered, it generates a data processing completion event.

[0073] In the above tobacco leaf sorting and grading management method based on digital twin, real-time updates and decisions are made through an event-driven architecture. During the sorting and grading of tobacco leaves, when new tobacco leaf data is collected, a data collection event is immediately generated and sent. After receiving the event, the event consumer immediately starts processing the data and updating the model, realizing real-time grading decisions and responses. When the tobacco leaf harvesting season arrives and the data collection volume surges, the number of event consumers can be increased to handle the high load, ensuring that the system can efficiently process a large amount of data. During off-peak periods, the number of consumers can be reduced to save resources. Simplified system integration: The data collection device, data processing service, and model update service communicate through standardized event messages without the need to understand each other's internal implementations, simplifying the system integration and maintenance work. By using the event-driven architecture, the tobacco leaf grading management system can quickly respond and update the model when the data changes, improving the real-time performance, scalability, and reliability of the system, while simplifying the system integration and maintenance work.

[0074] In one embodiment, the event consumption program at least includes data processing, model update, and anomaly detection. When the event consumption program is selected for data processing, the specific steps may include:

[0075] When the event consumption program is for data processing, obtain the tobacco leaf data detected by the preset sorting and grading equipment;

[0076] Call the data trigger program and transfer the tobacco leaf data to the event trigger program, and the event trigger program obtains the tobacco leaf data;

[0077] Read that the event trigger condition corresponding to the tobacco leaf data is that the sorting and grading equipment performs a data collection operation;

[0078] Based on the tobacco leaf data and the data collection operation of the sorting and grading equipment, call the data processing event to process the collected data until a data processing completion event is generated after the data processing event is completed.

[0079] In this embodiment, real-time updates and decisions are made through an event-driven architecture. In the sorting and grading of tobacco leaves, when new tobacco leaf data is collected, a data collection event is immediately generated and sent. After receiving the event, the event consumer immediately starts processing the data and updating the model, achieving real-time grading decisions and responses. When the tobacco leaf harvest season arrives and the data collection volume surges, the number of event consumers can be increased to handle the high load, ensuring that the system can efficiently process a large amount of data. During off-peak periods, the number of consumers can be reduced to save resources. Simplified system integration: The data collection device, data processing service, and model update service communicate through standardized event messages without the need to understand each other's internal implementations, simplifying the system integration and maintenance work. By using the event-driven architecture, the tobacco leaf grading management system can quickly respond and update the model when the data changes, improving the real-time performance, scalability, and reliability of the system, while simplifying the system integration and maintenance work.

[0080] In one embodiment, the event consumer program at least includes data processing, model update, and anomaly detection. When the event consumer program is selected for model update, the specific steps may include:

[0081] When the event consumer program is for model update, receive the data processing completion event;

[0082] Obtain the updated tobacco leaf data, where the updated tobacco data is the tobacco leaf data obtained after data processing of the tobacco leaf data detected by the sorting and grading equipment;

[0083] Construct an incremental digital model based on the updated tobacco leaf data and perform incremental training;

[0084] Fuse the incremental digital model with the digital twin model and generate an updated twin model.

[0085] Among them, the continuous update of the model through the incremental learning method involves the following steps and technologies:

[0086] Incremental data collection: First, new data needs to be continuously collected, which can be real-time data streams or batch data updated regularly; Model expansion: Utilize the existing model structure to expand the model by adding new data and features. This can be achieved by adding new layers or nodes to the existing model; Incremental training: Use the incremental dataset to perform incremental training on the expanded model. Incremental training means performing partial training on the existing model using new data instead of training the entire model from scratch; Model fusion: Integrate the model after incremental training with the original model to integrate the newly learned knowledge and patterns; Validation and testing: Validate and test the updated model to ensure its performance on new data meets expectations and maintain the accuracy and generalization ability of the model; Deployment and monitoring: Deploy the updated model to the actual environment and continuously monitor its performance and prediction ability.

[0087] In this embodiment, the digital twin system is updated through incremental learning. After training the updated data through incremental learning and integrating it into the digital twin system, it not only ensures the update of the model but also ensures the adjustment of the model by the new tobacco leaf data.

[0088] In one embodiment, when the event consumption program is anomaly detection, tobacco leaf data is acquired;

[0089] Compare the tobacco leaf data with the preset standard change range;

[0090] If the tobacco leaf data is outside the preset standard change range, acquire the detection environment data related to the tobacco leaf data;

[0091] If the detection environment data is within the preset standard environment range, generate an anomaly detection event.

[0092] In this embodiment, an anomaly detection service is implemented to monitor the data stream in real time, detect abnormal situations, and generate anomaly detection events, and timely correct the problems generated during the data collection process in the digital twin system to improve the stability of the system.

[0093] In one embodiment, considering that during the collection process of tobacco leaf data, there is a situation where the data volume is too large for the system to process in a timely manner, and there is also a harvest period where a large number of immature or mature tobacco leaves need to be judged in a short time. The specific process can be executed as follows:

[0094] Statistical data processing events for the processing time of the collected data;

[0095] If the processing time is within the critical time, perform the processing operation normally;

[0096] If the processing time is outside the critical time, extract the region information corresponding to the tobacco leaf data;

[0097] Perform the same processing operation on the collected data based on the regional information and generate accelerated processing data;

[0098] When the processing time is within the critical time, perform secondary verification processing on the accelerated processing data;

[0099] If the error between the verification data and the accelerated processing data is within the preset range, replace the corresponding accelerated processing data with the verification data;

[0100] If the error between the verification data and the accelerated processing data is outside the preset range, generate an anomaly detection event.

[0101] In this embodiment, first monitor the processing time of the collected data. When the processing time is abnormal, preferentially adopt a unified processing method for the tobacco leaves in the same region. A large number of tobacco leaves in the same region are processed uniformly. Since the environmental factors such as temperature and sunlight irradiation corresponding to the tobacco leaves in the same region do not differ much, the same processing method can be adopted for centralized processing, thereby alleviating the situation where the data volume is too large during the collection process of tobacco leaf data and the system cannot process it in time, thus improving the processing efficiency of the system.

[0102] It is worth mentioning that considering that the accelerated processing methods in different regions may have different error rates of data due to regional differences, for regions with a large error rate, the specific processing method can be:

[0103] Statistically analyze the acceleration stability of different regions, where the acceleration stability is the error between the verification data and the accelerated processing data corresponding to the target region;

[0104] Based on the acceleration stability, preferentially process the tobacco leaf data corresponding to the regions with high acceleration stability;

[0105] Perform optimization operations on the data processing of regions with low acceleration stability;

[0106] If the acceleration stability of the optimized region is within the preset improvement range, preferentially process the tobacco leaf data corresponding to the regions with high acceleration stability according to the acceleration stability;

[0107] If the acceleration stability of the optimized region is outside the preset improvement range, process the tobacco leaf data corresponding to the target region in the order of the lowest priority.

[0108] In this embodiment, the processing priority of different regions is determined by calculating the acceleration stability. For regions with poor acceleration stability, the calculation resources can be accumulated and then calculated through a lag processing method, thereby improving the accuracy of the tobacco leaf data in regions with poor acceleration stability.

[0109] In this embodiment, the above method is adopted, and real-time update and decision-making are carried out through an event-driven architecture. In the sorting and grading of tobacco leaves, when new tobacco leaf data is collected, a data collection event is immediately generated and sent. After receiving the event, the event consumer immediately starts processing the data and updating the model, realizing real-time grading decision-making and response. When the tobacco leaf harvest season comes, the data collection volume surges, and the high load can be handled by increasing the number of event consumers to ensure that the system can efficiently process a large amount of data. During the off-peak period, the number of consumers can be reduced to save resources. The simplified system integration enables communication between the data collection device, the data processing service, and the model update service through standardized event messages without the need to understand each other's internal implementations, simplifying the system integration and maintenance work. By using the event-driven architecture, the tobacco leaf grading management system can quickly respond and update the model when the data changes, improving the real-time performance, scalability, and reliability of the system, while simplifying the system integration and maintenance work.

[0110] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0111] Based on the same inventive concept, the embodiments of the present application also provide a digital twin-based tobacco leaf sorting and grading management device for implementing the above-mentioned digital twin-based tobacco leaf sorting and grading management method. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more of the following embodiments of the digital twin-based tobacco leaf sorting and grading management device can refer to the limitations on the digital twin-based tobacco leaf sorting and grading management method in the above text, and will not be repeated here.

[0112] In one embodiment, as Figure 3 shown, a digital twin-based tobacco leaf sorting and grading management device is provided, including: a digital model construction module, an event configuration module, a data processing module, a completion event module, and an event consumption processing module, where:

[0113] A digital model construction module for creating a digital twin model of tobacco leaves and a preset sorting and grading device. The digital twin model at least includes tobacco leaves and a simulated device corresponding to the sorting and grading device, and the simulated device is used to simulate the data collection of the sorting and grading device;

[0114] An event configuration module for obtaining the event content obtained during sorting and grading. The event content at least includes the data collection of tobacco leaves;

[0115] A data processing module for calling an event trigger program and transmitting the event content to the event trigger program. After the event trigger program obtains the event content, it reads the event trigger conditions corresponding to the event content and determines whether the event content is triggered based on the event content and the event trigger conditions;

[0116] A completed event module for, if the event is triggered, calling an event consumption program corresponding to the event content for processing and generating a data processing completed event after completion.

[0117] In one embodiment, the event consumption processing module is further configured to: when the event consumption program is data processing, obtain the tobacco leaf data detected by the preset sorting and grading device; call a data trigger program and transmit the tobacco leaf data to the event trigger program. After the event trigger program obtains the tobacco leaf data, it reads the event trigger condition corresponding to the tobacco leaf data as a data collection operation of the sorting and grading device; based on the tobacco leaf data and the data collection operation of the sorting and grading device, call a data processing event to process the collected data until a data processing completed event is generated after the data processing event is completed.

[0118] In one embodiment, the event consumption update module is further configured to: when the event consumption program is model update, receive the data processing completed event; obtain updated tobacco leaf data, where the updated tobacco data is the tobacco leaf data obtained after the tobacco leaf data detected by the sorting and grading device is processed; construct an incremental digital model based on the updated tobacco leaf data and perform incremental training; fuse the incremental digital model with the digital twin model and generate an updated twin model.

[0119] In one embodiment, the event consumption exception module is further configured to: when the event consumption program is exception detection, obtain the tobacco leaf data; compare the tobacco leaf data with a preset standard change range; if the tobacco leaf data is outside the preset standard change range, obtain the detection environment data related to the tobacco leaf data; if the detection environment data is within the preset standard environment range, generate an exception detection event.

[0120] In one embodiment, the event consumption anomaly module is further configured to: call a data processing event to process the collected data, including: counting the processing time of the data processing event for the collected data; if the processing time is outside the critical time, extracting the regional information corresponding to the tobacco leaf data; performing the same processing operation on the collected data based on the regional information and generating accelerated processing data; when the processing time is within the critical time, performing secondary verification processing on the accelerated processing data; if the error between the verification data and the accelerated processing data is within the preset range, replacing the corresponding accelerated processing data with the verification data; if the error between the verification data and the accelerated processing data is outside the preset range, generating an anomaly detection event.

[0121] In one embodiment, the event consumption anomaly module is further configured to: count the acceleration stability of different regions, where the acceleration stability is the error between the verification data and the accelerated processing data corresponding to the target region; based on the acceleration stability, preferentially process the tobacco leaf data corresponding to the region with high acceleration stability; perform an optimization operation on the data processing of the region with low acceleration stability; if the acceleration stability of the optimized region is within the preset improvement range, preferentially process the tobacco leaf data corresponding to the region with high acceleration stability according to the acceleration stability; if the acceleration stability of the optimized region is outside the preset improvement range, process the tobacco leaf data corresponding to the target region in the order of the lowest priority.

[0122] Each module in the above tobacco leaf sorting and grading management device based on digital twin can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0123] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, 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 the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network 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, it implements a method for managing tobacco leaf sorting and grading based on digital twin.

[0124] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 4As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, 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 and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for managing tobacco leaf sorting and grading based on digital twins.

[0125] Those skilled in the art can understand that Figure 4 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0126] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0127] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0128] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0129] 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 for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0130] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing 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 embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0131] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope described in this specification.

[0132] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A tobacco leaf sorting and grading management method based on digital twins, characterized in that: The method comprises: Creating a digital twin model of tobacco leaves and a preset sorting and grading device, wherein the digital twin model includes at least tobacco leaves and a simulation device corresponding to the sorting and grading device, wherein the simulation device is used to simulate data collection of the sorting and grading device; Acquiring event content obtained during sorting and grading, wherein the event content at least includes data collection of tobacco leaves; Calling an event triggering program and transmitting the event content to the event triggering program, after the event triggering program obtains the event content, reading the event triggering condition corresponding to the event content, and determining whether the event content is triggered based on the event content and the event triggering condition; If an event is triggered, the event consumer program corresponding to the event content is called for processing, and a data processing completion event is generated after completion; When the event consumer updates the model, it receives the data processing completion event; Acquire updated tobacco leaf data, where the updated tobacco leaf data is tobacco leaf data obtained after data processing of tobacco leaf data detected by the sorting and grading equipment; Build incremental digital models based on updated tobacco leaf data and perform incremental training; Acquire incremental data, where the incremental data is a real-time data stream or regularly updated batch data; Based on the existing model structure, add new data and features to expand the model; Use the incremental dataset to incrementally train the expanded model; Fuse the incremental digital model with the digital twin model and generate an updated twin model; When the event consumption program is data processing, the tobacco leaf data detected by the preset sorting and grading equipment is obtained; Calling a data triggering program and transmitting tobacco leaf data to an event triggering program, wherein the event triggering program obtains the tobacco leaf data; Counting the acceleration stability of different regions, where the acceleration stability is the error between the verification data and the acceleration processing data corresponding to the target region; Based on the acceleration stability, tobacco leaf data corresponding to the areas with high acceleration stability are processed first; Optimize data processing in areas with low acceleration stability; If the acceleration stability of the optimized region is within the preset improvement range, the tobacco leaf data corresponding to the region with high acceleration stability will be processed first according to the acceleration stability; If the acceleration stability of the optimized area is outside the preset improvement range, the tobacco leaf data corresponding to the target area is processed in the order of the lowest priority; the event trigger condition corresponding to the tobacco leaf data is read to perform data collection operations for the sorting and grading equipment; Data collection operations are performed based on tobacco leaf data and sorting and grading equipment, and data processing events are called to process the collected data until a data processing completion event is generated after the data processing event is completed.

2. The method according to claim 1, characterized in that: The method further comprises: When the event consumer is anomaly detection, obtain tobacco leaf data; Compare tobacco leaf data with a preset standard variation range; If the tobacco leaf data is outside the preset standard variation range, obtaining detection environment data related to the tobacco leaf data; If the detection environment data is within the preset standard environment range, an abnormal detection event is generated.

3. The method according to claim 2, characterized in that The calling of the data processing event to process the collected data includes: The processing time of the collected data by the statistical data processing event; If the processing time is outside the critical time, the regional information corresponding to the tobacco leaf data is extracted; Perform the same processing operation on the collected data based on the regional information and generate accelerated processing data; When the processing time is within the critical time, the accelerated processing data is subjected to secondary verification; If the error between the verification data and the accelerated processing data is within a preset range, the verification data replaces the corresponding accelerated processing data; If the error between the verification data and the accelerated processing data is outside a preset range, an abnormal detection event is generated.

4. A tobacco leaf sorting and grading management device based on digital twin as claimed in claim 1, characterized in that: The device comprises: A digital model building module, used to create a digital twin model of tobacco leaves and a preset sorting and grading device, wherein the digital twin model at least includes tobacco leaves and a simulation device corresponding to the sorting and grading device, wherein the simulation device is used to simulate data collection of the sorting and grading device; An event configuration module, used to obtain event content obtained during sorting and grading, wherein the event content at least includes data collection of tobacco leaves; A data processing module is used to call an event triggering program and transmit the event content to the event triggering program. After the event triggering program obtains the event content, it reads the event triggering condition corresponding to the event content and determines whether the event content is triggered based on the event content and the event triggering condition; The completion event module is used to call the event consumer program corresponding to the event content for processing if an event is triggered, and generate a data processing completion event after completion.

5. 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 method according to any one of claims 1 to 3 are implemented.

6. 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 method according to any one of claims 1 to 3 are implemented.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images