Tobacco leaf detection data management method and system based on near infrared spectrometer and medium

Abstract

The invention provides a tobacco leaf detection data management system, method and device based on a near infrared spectrometer, a medium and a client. The system, method and device are used for sending collected tobacco leaf detection data and a data processing request to an edge computing node; the edge computing node is used for preprocessing the data processing request, the tobacco leaf detection data and the real-time analysis result, and performing real-time analysis by using a machine learning algorithm; the master control server is used for summarizing and globally analyzing the real-time analysis results, acquiring a configuration file associated with the real-time analysis results to determine an operation type corresponding to the data processing request, and executing corresponding operation processing on the real-time analysis results based on the operation type; and the data server is used for storing the data processing request, the tobacco leaf detection data and the real-time analysis result sent by the client, the edge computing node and the master control server so as to solve the technical problem that the detection data generated by detecting whether the tobacco leaves are mildewed or not by the near-infrared spectrometer cannot be efficiently processed.

Description

Technical Field

[0001] The present invention relates to the technical field of tobacco leaf detection, and in particular to a tobacco leaf detection data management system, method, equipment and medium based on a near-infrared spectrometer. Background Art

[0002] As a special leaf plant, tobacco leaves are easily contaminated by mold in the air. Mycotoxins such as aflatoxin, which are the products of mold metabolism, are highly carcinogenic and have an impact on human health. They also cause huge problems and economic losses to the production and manufacturing of cigarette industry enterprises.

[0003] To detect moldy tobacco leaves, existing technologies primarily rely on sensory testing, sensory flat-sniffing, and microbial counting. These methods lack accurate evaluation criteria, are time-consuming and labor-intensive, and offer limited assurance of detection results. Near-infrared (NIR) light is an electromagnetic radiation wave between visible light (VIS) and mid-infrared (MIR). The American Society for Testing and Materials (ASTM) defines the NIR spectral region as 780-2526 nm, the first non-visible region discovered in absorption spectra. The NIR spectral region coincides with the absorption regions of the combined frequency and harmonic harmonics of hydrogen-containing groups (OH, NH, CH) in organic molecules. By scanning the NIR spectrum of a sample, characteristic information about the hydrogen-containing groups in the organic molecules can be obtained. Therefore, a tobacco leaf detection method based on a NIR spectrometer is proposed that is convenient, rapid, efficient, accurate, and low-cost, and that performs detection without destroying the sample, consuming chemical reagents, or polluting the environment. However, the existing technology lacks a system for efficiently managing NIR spectrometer data.

[0004] Therefore, it is urgent to propose a tobacco leaf inspection data management system based on near-infrared spectrometer. Summary of the Invention

[0005] In order to overcome the problems existing in the related art, the present disclosure provides a tobacco leaf detection data management system, method, equipment and medium based on a near-infrared spectrometer to solve the technical problems of chaotic near-infrared spectrometer data management and low efficiency in the related art.

[0006] One or more embodiments of this specification provide a tobacco leaf detection data management system based on a near-infrared spectrometer, including a client, an edge computing node, a master control server, and a data server, which communicate with each other via a network, wherein:

[0007] The client is used to send the tobacco leaf detection data collected by the near-infrared spectrometer and the data processing request to the edge computing node;

[0008] an edge computing node, configured to pre-process the data processing request, tobacco leaf detection data, and real-time analysis results according to the data processing request, perform real-time analysis using a machine learning algorithm, and send the real-time analysis results to a master control server;

[0009] a main control server, configured to aggregate and globally analyze the real-time analysis results, access corresponding storage space, obtain a configuration file associated with the real-time analysis results, parse the configuration file to determine an operation type corresponding to the data processing request, and perform corresponding operation processing on the real-time analysis results based on the operation type;

[0010] A data server is used to store the data processing requests, tobacco leaf detection data and real-time analysis results sent by the client, edge computing node and main control server.

[0011] Preferably, the edge computing nodes are distributed at each tobacco leaf detection collection point, and are specifically configured as follows:

[0012] Preliminarily processing and filtering the data processing request, tobacco leaf detection data, and real-time analysis results according to the data processing request;

[0013] Utilizing a machine learning algorithm to perform real-time analysis on the data processing request, tobacco leaf testing data, and real-time analysis results, identify key indicators such as tobacco leaf quality, moisture, and chemical composition, and generate an analysis report;

[0014] The analysis report and the data processing request are compressed and encrypted and then sent to the main control server.

[0015] Preferably, the edge computing node is further configured to cache configuration files, data processing logic, and model parameters of the machine learning algorithm.

[0016] Preferably, the main control server is configured as follows:

[0017] Parsing the configuration file to obtain a file management permission list corresponding to the real-time analysis result;

[0018] Obtaining identity authentication information of the user who initiated the data processing request or tobacco leaf testing data;

[0019] Compare the file management permission list with the identity authentication information of the initiator user to confirm the operation permission;

[0020] Based on the confirmation of the operation authority, the operation type corresponding to the real-time analysis result is determined.

[0021] Preferably, the master control server is further used to coordinate task allocation among multiple edge nodes and share computing resources among multiple edge nodes.

[0022] Preferably, the operation types include viewing, querying, resetting, comparing, creating, modifying, deleting, enabling, disabling, importing near-infrared spectrum coding, importing near-infrared inspection results, importing near-infrared data, saving and closing.

[0023] One or more embodiments of this specification provide a tobacco leaf detection data management method based on a near-infrared spectrometer:

[0024] The following steps are involved:

[0025] Send the tobacco leaf detection data collected by the near-infrared spectrometer and the data processing request to the edge computing node;

[0026] pre-processing the data processing request, tobacco leaf detection data, and real-time analysis results according to the data processing request, and performing real-time analysis using a machine learning algorithm;

[0027] Aggregating and globally analyzing the real-time analysis results, accessing corresponding storage space, obtaining a configuration file associated with the real-time analysis results, parsing the configuration file to determine an operation type corresponding to the data processing request, and performing corresponding operation processing on the real-time analysis results based on the operation type;

[0028] The data processing request, tobacco leaf detection data and real-time analysis results are stored.

[0029] Preferably, the edge computing nodes are distributed at each tobacco leaf detection collection point, specifically including the following steps:

[0030] Preliminarily processing and filtering the data processing request, tobacco leaf detection data, and real-time analysis results according to the data processing request;

[0031] Utilizing a machine learning algorithm to perform real-time analysis on the data processing request, tobacco leaf testing data, and real-time analysis results, identify key indicators such as tobacco leaf quality, moisture, and chemical composition, and generate an analysis report;

[0032] The analysis report and the data processing request are compressed and encrypted and then sent to the main control server.

[0033] One or more embodiments of the present specification provide a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned tobacco leaf detection data management method based on a near-infrared spectrometer is implemented.

[0034] One or more embodiments of the present specification provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned tobacco leaf detection data management method based on near-infrared spectrometer.

[0035] The present disclosure provides a tobacco leaf detection data management system, method, device and medium based on a near-infrared spectrometer, which has the advantages that, through a client, the tobacco leaf detection data and data processing request collected by the near-infrared spectrometer are sent to an edge computing node, which effectively shortens the data transmission distance, reduces latency, enables data to quickly enter the processing flow, alleviates network congestion, and ensures the stable operation of the system under high data traffic; the edge computing node is used to pre-process the data processing request, tobacco leaf detection data and real-time analysis results according to the data processing request, and uses a machine learning algorithm for real-time analysis, which can more accurately identify the quality, composition and other information of the tobacco leaf, reduce the load of the main control server, and improve the computing efficiency of the overall system; the main control server is used to send the real-time analysis Results are aggregated and globally analyzed, corresponding storage space is accessed, configuration files associated with the real-time analysis results are obtained, the configuration files are parsed to determine the operation type corresponding to the data processing request, and corresponding operation processing is performed on the real-time analysis results based on the operation type. By aggregating and globally analyzing the real-time results and determining the operation type in combination with the configuration files, tobacco leaf data is comprehensively evaluated from macro and micro levels, and the value behind the data is deeply explored, providing comprehensive and in-depth decision-making basis for tobacco leaf planting, processing, sales and other links; a data server is used to store the data processing requests, tobacco leaf detection data and real-time analysis results, reducing the security risks of data during network transmission. At the same time, local encryption, access control and other security measures can be taken to ensure data security and privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A schematic diagram of the structure of a tobacco leaf detection data management system based on a near-infrared spectrometer provided in one or more embodiments of this specification;

[0038] Figure 2 View historical price pages provided for one or more embodiments of this specification;

[0039] Figure 3 A comparison page for viewing evaluation information provided for one or more embodiments of this specification;

[0040] Figure 4 A query page provided for one or more embodiments of this specification;

[0041] Figure 5 A reset page provided for one or more embodiments of this specification;

[0042] Figure 6 A new page provided for one or more embodiments of this specification;

[0043] Figure 7 An editing page provided for one or more embodiments of this specification;

[0044] Figure 8 An operation viewing page provided for one or more embodiments of this specification;

[0045] Figure 9 A viewing page provided for one or more embodiments of this specification;

[0046] Figure 10 A modification page is provided for one or more embodiments of this specification;

[0047] Figure 11 An editing page provided for one or more embodiments of this specification;

[0048] Figure 12 Deleted pages provided for one or more embodiments of this specification;

[0049] Figure 13 A deletion confirmation page provided for one or more embodiments of this specification;

[0050] Figure 14 An activation page provided for one or more embodiments of this specification;

[0051] Figure 15 A confirmation page for enabling one or more embodiments of this specification;

[0052] Figure 16 A deactivation page provided for one or more embodiments of this specification;

[0053] Figure 17 A deactivation confirmation page provided for one or more embodiments of this specification;

[0054] Figure 18 A schematic flow chart of a tobacco leaf detection data management method based on a near-infrared spectrometer provided in one or more embodiments of this specification;

[0055] Figure 19 A schematic diagram of the structure of a computer device provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0056] In order to help those skilled in the art better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this invention.

[0057] The main purpose of the present invention is to view the basic attribute information of tobacco leaves and the unit price information of tobacco leaves in the financial system for subsequent raw material-related functions, the data processing request, tobacco leaf detection data and real-time analysis results for subsequent functions such as recycled tobacco leaf demand calculation and formula formulation, view tobacco stem data information for subsequent functions such as tobacco stem procurement demand calculation, maintain the use value coefficient of tobacco leaves for evaluating the use value of single-material tobacco, maintain and view the near-infrared spectral data of tobacco leaves in the infrared spectrometer, mainly including 72 chemical components of tobacco leaves, for digital formula design, the input data of the model and the user selects the query conditions according to needs, the system will query the data according to the query conditions and display it in a list.

[0058] The present invention will be described in detail below with reference to specific implementation methods and the accompanying drawings.

[0059] System Example

[0060] According to an embodiment of the present invention, a tobacco leaf detection data management system based on a near-infrared spectrometer is provided. Figure 1 As shown in FIG. 1 , a schematic diagram of the structure of a tobacco leaf detection data management system based on a near-infrared spectrometer provided in this embodiment is provided. According to the tobacco leaf detection data management system based on a near-infrared spectrometer in this embodiment of the present invention, the client 10, the edge computing node 20, the master control server 30, and the data server 40 communicate with each other through a network, wherein:

[0061] The client 10 is used to send the tobacco leaf detection data collected by the near-infrared spectrometer and the data processing request to the edge computing node.

[0062] The edge computing node 20 is used to pre-process the data processing request, tobacco leaf detection data and real-time analysis results according to the data processing request, perform real-time analysis using a machine learning algorithm, and send the real-time analysis results to the main control server.

[0063] The main control server 30 is used to summarize and globally analyze the real-time analysis results, access the corresponding storage space, obtain the configuration file associated with the real-time analysis results, parse the configuration file to determine the operation type corresponding to the data processing request, and perform corresponding operation processing on the real-time analysis results based on the operation type, wherein the operation types include viewing, querying, resetting, comparing, creating, modifying, deleting, enabling, disabling, importing near-infrared spectral encoding, importing near-infrared inspection results, importing near-infrared data, saving and closing.

[0064] The data server 40 is used to store the data processing requests, tobacco leaf detection data and real-time analysis results sent by the client, edge computing node and main control server.

[0065] The client 10 is also used to display the result of the operation processing.

[0066] The following is an explanation using specific examples:

[0067] Cigarette Information

[0068] View historical prices: Select any data and click the "View historical prices" button. The system will pop up the "View historical prices" page for this data. The data on this page can only be viewed, and cannot be modified or saved. Compare evaluation information: Select any data and click the "Compare evaluation information" button. The system will pop up the "Compare evaluation information" interface for this data. The data on this page can only be viewed, and cannot be modified or saved. Figure 2 As shown, this is the page for viewing historical prices provided in this embodiment.

[0069] Evaluation information comparison: System operation role: Formula Research Laboratory of the company's technology R&D center.

[0070] The steps are as follows:

[0071] Select any data and click the "Evaluation Information Comparison" button. The system will pop up the "Evaluation Information Comparison" interface for this data. The data on this page can only be viewed and cannot be modified or saved.

[0072] like Figure 3 As shown, this is the evaluation information comparison page provided in this embodiment.

[0073] Query: System operation role: Formula Research Laboratory of the company's technical R&D center.

[0074] The steps are as follows:

[0075] After entering the page, the user selects the query conditions as needed and clicks the query button. The system will query the data based on the query conditions and display it in the list.

[0076] like Figure 4 As shown, this is the query page provided by this embodiment.

[0077] Click the "Query" button.

[0078] Reset: System operation role: Formula Research Laboratory of the company's technology research and development center.

[0079] The steps are as follows:

[0080] After clicking the Reset button, the system will restore the query condition area to the default data.

[0081] like Figure 5 As shown, this is the reset page provided in this embodiment.

[0082] Click the Reset button.

[0083] 2. Use value and coefficient

[0084] Newly built: System operation role: Formula research laboratory of the company's technology research and development center.

[0085] The steps are as follows:

[0086] Click the "New" button and the system will open a new page. Items marked with a red * are required. After entering the corresponding data, click the Save button to complete the data saving.

[0087] like Figure 6 As shown, this is the new page provided in this embodiment.

[0088] Click the "New" button.

[0089] like Figure 7 As shown, this is the editing page provided in this embodiment.

[0090] View: System operation role: Formula Research Laboratory of the company's technology research and development center.

[0091] The steps are as follows:

[0092] Click the "View" button in the operation area on the right side of the data row, and the system will pop up the "View Page" of this data. The data on this page can only be viewed and cannot be modified, saved, or operated.

[0093] like Figure 8 As shown, this is the operation viewing page provided in this embodiment.

[0094] Click the "View" button.

[0095] like Figure 9 As shown, this is the viewing page provided in this embodiment.

[0096] Modification: System operation role: Formula Research Laboratory of the company's technology R&D center.

[0097] The steps are as follows:

[0098] Select a data whose enabling status is "No", click the "Modify" button in the operation area on the right side of the data row, and the system will open the editing page for this data. The user can modify the corresponding data item content as needed. After the modification is completed, click the Save button to complete the data saving.

[0099] like Figure 10 As shown, this is the modification page provided in this embodiment.

[0100] Click the "Edit" button:

[0101] like Figure 11 As shown, this is the editing page provided in this embodiment.

[0102] Delete: System operation role: Formula Research Laboratory of the company's technical R&D center.

[0103] The steps are as follows:

[0104] Select a data whose enabling status is "No", click the "Delete" button in the operation area on the right side of the data row, and the system will pop up a "Delete" confirmation window. The user clicks "Yes" to complete the deletion of this data.

[0105] like Figure 12 As shown, this is the deletion page provided in this embodiment.

[0106] Click the Delete button.

[0107] like Figure 13 As shown, this is the deletion confirmation page provided in this embodiment.

[0108] Enable: System operation role: Formula Research Laboratory of the company's technology research and development center.

[0109] The steps are as follows:

[0110] Select a data whose activation status is "No", click the "Enable" button, the system will pop up the "Enable" window, and the user clicks "Yes" to complete the activation of this data.

[0111] like Figure 14 As shown, this is the activation page provided in this embodiment.

[0112] Select a data whose enable status is "No" and click the "Enable" button.

[0113] like Figure 15 As shown, this is the activation confirmation page provided in this embodiment.

[0114] Deactivated: System operation role: Formula Research Laboratory of the company's technology R&D center.

[0115] The steps are as follows:

[0116] Select a data whose activation status is "Yes", click the "Disable" button, and the system will pop up a "Do you want to disable" confirmation window. The user clicks "Yes" to complete the deactivation of this data.

[0117] like Figure 16 As shown, this is the deactivation page provided in this embodiment.

[0118] Select a data whose activation status is "Yes" and click the "Disable" button.

[0119] like Figure 17 As shown, this is the deactivation confirmation page provided in this embodiment.

[0120] The system provided in this embodiment is used to send the tobacco leaf detection data and data processing requests collected by the near-infrared spectrometer to the edge computing node through the client 10, which effectively shortens the data transmission distance, reduces the delay, enables the data to quickly enter the processing flow, alleviates network congestion, and ensures the stable operation of the system under high data traffic; the edge computing node 20 is used to pre-process the data processing request, tobacco leaf detection data and real-time analysis results according to the data processing request, and uses machine learning algorithms to perform real-time analysis, which can more accurately identify the quality, composition and other information of the tobacco leaves, reduce the load of the main control server, and improve the computing efficiency of the entire system; the main control server 30 is used to summarize and globally analyze the real-time analysis results, access the corresponding storage space, obtains a configuration file associated with the real-time analysis result, parses the configuration file to determine the operation type corresponding to the data processing request, performs corresponding operation processing on the real-time analysis result based on the operation type, summarizes and globally analyzes the real-time results, and determines the operation type in combination with the configuration file, comprehensively evaluates the tobacco data from macro and micro levels, deeply explores the value behind the data, and provides comprehensive and in-depth decision-making basis for tobacco planting, processing, sales and other links; data server 40 is used to store the data processing request, tobacco detection data and real-time analysis results, reducing the security risk of data during network transmission, and at the same time, local encryption, access control and other security measures can be taken to ensure data security and privacy.

[0121] In one embodiment, the edge computing nodes 20 are distributed at each tobacco leaf detection collection point, and are specifically configured as follows:

[0122] The data processing request, tobacco leaf detection data and real-time analysis results are preliminarily processed and filtered according to the data processing request, thereby reducing frequent access to the main control server and improving the overall response speed of the system.

[0123] An AI real-time analysis module is integrated into the edge computing node 20, and a machine learning algorithm is used to perform real-time analysis on the data processing request, tobacco leaf detection data, and real-time analysis results, identify key indicators such as tobacco leaf quality, moisture, and chemical composition, and generate an analysis report. Through AI real-time analysis, the system can detect abnormal data or potential problems in advance before uploading the data to the main control server 30, thereby reducing the burden of subsequent data processing.

[0124] The analysis report and the data processing request are compressed and encrypted and then sent to the main control server 30 .

[0125] The system provided in this embodiment improves data quality through preliminary processing and filtering, reduces transmission volume and server pressure, and improves processing efficiency. It uses machine learning algorithms to accurately identify key indicators of tobacco leaves, generates intuitive reports to assist decision-making, reduces costs through compression, ensures data security through encryption, realizes centralized data management, and can flexibly adapt to different business needs.

[0126] In one embodiment, the edge computing node 20 is further configured to cache configuration files, data processing logic, and model parameters of the machine learning algorithm.

[0127] The system provided in this embodiment can reduce requests to the main controller by caching key resources, process data in real time, reduce resource usage of the main controller, and enhance the security of sensitive data.

[0128] In one embodiment, the master server 30 is configured as follows:

[0129] Parse the configuration file to obtain a file management permission list corresponding to the real-time analysis result.

[0130] Obtain the identity authentication information of the user who initiated the data processing request or tobacco leaf testing data.

[0131] The file management permission list is compared with the identity authentication information of the initiator user to confirm the operation permission.

[0132] Based on the confirmation of the operation authority, the operation type corresponding to the real-time analysis result is determined.

[0133] The system provided in this embodiment prevents unauthorized access by checking the file management permission list and user identity authentication information, ensures the security of data such as real-time analysis results, determines the operation type based on the permission confirmation result, standardizes the operation process of data processing requests and tobacco leaf inspection data, and improves the orderliness of system operation.

[0134] In one embodiment, the master control server 30 is further configured to coordinate task allocation among multiple edge nodes and share computing resources among multiple edge nodes.

[0135] The system provided in this embodiment improves the efficiency, flexibility and reliability of the system through the task allocation and resource sharing functions of the main control server 30, while optimizing resource utilization and real-time response capabilities.

[0136] Method Example

[0137] According to an embodiment of the present invention, a tobacco leaf detection data management method based on a near-infrared spectrometer is provided. Figure 18 FIG. 1 is a flow chart of a tobacco leaf detection data management method based on a near-infrared spectrometer according to an embodiment of the present invention. The tobacco leaf detection data management method based on a near-infrared spectrometer according to an embodiment of the present invention includes:

[0138] Step 21: Send the collected tobacco leaf detection data and data processing request from the near-infrared spectrometer to the edge computing node.

[0139] Step 22: pre-process the data processing request, tobacco leaf detection data, and real-time analysis results according to the data processing request, and perform real-time analysis using a machine learning algorithm.

[0140] Step 23: Summarize and globally analyze the real-time analysis results, access the corresponding storage space, obtain the configuration file associated with the real-time analysis results, parse the configuration file to determine the operation type corresponding to the data processing request, and perform corresponding operation processing on the real-time analysis results based on the operation type.

[0141] Step 24: Store the data processing request, tobacco leaf detection data, and real-time analysis results.

[0142] The method provided in this embodiment effectively shortens the data transmission distance and reduces the delay by sending the tobacco leaf detection data and data processing request collected by the near-infrared spectrometer to the edge computing node, so that the data can quickly enter the processing flow, alleviate network congestion, and ensure the stable operation of the system under high data traffic; the data processing request, tobacco leaf detection data and real-time analysis results are pre-processed according to the data processing request, and real-time analysis is performed using a machine learning algorithm, which can more accurately identify the quality, composition and other information of the tobacco leaves, reduce the load of the main control server, and improve the computing efficiency of the entire system; the real-time analysis results are summarized and globally analyzed, and the corresponding storage space is accessed to obtain The configuration file associated with the real-time analysis result is parsed to determine the operation type corresponding to the data processing request, and corresponding operation processing is performed on the real-time analysis result based on the operation type. By summarizing and globally analyzing the real-time results and determining the operation type in combination with the configuration file, the tobacco leaf data is comprehensively evaluated from macro and micro levels, and the value behind the data is deeply explored to provide a comprehensive and in-depth decision-making basis for tobacco leaf planting, processing, sales and other links; the data processing request, tobacco leaf detection data and real-time analysis results are stored, reducing the security risk of data during network transmission. At the same time, local encryption, access control and other security measures can be adopted to ensure the security and privacy of the data.

[0143] In one embodiment, edge computing nodes are distributed at each tobacco leaf detection collection point, specifically including the following steps:

[0144] The data processing request, tobacco leaf detection data and real-time analysis results are preliminarily processed and filtered according to the data processing request.

[0145] The data processing request, tobacco leaf inspection data and real-time analysis results are analyzed in real time using a machine learning algorithm to identify key indicators such as tobacco leaf quality, moisture, and chemical composition, and generate an analysis report.

[0146] The analysis report and the data processing request are compressed and encrypted and then sent to the main control server.

[0147] The method provided in this embodiment improves data quality through preliminary processing and filtering, reduces transmission volume and server pressure, and improves processing efficiency. It uses machine learning algorithms to accurately identify key indicators of tobacco leaves, generates intuitive reports to assist in decision-making, reduces costs through compression, ensures data security through encryption, realizes centralized data management, and can flexibly adapt to different business needs.

[0148] The embodiment of the present invention is a method embodiment corresponding to the above-mentioned system embodiment. The specific operations of the processing steps of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0149] like Figure 19 As shown, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the tobacco leaf detection data management method based on a near-infrared spectrometer in the above-mentioned embodiment, or, when executed by a processor, implements the tobacco leaf detection data management method based on a near-infrared spectrometer in the above-mentioned embodiment.

[0150] 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 embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0151] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, refer to the partial description of the method embodiments. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. A person of ordinary skill in the art can understand and implement it without making any creative efforts.

[0152] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and the contents not described in detail in the specification of the present invention are common knowledge to those skilled in the art.

Claims

1. A tobacco leaf detection data management system based on near infrared spectrometer, characterized in that: It includes the client, edge computing node, master server and data server, which communicate with each other through the network. The client is used to send the tobacco leaf detection data collected by the near-infrared spectrometer and the data processing request to the edge computing node; an edge computing node, configured to pre-process the data processing request, tobacco leaf detection data, and real-time analysis results according to the data processing request, perform real-time analysis using a machine learning algorithm, and send the real-time analysis results to a master control server; a main control server, configured to aggregate and globally analyze the real-time analysis results, access corresponding storage space, obtain a configuration file associated with the real-time analysis results, parse the configuration file to determine an operation type corresponding to the data processing request, and perform corresponding operation processing on the real-time analysis results based on the operation type; A data server is used to store the data processing requests, tobacco leaf detection data and real-time analysis results sent by the client, edge computing node and main control server.

2. The tobacco leaf detection data management system according to claim 1, wherein: The edge computing nodes are distributed at each tobacco leaf detection collection point, and the specific configuration is as follows: Preliminarily processing and filtering the data processing request, tobacco leaf detection data, and real-time analysis results according to the data processing request; Utilizing a machine learning algorithm to perform real-time analysis on the data processing request, tobacco leaf testing data, and real-time analysis results, identify key indicators such as tobacco leaf quality, moisture, and chemical composition, and generate an analysis report; The analysis report and the data processing request are compressed and encrypted and then sent to the main control server.

3. The tobacco leaf detection data management system according to claim 1, wherein: The edge computing node is also configured to cache configuration files, data processing logic, and model parameters of the machine learning algorithm.

4. The tobacco leaf detection data management system according to claim 1, wherein: The master server is configured as follows: Parsing the configuration file to obtain a file management permission list corresponding to the real-time analysis result; Obtaining identity authentication information of the user who initiated the data processing request or tobacco leaf testing data; Compare the file management permission list with the identity authentication information of the initiator user to confirm the operation permission; Based on the confirmation of the operation authority, the operation type corresponding to the real-time analysis result is determined.

5. The tobacco leaf detection data management system according to claim 1, wherein: The master control server is also used to coordinate task allocation among multiple edge nodes and share computing resources among multiple edge nodes.

6. The tobacco leaf detection data management system according to claim 1, wherein: The operation types include viewing, querying, resetting, comparing, creating, modifying, deleting, enabling, disabling, importing near-infrared spectrum coding, importing near-infrared inspection results, importing near-infrared data, saving and closing.

7. A tobacco leaf detection data management method based on near-infrared spectrometer, characterized in that: The following steps are involved: Send the tobacco leaf detection data collected by the near-infrared spectrometer and the data processing request to the edge computing node; pre-processing the data processing request, tobacco leaf detection data, and real-time analysis results according to the data processing request, and performing real-time analysis using a machine learning algorithm; Aggregating and globally analyzing the real-time analysis results, accessing corresponding storage space, obtaining a configuration file associated with the real-time analysis results, parsing the configuration file to determine an operation type corresponding to the data processing request, and performing corresponding operation processing on the real-time analysis results based on the operation type; The data processing request, tobacco leaf detection data and real-time analysis results are stored.

8. The tobacco leaf detection data management method according to claim 7, wherein: The edge computing nodes are distributed at each tobacco leaf detection collection point, specifically including the following steps: Preliminarily processing and filtering the data processing request, tobacco leaf detection data, and real-time analysis results according to the data processing request; Utilizing a machine learning algorithm to perform real-time analysis on the data processing request, tobacco leaf testing data, and real-time analysis results, identify key indicators such as tobacco leaf quality, moisture, and chemical composition, and generate an analysis report; The analysis report and the data processing request are compressed and encrypted and then sent to the main control server.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the tobacco leaf detection data management method based on the near-infrared spectrometer as described in any one of claims 7 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the tobacco leaf detection data management method based on near-infrared spectrometer as described in any one of claims 7 to 8 are implemented.

Images