A control method, device and equipment for tobacco production bin and bin replacement

Abstract

The application relates to an artificial intelligence technology and discloses a control method for a tobacco production storage cabinet and cabinet replacement, which comprises the following steps: feature extraction is performed on obtained historical storage cabinet information to obtain storage cabinet features of the historical storage cabinet information; after hierarchical clustering is performed on the storage cabinet features, weighting processing is performed to obtain weight features of the storage cabinet features; a tobacco storage cabinet metering function is constructed according to the weight features; the tobacco storage cabinet is visually identified according to the metering function to obtain a visual interface of the tobacco storage cabinet; and cabinet replacement information of the tobacco storage cabinet is determined according to the metering function and the visual interface. In addition, the application also relates to a blockchain technology, and data lists can be stored in nodes of a blockchain. The application further provides a control device and equipment for a tobacco production storage cabinet and cabinet replacement. The application can improve the control efficiency of a tobacco production storage cabinet and cabinet replacement.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a control method, apparatus and equipment for storage and changing cabinets in tobacco production. Background Technology

[0002] With the deepening integration of "informatization and industrialization," intelligent manufacturing technology is constantly driving the transformation of the tobacco industry. Cigarette production has basically achieved automation in the tobacco processing, cigarette making, and logistics stages. There is a connecting link between the cigarette making and packaging workshops—the tobacco feeding stage. The storage cabinet, as the supply end of this stage, is the last process in the cigarette making line and also the raw material supply process for the cigarette making and packaging workshops. It not only plays a crucial role in the cigarette making machine but also affects the quality of the final product.

[0003] Currently, flow control from the storage tank to the tobacco feeder still relies heavily on manual judgment. When the cigarette making workshop is operating at full capacity, the amount of tobacco required per unit time increases. If the discharge point is in the storage tank recess or during the tank changing stage, it will cause a shortage of tobacco or blockage, leading to tobacco breakage and machine shutdown. Therefore, improving the control efficiency of storage tanks and tank changing in tobacco production has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a control method and apparatus for storage and changing cabinets in tobacco production, the main purpose of which is to solve the problem of low efficiency in the control of storage and changing cabinets in tobacco production.

[0005] To achieve the above objectives, the present invention provides a control method for storage and switching cabinets in tobacco production, comprising:

[0006] Obtain historical storage information of tobacco storage cabinets, extract features from the historical storage information, and obtain the storage cabinet features of the historical storage information;

[0007] Hierarchical clustering is performed on the characteristics of the storage tank to obtain the hierarchical features of the storage tank features;

[0008] The feature weight value of the hierarchical feature is calculated using a weight value algorithm, and the hierarchical feature is weighted according to the feature weight value to obtain the weighted feature of the hierarchical feature;

[0009] A measurement function for the tobacco storage cabinet is constructed based on the weighted features, and the tobacco storage cabinet is visualized based on the measurement function to obtain a visual interface for the tobacco storage cabinet.

[0010] The available storage cabinets in the tobacco storage cabinets are generated according to the measurement function. The physical distance of the available storage cabinets is calculated according to the visualization interface. The available storage cabinet corresponding to the minimum physical distance is selected as the target storage cabinet. The tobacco storage cabinet is replaced using the target storage cabinet.

[0011] Optionally, the step of extracting features from the historical storage tank information to obtain the storage tank features of the historical storage tank information includes:

[0012] The historical storage tank information is corrected to obtain standard information for the historical storage tank information.

[0013] The parameters of the feature extraction model to be optimized are optimized using a pre-set training feature set to obtain the optimized feature extraction model.

[0014] The standard information is input into the optimized feature extraction model to obtain the standard features of the standard information, and the standard features are determined to be the storage tank features of the historical storage tank information.

[0015] Optionally, the step of correcting the historical storage tank information to obtain standard information of the historical storage tank information includes:

[0016] The missing values ​​of the historical storage tank information are corrected to obtain the primary storage tank information of the historical storage tank information;

[0017] One of the primary storage tank information is selected as the target storage tank information, and the following outlier distance algorithm is used to process outliers in the target storage tank information:

[0018]

[0019] Where d represents the outlier distance of the target storage tank information, and y j The average vector representing the target storage tank information, x j The vector representing the target storage tank information, j represents the identifier of the target storage tank information; the target storage tank information after outlier processing is the secondary storage tank information of the primary storage tank information, and outlier correction is performed on the secondary storage tank information to obtain the standard information of the secondary storage tank information.

[0020] Optionally, the step of optimizing the parameters of the feature extraction model to be optimized using a preset training feature set to obtain an optimized feature extraction model includes:

[0021] The training information in the preset training feature set is processed by word segmentation to obtain the training word segments of the training information;

[0022] The trained words are numbered to obtain a text sequence of the trained words. The text sequence is then transformed into a vector using the feature extraction model to be optimized, resulting in the word vector of the text sequence.

[0023] The context vector of the word segmentation vector is generated, and the context vector is normalized using the following normalization algorithm to obtain the normalized context vector:

[0024]

[0025] Among them, s ′ Let represent the normalized vector, s represent the context vector, and e represent an infinite non-repeating decimal.

[0026] The loss function of the feature extraction model to be optimized is generated based on the normalized vector, and the parameters of the feature extraction model to be optimized are optimized using the loss function to obtain the optimized feature extraction model.

[0027] Optionally, the step of performing hierarchical clustering on the storage tank features to obtain hierarchical features of the storage tank features includes:

[0028] The storage tank features are subjected to dimensionality reduction processing to obtain the dimensionality-reduced features of the storage tank features;

[0029] Based on the storage tank characteristics, determine the storage tank items with the storage tank characteristics, select one of the storage tank items as the target item, and calculate the feature similarity between the dimensionality reduction feature and the target item;

[0030] The target item corresponding to the maximum value in the feature similarity is determined as the clustering item of the dimensionality reduction feature. The dimensionality reduction feature is clustered according to the clustering item to obtain the hierarchical features of the distributed solar energy.

[0031] Optionally, the step of performing hierarchical clustering on the storage tank features to obtain hierarchical features of the storage tank features includes:

[0032] Determine the integer programming function for clustering the storage tank features based on the quality influence features in the storage tank features;

[0033] The first-level feature set of the storage tank features is generated according to the integer programming function, and the clustering index of the first-level feature set is calculated according to the preset clustering index algorithm.

[0034] The clustering form of the storage tank features is continuously optimized based on the clustering index until the clustering index is greater than the preset clustering threshold, at which point the clustering form for clustering the storage tank features is determined.

[0035] The storage tank features are grouped and clustered according to the determined clustering form to obtain the hierarchical features of the storage tank features.

[0036] Optionally, the step of visually identifying the tobacco storage cabinet based on the measurement function to obtain a visual interface for the tobacco storage cabinet includes:

[0037] Based on the total number and location of the tobacco storage cabinets, the space configuration of the tobacco storage cabinets is performed on the preset tobacco storage cabinet interface to obtain the first-level configuration interface of the preset tobacco storage cabinet interface;

[0038] One of the metering functions is selected as the target function, and the flow rate parameters of the tobacco storage tank corresponding to the target function are determined according to the target function.

[0039] Based on the flow parameters, the tobacco storage tank in the primary configuration interface is visually labeled with its content, thus obtaining the secondary configuration interface of the primary configuration interface;

[0040] The secondary configuration interface is rendered to obtain the visual interface of the tobacco storage cabinet.

[0041] To address the aforementioned problems, the present invention also provides a control device for storage and switching cabinets in tobacco production, the device comprising:

[0042] The storage cabinet feature module is used to acquire historical storage cabinet information of tobacco storage cabinets, extract features from the historical storage cabinet information, and obtain the storage cabinet features of the historical storage cabinet information.

[0043] The hierarchical feature module is used to perform hierarchical clustering on the features of the storage tank to obtain the hierarchical features of the storage tank features;

[0044] The weight feature module is used to calculate the feature weight value of the hierarchical feature using a weight value algorithm, and to assign weights to the hierarchical feature based on the feature weight value to obtain the weight feature of the hierarchical feature.

[0045] A visualization interface module is used to construct a measurement function for the tobacco storage cabinet based on the weight features, and to visualize the tobacco storage cabinet based on the measurement function to obtain a visualization interface for the tobacco storage cabinet.

[0046] The target storage module is used to generate available storage cabinets in the tobacco storage cabinet according to the metering function, calculate the physical distance of the available storage cabinets according to the visualization interface, select the available storage cabinet corresponding to the minimum physical distance as the target storage cabinet, and use the target storage cabinet to complete the cabinet replacement of the tobacco storage cabinet.

[0047] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0048] At least one processor; and,

[0049] A memory communicatively connected to the at least one processor; wherein,

[0050] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the control method for storage and changing of tobacco production described above.

[0051] This invention extracts features from historical tobacco storage information to obtain storage features, quickly establishing connections between these historical storage information entries. This facilitates subsequent clustering analysis of the storage features. Furthermore, data correction is performed on the historical storage information during feature extraction, making data analysis more efficient. Contextual vectors are used to represent the historical storage information, establishing a connection between the trained word segmentation and the context. The clustering form of the storage features is continuously optimized based on clustering indicators, improving clustering efficiency. This method is applicable to situations with numerous storage features. Weighting of the generated hierarchical features ensures their uniqueness and improves the accuracy of the historical storage information representation. Calculating the distance between tobacco storage cabinets saves time and cost in changing cabinets. Therefore, this invention proposes a control method, device, and equipment for storage and changing cabinets in tobacco production, which can solve the problem of low control efficiency in tobacco storage and changing cabinets. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating a control method for storage and switching cabinets in tobacco production according to an embodiment of the present invention.

[0053] Figure 2 This is a schematic diagram of the process for generating storage tank features according to an embodiment of the present invention;

[0054] Figure 3 This is a schematic diagram of the process for generating hierarchical features according to an embodiment of the present invention;

[0055] Figure 4 This is a functional block diagram of a control device for a storage cabinet and a changing cabinet in tobacco production provided in an embodiment of the present invention;

[0056] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing the control method for storage and switching cabinets in tobacco production, according to an embodiment of the present invention.

[0057] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0058] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0059] This application provides a control method for storage and switching cabinets in tobacco production. The execution entity of this control method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the control method for storage and switching cabinets in tobacco production can be executed by software or hardware installed on a terminal device or a server device. The software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0060] Reference Figure 1 The diagram shown is a flowchart illustrating a control method for storage and switching cabinets in tobacco production according to an embodiment of the present invention. In this embodiment, the control method for storage and switching cabinets in tobacco production includes:

[0061] S1. Obtain historical storage information of tobacco storage cabinets, extract features from the historical storage information, and obtain the storage features of the historical storage information.

[0062] In this embodiment of the invention, the historical storage cabinet information includes, but is not limited to, the type of tobacco storage cabinet, basic parameters, and location of the storage cabinet. The storage cabinet type includes: leaf storage cabinet, stem storage cabinet, and tobacco storage cabinet, or according to the structure of the storage cabinet, it can be divided into ordinary type, top type, double-layer type, and triple-layer type. The basic parameters include: the dimensions (length * width * height) of the storage cabinet, the height of the discharge port, the bottom belt conveyor speed, the auxiliary material cart belt speed, the auxiliary material cart travel speed, and the power supply model.

[0063] In detail, the feature extraction of the historical storage tank information may include determining that the auxiliary material cart speed of the storage tank is 13m / min, the bottom belt conveyor speed is 0.5m / min, etc.

[0064] In detail, the feature extraction of the historical storage tank information is to quickly establish the relationship between the historical storage tank information, and at the same time, facilitate the subsequent cluster analysis of the storage tank features.

[0065] In this embodiment of the invention, the reference Figure 2 As shown, the step of extracting features from the historical storage tank information to obtain the storage tank features of the historical storage tank information includes:

[0066] S21. Correct the historical storage tank information to obtain standard information of the historical storage tank information;

[0067] S22. Optimize the parameters of the feature extraction model to be optimized using a preset training feature set to obtain the optimized feature extraction model.

[0068] S23. Input the standard information into the optimized feature extraction model to obtain the standard features of the standard information, and determine the standard features as the storage tank features of the historical storage tank information.

[0069] In detail, data correction is performed on the historical storage tank information because the preprocessing of the historical storage tank information determines the efficiency and accuracy of subsequent data processing.

[0070] Specifically, the step of correcting the historical storage tank information to obtain standard information for the historical storage tank information includes:

[0071] The missing values ​​of the historical storage tank information are corrected to obtain the primary storage tank information of the historical storage tank information;

[0072] One of the primary storage tank information is selected as the target storage tank information, and the following outlier distance algorithm is used to process outliers in the target storage tank information:

[0073]

[0074] Where d represents the outlier distance of the target storage tank information, and y j The average vector representing the target storage tank information, x j The vector representing the target storage tank information, where j represents the identifier of the target storage tank information;

[0075] After outlier processing, the target storage tank information is collected as the secondary storage tank information of the primary storage tank information. Outlier correction is performed on the secondary storage tank information to obtain the standard information of the secondary storage tank information.

[0076] In detail, most of the time in data analysis is spent on data preprocessing. Good data preprocessing often makes our data analysis work twice as effective, and correctly handling missing values ​​is of paramount importance.

[0077] Furthermore, the main reasons for missing values ​​include the following aspects: information is temporarily unavailable, such as the revenue of a certain product having a lag effect; data is not recorded, omitted, or lost due to human factors; data loss is caused by malfunctions of data acquisition equipment, storage media, or transmission media; the cost of acquiring data is too high; some attributes of certain objects are unavailable, such as the name of an unmarried person's spouse or the fixed income status of a child; the system has high real-time performance requirements, that is, it requires rapid judgment or decision-making before this information is obtained.

[0078] In detail, the missing values ​​can be processed by methods such as deletion, imputation, and ignoring. The imputation includes, but is not limited to, one or more of the following: special value filling, average value filling, hot card filling, K nearest neighbor method, and multiple imputation.

[0079] In detail, the step of optimizing the parameters of the feature extraction model to be optimized using a preset training feature set to obtain the optimized feature extraction model includes:

[0080] The training information in the preset training feature set is processed by word segmentation to obtain the training word segmentation of the training information;

[0081] The trained words are numbered to obtain a text sequence of the trained words. The text sequence is then transformed into a vector using the feature extraction model to be optimized, resulting in the word vector of the text sequence.

[0082] The context vector of the word segmentation vector is generated, and the context vector is normalized using the following normalization algorithm to obtain the normalized context vector:

[0083]

[0084] Among them, s ′ Let represent the normalized vector, s represent the context vector, and e represent an infinite non-repeating decimal.

[0085] The loss function of the feature extraction model to be optimized is generated based on the normalized vector, and the parameters of the feature extraction model to be optimized are optimized using the loss function to obtain the optimized feature extraction model.

[0086] In detail, word segmentation tools for processing the training information include: Harbin Institute of Technology LTP, Institute of Computing Technology of Chinese Academy of Sciences NLPIR, Tsinghua University THULAC and jieba, etc. Chinese word segmentation is the process of dividing a sequence of Chinese characters into individual words and recombining the continuous sequence of characters into a word sequence according to certain rules. Common word segmentation methods are divided into three categories: word segmentation methods based on string matching, word segmentation methods based on understanding, and word segmentation methods based on statistics.

[0087] Specifically, Python can be used to perform text clause segmentation on the training information.

[0088] In the embodiment of the present invention, numbering the training word segmentation is for better identification and reuse, and establishing the connection between the training word segmentation and the context.

[0089] Specifically, assuming that the training word segmentation only has three words, "I", "very", and "good", then assign the label "001" to "I", assign the label "002" to "very", and assign the label "003" to "good", and use "001", "002", and "003" to represent the text sequence of the training word segmentation.

[0090] Specifically, the context vector of the word segmentation vector is generated according to the bidirectional hidden Markov chain.

[0091] Furthermore, the loss function of the feature extraction model to be optimized is generated according to the residual between the normalized vector and the label of the training information in the preset training feature set.

[0092] S2. Perform hierarchical clustering on the cabinet features to obtain the hierarchical features of the cabinet features.

[0093] In the embodiment of the present invention, as Figure 3 shown, the performing hierarchical clustering on the cabinet features to obtain the hierarchical features of the cabinet features includes:

[0094] S31. Perform dimensionality reduction processing on the cabinet features to obtain the dimensionality-reduced features of the cabinet features;

[0095] S32. Determine the cabinet items of the cabinet features according to the cabinet features, select one of the cabinet items of the cabinet items as the target item one by one, and calculate the feature similarity between the dimensionality-reduced features and the target item;

[0096] S33. Determine the target item corresponding to the maximum value in the feature similarity as the clustering item of the dimensionality-reduced features, and perform clustering on the dimensionality-reduced features according to the clustering item to obtain the hierarchical features of the distributed solar energy.

[0097] Specifically, performing dimensionality reduction processing on the cabinet features is to avoid the curse of dimensionality of the cabinet features. At the same time, mapping the cabinet features from matrix form to vector form, the dimensionality reduction processing of the cabinet features can be performed using a preset normalization model, or the convolutional idea and pooling idea can be used to perform dimensionality reduction processing on the cabinet features. Among them, the pooling operation mainly includes average pooling and maximum pooling, and methods such as multidimensional scaling transformation (MDS), isometric feature mapping (ISOMAP), and principal component analysis (PCA) can also be used.

[0098] Furthermore, the multidimensional scaling transformation requires that the distance of the storage tank feature be preserved in the low-dimensional space. However, in order to effectively reduce dimensionality, it is often only necessary to make the distance after dimensionality reduction as close as possible to the distance of the storage tank feature. The distance after dimensionality reduction and the distance of the storage tank feature are both obtained by using the Euclidean distance formula.

[0099] In detail, the calculation of the feature similarity between the dimensionality reduction feature and the target item can be performed using Euclidean distance algorithm, Manhattan distance algorithm, Chebyshev distance algorithm, and Mahalanobis distance algorithm, etc.

[0100] Specifically, the hierarchical clustering of the storage tank features to obtain the hierarchical features of the storage tank features includes:

[0101] Determine the integer programming function for clustering the storage tank features based on the quality influence features in the storage tank features;

[0102] The first-level feature set of the storage tank features is generated according to the integer programming function, and the clustering index of the first-level feature set is calculated according to the preset clustering index algorithm.

[0103] The clustering form of the storage tank features is continuously optimized based on the clustering index until the clustering index is greater than the preset clustering threshold, at which point the clustering form for clustering the storage tank features is determined.

[0104] The storage tank features are grouped and clustered according to the determined clustering form to obtain the hierarchical features of the storage tank features.

[0105] In detail, the integer programming function is a function that determines the decision variables and is related to the decision variables. The quality impact characteristic is the decision variable, and the change of the decision variable will determine the function value of the integer programming function. Here, the decision variable may be the flow rate, running time, and size of the storage tank, etc. The integer programming function represents the functional relationship between the amount of tobacco in the storage tank and the decision variables.

[0106] Furthermore, the continuous optimization of the clustering form of the storage tank features based on the clustering index is to ensure that the clustering form is globally optimal. By continuously iterating the first-level feature set, an optimal clustering form of the storage tank features is obtained.

[0107] In detail, the clustering index can be generated using the quartic method.

[0108] In this embodiment of the invention, hierarchical clustering of the storage cabinet features yields hierarchical features that allow for a simple and quick understanding of the independence and correlation between the storage cabinet features of the tobacco storage cabinet.

[0109] S3. Calculate the feature weight value of the hierarchical feature using the weight value algorithm, and assign weights to the hierarchical feature according to the feature weight value to obtain the weight feature of the hierarchical feature.

[0110] In this embodiment of the invention, the feature weight values ​​of the hierarchical features are calculated using the following weighting algorithm:

[0111]

[0112] Among them, C i E represents the feature weight value of the hierarchical feature. i This represents the i-th hierarchical feature in the hierarchical features. represents the covariance of the feature vector of the i-th level feature in the user features, and trace() represents the spatial filtering function.

[0113] In detail, the feature weight value is multiplied by the hierarchical feature to obtain the weight feature of the hierarchical feature.

[0114] In detail, the dot product refers to calculating the Hadamard product of the weight matrix generated by the feature weight values ​​and the hierarchical features. That is, the matrix dimension of the preset weight matrix is ​​consistent with the matrix dimension of the text dependency features, and the weight features are obtained by multiplying them element by element.

[0115] For example, when the weight matrix is The hierarchical features are When, the weighted feature is

[0116] S4. Construct a measurement function for the tobacco storage cabinet based on the weighted features, and visualize the tobacco storage cabinet according to the measurement function to obtain the visualization interface of the tobacco storage cabinet.

[0117] In this embodiment of the invention, the metering function of the tobacco storage cabinet can be generated by curve fitting the weighted features.

[0118] In this embodiment of the invention, the curve fitting refers to approximating or analogizing the functional relationship between coordinates represented by a set of discrete points on a plane using a continuous curve; the curve fitting can be implemented using Origin or MATLAB.

[0119] In detail, the measurement function is a function used to represent the tobacco quantity feature and the content variable feature in the weighted features.

[0120] In this embodiment of the invention, the step of visually identifying the tobacco storage cabinet based on the measurement function to obtain a visual interface for the tobacco storage cabinet includes:

[0121] Based on the total number and location of the tobacco storage cabinets, the space configuration of the tobacco storage cabinets is performed on the preset tobacco storage cabinet interface to obtain the first-level configuration interface of the preset tobacco storage cabinet interface;

[0122] One of the metering functions is selected as the target function, and the flow rate parameters of the tobacco storage tank corresponding to the target function are determined according to the target function.

[0123] Based on the flow parameters, the tobacco storage tank in the primary configuration interface is visually labeled with its content, thus obtaining the secondary configuration interface of the primary configuration interface;

[0124] The secondary configuration interface is rendered to obtain the visual interface of the tobacco storage cabinet.

[0125] In detail, the spatial configuration refers to determining the coordinates of the tobacco storage cabinet in the preset tobacco storage cabinet interface, and configuring the tobacco storage cabinet in the preset tobacco storage cabinet interface according to the coordinates.

[0126] Specifically, the objective function can be a multivariate function.

[0127] In detail, the interface rendering refers to the entire process by which the browser transforms HTML into an image that the human eye can see.

[0128] S5. Generate available storage cabinets in the tobacco storage cabinet according to the metering function, calculate the physical distance of the available storage cabinets according to the visualization interface, select the available storage cabinet corresponding to the minimum physical distance as the target storage cabinet, and use the target storage cabinet to complete the replacement of the tobacco storage cabinet.

[0129] In this embodiment of the invention, generating the available storage tank in the tobacco storage tank according to the metering function means determining the amount of tobacco in the tobacco storage tank according to the metering function corresponding to the tobacco storage tank. For example, when the running time and filling time of the tobacco storage tank are determined, the running time and filling time are substituted into the metering function to obtain the amount of tobacco in the tobacco storage tank.

[0130] In detail, the physical distance of the available storage cabinets calculated based on the visualization interface is obtained by proportionally enlarging the interface distance of the tobacco storage cabinets on the interface.

[0131] In detail, the amount of tobacco in the tobacco storage cabinets varies, and there may even be no tobacco at all. Therefore, it is necessary to determine which tobacco storage cabinet to replace the current one. The replacement cost is minimized when the physical distance between the two tobacco storage cabinets is minimized.

[0132] This invention extracts features from historical tobacco storage information to obtain storage features, quickly establishing connections between these historical storage information entries. This facilitates subsequent clustering analysis of the storage features. Furthermore, the feature extraction process corrects the historical storage information, making data analysis more efficient. Contextual vectors are used to represent the historical storage information, establishing a connection between the trained word segmentation and the context. The clustering form of the storage features is continuously optimized based on clustering indicators, improving clustering efficiency. This method is applicable to situations with numerous storage features. Weighting the generated hierarchical features ensures their uniqueness and improves the accuracy of historical storage information representation. Calculating the distance between tobacco storage cabinets saves time and cost in changing cabinets. Therefore, this invention proposes a control method for storage and changing cabinets in tobacco production, solving the problem of low control efficiency in this area.

[0133] like Figure 4 The diagram shown is a functional block diagram of a control device for a storage cabinet and a changing cabinet for tobacco production provided in an embodiment of the present invention.

[0134] The control device 100 for storage and switching in tobacco production described in this invention can be installed in an electronic device. Depending on the functions implemented, the control device 100 may include a storage cabinet feature module 101, a hierarchical feature module 102, a weighted feature module 103, a visualization interface module 104, and a target storage cabinet module 105. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and is stored in the memory of the electronic device.

[0135] In this embodiment, the functions of each module / unit are as follows:

[0136] The storage cabinet feature module 101 is used to acquire historical storage cabinet information of tobacco storage cabinets, extract features from the historical storage cabinet information, and obtain the storage cabinet features of the historical storage cabinet information.

[0137] The hierarchical feature module 102 is used to perform hierarchical clustering on the storage tank features to obtain the hierarchical features of the storage tank features;

[0138] The weight feature module 103 is used to calculate the feature weight value of the hierarchical feature using a weight value algorithm, and to perform weighting processing on the hierarchical feature according to the feature weight value to obtain the weight feature of the hierarchical feature.

[0139] The visualization interface module 104 is used to construct a measurement function for the tobacco storage cabinet based on the weight features, and to visualize the tobacco storage cabinet based on the measurement function to obtain a visualization interface for the tobacco storage cabinet.

[0140] The target storage module 105 is used to generate available storage cabinets in the tobacco storage cabinet according to the metering function, calculate the physical distance of the available storage cabinets according to the visualization interface, select the available storage cabinet corresponding to the minimum physical distance as the target storage cabinet, and use the target storage cabinet to complete the cabinet replacement of the tobacco storage cabinet.

[0141] like Figure 5 The diagram shown is a schematic representation of an electronic device for implementing a control method for storage and switching cabinets in tobacco production, according to an embodiment of the present invention.

[0142] The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13. It may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a control program for storage and changing cabinets in tobacco production.

[0143] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing control programs for storage and switching in tobacco production) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0144] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of control programs for storage and switching in tobacco production, but also to temporarily store data that has been output or will be output.

[0145] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0146] The communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0147] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0148] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0149] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0150] The memory 11 in the electronic device stores a control program for the storage and switching of tobacco production cabinets. This program is a combination of multiple instructions, which, when run in the processor 10, can achieve the following:

[0151] Obtain historical storage information of tobacco storage cabinets, extract features from the historical storage information, and obtain the storage cabinet features of the historical storage information;

[0152] Hierarchical clustering is performed on the characteristics of the storage tank to obtain the hierarchical features of the storage tank features;

[0153] The feature weight value of the hierarchical feature is calculated using a weight value algorithm, and the hierarchical feature is weighted according to the feature weight value to obtain the weighted feature of the hierarchical feature;

[0154] A measurement function for the tobacco storage cabinet is constructed based on the weighted features, and the tobacco storage cabinet is visualized based on the measurement function to obtain a visual interface for the tobacco storage cabinet.

[0155] The available storage cabinets in the tobacco storage cabinets are generated according to the measurement function. The physical distance of the available storage cabinets is calculated according to the visualization interface. The available storage cabinet corresponding to the minimum physical distance is selected as the target storage cabinet. The tobacco storage cabinet is replaced using the target storage cabinet.

[0156] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0157] Furthermore, if the modules / units integrated into the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0158] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0159] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0160] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0161] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0162] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0163] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0164] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0165] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0166] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A control method for storage and changing cabinets in tobacco production, characterized in that, The method includes: Obtain historical storage information of tobacco storage cabinets, extract features from the historical storage information, and obtain the storage cabinet features of the historical storage information; Hierarchical clustering is performed on the characteristics of the storage tank to obtain the hierarchical features of the storage tank features; The feature weight values ​​of the hierarchical features are calculated using a weighting algorithm, and the hierarchical features are weighted according to the feature weight values ​​to obtain the weighted features of the hierarchical features. The weighting algorithm includes: Among them, C i E represents the feature weight value of the hierarchical feature. i This represents the i-th hierarchical feature in the hierarchical features. represents the feature vector covariance of the i-th level feature in the user features, and trace() represents the spatial filtering function; A measurement function for the tobacco storage cabinet is constructed based on the weighted features, and the tobacco storage cabinet is visualized based on the measurement function to obtain a visual interface for the tobacco storage cabinet. The available storage cabinets in the tobacco storage cabinets are generated according to the measurement function. The physical distance of the available storage cabinets is calculated according to the visualization interface. The available storage cabinet corresponding to the minimum physical distance is selected as the target storage cabinet. The tobacco storage cabinet is replaced using the target storage cabinet.

2. The control method for storage and changing cabinets in tobacco production as described in claim 1, characterized in that, The step of extracting features from the historical storage tank information to obtain the storage tank features of the historical storage tank information includes: The historical storage tank information is corrected to obtain standard information for the historical storage tank information. The parameters of the feature extraction model to be optimized are optimized using a pre-set training feature set to obtain the optimized feature extraction model. The standard information is input into the optimized feature extraction model to obtain the standard features of the standard information, and the standard features are determined to be the storage tank features of the historical storage tank information.

3. The control method for storage and changing cabinets in tobacco production as described in claim 2, characterized in that, The step of correcting the historical storage tank information to obtain standard information for the historical storage tank information includes: The missing values ​​of the historical storage tank information are corrected to obtain the primary storage tank information of the historical storage tank information; One of the primary storage tank information is selected as the target storage tank information, and the following outlier distance algorithm is used to process outliers in the target storage tank information: Where d represents the outlier distance of the target storage tank information, and y j The average vector representing the target storage tank information, x j The vector representing the target storage tank information, j represents the identifier of the target storage tank information; the target storage tank information after outlier processing is the secondary storage tank information of the primary storage tank information, and outlier correction is performed on the secondary storage tank information to obtain the standard information of the secondary storage tank information.

4. The control method for storage and changing cabinets in tobacco production as described in claim 2, characterized in that, The step of optimizing the parameters of the feature extraction model to be optimized using a preset training feature set to obtain the optimized feature extraction model includes: The training information in the preset training feature set is processed by word segmentation to obtain the training word segments of the training information; The trained words are numbered to obtain a text sequence of the trained words. The text sequence is then transformed into a vector using the feature extraction model to be optimized, resulting in the word vector of the text sequence. The context vector of the word segmentation vector is generated, and the context vector is normalized using the following normalization algorithm to obtain the normalized context vector: Among them, s ′ Let represent the normalized vector, s represent the context vector, and e represent an infinite non-repeating decimal. The loss function of the feature extraction model to be optimized is generated based on the normalized vector, and the parameters of the feature extraction model to be optimized are optimized using the loss function to obtain the optimized feature extraction model.

5. The control method for storage and changing cabinets in tobacco production as described in claim 1, characterized in that, The hierarchical clustering of the storage tank features to obtain the hierarchical features of the storage tank features includes: The storage tank features are subjected to dimensionality reduction processing to obtain the dimensionality-reduced features of the storage tank features; Based on the storage tank characteristics, determine the storage tank items with the storage tank characteristics, select one of the storage tank items as the target item, and calculate the feature similarity between the dimensionality reduction feature and the target item; The target item corresponding to the maximum value in the feature similarity is determined as the clustering item of the dimensionality reduction feature. The dimensionality reduction feature is clustered according to the clustering item to obtain the hierarchical features of distributed solar energy.

6. The control method for storage and changing cabinets in tobacco production as described in claim 1, characterized in that, The hierarchical clustering of the storage tank features to obtain the hierarchical features of the storage tank features includes: Determine the integer programming function for clustering the storage tank features based on the quality influence features in the storage tank features; The first-level feature set of the storage tank features is generated according to the integer programming function, and the clustering index of the first-level feature set is calculated according to the preset clustering index algorithm. The clustering form of the storage tank features is continuously optimized based on the clustering index until the clustering index is greater than the preset clustering threshold, at which point the clustering form for clustering the storage tank features is determined. The storage tank features are grouped and clustered according to the determined clustering form to obtain the hierarchical features of the storage tank features.

7. The control method for storage and changing cabinets in tobacco production as described in any one of claims 1 to 6, characterized in that, The step of visually identifying the tobacco storage cabinet based on the measurement function to obtain the visual interface of the tobacco storage cabinet includes: Based on the total number and location of the tobacco storage cabinets, the space configuration of the tobacco storage cabinets is performed on the preset tobacco storage cabinet interface to obtain the first-level configuration interface of the preset tobacco storage cabinet interface; One of the metering functions is selected as the target function, and the flow rate parameters of the tobacco storage tank corresponding to the target function are determined according to the target function. Based on the flow parameters, the tobacco storage tank in the primary configuration interface is visually labeled with its content, thus obtaining the secondary configuration interface of the primary configuration interface; The secondary configuration interface is rendered to obtain the visual interface of the tobacco storage cabinet.

8. A control device for storage and changing cabinets in tobacco production, characterized in that, The device includes: The storage cabinet feature module is used to acquire historical storage cabinet information of tobacco storage cabinets, extract features from the historical storage cabinet information, and obtain the storage cabinet features of the historical storage cabinet information. The hierarchical feature module is used to perform hierarchical clustering on the features of the storage tank to obtain the hierarchical features of the storage tank features; The weight feature module is used to calculate the feature weight value of the hierarchical feature using a weight value algorithm, and to assign weights to the hierarchical feature based on the feature weight value to obtain the weight feature of the hierarchical feature. A visualization interface module is used to construct a measurement function for the tobacco storage cabinet based on the weight features, and to visualize the tobacco storage cabinet based on the measurement function to obtain a visualization interface for the tobacco storage cabinet. The target storage module is used to generate available storage cabinets in the tobacco storage cabinet according to the metering function, calculate the physical distance of the available storage cabinets according to the visualization interface, select the available storage cabinet corresponding to the minimum physical distance as the target storage cabinet, and use the target storage cabinet to complete the cabinet replacement of the tobacco storage cabinet.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the control method for storage and changing of tobacco production as described in any one of claims 1 to 7.

Images