Tobacco strip alcoholization state prediction method and device, electronic equipment and storage medium
By screening key indicators and the establishment of sliced tobacco alcoholic predictive models, the accuracy and efficiency problem of the predictive predictive predictive predictive prediction of sliced cigarettes in the existing technology have been solved, and the accurate prediction of sliced cigarette alcoholization state is realized, and the quality control of the modern tobacco industry is met. need.
Patent Information
- Application Number
- CN202411469059.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-21
- Publication Date
- 2025-01-28
AI Technical Summary
It is difficult for the prior art to accurately predict the amortization state of tablet smoke, and traditional sensory evaluations have problems such as strong subjectivity, low efficiency and difficulty in quantification.
By obtaining the detection data and sensory quality scores of various levels of cigarettes, convert it into a target sensory quality score, screen key indicators, and establish a model predictive model of sliced cigarettes to achieve accurate predictions on the glycomy state of sashimi.
The accurate prediction of sliced tobacco glycomies has been realized, the subjectivity and efficiency of traditional methods are solved, and the modern tobacco industry needs the demand for quality control and standardized production in the modern tobacco industry.
Smart Images
Figure CN119380839A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, electronic equipment and storage medium for predicting the aging state of tobacco leaves. Background Art
[0002] In the tobacco industry, the aging process of tobacco strips is a crucial link, which directly affects the final quality and taste of tobacco products. Aging refers to a series of complex reactions of the chemical components in tobacco through natural or artificially controlled environmental conditions, so as to achieve the purpose of improving the aroma of tobacco, reducing impurities, and increasing the mellowness of the taste. This process usually takes months or even years and is affected by many factors, such as temperature, humidity, oxygen content, and the chemical composition of the tobacco itself. At the same time, if the aging time of tobacco strips is too long, it will bring about adverse effects such as reduced aroma, increased impurities, and worse taste.
[0003] Traditionally, the method of evaluating the aging state of tobacco leaves mainly relies on sensory evaluation, that is, experienced smokers judge the sensory qualities of tobacco such as aroma and taste by tasting. However, this method has the disadvantages of strong subjectivity, low efficiency, and difficulty in quantification, which makes it difficult to meet the needs of the modern tobacco industry for quality control and standardized production.
[0004] With the continuous advancement of detection technology and the widespread application of data analysis methods, people have begun to try to indirectly evaluate the aging state of tobacco strips by detecting various physical and chemical indicators during the aging process. By using the near-infrared model, tobacco strip samples can be quickly tested to obtain 55 groups of data including conventional chemical composition, pH, starch, polyphenols, amino acids, Amadori, and neophytadiene.
[0005] However, although the test data of each sample are very rich, not all test data are of reference value for predicting the aging state of tobacco leaves, and it is impossible to accurately predict the aging state of tobacco leaves based on the test data. Summary of the invention
[0006] The present invention provides a method, a device, an electronic device and a storage medium for predicting the aging state of tobacco strips, so as to realize accurate prediction of the aging state of tobacco strips.
[0007] According to one aspect of the present invention, a method for predicting the aging state of tobacco slices is provided, comprising:
[0008] Acquire the test data of each grade of tobacco strips and the sensory quality score corresponding to the test data, and convert the sensory quality score into a target sensory quality score; the test data includes the index data of each test index at different time periods; the target sensory quality score is used to judge the aging state of the tobacco strips;
[0009] Based on the index data of each detection index of each grade of tobacco leaves at different time periods, the detection index is screened to obtain key indicators;
[0010] Performing model fitting based on the index data of the key index and the target sensory quality score corresponding to the index data of the key index, and establishing a prediction model for the aging state of tobacco leaves;
[0011] The detection data of the to-be-predicted tobacco strips in any period of time are acquired, and the aging state of the to-be-predicted tobacco strips is determined based on the detection data of the to-be-predicted tobacco strips in any period of time and the aging state prediction model of the tobacco strips.
[0012] According to another aspect of the present invention, there is provided a device for predicting the aging state of tobacco leaves, comprising:
[0013] A data acquisition module is used to acquire the test data of each grade of tobacco strips and the sensory quality score corresponding to the test data, and convert the sensory quality score into a target sensory quality score; the test data includes the index data of each test index at different time periods; the target sensory quality score is used to judge the aging state of the tobacco strips;
[0014] A key indicator screening model is used to screen the detection indicators based on the indicator data of each detection indicator of each grade of tobacco leaves at different time periods to obtain key indicators;
[0015] A module for establishing a model for predicting the aging state of tobacco strips, for performing model fitting based on the index data of the key index and the target sensory quality score corresponding to the index data of the key index, and establishing a model for predicting the aging state of tobacco strips;
[0016] The aging state prediction module is used to obtain the detection data of the tobacco strips to be predicted in any time period, and determine the aging state of the tobacco strips to be predicted based on the detection data of the tobacco strips to be predicted in any time period and the tobacco strip aging state prediction model.
[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0018] at least one processor; and
[0019] a memory communicatively connected to the at least one processor; wherein,
[0020] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the aging state of tobacco slices described in any embodiment of the present invention.
[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting the aging state of tobacco slices described in any embodiment of the present invention when executed.
[0022] The technical solution of the embodiment of the present invention is to obtain the detection data of each grade of tobacco strips and the sensory quality score corresponding to the detection data, and convert the sensory quality score into a target sensory quality score; the detection data includes the index data of each detection index at different time periods; the target sensory quality score is used to judge the aging state of the tobacco strips; the detection index is screened based on the index data of each detection index at different time periods of each grade of tobacco strips to obtain the key index; the model is fitted based on the index data of the key index and the target sensory quality score corresponding to the index data of the key index to establish the aging state prediction model of the tobacco strips; the detection data of the tobacco strips to be predicted in any time period are obtained, and the aging state of the tobacco strips to be predicted is determined based on the detection data of the tobacco strips to be predicted in any time period and the tobacco strip aging state prediction model. Accurate prediction of the aging state of the tobacco strips is achieved.
[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0025] Figure 1 This is a flow chart of a method for predicting the aging state of tobacco slices provided in Example 1 of the present invention;
[0026] Figure 2 It is a schematic diagram of the structure of a device for predicting the aging state of tobacco leaves provided in the second embodiment of the present invention;
[0027] Figure 3 It is a structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION
[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0030] Embodiment 1
[0031] Figure 1 This is a flow chart of a method for predicting the aging state of tobacco strips provided in the first embodiment of the present invention. This embodiment is applicable to the case of predicting the aging state of tobacco strips in stock. The method can be executed by a device for predicting the aging state of tobacco strips. The device can be implemented in the form of hardware and / or software. The device can be configured in electronic devices such as computers and servers. Figure 1 As shown, the method includes:
[0032] S110, obtaining the test data of each grade of tobacco leaves and the sensory quality score corresponding to the test data, and converting the sensory quality score into a target sensory quality score; the test data includes the index data of each test index at different time periods; the target sensory quality score is used to judge the aging state of the tobacco leaves.
[0033] Among them, different production area types include different grades of tobacco leaves. For example, the production area type is Southwest Fragrance type, which includes Sichuan Huili, Yunnan Pu'er, Yunnan Honghe and other different grades of tobacco leaves.
[0034] In this embodiment, the tobacco strip samples of each grade of tobacco strips sampled at different time periods are tested by a near infrared model to obtain the test data of each grade of tobacco strips, and the sensory quality score of the tobacco strips corresponding to the test data is recorded. Among them, the test indicators of the test data include pH, polyphenols, amino acids, Amadori compounds, neophytadiene, etc. Specifically, polyphenols include chlorogenic acid, cryptochlorogenic acid, rutin, etc., amino acids include serine, glutamine, glycine, alanine, etc., and Amadori compounds include Glu-An, Fru-Amb, Fru-His, Fru-Val, etc.
[0035] Among them, the sensory quality score is determined by scoring by professional sensory evaluation experts according to specific standards. For example, in some evaluation methods, aroma quality and aroma quantity may each account for 15 points, impurities, concentration, strength, irritation, aftertaste may each account for 10 points, and combustibility and gray may each account for 10 points. The evaluation experts will evaluate the tobacco slices one by one according to these standards and give corresponding scores. Then, these scores will be added up to obtain a comprehensive score, which can be used to measure the sensory quality of the tobacco slices. In this embodiment, the sensory quality score can be converted to obtain a target sensory quality score. Among them, the target sensory quality score is used to judge the alcoholization state of the tobacco slice. Specifically, the sensory quality score of the tobacco slice at the critical value of excessive alcoholization can be assigned to N or N.5 points. When the sensory quality score of a certain grade of tobacco is just at the critical value of over-alcoholization when sampling for n times, it is assigned a value of N; when the sensory quality score of the tobacco of this grade is at the critical value of over-alcoholization when sampling for n times, but it has been over-alcoholized when sampling for n+1 times, the sensory quality score of the nth time is assigned a value of N.5. For example, N can be 60, so the sensory quality score of tobacco at the critical value of over-alcoholization can be assigned a value of 60 or 60.5 points.
[0036] The conversion formula for the sensory quality score of the non-over-alcoholization critical value of the tobacco slices is:
[0037] Y i =Y i ×Y n / Y′ n
[0038] Among them, Y i is the converted target sensory quality score, Y i is the raw sensory quality score, Y n is the target sensory quality score of the tobacco leaves after conversion at the critical value of over-alcoholization, that is, N; Y′ n It is the original sensory quality score of the tobacco slice at the critical value of over-alcoholization. It can be understood that the above formula is actually scaling the original sensory quality score to meet the score standards of N and N.5 assigned when it is at the critical value of over-alcoholization.
[0039] S120, screening the detection indicators based on the indicator data of each detection indicator of each grade of tobacco leaves at different time periods to obtain key indicators.
[0040] Since not all detection indicators have reference value for predicting the aging state of tobacco strips, it is necessary to screen the detection indicators. In this embodiment, the detection indicators are screened based on the indicator data of each detection indicator of each grade of tobacco strips at different time periods to obtain key indicators. Among them, the key indicators are indicators that have reference value for predicting the aging state of tobacco strips.
[0041] On the basis of the above embodiment, optionally, the detection indicators are screened based on the indicator data of each detection indicator of each grade of tobacco leaves at different time periods to obtain key indicators, including: for any detection indicator, an indicator change curve is generated based on the indicator data of the same grade of tobacco leaves at different time periods, and the indicator change curve changes with time; when the indicator change curves corresponding to the grades of tobacco leaves all meet the key indicator screening conditions, the detection indicator is determined as the key indicator.
[0042] In this embodiment, for any detection index, an index change curve is generated based on the index data of the same grade of tobacco leaves at different time periods, and the index change curve can characterize the change trend of the detection data of the detection index over time. Furthermore, the index change curves of each grade of tobacco leaves are judged based on the key indicator screening conditions. If the index change curves of each grade of tobacco leaves meet the key indicator screening conditions, the detection index is determined as the key indicator. Among them, the key indicator screening conditions can be that the index change curve shows a decreasing trend as a whole. Exemplarily, assuming that the detection index is chlorogenic acid, if the index change curves of the chlorogenic acid indicators of each grade of tobacco leaves show a decreasing trend as a whole, the chlorogenic acid indicator is the key indicator.
[0043] It should be noted that when the indicator change curve shows a trend of first increasing and then decreasing, since the indicator change curve as a whole still shows a decreasing trend, the indicator change curve still meets the key indicator screening conditions.
[0044] For example, the key indicators after screening are shown in Table 2:
[0045] Table 2
[0046]
[0047]
[0048]
[0049] S130, performing model fitting based on the indicator data of the key indicator and the target sensory quality score corresponding to the indicator data of the key indicator, and establishing a prediction model for the aging state of tobacco leaves.
[0050] In this embodiment, a model fitting is performed based on the linear relationship between the index data of the key index and the target sensory quality score corresponding to the index data of the key index to establish a prediction model for the aging state of tobacco slices.
[0051] On the basis of the above embodiment, optionally, the indicator data based on the key indicator and the target sensory quality score corresponding to the indicator data of the key indicator are used for model fitting to establish a tobacco leaf aging state prediction model, including: standardizing the indicator data of the key indicator to obtain standard indicator data; establishing a detection data matrix based on the standard indicator data; establishing a quality prediction matrix based on the target sensory quality score corresponding to the standard indicator data; and fitting a multivariate linear regression model based on the detection data matrix and the quality prediction matrix to obtain a tobacco leaf aging state prediction model.
[0052] Among them, standard indicator data refers to standardized indicator data after annotation processing. In this embodiment, the indicator data of key indicators are standardized to obtain standard indicator data; a detection data matrix is established based on the standard indicator data; a quality prediction matrix is established based on the target sensory quality score corresponding to the standard data; a multivariate linear regression model is fitted based on the detection data matrix and the quality prediction matrix to obtain a prediction model for the aging state of tobacco leaves. Among them, the standardization method can be Z-scor standardization method, range standardization method, proportion method, etc., which are not limited here.
[0053] On the basis of the above embodiment, optionally, the step of fitting a multiple linear regression model based on the detection data matrix and the quality prediction matrix to obtain a tobacco aging state prediction model comprises: using a preset regression analysis method to fit the multiple linear regression model based on the detection data matrix and the quality prediction matrix to obtain an unknown parameter matrix, wherein the unknown parameter matrix comprises unknown parameters in the multiple linear regression model; and determining the tobacco aging state prediction model based on the unknown parameter matrix and the multiple linear regression model.
[0054] The preset regression analysis method may be the least squares method. In this embodiment, the preset regression analysis method may be used to perform model fitting on the multiple linear regression model based on the detection data matrix and the quality prediction matrix, estimate the unknown parameters in the multiple linear regression model, and obtain an unknown parameter matrix; further, the unknown parameters in the unknown parameter matrix are substituted into the multiple linear regression model to obtain a prediction model for the aging state of tobacco leaves.
[0055] Specifically, the linear relationship of the multiple linear regression model is expressed as:
[0056] Y=Xβ+ε
[0057] Where Y is the quality prediction value matrix of number n, Y = (Y1, Y2, ..., Y n ) T ; β is the unknown parameter matrix of number m+1, β=(β1,β2,…,β m ) T ; ε is the error matrix of number n, ε=(ε1,ε2,…,ε n ) T , ε i ~N(0,σ 2 ); X is an n×(m+1) detection data matrix.
[0058] S140, acquiring detection data of the to-be-predicted tobacco strips in any time period, and determining the aging state of the to-be-predicted tobacco strips based on the detection data of the to-be-predicted tobacco strips in any time period and the tobacco strip aging state prediction model.
[0059] The to-be-predicted tobacco strip refers to the tobacco strip sample for which the tobacco strip aging state prediction is to be performed. In this embodiment, after the tobacco strip aging state prediction model is established, the detection data of the tobacco strip to be predicted in any period of time can be obtained, and the detection data of the period of time can be predicted based on the tobacco strip aging state prediction model to determine the aging state of the tobacco strip to be predicted. The aging state of the tobacco strip includes not over-aging, being at the over-aging critical value, and over-aging.
[0060] On the basis of the above embodiment, optionally, the aging state of the to-be-predicted tobacco strips is determined based on the detection data of the to-be-predicted tobacco strips in any time period and the tobacco strip aging state prediction model, comprising: standardizing the index data of key indicators in the detection data of the to-be-predicted tobacco strips in any time period to obtain the to-be-predicted index data; performing prediction based on the to-be-predicted index data and the tobacco strip aging state prediction model to obtain the target sensory quality score of the to-be-predicted tobacco strips; and determining the aging state of the to-be-predicted tobacco strips based on the target sensory quality score of the to-be-predicted tobacco strips.
[0061] The index data to be predicted refers to the index data of the key index in the detection data of the tobacco strips sampled at any time period after being standardized. In this embodiment, the index data of the key index in the detection data of the tobacco strips to be predicted at any time period is standardized to obtain the index data to be predicted at any time period; the index data to be predicted at any time period is substituted into the tobacco strip aging state prediction model for prediction to obtain the target sensory quality score of the tobacco strips to be predicted. The aging state of the tobacco strips to be predicted is determined based on the target sensory quality score of the tobacco strips to be predicted. It can be understood that during the aging process of the tobacco strips, as the aging process proceeds, the target sensory quality score of the tobacco strips will show a decreasing trend due to over-aging. Therefore, the target sensory quality score of the tobacco strips to be predicted is compared with the target sensory quality score of the over-aging critical value. If the target sensory quality score of the tobacco strips to be predicted is greater than the target sensory quality score of the over-aging critical value, the aging state of the tobacco strips to be predicted is not over-aging; if the target sensory quality score of the tobacco strips to be predicted is less than the target sensory quality score of the over-aging critical value, the aging state of the tobacco strips to be predicted is over-aging; if the target sensory quality score of the tobacco strips to be predicted is equal to the target sensory quality score of the over-aging critical value, the aging state of the tobacco strips to be predicted is at the over-aging critical value.
[0062] This embodiment predicts the target sensory quality score of the tobacco strips to be predicted by using the tobacco strip aging state prediction model, thereby determining the aging state of the tobacco strips to be predicted by the target sensory quality score, which can achieve prediction of the sensory quality of the tobacco strips while realizing the prediction of the aging state of the tobacco strips.
[0063] The technical solution of this embodiment is to obtain the test data of each grade of tobacco strips and the sensory quality score corresponding to the test data, and convert the sensory quality score into a target sensory quality score; the test data includes the index data of each test index at different time periods; the target sensory quality score is used to judge the mellowing state of tobacco strips; the test index is screened based on the index data of each test index at different time periods of each grade of tobacco strips to obtain key indicators; the model is fitted based on the index data of the key indicators and the target sensory quality score corresponding to the index data of the key indicators to establish a prediction model for the mellowing state of tobacco strips; the test data of the tobacco strips to be predicted at any time period is obtained, and the mellowing state of the tobacco strips to be predicted is determined based on the test data of the tobacco strips to be predicted at any time period and the prediction model for the mellowing state of tobacco strips. Accurate prediction of the mellowing state of tobacco strips is achieved.
[0064] On the basis of the above-mentioned embodiment, optionally, the method of standardization processing includes: for any of the key indicators, determining the initial indicator data of the key indicator; and standardizing the indicator data of the key indicator based on the initial indicator data.
[0065] Specifically, the standardized formula is:
[0066] x′ i =x in / x i0 ,
[0067] Among them, x i0 represents the initial indicator data of the i-th key indicator, that is, the detection data of the first sampling of the i-th key indicator; x in It is the detection data of the nth sampling of the i key indicator.
[0068] Embodiment 2
[0069] Figure 2 Schematic diagram of the structure of a device for predicting the aging state of tobacco leaves provided in the second embodiment of the present invention. Figure 2 As shown, the device comprises:
[0070] The data acquisition module 210 is used to acquire the test data of each grade of tobacco strips and the sensory quality score corresponding to the test data, and convert the sensory quality score into a target sensory quality score; the test data includes the index data of each test index at different time periods; the target sensory quality score is used to judge the aging state of the tobacco strips;
[0071] A key indicator screening model 220 is used to screen the detection indicators based on the indicator data of each detection indicator of each grade of tobacco flakes at different time periods to obtain key indicators;
[0072] The module 230 for establishing a model for predicting the aging state of tobacco strips is used to perform model fitting based on the index data of the key index and the target sensory quality score corresponding to the index data of the key index, so as to establish a model for predicting the aging state of tobacco strips;
[0073] The aging state prediction module 240 is used to obtain the detection data of the tobacco strips to be predicted in any time period, and determine the aging state of the tobacco strips to be predicted based on the detection data of the tobacco strips to be predicted in any time period and the tobacco strip aging state prediction model.
[0074] The technical solution of this embodiment is to obtain the test data of each grade of tobacco strips and the sensory quality score corresponding to the test data, and convert the sensory quality score into a target sensory quality score; the test data includes the index data of each test index at different time periods; the target sensory quality score is used to judge the mellowing state of tobacco strips; the test index is screened based on the index data of each test index at different time periods of each grade of tobacco strips to obtain key indicators; the model is fitted based on the index data of the key indicators and the target sensory quality score corresponding to the index data of the key indicators to establish a prediction model for the mellowing state of tobacco strips; the test data of the tobacco strips to be predicted at any time period is obtained, and the mellowing state of the tobacco strips to be predicted is determined based on the test data of the tobacco strips to be predicted at any time period and the prediction model for the mellowing state of tobacco strips. Accurate prediction of the mellowing state of tobacco strips is achieved.
[0075] Based on the above embodiment, optionally, the key indicator screening model 220 is specifically used for:
[0076] For any detection index, an index change curve is generated based on the index data of the same grade of tobacco leaves at different time periods, and the index change curve changes with time;
[0077] When the indicator change curves corresponding to the tobacco leaves of each grade meet the key indicator screening conditions, the detection indicator is determined as the key indicator.
[0078] Based on the above embodiment, optionally, the key indicator screening condition is that the indicator change curve presents an overall decreasing trend.
[0079] Based on the above embodiment, optionally, the tobacco aging state prediction model building module 230 is specifically used for:
[0080] Standardizing the indicator data of the key indicators to obtain standard indicator data;
[0081] Establish a detection data matrix based on standard indicator data;
[0082] Establishing a quality prediction matrix based on the target sensory quality scores corresponding to the standard indicator data;
[0083] A multiple linear regression model is fitted based on the detection data matrix and the quality prediction matrix to obtain a prediction model for the aging state of tobacco leaves.
[0084] On the basis of the above embodiment, optionally, the tobacco aging state prediction model building module 230 includes a tobacco aging state prediction model fitting unit, which is used to:
[0085] Using a preset regression analysis method, the multivariate linear regression model is fitted based on the detection data matrix and the quality prediction matrix to obtain an unknown parameter matrix, wherein the unknown parameter matrix includes unknown parameters in the multivariate linear regression model;
[0086] A prediction model for the aging state of tobacco slices is determined based on the unknown parameter matrix and the multivariate linear regression model.
[0087] Based on the above embodiment, optionally, the alcoholization state prediction module 240 is specifically used for:
[0088] Standardizing the index data of the key index in the detection data of the to-be-predicted tobacco strips in any period of time to obtain the to-be-predicted index data;
[0089] Predicting based on the to-be-predicted index data and the tobacco strip aging state prediction model to obtain the target sensory quality score of the tobacco strip to be predicted;
[0090] The aging state of the tobacco strips to be predicted is determined based on the sensory quality score of the tobacco strips to be predicted.
[0091] Based on the above embodiment, optionally, the device further includes a standardization module, which is used to determine the initial indicator data of the key indicator for any of the key indicators;
[0092] The indicator data of the key indicator is standardized based on the initial indicator data.
[0093] The device for predicting the aging state of tobacco strips provided in the embodiment of the present invention can execute the method for predicting the aging state of tobacco strips provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0094] Embodiment 3
[0095] Figure 3 1 is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0096] like Figure 3As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0097] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0098] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the tobacco aging state prediction method.
[0099] In some embodiments, the method for predicting the aging state of tobacco leaves may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for predicting the aging state of tobacco leaves described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for predicting the aging state of tobacco leaves by any other appropriate means (e.g., by means of firmware).
[0100] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0101] The computer program for implementing the method for predicting the alcoholization state of tobacco slices of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or the block diagram are implemented. The computer program can be executed completely on the machine, partially on the machine, as an independent software package, partially on the machine and partially on a remote machine, or completely on a remote machine or server.
[0102] Embodiment 4
[0103] Embodiment 4 of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a processor to execute a method for predicting the aging state of tobacco leaves, the method comprising:
[0104] Obtaining the test data of each grade of tobacco strips and the sensory quality scores corresponding to the test data, and converting the sensory quality scores into target sensory quality scores; the test data includes the index data of each test index at different time periods; the target sensory quality scores are used to judge the aging state of the tobacco strips;
[0105] Based on the index data of each test index of each grade of tobacco leaves at different time periods, the test indexes are screened to obtain key indexes;
[0106] Model fitting is performed based on the index data of key indicators and the target sensory quality scores corresponding to the index data of key indicators to establish a prediction model for the aging state of tobacco leaves;
[0107] The detection data of the tobacco strips to be predicted in any period of time is obtained, and the aging state of the tobacco strips to be predicted is determined based on the detection data of the tobacco strips to be predicted in any period of time and the tobacco strip aging state prediction model.
[0108] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0109] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0110] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0111] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0112] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0113] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for predicting the aging state of tobacco leaves, characterized in that: include: Acquire the test data of each grade of tobacco leaves and the sensory quality score corresponding to the test data, and convert the sensory quality score into a target sensory quality score; The detection data includes the index data of each detection index at different time periods; the target sensory quality score is used to judge the aging state of the tobacco leaves; Based on the index data of each detection index of each grade of tobacco leaves at different time periods, the detection index is screened to obtain key indicators; Performing model fitting based on the index data of the key index and the target sensory quality score corresponding to the index data of the key index, and establishing a prediction model for the aging state of tobacco leaves; The detection data of the to-be-predicted tobacco strips in any period of time are acquired, and the aging state of the to-be-predicted tobacco strips is determined based on the detection data of the to-be-predicted tobacco strips in any period of time and the aging state prediction model of the tobacco strips.
2. The method according to claim 1, characterized in that The detection indicators are screened based on the indicator data of each detection indicator of each grade of tobacco in different time periods to obtain key indicators, including: For any detection index, an index change curve is generated based on the index data of the same grade of tobacco leaves at different time periods, and the index change curve changes with time; When the indicator change curves corresponding to the tobacco leaves of each grade meet the key indicator screening conditions, the detection indicator is determined as the key indicator.
3. The method according to claim 2, characterized in that The key indicator screening condition is that the indicator change curve shows an overall decreasing trend.
4. The method according to claim 1, characterized in that The method of performing model fitting based on the index data of the key index and the target sensory quality score corresponding to the index data of the key index to establish a prediction model for the aging state of tobacco leaves comprises: Standardizing the indicator data of the key indicators to obtain standard indicator data; Establish a detection data matrix based on standard indicator data; Establishing a quality prediction matrix based on the target sensory quality scores corresponding to the standard indicator data; A multiple linear regression model is fitted based on the detection data matrix and the quality prediction matrix to obtain a prediction model for the aging state of tobacco leaves.
5. The method according to claim 4, characterized in that The method of fitting a multiple linear regression model based on the detection data matrix and the quality prediction matrix to obtain a tobacco aging state prediction model includes: Using a preset regression analysis method, the multivariate linear regression model is fitted based on the detection data matrix and the quality prediction matrix to obtain an unknown parameter matrix, wherein the unknown parameter matrix includes unknown parameters in the multivariate linear regression model; A prediction model for the aging state of tobacco slices is determined based on the unknown parameter matrix and the multivariate linear regression model.
6. The method according to claim 1, characterized in that The step of determining the aging state of the to-be-predicted tobacco strips based on the detection data of the to-be-predicted tobacco strips at any time period and the tobacco strip aging state prediction model comprises: Standardizing the index data of the key index in the detection data of the to-be-predicted tobacco strips in any period of time to obtain the to-be-predicted index data; Predicting based on the to-be-predicted index data and the tobacco strip aging state prediction model to obtain the target sensory quality score of the tobacco strip to be predicted; The aging state of the tobacco strips to be predicted is determined based on the sensory quality score of the tobacco strips to be predicted.
7. The method according to claim 4 or 6, characterized in that: The method for standardization processing comprises: For any of the key indicators, determining initial indicator data of the key indicator; The indicator data of the key indicator is standardized based on the initial indicator data.
8. A device for predicting the aging state of tobacco leaves, characterized in that: include: A data acquisition module is used to acquire the test data of each grade of tobacco strips and the sensory quality score corresponding to the test data, and convert the sensory quality score into a target sensory quality score; the test data includes the index data of each test index at different time periods; the target sensory quality score is used to judge the aging state of the tobacco strips; A key indicator screening model is used to screen the detection indicators based on the indicator data of each detection indicator of each grade of tobacco leaves at different time periods to obtain key indicators; A module for establishing a model for predicting the aging state of tobacco strips, for performing model fitting based on the index data of the key index and the target sensory quality score corresponding to the index data of the key index, and establishing a model for predicting the aging state of tobacco strips; The aging state prediction module is used to obtain the detection data of the tobacco strips to be predicted in any time period, and determine the aging state of the tobacco strips to be predicted based on the detection data of the tobacco strips to be predicted in any time period and the tobacco strip aging state prediction model.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the alcoholization state of tobacco sheets according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting the aging state of tobacco slices according to any one of claims 1 to 7 when executed.