A method for establishing a sensory taste detection model and a method for sensory taste detection

Abstract

The application discloses a kind of sensory taste detection model establishment methods, applied to sensory detection field, comprising: obtaining the sensory taste data of target classification item and the production data of cigarette product;The sensory taste data of target classification item is corrected, to correct the dispersion degree of the sensory taste data of target classification item to the dispersion degree of all sensory taste data direction, obtain the corrected sensory taste data of target classification item;Production data and corrected sensory taste data are stored in database as sensory taste detection model corresponding.This application corrects sensory taste data, and establishes sensory taste detection model based on the corrected sensory taste data and production data, solves the problem that sensory taste data is influenced by the subjective bias of scorer.In addition, the application also provides a kind of sensory taste detection method, sensory taste detection model establishment device, equipment and readable storage medium, also have the beneficial effects of above.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of sensory detection, in particular to a sensory taste detection model establishment method, a sensory taste detection method, a sensory taste detection model establishment device, equipment and a readable storage medium. BACKGROUND

[0002] Cigarettes are mass consumer goods, with a variety of flavors, and different people have different preferences for cigarette flavors. Cigarettes have a variety of flavors, and the evaluation criteria include multiple dimensions. Existing research has shown that different groups have obvious preferences for cigarette flavors. According to the gender, region, age, and other factors of smokers, they tend to choose different types of cigarettes.

[0003] Past research on the preferences of smokers for cigarette flavors based on factors such as gender, region, and age has been relatively rough, often summarizing a few rules based on experience, without forming a system. The existing technology has the technical problem that it is difficult to select appropriate cigarettes for customer tags, and manufacturers have difficulty finding suitable groups for a certain type of cigarette. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a sensory taste detection model establishment method, a sensory taste detection method, a sensory taste detection model establishment device, equipment and a readable storage medium, which solves the problem that sensory taste data is affected by the subjective bias of the scorer in related technology.

[0005] To solve the above technical problems, the present application provides a sensory taste detection model establishment method, comprising:

[0006] obtaining sensory taste data of a target classification item and production data of a cigarette product;

[0007] correcting the sensory taste data of the target classification item to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data, obtaining corrected sensory taste data of the target classification item;

[0008] storing the production data and the corrected sensory taste data in the database as a sensory taste detection model.

[0009] Optionally, the correction of the sensory taste data of the target classification item to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data, obtaining the corrected sensory taste data of the target classification item, comprises:

[0010] inputting the sensory taste data of the target classification item into In the formula, the modified sensory taste data of the target classification item is obtained; the x is the modified sensory taste data of the target classification item, the x i is the sensory taste data of the target classification item, the λ is an average value of the sensory taste data of the target classification item, and the σ is a standard deviation of the sensory taste data of the target classification item all is an average value of all the sensory taste data, and the σ all is a standard deviation of all the sensory taste data.

[0011] Optionally, the production data and the modified sensory taste data are stored in a database as a sensory taste detection model.

[0012] The production data and comprehensive data are stored in the database as the sensory taste detection model; the comprehensive data includes the modified sensory taste data and sensory evaluation data of a cigarette product.

[0013] Optionally, the sensory taste data of the target classification item is obtained by:

[0014] The obtained initial sensory taste data is classified by a sensory taste classification item to obtain first classification data; the sensory taste classification item includes aroma concentration, fullness, delicacy, coordination, miscellaneous gas, irritability, and aftertaste degree;

[0015] The first classification data is classified again by a group classification item to obtain second classification data; the group classification item includes at least one of age, gender, and main living area;

[0016] The sensory taste data is obtained from the second classification data according to a preset condition.

[0017] Optionally, the production data and the modified sensory taste data are stored in a database as a sensory taste detection model.

[0018] Group classification item information corresponding to the modified sensory taste data is obtained.

[0019] The production data, the modified sensory taste data, and the group classification item information are stored in a database as the sensory taste detection model.

[0020] Optionally, after the production data, the modified sensory taste data, and the group classification item information are stored in a database as the sensory taste detection model, the method further includes:

[0021] Current group classification item information is obtained.

[0022] The sensory taste detection model is called to match the current group classification item information, and current corrected sensory taste data is obtained.

[0023] The maximum value of the current corrected sensory taste data is calculated as the optimal favorite taste corresponding to the current group classification item information.

[0024] The application further provides a sensory taste detection method, comprising:

[0025] Production data of the cigarette product is obtained; the production data comprises at least one of the following: production manufacturer, brand, cigarette packaging mode, important process production parameters, and raw material source;

[0026] A sensory taste detection model is called to match the production data, and corrected sensory taste data of a target classification item is obtained.

[0027] The sensory taste detection model is a corresponding sensory taste detection model between the production data and the corrected sensory taste data, and the corrected sensory taste data is a result of correcting the sensory taste data of the target classification item of the cigarette product, so as to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data.

[0028] The application further provides a sensory taste detection model establishment device, comprising:

[0029] An acquisition module is configured to acquire sensory taste data of a target classification item and production data of a cigarette product;

[0030] A correction module is configured to correct the sensory taste data of the target classification item, so as to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data, and obtain corrected sensory taste data of the target classification item.

[0031] A storage module is configured to store the production data and the corrected sensory taste data in a database as a sensory taste detection model.

[0032] The application further provides a sensory taste detection model establishment device, comprising:

[0033] A memory is configured to store a computer program;

[0034] A processor is configured to execute the computer program to realize the steps of the above-mentioned sensory taste detection model establishment method.

[0035] The application further provides a readable storage medium for storing a computer program, wherein the computer program is executed by a processor to implement the steps of the method for establishing the sensory taste detection model.

[0036] It can be seen that the application corrects the sensory taste data of the target classification item to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data, obtains the corrected sensory taste data of the target classification item, and stores the production data and the corrected sensory taste data in the database as the sensory taste detection model. The application corrects the sensory taste data and establishes the sensory taste detection model based on the corrected sensory taste data and the production data, solves the problem that the sensory taste data is affected by the subjective bias of the scorers, and improves the efficiency of the sensory taste detection of the cigarette products.

[0037] In addition, the application further provides a sensory taste detection method, a sensory taste detection model establishment device, equipment and a readable storage medium, which also have the beneficial effects described above. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only embodiments of the application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of the provided drawings.

[0039] Figure 1 A flow chart of a sensory taste detection model establishment method provided by an embodiment of the application;

[0040] Figure 2 A flow chart of a method for classifying sensory taste data provided by an embodiment of the application;

[0041] Figure 3 A flow chart of a method for calculating the optimal favorite taste corresponding to the group classification item information provided by an embodiment of the application;

[0042] Figure 4 A flow chart of a sensory taste detection method provided by an embodiment of the application;

[0043] Figure 5 A structural schematic diagram of a sensory taste detection model establishment device provided by an embodiment of the application;

[0044] Figure 6 A structural schematic diagram of a sensory taste detection model establishment device provided by an embodiment of the application. DETAILED DESCRIPTION

[0045] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0046] Reference should be made to Figure 1 , Figure 1 A flowchart of a method for establishing a sensory taste detection model provided by the embodiments of the present application. The method can include:

[0047] S101: Obtain sensory taste data of a target classification item and production data of a cigarette product.

[0048] The execution subject of the embodiments is a terminal. The embodiments of the present application are not limited to the type of the terminal, as long as the terminal can complete the operation of sensory quality detection. For example, the terminal can be a general-purpose terminal or a special-purpose terminal.

[0049] It should be noted that the production data of the cigarette product in the embodiments can include at least one of a production process, a production raw material, and a rolling method.

[0050] The embodiments of the present application are not limited to the starting time of the program for obtaining the sensory taste data of the target classification item and the production data of the cigarette product. For example, the program can be automatically started after the program for establishing a sensory taste detection model is started, or the program can be started after receiving a starting instruction of an operator. The embodiments of the present application are not limited to the specific manner of receiving the instruction of the operator. For example, the starting instruction of the operator can be received in a voice input manner, or the starting instruction of the operator can be received in an operation port input manner. The embodiments of the present application are not limited to the frequency of obtaining the sensory taste data of the target classification item and the production data of the cigarette product, as long as the sensory taste data of the target classification item and the production data of the cigarette product can be obtained in time. For example, the obtaining can be performed in real time, that is, after the operation of obtaining is completed once, the next obtaining is performed immediately; or the operation of obtaining can be performed once every first preset obtaining time period. The embodiments of the present application are not limited to the setting value of the first preset obtaining time period. For example, the first preset obtaining time period can be 2 seconds, 4 seconds, or 5 seconds. In order to ensure that the sensory taste data of the target classification item and the production data of the cigarette product are obtained in time, the embodiments of the present application can be obtained in real time.

[0051] The embodiment is not limited to the number of the sensory taste data of the target classification item and the production data of the cigarette product, as long as the operation of establishing the sensory taste detection model can be completed. For example, the number of the sensory taste data of the target classification item and the production data of the cigarette product can be 50 groups, the number of the sensory taste data of the target classification item and the production data of the cigarette product can be 100 groups, and the number of the sensory taste data of the target classification item and the production data of the cigarette product can be 200 groups.

[0052] It should be noted that the target classification item in the embodiment is the classification of the sensory taste data, which is the target classification item selected. The embodiment is not limited to the basis for classifying the sensory taste data. For example, the sensory taste data can be classified according to age intervals, or the sensory taste data can be classified according to regional information.

[0053] Further, in order to establish the sensory taste detection model according to different classification dimensions and improve the accuracy of the sensory taste detection model, the above-mentioned obtaining of the sensory taste data of the target classification item can include the following steps, please refer to Figure 2 , Figure 2 A flowchart of a method for classifying sensory taste data provided by the embodiment of the application is shown in FIG. 2.

[0054] S201: Classifying the obtained initial sensory taste data by a sensory taste classification item to obtain first classification data, wherein the sensory taste classification item includes aroma concentration, fullness, delicacy, coordination, miscellaneous gas, irritability and aftertaste.

[0055] The embodiment is not limited to the number of grades set for each classification item. For example, the aroma concentration, fullness, delicacy, coordination, miscellaneous gas, irritability and aftertaste in the sensory taste classification item can be divided into 3 grades, the aroma concentration, fullness, delicacy, coordination, miscellaneous gas, irritability and aftertaste in the sensory taste classification item can be divided into 5 grades, and the aroma concentration, fullness, delicacy, coordination, miscellaneous gas, irritability and aftertaste in the sensory taste classification item can be divided into 6 grades.

[0056] S202: Classifying the first classification data by a group classification item to obtain second classification data, wherein the group classification item includes at least one of age, gender and main living area.

[0057] The embodiment is not limited to the number of grades set for the group classification item. For example, the group classification item can be divided into 3 grades, the group classification item can be divided into 4 grades, and the group classification item can be divided into 5 grades.

[0058] S203: obtaining the sensory taste data from the second classification data according to a preset condition.

[0059] It should be noted in the embodiment that the preset condition is data defined by an operator.

[0060] S102: correcting the sensory taste data of the target classification item to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data, to obtain corrected sensory taste data of the target classification item.

[0061] It should be noted in the embodiment that the obtained sensory taste data of the target classification item is corrected to obtain the corrected sensory taste data of the target classification item, wherein the sensory taste data of the target classification item is corrected to approach the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data.

[0062] Further, in order to more accurately correct the sensory taste data of the target classification item, the above-mentioned correction of the sensory taste data of the target classification item to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data, to obtain the corrected sensory taste data of the target classification item, can include:

[0063] inputting the sensory taste data of the target classification item into the formula to obtain the corrected sensory taste data of the target classification item, wherein the x is the corrected sensory taste data of the target classification item, the x i is the sensory taste data of the target classification item, the λ is the average value of the sensory taste data of the target classification item, the σ is the standard deviation of the sensory taste data of the target classification item, the λ all is the average value of all the sensory taste data, and the σ all is the standard deviation of all the sensory taste data.

[0064] S103: storing the production data and the corrected sensory taste data in the database as a sensory taste detection model.

[0065] It should be noted in the embodiment that a mapping relationship is established between the production data and the corrected sensory taste data, and the mapping relationship is stored in the database as a sensory taste detection model.

[0066] Further, in order to improve the detection dimension of the sensory taste detection model, the above-mentioned storage of the production data and the corrected sensory taste data in the database as a sensory taste detection model can include:

[0067] The production data and the comprehensive data are stored in the database as a sensory taste detection model, wherein the comprehensive data comprises the corrected sensory taste data and the sensory evaluation data of the cigarette product.

[0068] It should be noted that the sensory evaluation data in the embodiment can include at least one of aroma style characteristics, irritation site and aftertaste residue type. The embodiment does not limit the specific content of the aroma style characteristics, the irritation site and the aftertaste residue type. For example, the aroma style characteristics can be classified into fresh, roasted and burnt, the irritation site can be classified into no irritation, irritation in oral cavity, irritation in nasal cavity and irritation in throat, and the aftertaste residue type can be classified into no residue, astringent, bitter aftertaste and burnt aftertaste; or any combination of the above.

[0069] Further, in order to improve the detection ability of the sensory taste detection model and enable the sensory taste detection model to detect the applicable group, the production data and the corrected sensory taste data are stored in the database as the sensory taste detection model, which can include the following steps:

[0070] Obtaining group classification item information corresponding to the corrected sensory taste data.

[0071] The production data, the corrected sensory taste data and the group classification item information are stored in the database as the sensory taste detection model.

[0072] It should be noted that the sensory taste detection model established based on the production data, the corrected sensory taste data and the group classification item information can determine the corresponding sensory taste data according to the production data, and further obtain the corresponding group classification item information to determine the applicable group of the current cigarette product.

[0073] Further, in order to be able to determine the corresponding corrected sensory taste data according to the group classification item information, after the production data, the corrected sensory taste data and the group classification item information are stored in the database as the sensory taste detection model, the following steps can be further included, for details, please refer to Figure 3 , Figure 3 A flowchart of a method for calculating the optimal favorite taste corresponding to the group classification item information provided by the embodiment of the present application is shown in the following figure:

[0074] S301: Obtaining current group classification item information.

[0075] The embodiment is not limited to the frequency of obtaining the current group classification item information, as long as the current group classification item information can be obtained in time. For example, the obtaining can be performed in real time, that is, after the operation of obtaining is completed, the next obtaining is performed immediately; or the operation of obtaining can be performed once every second preset obtaining time period. The embodiment is not limited to the setting value of the second preset obtaining time period. For example, the second preset obtaining time period can be 1 second, 3 seconds, or 5 seconds. In order to ensure that the current group classification item information is obtained in time, the embodiment can adopt the way of obtaining in real time to obtain the current group classification item information.

[0076] S302: calling the sensory taste detection model to match the current group classification item information to obtain current corrected sensory taste data.

[0077] S303: calculating the maximum value of the current corrected sensory taste data as the optimal favorite taste corresponding to the current group classification item information.

[0078] It should be noted that the corrected sensory taste corresponding to the maximum value of the current corrected sensory taste data is the optimal favorite taste of the group in the current group classification item information. The embodiment can also determine several favorite tastes of the group in the current group classification item information.

[0079] By using the method for establishing the sensory taste detection model provided in the embodiment, the sensory taste data of the target classification item and the production data of the cigarette product are obtained, the sensory taste data of the target classification item is corrected, the dispersion degree of the sensory taste data of the target classification item is corrected to the dispersion degree of all the sensory taste data, the corrected sensory taste data of the target classification item is obtained, and the production data and the corrected sensory taste data are stored in the database as the sensory taste detection model. The method for establishing the sensory taste detection model based on the corrected sensory taste data and the production data solves the problem that the sensory taste data is affected by the subjective bias of the scorer, and improves the efficiency of the sensory taste detection of the cigarette product.

[0080] By inputting the sensory taste data of the target classification item into the above formula, the corrected sensory taste data of the target classification item is obtained, which can more accurately correct the sensory taste data of the target classification item, by corresponding storage of the production data and the comprehensive data in the database as the sensory taste detection model, the detection dimension of the sensory taste detection model is improved, by classification of the obtained initial sensory taste data, the sensory taste data of the target classification item is obtained, the sensory taste detection model is established according to different classification dimensions, the accuracy of the sensory taste detection model is improved, by corresponding storage of the production data, the corrected sensory taste data and the group classification item information in the database as the sensory taste detection model, the corresponding corrected sensory taste data can be determined according to the group classification item information, the optimal favorite taste of the group in the current group classification item information is determined by calling the sensory taste detection model, the practicality of the sensory taste detection model is improved, and the user's use experience is improved.

[0081] In order to make the application more convenient to understand, the following describes the sensory taste detection method provided by the embodiment of the application, and the following described sensory taste detection method can be correspondingly referred to the above described sensory taste detection model establishing method.

[0082] For details, please refer to Figure 4 , Figure 4 The flowchart of the sensory taste detection method provided by the embodiment of the application can include:

[0083] S401: Obtain the production data of the cigarette product, the production data including at least one of the production manufacturer, the brand, the rolling method, the important process production parameter and the raw material source.

[0084] S402: Call the sensory taste detection model to match the production data, and obtain the corrected sensory taste data of the target classification item.

[0085] It needs to be explained that the sensory taste detection model is a corresponding sensory taste detection model between the production data and the corrected sensory taste data, and the corrected sensory taste data is the result of correcting the sensory taste data of the target classification item of the cigarette product, so as to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data.

[0086] The application embodiment provides a sensory taste detection method, production data of a cigarette product is acquired, wherein the production data comprises at least one of a production manufacturer, a brand, a rolling and packaging mode, important process production parameters, and raw material sources, a sensory taste detection model is called to match the production data, and modified sensory taste data of a target classification item is obtained. The application modifies sensory taste data, establishes a sensory taste detection model based on the modified sensory taste data and production data, calls the model to match production data of a cigarette product, and obtains modified sensory taste data of a target classification item, thereby solving the problem that sensory taste data is affected by subjective bias of a scorer.

[0087] The application embodiment provides a sensory taste detection model establishment device, and the following description of the sensory taste detection model establishment device can be correspondingly referred to the above description of the sensory taste detection model establishment method.

[0088] For details, please refer to Figure 5 , Figure 5 The structure diagram of the sensory taste detection model establishment device provided by the application embodiment can comprise:

[0089] The acquisition module 100 is configured to acquire sensory taste data of a target classification item and production data of a cigarette product.

[0090] The modification module 200 is configured to modify the sensory taste data of the target classification item, so as to modify the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data, and obtain modified sensory taste data of the target classification item.

[0091] The storage module 300 is configured to store the production data and the modified sensory taste data in a database as a sensory taste detection model.

[0092] Further, based on the above embodiment, the modification module 200 can comprise:

[0093] The modification unit is configured to input the sensory taste data of the target classification item into the formula to obtain the modified sensory taste data of the target classification item. In the formula, x is the modified sensory taste data of the target classification item, x i is the sensory taste data of the target classification item, λ is an average value of the sensory taste data of the target classification item, σ is a standard deviation of the sensory taste data of the target classification item, λ all is an average value of all the sensory taste data, and σ all is a standard deviation of all the sensory taste data.

[0094] Further, based on any of the above embodiments, the storage module 300 can comprise:

[0095] a first storage unit, configured to store the production data and the comprehensive data in the database as the sensory taste detection model; the comprehensive data comprises the corrected sensory taste data and the sensory evaluation data of the cigarette product.

[0096] Further, based on any of the above embodiments, the acquisition module 100 can comprise:

[0097] a first classification unit, configured to classify the acquired initial sensory taste data through a sensory taste classification item to obtain first classification data; the sensory taste classification item comprises aroma concentration, fullness, delicacy, coordination, miscellaneous gas, irritability and aftertaste degree;

[0098] a second classification unit, configured to classify the first classification data through a group classification item to obtain second classification data; the group classification item comprises at least one of age, gender and main living area;

[0099] a first acquisition unit, configured to acquire the sensory taste data from the second classification data according to a preset condition.

[0100] Further, based on any of the above embodiments, the storage module 300 can comprise:

[0101] a second acquisition unit, configured to acquire group classification item information corresponding to the corrected sensory taste data;

[0102] a second storage unit, configured to store the production data, the corrected sensory taste data and the group classification item information in the database as the sensory taste detection model.

[0103] Further, based on any of the above embodiments, the storage module 300 can further comprise:

[0104] a third acquisition unit, configured to acquire current group classification item information;

[0105] a calling unit, configured to call the sensory taste detection model to match the current group classification item information to obtain current corrected sensory taste data;

[0106] a calculation unit, configured to calculate a maximum value of the current corrected sensory taste data as an optimal favorite taste corresponding to the current group classification item information.

[0107] It should be noted that the modules and units in the above sensory taste detection model establishment device can be changed in sequence without affecting the logic.

[0108] The application embodiment provides a sensory taste detection model establishment device, the acquisition module 100 is used for acquiring sensory taste data of a target classification item and production data of a cigarette product, the correction module 200 is used for correcting the sensory taste data of the target classification item to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data, and obtain corrected sensory taste data of the target classification item, and the storage module 300 is used for storing the production data and the corrected sensory taste data in the database as a sensory taste detection model. The application corrects the sensory taste data, and establishes a sensory taste detection model based on the corrected sensory taste data and the production data, thereby solving the problem that the sensory taste data is affected by the subjective bias of the scorer, and improving the efficiency of the sensory taste detection of the cigarette product.

[0109] The corrected sensory taste data of the target classification item is obtained by inputting the sensory taste data of the target classification item into the above formula, the sensory taste data of the target classification item can be more accurately corrected, the production data and the comprehensive data are stored in the database as a sensory taste detection model, the detection dimension of the sensory taste detection model is improved, the initial sensory taste data is classified to obtain the sensory taste data of the target classification item, the sensory taste detection model is established according to different classification dimensions, the accuracy of the sensory taste detection model is improved, the production data, the corrected sensory taste data and the group classification item information are stored in the database as a sensory taste detection model, the corresponding corrected sensory taste data can be determined according to the group classification item information, the optimal favorite taste of the group in the current group classification item information is determined by calling the sensory taste detection model, the practicality of the sensory taste detection model is improved, and the user experience is improved.

[0110] The application embodiment provides a sensory taste detection model establishment device, and the sensory taste detection model establishment device described below can be correspondingly referred to the sensory taste detection model establishment method described above.

[0111] Please refer to Figure 6 , Figure 6 The structure diagram of the sensory taste detection model establishment device provided by the application embodiment can include:

[0112] The memory 10 is used for storing a computer program;

[0113] The processor 20 is used for executing the computer program to realize the above-mentioned sensory taste detection model establishment method.

[0114] The memory 10, the processor 20 and the communication interface 31 all complete the communication among each other through the communication bus 32.

[0115] In the embodiment of the present application, the memory 10 stores one or more programs, which can include program codes including computer operation instructions. In the embodiment of the present application, the memory 10 can store programs for implementing the following functions:

[0116] obtaining sensory taste data of a target classification item and production data of a cigarette product;

[0117] correcting the sensory taste data of the target classification item to correct the dispersion degree of the sensory taste data of the target classification item to the dispersion degree of all the sensory taste data, to obtain corrected sensory taste data of the target classification item;

[0118] storing the production data and the corrected sensory taste data in a database as a sensory taste detection model.

[0119] In a possible implementation, the memory 10 can include a program storage area and a data storage area. The program storage area can store an operating system and at least one application program required by a function, etc. The data storage area can store data created during use.

[0120] In addition, the memory 10 can include a read-only memory and a random access memory, and provide instructions and data for the processor. A part of the memory can also include an NVRAM. The memory stores an operating system and operation instructions, executable modules or data structures, or subsets thereof, or an extended set thereof, wherein the operation instructions can include various operation instructions for implementing various operations. The operating system can include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0121] The processor 20 can be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic device. The processor 20 can be a microprocessor or any conventional processor, etc. The processor 20 can invoke programs stored in the memory 10.

[0122] The communication interface 31 can be an interface of a communication module, used for connecting with other devices or systems.

[0123] It should be noted that, Figure 6 The structure shown does not constitute a limitation on the sensory taste detection model establishment device in the embodiment of the present application. In actual application, the sensory taste detection model establishment device can include more or fewer components than those shown, or combine certain components. Figure 6 The structure shown does not constitute a limitation on the sensory taste detection model establishment device in the embodiment of the present application. In actual application, the sensory taste detection model establishment device can include more or fewer components than those shown, or combine certain components.

[0124] The readable storage medium provided by the embodiment of the present application is described below, and the readable storage medium described below can be correspondingly referred to the method for establishing the sensory taste detection model described above.

[0125] The present application also provides a readable storage medium, and the readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps of the method for establishing the sensory taste detection model.

[0126] The readable storage medium can include a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage program codes.

[0127] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same or similar parts of each embodiment can be referred to each other. For the device disclosed by the embodiment, since it corresponds to the method disclosed by the embodiment, the description is relatively simple, and the related parts can be referred to the method part.

[0128] The professional person can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present text can be realized by electronic hardware, computer software or combination of both, and in order to clearly show the interchangeability of hardware and software, the composition and steps of each example have been described in the above description. The functions are executed in hardware or software, which depends on the specific application and design constraints of the technical solution. The professional person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0129] Finally, it should be noted that in the present text, the relationship such as first and second is only used to distinguish one entity or operation from another entity or operation, and does not necessarily require or imply any actual relationship or order between the entities or operations. Moreover, the term "includes", "contains" or any other variant is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0130] The method for establishing the sensory taste detection model, the sensory taste detection method, the device for establishing the sensory taste detection model, the equipment and the readable storage medium provided by the present application are described in detail above, and the principles and implementation manners of the present application are described by using specific examples. The above description of the embodiments is only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges will be changed, and the above description of the present application should not be understood as a limitation of the present application.

Claims

1. A method for establishing a sensory taste detection model, characterized in that, include: Obtain sensory taste data for the target category and production data for cigarette products; The sensory taste data of the target category is corrected to adjust the dispersion of the sensory taste data of the target category in the direction of the dispersion of all sensory taste data, so as to obtain the corrected sensory taste data of the target category. The production data and the corrected sensory taste data are stored in the database as a sensory taste detection model. The step of correcting the sensory taste data of the target classification item to adjust the dispersion of the sensory taste data of the target classification item towards the dispersion of all sensory taste data, thereby obtaining the corrected sensory taste data of the target classification item, includes: Input the sensory taste data of the target classification item into... In the formula, the modified sensory taste data of the target classification item is obtained; The corrected sensory taste data for the target classification item, the The sensory taste data for the target classification item, the The average value of the sensory taste data for the target category is... The standard deviation of the sensory taste data for the target classification item is the standard deviation of the sensory taste data for the target classification item. The average value of all the sensory taste data, the The standard deviation of all the sensory taste data; The acquisition of sensory taste data for the target category includes: The initial sensory taste data is classified by sensory taste classification items to obtain the first category data; the sensory taste classification items include aroma concentration, fullness, delicacy, harmony, off-flavors, irritation and aftertaste. The first category data is further classified using group classification items to obtain the second category data; the group classification items include at least one of age, gender, and main place of residence. The sensory taste data is obtained from the second category of data according to preset conditions.

2. The method for establishing a sensory taste detection model according to claim 1, characterized in that, The step of storing the production data and the corrected sensory taste data in a database as a sensory taste detection model includes: The production data and comprehensive data are stored in the database as a corresponding sensory taste detection model; the comprehensive data includes the corrected sensory taste data and the sensory evaluation data of cigarette products.

3. The method for establishing a sensory taste detection model according to claim 1, characterized in that, The step of storing the production data and the corrected sensory taste data in a database as a sensory taste detection model includes: Obtain the group classification information corresponding to the modified sensory taste data; The production data, the modified sensory taste data, and the group classification information are stored in the database as the sensory taste detection model.

4. The method for establishing a sensory taste detection model according to claim 3, characterized in that, After storing the production data, the modified sensory taste data, and the group classification information in the database as the sensory taste detection model, the method further includes: Obtain information on the current group's classification items; The sensory taste detection model is invoked to match the current group classification information to obtain the current corrected sensory taste data; The maximum value of the current modified sensory taste data is calculated and used as the optimal preferred taste corresponding to the current group classification item information.

5. A sensory taste detection method, characterized in that, include: Obtain production data for cigarette products; the production data includes at least one of the following: manufacturer, brand, rolling and packaging method, key process parameters, and raw material source. The sensory taste detection model is invoked to match the production data to obtain the corrected sensory taste data for the target category. The sensory taste detection model is the sensory taste detection model corresponding to the production data and the modified sensory taste data. The modified sensory taste data is the result of correcting the sensory taste data of the target category of the cigarette product to the direction of the dispersion of the sensory taste data of the target category in the direction of the dispersion of all sensory taste data. The process of correcting the sensory flavor data of the target category of the cigarette product to adjust the dispersion of the sensory flavor data of the target category towards the dispersion of all sensory flavor data includes: Input the sensory taste data of the target classification item into... In the formula, the modified sensory taste data of the target classification item is obtained; The corrected sensory taste data for the target classification item, the The sensory taste data for the target classification item, the The average value of the sensory taste data for the target category is... The standard deviation of the sensory taste data for the target classification item is the standard deviation of the sensory taste data for the target classification item. The average value of all the sensory taste data, the The standard deviation of all the sensory taste data; The process of obtaining the sensory taste data of the target classification item includes: The initial sensory taste data is classified by sensory taste classification items to obtain the first category data; the sensory taste classification items include aroma concentration, fullness, delicacy, harmony, off-flavors, irritation and aftertaste. The first category data is further classified using group classification items to obtain the second category data; the group classification items include at least one of age, gender, and main place of residence. The sensory taste data is obtained from the second category of data according to preset conditions.

6. A sensory taste detection model establishment device, characterized in that, include: The acquisition module is used to acquire sensory taste data of the target category and production data of cigarette products; The correction module is used to correct the sensory taste data of the target category item, so as to correct the dispersion of the sensory taste data of the target category item in the direction of the dispersion of all sensory taste data, and obtain the corrected sensory taste data of the target category item. The storage module is used to store the production data and the corrected sensory taste data in the database as a sensory taste detection model. The correction module includes: The correction unit is used to input the sensory taste data of the target classification item into the correction unit. In the formula, the modified sensory taste data of the target classification item is obtained; The corrected sensory taste data for the target classification item, the The sensory taste data for the target classification item, the The average value of the sensory taste data for the target category is... The standard deviation of the sensory taste data for the target classification item is the standard deviation of the sensory taste data for the target classification item. The average value of all the sensory taste data, the The standard deviation of all the sensory taste data; The acquisition module includes: The first classification unit is used to classify the acquired initial sensory taste data according to sensory taste classification items to obtain the first classification data; the sensory taste classification items include aroma concentration, fullness, delicacy, harmony, off-flavors, irritation and aftertaste. The second classification unit is used to perform secondary classification on the first classification data using group classification items to obtain second classification data; the group classification items include at least one of age, gender, and main place of residence. The first acquisition unit is used to acquire the sensory taste data from the second category data according to preset conditions.

7. A sensory taste detection model establishment device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the sensory taste detection model establishment method as described in any one of claims 1 to 4.

8. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the sensory taste detection model establishment method as described in any one of claims 1 to 4.

Images