Cigar quality evaluation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a cigar quality evaluation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring electroencephalogram information and image information of a target cigar used by a user and identity information of the user; determining a personal information base corresponding to the user from a preset archive based on the identity information; identifying a combustion state of a target cigar in the image information to determine a combustion stage corresponding to the target cigar as a target combustion stage; the burning stage comprises a cigar front section, a cigar middle section and a cigar tail section; determining historical electroencephalogram information and historical quality evaluation information in a combustion stage same as the target combustion stage from a personal information base; and based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information, determining the quality evaluation information of the user on the target cigar. By adopting the method, the accuracy of cigar quality evaluation can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of tobacco product detection and analysis, and particularly to a method, device, computer device, computer-readable storage medium and computer program product for evaluating the quality of cigars. Background Art

[0002] As a tobacco product, the quality of cigars has always mainly relied on the taste, smell and vision of professional tasters for evaluation. This requires a high level of personal professionalism from professional tasters, thus bringing uncertainty to the accurate evaluation of cigar quality, that is, affecting the accuracy of cigar quality evaluation. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, computer-readable storage medium and computer program product for evaluating the quality of cigars to improve the accuracy of cigar quality evaluation.

[0004] In a first aspect, the present application provides a method for evaluating the quality of cigars, including:

[0005] Obtaining electroencephalogram information, image information of the user using the target cigar, and the identity information of the user;

[0006] Based on the identity information, determining the personal information library corresponding to the user from a preset archive library;

[0007] Identifying the burning state of the target cigar in the image information to determine the burning stage corresponding to the target cigar as the target burning stage; the burning stage includes the front section of the cigar, the middle section of the cigar, and the tail section of the cigar;

[0008] Determining the historical electroencephalogram information and historical quality evaluation information in the burning stage that is the same as the target burning stage from the personal information library; and,

[0009] Based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information, determining the quality evaluation information of the user for the target cigar.

[0010] In one embodiment, based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information, determining the quality evaluation information of the user for the target cigar includes: based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information, determining the first quality evaluation information of the user for the target cigar;

[0011] The method for evaluating the quality of cigars further includes: obtaining the evaluation information of the user for the target cigar; the evaluation information includes at least one of evaluation voice information, evaluation text information, and scoring information;

[0012] Based on the evaluation information, evaluation features are obtained, and based on the evaluation features, second quality evaluation information of the user for the target cigar is determined;

[0013] According to the first quality evaluation information and the second quality evaluation information, the quality evaluation information of the user for the target cigar is determined.

[0014] In one embodiment, based on the evaluation information, evaluation features are obtained, and based on the evaluation features, second quality evaluation information of the user for the target cigar is determined, including:

[0015] The evaluation information is input into a preset first model to extract evaluation features, and the cigar quality grade corresponding to the evaluation features is determined from a preset cigar quality grade table as the second quality evaluation information of the user for the target cigar.

[0016] In one embodiment, based on the mapping relationship between historical electroencephalogram information and historical quality evaluation information and the electroencephalogram information, the quality evaluation information of the user for the target cigar is determined, including:

[0017] The historical electroencephalogram information, the historical quality evaluation information, and the electroencephalogram information are input into a preset cigar quality evaluation model to extract the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information, and based on the mapping relationship and the electroencephalogram information, the quality evaluation information of the user for the target cigar is determined.

[0018] In one embodiment, based on the mapping relationship between historical electroencephalogram information and historical quality evaluation information and the electroencephalogram information, the quality evaluation information of the user for the target cigar is determined, including:

[0019] The historical time-domain electroencephalogram signal in the historical electroencephalogram information is converted into a historical frequency-domain electroencephalogram signal, and the total energy value of the historical power spectral density in the target Hertz band of the historical frequency-domain electroencephalogram signal is determined to obtain historical electroencephalogram features;

[0020] The time-domain electroencephalogram signal in the electroencephalogram information is converted into a frequency-domain electroencephalogram signal, and the total energy value of the power spectral density in the target Hertz band of the frequency-domain electroencephalogram signal is determined to obtain the electroencephalogram features of the user;

[0021] Based on the mapping relationship between the historical electroencephalogram features and the historical quality evaluation information and the electroencephalogram features, the quality evaluation information of the user for the target cigar is determined.

[0022] In one embodiment, the cigar quality evaluation method further includes:

[0023] Preprocess the electroencephalogram information;

[0024] Wherein, the preprocessing includes positioning electrode channels, converting reference electrodes, filtering, denoising, and intercepting an analysis segment and performing baseline correction.

[0025] In a second aspect, the present application also provides a cigar quality evaluation device, which includes:

[0026] An acquisition module, configured to acquire the electroencephalogram information, image information of the user using the target cigar, and the identity information of the user;

[0027] A first determination module, configured to determine, based on the identity information, the personal information library corresponding to the user from a preset archive; identify the burning state of the target cigar in the image information to determine the burning stage corresponding to the target cigar as the target burning stage; the burning stage includes the front section of the cigar, the middle section of the cigar, and the tail section of the cigar;

[0028] A second determination module, configured to determine the historical electroencephalogram information and historical quality evaluation information in the same burning stage as the target burning stage from the personal information library; and determine the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information.

[0029] In a third aspect, the present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the foregoing first aspect are implemented.

[0030] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the foregoing first aspect are implemented.

[0031] In a fifth aspect, the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method described in the foregoing first aspect are implemented.

[0032] The above-mentioned cigar quality evaluation method, device, computer device, computer-readable storage medium and computer program product start from the user to evaluate the cigar quality. The electroencephalogram information of the user using the target cigar is used as the evaluation basis, avoiding relying on professional tasters to evaluate the cigar quality individually, thus ensuring the accuracy of the cigar quality evaluation. The personal information library corresponding to the user is determined through the user's identity information, and the burning state of the target cigar in the image information of the user using the target cigar is identified to determine the target burning stage, and the historical electroencephalogram information and historical quality evaluation information in the same burning stage as the target burning stage are determined from the personal information library; based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information, the quality evaluation information of the user for the target cigar is determined. That is, based on the user's personal and the burning stage of the cigar, the historical electroencephalogram information, the historical quality evaluation information, and the mapping relationship between the two can be determined more accurately, and then the quality evaluation information of the user for the target cigar can be determined more accurately. In addition, different quality evaluation information is determined for different users, so that the cigar quality evaluation can be bound to the user and the personalized evaluation of the cigar quality for the user can be realized, ensuring the accuracy of the cigar quality evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0034] Figure 1 It is a schematic flowchart of a cigar quality evaluation method in an embodiment;

[0035] Figure 2 It is another schematic flowchart of a cigar quality evaluation method in an embodiment;

[0036] Figure 3 It is still another schematic flowchart of a cigar quality evaluation method in an embodiment;

[0037] Figure 4 It is an electroencephalogram experimental paradigm diagram in an embodiment;

[0038] Figure 5 It is a schematic flowchart of electroencephalogram data preprocessing in an embodiment;

[0039] Figure 6 It is an electroencephalogram topographic map in different frequency bands when a user adapts to a cigar in an embodiment;

[0040] Figure 7(a) is a graph showing the alpha-band frequency domain analysis results of the middle sections of three different brands of cigars in one embodiment;

[0041] Figure 7(b) is a graph showing the beta-band frequency domain analysis results of the middle sections of three different brands of cigars in one embodiment;

[0042] Figure 7(c) is a graph showing the theta-band frequency domain analysis results of the middle sections of three different brands of cigars in one embodiment;

[0043] Figure 7(d) is a graph showing the delta-band frequency domain analysis results of the middle sections of three different brands of cigars in one embodiment;

[0044] Figure 7(e) is a graph showing the gamma-band frequency domain analysis results of the middle sections of three different brands of cigars in one embodiment;

[0045] Figure 8 is a graph showing the frequency domain analysis results of the front, middle, and rear sections of a cigar in one embodiment;

[0046] Figure 9 is a structural block diagram of a cigar quality evaluation device in one embodiment;

[0047] Figure 10 is an internal structure diagram of a computer device in one embodiment. Detailed implementation manners

[0048] In order to make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] In one embodiment, as Figure 1 shown, a cigar quality evaluation method is provided. In this embodiment, the method is exemplified by being applied to a server. It can be understood that the method can also be applied to a system including a terminal and a server and implemented through the interaction between the terminal and the server. In some embodiments, the method can also be applied to a specific cigar quality evaluation device or terminal. In this embodiment, the method includes steps S101 to S105:

[0050] Step S101: The server obtains the electroencephalogram information, image information, and identity information of the user using the target cigar.

[0051] In some embodiments, the times corresponding to the electroencephalogram information and the image information can be the same. For example, the time corresponding to the image information is from exactly 2:00 pm to 2:03 pm, and the time corresponding to the electroencephalogram information is also from exactly 2:00 pm to 2:03 pm. That is, the consistency of the electroencephalogram information and the image information in the time dimension is ensured.

[0052] In some embodiments, the server may obtain the user's identity information through image information. For example, the image information includes an image of the user using the target cigar and the user's face image, and the user's identity information is determined through face recognition.

[0053] In some embodiments, the server may interact with a specific electroencephalogram (EEG) information collection device to obtain the EEG information of the user using the target cigar; similarly, the server may interact with a specific image collection device to obtain the image information of the user using the target cigar. The same principle applies to the acquisition of the user's identity information.

[0054] In some embodiments, the server may interact with a cigar quality evaluation device or terminal for information exchange. The cigar quality evaluation device or terminal may simultaneously collect the EEG information, image information of the user using the target cigar, and the user's identity information.

[0055] Step S102: Based on the identity information, the server determines the personal information library corresponding to the user from a preset archive.

[0056] Among them, the archive may be pre-established and collect the user's identity information and relevant information on the user's use of cigars in the past. For example, the EEG information of using cigars in the past, that is, historical EEG information. Exemplarily, the archive may include multiple personal information libraries, and one user may correspond to one personal information library. Different users correspond to different personal information libraries, and different users can be distinguished through the personal information library. The personal information library does not need to determine the user's personal information.

[0057] It should be noted that the user-related information involved in this application, including but not limited to identity information, personal information library, etc., are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0058] In some embodiments, the specific storage location corresponding to the preset archive may be the database of the server.

[0059] Step S103: The server identifies the burning state of the target cigar in the image information to determine the burning stage corresponding to the target cigar as the target burning stage; the burning stage includes the front section of the cigar, the middle section of the cigar, and the tail section of the cigar.

[0060] Among them, the burning stage may represent the relationship between the burning position of the cigar and the overall total length of the cigar. Exemplarily, different cigar usage durations may correspond to different burning stages. For example, starting from when the cigar is lit, as the cigar usage duration increases, the burning stage goes from the front section of the cigar to the middle section of the cigar, and finally to the tail section of the cigar until it burns out.

[0061] In some exemplary embodiments, the server can identify the combustion state of the target cigar by recognizing the image information. Exemplarily, the server can use a pre-set or online image recognition model in the local database to recognize the image information.

[0062] Step S104: The server determines the historical EEG information and historical quality evaluation information in the personal information database at the same combustion stage as the target combustion stage.

[0063] Among them, the historical quality evaluation information can be for the historical EEG information, that is, the quality evaluation information of the cigar determined by the user based on the user's use of the cigar in the past.

[0064] In some embodiments, different parts of the cigar can have different tastes, that is, bring different feelings to the user. Correspondingly, different combustion stages of the cigar can correspond to different EEG information and different quality evaluation information.

[0065] Step S105: The server determines the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical EEG information and the historical quality evaluation information and the EEG information.

[0066] The mapping relationship between the historical EEG information and the historical quality evaluation information can be a non-linear relationship.

[0067] In some embodiments, the personal information database can not only store the historical EEG information and the historical quality evaluation information, but also automatically extract or recognize or learn the mapping relationship between the historical EEG information and the historical quality evaluation information from the personal information database. Therefore, the server can directly obtain the mapping relationship between the historical EEG information and the historical quality evaluation information from the personal information database.

[0068] The above technical solution starts from the user to evaluate the quality of cigars, and uses the EEG information of the user using the target cigar as the evaluation basis, avoiding relying on professional tasters to evaluate the quality of cigars individually, thus ensuring the accuracy of cigar quality evaluation. Determine the personal information database corresponding to the user through the user's identity information, identify the burning state of the target cigar in the image information of the user using the target cigar, determine the target burning stage, and determine the historical EEG information and historical quality evaluation information at the burning stage that is the same as the target burning stage from the personal information database; based on the mapping relationship between the historical EEG information and the historical quality evaluation information and the EEG information, determine the quality evaluation information of the user for the target cigar. That is, based on the user's personal and the burning stage of the cigar, the historical EEG information, the historical quality evaluation information, and the mapping relationship between the two can be determined more accurately, and then the quality evaluation information of the user for the target cigar can be determined more accurately. In addition, for different users, different quality evaluation information is determined, so that the cigar quality evaluation can be bound to the user and realize the personalized evaluation of the cigar quality for the user, ensuring the accuracy of the cigar quality evaluation.

[0069] In one embodiment, the above-mentioned determining the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical EEG information and the historical quality evaluation information and the EEG information may include: the server determines the first quality evaluation information of the user for the target cigar based on the mapping relationship between the historical EEG information and the historical quality evaluation information and the EEG information; the cigar quality evaluation method further includes: obtaining the evaluation information of the user for the target cigar; the evaluation information includes at least one of evaluation voice information, evaluation text information, and scoring information; based on the evaluation information, an evaluation feature is obtained, and based on the evaluation feature, the second quality evaluation information of the user for the target cigar is determined; according to the first quality evaluation information and the second quality evaluation information, the quality evaluation information of the user for the target cigar is determined.

[0070] Among them, the evaluation information may be information for evaluating the quality of the cigar during or after the user uses the cigar. Exemplarily, according to the different forms of expression of the evaluation information, the evaluation information may include evaluation voice information, evaluation text information, scoring information, etc. Among them, the scoring information may be a score determined based on a preset scoring mechanism, such as a full score of 10, etc.

[0071] In some embodiments, the server may interact with a specific evaluation information collection device to obtain the evaluation information. In some embodiments, the devices for collecting evaluation information, EEG information, and image information may be integrated into one device, and the server may interact with the integrated device to obtain the corresponding information.

[0072] In addition to evaluating the quality of cigars based on EEG information, the above technical solution also evaluates the quality of cigars according to the evaluation information of the target cigar by the user, obtaining the first quality evaluation information and the second quality evaluation information respectively, and determining the quality evaluation information of the target cigar by the user more accurately and comprehensively by integrating the first quality evaluation information and the second quality evaluation information.

[0073] In one embodiment, obtaining evaluation features based on the evaluation information and determining the second quality evaluation information of the target cigar by the user based on the evaluation features may include: the server inputs the evaluation information into a preset first model to extract evaluation features, and determines the cigar quality level corresponding to the evaluation features from a preset cigar quality level table as the second quality evaluation information of the target cigar by the user.

[0074] In some embodiments, the first model may include multiple functional modules, and different functional modules may correspond to different forms of evaluation information. For the evaluation voice information, it may correspond to a voice-to-text module, a text feature extraction module, etc.

[0075] In some embodiments, the server may score according to the evaluation features. For example, the evaluation features may include the number of occurrences of the keyword "good to smoke" in the evaluation information, and score according to the number of occurrences. Then, according to the total score, determine the cigar quality level corresponding to the evaluation features from a preset cigar quality level table. The higher the total score, the higher the cigar quality level.

[0076] The above technical solution extracts features from the evaluation information through the first model to obtain evaluation features, and determines the cigar quality level corresponding to the evaluation features from a preset cigar quality level table as the second quality evaluation information of the target cigar by the user. This helps to improve the efficiency of determining the second quality evaluation information and the accuracy of the determined second quality evaluation information.

[0077] In one embodiment, determining the quality evaluation information of the target cigar by the user based on the mapping relationship between the historical EEG information and the historical quality evaluation information and the EEG information may include: inputting the historical EEG information, the historical quality evaluation information, and the EEG information into a preset cigar quality evaluation model to extract the mapping relationship between the historical EEG information and the historical quality evaluation information, and determining the quality evaluation information of the target cigar by the user based on the mapping relationship and the EEG information.

[0078] In some embodiments, the preset cigar quality evaluation model may further include the aforementioned first model.

[0079] The above technical solution extracts the mapping relationship between historical electroencephalogram information and historical quality evaluation information by using a cigar quality evaluation model, thereby helping to improve the determination efficiency and accuracy of the mapping relationship.

[0080] In one embodiment, as Figure 2 shown, determining the quality evaluation information of the target cigar for the user based on the mapping relationship between historical electroencephalogram information and historical quality evaluation information and the electroencephalogram information may include steps S201 to S203:

[0081] Step S201: Convert the historical time-domain electroencephalogram signal in the historical electroencephalogram information into a historical frequency-domain electroencephalogram signal, and determine the total energy value of the historical power spectral density of the historical frequency-domain electroencephalogram signal in the target Hertz band to obtain historical electroencephalogram features.

[0082] Step S202: Convert the time-domain electroencephalogram signal in the electroencephalogram information into a frequency-domain electroencephalogram signal, and determine the total energy value of the power spectral density of the frequency-domain electroencephalogram signal in the target Hertz band to obtain the electroencephalogram features of the user.

[0083] Step S203: Determine the quality evaluation information of the target cigar for the user based on the mapping relationship between the historical electroencephalogram features and the historical quality evaluation information and the electroencephalogram features.

[0084] The above technical solution extracts features from the electroencephalogram information and determines the quality evaluation information according to the extracted features. Specifically: convert the time-domain electroencephalogram signal into a frequency-domain electroencephalogram signal, select the target Hertz band, calculate the corresponding total energy value of the power spectral density as the electroencephalogram features, and similarly obtain the historical electroencephalogram features. Then, based on the mapping relationship between the historical electroencephalogram features and the historical quality evaluation information and the electroencephalogram features, determine the quality evaluation information of the target cigar for the user. This helps to more accurately determine the quality evaluation information of the target cigar for the user.

[0085] In one embodiment, the above-mentioned cigar quality evaluation method may further include: preprocessing the electroencephalogram information; wherein, the preprocessing includes positioning electrode channels, converting reference electrodes, filtering, denoising, and intercepting an analysis segment and performing baseline correction.

[0086] The above technical solution preprocesses the electroencephalogram information to obtain better-quality electroencephalogram information, providing a more accurate basis for determining the subsequent quality evaluation information.

[0087] In an exemplary embodiment, based on the above-mentioned cigar quality evaluation method, a cigar quality evaluation system is provided. A dataset is established by collecting electroencephalogram signals when a user smokes a cigar and performing feature extraction, and a cigar quality evaluation system is constructed based on the dataset. The cigar quality evaluation system may include the following modules:

[0088] Electroencephalogram (EEG) signal acquisition module. This module consists of an EEG cap composed of multiple electrodes, which can acquire the EEG signals of users during the process of smoking cigars. The electrode distribution follows the international standard 10-20 system to ensure comprehensive and accurate capture of the electrical activities in different regions of the brain. The acquired EEG signals are amplified by a preamplifier and then converted from analog signals to digital signals through an analog-to-digital converter for subsequent processing.

[0089] Signal preprocessing module. It preprocesses the acquired EEG signals, including removing noise such as power frequency interference and electromyogram artifacts. Digital filtering techniques, such as Butterworth filters, are used to set appropriate cut-off frequencies to filter out unwanted frequency components. At the same time, other interference signals are further removed through algorithms such as independent component analysis (ICA) to improve the quality of the EEG signals.

[0090] Feature extraction module. It extracts features related to the cigar experience from the preprocessed EEG signals. These features include but are not limited to the power spectral density of different frequency bands (such as alpha wave, beta wave, theta wave, gamma wave), the time-domain features of the EEG signals (such as peak value, mean value, standard deviation, etc.), and the coherence between different brain regions. The power spectral density is calculated through the fast Fourier transform (FFT), the time-domain features are calculated using statistical methods, and the brain region coherence is calculated using the coherence analysis algorithm.

[0091] Quality evaluation module. Based on the extracted EEG features, a cigar quality evaluation model is established. This model is based on a large amount of experimental data and machine learning algorithms, such as support vector machine (SVM), neural network (such as multi-layer perceptron), etc. The newly acquired EEG features are input into the model, and the model outputs the evaluation results of the cigar quality, including dimensions such as taste evaluation (such as the degree of mellow, spicy, etc.), aroma evaluation (such as richness, persistence, etc.), and overall satisfaction.

[0092] As Figure 3 shown, the steps for the system to achieve cigar quality evaluation may include steps S301 to S304:

[0093] Step S301: Obtain the initial data set of the user's cigars, and the initial data set includes EEG data and evaluation label data.

[0094] The data can be collected and saved manually, so the cigar quality evaluation system can directly obtain and call it.

[0095] Exemplarily, preparatory work can be done manually in advance to serve the acquisition of EEG data. Specifically: 1. Prepare cigar samples in advance. According to the method of GB 15269.4-2011, balance the cigar samples in a cigar maintenance cabinet (relative humidity 60%, temperature 20°C) for more than 14 days. 2. Select users through questionnaires. The users are required to be adult males, with an average age of 24-30 years, no medical history, and a smoking age of more than three years. 3. Use manual sensory evaluation combined with quantitative description to score the flavor characteristics of the samples to construct a flavor evaluation profile. Use quantitative descriptive sensory evaluation to describe sensory characteristics, and use a 5-point intensity scale (1-5 points; very weak, weak, moderate, strong, very strong) to score the sensory intensity of each descriptor. The experimenter assigns the value "0" to the terms that the participants did not score. Each experiment is divided into three stages: the front stage, the middle stage, and the end stage. The sensory officers score the listed sensory descriptors in each time period in turn. 4. Implement the acquisition of their EEG signals through the EEG signal acquisition module. 5. Label and organize the collected EEG signals and subjective evaluation data to establish an initial data set.

[0096] In some embodiments, each subject (cigar user) is required to stop smoking the night before the experiment. Therefore, the subjects are deprived of the right to smoke about 10-12 hours before the experiment. Six different brands of cigars are used for testing. The subjects do not know which kind of cigar they are smoking. The experiment is carried out under quiet and undisturbed conditions, with good ventilation and no strange smell, white lighting, controlled temperature (20±2°C) and air flow conditions. All subjects use the local circulation smoking method in accordance with YC / T138-1998. For example, after the smoke enters the mouth and pauses slightly, it is slowly exhaled from the mouth and nose.

[0097] In some embodiments, pre-tests of electroencephalograms are performed on all subjects to check their electroencephalogram signals under various conditions, including the quiet state, movements with eyes open or closed, swallowing, eye movements, smiling, and detection of inner emotions. The purpose is to monitor their resting state and emotional fluctuations. In addition, the subjects are also trained to be familiar with the entire procedure of the preparation stage.

[0098] In some embodiments, the experimenter selects a suitable EEG cap according to the head circumference of the subject (to ensure that the electrodes fit the scalp). When wearing the EEG cap, the electrode positions are adjusted with reference to the bridge of the nose and the earlobes on both sides to determine the positions of the FPZ and REF reference electrodes. Conductive paste GT5 is supplemented for the wet electrodes, and the impedance of each electrode is adjusted to be less than 10KΩ to verify that the conductivity from the electrode to the head is sufficient.

[0099] In some embodiments, the acquisition process may be as follows: measure the length of each cigar, divide it into three equal parts (front section, middle section, and tail section), let the subject take 20 puffs for each part, control the puff time for each puff within 3 seconds, start collecting from the beginning of puffing, and the collection time is 15s; at the same time, use the method of automatically marking the Marker to collect events until 20 puffs are taken for each section. Throughout the process, the subject has no communication and is concentrated, but cannot fall asleep.

[0100] Step S302: Preprocess the EEG data.

[0101] As Figure 5 shown, a flowchart for preprocessing EEG data is provided. Specifically:

[0102] Use the EEGLAB plugin of Matlab software to preprocess the EEG data. The processing steps include:

[0103] ① Locate the electrode channels for each test data, and remove the useless ECG electrodes, HEOL horizontal electrooculogram electrodes, HEOG vertical electrooculogram electrodes, VEOU upper vertical electrooculogram electrodes, and VEOL lower vertical electrooculogram electrodes.

[0104] ② Convert the reference electrode and adopt the whole-brain average reference value.

[0105] ③ Through 1Hz high-pass filtering and 40Hz low-pass filtering, filter out the bands irrelevant to the research; in addition, filter the 49 - 51HZ filtering band to remove power frequency interference.

[0106] ④ Intercept the analysis segment and perform baseline correction. Segment the EEG (electroencephalogram, EEG) data through the stimulus presentation event, and intercept the EEG data between 1s before the stimulus occurs and 16s after the stimulus presentation.

[0107] ⑤ Use the independent component analysis (ICA) algorithm for analysis, and use IClable to mark and remove artifacts such as blinks, horizontal eye movements, muscle activities, and obvious electrode noises (marked as non-EEG activities) to ensure the integrity and smoothness of the EEG data.

[0108] ⑥ The same test person repeats the test 10 times under each group of conditions, and the test data of each test person under each group of conditions are superimposed and then averaged.

[0109] Step S303: Extract features from the EEG data, and mark the extracted features according to the evaluation label data to obtain the quality grade feature information.

[0110] Perform frequency-domain analysis on the preprocessed EEG signals. Convert the artifact-removed EEG signals from the time domain to the frequency domain through fast Fourier transform, calculate the power spectral density (PSD), and then calculate the total energy value (dB) of the PSD in specific Hertz bands. The division basis for each band is delta (1 - 3 Hz), theta (4 - 7 Hz), alpha (8 - 13 Hz), beta (14 - 30 Hz), gamma (31 - 50 Hz), so as to achieve feature extraction. Mark the EEG signal data as the corresponding quality grades (such as high, medium, and low quality) according to the participants' subjective evaluations of cigars.

[0111] In some embodiments, the system can select the energy values of EEG in different bands for repeated measures analysis of variance and paired-sample T-tests, and perform correlation analysis on the EEG data and evaluation label data to mark the extracted features and obtain quality grade feature information.

[0112] In some embodiments, as Figure 6 shown, the topographic maps of brain regions in different frequency bands of a subject during the suction of a certain type of sample cigar are randomly selected. It can be found that during suction, the brain activity in the middle section of the cigar is the most active. Among them, the active areas of the Delta band are mainly concentrated in the frontal, parietal, and occipital regions; the active areas of the Theta band are mainly concentrated in the parietal and occipital regions; the Alpha band and Beta band are mainly active in the occipital region.

[0113] In some embodiments, to compare the differences in EEG activities caused by suction of cigars of different brands, as shown in Figures 7(a) to 7(e), taking the middle section as an example, select three different brands of cigars HS, SX, and SS, and obtain the corresponding frequency-domain analysis results in bands such as delta (1 - 3 Hz), theta (4 - 7 Hz), alpha (8 - 13 Hz), beta (14 - 30 Hz), and gamma (31 - 50 Hz).

[0114] In some embodiments, to compare the differences in EEG activities caused by suction of different sections of cigars, select the data of 3 subjects suctioning a certain type of sample cigar for averaging and analysis. As Figure 8 shown, a possible frequency-domain analysis result of the front, middle, and rear sections of a certain type of sample cigar is given. The differences in the activity levels of other bands in the front, middle, and rear sections are relatively small, while the differences in the gamma band are obvious, and the middle section is more active as a whole. The Delta band is the most active in the frontal lobe, and the theta band, Alpha band, Beta band, and gamma band are mainly active in the occipital region.

[0115] Step S304: Train the preset initial evaluation model according to the quality grade characteristic information to obtain a cigar quality evaluation model for cigar quality evaluation.

[0116] In some embodiments, the preprocessed EEG signal feature data and the corresponding quality labels, i.e., quality grade characteristic information, can be divided into two data sets with 70% as the training set and 30% as the test set.

[0117] In some embodiments, the machine learning algorithm in the quality evaluation model can be trained using the training set. The support vector machine is selected as the classification model. Since the relationship between EEG signal features and quality grades may be non-linear, SVM with a kernel function (such as the radial basis function RBF) is used. Initialize the model parameters, including the penalty parameter C and the kernel function parameter γ. During the training process, the model adjusts the parameters of the hyperplane according to the relationship between EEG features and quality labels to find the decision boundary that can best distinguish different quality grades. The loss function of the model is minimized through an optimization algorithm (such as the gradient descent method), and this loss function usually measures the difference between the quality grade predicted by the model and the actual label.

[0118] Use the test set to verify the trained model and evaluate performance metrics such as the accuracy, recall rate, and F1 value of the model. If the performance does not meet the expectations, adjust the model parameters or improve the algorithm and retrain until the model performance meets the requirements.

[0119] In some embodiments, in practical applications, when a user purchases or uses the above system, an initial EEG signal acquisition and cigar experience evaluation need to be performed first to establish personal profile information. When the user smokes a new cigar, the system provides services for the user according to the above signal acquisition, preprocessing, feature extraction, and quality evaluation processes.

[0120] In some embodiments, the above system can regularly collect user feedback information, such as the preference for recommended cigars and changes in the new cigar experience, and use this feedback information to update the model and algorithm to improve the accuracy and personalization of the system.

[0121] The above system can evaluate cigar quality more objectively and accurately, provide personalized cigar selection suggestions for users, and enhance the user's cigar experience. At the same time, the above system also provides a new technical means for quality control and marketing in the cigar industry.

[0122] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0123] Based on the same inventive concept, an embodiment of the present application further provides a cigar quality evaluation device for implementing the above-mentioned cigar quality evaluation method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the cigar quality evaluation device provided below can refer to the limitations on the cigar quality evaluation method in the above text, and will not be repeated here.

[0124] In an exemplary embodiment, as Figure 9 shown, a cigar quality evaluation device 900 is provided, including:

[0125] An acquisition module 901, configured to acquire the electroencephalogram information, image information of the user using the target cigar, and the identity information of the user;

[0126] A first determination module 902, configured to determine the personal information library corresponding to the user from a preset archive library based on the identity information; identify the burning state of the target cigar in the image information to determine the burning stage corresponding to the target cigar as the target burning stage; the burning stage includes the front section, middle section, and tail section of the cigar;

[0127] A second determination module 903, configured to determine the historical electroencephalogram information and historical quality evaluation information in the same burning stage as the target burning stage from the personal information library; and determine the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information.

[0128] In one embodiment, the second determination module 903 is further configured to determine the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information, including: determining the first quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information; and is further configured to obtain the evaluation information of the user for the target cigar; the evaluation information includes at least one of evaluation voice information, evaluation text information, and scoring information; obtaining an evaluation feature based on the evaluation information, and determining the second quality evaluation information of the user for the target cigar based on the evaluation feature; and determining the quality evaluation information of the user for the target cigar according to the first quality evaluation information and the second quality evaluation information.

[0129] In one embodiment, the second determination module 903 is further configured to obtain an evaluation feature based on the evaluation information, and determine the second quality evaluation information of the user for the target cigar based on the evaluation feature, including: inputting the evaluation information into a preset first model to extract the evaluation feature, and determining the cigar quality level corresponding to the evaluation feature from a preset cigar quality level table as the second quality evaluation information of the user for the target cigar.

[0130] In one embodiment, the second determination module 903 is further configured to determine the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information, including: inputting the historical electroencephalogram information, the historical quality evaluation information, and the electroencephalogram information into a preset cigar quality evaluation model to extract the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information, and determining the quality evaluation information of the user for the target cigar based on the mapping relationship and the electroencephalogram information.

[0131] In one embodiment, the second determination module 903 is further configured to determine the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information, including: converting the historical time-domain electroencephalogram signal in the historical electroencephalogram information into a historical frequency-domain electroencephalogram signal, and determining the total energy value of the historical power spectral density of the historical frequency-domain electroencephalogram signal in the target Hertz band to obtain a historical electroencephalogram feature; converting the time-domain electroencephalogram signal in the electroencephalogram information into a frequency-domain electroencephalogram signal, and determining the total energy value of the power spectral density of the frequency-domain electroencephalogram signal in the target Hertz band to obtain the electroencephalogram feature of the user; and determining the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram feature and the historical quality evaluation information and the electroencephalogram feature.

[0132] In one embodiment, the acquisition module 901 is further configured to preprocess the electroencephalogram information; wherein, the preprocessing includes positioning electrode channels, converting reference electrodes, filtering, denoising, and intercepting an analysis segment and performing baseline correction.

[0133] Each module in the above cigar quality evaluation device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0134] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 10 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data required to execute the cigar quality evaluation method, such as electroencephalogram information, etc. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a cigar quality evaluation method.

[0135] Those skilled in the art can understand that Figure 10 the structure shown in

[0136] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0136] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps in each of the above method embodiments.

[0137] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, it implements the steps in each of the above method embodiments.

[0138] In an embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, it implements the steps in each of the above method embodiments.

[0139] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0140] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0141] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for evaluating the quality of cigars, characterized in that, The method includes: Obtaining electroencephalogram information, image information of the user using the target cigar, and the identity information of the user; Based on the identity information, determining the personal information library corresponding to the user from a preset archive; Identifying the burning state of the target cigar in the image information to determine the corresponding burning stage of the target cigar as the target burning stage; the burning stage includes the front section of the cigar, the middle section of the cigar, and the tail section of the cigar; Determining the historical electroencephalogram information and historical quality evaluation information in the same burning stage as the target burning stage from the personal information library; and Based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information, determining the quality evaluation information of the user for the target cigar.

2. The method according to claim 1, wherein The determining the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information includes: determining the first quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information; The method further includes: Obtaining the evaluation information of the user for the target cigar; the evaluation information includes at least one of evaluation voice information, evaluation text information, and scoring information; Based on the evaluation information, obtaining evaluation features, and based on the evaluation features, determining the second quality evaluation information of the user for the target cigar; Determining the quality evaluation information of the user for the target cigar according to the first quality evaluation information and the second quality evaluation information.

3. The method according to claim 2, wherein The obtaining evaluation features based on the evaluation information and determining the second quality evaluation information of the user for the target cigar based on the evaluation features includes: Inputting the evaluation information into a preset first model to extract the evaluation features, and determining the cigar quality grade corresponding to the evaluation features from a preset cigar quality grade table as the second quality evaluation information of the user for the target cigar.

4. The method according to claim 1, characterized in that, The determining the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information includes: Inputting the historical electroencephalogram information, the historical quality evaluation information, and the electroencephalogram information into a preset cigar quality evaluation model to extract the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information, and based on the mapping relationship and the electroencephalogram information, determining the quality evaluation information of the user for the target cigar.

5. The method according to claim 1, characterized in that The determining the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical electroencephalogram information and the historical quality evaluation information and the electroencephalogram information includes: Converting the historical time-domain electroencephalogram signal in the historical electroencephalogram information into a historical frequency-domain electroencephalogram signal, and determining the total energy value of the historical power spectral density of the historical frequency-domain electroencephalogram signal in the target Hertz band to obtain historical electroencephalogram features; Convert the time-domain electroencephalogram (EEG) signal in the EEG information into a frequency-domain EEG signal, and determine the total energy value of the power spectral density of the frequency-domain EEG signal in the target Hertz band to obtain the EEG characteristics of the user; Based on the mapping relationship between the historical EEG characteristics and the historical quality evaluation information and the EEG characteristics, determine the quality evaluation information of the user for the target cigar.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Preprocess the EEG information; Wherein, the preprocessing includes positioning electrode channels, converting reference electrodes, filtering, denoising, and intercepting an analysis segment and performing baseline correction.

7. A cigar quality evaluation device, characterized in that, The device includes: An acquisition module, configured to acquire the EEG information, image information of a user using a target cigar, and the identity information of the user; A first determination module, configured to determine, based on the identity information, a personal information library corresponding to the user from a preset archive; identify the burning state of the target cigar in the image information to determine the burning stage corresponding to the target cigar as the target burning stage; the burning stage includes the front section of the cigar, the middle section of the cigar, and the tail section of the cigar; A second determination module, configured to determine the historical EEG information and historical quality evaluation information in the same burning stage as the target burning stage from the personal information library; and determine the quality evaluation information of the user for the target cigar based on the mapping relationship between the historical EEG information and the historical quality evaluation information and the EEG information.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images