A packaging material evaluation method based on fuzzy network DEA integrating sensory experience

Abstract

The present invention discloses a fuzzy network DEA packaging material evaluation method integrating sensory experience, constructs an evaluation index system of packaging material sensory experience from the perspective of consumer sensory experience, sets index data and performs fuzzy processing on the index data, establishes a fuzzy three-stage network data envelopment analysis model and performs calculation and solution, ranks the calculated applicability results, obtains fuzzy network DEA packaging material evaluation results integrating sensory experience, and provides the best material selection scheme for decision makers. The present invention divides the complex system of sensory experience of packaging materials into three stages, namely, from the physical properties of materials to the physiological reactions of consumers to the emotional reactions, and performs fuzzy processing on uncertain subjective evaluations, thereby improving the accuracy of packaging material applicability evaluation, and can effectively provide decision-making schemes for packaging designers to select packaging materials.

Description

Technical Field

[0001] The present invention is a packaging material evaluation method, and more particularly, relates to a fuzzy network DEA packaging material evaluation method integrating sensory experience, and mainly relates to the field of packaging science and technology. Background Art

[0002] There are thousands of packaging materials with widely varying performances, which makes choosing the right packaging material for a particular product a difficult task. The selection of packaging materials should not only consider the conventional physical and chemical properties of the materials, but also pay attention to the sensory experience of the consumer. Packaging is not only a container for a product, but also a carrier of consumer experience. When consumers buy a product for the first time, visual information often dominates, but in the consumer decision-making behavior of repurchasing products, the non-visual sensory experience such as touch, taste and convenience of using the packaging that the packaging brings to consumers will play a more critical role. It is impossible to isolate various senses when analyzing human behavior, and a holistic, multimodal approach is needed in sensory material evaluation. Therefore, making material selection decisions from the perspective of consumer sensory experience is both realistic and challenging.

[0003] Although most studies on material selection focus only on engineering, economics, and the environment, in recent years, consumer sensory experience has received increasing attention. For example, "Characterizing Consumer Emotional Response to Milk Packaging Guides Packaging Material Selection" in "Food Quality and Preference" and "The Effects of Inner Packaging Color on the Desirability of Food" in "Journal of Retailing and Consumer Services". The main advantage of these studies is that they can find out the material characteristics that affect consumer sensory experience. However, they only evaluate materials based on consumers' subjective evaluations, and only perform simple analyses such as correlation and regression analysis; and they consider fewer influencing factors. After all, the calculation amount of multi-factor analysis and evaluation is very large.

[0004] In response to the complex material selection problem, domestic and foreign scholars have proposed many multi-criteria decision-making models. The published literature includes: "A comprehensive mcdm-based approach using TOPSIS, COPRAS and DEA as an auxiliary tool for material selection problems" in "Materials & Design"; "Material selection in green design: a method combining DEA and TOPSIS" in "Sustainability", etc. Among them, data envelopment analysis (DEA) is widely used to study the relative effectiveness of multiple solutions. Since the advent of DEA, it has been continuously developed and improved. Whether it is to improve on the basis of the original model or to combine DEA with other models to "complement each other's strengths and weaknesses", many research results have been achieved. However, to date, there has been no report on the direct application of the fuzzy three-stage network data envelopment analysis model to evaluate the suitability of packaging materials.

[0005] Two patents need to be specially pointed out: the first is the Chinese patent "A method for evaluating the greenness of packaging using a multi-stage network data envelopment analysis model" (patent number CN 109447453 A); the second is the Chinese patent "A method for identifying the root cause of early product failure based on fuzzy data processing" (patent number CN 105975797 B). These two background technologies belong to the G06Q10 / 06 technical field with the present invention, solve the most similar technical problems, and disclose the most technical features, so they are the closest prior arts to the present invention. Although patent CN 105975797 B involves fuzzy data envelopment analysis, patent CN 109447453 A provides inspiration for using network data envelopment analysis to solve the problem that the traditional DEA model regards the entire system decision-making process as a "black box" and does not analyze its internal structure, but this method has the problem that the analysis is not accurate enough and it cannot clearly analyze the sensory experience of the packaging material. Therefore, its application is subject to some limitations, and it is necessary to improve it. Summary of the invention

[0006] The present invention aims at the shortcomings of the existing evaluation methods and provides a fuzzy network DEA packaging material evaluation method and method that integrates sensory experience. The selection of packaging materials requires analyzing many indicators, processing a large amount of data, weighing various factors and making the best decision. In addition, human behavior is not easy to analyze. This will be a huge and complex system. The technical problem to be solved by the present invention is to select packaging materials from the perspective of consumer sensory experience, and to visualize and simplify the complex problem of sensory experience of packaging materials so as to more accurately evaluate the applicability of packaging materials. The technical feature that distinguishes the present invention from the prior art is that in order to more accurately and clearly analyze the complex problem of sensory experience of packaging materials, the system is divided into three stages, namely, from the physical properties of the material to the physiological response of the consumer to the emotional response, and at the same time, the uncertain subjective evaluation is fuzzy. This technical feature is not common knowledge, and the present invention is not a simple superposition of two patents in the background technology. For those skilled in the art, the technical solution of the present invention is not obvious relative to the combination of these two patents.

[0007] The technical solution proposed in the present invention is: a fuzzy network DEA packaging material evaluation method integrating sensory experience, which constructs an evaluation index system for the sensory experience of packaging materials from the perspective of consumer sensory experience, then sets index data and performs fuzzy processing on the index data, and at the same time establishes a fuzzy three-stage network data envelopment analysis model and performs calculation and solution, and ranks the calculated suitability results to obtain the fuzzy network DEA packaging material evaluation results integrating sensory experience, thereby providing decision makers with the best material selection plan.

[0008] Furthermore, the fuzzy network DEA packaging material evaluation method integrating sensory experience includes the following steps:

[0009] (1) Establish an evaluation index system for the sensory experience of packaging materials;

[0010] (2) Fuzzy the indicator data;

[0011] (3) Establish a fuzzy three-stage network data envelopment analysis model for computational solution;

[0012] (4) The calculated suitability results are ranked to provide the best material selection options for decision makers.

[0013] Furthermore, the three stages include:

[0014] (1) Material expression stage, that is, the stage in which packaging materials convey information to consumers;

[0015] (2) sensory response stage, that is, the stage in which the perceptual system responds automatically;

[0016] (3) The emotional response stage, which is the consumer’s response stage at the cognitive level.

[0017] Furthermore, the applicability is obtained by summing the products of the efficiency values ​​of the three stages and the weights of each stage, and is recorded as CSI.

[0018] Furthermore, the evaluation index system for constructing the sensory experience of packaging materials is to select evaluation indicators of each stage of the sensory experience of packaging materials to establish the evaluation index system, and the input and output indicators of the evaluation indicators include:

[0019] (1) Sensory property indicators of packaging materials, including hue, gloss, light transmittance, hardness, density, etc.;

[0020] (2) Sensory evaluation indicators, including eye-catching, smooth, hard, etc., which describe the human sensory aspects;

[0021] (3) Physiological signal indicators, including eye tracking, EEG, heart rate and other physiological test related indicators;

[0022] (4) Emotional evaluation indicators, including evaluation indicators that describe human emotions such as comfort, pleasure, and excitement.

[0023] Furthermore, the sensory attribute index and physiological signal index of the packaging material are obtained through experiments.

[0024] Furthermore, the sensory evaluation and emotional evaluation are both subjective evaluation scores, obtained through questionnaires, and expressed in the form of triangular fuzzy numbers.

[0025] Furthermore, the fuzzy processing refers to converting the fuzzy value obtained through the consumer's subjective rating into a triangular fuzzy number. Indicates that Where N L ,N,N R They represent the left boundary, right boundary and main value of the interval respectively.

[0026] Furthermore, the establishment of the fuzzy three-stage network data envelopment analysis model and the calculation and solution are to convert the fuzzy number into α cut sets of different levels at the confidence level α∈[0,1]; set g decision-making units DMU to be evaluated, and calculate the efficiency E1, E2, and E3 of the three stages; wherein, in the first stage, for each DMU j, there are m packaging material attribute indicators as input indicators, the efficiency E1 of the first stage is the ratio of input to output in this stage, representing the expressiveness of the material, that is, the ability of the packaging material to convey information to consumers; in the second stage, the output indicators of the first stage are used as the input indicators of this stage, and the d2 physiological signal indicators of consumers are used as output indicators. The efficiency E2 of the second stage is the ratio of input to output in this stage, representing sensory quality, that is, the perception system's ability to perceive materials; in the third stage, the output indicators of the second stage are used as the input indicators of this stage, and the r emotional evaluation indicators of consumers are used as output indicators. The efficiency E3 of the third stage is the ratio of input to output in this stage, representing emotional arousal, that is, the subjective preference of consumers at the cognitive level;

[0027] The main function of the fuzzy three-stage network data envelopment analysis model is set as:

[0028] maxCSI=W1·E1+W2·E2+W3·E3 (1)

[0029] Where:

[0030] W1 is the weight coefficient of the first stage

[0031] E1 is the first stage efficiency: the performance of the material

[0032] W2 is the weight coefficient of the second stage

[0033] E2 is the second stage efficiency: sensory quality

[0034] W3 is the weight coefficient of the third stage

[0035] E3 is the third stage efficiency: emotional stimulation;

[0036] Following the idea of ​​mathematical programming to solve the problem, a three-stage nonlinear programming model is first established; then, under the constraint that all efficiencies in DEA do not exceed 1, the nonlinear programming is converted into a fractional programming; then, through Charnes-Cooper transformation, the fractional programming is converted into a linear programming; in order to solve the efficiency of each DMU, ​​the linear programming is converted into a dual programming; finally, using triangular fuzzy numbers, the fuzzy programming is converted into a deterministic programming, that is, the evaluated decision-making unit DMU f The input of the reference decision unit takes the maximum value and the output takes the minimum value. Obviously, DMU f The DEA effectiveness reaches the maximum value, which is the most optimistic estimate; on the contrary, DMU f The DEA effectiveness reaches the minimum value, which is the most pessimistic estimate;

[0037] In order to compare the effectiveness of each DMU in an overall sense, a number of points k are uniformly selected in the interval [0,1] of the confidence level α.i (i=1,2,…,k), then the minimum and maximum values ​​of the relative effectiveness of the decision-making unit are The weights are The average confidence validity of the decision-making unit is and the average confidence weight They are:

[0038]

[0039] Finally, the overall suitability CSI is obtained

[0040]

[0041] This is used as a fuzzy three-stage network data envelopment analysis model to evaluate packaging materials.

[0042] The beneficial technical effects of the present invention are:

[0043] The present invention organically combines the evaluation of packaging materials with people's own psychological perception. In classical cognitive psychology, perception and cognition are considered to be two stages in which the body processes external information at the physiological and psychological levels respectively. In order to analyze the relationship between packaging materials and consumers' sensory experience and thus evaluate packaging materials, this process is divided into three stages, namely, packaging materials are used as stimulus sources, the human body's perception system automatically detects these stimuli and makes corresponding physiological responses, and then enters the cognitive stage to produce emotional responses. Compared with the prior art, the beneficial effects achieved by the present invention are: dividing the evaluation system into three stages to "open the black box", further analyzing the relationship between packaging materials and consumers' sensory experience, visualizing the abstract issue of consumers' sensory experience, and performing fuzzy processing to resolve the uncertainty in consumers' sensory experience, thereby jointly improving the accuracy of the evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of the method flow of the present invention;

[0045] Figure 2 It is a schematic diagram of the fuzzy three-stage network data envelopment analysis model of the present invention. DETAILED DESCRIPTION

[0046] Please refer to Figure 1 This is a fuzzy network DEA packaging material evaluation method based on the integration of sensory experience. The method uses fuzzy theory and a three-stage network data envelopment analysis model. The method includes the following steps:

[0047] S1: Construct an evaluation index system for sensory experience of packaging materials;

[0048] S2: Fuzzy the indicator data;

[0049] S3: Establish a fuzzy three-stage network data envelopment analysis model for computational solution;

[0050] S4: Rank the calculated suitability results to provide the best material selection options for decision makers.

[0051] Furthermore, the applicability is obtained by summing the products of the efficiency values ​​of the three stages and the weights of each stage, and is recorded as CSI.

[0052] Furthermore, the three stages include:

[0053] 1) Material performance stage, that is, the stage where packaging materials convey information to consumers;

[0054] 2) sensory response stage, that is, the stage in which the perceptual system responds automatically;

[0055] 3) Emotional response stage, which is the consumer’s response stage at the cognitive level.

[0056] Furthermore, the evaluation index system of the sensory experience of packaging materials in step S1 selects evaluation indicators for each stage, and its input and output indicators include:

[0057] 1) Sensory attribute indicators of packaging materials, including hue, gloss, light transmittance, hardness, density, etc.;

[0058] 2) Sensory evaluation indicators, including eye-catching, smooth, hard and other evaluation indicators that describe human sensory aspects;

[0059] 3) Physiological signal indicators, including eye tracking, EEG, heart rate and other physiological test related indicators;

[0060] 4) Emotional evaluation indicators, including evaluation indicators that describe human emotions such as comfort, pleasure, and excitement.

[0061] Furthermore, the fuzzy processing in step S2 refers to converting the fuzzy value obtained by the consumer's subjective rating into a triangular fuzzy number. Indicates that Where N L , N R , N represents the left and right boundaries and the main value of the interval respectively.

[0062] Furthermore, the fuzzy network DEA packaging material evaluation method integrating sensory experience is characterized in that the step S3 establishes a fuzzy three-stage network data envelopment analysis model, and the formula is as follows:

[0063] In the confidence level α∈[0,1], the fuzzy number is converted into α cut-offs at different levels: in Except for the indicators related to subjective scoring, other indicators are non-fuzzy numbers. For the convenience of calculation, these indicators can be expressed in the form of fuzzy numbers with the same left and right boundaries and main values.

[0064] Assume that there are g decision making units DMU to be evaluated (DMU = {DMU1, DMU2, DMU3, ..., DMU g}). In the first stage, m packaging material attribute indicators are used as input indicators, expressed as The output index is the sensory evaluation index of d1 consumers, expressed as The efficiency E1 of the first stage is the ratio of input to output in this stage, which represents the expressiveness of the material, that is, the ability of the packaging material to convey information to consumers. In the second stage, the output index of the first stage is used as the input index of this stage, and the d2 physiological signal indexes of consumers are used as output indexes, expressed as The efficiency E2 of the second stage is the ratio of input to output in this stage, which represents sensory quality, that is, the perception system's ability to perceive materials. In the third stage, the output index of the second stage is used as the input index of this stage, and the r emotional evaluation indexes of consumers are used as output indicators, expressed as The efficiency E3 of the third stage is the ratio of input to output in this stage, which represents emotional arousal, that is, the subjective preference of consumers at the cognitive level.

[0065] Set the main function maxCSI to:

[0066] maxCSI=w1·E1+w2·E2+w3·E3

[0067] Efficiency of each stage:

[0068]

[0069] The weight of each stage:

[0070]

[0071] w1+w2+w3=1

[0072] The above formulas are sorted out to obtain the nonlinear programming model:

[0073]

[0074] make γ=tη,θ=tu,π=tv,through Charnes-Cooper transformation, the fractional programming is converted into a linear programming for solution:

[0075]

[0076] Convert the linear programming into dual programming. For the fth decision making unit DMU f :

[0077] In the first stage,

[0078] min e1

[0079]

[0080] In the second stage,

[0081] min e2

[0082]

[0083] In the third stage,

[0084] min e3

[0085]

[0086] The three-stage network DEA is fuzzy expanded. Under the confidence level α, the parameters corresponding to the minimum and maximum values ​​of each evaluation index of the decision-making unit are Convert fuzzy planning into deterministic planning. That is, the evaluated decision-making unit DMU f The input of the reference decision unit takes the maximum value and the output takes the minimum value. Obviously, DMU f The DEA effectiveness is maximized. On the contrary, DMU f The DEA effectiveness reaches the minimum value, which is the most pessimistic estimate.

[0087] For the first stage, the most pessimistic estimate of the decision-making unit situation at the current confidence level is the minimum planning:

[0088]

[0089] The most optimistic estimate of the decision-making unit situation at the current confidence level is the maximum planning:

[0090]

[0091] For the second stage, minimum value planning:

[0092]

[0093] Maximum value planning:

[0094]

[0095] For the third stage, minimum planning:

[0096]

[0097] Maximum value planning:

[0098]

[0099] Maximum planning and minimum planning provide us with a closed interval of relative effectiveness through extreme estimates of the most optimistic and pessimistic situations. However, when the confidence level α takes any value in [0,1], it is difficult to explain the effectiveness of the decision-making unit in an overall sense. Even when the confidence level is 1, a DEA-effective decision-making unit cannot guarantee DEA effectiveness at other confidence levels. Therefore, in order to compare and rank the relative effectiveness of decision-making units under fuzzy conditions, it is not enough to simply compare the effective values ​​at a certain confidence level, but it is necessary to compare and judge the overall situation of the fuzzy target values ​​of the decision-making units. Therefore, the average value of the values ​​taken at multiple confidence levels is used instead of the true effective value of DEA. That is, a number of points k are uniformly selected in the interval [0,1] of the confidence level α, α i (i=1,2,…,k), the minimum and maximum values ​​of the relative effectiveness of the decision-making unit are The weights are Then the average confidence validity and average confidence weight of the decision unit are:

[0100]

[0101] The overall consumer suitability can be expressed as:

[0102]

[0103] According to the above method, use the following Figure 1 The fuzzy network DEA packaging material evaluation method based on fusion sensory experience is shown in Figure 2 The schematic diagram of the fuzzy three-stage network data envelopment analysis model is shown in Figure 1. It is assumed that this embodiment is to evaluate the suitability of 12 different cosmetic bottle packaging materials for consumer sensory experience. An evaluation index system for the sensory experience of cosmetic bottle packaging materials is constructed, and the evaluation index data of each stage of the 12 decision units are collected as shown in Tables 1, 2, 3, and 4. The data of material attribute index and physiological signal index are obtained through experiments; sensory evaluation and emotional evaluation are both subjective evaluation scores, obtained through questionnaires, and expressed in the form of triangular fuzzy numbers.

[0104] Table 1 Material property index data

[0105]

[0106]

[0107] Table 2 Sensory evaluation index data

[0108]

[0109]

[0110] Table 3 Physiological signal index data

[0111]

[0112] Note: The number of fixation points and fixation duration are indicators related to eye tracking; heart rate and LF / HF (the ratio of low-frequency to high-frequency power of heart rate variability) are indicators related to heart rate; SMR (Hz), βL (Hz), and βH (Hz) are brain rhythms and are indicators related to EEG.

[0113] Table 4 Emotional evaluation index data

[0114]

[0115] Build as attached Figure 2 The fuzzy three-stage network data envelopment analysis model shown in the figure is encoded and calculated using Python software. 10 points are uniformly selected in the interval [0,1] of the confidence level α, that is, k = 10. Due to space limitations, only α is given. i The values ​​of efficiency and weight of each stage when =0.1 are shown in Table 5. Finally, the CSI results of these 12 decision-making units are obtained, as shown in Table 6.

[0116] Table 5 α i =0.1 Efficiency and weight of each stage

[0117]

[0118]

[0119] Table 6 CSI results and rankings

[0120]

[0121] The analysis and calculation results lead to the evaluation conclusion: the consumer applicability of the 12th packaging material is the highest, and when the confidence is the lowest, the efficiency of the three stages of this material is 1, which is effective compared with other units. The 9th packaging material follows closely, and the worst is the 11th packaging material. DEA does not need to manually set the influence weights of each evaluation index in advance, but selects relatively effective sample individuals through mathematical programming, so that decision makers can scientifically and efficiently select the best material from the alternative materials.

[0122] The explanations of the symbols in the above embodiments are as follows:

[0123]

[0124]

[0125]

[0126]

[0127] The above is a description of the specific implementation of the present invention in conjunction with the accompanying drawings, but these descriptions cannot be understood as limiting the scope of the present invention. The protection scope of the present invention is defined by the attached claims, and any non-inventive changes based on the claims of the present invention are within the protection scope of the present invention. This embodiment clarifies the complex sensory experience of consumers through this series of measures, and can more accurately evaluate the applicability of packaging materials compared to conventional evaluation methods.

Claims

1. A fuzzy network DEA packaging material evaluation method based on fusion sensory experience, characterized by: From the perspective of consumer sensory experience, an evaluation index system for the sensory experience of packaging materials is constructed. Then, the index data is set and fuzzy processed. At the same time, a fuzzy three-stage network data envelopment analysis model is established and calculated and solved. The calculated suitability results are ranked to obtain the fuzzy network DEA packaging material evaluation results that integrate sensory experience, providing decision makers with the best material selection plan. The fuzzy network DEA packaging material evaluation method integrating sensory experience includes the following steps: (1) Establish an evaluation index system for the sensory experience of packaging materials; (2) Fuzzy the indicator data; (3) Establish a fuzzy three-stage network data envelopment analysis model for computational solution; (4) Rank the calculated suitability results to provide decision makers with the best material selection options; in, The establishment of the fuzzy three-stage network data envelopment analysis model and the calculation and solution are to convert the fuzzy number into α cut sets of different levels at the confidence level α∈[0,1]; set g decision-making units DMU to be evaluated, and calculate the efficiency E1, E2, and E3 of the three stages; wherein, in the first stage, for each DMU j , there are m packaging material attribute indicators as input indicators, the efficiency E1 of the first stage is the ratio of input to output of this stage as the output indicator, and the output indicator is d1 consumers' sensory evaluation indicators, which represent the expressiveness of the material, that is, the ability of the packaging material to convey information to consumers; in the second stage, the output indicator of the first stage is used as the input indicator of this stage, and the d2 physiological signal indicators of consumers are used as output indicators. The efficiency E2 of the second stage is the ratio of input to output of this stage, which represents the sensory quality, that is, the perception system's ability to perceive materials; in the third stage, the output indicator of the second stage is used as the input indicator of this stage, and the r emotional evaluation indicators of consumers are used as output indicators. The efficiency E3 of the third stage is the ratio of input to output of this stage, which represents emotional arousal, that is, the subjective preference of consumers at the cognitive level; The main function of the fuzzy three-stage network data envelopment analysis model is set as: maxCSI=W1·E1+W2·E2+W3·E3 (1) Where: W1 is the weight coefficient of the first stage E1 is the first stage efficiency: the performance of the material W2 is the weight coefficient of the second stage E2 is the second stage efficiency: sensory quality W3 is the weight coefficient of the third stage E3 is the third stage efficiency: emotional stimulation; Following the idea of ​​mathematical programming to solve the problem, a three-stage nonlinear programming model is first established; then, under the constraint that all efficiencies in DEA do not exceed 1, the nonlinear programming is converted into a fractional programming; then, the fractional programming is converted into a linear programming through Charnes-Cooper transformation; in order to solve the efficiency of each DMU, ​​the linear programming is converted into a dual programming; finally, triangular fuzzy numbers are used to convert the dual programming into a deterministic programming, that is, the decision-making unit DMU being evaluated f The input of the reference decision unit takes the maximum value and the output takes the minimum value. Obviously, DMU f The DEA effectiveness reaches the maximum value, which is the most optimistic estimate; on the contrary, DMU f The DEA effectiveness reaches the minimum value, which is the most pessimistic estimate; In order to compare the effectiveness of each DMU in an overall sense, a number of points k are uniformly selected in the interval [0,1] of the confidence level α. i (i=1,2,…,k), the minimum and maximum values ​​of the relative effectiveness of the decision-making unit are The weights are The average confidence validity of the decision-making unit is and the average confidence weight They are: Finally, the overall suitability CSI is obtained This is used as a fuzzy three-stage network data envelopment analysis model to evaluate packaging materials.

2. The fuzzy network DEA packaging material evaluation method based on fusion sensory experience according to claim 1 is characterized in that: The three stages described include: (1) Material expression stage, that is, the stage in which packaging materials convey information to consumers; (2) sensory response stage, that is, the stage in which the perceptual system responds automatically; (3) The emotional response stage, which is the consumer’s response stage at the cognitive level.

3. The fuzzy network DEA packaging material evaluation method based on fusion sensory experience according to claim 1 is characterized in that: The fitness is obtained by summing the products of the efficiency values ​​of the three stages and the weights of each stage, and is denoted as CSI.

4. The fuzzy network DEA packaging material evaluation method based on fusion sensory experience according to claim 1 is characterized in that: The evaluation index system for constructing the sensory experience of packaging materials is to select the evaluation indexes of each stage of the sensory experience of packaging materials to establish the evaluation index system. The input and output indicators of the evaluation indexes include: (1) Sensory attribute indicators of packaging materials, including hue, gloss, light transmittance, hardness, and density; (2) sensory evaluation indicators, including eye-catching, smooth, and hard evaluation indicators that describe human sensory aspects; (3) Physiological signal indicators, including relevant indicators of eye tracking, EEG, and heart rate physiological tests; (4) Emotional evaluation indicators, including evaluation indicators that describe human emotions such as comfort, pleasure, and excitement.

5. The fuzzy network DEA packaging material evaluation method based on fusion sensory experience according to claim 4 is characterized in that: The sensory attribute index and physiological signal index of the packaging material are obtained through experiments.

6. The fuzzy network DEA packaging material evaluation method based on fusion sensory experience according to claim 4 is characterized in that: The sensory evaluation and emotional evaluation are both subjective evaluation scores, obtained through questionnaires, and expressed in the form of triangular fuzzy numbers.

7. The fuzzy network DEA packaging material evaluation method based on fusion sensory experience according to claim 4 is characterized in that: The fuzzy processing mentioned above refers to converting the fuzzy value obtained through the consumer's subjective rating into a triangular fuzzy number. Indicates that Where N L , N R , N represents the left and right boundaries and the main value of the interval respectively.

Images