Bicycle characteristic optimization design method based on eye movement and electroencephalogram

Abstract

The invention discloses a bicycle feature optimization design method based on eye movement and electroencephalogram. The method comprises the steps that S1, a bicycle target sample picture is selected to be preprocessed, and bicycle morphological feature areas are divided; s2, a subject wears an electroencephalogram cap, the position and the sitting posture of the subject are adjusted, the head position of the subject is corrected, the sight of the subject moves along with a red dot in a screen, and an experiment task is started after the error reaches the standard; s3, collecting eye movement data of the subject in the bicycle morphological feature observation area through an eye movement tracker to obtain eye movement evaluation indexes; electroencephalogram data of the subject in the bicycle morphological characteristic observation area is collected through electroencephalogram equipment to obtain electroencephalogram indexes; s4, obtaining a bicycle feature design optimization process through the combination of the eye movement index and the electroencephalogram index; according to the method, direct data of selective attention of the user in the cognitive recognition process can be obtained through the eye movement tracking technology and the electroencephalogram technology to be applied to bicycle design, the bicycle design efficiency and accuracy are improved, the requirement of the market for high-quality bicycle design is met, and the wide market prospect is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of bicycle feature design based on human-computer interaction, and in particular to a bicycle feature optimization design method based on eye movement and electroencephalogram technology. Background Art

[0002] Visual cognition is the process by which humans acquire, process and understand external information through the visual system, and is one of the important ways for humans to understand the world. In bicycle design, visual feature cognition is of great significance for shaping brand image and conveying product value. By deeply understanding the user's visual cognitive process, the user's aesthetic preferences and needs can be grasped more accurately, so as to design bicycle brand features that are more in line with user expectations. However, traditional bicycle design relies on the designer's intuition and experience, lacks scientific design processes and user feedback mechanisms, and often fails to fully consider the user's visual cognition, resulting in a mismatch between design and user cognition. In the past studies of the current traditional bicycle feature design process, the discussion of bicycle feature design is mostly limited to subjective perceptual analysis, and few studies have used the user's objective eye movement and EEG data to guide the optimization design research of bicycles. The application of eye tracking technology and EEG technology in user experience research is becoming more and more extensive. These two technologies can provide users with intuitive reactions and cognitive states when observing and using products, providing new evaluation and optimization means for product design. Therefore, the present invention proposes a bicycle feature optimization design method based on eye movement and EEG. Summary of the invention

[0003] In view of the difficulties in the existing technology, the present invention aims to capture the user's visual attention and cognitive response through objective data, overcome the limitations of existing design methods, and form a bicycle feature optimization design method. The bicycle feature optimization design is driven by the user-centered perspective and the objective data of user cognition to ensure that the bicycle features can be more effectively conveyed to consumers. Based on this method, it helps to solve the problem of lack of scientific aesthetic evaluation and user feedback in the existing bicycle feature design, thereby improving the scientificity and rationality of the design. A bicycle feature optimization design method combining eye tracking and electroencephalogram technology is proposed.

[0004] In order to solve the problems of the prior art, the present invention adopts the following technical solutions:

[0005] A bicycle feature optimization design method based on eye movement and EEG includes the following steps:

[0006] S1: Select bicycle target sample images for preprocessing and divide bicycle morphological feature areas;

[0007] S2: The subject wears an EEG cap, and adjusts the subject's position and sitting posture, corrects the subject's head position, and the subject's gaze moves with the red dot on the screen. After the error reaches the standard, the subject enters the experimental task;

[0008] S3: The eye movement data of the subjects when observing the characteristic area of ​​the bicycle shape are collected by an eye tracker to obtain eye movement evaluation indicators; the EEG data of the subjects when observing the characteristic area of ​​the bicycle shape are collected by an EEG device to obtain EEG indicators;

[0009] S4: The optimization process of bicycle feature design is obtained by combining eye movement indicators and EEG indicators, including;

[0010] The recognition order of the bicycle morphological feature areas by the subjects was obtained according to the first fixation time of the subjects on the AOI of the bicycle morphological feature areas;

[0011] The feature key identification area of ​​the first bicycle morphological feature design is obtained by calculating and matching the AOI fixation time proportion of the subject on the bicycle morphological feature area and the AOI first fixation time; and the feature key identification area of ​​the first bicycle morphological feature design is obtained by judging the feature key identification area of ​​the first bicycle morphological feature design through the fixation heat map to obtain the feature key identification area of ​​the second bicycle morphological feature design;

[0012] According to the average pupil diameter, EEG Alpha wave and Beta wave data of the subjects, the cognitive load and attention acquisition feature recognition importance of design elements of different feature designs were analyzed by multi-factor analysis of variance.

[0013] According to the experimental results of the subjects in the brand recognition experimental paradigm, the recognition accuracy of each bicycle and design element was calculated;

[0014] By conducting cognitive experiments and recognition experiments on subjects, the optimal feature design elements were obtained by combining the recognition accuracy, recognition order, feature recognition importance and the feature key recognition area of ​​the second bicycle morphological feature design, and the optimal feature design elements were applied to the bicycle feature design.

[0015] Furthermore, in step S4, the process of obtaining the feature key identification area of ​​the first bicycle morphological feature design is calculated based on the AOI fixation duration ratio and the AOI first fixation time of the subject on the bicycle morphological feature area:

[0016] 401. Obtain the AOI fixation duration ratio D through the following formula: i :

[0017]

[0018] 402. Obtain the standardized fixation time according to the following formula based on the first fixation time:

[0019]

[0020] Among them: T i ′ is the first fixation time and is reverse normalized, that is:

[0021]

[0022] Where: T i Indicates the time point of the first gaze at the i-th AOI area;

[0023] 403. Obtain the comprehensive interest ratio of the AOI region I according to the AOI gaze duration ratio and the standardized gaze time i :

[0024] I i =α·D i +(1-α)·T i ″

[0025] Among them, α is the weight parameter,

[0026] 404. According to the comprehensive interest ratio of each AOI area, a key feature recognition area for bicycle morphological feature design is obtained.

[0027] Furthermore, the experimental task consists of a cognitive experimental paradigm and a brand recognition experimental paradigm, wherein:

[0028] The observation experiment steps of the cognitive experiment paradigm include: calibration—displaying the brand and model name for 5000ms—displaying the central focus cross for 3000ms—randomly displaying two perspective pictures of the model in sequence, each picture for 8000ms—repeating the above steps until all models are observed;

[0029] The experimental steps of the brand recognition experimental paradigm include: correction - displaying the central focus for 3000ms - randomly displaying bicycle pictures - the subjects judge the bicycle brand and model name, the picture is displayed for a maximum of 10000ms, and then automatically enters the brand judgment questionnaire - repeat the above steps until all pictures are recognized.

[0030] Beneficial Effects

[0031] Compared with the traditional technical solution, the beneficial effects brought by the present invention are:

[0032] 1. Scientificity and objectivity: This invention uses eye tracking technology and EEG technology to obtain direct data on the user's selective attention during the cognitive recognition process, and analyzes the impact of different design elements on the user's cognitive load and brand recognition, forming a user-centered bicycle feature optimization design method. Compared with traditional design methods, this objective data-driven design method is more scientific and objective, and can better reflect the real needs of users.

[0033] 2. Comprehensiveness and accuracy: The present invention not only focuses on the user's physiological indicators, but also on the user's psychological indicators. By comprehensively analyzing the user's physiological and psychological indicators, it can more comprehensively reflect the user's psychological state and cognitive process. Compared with the existing technology, the present invention can more comprehensively reflect the user's psychological state and cognitive process when analyzing the user's response to different design features, thereby improving the accuracy of design optimization.

[0034] 3. Dynamic and real-time performance: The present invention can reflect the changes of users in the cognitive recognition process in real time by analyzing the dynamic data of users in the cognitive recognition process. Compared with the existing technology, the present invention can reflect the dynamic changes of users in the cognitive recognition process in a more real-time manner when analyzing the reactions of users to different design features, thereby improving the real-time performance of design optimization.

[0035] 4. Wide applicability: The principles and methods of the present invention are not only applicable to the field of bicycle design, but can also be extended to the feature optimization design of other products, such as furniture, automobiles, electronic products, etc. This wide applicability makes the present invention have greater market potential and application prospects.

[0036] 5. Improved user experience: Through the design optimization method of the present invention, designers can better understand the needs and preferences of users and create products that are both beautiful and practical and can resonate with users. This user-centered design optimization method can improve user experience and enhance the market competitiveness of products. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of the design method based on eye movement and EEG data of the present invention.

[0038] Figure 2 This is the morphological feature area divided by the present invention for bicycle products. DETAILED DESCRIPTION

[0039] The following is combined with Figure 1 ~Attached Figure 2 The present invention is described as follows:

[0040] The present invention provides a bicycle feature optimization design method based on eye movement and EEG, wherein:

[0041] The present invention uses eye tracking technology and electroencephalogram technology to obtain direct data of users' selective attention in the process of cognitive recognition, and analyzes the influence of different design elements on users' cognitive load and brand recognition, forming a user-centered bicycle feature optimization design method, which drives the feature optimization design of bicycle products based on objective data. The present invention combines the feature design elements with the highest recognition accuracy, applies the design elements to bicycle feature design, and improves the accuracy and reliability of data. The present invention combines the feature design elements with the highest recognition accuracy, applies the design elements to bicycle feature design, and fully reflects the user's psychological state and cognitive process. The present invention combines the feature design elements with the highest recognition accuracy, applies the design elements to bicycle feature design, and fully reflects the dynamic changes of users in the process of cognitive recognition. The present invention conducts cognitive experiments and recognition experiments on subjects, combines the feature design elements with the highest recognition accuracy, and applies the design elements to bicycle feature design, thereby improving the scientificity and objectivity of the design. The present invention uses eye tracking technology and electroencephalogram technology to obtain direct data on the user's selective attention during the cognitive recognition process, and analyzes the influence of different design elements on the user's cognitive load and brand recognition, forming a user-centered bicycle feature optimization design method, which drives the feature optimization design of bicycle products based on objective data. The implementation of the present invention includes the following steps:

[0042] S1: Target sample image selection and design element extraction

[0043] Determine the sample images of bicycles, and let the designer select the sample images, pre-process the sample images, and use the morphological analysis method to divide the morphological characteristic areas of bicycle products, including 5 morphological characteristic areas, namely: handlebar area, seat area, frame area, wheel group area, sprocket crank area. Figure 2 shown.

[0044] The specific process of preprocessing the sample products in step S1 is as follows: based on the differences in morphological features, sample images with high similarity are removed, and in order to reduce the impact of brand trademarks, colors and sizes on the research, trademarks need to be removed from sample images, and samples with the same background and size need to be processed.

[0045] S2: Subjects perform experimental tasks

[0046] The subject wears an EEG cap, and the subject's position and sitting posture are adjusted, and the subject's head position is corrected so that the eye tracker can accurately capture data; the calibration program is entered, and the subject's eyes follow the red dot on the screen, and the experiment continues after the error reaches the standard; after calibration, the subject presses any key to enter the experiment.

[0047] Cognitive experimental paradigms include:

[0048] Experimental rules: Before the experiment, inform the subjects to observe and remember the details of the bicycle as comprehensively as possible, and inform them that there will be a brand recognition test experiment for each model later;

[0049] Cognitive experiment steps: calibration - display the brand and model name for 5000ms - display the central focus cross for 3000ms - randomly display two perspective pictures of the model in sequence, each picture for 8000ms - repeat the above steps until all models are recognized;

[0050] The brand identity experimental paradigm includes:

[0051] Calibration—display the center focus for 3000ms—randomly display bicycle pictures—subjects judge the bicycle brand and model. The pictures are displayed for up to 10000ms, and then automatically enter the brand judgment questionnaire—repeat the above steps until all pictures are recognized.

[0052] S3: Use eye tracking and EEG equipment to collect users’ eye movement data and EEG data when observing different bicycle designs, and collect eye movement indicators and EEG indicators that are more significantly related to feature design recognition

[0053] The sample images screened and processed in the above step S1 are subjected to eye movement and EEG experimental tests, and the eye movement data and EEG data of several subjects in the process of performing the experimental tasks are collected through the eye tracker and EEG cap to obtain eye movement evaluation indicators and EEG signal indicators, and then the eye movement data and EEG signal data are subjected to multifactor variance analysis to obtain indicators that are more significantly related to the design elements.

[0054] Among them, eye movement data include: average pupil diameter, AOI first fixation time, AOI fixation duration, and fixation heat map.

[0055] The frequency domain data of the EEG signal includes: EEG frequency domain signal.

[0056] Among them, eye movement indicators related to cognitive load and attention include: average pupil diameter.

[0057] Among them, EEG signal indicators related to cognitive load and attention include: Alpha waves and Beta waves.

[0058] Among them, the eye movement indicators related to morphological characteristics and recognition order include: AOI first fixation time, AOI fixation duration, and fixation heat map.

[0059] Among them, the behavioral data includes recognition completion time and recognition completion speed.

[0060] The evaluation dimensions of feature recognition difficulty include error rate / accuracy rate and completion rate; the error rate is the number of recognition errors during the completion of the experimental task, and the accuracy rate is obtained by converting the error rate. The higher the error rate, the higher the recognition difficulty, and vice versa, the higher the accuracy rate, the lower the recognition difficulty; the higher the accuracy rate, the more the design features can be recognized by the subjects, and the better the brand recognition.

[0061] The evaluation dimensions of feature recognition difficulty include recognition completion time, recognition completion speed and attention load; the recognition completion time is the time it takes for the subject to complete the recognition experimental task. The longer the recognition completion time is, the higher the recognition difficulty is, and the shorter the task completion time is, the lower the recognition difficulty is.

[0062] S4: Optimize the bicycle feature design based on the eye movement index and EEG index

[0063] The collected eye movement and EEG indicators are analyzed through professional software to obtain the key design elements of feature design. Based on the data analysis results, the user's response to different design features is analyzed, and the color, pattern, shape and other feature designs of the bicycle are adjusted to optimize the design. Through iterative testing and user feedback, the design is further refined and optimized to increase the brand recognition of the bicycle, including:

[0064] Based on the subjects' average pupil diameter, EEG Alpha and Beta waves, the subjects' cognitive load and attention to different feature designs were analyzed to obtain the recognition importance of design elements and adjust the importance ranking of each feature design element.

[0065] According to the AOI gaze sequence of the subjects on each morphological feature area of ​​the bicycle, the recognition order of the subjects on the morphological feature areas of the bicycle is obtained. The AOI gaze sequence is obtained by sorting the AOI first gaze time of the subjects on the morphological feature areas of the bicycle, thereby obtaining the recognition order of the subjects on the morphological feature areas of the bicycle, and finally sorting the design importance of the bicycle feature areas according to the recognition order.

[0066] According to the proportion of the subjects' AOI gaze time to each morphological feature area and the AOI first gaze time, the characteristic key identification area of ​​the first bicycle morphological feature design is calculated. Wherein, the AOI gaze time proportion includes extracting the gaze time of the subjects between different morphological feature areas during the execution of the task, and calculating the gaze time data. Afterwards, the morphological feature areas and the subjects' gaze time during the task execution are matched and bound, and the proportion of the subjects' AOI gaze time to the morphological feature areas is calculated and generated. According to the proportion of the subjects' AOI gaze time to the bicycle morphological feature areas and the AOI first gaze time, the characteristic key identification area of ​​the bicycle morphological feature design is obtained by calculation;

[0067] The process of obtaining the feature key recognition area of ​​the first bicycle morphological feature design is calculated based on the proportion of the subjects' AOI fixation time on the bicycle morphological feature area and the AOI first fixation time:

[0068] 401. Obtain the AOI fixation duration ratio D through the following formula: i :

[0069]

[0070] 402. Obtain the standardized fixation time according to the following formula based on the first fixation time:

[0071]

[0072] Among them: T i ′ is the first fixation time and is reverse normalized, that is:

[0073]

[0074] Where: T i Indicates the time point of the first gaze at the i-th AOI area;

[0075] 403. Obtain the comprehensive interest ratio of the AOI region I according to the AOI gaze duration ratio and the standardized gaze time i :

[0076] I i =α·D i +(1-α)·T i ″

[0077] Among them, α is the weight parameter;

[0078] 404. According to the comprehensive interest ratio of each AOI area, a key feature recognition area for bicycle morphological feature design is obtained.

[0079] The feature key identification area of ​​the first bicycle morphological feature design is combined with the gaze heat map to determine the feature key identification area of ​​the second bicycle morphological feature design.

[0080] The design method of adjusting the design elements includes: conducting cognitive experiments and recognition experiments on subjects, combining the characteristic design elements with the highest recognition accuracy, the shortest recognition completion time, and the fastest recognition completion speed, and applying the design elements to the bicycle characteristic design.

[0081] Embodiment 1: This embodiment provides a bicycle feature design optimization method based on eye movement and EEG data, and the specific steps are as follows: Step 1: Select 30 healthy volunteers aged between 20 and 40 as subjects, and ensure that they have normal vision, without color blindness, color weakness and other visual abnormalities. Step 2: Collect and process bicycle design drawings, remove trademarks, and process them with the same background and size. Step 3: The subjects conduct cognitive experimental paradigms and brand recognition experimental paradigms, observe different bicycle design schemes, and collect eye movement and EEG data. Step 4: Use eye tracking equipment to record the eye movement trajectory of the subjects when observing the bicycle, including data such as fixation point, fixation time, and fixation point movement path. At the same time, use EEG equipment to record the EEG waveform of the subjects when observing the bicycle, including data such as alpha waves and beta waves. Step 5: Analyze the eye movement data and EEG data collected in the experiment, compare the differences between the experimental picture data, and find out the design elements that have the greatest impact on user cognitive load and brand recognition. Step 6: Combine the characteristic design elements with the highest recognition accuracy and apply the design elements to the characteristic design of the bicycle, including color, shape, pattern, etc. Step 7: Conduct cognitive experiments and recognition experiments on the bicycles designed after optimization and before optimization to verify the effectiveness of the optimized design. Step 8: According to the results of cognitive experiments and recognition experiments, further optimize the bicycle with optimized design, and finally obtain a bicycle that meets the user's aesthetic preferences. The above steps are carried out in an indoor environment, with the temperature controlled at 20-25℃ and the humidity controlled at 50-60% to ensure the comfort and stability of the experimental environment. The eye tracking device uses the Tobii Pro Nano series eye tracking system produced by Swedish TobiiTechnology, and the EEG device uses the Versatile EEG system produced by American Bitbrain.

[0082] Due to the advanced nature of this technical solution, it can be widely used in the fields of bicycle design and optimization, human-computer interaction technology, and biological signal processing technology. In the field of bicycle design and optimization, the present invention provides an objective and scientific bicycle feature design method. By using eye tracking technology and electroencephalography technology, direct data on the user's selective attention in the cognitive recognition process can be obtained, and the influence of different design elements on the user's cognitive load and brand recognition can be analyzed to form a user-centered bicycle feature optimization design method, which drives the feature optimization design of bicycle products based on objective data. This will greatly improve the efficiency and accuracy of bicycle design, meet the market demand for high-quality bicycle design, and has broad market prospects.

[0083] In the field of human-computer interaction technology, the present invention provides a new method and technical means. By collecting and analyzing the user's eye movement indicators and EEG indicators in the cognitive recognition process, the user's psychological state and cognitive process can be deeply understood. This will greatly promote the development of human-computer interaction technology and provide technical support for designing products that better meet user needs and psychology, which has broad market demand.

[0084] In the field of biological signal processing technology, the present invention provides a new data processing and analysis method. By combining eye tracking technology and EEG technology, it can obtain direct data on the user's selective attention in the cognitive recognition process, and analyze the influence of different design elements on the user's cognitive load and brand recognition. This will greatly promote the development of biological signal processing technology, provide new methods and ideas for the application of biological signal processing technology in product design, and have broad market application prospects. In general, the technical application prospects of the present invention are broad, the market demand is large, and it has important commercial value and social benefits.

[0085] Although the present invention has been described above, the present invention is not limited to the above-mentioned specific embodiments. The above-mentioned specific embodiments are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can make many modifications without departing from the purpose of the present invention, which are all within the protection of the present invention.

Claims

1. A bicycle feature optimization design method based on eye movement and EEG, characterized in that: The steps include: S1: Select bicycle target sample images for preprocessing and divide bicycle morphological feature areas; S2: The subject wears an EEG cap, and adjusts the subject's position and sitting posture, corrects the subject's head position, and the subject's gaze moves with the red dot on the screen. After the error reaches the standard, the subject enters the experimental task; S3: The eye movement data of the subjects when observing the characteristic area of ​​the bicycle shape are collected by an eye tracker to obtain eye movement evaluation indicators; the EEG data of the subjects when observing the characteristic area of ​​the bicycle shape are collected by an EEG device to obtain EEG indicators; S4: The optimization process of bicycle feature design is obtained by combining eye movement indicators and EEG indicators, including; The recognition order of the bicycle morphological feature areas by the subjects was obtained according to the first fixation time of the subjects on the AOI of the bicycle morphological feature areas; The feature focus recognition area of ​​the first bicycle morphological feature design is obtained by calculating and matching the AOI fixation duration ratio of the subjects to the bicycle morphological feature area and the AOI first fixation time; and determining the key feature recognition area of ​​the first bicycle morphological feature design by looking at the heat map to obtain the key feature recognition area of ​​the second bicycle morphological feature design; According to the average pupil diameter, EEG Alpha wave and Beta wave data of the subjects, the cognitive load and attention acquisition feature recognition importance of design elements of different feature designs were analyzed by multi-factor analysis of variance. According to the experimental results of the subjects in the brand recognition experimental paradigm, the recognition accuracy of each bicycle and design element was calculated; By conducting cognitive experiments and recognition experiments on subjects, the optimal feature design elements were obtained by combining the recognition accuracy, recognition order, feature recognition importance and the feature key recognition area of ​​the second bicycle morphological feature design, and the optimal feature design elements were applied to the bicycle feature design.

2. The bicycle feature optimization design method based on eye movement and EEG according to claim 1 is characterized in that: In step S4, the process of calculating and obtaining the feature key identification area of ​​the first bicycle morphological feature design according to the AOI fixation duration ratio and the AOI first fixation time of the subject on the bicycle morphological feature area is as follows:

401. Obtain the AOI fixation duration ratio D through the following formula: i :

402. Obtain the standardized fixation time according to the following formula based on the first fixation time: in; T i ′ is the first fixation time and is reverse normalized, that is: Where: T i Indicates the time point of the first gaze at the i-th AOI area; 403. Obtain the comprehensive interest ratio of the AOI region I according to the AOI gaze duration ratio and the standardized gaze time i : I i =α·D i +(1-a)·T i ″ Among them, α is the weight parameter, 404. According to the comprehensive interest ratio of each AOI area, a key feature recognition area for bicycle morphological feature design is obtained.

3. A bicycle feature optimization design method based on eye movement and EEG according to any one of claims 1-2, characterized in that: The experimental task consists of a cognitive experimental paradigm and a brand recognition experimental paradigm, in which: The observation experiment steps of the cognitive experiment paradigm include: calibration—displaying the brand and model name for 5000ms—displaying the central focus cross for 3000ms—randomly displaying two perspective pictures of the model in sequence, each picture for 8000ms—repeating the above steps until all models are observed; The experimental steps of the brand recognition experimental paradigm include: correction - displaying the central focus for 3000ms - randomly displaying bicycle pictures - the subjects judge the bicycle brand and model name, the picture is displayed for a maximum of 10000ms, and then automatically enters the brand judgment questionnaire - repeat the above steps until all pictures are recognized.

Images