Method and system for designing adjustable interactive interface fusing group eye movement information

Abstract

The invention discloses an adjustable interactive interface design method and system fusing group eye movement information. The method comprises the steps that firstly, a plurality of eye movement feature values of an individual in the interaction process with an interactive interface are collected; aggregating the individual eye movement feature values and demographic information to represent an individual feature set; obtaining preference degrees of individuals for different interface design elements to form a preference set; collecting eye movement characteristic values associated with the individual for different interface design elements, and forming a relationship network in combination with individual weight values; forming a group database capable of configuring individual weight distribution by aggregating individual data; and establishing a group decision model, calculating the recommendation degree of each interface design element according to the eye movement characteristic value of the user and the demographic information, and sorting the attraction of the interface design elements to the user according to the recommendation degree. The method can adapt to the change of different user behavior modes and preferences, and improves the user experience and decision-making efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of interface design, and in particular to a method and system for realizing dynamic optimization and iterative design of an interactive interface by integrating eye tracking technology and group decision data. Background Art

[0002] In recent years, with the rapid development of human-computer interaction technology, the design of interactive interfaces not only needs to meet the basic operational needs of users, but also needs to achieve a more efficient user experience, especially in applications under complex decision-making environments, such as multi-user collaborative systems and intelligent data analysis platforms. In this context, eye tracking technology, as an intuitive and effective means of capturing user behavior, has received widespread attention because it can reflect users' attention distribution, operational preferences, and cognitive load in real time. At the same time, group decision-making, as an important form of collective intelligence, has been widely used in business analysis, medical diagnosis, education and training, and other fields. How to combine the real-time behavioral data of individual users with the group eye movement decision-making data process has become an important topic in the field of interactive interface design.

[0003] Traditional interactive interface design methods mostly rely on static design solutions, usually using preset logical rules to meet user needs. However, this method often exhibits problems such as insufficient adaptability and delayed feedback when faced with dynamically changing user behaviors or decision-making scenarios involving multiple users. For example, some collaborative tools based on fixed interface design cannot adjust the interface layout in time to adapt to the attention distribution or decision-making preferences of different users, thereby reducing decision-making efficiency and user satisfaction.

[0004] In existing research, although eye tracking technology and group decision-making theory have made certain progress, there are still many challenges in combining the two. On the one hand, eye movement data is complex and has high real-time requirements, requiring efficient algorithms to support dynamic analysis and model updates; on the other hand, group decision-making involves behavioral interaction and information sharing among multiple users, which requires a balance between coordination and adaptability in interface design. In addition, most of the current related technologies remain at the stage of data collection and analysis, lacking an iterative optimization mechanism for practical applications. Summary of the invention

[0005] Purpose of the invention: In view of the problems existing in the above-mentioned prior art, such as poor adaptability, untimely response, and difficulty in meeting the needs of multi-user collaboration in complex scenarios, the purpose of the present invention is to provide an adjustable interactive interface design method and system that integrates group eye movement information, which can dynamically adjust the interface layout, functional modules and element design to adapt to changes in different user behavior patterns and preferences, thereby improving user experience and decision-making efficiency.

[0006] Technical solution: To achieve the above-mentioned invention object, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for designing an adjustable interactive interface integrating group eye movement information, comprising the following steps:

[0008] Collect the eye movement signals of the individuals who assist in the establishment of the group decision-making model during the interaction with the interactive interface, and obtain multiple eye movement feature values ​​after preprocessing;

[0009] Construct an individual eye movement feature value set {p uj ,u∈{1,2,…,N},j∈{1,2,…,M}}, where M is the number of eye movement feature value types and N is the number of individuals assisting in the establishment of the group decision-making model;

[0010] Constructing a demographic information set ul ,u∈{1,2,…,N},l∈{1,2,…,L}}, where L is the number of demographic information types;

[0011] Obtain the preference of individual u for different interface design elements f and form a preference set {S uf ,u∈

[0012] {1,2,…,N},f∈{1,2,…,H}}; where H is the number of interface design elements;

[0013] Collect the scores of individual u for each eye movement feature value j associated with different interface design elements f And combined with the individual weight value a u Form a relationship network with user-adjustable weights {d fj ,f∈{1,2,…,H},j∈{1,2,…,M}};

[0014] By aggregating individual data, a group database with configurable individual weight distribution is formed; the group database includes an eye movement feature value set, a preference set, and a demographic information set;

[0015] Establish a group decision-making model to express the relationship between eye movement feature values ​​and interactive interface design elements;

[0016] When users use the group decision model, multiple eye movement feature values ​​and user demographic information are obtained after the users complete the interactive task;

[0017] The recommendation level of each interface design element is calculated based on the user's eye movement feature values ​​and demographic information, and the attractiveness of the interface design elements to users is ranked according to the recommendation level.

[0018] Furthermore, the calculation formula of the recommendation degree is:

[0019]

[0020] Among them, G vf represents the degree of recommendation of user v for interface design element f, S vf represents the preference of user v for interface design element f, represents the score given by user v to each eye movement feature value j associated with different interface design elements f, max(d fj ) means all d fj The maximum value in, max(S uf ) indicates all S uf The maximum value in; the threshold b is d fj The mean value of E(d fj >b) is the indicator function.

[0021] Furthermore, the weighted relationship network d fj The calculation formula is: in, d ul represents the lth demographic characteristic value of individual u, d vl represents the lth demographic characteristic value of user v, w l Represents the importance weight of the lth feature.

[0022] Furthermore, the group decision model includes an in-domain ontology model and an inference model; the in-domain ontology model defines the processed eye movement feature values, the relationship between different interface design elements and the associated eye movement feature values, different interface design elements, and the individual's preference for interface design elements; the inference model is used to complete the interface design element recommendation based on the in-domain ontology model, combine the in-domain ontology model and the user's weight setting for demographic information to obtain the recommendation level of each interface design element, re-sort the interface design elements according to the size of the recommendation level value, and obtain the group decision result of the model.

[0023] Furthermore, the method further comprises:

[0024] Collect user feedback data on interactive interface design;

[0025] Determine whether the user's eye movement feature value and feedback data have been included in the group decision model. If not, update the model.

[0026] Furthermore, the eye movement signal is preprocessed to obtain the eye movement feature value, which specifically includes:

[0027] De-noising the collected eye movement signal data, including calculating the distance between consecutive eye movement points, identifying and removing abnormal points; smoothing the coordinates of consecutive eye movement points; and filtering using a three-point bilateral convolution filtering method;

[0028] Performing wavelet filtering on the denoised eye movement signal data, reconstructing the wavelet coefficients after removing the noise, and restoring the denoised eye movement signal data;

[0029] Extract eye movement feature values ​​in multiple interactive tasks, including feature values ​​of time, space and physiological dimensions of eye movement signals, wherein the feature value of time dimension includes one or more of fixation number, fixation time, number of saccades and eye movement speed; the feature value of space dimension includes one or more of fixation path and fixation area; the feature value of physiological dimension includes one or more of pupil diameter, number of blinks and fixation entropy.

[0030] Furthermore, for the eye movement signal data

[0031] {(X (1) ,Y (1) ),(X (2) ,Y (2) ),(X (3) ,Y (3) )…(X (n) ,Y (n) )}, the three-point bilateral convolution filtering method is expressed as:

[0032] X (i+1) =α 1 *X (i) +α 2 *X (i+1) +α 3 *X (i+2)

[0033]

[0034] X (1) =β 1 *X (1) +β 2 *X (2)

[0035] X (n) =β 1 *X (n) +β 2 *X (n-1)

[0036] Where X (i) and Y (i) are the horizontal and vertical coordinates of the ith eye movement point, respectively; n is the total number of eye movement points, L iis the distance between the i-th eye movement point and the i+1-th eye movement point, L i+1 is the distance between the i+1th eye movement point and the i+2th eye movement point, α 1 ,α 2 ,α 3 is the convolution kernel coefficient;

[0037] β 1 ,β 2 is the weight coefficient.

[0038] In a second aspect, the present invention provides an adjustable interactive interface design system integrating group eye movement information, comprising:

[0039] The group decision model building module is used to collect the eye movement signals of the individuals who assist in the establishment of the group decision model during the interaction with the interactive interface, and obtain multiple eye movement feature values ​​after preprocessing; forming an individual eye movement feature value set {p uj ,u∈{1,2,…,N},j∈{1,2,…,M}}, where M is the number of eye movement feature value types and N is the number of individuals assisting in the establishment of the group decision model; constructing a demographic information set {D ul ,u∈

[0040] {1,2,…,N},l∈{1,2,…,L}}, where L is the number of demographic information types; obtain the preference degree of individual u for different interface design elements f, and form a preference set {S uf ,u∈{1,2,…,N},f∈

[0041] {1,2,…,H}}; where H is the number of interface design elements; collect the scores of each eye movement feature value j associated with different interface design elements f by individual u And combined with the individual weight value a u Form a relationship network with user-adjustable weights {d fj ,f∈{1,2,…,H},j∈{1,2,…,M}}; by aggregating individual data, a group database with configurable individual weight distribution is formed; the group database includes an eye movement feature value set, a demographic information set and a preference set; a group decision model is established to express the relationship between the eye movement feature value and the interactive interface design elements;

[0042] The human-computer interaction module is used to interact with the user and obtain multiple eye movement feature values ​​and user demographic information after the user completes the interactive task;

[0043] The recommendation ranking module is used to calculate the recommendation degree of each interface design element according to the user's eye movement feature value and demographic information, and to rank the attractiveness of the interface design elements to the user according to the recommendation degree.

[0044] Furthermore, the system also includes an automatic iterative update module for collecting user feedback data on the interactive interface design; determining whether the user's eye movement feature values ​​and feedback data have been included in the group decision model, and if not, updating the model.

[0045] In a third aspect, the present invention provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the adjustable interactive interface design method that integrates group eye movement information.

[0046] Beneficial effects: Compared with the prior art, the present invention has the following advantages:

[0047] 1) The interface design method proposed in the present invention is not only based on the user's objective eye movement data, but also integrates the model obtained through group eye movement behavior and preferences. It can obtain the personalized interface design for each user based on the eye movement feature value of each user. In addition, the model can be updated in real time according to the user's input data, optimizing the accuracy of the recommendation of information related to interface design.

[0048] 2) In the present invention, users can modify the content of the group eye movement model by adjusting the weights themselves, thereby matching a more personalized recommendation method. By adjusting the parameters of the model, a more accurate recommendation experience that better meets personal preferences can be provided.

[0049] 3) Based on the model framework of the present invention, multi-dimensional eye movement features can be adjusted and integrated in real time according to different interaction scenarios, and dynamic adjustments can be made according to specific interaction scenarios and task requirements, thereby improving the adaptability of eye movement data. With the support of multi-dimensional eye movement data, interface design can respond to user behavior more accurately and optimize the response speed and accuracy of the decision support system.

[0050] 4) The present invention utilizes eye movement data, which can accurately reflect the user's focus and operation path on the interface, helping designers identify visibility and layout issues of important information. By analyzing the user's line of sight dwell time and scanning trajectory, problems such as unclear or complex interfaces can be discovered, and the information structure and interaction logic can be optimized. At the same time, eye movement data provides objective feedback based on the user's actual behavior, supports the scientific nature of design improvements, and reduces the subjective bias of traditional methods. Combined with real-time analysis, eye movement data can also customize personalized designs for different user groups, significantly improving the interface's operating efficiency and user satisfaction.

[0051] 5) The present invention proposes an interactive interface design method and system that integrates eye movement and group decision-making. In the interactive module, users use eye movement data to feedback individual attention areas and operation paths, and input preference and evaluation data to assist the group decision model in optimizing the interface design. The present invention can support users to dynamically adjust the weights of eye movement data and group preference data in interface design optimization according to actual needs, thereby realizing a design scheme that combines personalization with group commonality, and improving the scientific nature of interface design and the adaptability of user experience.

[0052] 6) The present invention enhances the intelligence and adaptability of the interface, and is widely applicable to smart terminals, multi-user collaboration platforms and complex data visualization scenarios, and can promote technological progress in the field of human-computer interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 Diagram of the analytical process designed for an interactive interface integrating eye movements and group decision making.

[0054] Figure 2 Schematic diagram of the domain ontology model designed for assistive interfaces.

[0055] Figure 3 This is an application example diagram during user use. DETAILED DESCRIPTION

[0056] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings and specific embodiments.

[0057] An embodiment of the present invention discloses an adjustable interactive interface design method that integrates group eye movement information. By capturing user attention and decision preferences in real time, combined with the proposed group decision model, an interactive interface design method that adapts to multi-user scenarios is constructed to improve user decision-making efficiency and interface interaction experience. The interactive interface design method of the present invention can better match the user's eye movements and preferences, and automatically propose an interactive interface that is more popular with users and improves interaction efficiency. In the specific implementation, it is first necessary to invite participants with experience in eye movement testing and interface design to assist in the establishment of the model. After the model is established, the model can be used to judge the user's preference for a certain design element by importing the user's eye movement data and demographic information with different weights. In addition, it can also be judged whether various types of data of new users are included in the model. If not, the model completes automatic iterative updates.

[0058] like Figure 1As shown, the interactive interface design method for integrating eye movement and group decision-making disclosed in the embodiment of the present invention mainly includes collecting and determining the individual eye movement data preference degree and constructing a demographic information set, taking all the preference values ​​of all people to form a group database, establishing a domain ontology model containing basic information of the target decision domain, collecting the user's eye movement feature values, calculating the recommendation degree of each interface design element and forming a recommendation ranking, collecting user feedback data on the interface design, and judging whether the existing domain ontology model needs to be updated. The specific steps of the adjustable interactive interface design method integrating group eye movement information in the embodiment of the present invention are described in detail below.

[0059] Step S1, collecting eye movement signals of individuals in the process of interacting with the interactive interface to assist in the establishment of the group decision-making model, and obtaining multiple eye movement feature values ​​after preprocessing. In this step, for the determined individual u, multiple eye movement feature values ​​such as the number of fixations, fixation time, and pupil diameter of the individual are collected to represent the objective eye movement feedback in the process of interacting with the interactive interface.

[0060] Step S2: Collect the eye movement feature value sets {p uj ,u∈{1,2,…,N},j∈{1,2,…,M}}. N is the number of individuals assisting in the establishment of the group decision-making model, and M is the number of eye movement feature value types.

[0061] Step S3: Constructing a demographic information set {D ul ,u∈{1,2,…,N},l∈{1,2,…,L}; where L is the number of demographic information types;

[0062] Step S4: Obtain the preference characteristics of individual u (u∈{1,2,…,N}) for different interface design elements f, and form a preference set {S uf ,u∈{1,2,…,N},f∈{1,2,…,H}}. Where H is the number of interface design elements.

[0063] Step S5: Collect the scores of each eye movement feature value j associated with different interface design elements f by individual u (u∈{1,2,…,N}) Combined with the assigned individual weight value a u After that, a network of relationships is formed. fj ,f∈{1,2,…,H},j∈{1,2,…,M}}.

[0064] Step S6: by aggregating individual data, a group database with configurable individual u (u∈{1,2,…,N}) weight distribution is formed, including an eye movement feature value set, a preference set, and a demographic information set.

[0065] Step S7: Establish a group decision model to express the relationship between eye movement feature values ​​and interactive interface design elements.

[0066] Step S8, when user v uses the group decision model, collect the user's eye movement feature values ​​such as the number of gazes, gaze time, number of glances, glance time, pupil diameter, number of blinks, etc. after completing an interactive task; at the same time, collect the user's demographic information such as age, gender, occupation, etc.

[0067] Step S9: Calculate the recommendation level G of each interface design element based on the user's eye movement feature value and demographic information vf , according to G vf The size of the numerical value ranks the attractiveness of the interface design elements to users, and the final evaluation result can be obtained by combining the demographic information weight that can be adjusted by users.

[0068] Step S10: Collect user feedback data on the interface design, including objective and subjective data, and determine whether the user's eye movement feature value and feedback data have been included in the current group decision model. If not, update the model.

[0069] As described above, the adjustable interactive interface design method integrating group eye movement information described in the embodiment of the present invention collects user eye movement data and group preference data, comprehensively analyzes the user's visual focus and group decision-making tendency, so as to optimize the interface layout and interactive design. The design optimization results can be presented to the user in real time through the feedback module, supporting dynamic adjustment to achieve the personalization and universality of the interface design, and improve the scientificity and adaptability of the user experience.

[0070] For example, in step S1, for individual u, multiple signal data are recorded by an eye tracking device. These signals can reflect the individual's attention and preference for a certain stimulus (such as an image, interface, text, etc.). Common eye movement feature values ​​include: number of fixations, fixation time, pupil diameter, etc. In specific implementation, a series of processing such as noise reduction is performed on the eye movement signal data collected in the user test design interface scenario. The eye movement data to be denoised is recorded as: {(X 1 ,Y 1 )(X 2 ,Y 2 )(X 3 ,Y 3 )…(X n ,Y n )}, and calculate the Euclidean distance {L 1 ,L 2 …L n-1}, the distance between adjacent eye movement points is calculated using the following formula:

[0071]

[0072] Where (X i ,Y i ) and (X i+1 ,Y i+1 ) are the positions of two consecutive eye movement points in the coordinate space, X is the horizontal coordinate of the eye movement point, and Y is the vertical coordinate of the eye movement point.

[0073] By calculating the distance between consecutive points, it can be used to preliminarily reduce the noise in the eye data, such as identifying abnormal points (such as sudden jumps caused by device errors or user blinking) and processing them (such as removal or interpolation). At the same time, the Euclidean distance can be used to determine whether the user's eye movement behavior is fixation or saccade. If the Euclidean distance is small, it indicates that the range of change between the eye movement points is small, which may be a fixation; if the Euclidean distance is large, it indicates that the eye is moving quickly, which may be a saccade.

[0074] The coordinates of continuous points are smoothed and the sliding average method is used to further reduce noise interference. The specific formula is:

[0075]

[0076] where y i is the smoothed value of the i-th eye movement coordinate, x j is the jth point in the original data, k is the half width of the sliding window, which determines the neighborhood range when taking the average value. For the i-th point, the mean of the k points before and after it can be calculated, which can quickly process large-scale eye movement data.

[0077] Finally, the improved three-point bilateral convolution filtering method is used to process the eye movement data. The filtered eye movement data is recorded as {(X (1) ,Y (1) ),(X (2) ,Y (2) ),(X (3) ,Y (3) )…(X (n) ,Y (n) )},

[0078] X (i+1) =α 1 *X (i) +α 2 *X (i+1) +α 3 *X (i+2)

[0079]

[0080] X (1) =β 1 *X(1) +β 2 *X (2)

[0081] X (n) =β 1 *X (n) +β 2 *X (n-1)

[0082] where α 1 ,α 2 ,α 3 is the convolution kernel coefficient, α 2 =0.5; β 1 ,β 2 is the weight coefficient, β 1 =0.8,β 2 =0.2.

[0083] Then the denoised eye movement data are subjected to wavelet filtering to further extract detail information from the denoised data, remove residual noise and retain eye movement features, and obtain wavelet coefficients consisting of detailed noise and eye movement features.

[0084] By using the difference in properties of wavelet coefficients at different scales (noise is mainly concentrated in high-frequency components), the high-frequency detailed coefficients d j Set a threshold and treat coefficients less than the threshold as noise and set them to 0. Use soft thresholding to remove wavelet coefficients from noise. Compared with hard thresholding, the soft thresholding method can avoid over-smoothing and retain important details of eye movement signals. The specific method is:

[0085]

[0086] The threshold T can be selected based on the noise level σ, and the specific method is:

[0087]

[0088] Where σ is the standard deviation of the noise and B is the number of data points.

[0089] The denoised wavelet coefficients are reconstructed to restore the denoised eye movement data.

[0090] The characteristic value calculation in step S1 may be: extracting eye movement characteristic values ​​in the K tasks. For example, the eye movement characteristic values ​​such as the number of fixations, fixation time, number of saccades, eye movement velocity, pupil diameter, number of blinks, fixation entropy, etc. may be calculated according to the time, space and physiological dimensions of the eye movement signal.

[0091] The eigenvalues ​​of the time dimension mainly focus on the temporal variation characteristics of eye movement signals. By analyzing indicators such as the duration, number, and eye movement speed of fixations and saccades, it reveals the user's attention allocation and information processing characteristics during the task. The eigenvalues ​​of the spatial dimension focus on the spatial distribution of eye movement points, and are used to analyze the user's gaze path, gaze area, and other information. The eigenvalues ​​of the physiological dimension extract indicators related to the user's physiological state from eye movement signals, such as pupil size, gaze entropy, and blinking behavior.

[0092] Calculate each eye movement feature value, taking eye movement velocity and gaze entropy as examples:

[0093] The formula for calculating eye movement velocity is as follows:

[0094]

[0095] Among them, V is the eye movement speed, usually in degrees per second; D is the displacement distance of the eyes in one scan, usually in degrees; t is the time required to complete the scan, usually in seconds.

[0096] The calculation formula of gaze entropy is as follows:

[0097]

[0098] Where n is the number of AOIs divided; p i is the fixation probability of the i-th AOI (the ratio of the number of fixations or time to the total number of fixations or time).

[0099] In step S4, the preference characteristics of individual u (u∈{1,2,…,N}) for interface design elements f (such as color scheme, layout format, font size, button style, icon style, etc.) are directly obtained through questionnaires, interviews or user feedback tools to establish a preference set.

[0100] In step S5, the eye movement data associated with different interface design elements f by individual u (u∈{1,2,…,N}) are collected to form a relationship network {d fj ,f∈{1,2,…,H},j∈{1,2,…,M}}, further reveals the user’s visual attention distribution and the interdependence between elements, and based on this, provides strong support for interface design optimization and helps improve user experience.

[0101] In step S6, the basic aggregation method is used to collect the preferences of individual u for different interface design elements f. In order to more accurately reflect the group preferences, different weights can be assigned to the preference data of different users, and weighted to reflect importance or representativeness. Finally, based on the results of weighted aggregation, a group database with configurable weight distribution of individual u (u∈{1,2,…,N}) is established.

[0102] In step S7, a domain ontology model is created that can express the relationship between eye movement feature values ​​and interactive interface design elements. This model aims to systematically capture the core elements and their attributes in interactive interface design and provide a solid foundation for intelligent reasoning. It will include basic elements in interactive interface design, such as color, font, layout, and interactive components, aiming to achieve design automation, optimize interface layout, and meet the personalized needs of users.

[0103] The model defines class, relationship, instance, and score and assigns them values. Class represents the processed eye movement feature values, and the index is represented by j; relationship represents the relationship between individual u (u∈{1,2,…,N}) combined with the weight value for the non-interface design elements and the associated eye movement data, and is represented by d fj Indicates; instance represents different interface design elements, index is represented by f; score represents the preference of individual u (u∈{1,2,…,N}) for interface design elements, represented by S uf This information directly contributes to the formation of group decision-making.

[0104] In step S8, the collection of eye movement feature values ​​is carried out during the user's participation in the experiment. The user will perform a series of test tasks based on specific interface design elements or product options. It is assumed that the user completes such tasks K times. Every time the user completes a task, the eye movement sensor will capture their eye movement data. This data is then recorded and stored in the system. The eye movement data is preprocessed according to the process in step S1, and the feature values ​​of the eye movement signal are calculated, so as to subsequently analyze the relationship between the user's preference for different design elements and the eye movement feature values.

[0105] In step S9, the recommendation level of each interface design element is calculated, and a recommendation ranking is formed in combination with the user's weight setting for demographic information.

[0106] User demographic information is often converted into a series of quantitative features, such as gender, age, occupation, and educational background. Based on this information, the user can adjust the weight distribution of N individuals, for example, increase the weight of individuals with similar demographic information to oneself, so as to improve the accuracy of the recommendation system. In some embodiments, the individual weights can be determined according to the following method:

[0107] First, define the demographic information set D ul The demographic information feature vector of each individual u(u∈{1,2,…,N}) in:

[0108] D u ={du1 ,d u2 ,...d uL}

[0109] Where L represents the dimension of demographic information (e.g., gender, age, occupation, etc.);

[0110] d ul ,l∈{1,2,…,L} represents the lth demographic characteristic value of individual u.

[0111] Next, define the demographic feature vector of the current user:

[0112] D v ={d v1 ,d v2 ,...d vl}

[0113] Different demographic characteristics may have different importance, allowing the user to assign weights to each characteristic:

[0114]

[0115] Among them, w l Represents the importance weight of the lth feature (defined by the current user).

[0116] Finally, based on the similarity S u Adjust the weight of individual u (u∈{1,2,…,N}):

[0117]

[0118] Among them, a u is the normalized weight (ensuring that the sum of all weights is 1), which represents the influence of individual u (u∈{1,2,…,N}) in group decision-making; N is the total number of people in the group.

[0119] Calculate the weighted d fj The value is as follows:

[0120] Construct a group decision-making reasoning model to complete the interface design element recommendation based on the ontology model in the above field. The basic logic is based on the group database p uj , D ul and S uf (u∈{1,2,…,N}),d fj , f information, combined Figure 2 The domain ontology model of auxiliary interface design and the weight setting of users on demographic information are used to obtain the recommendation level G of each interface design element f. vf , according to G vfSorting the interface design elements by numerical values ​​will obtain the group decision result of the model for a specific interface design element. vf The calculation is expressed as:

[0121]

[0122] The threshold b is the value of all d fj The average value, S vf represents the preference of user v for interface design element f, represents the eye movement feature value associated with different interface design elements f by user v, max(d fj ) means all d fj The maximum value in, max(S uf ) indicates all S uf The maximum value among them. E(d fj >b) is the indicator function, defined as:

[0123]

[0124] In step S10, after using the interactive interface for a period of time, users' opinions on the interface design and feedback on the usage experience are collected through tools such as questionnaires and scales, which include objective and subjective data.

[0125] Based on the recorded and processed user eye movement data and user feedback, we first check whether the new eye movement data is covered by the existing domain ontology model by extracting features from the new data and checking whether its distribution is consistent with the training data. We use the Kullback-Leibler (KL) Divergence method to measure the difference between the two groups of distributions:

[0126]

[0127] KL divergence is an asymmetric method to measure the difference between two probability distributions P and Q. If P and Q are exactly the same, the calculated KL divergence value is 0. The larger the KL divergence value, the greater the deviation of Q from P. Where P(j) represents the probability of distribution P on eye movement feature value j; Q(j) represents the probability of distribution Q on eye movement feature value j.

[0128] If the difference is too large, it may mean that the user's eye movement feature value is not covered by the existing ontology model in the field, and it is necessary to use the new data to fine-tune the existing model, that is, incorporate the new data into the original model; otherwise, there is no need to adjust the model.

[0129] Based on the same inventive concept, an embodiment of the present invention also discloses an adjustable interactive interface design system integrating group eye movement information, including:

[0130] The group decision model building module is used to collect the eye movement signals of the individuals who assist in the establishment of the group decision model during the interaction with the interactive interface, and obtain multiple eye movement feature values ​​after preprocessing; forming an individual eye movement feature value set {p uj ,u∈{1,2,…,N},j∈{1,2,…,M}}; construct a demographic information set {D ul ,u∈{1,2,…,N},l∈{1,2,…,L}}; obtain the preference degree of individual u for different interface design elements f and form the preference set {S uf ,u∈{1,2,…,N},f∈{1,2,…,H}}; collect the scores of each eye movement feature value j associated with different interface design elements f by individual u Combined with the individual weight value a u Form a relationship network with user-adjustable weights {d fj ,f∈{1,2,…,H},j∈{1,2,…,M}}; by aggregating individual data, a group database with configurable individual weight distribution is formed; the group database includes an eye movement feature value set, a demographic information set and a preference set; a group decision model is established to express the relationship between the eye movement feature value and the interactive interface design elements;

[0131] The human-computer interaction module is used to interact with the user and obtain multiple eye movement feature values ​​and user demographic information after the user completes the interactive task;

[0132] The recommendation ranking module is used to calculate the recommendation degree of each interface design element according to the user's eye movement feature value and demographic information, and to rank the attractiveness of the interface design elements to the user according to the recommendation degree.

[0133] Furthermore, the system also includes: an automatic iterative update module for collecting user feedback data on the interactive interface design; determining whether the user's eye movement feature values ​​and feedback data have been included in the group decision model, and if not, updating the model.

[0134] The embodiment of the present invention also discloses a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the adjustable interactive interface design method for integrating group eye movement information.

Claims

1. A method for designing an adjustable interactive interface integrating group eye movement information, characterized in that: The steps include: Collect the eye movement signals of the individuals who assist in the establishment of the group decision-making model during the interaction with the interactive interface, and obtain multiple eye movement feature values ​​after preprocessing; Construct an individual eye movement feature value set {p uj , u∈{1, 2, ..., N}, j∈{1, 2, ..., M}}, where M is the number of eye movement feature value types and N is the number of individuals assisting in the establishment of the group decision-making model; Constructing a demographic information set ul , u∈{1,2,...,N}, l∈{1,2,...,L}}, where L is the number of demographic information categories; Obtain the preference of individual u for different interface design elements f and form a preference set {S uf , u∈{1, 2, ..., N}, f∈{1, 2, ..., H}}; where H is the number of interface design element types; Collect the scores of individual u for each eye movement feature value j associated with different interface design elements f Combined with the individual weight value a u Form a relationship network with user-adjustable weights {d fj , f∈{1, 2, ..., H}, j∈{1, 2, ..., M}}; By aggregating individual data, a group database with configurable individual weight distribution is formed; the group database includes an eye movement feature value set, a preference set, and a demographic information set; Establish a group decision-making model to express the relationship between eye movement feature values ​​and interactive interface design elements; When users use the group decision model, multiple eye movement feature values ​​and user demographic information are obtained after the users complete the interactive task; The recommendation level of each interface design element is calculated based on the user's eye movement feature values ​​and demographic information, and the attractiveness of the interface design elements to users is ranked according to the recommendation level.

2. The adjustable interactive interface design method integrating group eye movement information according to claim 1 is characterized in that: The calculation formula of the recommendation degree is: Among them, G vf represents the degree of recommendation of user v for interface design element f, S vf represents the preference of user v for interface design element f, represents the score given by user v to each eye movement feature value j associated with different interface design elements f, max(d fj ) means all d fj The maximum value in, max(S uf ) indicates that all S uf The maximum value in; the threshold b is d fj The mean value of E(d fj >b) is the indicator function.

3. The adjustable interactive interface design method integrating group eye movement information according to claim 2 is characterized in that: Weighted relationship network d fj The calculation formula is: in, d ul represents the lth demographic characteristic value of individual u, d vl represents the lth demographic characteristic value of user v, w l Represents the importance weight of the lth feature.

4. The adjustable interactive interface design method integrating group eye movement information according to claim 1 is characterized in that: The group decision model includes an in-domain ontology model and a reasoning model; the in-domain ontology model defines various processed eye movement feature values, the relationship between different interface design elements and the associated eye movement feature values, different interface design elements, and the individual's preference for the interface design elements; The reasoning model is used to complete the recommendation of interface design elements based on the domain ontology model. The recommendation level of each interface design element is obtained by combining the domain ontology model and the user's weight setting for demographic information. The interface design elements are re-ranked according to the value of the recommendation level to obtain the group decision result of the model.

5. The adjustable interactive interface design method integrating group eye movement information according to claim 1, characterized in that: Also includes: Collect user feedback data on interactive interface design; Determine whether the user's eye movement feature value and feedback data have been included in the group decision model. If not, update the model.

6. The adjustable interactive interface design method integrating group eye movement information according to claim 1, characterized in that: After preprocessing the eye movement signal, the eye movement feature value is obtained, including: De-noising the collected eye movement signal data, including calculating the distance between consecutive eye movement points, identifying and removing abnormal points; smoothing the coordinates of consecutive eye movement points; and filtering using a three-point bilateral convolution filtering method; Performing wavelet filtering on the denoised eye movement signal data, reconstructing the wavelet coefficients after removing the noise, and restoring the denoised eye movement signal data; Extract eye movement feature values ​​in multiple interactive tasks, including feature values ​​of time, space and physiological dimensions of eye movement signals, wherein the feature value of time dimension includes one or more of fixation number, fixation time, number of saccades and eye movement speed; the feature value of space dimension includes one or more of fixation path and fixation area; the feature value of physiological dimension includes one or more of pupil diameter, number of blinks and fixation entropy.

7. The adjustable interactive interface design method integrating group eye movement information according to claim 6, characterized in that: For the eye movement signal data {(X (1) , Y (1) ), (X (2) , Y (2) ), (X (3) , Y (3) )…(X (n) , Y (n) )}, the three-point bilateral convolution filtering method is expressed as: X (i+1) =α1*X (i) +α2*X (i+1) +α3*X (i+2) X (1) =β1*X (1) +β2*X (2) X (n) =β1*X (n) +β2*X (n-1) Where X (i) and Y (i) are the horizontal and vertical coordinates of the ith eye movement point, respectively; n is the total number of eye movement points, L i is the distance between the i-th eye movement point and the i+1-th eye movement point, L i+1 is the distance between the i+1th eye movement point and the i+2th eye movement point, α1, α2, α3 are the convolution kernel coefficients; β1, β2 are the weight coefficients.

8. An adjustable interactive interface design system integrating group eye movement information, characterized in that: include: A group decision model building module is used to collect eye movement signals of individuals who assist in building the group decision model during the interaction with the interactive interface, and obtain multiple eye movement feature values ​​after preprocessing; Forming an individual eye movement feature value set {p uj , u∈{1,2,...,N}, j∈{1,2,...,M}}, where M is the number of eye movement feature value types and N is the number of individuals assisting in the establishment of the group decision model; construct a demographic information set {D ul , u∈{1,2,...,N},l∈{1,2,...,L}}, where L is the number of demographic information types; obtain the preference of individual u for different interface design elements f, and form a preference set {S uf , u∈{1,2,...,N},f∈{1,2,...,H}}; where H is the number of interface design elements; collect the scores of each eye movement feature value j associated with different interface design elements f by individual u Combined with the individual weight value a u Form a relationship network with user-adjustable weights {d fj , f∈{1,2,...,H},j∈{1,2,...,M}}; by aggregating individual data, a group database with configurable individual weight distribution is formed; the group database includes an eye movement feature value set, a demographic information set and a preference set; a group decision model is established to express the relationship between the eye movement feature value and the interactive interface design elements; The human-computer interaction module is used to interact with the user and obtain multiple eye movement feature values ​​and user demographic information after the user completes the interactive task; The recommendation ranking module is used to calculate the recommendation degree of each interface design element according to the user's eye movement feature value and demographic information, and to rank the attractiveness of the interface design elements to the user according to the recommendation degree.

9. The adjustable interactive interface design system integrating group eye movement information according to claim 8, characterized in that: Also includes: Automatic iteration update module, used to collect user feedback data on interactive interface design; Determine whether the user's eye movement feature value and feedback data have been included in the group decision model. If not, update the model.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for designing an adjustable interactive interface integrating group eye movement information according to any one of claims 1 to 7 are implemented.

Images