Human factor verification method and device for in-vehicle infotainment interface and vehicle

Abstract

The invention relates to the field of interface design, and particularly discloses a human factor verification method and device for a vehicle machine interface and a vehicle, and the method comprises the steps: determining a target interface region corresponding to a target button in a to-be-evaluated interface; obtaining eye movement fixation data of the user during driving in different scenes, wherein the eye movement fixation data comprises at least one of first fixation time, the number of fixation points in the target interface area, the maximum duration of single-time road deviation and the number of times of target interface area glancing; based on the eye movement fixation data, scene interface verification values corresponding to the to-be-evaluated interface in different scenes are determined; and determining a comprehensive interface verification value of the to-be-evaluated interface based on the scene interface verification values corresponding to the to-be-evaluated interface in different scenes. By obtaining the multi-dimensional eye movement fixation data of the user and combining the scoring results in different scenes, the user experience of the vehicle-mounted terminal interface can be effectively quantified, and a basis is provided for interface optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of interface design, in particular to a human factor verification method and device for vehicle interface and a vehicle. BACKGROUND

[0002] In recent years, with the rapid development of the automobile industry, the functions of the vehicle machine system are increasingly complex, and users have higher requirements for the interactive experience of the vehicle interface.

[0003] However, the existing vehicle interface optimization process mainly relies on subjective questionnaires or simple operation tests, which cannot comprehensively and objectively reflect the user's experience in the real driving environment, resulting in low accuracy of the experience results of the vehicle interface, insufficient reference, and inability to effectively guide the optimization design of the vehicle interface. SUMMARY

[0004] In view of the above problems, the present disclosure provides a human factor verification method, device and vehicle for vehicle interface to overcome the above problems or at least partially solve the above problems, and the technical solution is as follows: A human factor verification method for vehicle interface, comprising: determining a target interface region corresponding to a target button in a to-be-evaluated interface; obtaining eye movement fixation data of a user when driving in different scenarios, the eye movement fixation data comprising at least one of first fixation time, number of fixation points in the target interface region, maximum single deviation time from the road, and number of saccades in the target interface region; determining a scenario interface verification value corresponding to the to-be-evaluated interface in different scenarios based on the eye movement fixation data; and determining a comprehensive interface verification value of the to-be-evaluated interface based on the scenario interface verification values corresponding to the to-be-evaluated interface in different scenarios.

[0005] The present application can more accurately reflect the user's experience in actual use by introducing multi-dimensional eye movement fixation data and combining specific driving scenarios for scoring, thereby providing a scientific basis for the optimization of the vehicle interface. Not only can the attention distribution of the user in different driving scenarios be quantified, but also potential problems in interface design can be revealed through the comprehensive interface verification value. In addition, by weighting the scores of multiple scenarios, the adaptability of the interface under different driving conditions can be more comprehensively evaluated to ensure that it can provide good user experience in various situations. The application of this method helps to improve the safety and ease of use of the vehicle system, meets the user's demand for efficient interaction, and provides a clear direction for the design improvement of the vehicle interface.

[0006] In one example, the determining, based on the eye gaze data, a scene interface verification value corresponding to the interface to be evaluated in a different scene respectively, comprises: obtaining an optimal value pre-labeled for each eye gaze data; determining a normalized deviation value of an actual value of each eye gaze data from the optimal value respectively; determining a single-item verification value of each eye gaze data based on the normalized deviation value; and performing weighted summation on the single-item verification values of at least one of the eye gaze data to obtain the scene interface verification value.

[0007] The application can effectively eliminate the differences in dimensions and ranges of different eye movement data by introducing the calculation method of the normalized deviation value, thereby improving the scientificity and comparability of the scoring result. By comparing and analyzing the actual performance of each eye gaze data with the optimal value, the attention distribution characteristics of the user in different scenes can be more accurately quantified, thereby providing more detailed data support for interface optimization.

[0008] In one example, the determining, based on the eye gaze data, a scene interface verification value corresponding to the interface to be evaluated in a different scene respectively, comprises: obtaining an optimal value pre-labeled for each eye gaze data; determining a normalized deviation value of an actual value of each eye gaze data from the optimal value respectively; determining a single-item verification value of each eye gaze data based on the normalized deviation value; and performing weighted summation on the single-item verification values of at least one of the eye gaze data to obtain the scene interface verification value.

[0009] The application further refines the calculation process of the normalized deviation value by introducing the exponential decay processing of the sensitivity coefficient. This method can not only effectively reduce the influence of extreme data on the scoring result, but also can reflect the adaptability difference of the user in different scenes to a certain extent. By performing nonlinear adjustment on the deviation ratio, the variation law of human visual attention can be more realistically simulated, thereby improving the accuracy and robustness of the scoring model.

[0010] In one example, the determining, based on the eye gaze data, a scene interface verification value corresponding to the interface to be evaluated in a different scene respectively, comprises: obtaining an optimal value pre-labeled for each eye gaze data; determining a normalized deviation value of an actual value of each eye gaze data from the optimal value respectively; determining a single-item verification value of each eye gaze data based on the normalized deviation value; and performing weighted summation on the single-item verification values of at least one of the eye gaze data to obtain the scene interface verification value.

[0011] The present application further improves the pertinence and practicality of the scoring system by assigning weights to different eye movement fixation data. The weights are set based on the actual impact of each data on driving safety and operational efficiency, ensuring that the scoring results can more accurately reflect the performance of the interface design in key performance indicators. By weighted summation of individual verification values, not only the contribution of important indicators can be highlighted, but also the influence of secondary indicators can be balanced in the comprehensive interface verification value, making the final score more valuable and instructive. This method not only helps to identify the core problems in interface design, but also provides clear priority ranking for optimization work, thereby improving the overall performance and user experience of the car machine interface.

[0012] In one example, the eye movement fixation data of the user driving in different scenarios is obtained, specifically including: obtaining the eye movement fixation data of the driver when clicking the target button in multiple scenarios simulating real driving environment; the different scenarios include at least one of different stable vehicle speed driving scenarios, different road type scenarios, different light condition scenarios and different driving load scenarios.

[0013] When obtaining the eye movement fixation data of the user driving in different scenarios, the present application also emphasizes the coverage range of scenario diversity. These scenarios include but are not limited to different stable vehicle speed driving environments, different types of road conditions, various light changes and different driving load states. By collecting data in a simulated real driving environment, the actual use situation of the user can be restored to the greatest extent, thereby ensuring the authenticity and reliability of the evaluation results.

[0014] In one example, the comprehensive interface verification value of the interface to be evaluated is determined based on the scene interface verification values of the interface to be evaluated in different scenarios, specifically including: based on at least one of the occurrence frequency of the driving scene in the actual driving process, the safety risk level and the task importance, the scene weight of each driving scene is pre-labeled; multiply each scene interface verification value by its corresponding scene weight to get the weighted scene score; sum all the weighted scene scores to get the comprehensive interface verification value of the interface to be evaluated.

[0015] The scientificity and practicality of the comprehensive interface verification value are further improved by introducing the concept of scene weight. The setting of the scene weight is based on the multi-dimensional characteristics of the driving scene in the actual driving process, including the frequency of occurrence, the safety risk level, and the task importance of key factors. By weighting the scores of each scene, the contribution of different scenes to the overall user experience can be more accurately reflected, ensuring that the comprehensive interface verification value fully reflects the performance of the interface design in various driving environments. Not only does this enhance the credibility of the evaluation results, but it also provides more accurate direction for interface optimization, helping designers focus on the scenes and issues that have the greatest impact on users.

[0016] In one example, after determining the comprehensive interface verification value of the interface to be evaluated, the method further includes: in response to the comprehensive interface verification value being lower than a first preset threshold, optimizing the target button in the interface to be evaluated, and the optimization measures include adjusting at least one of the interface position, size, color, shape, and icon style of the target button in the interface; In one example, after determining the scene interface verification value corresponding to each scene of the interface to be evaluated, the method further includes: in response to the scene interface verification value corresponding to the target scene being higher than a second preset threshold, taking the interface to be evaluated as the recommended interface for the target scene. By adjusting the interface position of the target button, the visual search time of the driver can be reduced, thereby improving the operation efficiency; by changing the size and color of the button, its visual salience can be enhanced, making it easier for the driver to recognize under different lighting conditions; and by optimizing the shape and icon style of the button, the overall aesthetics and user cognitive consistency of the interface can be improved. In addition, in certain specific scenarios, if the scene interface verification value performs well, the interface can be taken as a recommended solution, providing a reference for the design of similar scenarios. This method not only realizes precise optimization based on problems, but also takes into account user experience while ensuring safety, providing systematic support for the continuous improvement of the car interface.

[0017] The present application also provides a human factor verification device for a car interface, comprising: a target interface region determination module for determining a target interface region corresponding to a target button in an interface to be evaluated; an eye movement data acquisition module for acquiring eye movement fixation data of a user when driving in different scenarios, the eye movement fixation data including at least one of first fixation time, number of fixation points in the target interface region, maximum single deviation time from the road, and number of saccades in the target interface region; a scene interface verification value determination module for determining scene interface verification values corresponding to each scene of the interface to be evaluated based on the eye movement fixation data; and a comprehensive interface verification value determination module for determining a comprehensive interface verification value of the interface to be evaluated based on the scene interface verification values corresponding to each scene of the interface to be evaluated.

[0018] The application also provides a vehicle, comprising: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the human factor verification method of the vehicle-machine interface according to any one of the examples described above.

[0019] By the above technical solution, the human factor verification method, device and vehicle of the vehicle-machine interface provided by the present disclosure realize comprehensive and objective evaluation of the vehicle-machine interface by introducing a multi-dimensional scoring system based on eye movement data and combining weight distribution of driving scenarios. This method can quantify the attention distribution of users under different driving conditions and provide a basis for optimization. At the same time, by adjusting the interface properties of the target button and combining the recommendation mechanism of the specific scenario, the safety and ease of use of the interface are further improved. In addition, the present application introduces a normalized deviation value and a weight distribution mechanism, which significantly improves the scientificity and practicality of the scoring results. The calculation of the normalized deviation value effectively solves the problem of different eye movement data dimensions and range differences, making the scoring more accurate and comparable. The weight distribution is set according to the actual influence of each eye movement data on driving safety and operation efficiency, ensuring that the scoring system can more truly reflect the performance of the interface design in key performance indicators. This evaluation method combining multi-dimensional data and scenario weight can not only comprehensively evaluate the adaptability of the vehicle-machine interface in different driving environments, but also provide a clear direction and priority ranking for interface optimization, thereby helping designers focus on the problems and scenarios that have the greatest impact on user experience.

[0020] The above description is only a summary of the technical solutions of the present disclosure. In order to enable a clearer understanding of the technical means of the present disclosure, the specific embodiments of the present disclosure can be implemented in accordance with the content of the description, and in order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the following specific embodiments of the present disclosure are described. BRIEF DESCRIPTION OF DRAWINGS

[0021] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments, and are not meant to limit the present disclosure. Moreover, the same reference numerals are used throughout the several views to designate the same or similar parts. In the drawings: Figure 1 A flowchart of a human factor verification method of a vehicle-machine interface in an embodiment of the present disclosure is shown; Figure 2 A structural diagram of a human factor verification device of a vehicle-machine interface in an embodiment of the present disclosure is shown; Figure 3A structural schematic diagram of a vehicle in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0022] Exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art.

[0023] The technical solutions provided by the embodiments of the present application are described in detail below with reference to the drawings.

[0024] In recent years, with the rapid development of the automotive industry, the functions of the car machine system are increasingly complex, and users have higher requirements for the interactive experience of the car machine interface. However, the existing car machine interface optimization methods mostly rely on subjective questionnaires or simple operation tests, which are difficult to comprehensively and objectively reflect the user's experience in the real driving environment, resulting in low accuracy of the optimization results of the car machine interface, insufficient reference, and inability to effectively guide the optimization design of the car machine interface. Moreover, the traditional optimization methods often ignore the diversity and complexity of driving scenarios, and cannot accurately quantify the attention allocation of users under different conditions. This limitation makes it difficult to discover and solve potential problems in interface design in a timely manner, thereby affecting the overall performance and user experience of the car machine system. In addition, the lack of scientific data support also leads to a lack of clear direction and priority for optimization work, further restricting the improvement efficiency of the car machine interface. Therefore, there is an urgent need for a more comprehensive, objective and actual use situation-based optimization method to make up for the shortcomings of existing technologies and promote the continuous optimization of car machine interface design.

[0025] To this end, the present application provides a human factor verification method for a car machine interface, as shown in Figure 1 The present application provides a human factor verification method for a car machine interface, as shown in

[0026] Specifically, staff can obtain the frequency of user interaction with each function button on any interface of the vehicle through in-vehicle infotainment system data and user sentiment data. Based on the frequency of each function button on any interface, the layout of the top few function buttons can be prioritized for page layout design. Taking the air conditioning switch button as an example, multiple versions of the interface design can be generated. Then, the human factors verification method provided in this solution can be used for human factors verification evaluation to select the optimal interface design. Certain input parameters (such as thresholds and weights) or intermediate results in this process can be manually adjusted to help improve accuracy.

[0027] The analysis method involved in the embodiments of this application can be implemented by a terminal device or a server, and this application does not impose any special limitations on it. For ease of understanding and description, the following embodiments are all described in detail using an in-vehicle infotainment system as an example.

[0028] It should be noted that the server can be a single device or a system composed of multiple devices, i.e., a distributed server. This application does not make any specific limitations in this regard.

[0029] like Figure 1 As shown in the figure, this application provides a human factors verification method for a vehicle infotainment interface, including: S101: Determine the target interface area corresponding to the target button in the interface to be evaluated.

[0030] First, after receiving the interface to be evaluated, the vehicle's infotainment system delineates a target interface area based on the location of the target button within that interface. It's important to note that the target button refers to a frequently used function button on the infotainment interface, such as the air conditioning switch, navigation start button, or volume control. These buttons are typically closely related to driving safety and user efficiency, therefore their design rationale requires careful evaluation. The target interface area refers to the area occupied by the target button on the interface and its surrounding areas that may affect the user's visual attention. The delineation of the target interface area can be dynamically adjusted based on the actual size and position of the target button, as well as the distribution of surrounding visual elements, to ensure that the collected eye-tracking data accurately reflects the user's attention allocation to that button.

[0031] In determining the target interface region corresponding to the target button, the size of the target button can be directly used to demarcate a target interface region of corresponding size, i.e., the range of the target interface region is consistent with the actual size of the target button. In addition, the target interface region can also be appropriately expanded in combination with visual guidance elements in interface design, such as the blank area around the button, color contrast, or icon style, etc., to capture additional attention distribution that the user may involve in the operation process. This dynamic adjustment method can more comprehensively reflect the visual behavior characteristics of the user in the real driving environment, thereby providing a more accurate basis for subsequent data analysis.

[0032] In interface evaluation, the to-be-evaluated interface can contain only one target button, or can contain multiple target buttons, i.e., the interface layout of multiple target buttons is evaluated at the same time.

[0033] In the evaluation scenario of multiple target buttons, the target interface region corresponding to each target button needs to be demarcated respectively, and it is ensured that there is no overlap or interference between these regions. In this way, the eye movement data of each target button can be analyzed independently, so as to more accurately evaluate the design rationality. In addition, in actual operation, in order to further improve the evaluation efficiency, the target buttons with higher usage frequency or stronger association with driving safety can be preferentially selected for key analysis. This strategy not only focuses on key issues, but also effectively reduces unnecessary consumption of computing resources.

[0034] S102: Obtain eye movement fixation data of the user when driving in different scenarios.

[0035] After determining the target interface region in the to-be-evaluated interface, the car machine system can obtain the eye movement fixation data of the user when driving in different scenarios through devices such as eye trackers. The eye movement fixation data includes first fixation time, number of fixation points in the target interface region, maximum single deviation from the road duration, and saccade number of the target interface region.

[0036] The first fixation time refers to the time interval from the presentation of the stimulus target (such as a picture, text) to the first eye fixation of the subject on the target. The maximum single deviation from the road duration refers to the maximum time for a single driver's line of sight to deviate from the front road. The number of fixation points in the target interface region refers to the number of times the fixation point of the subject falls into the target interface region during the saccade process. The saccade number of the target interface region refers to the number of times the subject saccades the target interface region. The fixation point refers to the moment and position at which the eye is relatively stable and gazing in a certain position when watching a visual scene, which can be obtained through devices such as eye trackers.

[0037] The above four kinds of eye movement fixation data are illustrated as follows: the subject spends 0.8s of time to saccade to the target interface area after the interface is presented for the first time, the fixation point falls into the target interface area, and two fixation points are left in the target interface area, but the target button is not saccaded to (at this time, the target interface area includes the target button and the surrounding area thereof); since the subject is in a driving state at this time, the subject needs to concentrate on the road ahead after the first saccade fails; the subject spends 1s of time to confirm that the current driving state is correct, and then moves the gaze to the car screen to find the target interface area again, and after spending 1.2s, three fixation points are left in the target interface area, and the target button is found. At this time, the first fixation time is 0.8+1+1.2=3s, the maximum time of deviating from the road is the larger one of 1.2s and 0.8s, that is, 1.2s. The number of fixation points in the target interface area is 5, and the number of saccades in the target interface area is 2.

[0038] It is worth noting that the collection process of eye movement data needs to fully consider the individual differences of users, such as driving experience, visual sensitivity, and operation habits, etc. These factors may have a certain impact on eye movement fixation data, so a corresponding correction mechanism needs to be introduced in the data analysis stage. For example, by comparing the data distribution of different user groups, abnormal values or extreme samples can be removed to ensure the stability and reliability of the final score results. At the same time, in order to improve the representativeness of the data, it is recommended to cover a diverse user group as much as possible in the experimental design stage, including users of different ages, genders, and driving proficiency.

[0039] In one embodiment, when acquiring the eye movement fixation data of the user, the eye movement fixation data of the driver when clicking the target button is acquired in multiple scenarios simulating real driving environments; wherein the different scenarios include at least one of different stable speed driving scenarios, different road type scenarios, different light condition scenarios, and different driving load scenarios. Specifically, the different stable speed scenarios can include low-speed driving scenarios in urban roads (such as 30km / h or 50km / h), medium-high speed driving scenarios in highways (such as 80km / h), etc. Different road type scenarios can cover urban roads, rural roads, mountainous roads, complex intersection roads, etc. Different light condition scenarios involve daytime sunny, overcast, dusk, and night driving environments, etc. These light changes will significantly affect the visual perception and attention allocation of the driver. Different driving load scenarios can be constructed by simulating single task operation and multi-task parallel situations, such as only setting navigation in a smooth driving state, or handling incoming calls, adjusting air conditioning, etc. in traffic jams. By collecting eye movement data in diversified scenarios, the behavior characteristics of users in real driving environments can be more comprehensively reflected, thereby providing more representative basis for subsequent scoring.

[0040] In addition, a dynamic scene switching mechanism can also be introduced in the experimental design to simulate unexpected situations or environmental changes that may occur during actual driving. For example, when a vehicle enters a tunnel from a highway, the sudden change in lighting conditions can interfere with the driver's visual transfer; or when an emergency brake is encountered, the driver's attention allocation to the vehicle interface may be significantly affected. The design of such dynamic scenes not only enhances the authenticity and complexity of data collection, but also helps to identify the adaptability and robustness of interface design in dealing with unexpected situations. By combining the analysis of static and dynamic scenes, the comprehensiveness and accuracy of the scoring system can be further optimized to ensure that the human factor verification results truly reflect the performance of the vehicle interface under various driving conditions.

[0041] S103: Determine the scene interface verification value corresponding to the to-be-evaluated interface in different scenes based on the eye fixation data.

[0042] In one embodiment, after obtaining the eye fixation data, the scene interface verification value of the to-be-evaluated interface in different scenes can be determined based on the eye fixation data. Here, the scene refers to the driving scene of the vehicle, and the size of the scene interface verification value is used to quantify the performance of the to-be-evaluated interface in a specific driving scene. Specifically, when selecting the test scene, the test scene can be limited by the use scene of the to-be-evaluated interface. For example, if the to-be-evaluated interface is mainly used in high-speed driving environment, the test scene can focus on the driving conditions such as expressway, urban expressway, etc. that match it. For interfaces suitable for low-speed or parking scenes, such as reverse image interfaces, corresponding scenes such as parking lots, narrow road sections, etc. should be selected for testing. In this way, the scoring results can be more in line with actual use requirements, and the pertinence and practicality of the human factor verification method can be improved.

[0043] S104: Determine the comprehensive interface verification value of the to-be-evaluated interface based on the scene interface verification value corresponding to the to-be-evaluated interface in different scenes.

[0044] After obtaining the scene interface verification values of the interface to be evaluated in multiple scenarios, the comprehensive interface verification value of the interface to be evaluated can be determined based on the scene interface verification values respectively corresponding to the interface to be evaluated in different scenarios and the importance of each scenario. In determining the comprehensive interface verification value, a quantitative analysis of the importance of different scenarios is first needed. Specifically, a corresponding weight value can be assigned to each scenario according to the frequency of occurrence of each driving scenario in actual use, the degree of influence on driving safety, and the criticality of user operation. For example, the highway scenario can be assigned a higher weight due to its high speed and complex road conditions, while the parking lot scenario can be assigned a relatively low weight due to its low speed characteristics. Through this weight distribution mechanism, the contribution of each scenario in the overall human factor verification can be more scientifically reflected.

[0045] The comprehensive interface verification value of the interface to be evaluated is obtained by weighting the scene interface verification values of each scenario and the corresponding weight values. This process needs to ensure the rationality and objectivity of weight distribution, and at the same time, it needs to be calibrated in combination with actual driving data. For example, a large number of real driving records can be referred to to statistically analyze the occurrence probability of different scenarios, and the weight can be dynamically adjusted in combination with expert evaluation. In addition, when calculating the comprehensive interface verification value, the influence of extreme scenarios also needs to be considered to avoid excessive deviation of the overall result due to the low score of individual low-frequency but high-risk scenarios. In this way, the performance of the car-machine interface in diversified driving environments can be more comprehensively reflected, providing a reliable basis for subsequent optimization.

[0046] In order to further improve the scientificity of the human factor verification method, multi-dimensional evaluation indicators can also be introduced. In addition to eye movement fixation data, objective data such as user subjective feedback, operation completion time, and error rate can also be combined to form a more comprehensive human factor verification system. For example, after the user completes a specific task, a questionnaire survey can be conducted to collect his subjective feelings about the interface usability and intuitiveness, and these data can be combined with eye movement data to generate a more comprehensive scoring model. This method not only makes up for the limitations of a single data source, but also reveals potential problems in interface design from multiple angles.

[0047] In one embodiment, in determining the scene interface verification values respectively corresponding to the interface to be evaluated in different scenarios, first, the optimal values of each eye movement fixation data are obtained, and then the normalized deviation values of the actual values of each eye movement fixation data from the optimal values are determined. Then, based on the normalized deviation values, the single verification values of each eye movement fixation data, and the weighted sum of the single verification values of at least one eye movement fixation data, the scene interface verification value is obtained.

[0048] By this method, it can be ensured that each eye movement fixation data is reasonably reflected in the scoring process, while avoiding the excessive influence of some abnormal values on the overall scoring results. For example, the optimal value of the first fixation time may be set as a certain short time interval, and some users may exceed this interval in actual testing. By calculating the normalized deviation value, this difference can be quantified and controlled within a reasonable range, thereby improving the fairness and accuracy of the score. In addition, the weight of each eye movement fixation data also needs to be dynamically adjusted according to its actual impact on driving safety and user experience. For example, the maximum duration of single deviation from the road may be given a higher weight because this indicator is directly related to driving safety, while the number of saccades in the target interface area may have a lower weight, mainly reflecting the user's operation efficiency.

[0049] In one embodiment, when determining the normalized deviation value of each eye movement fixation data from the optimal value, the absolute difference between the actual value of each eye movement fixation data and the corresponding optimal value can be calculated; the absolute difference is subjected to ratio operation with the corresponding optimal value to obtain the deviation ratio of each eye movement fixation data; and the deviation ratio is subjected to exponential decay processing according to a preset sensitivity coefficient to obtain the normalized deviation value.

[0050] By this method, the interference of abnormal values on the scoring results can be effectively reduced, and the robustness of the scoring model can be improved. Specifically, the introduction of the sensitivity coefficient can flexibly adjust the weight of the deviation ratio according to the actual needs, thereby ensuring the accuracy of the score while avoiding excessive sensitivity. For example, in the indicators related to driving safety, a higher sensitivity coefficient can be set to highlight their importance; while for the indicators of operation efficiency, the sensitivity coefficient can be appropriately reduced to balance the overall score. In addition, the exponential decay processing method can also ensure that the normalized deviation value converges within a reasonable range, avoiding distortion of the score caused by individual extreme data. This scientific data processing method not only improves the reliability of the scoring results, but also provides more accurate guidance for subsequent interface optimization.

[0051] In one embodiment, in order to further enhance the applicability of the human factor verification method, the user's subjective feedback can also be combined to correct the comprehensive interface verification value. Specifically, the user's satisfaction with the interface design can be collected through questionnaire survey or interview, and these subjective data can be combined with eye movement data to form a multi-dimensional comprehensive interface verification value system. For example, the subjective satisfaction score can be included in the final score calculation according to a certain proportion to make up for the details of user experience that may be ignored by relying solely on objective data. In this way, not only can the actual use effect of the interface be more comprehensively reflected, but also the designer can better understand the user's needs, so as to develop more targeted optimization strategies.

[0052] Furthermore, the human factors verification method for in-vehicle interfaces provided in this application also supports a dynamic update mechanism, which can continuously optimize the scoring model based on new data from actual applications. For example, as the in-vehicle system iterates and upgrades or the user group changes, the parameters in the scoring model can be recalibrated by periodically collecting new eye-tracking data and subjective feedback. This dynamic adjustment capability enables the human factors verification method to adapt to different application scenarios and user needs, thereby maintaining its long-term effectiveness.

[0053] Specifically, the score for each indicator can be calculated using the normalized distance method, as shown in the following formula:

[0054] in: As an indicator The optimal value, The actual test value of the subject. For scoring, the closer to 1, the better the performance. This is the weighted sensitivity coefficient of the indicator.

[0055] Specifically, for the four eye movement indicators mentioned above, there are four scoring formulas as follows: First fixation time score: ,in, The score is the initial fixation time. The actual first fixation time of the subject. This represents the optimal value for the first fixation time. This is the weighted sensitivity coefficient for the first fixation time.

[0056] Score for the number of fixations within the target interface area: ,in, The score is based on the number of gaze points within the target interface area. The number of fixation points within the target interface area for the subject. This represents the optimal number of fixation points within the target interface area. The weighted sensitivity coefficient is used to score the number of gaze points within the target interface area.

[0057] Maximum time score for a single deviation from the road: ,in, The score is the maximum time spent deviating from the road in a single instance. The maximum time for a single deviation from the road by the subject. The optimal value for the maximum time of a single deviation from the road. This is the weighted sensitivity coefficient for the maximum time of a single deviation from the road.

[0058] Target interface area scan count score: ,in, Score the number of times the target interface area is scanned. The number of times the subject scanned the target interface area. The optimal number of scans for the target interface area. The weighted sensitivity coefficient for the number of times the target interface area is scanned.

[0059] In one embodiment, after calculating the individual verification value of each eye-tracking gaze data, when performing weighted summation to obtain the scene interface verification value, the indicator weights of each eye-tracking gaze data can be pre-assigned according to the degree of influence of each eye-tracking gaze data on driving safety and operational efficiency; the individual verification value of each eye-tracking gaze data is multiplied by the corresponding indicator weight to obtain a weighted score; and all weighted scores are summed to obtain the scene interface verification value.

[0060] This method ensures that the scene interface verification values ​​are more scientific and reasonable, fully reflecting the differences in importance of different eye-tracking indicators in actual driving. For example, indicators that directly affect driving safety, such as the maximum time of a single deviation from the road, can be given higher weights; while indicators that reflect operational efficiency more, such as the number of scans of the target interface area, can have their weight appropriately reduced. This weighting method not only highlights the role of key indicators but also avoids excessive interference from secondary indicators in the overall score, thereby improving the accuracy and practicality of human factor verification results.

[0061] Specifically, the scene interface verification value can be calculated using the following formula:

[0062] in, For scene interface verification values, , , , Let the indicator weights be the weights, and satisfy the following conditions: .

[0063] In one embodiment, after determining the scene interface verification value, when determining the comprehensive interface verification value of the interface to be evaluated, the scene weight of each driving scene can be pre-defined based on at least one of the frequency of occurrence of the driving scene in actual driving, the level of safety risk, and the importance of the task; then, the scene interface verification value of each scene is multiplied by its corresponding scene weight to obtain a weighted scene score; and the comprehensive interface verification value of the interface to be evaluated is obtained by summing all the weighted scene scores.

[0064] Specifically, it is set up In different vehicle speed scenarios, the first The overall score for each scenario is The corresponding weight is , the comprehensive interface verification value can be determined by the following formula:

[0065] In particular, if , then: , and satisfies: .

[0066] Through this method, it can be ensured that the comprehensive interface verification value can more accurately reflect the actual performance of the interface to be evaluated in different driving scenarios. The allocation of weights not only considers the frequency of occurrence of the scene, but also combines the safety risk level and the importance of the task, so that the scoring result is more valuable. For example, in the high-speed driving scenario, due to its high safety risk and strict requirements for driving operation, the corresponding weight will be significantly higher than that in low-speed or parking scenarios. This design can effectively avoid the deviation caused by unreasonable weight allocation.

[0067] In addition, in order to further improve the scientificity of the scoring system, a dynamic weight adjustment mechanism can also be introduced. Specifically, according to the change trend of the actual test data, the weight value of each scene can be dynamically updated. For example, when the user feedback or eye movement data in a specific scene shows abnormal fluctuations, the weight of that scene can be automatically adjusted through the algorithm to more accurately reflect its importance in the whole. This way not only enhances the flexibility of the scoring model, but also better adapts to complex actual driving environments.

[0068] In the implementation process, special attention should also be paid to the consistency and reliability of data collection. In order to ensure the objectivity of the scoring results, external interference factors should be minimized to affect the eye movement data. For example, through standardized experimental environment settings, unified test procedures, and strict subject screening mechanisms, data noise can be minimized. At the same time, for abnormal data points, statistical methods can be used for identification and processing to avoid their adverse effects on the final scoring results.

[0069] Finally, after completing the calculation of the comprehensive interface verification value, it is recommended to compare and analyze the scoring results with industry standards or historical data. Through this way, not only can the effectiveness of the scoring model be verified, but also a more explicit direction for the design optimization of the car interface can be provided. For example, if the score of a certain indicator is significantly lower than the industry average, it indicates that this indicator may become the focus of design improvement. This data-driven analysis method helps to continuously improve the performance of the car interface while meeting the growing needs of users.

[0070] In one embodiment, after obtaining the comprehensive interface verification value, the interface can be optimized by the comprehensive interface verification value and the scene interface verification value in each scene. Specifically, if the comprehensive interface verification value is lower than a first preset threshold, the target button in the interface to be evaluated is optimized, and the optimization measures include adjusting at least one of the interface position, size, color, shape and icon style of the target button in the interface.

[0071] It can be understood that if the comprehensive interface verification value is low, it means that the current interface to be evaluated may have major problems in actual use and needs to be improved first. At this time, the designer can locate the key scene that performs poorly according to the distribution of the specific scene interface verification value, and further analyze the root cause of the problem combined with user behavior data and subjective feedback. For example, if the score of the target button in a certain scene is significantly lower than that of other areas, it may indicate that the design of the button has obvious defects, such as unreasonable position, insufficient visual appeal or poor operation convenience, etc. To solve these problems, targeted optimization strategies can be taken, such as moving the button to an area where the user's line of sight is easier to capture, or improving its recognizability by increasing the button size, adjusting the color contrast, etc.

[0072] If the scene interface verification value corresponding to the target scene is higher than a second preset threshold, the interface to be evaluated can be used as the recommended interface of the target scene. It can be understood that in actual application, the selection of the recommended interface depends not only on the level of the scene interface verification value, but also on the comprehensive consideration of the specific needs and use habits of the user group. For example, for some specific user groups, such as elderly drivers or novice drivers, more attention may be needed to the intuitiveness and ease of operation of the interface, even if its scene interface verification value is slightly lower than that of other interfaces, it can also be used as a recommended option. This flexible recommendation mechanism can better meet the needs of different users and improve the overall user experience.

[0073] In addition, in the interface optimization process, the A / B testing method can also be introduced to verify the actual effect of the optimization measures. Specifically, the optimized interface and the original interface can be put into the same or similar driving scenes at the same time, and by comparing the comprehensive interface verification values and user feedback data of the two, the effectiveness of the optimization scheme can be evaluated. If the optimized interface shows significant improvement in scoring and user satisfaction, it can be used as the final design scheme; otherwise, the optimization strategy needs to be further adjusted. This method not only can reduce the design risk, but also can provide reliable data support for subsequent interface improvement.

[0074] To ensure the efficiency of the optimization process, a complete index tracking system can also be established. This system can record and analyze the trends of various eye movement indicators and comprehensive interface validation values in real time, helping designers quickly identify key issues in the optimization process. For example, if the score of a certain indicator has not reached the expected level after multiple optimizations, it may indicate that the current optimization direction is biased and the design approach needs to be reconsidered. At the same time, the tracking system can also provide long-term data accumulation for the design team, laying a solid foundation for future iteration and upgrade of car machine interfaces.

[0075] In addition, by comparing multiple versions of design schemes horizontally, it can be further determined which layout or style is more in line with the user's usage habits and attention distribution characteristics. Thus, in the interface optimization process, a set of data-driven design specifications is gradually formed. Such specifications not only guide the optimization direction of the current project, but also provide a reference for subsequent similar projects, thereby improving the overall design efficiency. For example, by analyzing the eye movement data and user feedback of different design schemes, some general design principles can be summarized, such as the optimal layout area of buttons, the reasonable range of color contrast, and the preferred scheme of icon style, etc. The establishment of these principles helps to reduce the trial and error cost in the design process, while ensuring the consistency and scientificity of the design scheme.

[0076] Further, in practical applications, machine learning algorithms can also be combined to deeply mine historical data to discover potential design optimization points. For example, through cluster analysis to identify common features in user behavior patterns, or using regression models to predict the score change trend that different design schemes may bring. This method not only enhances the accuracy of design decisions, but also helps the team to avoid potential risks in advance. In summary, the present scheme introduces a multi-dimensional scoring system based on eye movement data, combined with weight allocation of driving scenarios, to achieve a comprehensive and objective evaluation of the car-machine interface. This method can quantify the user's attention distribution under different driving conditions, providing a basis for optimization. At the same time, by adjusting the interface properties of the target button and combining with the recommendation mechanism of specific scenarios, the safety and usability of the interface are further improved. In addition, the present application introduces a normalized deviation value and a weight allocation mechanism, significantly improving the scientificity and practicality of the scoring results. The calculation of the normalized deviation value effectively solves the problem of different eye movement data dimensions and range differences, making the scoring more accurate and comparable. The weight allocation is set according to the actual influence of each eye movement data on driving safety and operation efficiency, ensuring that the scoring system can more truly reflect the performance of the interface design in key performance indicators. This human factor verification method combining multi-dimensional data and scenario weights can not only comprehensively evaluate the adaptability of the car-machine interface in different driving environments, but also provides a clear direction and priority ranking for interface optimization, helping designers focus on the problems and scenarios that have the greatest impact on user experience.

[0077] In addition, as Figure 2 indicated, Figure 2 is a structural schematic diagram of a car-machine interface human factor verification device provided by an embodiment of the present application, which comprises: A target interface area determination module 201 determines the target interface area corresponding to the target button in the interface to be evaluated.

[0078] An eye movement data acquisition module 202 acquires eye movement fixation data of a user when driving in different scenarios, wherein the eye movement fixation data comprises at least one of first fixation time, number of fixation points in the target interface area, maximum single deviation time from the road, and number of saccades in the target interface area.

[0079] A scenario interface verification value determination module 203 determines the scenario interface verification value corresponding to the interface to be evaluated in different scenarios based on the eye movement fixation data.

[0080] A comprehensive interface verification value determination module 204 determines the comprehensive interface verification value of the interface to be evaluated based on the scenario interface verification values corresponding to the interface to be evaluated in different scenarios.

[0081] In one specific embodiment, the scenario interface verification value determination module 203 comprises: acquiring the optimal value of each eye movement fixation data pre-labeled; determining the normalized deviation value of the actual value of each eye movement fixation data and the optimal value; determining the single-item verification value of each eye movement fixation data based on the normalized deviation value; and performing weighted summation on the single-item verification values of at least one eye movement fixation data to obtain the scenario interface verification value.

[0082] In one specific embodiment, the scene interface verification value determination module 203 comprises: calculating the absolute difference between the actual value of each eye movement fixation data and the corresponding optimal value; performing ratio operation on the absolute difference and the corresponding optimal value to obtain the deviation ratio of each eye movement fixation data; performing exponential decay processing on each deviation ratio according to a preset sensitivity coefficient to obtain the normalized deviation value.

[0083] In one specific embodiment, the scene interface verification value determination module 203 comprises: pre-allocating an index weight to each eye movement fixation data according to the influence degree of the eye movement fixation data on driving safety and operation efficiency; multiplying the single-item verification value of each eye movement fixation data by the corresponding index weight to obtain a weighted score; summing all the weighted scores to obtain the scene interface verification value.

[0084] In one specific embodiment, the eye movement data acquisition module 202 comprises: acquiring eye movement fixation data of a driver when the driver clicks the target button in a plurality of scenes simulating real driving environments; the different scenes include at least one of driving scenes with different stable vehicle speeds, different road type scenes, different light condition scenes, and different driving load scenes.

[0085] In one specific embodiment, the comprehensive interface verification value determination module 204 comprises: pre-calibrating a scene weight of each driving scene based on at least one of the occurrence frequency of the driving scene in the actual driving process, the safety risk level, and the task importance; multiplying each scene interface verification value by its corresponding scene weight to obtain a weighted scene score; summing all the weighted scene scores to obtain the comprehensive interface verification value of the interface to be evaluated.

[0086] In one specific embodiment, the comprehensive interface verification value determination module 204 comprises: in response to the comprehensive interface verification value being lower than a first preset threshold, optimizing the target button in the interface to be evaluated, the optimization measures including at least one of adjusting the interface position, size, color, shape, and icon style of the target button in the interface; in response to the scene interface verification value of the target scene being higher than a second preset threshold, taking the interface to be evaluated as the recommended interface of the target scene.

[0087] As to the apparatus in the above-mentioned embodiments, the specific manner in which each unit performs the operation has been described in detail in the embodiments of the method, and will not be described in detail here.

[0088] Figure 3 is a structural schematic diagram of a vehicle provided by an embodiment of the present application.

[0089] For example, Figure 3As shown, the vehicle includes a memory 301 and a processor 302, wherein the memory 301 stores executable program code 3011, and the processor 302 is configured to invoke and execute the executable program code 3011 to perform the human factor verification method of the vehicle-machine interface.

[0090] The embodiment can divide the functional modules of the vehicle according to the above method examples. For example, each functional module can be divided, or two or more functions can be integrated into one processing module. The integrated module can be implemented in the form of hardware. It should be noted that the division of the modules in the embodiment is illustrative, and is only a logical functional division. In actual implementation, another division manner can be used.

[0091] In the case of dividing each functional module corresponding to each function, the vehicle can include: a target interface area determination module configured to determine a target interface area corresponding to a target button in the to-be-evaluated interface; an eye movement data acquisition module configured to acquire eye movement fixation data of a user when driving in different scenes, the eye movement fixation data including at least one of a first fixation time, a number of fixation points in the target interface area, a maximum time length of single deviation from the road, and a number of saccades in the target interface area.

[0092] a scene interface verification value determination module configured to determine a scene interface verification value corresponding to the to-be-evaluated interface in different scenes based on the eye movement fixation data.

[0093] a comprehensive interface verification value determination module configured to determine a comprehensive interface verification value of the to-be-evaluated interface based on the scene interface verification values corresponding to the to-be-evaluated interface in different scenes. It should be noted that all related contents of each step involved in the above method embodiment can be referred to the function description of the corresponding functional module, and will not be repeated here.

[0094] The vehicle provided in the embodiment is used to perform the human factor verification method of the vehicle-machine interface, and thus can achieve the same effect as the above implementation method.

[0095] In the case of using an integrated unit, the vehicle can include a processing module and a storage module. The processing module can be used to control and manage the actions of the vehicle. The storage module can be used to support the vehicle to execute program codes and data.

[0096] The processing module can be a processor or a controller, which can realize or execute various exemplary logical blocks, modules and circuits in combination with the disclosure of the present application. The processor can also be a combination of computing functions, such as including one or more microprocessor combinations, digital signal processing (digital signal processing, DSP) and microprocessor combinations, etc. The storage module can be a memory.

[0097] The embodiment also provides a computer readable storage medium, which stores computer program codes (including but not limited to disk storage, CD-ROM, optical storage, etc.), when the computer program codes are run on a computer, the computer is caused to execute the above-mentioned related method steps to realize the human factor verification method of the vehicle-machine interface provided by the above-mentioned embodiment.

[0098] The embodiment also provides a computer program product, when the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to realize the human factor verification method of the vehicle-machine interface provided by the above-mentioned embodiment.

[0099] The beneficial effects of the above-mentioned embodiments can refer to the beneficial effects of the corresponding methods provided above, which will not be repeated here.

[0100] Through the description of the above embodiments, those skilled in the art can understand that, for the convenience and brevity of description, only the above-mentioned division of each functional module is taken as an example, in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0101] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual ones can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0102] In the description of the present disclosure, it needs to be understood that, if the orientation or positional relationship indicated by the terms such as "upper", "lower", "front", "back", "left" and "right" refers to the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, it is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the position or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present disclosure.

[0103] It should be noted that, in this document, the terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between the entities or operations. It should also be noted that the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or equipment including the element.

[0104] The above is only an embodiment of the present disclosure, and is not intended to limit the present disclosure. The present disclosure can have various changes and variations for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present disclosure shall be included in the scope of claims of the present disclosure.

Claims

1. A human factor authentication method for an in-vehicle infotainment interface, the method comprising: The method comprises the steps of: determining a target interface region corresponding to a target button in a to-be-evaluated interface; obtaining eye movement fixation data of a user driving in different scenes, the eye movement fixation data comprising at least one of a first fixation time, a number of fixation points in the target interface region, a maximum time of single deviation from a road, and a number of saccades in the target interface region; based on the eye movement fixation data, determining a scene interface verification value corresponding to the to-be-evaluated interface in different scenes respectively; based on the scene interface verification values corresponding to the to-be-evaluated interface in different scenes respectively, determining a comprehensive interface verification value of the to-be-evaluated interface.

2. The method of claim 1, wherein, The step of determining the scene interface verification value corresponding to the to-be-evaluated interface in different scenes respectively based on the eye movement fixation data comprises the steps of: obtaining an optimal value of each eye movement fixation data pre-labeled; determining a normalized deviation value of an actual value of each eye movement fixation data from the optimal value respectively; based on the normalized deviation value, determining a single verification value of each eye movement fixation data; performing weighted summation on the single verification value of at least one eye movement fixation data to obtain the scene interface verification value.

3. The method of claim 2, wherein, The step of determining the normalized deviation value of the actual value of each eye movement fixation data from the optimal value comprises the steps of: calculating an absolute difference value of the actual value of each eye movement fixation data from the corresponding optimal value; performing ratio operation on the absolute difference value and the corresponding optimal value to obtain a deviation ratio of each eye movement fixation data; performing exponential decay processing on each deviation ratio according to a preset sensitivity coefficient to obtain the normalized deviation value.

4. The method of claim 2, wherein, The step of performing weighted summation on the single verification value of at least one eye movement fixation data to obtain the scene interface verification value comprises the steps of: pre-allocating an index weight to each eye movement fixation data according to an influence degree of each eye movement fixation data on driving safety and operation efficiency; multiplying the single verification value of each eye movement fixation data by the corresponding index weight to obtain a weighted score; summing all the weighted scores to obtain the scene interface verification value.

5. The method of claim 1, wherein, The step of obtaining the eye movement fixation data of the user driving in different scenes comprises the steps of: obtaining the eye movement fixation data when the driver clicks the target button in a plurality of scenes simulating a real driving environment; the different scenes comprise at least one of driving scenes with different stable vehicle speeds, road type scenes, light condition scenes, and driving load scenes.

6. The method of claim 1, wherein, The step of determining the comprehensive interface verification value of the to-be-evaluated interface based on the scene interface verification values corresponding to the to-be-evaluated interface in different scenes respectively comprises the steps of: pre-labeling a scene weight of each driving scene based on at least one of a frequency of occurrence of the driving scene in an actual driving process, a safety risk level, and a task importance; multiplying each scene interface verification value by the corresponding scene weight to obtain a weighted scene score; summing all the weighted scene scores to obtain the comprehensive interface verification value of the to-be-evaluated interface.

7. The method of claim 1, wherein, After determining the comprehensive interface verification value of the to-be-evaluated interface, the method further comprises the steps of: In response to the comprehensive interface verification value being lower than a first preset threshold, the target button in the interface to be evaluated is optimized, and the optimization measures include adjusting at least one of the interface position, size, color, shape, and icon style of the target button in the interface.

8. The method of claim 1, wherein, After the scene interface verification values corresponding to the interface to be evaluated in different scenes are determined, the method further includes: In response to the scene interface verification value corresponding to the target scene being higher than a second preset threshold, the interface to be evaluated is taken as the recommended interface of the target scene.

9. A human authentication apparatus for an in-vehicle interface, characterized by comprising: Comprise: A target interface region determination module determines a target interface region corresponding to a target button in an interface to be evaluated; An eye movement data acquisition module acquires eye movement fixation data of a user when driving in different scenes, and the eye movement fixation data includes at least one of first fixation time, number of fixation points in the target interface region, maximum single deviation time from the road, and number of saccades in the target interface region; A scene interface verification value determination module determines scene interface verification values corresponding to the interface to be evaluated in different scenes based on the eye movement fixation data; A comprehensive interface verification value determination module determines a comprehensive interface verification value of the interface to be evaluated based on the scene interface verification values corresponding to the interface to be evaluated in different scenes.

10. A vehicle characterized by comprising: Comprise: At least one processor; And The memory is in communication connection with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the human factor verification method of the car machine interface as claimed in any one of claims 1-8.

Images