Automobile intelligent cabin man-machine interaction experience evaluation method and system

Abstract

The invention discloses an automobile intelligent cabin man-machine interaction experience evaluation method and system, and relates to the technical field of automobile man-machine interaction evaluation, and the method comprises the steps: obtaining man-machine interaction data when a driver experiencer uses an automobile intelligent cabin to complete a target man-machine interaction task; determining a plurality of evaluation indexes based on the man-machine interaction data; the evaluation indexes comprise an operation complexity index, a visual pleasure index and an interface index; constructing an evaluation index judgment matrix according to each evaluation index; inputting the evaluation index judgment matrix into an evaluation index model, and determining a man-machine interaction experience evaluation index of the automobile intelligent cabin; the evaluation index model comprises a comprehensive weight value corresponding to each evaluation index, and the comprehensive weight value of each evaluation index is comprehensively determined in advance based on an analytic hierarchy process and an entropy weight method. The interactive experience of the automobile cabin is evaluated through multiple evaluation indexes, and the evaluation result is more objective and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile human-computer interaction evaluation, and in particular to a method and system for evaluating the human-computer interaction experience of an automobile intelligent cockpit. Background Art

[0002] With the widespread application and development of artificial intelligence, information technology and Internet of Things technology in the field of transportation, the layout of the car cockpit and the presentation of human-computer interaction interface information are gradually changing towards digitalization, intelligence and networking. The human-computer interaction interface of the car is the carrier of human-vehicle interaction. It is not only closely related to the driving safety and system construction of the car, but also an important medium for user experience, user perception and information interaction in the cockpit. After the advanced driver assistance system (ADAS) and the in-vehicle information system (IVIS) are widely used in the car system, the essential attributes of the car are gradually evolving from the attributes of a vehicle for the purpose of passenger use to the attributes of an interactive passenger space driven by services. The interactive experience evaluation method of traditional cars usually focuses on the evaluation of driving control, interior space, seat comfort and other aspects, and does not involve functions such as voice recognition, touch screen, gesture control, and automatic driving. Therefore, the interactive experience evaluation method based on traditional cars cannot well evaluate the interactive experience of the smart car cockpit. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for evaluating the human-computer interaction experience of an automobile intelligent cockpit, which can evaluate the interactive experience of the intelligent automobile cockpit more objectively and accurately.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] In a first aspect, the present invention provides a method for evaluating human-computer interaction experience in an intelligent vehicle cockpit, comprising:

[0006] Obtaining human-computer interaction data when a driver or passenger uses a smart cockpit of a car to complete a target human-computer interaction task; the human-computer interaction data includes behavioral data, physiological data, and psychological data;

[0007] Based on the human-computer interaction data, a plurality of evaluation indicators are determined; the evaluation indicators include an operation complexity indicator, a visual pleasure indicator and an interface indicator; the operation complexity indicator is determined based on the behavior data, the visual pleasure indicator is determined based on the physiological data, and the interface indicator is determined based on the physiological data and the psychological data;

[0008] According to each of the evaluation indicators, an evaluation indicator judgment matrix is ​​constructed; each element in the evaluation indicator judgment matrix is ​​the relative importance between two of the evaluation indicators;

[0009] The evaluation index judgment matrix is ​​input into the evaluation index model to determine the human-computer interaction experience evaluation index of the automobile intelligent cockpit; the evaluation index model includes the comprehensive weight value corresponding to each evaluation index, and the comprehensive weight value of each evaluation index is pre-determined based on the hierarchical analysis method and the entropy weight method.

[0010] Optionally, before obtaining the human-computer interaction data when the driver and passenger use the car intelligent cockpit to complete the target human-computer interaction task, it also includes:

[0011] Obtain a target human-computer interaction task for the automobile intelligent cockpit.

[0012] Optionally, the target human-computer interaction tasks include: destination navigation, answering and making phone calls, music selection and switching, radio station selection and switching, in-vehicle APP interaction, air-conditioning temperature adjustment, instrument panel observation, voice wake-up and central control screen interaction.

[0013] Optionally, the behavior data includes the logic complexity, the number of operation actions, the management interface complexity and the input complexity of the target human-computer interaction task.

[0014] Optionally, the physiological data includes the number of blinks, blink frequency, blink amplitude, gaze time, gaze number and average pupil diameter.

[0015] Optionally, the psychological data include pleasure of the central control screen interface density, trust in the central control screen interface density, pleasure of the central control screen interface layout, pleasure of interface information density, dependence on interface information density, interface color emotion, trust in interface layout, interface layout interaction effort and interface cognitive evaluation.

[0016] Optionally, determining the comprehensive weight value corresponding to each evaluation indicator in the evaluation index model specifically includes:

[0017] Based on the hierarchical analysis method, determining a first weight value of each evaluation indicator;

[0018] Determine a second weight value of each evaluation indicator based on an entropy weight method;

[0019] For any of the evaluation indicators, a comprehensive weight value corresponding to the evaluation indicator is determined based on the first weight value of the evaluation indicator and the second weight value of the evaluation indicator.

[0020] Optionally, determining the second weight value of each evaluation indicator based on the entropy weight method specifically includes:

[0021] Perform dimensionless processing on each evaluation index value to obtain the dimensionless evaluation index;

[0022] Determining the information entropy value of each evaluation index according to the evaluation index after dimensionless processing;

[0023] According to the information entropy value of each evaluation index, the information utility value of each evaluation index is determined;

[0024] Based on the information utility value of each evaluation indicator, a second weight value of each evaluation indicator is determined.

[0025] Optionally, the evaluation index model is:

[0026] B=μ1A1+μ2A2+μ3A3+…+μ n A n ;

[0027] Among them, A1~A n Represents various evaluation indicators; μ1~μ n are the comprehensive weight values ​​corresponding to each evaluation index, and B is the human-computer interaction experience evaluation index.

[0028] In a second aspect, the present invention provides a human-computer interaction experience evaluation system for an automobile intelligent cockpit, comprising:

[0029] A data acquisition module is used to acquire human-computer interaction data when a driver uses the intelligent cockpit of a car to complete a target human-computer interaction task; the human-computer interaction data includes behavioral data, physiological data, and psychological data;

[0030] An evaluation index module, used to determine multiple evaluation indexes based on the human-computer interaction data; the evaluation indexes include an operation complexity index, a visual pleasure index and an interface index; the operation complexity index is determined based on the behavior data, the visual pleasure index is determined based on the physiological data, and the interface index is determined based on the physiological data and the psychological data;

[0031] A matrix construction module is used to construct an evaluation index judgment matrix according to each of the evaluation indexes; each element in the evaluation index judgment matrix is ​​the relative importance between two of the evaluation indexes;

[0032] An evaluation index module is used to input the evaluation index judgment matrix into an evaluation index model to determine the human-computer interaction experience evaluation index of the automobile intelligent cockpit; the evaluation index model includes a comprehensive weight value corresponding to each evaluation index, and the comprehensive weight value of each evaluation index is pre-determined based on the hierarchical analysis method and the entropy weight method.

[0033] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0034] The present invention discloses a method and system for evaluating the human-computer interaction experience of an automobile intelligent cockpit. The method comprises: firstly obtaining human-computer interaction data when a driver or passenger uses the automobile intelligent cockpit to complete a target human-computer interaction task; the human-computer interaction data comprises behavioral data, physiological data and psychological data; based on the human-computer interaction data, a plurality of evaluation indicators are determined; the evaluation indicators comprise an operation complexity indicator, a visual pleasure indicator and an interface indicator; the operation complexity indicator is determined according to the behavioral data, the visual pleasure indicator is determined according to the physiological data, and the interface indicator is determined according to the physiological data and the psychological data; according to each evaluation indicator, an evaluation indicator judgment matrix is ​​constructed; each element in the evaluation indicator judgment matrix is ​​the relative importance between two evaluation indicators; the evaluation indicator judgment matrix is ​​input into an evaluation index model to determine the human-computer interaction experience evaluation index of the automobile intelligent cockpit; the evaluation index model comprises a comprehensive weight value corresponding to each evaluation indicator, and the comprehensive weight value of each evaluation indicator is pre-comprehensively determined based on a hierarchical analysis method and an entropy weight method. The present invention uses multiple evaluation indicators such as operation complexity index, visual pleasure index and interface index for comprehensive evaluation, which can comprehensively evaluate the human-computer interaction experience of the car's intelligent cockpit and take into account different aspects of user feelings and experiences. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0036] Figure 1 A schematic diagram of a process flow of a method for evaluating human-computer interaction experience in an intelligent cockpit of an automobile provided in the first embodiment of the present invention;

[0037] Figure 2 This is a schematic diagram of the evaluation index system provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] The purpose of the present invention is to provide a method and system for evaluating the human-computer interaction experience of an automobile intelligent cockpit, which can evaluate the interactive experience of the intelligent automobile cockpit more objectively and accurately.

[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0041] Embodiment 1

[0042] like Figure 1 As shown, this embodiment provides a method for evaluating human-computer interaction experience in an intelligent cockpit of an automobile, comprising:

[0043] Step 1: Obtain human-computer interaction data when the driver and passenger use the car intelligent cockpit to complete the target human-computer interaction task; the human-computer interaction data includes behavioral data, physiological data and psychological data.

[0044] Step 2: Based on the human-computer interaction data, determine multiple evaluation indicators; the evaluation indicators include an operation complexity indicator, a visual pleasure indicator and an interface indicator; the operation complexity indicator is determined based on the behavioral data, the visual pleasure indicator is determined based on the physiological data, and the interface indicator is determined based on the physiological data and the psychological data.

[0045] Step 3: construct an evaluation index judgment matrix based on each of the evaluation indexes; each element in the evaluation index judgment matrix is ​​the relative importance between two of the evaluation indexes.

[0046] Step 4: Input the evaluation index judgment matrix into the evaluation index model to determine the human-computer interaction experience evaluation index of the automobile intelligent cockpit; the evaluation index model includes the comprehensive weight value corresponding to each evaluation index, and the comprehensive weight value of each evaluation index is pre-determined based on the hierarchical analysis method and the entropy weight method.

[0047] Among them, when executing step 2, the evaluation indicators for the human-computer interaction evaluation of the smart car cockpit are generally divided into complexity indicators, pleasure indicators and trust indicators. In this embodiment, the operation complexity index, visual pleasure index and interface index are specifically used. The complexity index, visual pleasure index and interface index are referred to as the first-level indicators.

[0048] Among them, the operation complexity index (first-level index) can be the human-computer interaction complexity entropy, such as Figure 2As shown in the figure, the secondary evaluation indicators for the complexity entropy of human-computer interaction include task logic complexity, number of actions, management interface complexity, and input complexity. Specifically, task logic complexity is used to evaluate the complexity of the task logic responsible for execution. The number of actions is used to evaluate the number of actions required for interaction. Management interface complexity is used to evaluate the complexity of the management interface. Input complexity is used to evaluate the complexity of user input. The specific visual pleasure is used to measure people's subjective feelings about the visual design of the cockpit. Visual trust is used to evaluate people's trust in the cockpit interface. The pleasure of the central control screen interface density is used to measure the pleasure brought by the density of the central control screen interface.

[0049] Among them, the visual pleasure index is specifically divided into visual pleasure, visual trust, and central control screen interface density pleasure. Figure 2 As shown, the secondary indicators for evaluating visual pleasantness include the number of blinks, blink frequency, blink amplitude, fixation time and number of fixations.

[0050] Specifically, the interface indicators are divided into interface density pleasure, interface density trust, interface layout pleasure and interface layout trust. Figure 2 As shown in , the interface indicators are divided into trust in the central control screen interface density, pleasantness in the central control screen interface layout, pleasantness of the interface information density, dependence on the interface information density, interface color emotion, trust in the interface layout, interactive effort in the interface layout, and interface cognitive evaluation. Among them, the secondary evaluation indicators for the three primary evaluation indicators of trust in the central control screen interface density, pleasantness in the central control screen interface density, and pleasantness in the central control screen interface layout are the number of blinks, blink frequency, blink amplitude, fixation time, number of fixations, and average pupil diameter.

[0051] Specifically, the psychological data include pleasure of the density of the central control screen interface, trust in the density of the central control screen interface, pleasure of the central control screen interface layout, pleasure of the interface information density, dependence on interface information density, interface color emotion, trust in the interface layout, interface layout interaction effort and interface cognitive evaluation.

[0052] Specifically, the physiological data includes the number of blinks, blink frequency, blink amplitude, fixation time, number of fixations and average pupil diameter.

[0053] The secondary indicators for the evaluation of the first-level indicators of pleasantness of interface information density, dependence of interface information density, interface color emotion, trust in interface layout, interactive effort of interface layout, and interface cognitive evaluation are P300, P200 and N400 amplitude, latency, and quantity. P300 amplitude is the amplitude of the P300 component detected in the brain wave. The P300 wave is usually related to cognition and attention. The change in its amplitude may reflect the user's pleasantness when facing interfaces with different information densities. P200 amplitude: Similar to P300, P200 wave is also a type of brain wave. Its amplitude change may be related to the user's cognition and attention, and has an impact on the pleasantness of interface information density. N400 amplitude: N400 wave is usually related to language and semantic processing. Here it is used to reflect the pleasantness of interface information density. Latency: Latency refers to the time from the start of stimulus presentation to the appearance of brain waves. For the pleasantness of interface information density, the length of the latency is related to the user's reaction speed to information density. Quantity: refers to the amount of information included in the interface. Users may prefer an interface with the right amount of information rather than an interface with too much or too little information.

[0054] In this embodiment, the priority relationship quantity scaling method is used to perform quantity scaling processing on each evaluation indicator in the automobile intelligent cockpit, and the quantity scaling of each evaluation indicator is determined, which may specifically include:

[0055] The relative importance of each indicator is scored using the priority relationship quantitative scaling method, and the quantitative scale (set quantitative scale) is 0.1 to 0.9, as shown in Table 1. This process requires participants or decision makers to assign a value between 0.1 and 0.9 to each indicator based on their cognition and judgment to reflect their relative importance in the whole. These values ​​will be used for subsequent analysis and decision-making. The importance of the indicators F1, F2, F3, F4, F5, and Fn is assigned using the expert scoring method, and the matrix is ​​assigned to obtain the evaluation indicator judgment matrix A.

[0056] F1 F2 F3 F4 ～ Fn F1 A11 A12 A13 A14 ～ A1n F2 A21 A22 A23 A24 ～ A2n F3 A31 A32 A33 A34 ～ A3n F4 A41 A42 A43 A44 ～ A4 ～ ～ ～ ～ ～ ～ ～ Fm Am1 Am2 Am3 Am4 ～ Amn

[0057] The evaluation index judgment matrix is ​​usually a square matrix, in which the elements represent the relative importance of each index, reflecting the expert's judgment on the relationship between each index. This matrix can be used in methods such as the analytic hierarchy process (AHP) to integrate the weights of various factors.

[0058] Table 1 Judgment matrix scale and meaning

[0059]

[0060]

[0061] In some implementations of this embodiment, the determination of the comprehensive weight value corresponding to each evaluation indicator in the evaluation index model may specifically include:

[0062] Based on the hierarchical analysis method, a first weight value of each evaluation index is determined.

[0063] Based on the entropy weight method, a second weight value of each evaluation indicator is determined.

[0064] For any of the evaluation indicators, a comprehensive weight value corresponding to the evaluation indicator is determined based on the first weight value of the evaluation indicator and the second weight value of the evaluation indicator.

[0065] Wherein, based on the hierarchical analysis method, the first weight value of each evaluation index is determined. Specifically, it includes:

[0066] The evaluation index judgment matrix is ​​normalized column by column to obtain a normalized judgment matrix.

[0067] Add the normalized judgment matrix row by row to get the sum vector.

[0068] After the sum vector is obtained, the sum vector is averaged to obtain the first weight of each evaluation index.

[0069] Specifically, the evaluation index judgment matrix A is normalized as follows:

[0070]

[0071] a ij is the relative importance value between the evaluation index labeled i and the evaluation index labeled j, To sum the normalized relative importance values, N is the order of the evaluation index judgment matrix.

[0072] Add the normalized evaluation index judgment matrix row by row to get the sum vector W i , as shown below:

[0073]

[0074] Then perform row averaging according to the following formula to obtain the first weight vector

[0075]

[0076] In the formula, N is the number of indicators.

[0077] In addition, this embodiment adopts the AHP entropy method to comprehensively assign weights for evaluation of the human-computer interaction experience of the car intelligent cockpit based on eye movement and EEG indicators. The higher the index value, the better the driver's experience during the interaction process.

[0078] Specifically, after obtaining the sum vector, the sum vector is row-averaged to obtain the first weight of each evaluation index, and the consistency check of the evaluation index judgment matrix is ​​further performed, specifically including:

[0079] According to the formula Determine the maximum characteristic root of the evaluation index judgment matrix, where γ max is the maximum characteristic root, N is the number of evaluation indicators, A is the evaluation indicator judgment matrix, W i is the sum vector, is the weight vector.

[0080] According to the formula Determine the consistency index CI of the evaluation index judgment matrix.

[0081] When the consistency index is less than the set consistency index, the evaluation index judgment matrix passes the consistency test.

[0082] The consistency index may be set according to the average random consistency index in Table 2.

[0083] Table 2 Average random consistency index CR value

[0084]

[0085] Among them, when the consistency index is less than the set consistency index, the evaluation index judgment matrix passes the consistency test, which can be specifically as follows:

[0086]

[0087] Among them, CR is the average random consistency index, and CI is the consistency index of the evaluation index judgment matrix.

[0088] The second weight of the evaluation index is determined based on the entropy weight method, which can be specifically as follows:

[0089] Each evaluation index value is dimensionally processed to obtain the dimensionless evaluation index.

[0090] According to the dimensionless evaluation index, the information entropy value of each evaluation index is determined.

[0091] According to the information entropy value of each evaluation index, the information utility value of each evaluation index is determined.

[0092] Based on the information utility value of each evaluation indicator, a second weight value of each evaluation indicator is determined.

[0093] The basic idea of ​​the entropy weight method is: if the value of an indicator changes more, the greater the degree of variation of the indicator value, the more information it provides, the smaller the information entropy value, the greater the weight, and vice versa.

[0094] The dimensionless processing specifically includes normalization processing and sum normalization processing.

[0095] Specifically, normalization is performed according to the following formula:

[0096]

[0097] where x ij is the original value of the i-th unit data of the j-th indicator, and defines the standardization, x jmin and x jmax are the minimum and maximum values ​​of the unit data of the evaluation index labeled j, respectively, ij *The data are normalized.

[0098] The summation and normalization are performed according to the following formula:

[0099]

[0100] Among them, m* is the number of unit data of the evaluation index labeled j, Y ij It is the evaluation index after dimensionless processing.

[0101] According to the dimensionless evaluation index, the information entropy value of each evaluation index is determined; the information entropy value of any evaluation index is determined according to the following formula:

[0102]

[0103] Among them, e j is the information entropy value of the evaluation index labeled j, Y ij is the dimensionless evaluation index labeled j.

[0104] According to the information entropy value of each evaluation index, the information utility value of each evaluation index is determined; the information utility value of any evaluation index is determined according to the following formula:

[0105] d j =1-e j .

[0106] Among them, d j is the information utility value of the evaluation index labeled j.

[0107] Based on the information utility value of each evaluation indicator, the second weight value of each evaluation indicator is determined; the second weight value of any evaluation indicator is determined according to the following formula:

[0108]

[0109] Among them, N is the number of evaluation indicators, w j is the second weight value of the evaluation index labeled j.

[0110] Wherein, for any evaluation indicator, based on the first weight value of the evaluation indicator and the second weight value of the evaluation indicator, the comprehensive weight value corresponding to the evaluation indicator is determined. In this embodiment, the comprehensive weight value of any evaluation indicator is determined according to the following formula:

[0111]

[0112] Among them, μ j is the comprehensive weight value of the evaluation index labeled j, N is the number of evaluation indicators, is the first weight value of the evaluation index labeled j, w j is the second weight value of the evaluation index labeled j.

[0113] When executing step 4, the evaluation index judgment matrix is ​​input into the evaluation index model to determine the human-computer interaction experience evaluation index of the automobile intelligent cockpit, which can be specifically as follows:

[0114] B=μ1A1+μ2A2+μ3A3+…+μ n A n .

[0115] Among them, A1~A n Indicates various evaluation indicators. μ1~μ n are the comprehensive weight values ​​corresponding to each evaluation index, and B is the human-computer interaction experience evaluation index.

[0116] In some implementations of this embodiment, before inputting the weights of the evaluation indicators and the scores of the evaluation indicators in the target human-computer interaction task into the evaluation index model to determine the human-computer interaction experience evaluation index of the automobile intelligent cockpit, the following is further included:

[0117] Obtain target human-computer interaction tasks for the automobile intelligent cockpit; the target human-computer interaction tasks specifically include: destination navigation, answering and making phone calls, music selection and switching, radio station selection and switching, in-vehicle APP interaction, air-conditioning temperature adjustment, instrument panel observation, voice wake-up or central control screen interaction.

[0118] The target human-computer interaction task is sent to the driving experiencer, and the scores of the driving experiencer on each of the evaluation indicators are collected.

[0119] Specifically, the present invention selects three mainstream smart cars as evaluation objects, recruits 15 users for a fee to experience driving, and requires the users to have a driving experience of more than 3 years; and invites 5 automotive human-computer interaction design experts to experience the three smart cars.

[0120] 20 users and expert group members wore eye trackers and completed 9 human-computer interaction tasks in static conditions in the cockpits of three smart cars: destination navigation, answering and making phone calls, music selection and switching, radio station selection and switching, in-car APP interaction, air-conditioning temperature adjustment, instrument panel observation, voice wake-up and central control screen interaction. They scored each complexity indicator, obtained score data, and collected relevant data of eye movement indicators.

[0121] Embodiment 2

[0122] This embodiment provides a human-computer interaction experience evaluation system for an automobile intelligent cockpit, including:

[0123] The quantitative scaling module is used to adopt the priority relationship quantitative scaling method to perform quantitative scaling processing on each evaluation indicator in the automobile intelligent cockpit, and determine the quantitative scaling of each evaluation indicator; the evaluation indicators include operation complexity indicators, visual pleasure indicators and interface indicators; the quantitative scaling is used to quantify the relative importance of the evaluation indicator among all evaluation indicators.

[0124] The assignment module is used to assign importance to each of the evaluation indicators based on the expert scoring method and construct an evaluation indicator judgment matrix; each element in the evaluation indicator judgment matrix is ​​the relative importance of the quantitative scale between two evaluation indicators.

[0125] The calculation module is used to determine the weight of each evaluation index in the evaluation index judgment matrix based on the entropy method and the hierarchical analysis method.

[0126] The evaluation index module is used to input the weight of each evaluation index and the score of each evaluation index in the target human-computer interaction task into the evaluation index model to determine the human-computer interaction experience evaluation index of the automobile intelligent cockpit.

[0127] In summary, the beneficial effects of the present invention are:

[0128] The present invention proposes an evaluation method for the human-computer interaction experience of an automobile intelligent cockpit based on eye movement and EEG indicators. Starting from the layout of the intelligent cockpit, the three primary indicators of human-computer interaction behavior complexity, pleasure, and trust, as well as the corresponding seven human-computer interaction complexity indicators and six eye movement indicators are used to construct an intelligent cockpit human-computer interaction experience evaluation index system, which overcomes the shortcoming of low accuracy in single parameter identification.

[0129] The automobile intelligent cockpit human-computer interaction experience evaluation method of the present invention is based on eye movement and EEG indicators. Starting from the intelligent cockpit central control human-computer interaction interface, the analytic hierarchy process and entropy weight method are used to determine the indicator weights, which is both subjective and reasonable, and objective and accurate.

[0130] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0131] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for evaluating the human-computer interaction experience of an automobile intelligent cockpit, characterized in that: include: Obtain human-computer interaction data when drivers and passengers use the car's intelligent cockpit to complete the target human-computer interaction task; The human-computer interaction data includes behavioral data, physiological data and psychological data; Based on the human-computer interaction data, a plurality of evaluation indicators are determined; the evaluation indicators include an operation complexity indicator, a visual pleasure indicator and an interface indicator; the operation complexity indicator is determined based on the behavior data, the visual pleasure indicator is determined based on the physiological data, and the interface indicator is determined based on the physiological data and the psychological data; According to each of the evaluation indicators, an evaluation indicator judgment matrix is ​​constructed; each element in the evaluation indicator judgment matrix is ​​the relative importance between two of the evaluation indicators; The evaluation index judgment matrix is ​​input into the evaluation index model to determine the human-computer interaction experience evaluation index of the automobile intelligent cockpit; the evaluation index model includes the comprehensive weight value corresponding to each evaluation index, and the comprehensive weight value of each evaluation index is pre-determined based on the hierarchical analysis method and the entropy weight method.

2. The method for evaluating the human-computer interaction experience of an intelligent vehicle cockpit according to claim 1, characterized in that: Before obtaining the human-computer interaction data when the driver and passenger use the car's intelligent cockpit to complete the target human-computer interaction task, it also includes: Obtain a target human-computer interaction task for the automobile intelligent cockpit.

3. The method for evaluating the human-computer interaction experience of an intelligent vehicle cockpit according to claim 2, characterized in that: The target human-computer interaction tasks include: destination navigation, answering and making phone calls, music selection and switching, radio station selection and switching, in-vehicle APP interaction, air conditioning temperature adjustment, instrument panel observation, voice wake-up and central control screen interaction.

4. The method for evaluating human-computer interaction experience of an intelligent vehicle cockpit according to claim 1, characterized in that: The behavior data includes the logic complexity, the number of operation actions, the management interface complexity and the input complexity of the target human-computer interaction task.

5. The method for evaluating human-computer interaction experience of an intelligent vehicle cockpit according to claim 1, characterized in that: The physiological data include the number of blinks, blink frequency, blink amplitude, fixation time, number of fixations and average pupil diameter.

6. The method for evaluating human-computer interaction experience of an intelligent vehicle cockpit according to claim 1, characterized in that: The psychological data include pleasure of the density of the central control screen interface, trust in the density of the central control screen interface, pleasure of the central control screen interface layout, pleasure of the interface information density, dependence on the interface information density, interface color emotion, trust in the interface layout, interface layout interaction effort and interface cognitive evaluation.

7. The method for evaluating human-computer interaction experience of an intelligent vehicle cockpit according to claim 1, characterized in that: Determination of the comprehensive weight value corresponding to each evaluation indicator in the evaluation index model specifically includes: Based on the hierarchical analysis method, determining a first weight value of each evaluation indicator; Determine a second weight value of each evaluation indicator based on an entropy weight method; For any of the evaluation indicators, a comprehensive weight value corresponding to the evaluation indicator is determined based on the first weight value of the evaluation indicator and the second weight value of the evaluation indicator.

8. The method for evaluating the human-computer interaction experience of an intelligent vehicle cockpit according to claim 7, characterized in that: Determining the second weight value of each evaluation indicator based on the entropy weight method specifically includes: Perform dimensionless processing on each evaluation index value to obtain the dimensionless evaluation index; Determining the information entropy value of each evaluation index according to the evaluation index after dimensionless processing; According to the information entropy value of each evaluation index, the information utility value of each evaluation index is determined; Based on the information utility value of each evaluation indicator, a second weight value of each evaluation indicator is determined.

9. The method for evaluating human-computer interaction experience of an intelligent vehicle cockpit according to claim 1, characterized in that: The evaluation index model is: B=μ1A1+μ2A2+μ3A3+…+μ n A n ; Among them, A1~A n Represents various evaluation indicators; μ1~μ n are the comprehensive weight values ​​corresponding to each evaluation index, and B is the human-computer interaction experience evaluation index.

10. A human-computer interaction experience evaluation system for an automobile intelligent cockpit, characterized in that: include: A data acquisition module is used to acquire human-computer interaction data when a driver uses the car's intelligent cockpit to complete a target human-computer interaction task; The human-computer interaction data includes behavioral data, physiological data and psychological data; An evaluation index module, used to determine multiple evaluation indexes based on the human-computer interaction data; the evaluation indexes include an operation complexity index, a visual pleasure index and an interface index; the operation complexity index is determined based on the behavior data, the visual pleasure index is determined based on the physiological data, and the interface index is determined based on the physiological data and the psychological data; A matrix construction module is used to construct an evaluation index judgment matrix according to each of the evaluation indexes; each element in the evaluation index judgment matrix is ​​the relative importance between two of the evaluation indexes; An evaluation index module, used to input the evaluation index judgment matrix into an evaluation index model to determine the human-computer interaction experience evaluation index of the automobile intelligent cockpit; The evaluation index model includes comprehensive weight values ​​corresponding to the evaluation indicators, and the comprehensive weight values ​​of the evaluation indicators are pre-determined based on the hierarchical analysis method and the entropy weight method.

Images