Vehicle subjective evaluation method, device, equipment and medium

Abstract

The invention discloses a vehicle subjective evaluation method, device, equipment and medium, and the method comprises the steps: obtaining electroencephalogram data of an evaluation person for a certain evaluation index of a vehicle, the electroencephalogram data comprising a plurality of effective channels corresponding to the evaluation index and electroencephalogram features corresponding to each effective channel; the electroencephalogram data of the evaluation indexes are substituted into a pre-trained subjective evaluation model, the total score of the evaluation personnel for the evaluation indexes is obtained, and the subjective evaluation model comprises the corresponding relation between electroencephalogram characteristics corresponding to different effective channels and the score and the weights of the different effective channels. According to the method, the physiological electroencephalogram signals of the evaluation personnel are directly read, so that the scoring data of the evaluation personnel are objectively reflected.

Description

Technical Field

[0001] The present invention relates to the field of vehicle testing technology, and in particular to a vehicle subjective evaluation method, device, equipment and medium. Background Art

[0002] In the automotive industry, the quality and performance of a vehicle is evaluated and improved through the subjective evaluation results of professional drivers. Generally, domestic and foreign OEMs develop vehicles through the logical iterative process of "subjective evaluation-->objective testing, simulation analysis-->data analysis-->technical improvement-->subjective evaluation", so the role of subjective evaluation of vehicle performance is very important.

[0003] The subjective evaluation of vehicle performance is mainly divided into static evaluation and dynamic evaluation. Static evaluation mainly includes: appearance quality, interior quality, space and field of view, seat performance, operational convenience, air conditioning performance, electronic and electrical performance, safety performance, and maintenance convenience. It mainly requires seeing with eyes, touching with hands, sitting with buttocks, smelling with noses, and listening with ears, which requires a serious and careful attitude. Dynamic evaluation mainly includes: power performance, driving feel, NVH performance, handling stability, ride comfort, steering performance, and braking performance, which requires rich driving experience and certain professional evaluation experience and automotive expertise.

[0004] However, subjective evaluation is affected by individual differences of the subjects, such as age, preference, gender, region, etc. Different people may give very different results. Therefore, it is very important to describe the driving experience from a relatively objective perspective and make subjective evaluation objective. Summary of the invention

[0005] The embodiments of the present application provide a vehicle subjective evaluation method, device, equipment and medium. The method directly reads the physiological EEG signals of the evaluator to objectively reflect the evaluator's scoring data, thereby improving the problem of large differences in subjective evaluation and low reliability caused by large individual differences.

[0006] In a first aspect, the present invention provides the following technical solution through an embodiment of the present invention:

[0007] A vehicle subjective evaluation method comprises: obtaining EEG data of an evaluator for one of the evaluation indicators of a vehicle, wherein the EEG data comprises a plurality of valid channels corresponding to the evaluation indicator, and EEG features corresponding to each valid channel; bringing the EEG data of the evaluation indicator into a pre-trained subjective evaluation model to obtain a total score of the evaluator for the evaluation indicator, wherein the subjective evaluation model comprises the correspondence between EEG features corresponding to different valid channels and scores, and weights of different valid channels.

[0008] Preferably, the training of the subjective evaluation model includes: obtaining a training data set, the training data set including: multiple evaluation indicators, multiple valid channels corresponding to each single evaluation indicator, EEG features with different scores corresponding to each single valid channel, the score corresponding to each EEG feature, and the weights of different valid channels in each evaluation indicator; training the initial network model based on the training data set to obtain a subjective evaluation model.

[0009] Preferably, obtaining multiple valid channels corresponding to each single evaluation index and EEG features of different scores corresponding to each single valid channel includes: selecting a set of standard sample vehicles, the set of standard sample vehicles including standard sample vehicles with scores from one to ten corresponding to each evaluation index in multiple evaluation indexes; collecting EEG data of all evaluation indexes of each standard sample vehicle in the set of standard sample vehicles from professional evaluators to obtain EEG data of each evaluation index of each standard sample vehicle with each score; determining multiple valid channels of the evaluation index based on multiple EEG data of one evaluation index of standard sample vehicles with different scores from professional evaluators; and determining EEG features of different scores corresponding to each single valid channel for each evaluation index of the standard sample vehicle with each score based on the EEG data, multiple valid channels of the evaluation index and EEG features corresponding to each valid channel.

[0010] Preferably, obtaining the score corresponding to each EEG feature includes: collecting EEG data of all evaluation indicators of each standard sample car in the standard sample car set from N professional evaluators to obtain N EEG data under each evaluation indicator of each score standard sample car; obtaining the average EEG feature of the effective channel based on the N EEG features under one effective channel in the N EEG data; taking the average EEG feature as a reference, selecting the upper and lower preset fluctuation ranges of the average EEG feature as the EEG feature range of the effective channel; judging the EEG feature range of each EEG feature, and determining the scores corresponding to each EEG feature under multiple effective channels based on the EEG feature range and the EEG features of different scores corresponding to each single effective channel.

[0011] Preferably, the method of determining multiple valid channels of the evaluation indicator based on multiple EEG data of one of the evaluation indicators of standard sample vehicles with different scores by professional evaluators comprises: determining, from each channel of the multiple EEG data, an effective channel whose EEG characteristics show a step-by-step change with the change of the score of the standard sample vehicle, to obtain multiple valid channels of the evaluation indicator.

[0012] Preferably, obtaining the weights of different valid channels in each evaluation index includes: for each evaluation index, determining the weights of different valid channels in each evaluation index according to the sensitivity of different valid channels to the evaluation index.

[0013] Preferably, after obtaining the EEG data of one of the evaluation indicators of the vehicle from the evaluator, the method further includes: preprocessing the EEG data of the evaluation indicator to obtain preprocessed EEG data.

[0014] In a second aspect, the present invention provides the following technical solution through an embodiment of the present invention:

[0015] A vehicle subjective evaluation device, comprising:

[0016] An acquisition module, used to acquire EEG data of an evaluator for one of the evaluation indicators of the vehicle, wherein the EEG data includes a plurality of valid channels corresponding to the evaluation indicator and an EEG feature corresponding to each valid channel;

[0017] The evaluation module is used to bring the EEG data of the evaluation index into a pre-trained subjective evaluation model to obtain the total score of the evaluator for the evaluation index, wherein the subjective evaluation model includes the correspondence between the EEG features and scores corresponding to different effective channels, and the weights of different effective channels.

[0018] In a third aspect, the present invention provides the following technical solution through an embodiment of the present invention:

[0019] An electronic device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods described in the first aspect are implemented.

[0020] In a fourth aspect, the present invention provides the following technical solution through an embodiment of the present invention:

[0021] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0022] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0023] The vehicle subjective evaluation method provided by the embodiment of the present invention obtains the EEG data of the evaluator for a certain evaluation index of the vehicle, brings the EEG data into the subjective evaluation model, directly reads the physiological EEG signals of the evaluator through the brain-computer interface, and outputs the total score for the evaluation index through the characteristic EEG extracted by the brain-computer interface, thereby objectively reflecting the true feelings of the evaluator. This method can avoid the problem of large differences in the evaluation method due to the influence of individual differences of the subjects, and can describe the driving experience of the driver from a relatively objective perspective. The subjective evaluators of the vehicle do not need to undergo long-term professional training, so that every person can be an excellent evaluator, saving costs and improving efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 Flow chart of a subjective vehicle evaluation method according to an embodiment of the present invention;

[0026] Figure 2 Schematic diagram of the pretreatment process in an embodiment of the present invention;

[0027] Figure 3 Schematic diagram of the EEG characteristic fluctuation range in an embodiment of the present invention;

[0028] Figure 4 Schematic diagram of the results of the subjective evaluation process in an embodiment of the present invention;

[0029] Figure 5 It is a structural schematic diagram of a vehicle subjective evaluation device in an embodiment of the present invention;

[0030] Figure 6 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The embodiments of the present application provide a vehicle subjective evaluation method, device, equipment and medium. The method directly reads the physiological EEG signals of the evaluator to objectively reflect the evaluator's scoring data, thereby improving the problem of large differences in subjective evaluation and low reliability caused by large individual differences.

[0032] The technical solution of the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0033] A vehicle subjective evaluation method comprises: obtaining EEG data of an evaluator for one of the evaluation indicators of a vehicle, wherein the EEG data comprises a plurality of valid channels corresponding to the evaluation indicator, and EEG features corresponding to each valid channel; bringing the EEG data of the evaluation indicator into a pre-trained subjective evaluation model to obtain a total score of the evaluator for the evaluation indicator, wherein the subjective evaluation model comprises the correspondence between EEG features corresponding to different valid channels and scores, and weights of different valid channels.

[0034] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0035] In a first aspect, an embodiment of the present invention provides a vehicle subjective evaluation method, specifically, Figure 1 As shown, the method includes the following steps S101 to S102:

[0036] Step S101, obtaining EEG data of an evaluator for one of the evaluation indicators of the vehicle, wherein the EEG data includes a plurality of valid channels corresponding to the evaluation indicator and EEG features corresponding to each valid channel.

[0037] It should be noted that the evaluator here refers to any person who has or does not have professional judgment ability. Evaluation indicators can be divided into static evaluation indicators and dynamic evaluation indicators. Static evaluation indicators mainly include: appearance quality, interior quality, space and vision, seat performance, operational convenience, air conditioning performance, electronic and electrical performance, safety performance, and maintenance convenience. Dynamic evaluation indicators mainly include: power performance, driving feel, NVH performance, handling stability, ride comfort, steering performance, braking performance, etc.

[0038] In the specific implementation process, the EEG data of the evaluator is obtained through the EEG acquisition device. For example, taking the comfort index as an example, the evaluator is asked to wear an EEG cap to experience the vehicle and record the EEG data of the comfort index.

[0039] In order to obtain more accurate EEG data, after obtaining the EEG data of one of the evaluation indicators of the vehicle by the evaluator, the method may further include: preprocessing the EEG data of the evaluation indicator to obtain the preprocessed EEG data.

[0040] In a specific embodiment, the collected EEG data is preprocessed. MATLAB can be selected as the data analysis platform, and the MATLAB extension toolkit EEGLAB can be used as a preprocessing tool, which also includes EEGLAB plug-ins REST, ICLabel, Viewprops, etc. The specific preprocessing steps are as follows: According to the EEG data, electrode channel data is selected.

[0041] Specifically, the distribution of the EEG cap electrode positions used in this application complies with the international 10-20 standard (standard electrode placement method). The method of naming the poles refers to the partitioning of the brain structure. Different letters represent different partitions, F represents the forehead, FP represents the frontal lobe, T represents the temporal lobe, O represents the occipital lobe, P represents the parietal lobe, C represents the central part, and Z represents the left and right brain centers. Based on the partitioning of brain functions, considering that the driver is mainly mentally active, attentive, fatigue and related operations in the driving state, the channels of the frontal lobe and part of the parietal lobe are selected as the objects of analysis, specifically including FP1, FPZ, FP2, F1, F2, F3, F4, F5, F6, F7, F8, FZ, FC1, FC2, FC3, FC4, FC5, FC6, FT7, FT8, AF3, AF4, AF7, AF8, a total of 25 channels.

[0042] Next, there is a built-in online reference electrode in the EEG recording system. In order to avoid the reference electrode affecting the data of other electrodes, the reference electrode is selected to be far away from the area of ​​interest. This application adopts the common bilateral mastoid averaging method and selects the protruding position on the temporal bone behind the ear to place the two reference electrodes M1 and M2.

[0043] Since EEG equipment is a high-precision device with high sensitivity, if it is not placed correctly during the measurement process, inaccurate EEG signals will be collected. This kind of lead is called a bad lead signal. Furthermore, in order to improve the convenience of the test while avoiding the impact of bad leads on the data, the average interpolation method is used to repair the bad leads of the EEG data and remove the DC offset.

[0044] Specifically, if the signal of the conductor is not used in the analysis process, the data of the conductor can be directly eliminated. If the data of the conductor is needed in the analysis process, the interpolation method can be used to repair the bad conductor.

[0045] Furthermore, since there is interference from power frequency and some high and low frequency noises during the EEG data collection process, and the tissues of the human body will cause signal attenuation, the collected original signal is not pure. In order to obtain a pure signal and remove the interference signal, after interpolation and removal of DC offset, it is also possible to filter the EEG data. For example, a bandpass filter of 0.5 to 40 Hz is selected to remove most artifacts such as linear drift, electrocardiogram, and electromyography.

[0046] Furthermore, the EEG signal itself is a continuous signal, and for the convenience of analysis, the key time points of the task state will be marked. In order to analyze the EEG signals induced by events, the signals for a period of time before and after the marking point will be extracted, so that the continuous EEG signal is divided into segments. However, due to baseline drift, the segmented data has different starting values, so the baseline needs to be corrected. For example, the present application segments the data segments 500ms before and 1000ms after the marking point, and eliminates signals exceeding ±80uV.

[0047] For the signals collected by the EEG cap, the signals collected by each channel are the superposition of the signals around it, which will show a high correlation, so these components need to be separated. The present invention adopts independent component analysis to remove the identified artifacts and then perform a 2-30Hz post-bandpass filter to select the β band of interest for analysis.

[0048] Therefore, if Figure 2 As shown, the preprocessing process proposed in the present application may include: selecting electrode channel data, re-reference setting, interpolation to remove DC offset, filtering, data segmentation and baseline correction, and independent component analysis (ICA).

[0049] Step S102, bringing the EEG data of the evaluation index into a pre-trained subjective evaluation model to obtain the total score of the evaluator for the evaluation index, wherein the subjective evaluation model includes the correspondence between the EEG features and scores corresponding to different effective channels, and the weights of different effective channels.

[0050] In a specific embodiment, the training of the subjective evaluation model includes: obtaining a training data set, the training data set including: multiple evaluation indicators, multiple valid channels corresponding to each single evaluation indicator, EEG features of different scores corresponding to each single valid channel, the score corresponding to each EEG feature, and the weights of different valid channels in each evaluation indicator; training the initial network model based on the training data set to obtain a subjective evaluation model.

[0051] In one example, multiple valid channels corresponding to each single evaluation index and EEG features of different scores corresponding to each single valid channel are obtained, including: selecting a set of standard sample vehicles, the standard sample vehicle set including standard sample vehicles with scores of one to ten corresponding to each evaluation index in multiple evaluation indexes; collecting EEG data of all evaluation indexes of each standard sample vehicle in the set of standard sample vehicles from professional evaluators to obtain EEG data of each evaluation index of each standard sample vehicle with each score; determining multiple valid channels of the evaluation index based on multiple EEG data of one evaluation index of standard sample vehicles with different scores from professional evaluators; and determining EEG features of different scores corresponding to each single valid channel for each evaluation index of the standard sample vehicle with each score based on the EEG data, multiple valid channels of the evaluation index and EEG features corresponding to each valid channel.

[0052] Specifically, prepare several standard sample vehicles, which have been scored by professional evaluators. Match the scores on the evaluation indicators with the sample vehicles one by one, and carry out subsequent data collection work.

[0053] The subjective evaluation of vehicles is based on a ten-point scale from extremely poor to perfect, as shown in Table 1 below:

[0054] Table 1

[0055]

[0056] For example, in terms of vehicle comfort, multiple standard prototype vehicles with comfort scores ranging from 1 to 10 points were selected; in terms of vehicle steering performance, multiple standard prototype vehicles with steering performance scores ranging from 1 to 10 points were selected; the same applies to other evaluation indicators.

[0057] Of course, as other optional embodiments, a five-point system or other scoring forms may also be used, which is not limited in this application.

[0058] In a specific embodiment, based on multiple EEG data of one of the evaluation indicators of standard sample cars with different scores collected by professional evaluators, multiple valid channels of the evaluation indicator are determined, which can include: based on multiple EEG data of one of the evaluation indicators of standard sample cars with different scores collected by professional evaluators, from each channel of the multiple EEG data, an effective channel whose EEG characteristics show a step-by-step change with the change of the score of the standard sample car is determined, to obtain multiple valid channels of the evaluation indicator.

[0059] Specifically, professionals conduct evaluations on standard prototypes with different evaluation scores, and collect EEG data of all channels through EEG caps. Since the evaluation scores of the standard prototypes are step-by-step increasing or step-by-step decreasing, the corresponding effective channels will have step-by-step intensity changes, or positively correlated step enhancements, or negatively correlated step weakening. By analyzing the changing patterns of EEG signals on each channel, those with regular changes (increasing or decreasing) are determined as effective channels, and other channel data are not used as effective data for this indicator. For example: based on multiple EEG data of comfort evaluation indicators of standard prototypes with scores ranging from one to ten, the multiple EEG data here are EEG data of comfort evaluation indicators with different scores, and the channels related to the comfort evaluation indicators are S{s1, s2, ..., sn}.

[0060] For different evaluation indicators, the same method as above can be used to obtain multiple EEG data of all evaluation indicators of standard sample vehicles with different scores, and determine multiple effective channels for each evaluation indicator.

[0061] Next, for each evaluation index of each standard sample car, based on the EEG data and multiple valid channels of the evaluation index, the valid channel corresponding to the EEG data can be determined, and then the EEG feature corresponding to each valid channel in the multiple valid channels can be combined to determine the EEG feature of each single valid channel at the score. Furthermore, for each evaluation index of standard sample cars with different scores, the EEG features of different scores corresponding to each single valid channel are determined.

[0062] In a specific embodiment, obtaining the score corresponding to each EEG feature may include: collecting EEG data of all evaluation indicators of each standard sample car in a set of standard sample cars from N professional evaluators to obtain N EEG data under each evaluation indicator of each score standard sample car; for each valid channel, according to the N EEG features under one valid channel in the N EEG data, obtaining the average EEG feature of the valid channel; taking the average EEG feature as a reference, selecting the upper and lower preset fluctuation ranges of the average EEG feature as the EEG feature range of the valid channel; judging the EEG feature range of each EEG feature, and determining the scores corresponding to each EEG feature under multiple valid channels according to the EEG feature range and the EEG features of different scores corresponding to each single valid channel.

[0063] Specifically, multiple professional evaluators put on EEG caps on standard prototypes to conduct subjective evaluation and score and collect EEG data for each evaluation indicator. Taking the comfort index as an example, professional evaluators put on EEG caps to experience the standard prototypes of each score in turn, and record the EEG data corresponding to each score of the comfort index. N professional evaluators obtain N EEG data for each evaluation indicator of each score standard prototype.

[0064] For example, N is greater than or equal to 10. The 10 EEG data are averaged to obtain the average EEG characteristics of each evaluation index of different score standard sample vehicles.

[0065] According to the EEG feature interval and the EEG features of different scores corresponding to each single valid channel, the scores corresponding to each EEG feature under multiple valid channels are determined, which may include: if it is judged that the EEG feature meets the EEG feature of a certain score, and the fluctuation range of the EEG feature is within the EEG feature interval, then the score is determined.

[0066] Specifically, data from multiple evaluators and standard prototypes with values ​​ranging from one point to ten points were collected for each channel. The EEG features of N evaluators collected from each standard prototype were fitted, and the average EEG feature was used as a benchmark. According to the fluctuation situation, an appropriate fluctuation ratio was selected as the upper and lower fluctuation range, which served as the corresponding EEG evaluation index for this segment and band. Similarly, the EEG feature range from one point to ten points for each valid channel was determined.

[0067] like Figure 3 As shown in the figure, the average EEG characteristics and EEG characteristic intervals are shown. The horizontal axis is the period s, and the vertical axis is the amplitude. Lines a and b represent the EEG characteristics of the two evaluators respectively.

[0068] For example, the EEG characteristic interval may be 5% above or below the average EEG characteristic. Of course, in other embodiments, the EEG characteristic interval may also be 4%, 6%, etc. above or below the average EEG characteristic.

[0069] In a specific embodiment, obtaining the weights of different valid channels in each evaluation index may include: for each evaluation index, determining the weights of different valid channels in each evaluation index according to the sensitivity of different valid channels to the evaluation index. The sensitivity may be expressed as the size of the range of intensity change within a unit time.

[0070] In each valid channel, the data will show different sensitivities to the evaluation index. For example, as the score of s1 channel increases, the intensity increases by 5 each time, while as the score of s2 channel increases, the intensity increases by 3. This indicates that s1 channel is more sensitive to the index and can better reflect the actual situation of the index, so it has a heavier weight. According to the speed of change of each channel in response to the increase of score, the sensitivity of each channel is set to A{a1, a2, ..., an}, and the weight of each channel is W{w1, w2, ..., wn}. The relationship between weight and sensitivity is as follows:

[0071]

[0072] The initial network model is trained based on the training data set to obtain a subjective evaluation model, which may include: matching the EEG features and scores corresponding to each valid channel to obtain the scores B{b1, b2, ..., bn} of all valid channels, combining the scores of each valid channel with the weights of the valid channels, and comprehensively obtaining the final total score C, completing the correspondence between the subjective score and the objective score obtained using the EEG data. The model is as follows:

[0073]

[0074] In this application, by performing the above steps for each evaluation index, a training data set is formed, which includes the effective channels corresponding to each evaluation index, the weights of each effective channel, the EEG feature maps with different scores corresponding to each effective channel, and the scores corresponding to each EEG feature. As the data increases, the data set is continuously improved, and the evaluation model will become more accurate.

[0075] like Figure 4 As shown, this application preprocesses the collected EEG data, and then continues to perform data analysis to find the EEG features corresponding to the score of the indicator to form an objective evaluation indicator. The collected EEG data is full-channel, but there are only a few channels with features related to the indicator. Therefore, it is necessary to first determine the relevant channels associated with the indicator, and then determine the channel weight based on the sensitivity of the channel to the indicator. Finally, based on the effective channel data corresponding to each score, determine the EEG feature indicator corresponding to each score of the indicator.

[0076] Based on the EEG data, multiple valid channels of evaluation indicators are determined. According to the EEG features corresponding to the multiple valid channels and the correspondence between the scores and the EEG features, the score of each valid channel is determined. The score of each valid channel is combined with the weight corresponding to the valid channel to obtain the total score.

[0077] During the actual evaluation process, evaluators wear EEG caps to conduct evaluation activities on the formal test prototype vehicle. Corresponding scores can be obtained based on the EEG data, thus making the subjective scores objectivist.

[0078] In summary, a subjective vehicle evaluation method provided by an embodiment of the present invention directly reads the physiological EEG signals of the evaluator to objectively reflect the scoring data of the evaluator, and applies the brain-computer interface to the field of subjective vehicle evaluation. This effectively solves the problem of poor evaluation accuracy due to individual differences when conducting subjective vehicle evaluation, and improves the problem of large differences and low reliability in subjective evaluations caused by large individual differences. This method can make every person an excellent evaluator, save costs and improve efficiency.

[0079] In the second aspect, based on the same inventive concept, this embodiment provides a vehicle subjective evaluation device, such as Figure 5 As shown, including:

[0080] An acquisition module 401 is used to acquire EEG data of an evaluator for one of the evaluation indicators of the vehicle, wherein the EEG data includes a plurality of valid channels corresponding to the evaluation indicator and an EEG feature corresponding to each valid channel;

[0081] The evaluation module 402 is used to bring the EEG data of the evaluation index into a pre-trained subjective evaluation model to obtain the total score of the evaluator for the evaluation index, wherein the subjective evaluation model includes the correspondence between the EEG features and scores corresponding to different effective channels, and the weights of different effective channels.

[0082] As an optional embodiment, the training of the subjective evaluation model includes: obtaining a training data set, the training data set including: multiple evaluation indicators, multiple valid channels corresponding to each single evaluation indicator, EEG features with different scores corresponding to each single valid channel, the score corresponding to each EEG feature, and the weights of different valid channels in each evaluation indicator; training the initial network model based on the training data set to obtain a subjective evaluation model.

[0083] As an optional embodiment, the obtaining of multiple valid channels corresponding to each single evaluation index and EEG features of different scores corresponding to each single valid channel includes: selecting a set of standard sample vehicles, the standard sample vehicle set including standard sample vehicles with scores of one to ten corresponding to each evaluation index in multiple evaluation indexes; collecting EEG data of all evaluation indexes of each standard sample vehicle in the set of standard sample vehicles from professional evaluators to obtain EEG data of each evaluation index of each standard sample vehicle with each score; determining multiple valid channels of the evaluation index based on multiple EEG data of one evaluation index of standard sample vehicles with different scores from professional evaluators; and determining EEG features of different scores corresponding to each single valid channel for each evaluation index of the standard sample vehicle with each score based on the EEG data, multiple valid channels of the evaluation index and EEG features corresponding to each valid channel.

[0084] As an optional embodiment, the obtaining of the score corresponding to each EEG feature includes: collecting EEG data of all evaluation indicators of each standard sample car in a set of standard sample cars from N professional evaluators to obtain N EEG data under each evaluation indicator of each score standard sample car; obtaining the average EEG feature of the effective channel based on the N EEG features under one effective channel in the N EEG data; taking the average EEG feature as a reference, selecting the upper and lower preset fluctuation ranges of the average EEG feature as the EEG feature range of the effective channel; determining the EEG feature range of each EEG feature, and determining the scores corresponding to each EEG feature under multiple effective channels based on the EEG feature range and the EEG features of different scores corresponding to each single effective channel.

[0085] As an optional embodiment, the method of determining multiple valid channels of an evaluation indicator based on multiple EEG data of one evaluation indicator of standard sample vehicles with different scores by professional evaluators includes: determining, from each channel of the multiple EEG data, an effective channel whose EEG characteristics show a step-by-step change with the change of the score of the standard sample vehicle, to obtain multiple valid channels of the evaluation indicator.

[0086] As an optional embodiment, obtaining the weights of different valid channels in each evaluation index includes: for each evaluation index, determining the weights of different valid channels in each evaluation index according to the sensitivity of different valid channels to the evaluation index.

[0087] As an optional embodiment, the device further includes: a preprocessing module, which is used to preprocess the EEG data of the evaluation index to obtain preprocessed EEG data.

[0088] The above modules can be implemented by software codes, in which case, the above modules can be stored in the memory of the control device. The above modules can also be implemented by hardware such as integrated circuit chips.

[0089] The implementation principle and technical effects of a vehicle subjective evaluation device provided in an embodiment of the present invention are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0090] In a third aspect, based on the same inventive concept, this embodiment provides an electronic device 500, such as Figure 6 As shown, it includes: a memory 501, a processor 502 and a computer program 503 stored in the memory and executable on the processor. When the processor 502 executes the program, the steps of the vehicle subjective evaluation method described in the first aspect are implemented.

[0091] Since the electronic device introduced in this embodiment is an electronic device used to implement the vehicle subjective evaluation method in the embodiment of this application, based on the vehicle subjective evaluation method introduced in the embodiment of this application, a person skilled in the art can understand the specific implementation of the electronic device in this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as a person skilled in the art implements the electronic device used in the vehicle subjective evaluation method in the embodiment of this application, it belongs to the scope of protection of this application.

[0092] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A module that specifies functions in one or more boxes.

[0094] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction module, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0096] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0097] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A subjective vehicle evaluation method, characterized in that: include: Obtaining EEG data of an evaluator for one of the evaluation indicators of the vehicle, wherein the EEG data includes a plurality of valid channels corresponding to the evaluation indicator and an EEG feature corresponding to each valid channel; The EEG data of the evaluation index is brought into a pre-trained subjective evaluation model to obtain the total score of the evaluator for the evaluation index, wherein the subjective evaluation model includes the correspondence between the EEG features and scores corresponding to different effective channels, and the weights of different effective channels.

2. The method according to claim 1, characterized in that The training of the subjective evaluation model includes: Acquire a training data set, the training data set comprising: a plurality of evaluation indicators, a plurality of valid channels corresponding to each single evaluation indicator, EEG features of different scores corresponding to each single valid channel, a score corresponding to each EEG feature, and weights of different valid channels in each evaluation indicator; The initial network model is trained based on the training data set to obtain a subjective evaluation model.

3. The method according to claim 2, characterized in that Obtain multiple valid channels corresponding to each single evaluation index and EEG features with different scores corresponding to each single valid channel, including: Selecting a set of standard sample vehicles, wherein the set of standard sample vehicles includes standard sample vehicles with a value of one to ten corresponding to each evaluation indicator in a plurality of evaluation indicators; Collecting the EEG data of all evaluation indicators of each standard sample car in the set of standard sample cars by professional evaluators, and obtaining the EEG data of each evaluation indicator of each score standard sample car; According to multiple EEG data of one evaluation index of different standard sample vehicles obtained by professional evaluators, multiple valid channels of the evaluation index are determined; For each evaluation index of each score standard sample vehicle, based on the EEG data, multiple valid channels of the evaluation index and the EEG features corresponding to each valid channel, the EEG features of different scores corresponding to each single valid channel are determined.

4. The method according to claim 3, characterized in that Get the score corresponding to each EEG feature, including: Collecting EEG data of N professional evaluators for all evaluation indicators of each standard sample car in the standard sample car set, and obtaining N EEG data under each evaluation indicator of each score standard sample car; According to the N EEG features of one effective channel in the N EEG data, an average EEG feature of the effective channel is obtained; Taking the average EEG feature as a reference, selecting the upper and lower preset fluctuation ranges of the average EEG feature as the EEG feature range of the effective channel; The EEG feature interval of each EEG feature is determined, and the scores corresponding to each EEG feature under multiple valid channels are determined according to the EEG feature interval and the EEG features with different scores corresponding to each single valid channel.

5. The method according to claim 3, characterized in that The method of determining multiple effective channels of one evaluation index based on multiple EEG data of one evaluation index of different score standard sample vehicles by professional evaluators includes: According to multiple EEG data of one of the evaluation indicators of standard sample cars with different scores by professional evaluators, effective channels whose EEG characteristics show a step-by-step change with the change of the score of the standard sample car are determined from each channel of the multiple EEG data to obtain multiple effective channels of the evaluation indicator.

6. The method according to claim 2, characterized in that Get the weights of different valid channels in each evaluation indicator, including: For each evaluation index, the weights of different effective channels in each evaluation index are determined according to the sensitivity of different effective channels to the evaluation index.

7. The method according to claim 1, characterized in that After obtaining the electroencephalogram data of the evaluator for one of the evaluation indicators of the vehicle, the method further includes: The EEG data of the evaluation index is preprocessed to obtain preprocessed EEG data.

8. A vehicle subjective evaluation device, characterized in that: include: An acquisition module, used to acquire EEG data of an evaluator for one of the evaluation indicators of the vehicle, wherein the EEG data includes a plurality of valid channels corresponding to the evaluation indicator and an EEG feature corresponding to each valid channel; The evaluation module is used to bring the EEG data of the evaluation index into a pre-trained subjective evaluation model to obtain the total score of the evaluator for the evaluation index, wherein the subjective evaluation model includes the correspondence between the EEG features and scores corresponding to different effective channels, and the weights of different effective channels.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images