A vehicle subjective evaluation method, device, equipment and medium

Abstract

The application discloses a vehicle subjective evaluation method, device, equipment and medium, and the method comprises the following steps: acquiring electroencephalogram data of an evaluator for a certain evaluation index of a vehicle, wherein the electroencephalogram data comprises a plurality of effective channels corresponding to the evaluation index and electroencephalogram features corresponding to each effective channel; and the electroencephalogram data of the evaluation index is input into a pre-trained subjective evaluation model to obtain a total score of the evaluator for the evaluation index, wherein the subjective evaluation model comprises a corresponding relationship between electroencephalogram features corresponding to different effective channels and scores, and weights of different effective channels. The method directly reads physiological electroencephalogram signals of the evaluator to objectively reflect the score data of the evaluator.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle testing, in particular to a vehicle subjective evaluation method, device, equipment and medium. BACKGROUND

[0002] In the automobile industry, the evaluation of the quality and performance of the whole vehicle is determined and improved through the subjective evaluation results of professional drivers. Generally, domestic and foreign automobile manufacturers develop and develop the whole vehicle through the iterative process of "subjective evaluation --> objective test, simulation analysis --> data analysis --> technical improvement --> subjective evaluation", so the role of subjective evaluation of the whole vehicle performance is very important.

[0003] The subjective evaluation of the whole vehicle performance mainly includes static evaluation and dynamic evaluation. The static evaluation mainly includes appearance quality, interior quality, space and field of view, seat performance, operation convenience, air conditioning performance, electronic and electrical performance, safety performance, and maintenance convenience, which mainly uses eyes to see, hands to touch, buttocks to sit, nose to smell, and ears to listen, and requires careful attitude. Dynamic evaluation mainly includes power performance, driving feeling, NVH performance, steering stability, ride comfort, steering performance, and braking performance, which requires rich driving experience and certain professional evaluation experience and automobile professional knowledge.

[0004] However, the subjective evaluation method is affected by individual differences such as age, preference, gender, and region, and different personnel may give different results. Therefore, it is very important to describe the driving experience of the driver from a relatively objective point of view and make the subjective evaluation objective. SUMMARY

[0005] The embodiment of the present application provides a vehicle subjective evaluation method, device, equipment and medium, which directly reads the physiological brain electrical signals of the evaluator to objectively reflect the evaluation data of the evaluator, and improves the problem of large subjective evaluation difference and low reliability caused by large individual difference.

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

[0007] A vehicle subjective evaluation method comprises: obtaining brain electrical data of an evaluator for one evaluation index of a vehicle, wherein the brain electrical data comprises a plurality of effective channels corresponding to the evaluation index, and brain electrical characteristics corresponding to each effective channel; and bringing the brain electrical data of the evaluation index into a pre-trained subjective evaluation model to obtain a total score of the evaluation index of the evaluator, wherein the subjective evaluation model comprises a corresponding relationship between brain electrical characteristics corresponding to different effective channels and scores, and weights of different effective channels.

[0008] Preferably, the training of the subjective evaluation model comprises: obtaining a training data set, the training data set comprising: a plurality of evaluation indexes, a plurality of effective channels corresponding to each single evaluation index, electroencephalogram features of different scores corresponding to each single effective channel, a score corresponding to each electroencephalogram feature, and a weight of different effective channels in each evaluation index; training an initial network model based on the training data set to obtain a subjective evaluation model.

[0009] Preferably, the obtaining of the plurality of effective channels corresponding to each single evaluation index and the electroencephalogram features of different scores corresponding to each single effective channel comprises: selecting a standard vehicle set, the standard vehicle set comprising a score standard vehicle to a score standard vehicle corresponding to each evaluation index in the plurality of evaluation indexes; collecting electroencephalogram data of professional evaluators for all evaluation indexes of each standard vehicle in the standard vehicle set to obtain electroencephalogram data under each evaluation index of each score standard vehicle; determining a plurality of effective channels of an evaluation index according to a plurality of electroencephalogram data of the professional evaluators for the evaluation index of the different score standard vehicles; and determining electroencephalogram features of different scores corresponding to each single effective channel based on the electroencephalogram data, the plurality of effective channels of the evaluation index, and electroencephalogram features corresponding to each effective channel for each evaluation index of each score standard vehicle.

[0010] Preferably, the obtaining of the score corresponding to each electroencephalogram feature comprises: collecting electroencephalogram data of N professional evaluators for all evaluation indexes of each standard vehicle in the standard vehicle set to obtain N electroencephalogram data under each evaluation index of each score standard vehicle; obtaining an average electroencephalogram feature of an effective channel according to N electroencephalogram features under the effective channel in the N electroencephalogram data; selecting an upper and lower preset fluctuation interval of the average electroencephalogram feature as an electroencephalogram feature interval of the effective channel based on the average electroencephalogram feature; and determining a score corresponding to each electroencephalogram feature in each of the plurality of effective channels based on the electroencephalogram feature interval and the electroencephalogram features of different scores corresponding to each single effective channel.

[0011] Preferably, the determining of the plurality of effective channels of an evaluation index according to a plurality of electroencephalogram data of the professional evaluators for the evaluation index of the different score standard vehicles comprises: determining an effective channel in which electroencephalogram features change in a step-by-step manner with the change of the score of the standard vehicle from each channel of the plurality of electroencephalogram data according to the plurality of electroencephalogram data of the professional evaluators for the evaluation index of the different score standard vehicles to obtain the plurality of effective channels of the evaluation index.

[0012] Preferably, the weight of each effective channel in each evaluation index is obtained by determining the weight of each effective channel in each evaluation index according to the sensitivity of the different effective channels to the evaluation index.

[0013] Preferably, after the EEG data of the evaluation personnel for one evaluation index of the vehicle is obtained, the EEG data of the evaluation index is preprocessed to obtain preprocessed EEG data.

[0014] In a second aspect, an embodiment of the present application provides the following technical solution.

[0015] A vehicle subjective evaluation device comprises:

[0016] An obtaining module is configured to obtain EEG data of an evaluation personnel for one evaluation index of a vehicle, wherein the EEG data comprises a plurality of effective channels corresponding to the evaluation index and EEG features corresponding to each effective channel.

[0017] An evaluation module is configured to input the EEG data of the evaluation index into a pre-trained subjective evaluation model to obtain a total score of the evaluation personnel for the evaluation index, wherein the subjective evaluation model comprises a corresponding relationship between EEG features corresponding to different effective channels and scores, and weights of different effective channels.

[0018] In a third aspect, an embodiment of the present application provides the following technical solution.

[0019] An electronic device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method of any one of the preceding first aspects when executing the program.

[0020] In a fourth aspect, an embodiment of the present application provides the following technical solution.

[0021] A computer readable storage medium has a computer program stored thereon, and the program is executed by a processor to implement the steps of the method of any one of the preceding first aspects.

[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 application can objectively reflect the real feelings of the evaluation personnel by obtaining the brain electrical data of the evaluation personnel for a certain evaluation index of the vehicle, bringing the brain electrical data into a subjective evaluation model, directly reading the physiological brain electrical signals of the evaluation personnel through a brain-computer interface, and extracting the characteristic brain electrical output for the total score of the evaluation index. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments described below. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0025] Figure 1 The flowchart of the vehicle subjective evaluation method in the embodiment of the application;

[0026] Figure 2 The schematic diagram of the preprocessing process in the embodiment of the application;

[0027] Figure 3 The schematic diagram of the brain electrical characteristic wave fluctuation interval in the embodiment of the application;

[0028] Figure 4 The result schematic diagram of the subjective evaluation process in the embodiment of the application;

[0029] Figure 5 The structural schematic diagram of the vehicle subjective evaluation device in the embodiment of the application;

[0030] Figure 6 The structural schematic diagram of the electronic device in the embodiment of the application. DETAILED DESCRIPTION

[0031] The embodiment of the application provides a vehicle subjective evaluation method, device, equipment and medium, which directly reads the physiological brain electrical signals of the evaluation personnel to objectively reflect the score data of the evaluation personnel, and improves the problem of large subjective evaluation difference and low reliability caused by large individual difference.

[0032] The technical solution of the embodiment of the application is as follows to solve the above technical problem:

[0033] A vehicle subjective evaluation method, comprising: acquiring electroencephalogram data of an evaluator for one evaluation index of a vehicle, wherein the electroencephalogram data comprises a plurality of effective channels corresponding to the evaluation index and electroencephalogram features corresponding to each effective channel; and inputting the electroencephalogram data of the evaluation index into a pre-trained subjective evaluation model to obtain a total score of the evaluator for the evaluation index, wherein the subjective evaluation model comprises a corresponding relationship between electroencephalogram features corresponding to different effective channels and scores, and weights of different effective channels.

[0034] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings in the specification and specific embodiments.

[0035] In a first aspect, the vehicle subjective evaluation method provided by the embodiments of the present application is specifically as shown in the following Figure 1 The method comprises the following steps S101 to S102:

[0036] In step S101, electroencephalogram data of an evaluator for one evaluation index of a vehicle is acquired, wherein the electroencephalogram data comprises a plurality of effective channels corresponding to the evaluation index and electroencephalogram features corresponding to each effective channel.

[0037] It should be noted that the evaluator herein refers to any person who does not have professional judgment ability or has professional judgment ability. The evaluation index can be divided into static evaluation index and dynamic evaluation index. The static evaluation index mainly includes appearance quality, interior quality, space and field of view, seat performance, operation convenience, air conditioning performance, electronic and electrical performance, safety performance and maintenance convenience. The dynamic evaluation index mainly includes power performance, driving feeling, NVH performance, steering stability, ride comfort, steering performance and braking performance.

[0038] In the specific implementation process, the electroencephalogram data of the evaluator is acquired by an electroencephalogram acquisition device. For example, taking the comfort index as an example, the evaluator wears an electroencephalogram cap to experience the vehicle and records the electroencephalogram data of the comfort index.

[0039] In order to obtain more accurate electroencephalogram data, after acquiring the electroencephalogram data of the evaluator for one evaluation index of a vehicle, the method can further comprise: preprocessing the electroencephalogram data of the evaluation index to obtain preprocessed electroencephalogram data.

[0040] In specific embodiments, the collected electroencephalogram data is preprocessed, MATLAB can be selected as a data analysis platform, and EEGLAB, an extension toolkit of MATLAB, is used as a preprocessing tool, which also contains plug-ins such as REST, ICLabel, and Viewprops, and the specific preprocessing steps are as follows: according to the electroencephalogram data, the electrode channel data is selected.

[0041] Specifically, the distribution of the electrode positions of the electroencephalogram cap used in the present application conforms to the international 10-20 standard (standard electrode placement method). The method of naming the poles refers to the partitioning of the structure of the brain. 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 center, and Z represents the center of the left and right brain. Based on the partitioning of brain function, considering that the driver is mainly in a state of mental activity, attention, fatigue, and related operation transformation under driving, therefore, 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 electroencephalogram recording system, in order to avoid the influence of the reference electrode on the data of other electrodes, the reference electrode is selected to be far away from the region of interest, and the present application adopts the common bilateral mastoid average method, and selects the protruding position on the temporal bone behind the ear to place two reference electrodes M1 and M2.

[0043] Since the electroencephalogram device is a high-precision device with high sensitivity, if it is not placed correctly during measurement, inaccurate electroencephalogram signals will be collected, such a lead is called a bad lead signal. Further, in order to improve the convenience of testing while avoiding the influence of bad leads on data, an average interpolation method is used to repair bad leads of electroencephalogram data and remove direct current offset.

[0044] Specifically, if the signal of the lead is not used during analysis, the data of the lead can be directly excluded, and if the data of the lead is needed during analysis, an interpolation method can be used to repair the bad lead.

[0045] Further, during the electroencephalogram data collection process, there is interference of power frequency and some high and low frequency noise, and the organization of the human body can cause signal attenuation, so that the collected original signal is not pure. In order to obtain a pure signal, remove the interference signal, after interpolating the bad lead and removing the direct current offset, the electroencephalogram data can also be filtered. For example: select a 0.5-40Hz band-pass filter to remove linear drift, electrocardiogram, electromyogram, and most artifacts.

[0046] Further, the electroencephalogram signal itself is a continuous signal, and key time points of the task state are marked for the convenience of analysis. In order to analyze the event-induced electroencephalogram signal, a signal of a period of time before and after the marked point is extracted, so that the continuous electroencephalogram signal is segmented into one segment after another. 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 of 500 ms before the marked point and 1000 ms after the marked point, and removes the signals exceeding ±80uV.

[0047] For the signals collected by the electroencephalogram cap, the signals collected by each channel are superimposed by the signals around them, and show high correlation, so the components need to be separated. The present application uses independent component analysis to remove the identified artifacts and perform post-bandpass filtering of 2-30Hz to select the beta band of interest for analysis.

[0048] Therefore, as shown in Figure 2 The preprocessing process proposed by the present application can include: selecting electrode channel data, re-reference setting, interpolating bad lead removal, removing direct current offset, filtering, data segmentation and baseline correction, and independent component analysis (ICA).

[0049] In step S102, the electroencephalogram data of the evaluation index is brought into a pre-trained subjective evaluation model to obtain a total score of the evaluation personnel for the evaluation index, wherein the subjective evaluation model includes a corresponding relationship between electroencephalogram features corresponding to different effective channels and scores, and weights of different effective channels.

[0050] In specific embodiments, the training of the subjective evaluation model includes: obtaining a training data set, the training data set including: multiple evaluation indexes, multiple effective channels corresponding to each single evaluation index, electroencephalogram features of different scores corresponding to each single effective channel, scores corresponding to each electroencephalogram feature, and weights of different effective channels in each evaluation index; training an initial network model based on the training data set to obtain the subjective evaluation model.

[0051] In an example, the acquiring of the multiple effective channels corresponding to each single evaluation index and the brain electrical feature corresponding to each single effective channel and each single score includes: selecting a set of standard sample vehicles, the set of standard sample vehicles including a standard sample vehicle corresponding to each single evaluation index in the multiple evaluation indexes and each single score from one to ten; collecting brain electrical data of professional evaluators for each single evaluation index of each single standard sample vehicle in the set of standard sample vehicles to obtain brain electrical data of each single evaluation index of each single standard sample vehicle; determining multiple effective channels of each single evaluation index according to multiple brain electrical data of the professional evaluators for the evaluation index of the different standard sample vehicles; and determining the brain electrical feature corresponding to each single effective channel and each single score based on the brain electrical data, the multiple effective channels of the evaluation index and the brain electrical feature corresponding to each single effective channel for each single evaluation index of each single standard sample vehicle.

[0052] Specifically, a plurality of standard sample vehicles are prepared, and the standard sample vehicles are scored by professional evaluators, and the scores of the evaluation indexes are one-to-one corresponding to the standard sample vehicles for subsequent data collection.

[0053] For the subjective evaluation of the vehicle from the worst to the best, a ten-point system is adopted, as shown in Table 1 below:

[0054] Table 1

[0055]

[0056] For example, for the comfort of the vehicle, multiple standard sample vehicles with comfort scores from 1 to 10 are selected, for the steering performance of the vehicle, multiple standard sample vehicles with steering performance scores from 1 to 10 are selected, and other evaluation indexes are the same.

[0057] Of course, as other optional embodiments, a five-point system or other scoring forms can also be adopted, and the present application is not limited.

[0058] In specific embodiments, the determining of the multiple effective channels of each single evaluation index according to the multiple brain electrical data of the professional evaluators for the evaluation index of the different standard sample vehicles can include: determining, from each single channel of the multiple brain electrical data, an effective channel in which the brain electrical feature changes in steps with the score of the standard sample vehicle according to the multiple brain electrical data of the professional evaluators for the evaluation index of the different standard sample vehicles, to obtain the multiple effective channels of the evaluation index.

[0059] Specifically, the professional conducts evaluation on the standard vehicle with different evaluation scores, and collects full-channel EEG data through the EEG cap. Since the evaluation standard vehicle corresponds to the evaluation score which is in a stepwise increase or stepwise decrease, the corresponding effective channel will have a stepwise intensity change, or a stepwise increase in positive correlation, or a stepwise decrease in negative correlation. By analyzing the change rule of the EEG signal on each channel, the regularly changed (increased or decreased) is determined as the effective channel, and the data of other channels is not used as the effective data of the index. For example, according to the comfort evaluation index of A personnel for the standard vehicle with a score of 1 to 10, the multiple EEG data here are the EEG data of the comfort evaluation index with different scores, and the comfort evaluation index related channel is S{s1, s2, …, sn}.

[0060] For different evaluation indexes, the same method as described above can be used to obtain multiple EEG data of all evaluation indexes of the standard vehicle with different scores, and determine multiple effective channels of each evaluation index.

[0061] Then, for each evaluation index of each score standard vehicle, based on the EEG data and the multiple effective channels of the evaluation index, the effective channel corresponding to the EEG data can be determined, and in combination with the EEG feature corresponding to each effective channel in the multiple effective channels, the EEG feature of each single effective channel under the score can be determined. Furthermore, for each evaluation index of the standard vehicle with different scores, the EEG feature corresponding to each single effective channel under different scores is determined.

[0062] In specific embodiments, obtaining the score corresponding to each EEG feature can include: collecting EEG data of N professional evaluators for all evaluation indexes of each standard vehicle in the standard vehicle set, to obtain N EEG data of each evaluation index of each score standard vehicle; for each effective channel, obtaining the average EEG feature of the effective channel according to the N EEG features of the effective channel under the N EEG data; taking the average EEG feature as a reference, selecting the upper and lower preset fluctuation intervals of the average EEG feature as the EEG feature interval of the effective channel; determining the EEG feature interval of each EEG feature, and determining the score corresponding to each EEG feature of the multiple effective channels according to the EEG feature interval and the EEG feature corresponding to each single effective channel under different scores.

[0063] Specifically, multiple professional evaluators wear EEG caps on the standard vehicle and conduct subjective evaluation and scoring and EEG data collection for each evaluation index. Taking the comfort index as an example, the professional evaluators wear EEG caps to experience each score standard vehicle in turn, and record the EEG data corresponding to each score of the comfort index. N professional evaluators correspond to N EEG data of each evaluation index of each score standard vehicle.

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

[0065] Based on 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 determined 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 prototype vehicles with scores ranging from one to ten were collected for each channel. By fitting the EEG features of N evaluators collected from each standard prototype vehicle, the average EEG feature was used as a benchmark, and the appropriate fluctuation ratio was selected as the upper and lower fluctuation range according to the fluctuation situation. This was used as the corresponding EEG evaluation indicator for this segment and band, and so on. The EEG feature range from one to ten points was determined for each valid channel.

[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 feature interval may be 5% above or below the average EEG feature. Of course, in other embodiments, the EEG feature interval may also be 4%, 6%, etc. above or below the average EEG feature.

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

[0070] In each valid channel, the data will show different sensitivities to the evaluation index. For example, as the score of the s1 channel increases, the intensity increases by 5 each time, while the intensity of the s2 channel increases by 3 as the score increases. This shows that the 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 in 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 the subjective evaluation model, which can include: matching the EEG features corresponding to each effective channel with the scores to obtain the scores B{b1, b2,..., bn} of all effective channels, combining the scores of each effective channel with the weights of the effective channels respectively, and comprehensively obtaining the final total score C to complete the correspondence between the subjective score and the objective score obtained by the EEG data, and the model is as follows:

[0073]

[0074] In the present application, by performing the above steps on each evaluation index, a training data set is formed, which includes the effective channels corresponding to each evaluation index, the weights of the effective channels, the different score EEG feature maps corresponding to each effective channel, and the scores corresponding to each EEG feature. With the increase of data, the data set is constantly improved, and the evaluation model will be more accurate.

[0075] As shown in Figure 4 The present application finds the EEG features corresponding to the index score by preprocessing the collected EEG data and then continuing data analysis to form an objective evaluation index. The collected EEG data is full-channel, but only a few channels are related to the features of the index. Therefore, the relevant channels associated with the index are first determined, then the channel weights are determined according to the sensitivity of the channels to the index, and finally the EEG feature index corresponding to each score of the index is determined according to the effective channel data corresponding to each score.

[0076] According to the EEG data, a plurality of effective channels of the evaluation index are determined, the scores of each effective channel are determined according to the corresponding relationship between the scores and the EEG features of the plurality of effective channels, and the total score is obtained by combining the scores of each effective channel with the weights corresponding to the effective channels.

[0077] In the actual evaluation process, the evaluation personnel wear an EEG cap to perform evaluation activities on the formal test vehicle, and the corresponding score can be obtained based on the EEG data to complete the objectification of the subjective score.

[0078] In summary, the vehicle subjective evaluation method provided by the embodiments of the present application directly reads the physiological EEG signals of the evaluation personnel to objectively reflect the score data of the evaluation personnel, applies the brain-computer interface to the field of vehicle subjective evaluation, and well solves the problems of poor evaluation accuracy caused by individual differences when the vehicle is subjected to subjective evaluation, improves the large subjective evaluation difference and low reliability caused by large individual differences, and adopts the method to make each person an excellent evaluation personnel, saves cost, and improves efficiency.

[0079] In a second aspect, based on the same inventive concept, the present embodiment provides a vehicle subjective evaluation device, as shown inFigure 5 As shown, comprising:

[0080] The acquisition module 401 is configured to acquire electroencephalogram data of an evaluation person for one evaluation index of a vehicle, wherein the electroencephalogram data comprises a plurality of effective channels corresponding to the evaluation index and electroencephalogram features corresponding to each effective channel.

[0081] The evaluation module 402 is configured to input the electroencephalogram data of the evaluation index into a pre-trained subjective evaluation model to obtain a total score of the evaluation person for the evaluation index, wherein the subjective evaluation model comprises a corresponding relationship between electroencephalogram features corresponding to different effective channels and scores, and weights of different effective channels.

[0082] As an optional embodiment, the training of the subjective evaluation model comprises: acquiring a training data set, the training data set comprising: a plurality of evaluation indexes, a plurality of effective channels corresponding to each single evaluation index, electroencephalogram features corresponding to different scores of each single effective channel, scores corresponding to each electroencephalogram feature, and weights of different effective channels in each evaluation index; and training an initial network model based on the training data set to obtain the subjective evaluation model.

[0083] As an optional embodiment, the acquisition of the plurality of effective channels corresponding to each single evaluation index and the electroencephalogram features corresponding to different scores of each single effective channel comprises: selecting a set of standard sample vehicles, the set of standard sample vehicles comprising a score standard sample vehicle to a ten-score standard sample vehicle corresponding to each evaluation index in the plurality of evaluation indexes; collecting electroencephalogram data of professional evaluation persons for all evaluation indexes of each standard sample vehicle in the set of standard sample vehicles to obtain electroencephalogram data under each evaluation index of each score standard sample vehicle; determining a plurality of effective channels of one evaluation index based on a plurality of electroencephalogram data of the professional evaluation person for the different score standard sample vehicles; and determining electroencephalogram features corresponding to different scores of each single effective channel based on the electroencephalogram data, the plurality of effective channels of the evaluation index, and the electroencephalogram features corresponding to each effective channel for each evaluation index of each score standard sample vehicle.

[0084] As an optional embodiment, obtaining the score corresponding to each EEG feature includes: collecting EEG data of N professional evaluators for all evaluation indicators of each standard sample vehicle in the standard sample vehicle set, and obtaining N EEG data under each evaluation indicator of each score standard sample vehicle; 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 benchmark, 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 score 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, based on multiple EEG data of one evaluation indicator of standard sample vehicles with different scores by professional evaluators, 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, configured 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 embodiment of the present invention provides a vehicle subjective evaluation device, whose implementation principle and technical effects 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 can be made to the corresponding content 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 capable of running 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 the embodiment is the electronic device used for implementing the vehicle subjective evaluation method in the embodiment, based on the vehicle subjective evaluation method introduced in the embodiment, those skilled in the art can understand the specific implementation of the electronic device in the embodiment and various changes thereof, so the implementation of the electronic device in the embodiment is not introduced in detail.

[0092] Those skilled in the art will understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can 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-ROMs, optical storage, etc.) containing computer-usable program code.

[0093] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams 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 apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 a module that implements the function specified in the flow or flows and / or block or blocks.

[0094] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction modules, which implement the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 a module that implements the function specified in the flow or flows and / or block or blocks.

[0095] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1steps of the functions specified in the block or blocks.

[0096] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the preferred embodiments by those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to encompass within their scope all such variations and modifications as are included within the scope of the application.

[0097] It is clear that the application can be subject to many modifications and variations without departing from the scope of the application as defined by the appended claims. Thus, the application is intended to embrace all such modifications and variations as fall within the scope of the appended claims and their equivalents.

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 multiple valid channels corresponding to the evaluation indicator and EEG features corresponding to each valid channel; Submitting 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, as well as the weights of different effective channels; The training of the subjective evaluation model includes: obtaining a training data set, the training data set including: a plurality of evaluation indicators, a plurality of valid channels corresponding to each single evaluation indicator, EEG features with 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; training an initial network model based on the training data set to obtain a subjective evaluation model; Acquiring multiple valid channels corresponding to each single evaluation indicator includes: selecting a set of standard sample vehicles, the set of standard sample vehicles including standard sample vehicles with scores ranging from one to ten corresponding to each evaluation indicator in the multiple evaluation indicators; collecting EEG data of professional evaluators for all evaluation indicators of each standard sample vehicle in the set of standard sample vehicles, and obtaining EEG data under each evaluation indicator of each score standard sample vehicle; and determining, from each channel of the multiple EEG data, an effective channel whose EEG characteristics change in a step-by-step manner as the score of the standard sample vehicle changes based on multiple EEG data of professional evaluators for one evaluation indicator of standard sample vehicles with different scores, and obtaining multiple valid channels for the evaluation indicator.

2. The method according to claim 1, wherein Obtain EEG features of different scores corresponding to each valid channel, including: For each evaluation indicator of each score standard sample vehicle, based on the EEG data, multiple valid channels of the evaluation indicator and the EEG features corresponding to each valid channel, the EEG features of different scores corresponding to each single valid channel are determined.

3. The method according to claim 2, wherein 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 set of standard sample cars, and obtaining N EEG data under each evaluation indicator of each score standard sample car; Obtaining an average EEG feature of one effective channel according to the N EEG features of the effective channel in the N EEG data; Taking the average EEG feature as a benchmark, 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 based on the EEG feature interval and the EEG features of different scores corresponding to each single valid channel.

4. The method according to claim 1, wherein 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.

5. The method according to claim 1, wherein After obtaining the EEG 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.

6. A vehicle subjective evaluation device, characterized in that: include: an acquisition module, configured to acquire EEG data of an evaluator for one of the evaluation indicators of a vehicle, wherein the EEG data includes multiple valid channels corresponding to the evaluation indicator and EEG features corresponding to each valid channel; An evaluation module, configured to input the EEG data of the evaluation index into a pre-trained subjective evaluation model to obtain the evaluator's total score for the evaluation index, wherein the subjective evaluation model includes the correspondence between the EEG features and scores corresponding to different effective channels, as well as the weights of different effective channels; The training of the subjective evaluation model includes: obtaining a training data set, the training data set including: a plurality of evaluation indicators, a plurality of valid channels corresponding to each single evaluation indicator, EEG features with 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; training an initial network model based on the training data set to obtain a subjective evaluation model; Acquiring multiple valid channels corresponding to each single evaluation indicator includes: selecting a set of standard sample vehicles, the standard sample vehicle set including standard sample vehicles with scores ranging from one to ten corresponding to each evaluation indicator in the multiple evaluation indicators; collecting EEG data of professional evaluators for all evaluation indicators of each standard sample vehicle in the set of standard sample vehicles, and obtaining EEG data under each evaluation indicator of each score standard sample vehicle; and determining, from each channel of the multiple EEG data, an effective channel whose EEG characteristics show a step-by-step change as the score of the standard sample vehicle changes based on multiple EEG data of professional evaluators for one of the evaluation indicators of standard sample vehicles with different scores, and obtaining multiple valid channels for the evaluation indicator.

7. 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 steps of the method according to any one of claims 1 to 5 are implemented when the processor executes the program.

8. 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 according to any one of claims 1 to 5 are implemented.

Images