Vehicle internal space evaluation method, device and equipment and readable storage medium

Abstract

The invention discloses a vehicle internal space evaluation method, device and equipment and a readable storage medium, and the method comprises the steps: collecting user behavior data when a user uses each internal space of a to-be-evaluated vehicle for each use scene and each user, predicting and outputting a first behavior prediction score of the user through the machine model; calculating a mean value and a standard deviation according to the first behavior prediction scores of the plurality of users; calculating a second behavior prediction score according to the first behavior prediction scores of the plurality of users, the mean value and the standard deviation; and multiplying the second behavior prediction score of each usage scene by a corresponding scene weight coefficient, performing accumulation, and performing calculation to obtain a third behavior prediction score of the to-be-evaluated vehicle. According to the invention, from the perspective of the subjective feeling of the user, an efficient, accurate and comprehensive evaluation reference is provided for improving the design of the internal space of the vehicle.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle interior space design, and in particular to a vehicle interior space evaluation method, device, equipment, and readable storage medium. Background Art

[0002] With the rapid development of the automotive industry, users have more and more requirements for the interior space of vehicles, and their needs are becoming more and more diversified. Therefore, the reasonable design of the interior space of vehicles is particularly important.

[0003] However, the current traditional vehicle interior space design mainly relies on the physical size measurement of the vehicle interior space, which has a very limited effect on improving the vehicle interior space design. Summary of the Invention

[0004] The present application provides a vehicle interior space evaluation method, device, equipment and readable storage medium, aiming to solve the technical problem that the current traditional vehicle interior space design mainly relies on the physical size measurement of the vehicle interior space, which has a very limited effect on improving the vehicle interior space design.

[0005] In a first aspect, an embodiment of the present application provides a vehicle interior space evaluation method, the vehicle interior space evaluation method comprising:

[0006] For each usage scenario and for each user, collect user behavior data when using each interior space of the vehicle to be evaluated, and output the user's first behavior prediction score through machine model prediction;

[0007] Based on the first behavior prediction scores of multiple users, the mean and standard deviation are calculated;

[0008] Calculate the second behavior prediction score based on the first behavior prediction scores, mean and standard deviation of multiple users;

[0009] The second behavior prediction score of each usage scenario is multiplied by the corresponding scenario weight coefficient and accumulated to calculate the third behavior prediction score of the vehicle to be evaluated.

[0010] Optionally, before collecting user behavior data of each user when using various interior spaces of the vehicle to be evaluated for each usage scenario and for each user, and outputting the user's first behavior prediction score through the machine model prediction, the following steps may be performed:

[0011] Use the training data set to train the machine model, where each sample data in the training data set includes usage scenarios, user behavior data, and corresponding behavior prediction score labels;

[0012] When the loss function of the machine model converges or the number of training times reaches a preset number, the machine model at which the loss function converges or the number of training times reaches the preset number is used as the trained machine model.

[0013] Optionally, calculating the second behavior prediction score based on the first behavior prediction scores, mean, and standard deviation of the multiple users includes:

[0014] The second behavior prediction score is calculated based on the first behavior prediction scores, mean and standard deviation of multiple users using Formula 1, where Formula 1 is:

[0015]

[0016] Among them, S is the second behavior prediction score, n is the total number of users, R i is the predicted score for the first action of the i-th user, μ is the mean, and σ is the standard deviation.

[0017] Optionally, after the second behavior prediction score of each usage scenario is multiplied by the corresponding scenario weight coefficient and accumulated to obtain the third behavior prediction score of the vehicle to be evaluated, the following steps are included:

[0018] The third behavior prediction score and the first physical size score of the vehicle to be evaluated are multiplied by corresponding weight coefficients and summed to obtain a final score of the vehicle to be evaluated.

[0019] Optionally, before calculating the final score of the vehicle to be evaluated by multiplying the third behavior prediction score and the first physical size score of the vehicle to be evaluated by corresponding weight coefficients and summing the results, the following steps may be performed:

[0020] Obtaining physical dimensions of each interior space of the vehicle to be evaluated, and obtaining physical dimensions of each interior space of multiple vehicles, wherein the multiple vehicles are of the same level as the vehicle to be evaluated, and each interior space of the multiple vehicles corresponds to each interior space of the vehicle to be evaluated in terms of interior space location;

[0021] For each interior space, a second physical dimension score of the vehicle to be evaluated is calculated based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated;

[0022] The first physical size score of the vehicle to be evaluated is calculated by multiplying the second physical size score of each interior space of the vehicle to be evaluated by the corresponding interior space weight coefficient and adding them up.

[0023] Optionally, calculating, for each interior space, a second physical dimension score of the vehicle to be evaluated based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated includes:

[0024] For each interior space, a second physical dimension score of the vehicle to be evaluated is calculated using Formula 2 based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated. Formula 2 is:

[0025] M=[(Size-Min) / (Max-Min)]*X

[0026] Where M is the second physical size score of the vehicle to be evaluated, Size is the physical size of the vehicle to be evaluated, Max and Min are the maximum and minimum values of the physical sizes of multiple vehicles, respectively, and X is the score conversion coefficient.

[0027] In a second aspect, an embodiment of the present application provides a vehicle interior space evaluation device, the vehicle interior space evaluation device comprising:

[0028] The prediction module is used to collect user behavior data when using various interior spaces of the vehicle to be evaluated for each usage scenario and for each user, and output the user's first behavior prediction score through machine model prediction;

[0029] A first calculation module is used to predict scores based on the first actions of multiple users and calculate a mean and a standard deviation;

[0030] A second calculation module is used to calculate a second behavior prediction score based on the first behavior prediction scores, mean and standard deviation of the multiple users;

[0031] The third calculation module is used to multiply the second behavior prediction score of each usage scenario by the corresponding scenario weight coefficient and accumulate them to calculate the third behavior prediction score of the vehicle to be evaluated.

[0032] Optionally, the vehicle interior space evaluation device further includes a training module for:

[0033] Use the training data set to train the machine model, where each sample data in the training data set includes usage scenarios, user behavior data, and corresponding behavior prediction score labels;

[0034] When the loss function of the machine model converges or the number of training times reaches a preset number, the machine model at which the loss function converges or the number of training times reaches the preset number is used as the trained machine model.

[0035] In a third aspect, an embodiment of the present application provides a vehicle interior space evaluation device, which includes a processor, a memory, and a vehicle interior space evaluation program stored on the memory and executable by the processor, wherein when the vehicle interior space evaluation program is executed by the processor, the steps of the vehicle interior space evaluation method described above are implemented.

[0036] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a vehicle interior space evaluation program is stored, wherein when the vehicle interior space evaluation program is executed by a processor, the steps of the vehicle interior space evaluation method as described above are implemented.

[0037] The beneficial effects of the technical solutions provided in the embodiments of the present application include:

[0038] In an embodiment of the present application, for each usage scenario and for each user, user behavior data of the user when using each interior space of the vehicle to be evaluated is collected, and the user's first behavior prediction score is output through machine model prediction; based on the first behavior prediction scores of multiple users, the mean and standard deviation are calculated; based on the first behavior prediction scores, mean and standard deviation of multiple users, the second behavior prediction score is calculated; the second behavior prediction score of each usage scenario is multiplied by the corresponding scenario weight coefficient and accumulated to calculate the third behavior prediction score of the vehicle to be evaluated. Through the embodiments of the present application, the user's subjective feeling of the vehicle's interior space is very important for improving the design of the vehicle's interior space. The user's feeling of the vehicle's interior space is also different in different usage scenarios, which are all lacking considerations in traditional vehicle interior space design. By collecting user behavior data of the user when using each interior space of the vehicle to be evaluated for each usage scenario and for each user, the machine model predicts and outputs the user's first behavior prediction score, thereby achieving efficient and accurate evaluation of the user's subjective feeling of each interior space based on the user behavior data. Further, by combining the mean and standard deviation of multiple users to obtain the second behavior prediction score, the subjective feeling bias of a single user is eliminated. Further, a third behavior prediction score is obtained by integrating multiple usage scenarios, achieving a comprehensive evaluation of the user's subjective feeling in multiple usage scenarios, thereby providing an efficient, accurate and comprehensive evaluation reference for improving the design of the vehicle's interior space from the perspective of the user's subjective feeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of a behavior prediction score calculation process of an embodiment of a vehicle interior space evaluation method of the present application;

[0040] Figure 2 This is a schematic diagram of the final score calculation process of an embodiment of the vehicle interior space evaluation method of the present application;

[0041] Figure 3 A schematic diagram of a physical dimension scoring calculation process of an embodiment of a vehicle interior space evaluation method of the present application;

[0042] Figure 4 This is a schematic diagram of the functional modules of an embodiment of the vehicle interior space evaluation device of the present application;

[0043] Figure 5 This is a schematic diagram of the hardware structure of the vehicle interior space evaluation device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0046] In a first aspect, an embodiment of the present application provides a method for evaluating vehicle interior space.

[0047] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the behavior prediction score calculation process of an embodiment of the vehicle interior space evaluation method of the present application. Figure 1 As shown in Figure 2, the vehicle interior space evaluation method includes:

[0048] In step S10 , for each usage scenario and for each user, user behavior data of the user when using each interior space of the vehicle to be evaluated is collected, and the user's first behavior prediction score is output through machine model prediction.

[0049] In this embodiment, the vehicle's usage scenarios include but are not limited to urban commuting scenarios, long and short distance travel scenarios, and family travel scenarios, among which the urban commuting scenarios can be further subdivided into peak hours and non-peak hours, and the long and short distance travel scenarios and family travel scenarios can be further subdivided into usage scenarios, which are not limited here. The various interior spaces of the vehicle include but are not limited to knee space, head space, lateral space, front space, rear space, storage space, and trunk space, among others.

[0050] It is easy to understand that users have different focuses and levels of attention when using the various interior spaces of a vehicle in different usage scenarios, and corresponding users will exhibit different behavioral performances. The different behavioral performances exhibited by users can reflect the users' different subjective feelings about the various interior spaces of the vehicle in different usage scenarios. For example, in urban commuting scenarios, users usually focus on lateral space, and in long and short distance travel scenarios, they usually focus on knee space. For the front space, the driver and front passenger are more concerned about the comfort of head and knee space, especially when they are stationary for a long time. For the rear space, rear passengers are more sensitive to lateral space (shoulder space) and knee space, especially in crowded compartments, especially in long-distance travel scenarios. Users have an increased demand for trunk space, and need a larger space to store luggage and items. For family travel scenarios, when there are children, the installation and use of child seats has a significant impact on space perception. At the same time, users have an increased demand for trunk space to store children's products (such as strollers and toys).

[0051] Therefore, various devices such as cameras and pressure sensors in the vehicle can be used to collect user behavior data of multiple users when using the various interior spaces of the vehicle to be evaluated in different usage scenarios, such as head space, knee space, seat adjustment and storage space usage. The machine model further performs feature extraction to extract features related to the perception of the vehicle's interior space from the original user behavior data, such as the distance between the head and the roof, the pressure distribution of the knees, the frequency of seat adjustment, and the frequency of storage space usage, etc., and further predicts and outputs the first behavior prediction score for each user.

[0052] Specifically, for example, in an urban commuting scenario, the machine model predicts and outputs the first-behavior predicted scores of 10 users for the vehicle to be evaluated, which are: 4.0, 3.5, 4.0, 3.5, 3.5, 3.0, 4.0, 5.0, 3.0, 4.5. Among them, the first-behavior predicted score of each user for the vehicle to be evaluated can be obtained by multiplying the predicted score of each interior space by the weight coefficient corresponding to each interior space and summing them up.

[0053] Step S20 , predicting scores based on the first actions of multiple users, and calculating the mean and standard deviation.

[0054] In this embodiment, continuing to take 10 users as an example, based on the first behavior prediction scores of the 10 users obtained in step S10, the mean and standard deviation are calculated according to the first behavior prediction scores of the 10 users. Specifically, the first behavior prediction scores of the 10 users can be added and divided by 10 to obtain the mean, and the squares of the differences between the first behavior prediction scores of each user and the mean are accumulated, divided by 10, and then the square root is taken to obtain the standard deviation. The calculation formula of the standard deviation is: Among them, σ is the standard deviation of the data set, N is the number of data in the data set, and x i is the i-th data in the data set, and μ is the mean of the data set.

[0055] Step S30 , calculating a second behavior prediction score based on the first behavior prediction scores, means, and standard deviations of the multiple users.

[0056] In this embodiment, the mean is the average value of all data points in the data set, indicating the center position or "typical value" of the data set. It can reflect the overall level of the data and is a core indicator for measuring data distribution. The standard deviation is an indicator that measures the degree of dispersion of data points relative to the mean. The larger the standard deviation, the more dispersed the data distribution, and the smaller the standard deviation, the more concentrated the data distribution. The standard deviation reflects the distribution of data points around the mean and reflects the stability of the data. Combining the mean and standard deviation can more comprehensively describe the distribution characteristics of the data. Therefore, the second behavior prediction score calculated based on the first behavior prediction scores, mean and standard deviation of multiple users can effectively eliminate the bias influence of the behavior prediction score of a single user and improve the accuracy of the behavior prediction score.

[0057] Step S40 : The second behavior prediction score of each usage scenario is multiplied by the corresponding scenario weight coefficient and the results are accumulated to calculate a third behavior prediction score of the vehicle to be evaluated.

[0058] In this embodiment, the second behavior prediction score of each usage scenario can be calculated respectively through the above-mentioned steps S10-S30, such as the second behavior prediction score of urban commuting scenarios, long and short distance travel scenarios, and family travel scenarios. Then, the second behavior prediction score of each usage scenario is multiplied by the corresponding scenario weight coefficient and accumulated to calculate the third behavior prediction score of the vehicle to be evaluated. The third behavior prediction score obtained by combining multiple usage scenarios realizes a more comprehensive user subjective feeling evaluation. Among them, the scenario weight coefficient corresponding to each usage scenario can be determined through user survey tests and other methods, which are not limited here.

[0059] In this embodiment, various devices such as cameras and pressure sensors in the vehicle can be used to collect user behavior data of multiple users when using various interior spaces of the vehicle to be evaluated in different usage scenarios, and further predict and output the first behavior prediction score of each user. The second behavior prediction score calculated based on the first behavior prediction scores, mean and standard deviation of multiple users can effectively eliminate the bias influence of the behavior prediction score of a single user and improve the accuracy of the behavior prediction score. The second behavior prediction score of each usage scenario is multiplied by the corresponding scenario weight coefficient and accumulated to calculate the third behavior prediction score of the vehicle to be evaluated. The third behavior prediction score obtained by comprehensively analyzing multiple usage scenarios realizes a more comprehensive evaluation of user subjective feelings, and provides an efficient, accurate and comprehensive evaluation reference for improving the design of the vehicle interior space from the perspective of user subjective feelings.

[0060] Furthermore, in one embodiment, before step S10, the following steps are included:

[0061] Use the training data set to train the machine model, where each sample data in the training data set includes usage scenarios, user behavior data, and corresponding behavior prediction score labels;

[0062] When the loss function of the machine model converges or the number of training times reaches a preset number, the machine model at which the loss function converges or the number of training times reaches the preset number is used as the trained machine model.

[0063] In this embodiment, the machine model can employ various deep learning neural network models, the specific structure of which is not limited herein. Before use, the machine model must be trained using a training dataset. A training dataset is one of the core resources used in the machine learning model training process. It consists of a series of samples, each of which typically includes input features and corresponding labels. The input features are the basic information for the model to learn, namely, user behavior data collected by various devices such as cameras and pressure sensors, which captures information about the various interior spaces of the evaluated vehicle under different usage scenarios, such as headroom, kneeroom, seat adjustment, and storage space usage. The labels are the target values that the model is expected to predict. In supervised learning, each input feature is associated with a label, i.e., a corresponding predicted score. Furthermore, a validation set can be used to adjust hyperparameters and select model architecture to prevent overfitting, and a test set can be used to ultimately evaluate model performance and provide an unbiased estimate. The machine model is trained using the training dataset, and the trained model is considered the one that achieves convergence of the loss function or reaches a preset number of training cycles. The trained machine model is used to predict behavior scores based on real-time user behavior data.

[0064] Furthermore, in one embodiment, step S30 includes:

[0065] The second behavior prediction score is calculated based on the first behavior prediction scores, mean and standard deviation of multiple users using Formula 1, where Formula 1 is:

[0066]

[0067] Among them, S is the second behavior prediction score, n is the total number of users, R i is the predicted score for the first action of the i-th user, μ is the mean, and σ is the standard deviation.

[0068] In this embodiment, it can be seen from the above formula 1 that the calculation of the second behavior prediction score uses the first behavior prediction score of each user, as well as the mean and standard deviation obtained based on the first behavior prediction scores of all users. Therefore, the second behavior prediction score calculated based on the first behavior prediction scores, mean and standard deviation of multiple users can effectively eliminate the deviation effect of the behavior prediction score of a single user, and can improve the accuracy of the behavior prediction score.

[0069] Furthermore, in one embodiment, referring to Figure 2 , Figure 2 This is a schematic diagram of the final score calculation process of an embodiment of the vehicle interior space evaluation method of this application, as shown in FIG. Figure 2 As shown, after step S40, the following steps are included:

[0070] Step S50 : The third behavior prediction score and the first physical size score of the vehicle to be evaluated are multiplied by corresponding weight coefficients respectively and summed to obtain a final score of the vehicle to be evaluated.

[0071] In this embodiment, the first physical size score can be obtained after calculation based on the physical sizes of each interior space of the vehicle to be evaluated, and represents the physical objective evaluation of the interior space of the vehicle to be evaluated. The third behavioral prediction score is calculated based on the aforementioned steps S10-S40, and accurately and comprehensively reflects the user's subjective feelings about the interior space of the vehicle to be evaluated. Therefore, the third behavioral prediction score and the first physical size score are integrated, and the final score of the vehicle to be evaluated not only takes into account the physical objective evaluation of the vehicle's interior space but also takes into account the user's subjective feelings about the vehicle's interior space, thereby improving the comprehensiveness and accuracy of the vehicle's interior space evaluation. Among them, the corresponding weight coefficients multiplied by the third behavior prediction score and the first physical size score can be determined through user survey tests and other methods. For example, by investigating the importance of the third behavior prediction score and the first physical size score by multiple users and scoring them, taking the average of the scores, and then calculating the corresponding weight coefficients. Specifically, for example, the average score of the first physical size score is 4.2, and the average score of the third behavior prediction score is 4.5, then the weight coefficient corresponding to the first physical size score is 4.2 / (4.2+4.5)=0.48, and the weight coefficient corresponding to the third behavior prediction score is 4.5 / (4.2+4.5)=0.52.

[0072] Furthermore, the above-mentioned final score calculation method can be used to evaluate competing vehicles of the vehicle to be evaluated, and the position of the vehicle to be evaluated among the competing vehicles can be determined. Based on the final score of the vehicle to be evaluated, targeted interior space design optimization suggestions can also be made for the vehicle to be evaluated, such as adjusting the seat layout, increasing storage space, and improving interior styling design, etc.

[0073] Furthermore, in one embodiment, referring to Figure 3 , Figure 3 This is a flow chart of calculating the physical size score of an embodiment of the vehicle interior space evaluation method of the present application. Figure 3 As shown, before step S50, the following steps are included:

[0074] Step S01, obtaining the physical dimensions of each interior space of the vehicle to be evaluated, and obtaining the physical dimensions of each interior space of multiple vehicles, wherein the multiple vehicles are of the same level as the vehicle to be evaluated, and the interior spaces of the multiple vehicles correspond to the interior spaces of the vehicle to be evaluated in terms of internal spatial location;

[0075] Step S02: For each interior space, a second physical dimension score of the vehicle to be evaluated is calculated based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated;

[0076] Step S03 : The second physical dimension score of each interior space of the vehicle to be evaluated is multiplied by the corresponding interior space weight coefficient and the results are accumulated to calculate the first physical dimension score of the vehicle to be evaluated.

[0077] In this embodiment, 3D scanners, laser rangefinders and other equipment can be used to measure the physical dimensions of the interior spaces of the vehicle to be evaluated and multiple vehicles of the same level as the vehicle to be evaluated, including but not limited to the physical dimensions of knee space, head space, lateral space, front space, rear space, storage space and trunk space. Then, for each interior space, a second physical dimension score of the vehicle to be evaluated is calculated based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated. Since the physical dimension data of the interior spaces of multiple vehicles of the same level as the vehicle to be evaluated are used in the calculation, the physical dimension score of the vehicle to be evaluated is obtained. Based on the data, and taking into account the maximum and minimum values of the physical dimensions of multiple vehicles, the calculated second physical dimension score of the vehicle to be evaluated can well reflect the objective evaluation of the physical dimensions of the vehicle to be evaluated among vehicles of the same level. The second physical dimension score of each interior space of the vehicle to be evaluated is further multiplied by the corresponding interior space weight coefficient and accumulated. The calculated first physical dimension score of the vehicle to be evaluated can comprehensively reflect the objective evaluation of the physical dimensions of the vehicle to be evaluated among vehicles of the same level. Among them, the corresponding interior space weight coefficient can be determined through user survey tests and other methods, which are not limited here.

[0078] Furthermore, in one embodiment, for each interior space, calculating the second physical dimension score of the vehicle to be evaluated based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated includes:

[0079] For each interior space, a second physical dimension score of the vehicle to be evaluated is calculated using Formula 2 based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated. Formula 2 is:

[0080] M=[(Size-Min) / (Max-Min)]*X

[0081] Where M is the second physical size score of the vehicle to be evaluated, Size is the physical size of the vehicle to be evaluated, Max and Min are the maximum and minimum values of the physical sizes of multiple vehicles, respectively, and X is the score conversion coefficient.

[0082] In this embodiment, it can be seen from the above formula 2 that when calculating the second physical dimension score of the vehicle to be evaluated, the physical dimension data of each interior space of multiple vehicles of the same level as the vehicle to be evaluated are used, and the maximum and minimum values of the physical dimensions of the multiple vehicles are taken into account. Therefore, the calculated second physical dimension score of the vehicle to be evaluated can well reflect the objective evaluation of the physical dimensions of the vehicle to be evaluated among vehicles of the same level, wherein the score conversion coefficient X can take a value of 5, for example.

[0083] In a second aspect, an embodiment of the present application also provides a vehicle interior space evaluation device.

[0084] In one embodiment, referring to Figure 4 , Figure 4 This is a functional module diagram of an embodiment of the vehicle interior space evaluation device of the present application, as shown in FIG. Figure 4 As shown, the vehicle interior space evaluation device includes:

[0085] The prediction module 10 is used to collect user behavior data when using various interior spaces of the vehicle to be evaluated for each usage scenario and for each user, and output the user's first behavior prediction score through machine model prediction;

[0086] A first calculation module 20 is configured to calculate a mean and a standard deviation of the predicted scores based on the first actions of multiple users;

[0087] A second calculation module 30 is configured to calculate a second behavior prediction score based on the first behavior prediction scores, mean values, and standard deviations of the plurality of users;

[0088] The third calculation module 40 is configured to calculate a third behavior prediction score of the vehicle to be evaluated by multiplying the second behavior prediction score of each usage scenario by the corresponding scenario weight coefficient and accumulating the results.

[0089] Furthermore, in one embodiment, the vehicle interior space evaluation device further includes a training module for:

[0090] Use the training data set to train the machine model, where each sample data in the training data set includes usage scenarios, user behavior data, and corresponding behavior prediction score labels;

[0091] When the loss function of the machine model converges or the number of training times reaches a preset number, the machine model at which the loss function converges or the number of training times reaches the preset number is used as the trained machine model.

[0092] Furthermore, in one embodiment, the second calculation module 30 is configured to:

[0093] The second behavior prediction score is calculated based on the first behavior prediction scores, mean and standard deviation of multiple users using Formula 1, where Formula 1 is:

[0094]

[0095] Among them, S is the second behavior prediction score, n is the total number of users, R i is the predicted score for the first action of the i-th user, μ is the mean, and σ is the standard deviation.

[0096] Furthermore, in one embodiment, the vehicle interior space evaluation device further includes a fourth calculation module configured to:

[0097] The third behavior prediction score and the first physical size score of the vehicle to be evaluated are multiplied by corresponding weight coefficients and summed to obtain a final score of the vehicle to be evaluated.

[0098] Furthermore, in one embodiment, the vehicle interior space evaluation device further includes a fifth calculation module, comprising:

[0099] an acquisition unit, configured to acquire physical dimensions of each interior space of the vehicle to be evaluated, and to acquire physical dimensions of each interior space of a plurality of vehicles, wherein the plurality of vehicles are of the same level as the vehicle to be evaluated, and the interior spaces of the plurality of vehicles correspond to the interior spaces of the vehicle to be evaluated in terms of interior space position;

[0100] a first calculating unit, configured to calculate, for each interior space, a second physical dimension score of the vehicle to be evaluated based on a maximum value and a minimum value of the physical dimensions of the plurality of vehicles and the physical dimension of the vehicle to be evaluated;

[0101] The second calculation unit is configured to multiply the second physical size score of each interior space of the vehicle to be evaluated by the corresponding interior space weight coefficient and add the results together to calculate the first physical size score of the vehicle to be evaluated.

[0102] Furthermore, in one embodiment, the first computing unit is configured to:

[0103] For each interior space, a second physical dimension score of the vehicle to be evaluated is calculated using Formula 2 based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated. Formula 2 is:

[0104] M=[(Size-Min) / (Max-Min)]*X

[0105] Where M is the second physical size score of the vehicle to be evaluated, Size is the physical size of the vehicle to be evaluated, Max and Min are the maximum and minimum values of the physical sizes of multiple vehicles, respectively, and X is the score conversion coefficient.

[0106] Among them, the functional implementation of each module in the above-mentioned vehicle interior space evaluation device corresponds to the various steps in the above-mentioned vehicle interior space evaluation method embodiment, and their functions and implementation processes are no longer detailed here.

[0107] In a third aspect, an embodiment of the present application provides a vehicle interior space evaluation device.

[0108] Reference Figure 5 , Figure 5 FIG2 is a schematic diagram of the hardware structure of the vehicle interior space evaluation device involved in the embodiment of the present application. In the embodiment of the present application, the vehicle interior space evaluation device may include a processor, a memory, a communication interface, and a communication bus.

[0109] The communication bus may be of any type and is used to interconnect the processor, memory, and communication interface.

[0110] Communication interfaces include input / output (I / O) interfaces, physical interfaces, and logical interfaces, used to interconnect components within the vehicle interior space evaluation device, as well as interfaces used to interconnect the vehicle interior space evaluation device with other devices (such as other computing devices or user devices). Physical interfaces can include Ethernet, fiber optic, and ATM interfaces; user devices can include displays, keyboards, and other devices.

[0111] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0112] The processor may be a general-purpose processor that can invoke a vehicle interior space evaluation program stored in a memory and execute the vehicle interior space evaluation method provided in the embodiments of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the vehicle interior space evaluation program is invoked can be referenced to the various embodiments of the vehicle interior space evaluation method of the present application and will not be further described here.

[0113] Those skilled in the art will understand that Figure 5 The hardware structure shown in the figure does not constitute a limitation to the present application and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0114] In a fourth aspect, an embodiment of the present application also provides a readable storage medium.

[0115] The readable storage medium of the present application stores a vehicle interior space evaluation program, wherein when the vehicle interior space evaluation program is executed by a processor, the steps of the vehicle interior space evaluation method as described above are implemented.

[0116] Among them, the method implemented when the vehicle interior space evaluation program is executed can refer to the various embodiments of the vehicle interior space evaluation method of the present application, and will not be repeated here.

[0117] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0118] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit the "first", "second" and "third" to different types.

[0119] In the description of the embodiments of this application, the words "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0120] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0121] In some processes described in the embodiments of the present application, multiple operations or steps are included that appear in a specific order. However, it should be understood that these operations or steps may not be performed in the order in which they appear in the embodiments of the present application or may be performed in parallel. The sequence numbers of the operations are only used to distinguish between different operations, and the sequence numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations or steps may be performed in sequence or in parallel, and these operations or steps may be combined.

[0122] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to execute the methods described in each embodiment of the present application.

[0123] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle interior space evaluation method, characterized in that: The vehicle interior space evaluation method comprises: For each usage scenario and for each user, collect user behavior data when using each interior space of the vehicle to be evaluated, and output the user's first behavior prediction score through machine model prediction; Based on the first behavior prediction scores of multiple users, the mean and standard deviation are calculated; Calculate the second behavior prediction score based on the first behavior prediction scores, mean and standard deviation of multiple users; The second behavior prediction score of each usage scenario is multiplied by the corresponding scenario weight coefficient and accumulated to calculate the third behavior prediction score of the vehicle to be evaluated.

2. The vehicle interior space evaluation method according to claim 1, wherein: Before collecting user behavior data of each user when using various interior spaces of the vehicle to be evaluated for each usage scenario and for each user, and outputting the user's first behavior prediction score through the machine model prediction, the following steps are included: Use the training data set to train the machine model, where each sample data in the training data set includes usage scenarios, user behavior data, and corresponding behavior prediction score labels; When the loss function of the machine model converges or the number of training times reaches a preset number, the machine model at which the loss function converges or the number of training times reaches the preset number is used as the trained machine model.

3. The vehicle interior space evaluation method according to claim 1, wherein: The calculating of the second behavior prediction score according to the first behavior prediction scores, mean and standard deviation of the plurality of users includes: The second behavior prediction score is calculated based on the first behavior prediction scores, mean and standard deviation of multiple users using Formula 1, where Formula 1 is: Among them, S is the second behavior prediction score, n is the total number of users, R i is the predicted score for the first action of the i-th user, μ is the mean, and σ is the standard deviation.

4. The vehicle interior space evaluation method according to claim 1, wherein: After the second behavior prediction score of each usage scenario is multiplied by the corresponding scenario weight coefficient and accumulated to obtain the third behavior prediction score of the vehicle to be evaluated, the method includes: The third behavior prediction score and the first physical size score of the vehicle to be evaluated are multiplied by corresponding weight coefficients and summed to obtain a final score of the vehicle to be evaluated.

5. The vehicle interior space evaluation method according to claim 4, wherein: Before calculating the final score of the vehicle to be evaluated by multiplying the third behavior prediction score and the first physical size score of the vehicle to be evaluated by corresponding weight coefficients and summing the results, the following steps are included: Obtaining physical dimensions of each interior space of the vehicle to be evaluated, and obtaining physical dimensions of each interior space of multiple vehicles, wherein the multiple vehicles are of the same level as the vehicle to be evaluated, and each interior space of the multiple vehicles corresponds to each interior space of the vehicle to be evaluated in terms of interior space location; For each interior space, a second physical dimension score of the vehicle to be evaluated is calculated based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated; The first physical size score of the vehicle to be evaluated is calculated by multiplying the second physical size score of each interior space of the vehicle to be evaluated by the corresponding interior space weight coefficient and adding them up.

6. The vehicle interior space evaluation method according to claim 5, wherein: For each interior space, calculating the second physical dimension score of the vehicle to be evaluated based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated includes: For each interior space, a second physical dimension score of the vehicle to be evaluated is calculated using Formula 2 based on the maximum and minimum values of the physical dimensions of the multiple vehicles and the physical dimensions of the vehicle to be evaluated. Formula 2 is: M=[(Size-Min) / (Max-Min)]*X Where M is the second physical size score of the vehicle to be evaluated, Size is the physical size of the vehicle to be evaluated, Max and Min are the maximum and minimum values of the physical sizes of multiple vehicles, respectively, and X is the score conversion coefficient.

7. A vehicle interior space evaluation device, characterized in that: The vehicle interior space evaluation device comprises: The prediction module is used to collect user behavior data when using various interior spaces of the vehicle to be evaluated for each usage scenario and for each user, and output the user's first behavior prediction score through machine model prediction; A first calculation module is used to predict scores based on the first actions of multiple users and calculate a mean and a standard deviation; A second calculation module is used to calculate a second behavior prediction score based on the first behavior prediction scores, mean and standard deviation of the multiple users; The third calculation module is used to multiply the second behavior prediction score of each usage scenario by the corresponding scenario weight coefficient and accumulate them to calculate the third behavior prediction score of the vehicle to be evaluated.

8. The vehicle interior space evaluation device according to claim 7, wherein: The vehicle interior space evaluation device further includes a training module for: Use the training data set to train the machine model, where each sample data in the training data set includes usage scenarios, user behavior data, and corresponding behavior prediction score labels; When the loss function of the machine model converges or the number of training times reaches a preset number, the machine model at which the loss function converges or the number of training times reaches the preset number is used as the trained machine model.

9. A vehicle interior space evaluation device, characterized in that: The vehicle interior space evaluation device includes a processor, a memory, and a vehicle interior space evaluation program stored in the memory and executable by the processor, wherein when the vehicle interior space evaluation program is executed by the processor, the steps of the vehicle interior space evaluation method according to any one of claims 1 to 6 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a vehicle interior space evaluation program, wherein when the vehicle interior space evaluation program is executed by a processor, the steps of the vehicle interior space evaluation method according to any one of claims 1 to 6 are implemented.

Images