Intelligent cockpit evaluation method and system

Abstract

The invention belongs to the technical field of vehicles, and relates to an intelligent cabin evaluation method and system, and the method comprises the steps: constructing environment scene libraries for evaluating a vehicle head-up display function, a vehicle 360-degree image function and a vehicle voice interaction function, the method comprises the steps that a vehicle head-up display function, a vehicle 360-degree image function and a vehicle voice interaction function are tested in different scenes according to a preset objective scoring standard in combination with an environment scene library, objective evaluation scores are obtained, then the objective evaluation scores are compared with subjective evaluation scores, and the objective scoring standard is adjusted.

Description

Technical Field

[0001] The present application belongs to the field of vehicle technology, and in particular, relates to a smart cockpit evaluation method and system. Background Art

[0002] Traditional technology does not have the ability to simulate and reproduce natural lighting, and can only rely on natural natural environments for testing, and is highly dependent on natural weather; traditional technology cannot simulate the dynamic driving scene noise of a vehicle in a laboratory, and can only rely on manual testing under the natural driving state of the vehicle to evaluate the performance of the vehicle voice under vehicle noise; and when evaluating the user experience of some functions of the vehicle, most of the existing technologies use testing of the functions and scoring each function according to preset scoring standards to obtain an evaluation score. This type of scoring is relatively mechanical and formulaic, and is more likely to be out of touch with the actual user experience of consumers. Summary of the invention

[0003] Based on this, it is necessary to provide a smart cockpit evaluation method for the above technical issues, which includes: Constructing a first environment scene library for evaluating a head-up display function of a vehicle, wherein the first environment scene library includes a plurality of first environment scenes of a cockpit; Building a second environment scene library for evaluating the 360-degree imaging function of the vehicle, wherein the second environment scene library includes several second environment scenes of the cockpit; Construct a third environment scenario library for evaluating the vehicle voice interaction function, wherein the third environment scenario library includes several third environment scenarios of the cockpit; According to a preset first objective scoring standard, obtaining an objective evaluation score of the vehicle head-up display function in each first environmental scene in the first environmental scene library, and obtaining a subjective evaluation score; According to the preset second objective scoring standard, obtain the objective evaluation score of the vehicle's 360-degree imaging function in each second environment scene in the second environment scene library, and obtain the subjective evaluation score; According to a preset third objective scoring standard, obtaining an objective evaluation score of the vehicle voice interaction function in each third environment scenario in the third environment scenario library, and obtaining a subjective evaluation score; According to the subjective evaluation score and objective evaluation score of each function, the corresponding objective scoring criteria are adjusted.

[0004] Furthermore, the step of constructing a first environment scene library for evaluating the vehicle head-up display function includes: Based on the preset light collection frequency, obtain the illumination in continuous time periods at different longitudes and latitudes, as well as the illumination of following vehicles at night and meeting vehicles at night; Based on the preset light collection frequency, obtain the illumination in continuous time periods at different longitudes and latitudes, as well as the brightness of rear-following vehicles and front-on vehicles at night; Combine brightness and illumination to obtain light parameter data; Constructing an initial first environment model, and using the light parameter data as training data, inputting the initial first environment model to obtain a first target environment model; According to the first target environment model, a test scene is fitted to obtain the first environment scene library.

[0005] Further, fitting the test scene according to the first target environment model to obtain the first environment scene library includes: According to the first target environment model, a plurality of first environment scenes with different light parameter data are generated, including a plurality of scenes of daytime driving, nighttime driving, following a vehicle from behind during nighttime driving, and oncoming vehicles during nighttime driving.

[0006] Furthermore, the step of constructing a second environment scene library for evaluating the 360-degree imaging function of the vehicle includes: Based on the preset light collection frequency, obtain the illumination of continuous time periods at different longitudes and latitudes and rear-end vehicles at night; Based on the preset light collection frequency, obtain the brightness of the rear-facing vehicles in continuous time periods at different longitudes and latitudes and at night; Combine brightness and illumination to obtain light parameter data; Constructing an initial second environment model, and using the light parameter data as training data, inputting the initial second environment model to obtain a second target environment model; According to the second target environment model, a test scene is fitted to obtain the second environment scene library.

[0007] Further, fitting the test scene according to the second target environment model to obtain the second environment scene library includes: According to the second target environment model, a plurality of second environment scenes with different light parameter data are generated, including a plurality of scenes of daytime driving, nighttime driving, and rearward meeting during nighttime driving.

[0008] Furthermore, the step of constructing a third environment scenario library for evaluating the vehicle voice interaction function includes: Collecting noise sources inside and outside the vehicle to obtain sound data, wherein the noise sources include one or more of road noise, mechanical / power noise, and audio playback sound; Preprocessing the sound data to obtain target sound data; Extracting features from the target sound data to obtain a third environmental feature; Constructing an initial third environment classification model, and using the third environment characteristics as training data, inputting the initial third environment classification model to obtain a third target environment classification model; A third environment of the cockpit is obtained according to the third target environment classification model.

[0009] Furthermore, the third scene in the third environment scene library includes: Noise-free conditions, including: Scenarios where the male / female driver uses Mandarin / dialect / local accent for voice interaction; A scenario where a male or female passenger in the front passenger seat uses Mandarin for voice interaction; A scene where a male / female / child voice in the left / right rear row uses Mandarin to interact with each other; In the presence of noise, including: When driving in an urban area, the car windows are open and there is no audio playing in the car, and the male / female driver in the main driving seat interacts with each other in Mandarin; When driving in an urban area, the car windows are closed and audio is playing in the car, and the male / female driver in the main driving position interacts with each other in Mandarin; During high-speed driving, the car windows are closed and audio is playing in the car, and the male / female driver in the main driving seat interacts with each other in Mandarin.

[0010] Furthermore, adjusting the corresponding objective scoring criteria according to the subjective evaluation score and the objective evaluation score of each function includes: The objective evaluation criteria are repeatedly adjusted and the objective evaluation scores are re-obtained until the difference between the objective evaluation scores and the subjective evaluation scores is less than a preset threshold.

[0011] Furthermore, obtaining the subjective evaluation score includes: Obtaining and averaging evaluation scores of multiple mass consumers to obtain a first subjective evaluation score; Obtaining the evaluation scores of multiple experts and averaging them to obtain a second subjective evaluation score; The subjective evaluation score is obtained by weighting according to the preset weight, the first subjective evaluation score and the second subjective evaluation score.

[0012] On the other hand, a smart cockpit evaluation system is also provided, including: Environment scene building blocks for: Constructing a first environment scene library for evaluating a head-up display function of a vehicle, wherein the first environment scene library includes a plurality of first environment scenes of a cockpit; Building a second environment scene library for evaluating the 360-degree imaging function of the vehicle, wherein the second environment scene library includes several second environment scenes of the cockpit; Construct a third environment scenario library for evaluating the vehicle voice interaction function, wherein the third environment scenario library includes several third environment scenarios of the cockpit; Evaluation module for: According to a preset first objective scoring standard, obtaining an objective evaluation score of the vehicle head-up display function in each first environmental scene in the first environmental scene library, and obtaining a subjective evaluation score; According to the preset second objective scoring standard, obtain the objective evaluation score of the vehicle's 360-degree imaging function in each second environment scene in the second environment scene library, and obtain the subjective evaluation score; According to a preset third objective scoring standard, obtaining an objective evaluation score of the vehicle voice interaction function in each third environment scenario in the third environment scenario library, and obtaining a subjective evaluation score; The scoring standard adjustment module is used to adjust the corresponding objective scoring standard according to the subjective evaluation score and the objective evaluation score of each function.

[0013] By adopting the above technical solutions, the objective evaluation standards for the head-up display function, 360-degree reversing image function and vehicle voice interaction function were adjusted according to the subjective evaluation scores, so that the objective evaluation standards can be combined with the actual usage experience of consumers and industry experts, thereby improving the practicality of the objective evaluation standards and being more in line with the actual usage experience of consumers. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 The present invention is a flowchart of a smart cockpit evaluation method in one embodiment. DETAILED DESCRIPTION

[0016] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all couplings of one or more related listed items.

[0018] It can be understood that the terms "first", "second", etc. used in the present application can be used in this article to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element.

[0019] Reference Figure 1 , an embodiment of the present invention provides a smart cockpit evaluation method, the method comprising: A first environment scene library for evaluating a vehicle head-up display function is constructed, wherein the first environment scene library includes a plurality of first environment scenes of a cockpit.

[0020] This step specifically includes: Based on the preset light collection frequency, obtain the illumination in continuous time periods at different longitudes and latitudes, as well as the illumination of following vehicles at night and meeting vehicles at night; Based on the preset light collection frequency, obtain the illumination in continuous time periods at different longitudes and latitudes, as well as the brightness of rear-following vehicles and front-on vehicles at night; Combine brightness and illumination to obtain light parameter data; Constructing an initial first environment model, and using the light parameter data as training data, inputting the initial first environment model to obtain a first target environment model; According to the first target environment model, a test scene is fitted to obtain the first environment scene library.

[0021] According to the first target environment model, a plurality of first environment scenes with different light parameter data are generated, including a plurality of scenes of daytime driving, nighttime driving, following a vehicle from behind during nighttime driving, and oncoming vehicles during nighttime driving.

[0022] A second environment scene library for evaluating the 360-degree imaging function of a vehicle is constructed, wherein the second environment scene library includes several second environment scenes of the cockpit.

[0023] This step specifically includes: Based on the preset light collection frequency, obtain the illumination of continuous time periods at different longitudes and latitudes and rear-end vehicles at night; Based on the preset light collection frequency, obtain the brightness of the rear-facing vehicles in continuous time periods at different longitudes and latitudes and at night; Combine brightness and illumination to obtain light parameter data; Constructing an initial second environment model, and using the light parameter data as training data, inputting the initial second environment model to obtain a second target environment model; According to the second target environment model, a test scene is fitted to obtain the second environment scene library.

[0024] According to the second target environment model, a plurality of second environment scenes with different light parameter data are generated, including a plurality of scenes of daytime driving, nighttime driving, and rearward meeting during nighttime driving.

[0025] A third environment scenario library for evaluating the vehicle voice interaction function is constructed, and the third environment scenario library includes several third environment scenarios of the cockpit.

[0026] Specifically include: Collecting noise sources inside and outside the vehicle to obtain sound data, wherein the noise sources include one or more of road noise, mechanical / power noise, and audio playback sound; Preprocessing the sound data to obtain target sound data; Extracting features from the target sound data to obtain a third environmental feature; Constructing an initial third environment classification model, and using the third environment characteristics as training data, inputting the initial third environment classification model to obtain a third target environment classification model; A third environment of the cockpit is obtained according to the third target environment classification model.

[0027] The third scenes in the third environment scene library include: Noise-free conditions, including: Scenarios where the male / female driver uses Mandarin / dialect / local accent for voice interaction; A scenario where a male or female passenger in the front passenger seat uses Mandarin for voice interaction; A scene where a male / female / child voice in the left / right rear row uses Mandarin to interact with each other; In the presence of noise, including: When driving in an urban area, the car windows are open and there is no audio playing in the car, and the male / female driver in the main driving seat interacts with each other in Mandarin; When driving in an urban area, the car windows are closed and audio is playing in the car, and the male / female driver in the main driving position interacts with each other in Mandarin; During high-speed driving, the car windows are closed and audio is playing in the car, and the male / female driver in the main driving seat interacts with each other in Mandarin.

[0028] According to a preset first objective scoring standard, an objective evaluation score of the vehicle head-up display function in each first environmental scene in the first environmental scene library is obtained, and a subjective evaluation score is obtained.

[0029] According to the preset second objective scoring standard, the objective evaluation score of the vehicle's 360-degree imaging function in each second environment scene in the second environment scene library is obtained, and the subjective evaluation score is obtained.

[0030] According to the preset third objective scoring standard, the objective evaluation score of the vehicle voice interaction function in each third environment scenario in the third environment scenario library is obtained, and the subjective evaluation score is obtained.

[0031] As described above, each function is tested according to the corresponding scoring criteria and the corresponding test process, and an objective evaluation score is obtained according to the test results and the scoring criteria.

[0032] Specifically, the steps for obtaining the subjective evaluation score include: Obtaining and averaging evaluation scores of multiple mass consumers to obtain a first subjective evaluation score; Obtaining the evaluation scores of multiple experts and averaging them to obtain a second subjective evaluation score; The subjective evaluation score is obtained by weighting according to the preset weight, the first subjective evaluation score and the second subjective evaluation score.

[0033] According to the subjective evaluation score and objective evaluation score of each function, the corresponding objective scoring criteria are adjusted, including: The objective evaluation criteria are repeatedly adjusted and the objective evaluation scores are re-obtained until the difference between the objective evaluation scores and the subjective evaluation scores is less than a preset threshold.

[0034] As described above, the present invention adjusts the objective evaluation criteria for the head-up display function, the 360-degree reversing image function, and the vehicle voice interaction function according to the subjective evaluation scores, so that the objective evaluation criteria can be combined with the actual usage experience of consumers and industry experts, thereby improving the practicality of the objective evaluation criteria and being more in line with the actual usage experience of consumers.

[0035] This embodiment also provides a smart cockpit evaluation system, including: Environment scene building blocks for: Constructing a first environment scene library for evaluating a head-up display function of a vehicle, wherein the first environment scene library includes a plurality of first environment scenes of a cockpit; Building a second environment scene library for evaluating the 360-degree imaging function of the vehicle, wherein the second environment scene library includes several second environment scenes of the cockpit; Construct a third environment scenario library for evaluating the vehicle voice interaction function, wherein the third environment scenario library includes several third environment scenarios of the cockpit; Evaluation module for: According to a preset first objective scoring standard, obtaining an objective evaluation score of the vehicle head-up display function in each first environmental scene in the first environmental scene library, and obtaining a subjective evaluation score; According to the preset second objective scoring standard, obtain the objective evaluation score of the vehicle's 360-degree imaging function in each second environment scene in the second environment scene library, and obtain the subjective evaluation score; According to a preset third objective scoring standard, obtaining an objective evaluation score of the vehicle voice interaction function in each third environment scenario in the third environment scenario library, and obtaining a subjective evaluation score; The scoring standard adjustment module is used to adjust the corresponding objective scoring standard according to the subjective evaluation score and the objective evaluation score of each function.

[0036] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0037] The various embodiments in the present disclosure are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0038] The protection scope of the present disclosure is not limited to the above-mentioned embodiments. Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the scope and spirit of the present disclosure. If these changes and modifications fall within the scope of the claims of the present disclosure and their equivalents, the intention of the present disclosure also includes these changes and modifications.

Claims

1. A smart cockpit evaluation method, characterized in that: Methods include: Constructing a first environment scene library for evaluating a head-up display function of a vehicle, wherein the first environment scene library includes a plurality of first environment scenes of a cockpit; Building a second environment scene library for evaluating the 360-degree imaging function of the vehicle, wherein the second environment scene library includes several second environment scenes of the cockpit; Construct a third environment scenario library for evaluating the vehicle voice interaction function, wherein the third environment scenario library includes several third environment scenarios of the cockpit; According to a preset first objective scoring standard, obtaining an objective evaluation score of the vehicle head-up display function in each first environmental scene in the first environmental scene library, and obtaining a subjective evaluation score; According to the preset second objective scoring standard, obtain the objective evaluation score of the vehicle's 360-degree imaging function in each second environment scene in the second environment scene library, and obtain the subjective evaluation score; According to a preset third objective scoring standard, obtaining an objective evaluation score of the vehicle voice interaction function in each third environment scenario in the third environment scenario library, and obtaining a subjective evaluation score; According to the subjective evaluation score and objective evaluation score of each function, the corresponding objective scoring criteria are adjusted.

2. The smart cockpit evaluation method according to claim 1, characterized in that: The step of constructing a first environment scene library for evaluating a vehicle head-up display function comprises: Based on the preset light collection frequency, obtain the illumination in continuous time periods at different longitudes and latitudes, as well as the illumination of following vehicles at night and meeting vehicles at night; Based on the preset light collection frequency, obtain the illumination in continuous time periods at different longitudes and latitudes, as well as the brightness of rear-following vehicles and front-on vehicles at night; Combine brightness and illumination to obtain light parameter data; Constructing an initial first environment model, and using the light parameter data as training data, inputting the initial first environment model to obtain a first target environment model; According to the first target environment model, a test scene is fitted to obtain the first environment scene library.

3. The smart cockpit evaluation method according to claim 2, characterized in that: The fitting of the test scene according to the first target environment model to obtain the first environment scene library comprises: According to the first target environment model, a plurality of first environment scenes with different light parameter data are generated, including a plurality of scenes of daytime driving, nighttime driving, following a vehicle from behind during nighttime driving, and oncoming vehicles during nighttime driving.

4. The smart cockpit evaluation method according to claim 1, characterized in that: The step of constructing a second environment scene library for evaluating the 360-degree imaging function of the vehicle comprises: Based on the preset light collection frequency, obtain the illumination in continuous time periods at different longitudes and latitudes and when meeting vehicles from behind at night; Based on the preset light collection frequency, the brightness of the continuous time periods at different longitudes and latitudes and when meeting the rear vehicles at night is obtained; Combine brightness and illumination to obtain light parameter data; Constructing an initial second environment model, and using the light parameter data as training data, inputting the initial second environment model to obtain a second target environment model; According to the second target environment model, a test scene is fitted to obtain the second environment scene library.

5. The smart cockpit evaluation method according to claim 4, characterized in that: The fitting of the test scene according to the second target environment model to obtain the second environment scene library comprises: According to the second target environment model, a plurality of second environment scenes with different light parameter data are generated, including a plurality of scenes of daytime driving, nighttime driving, and rearward meeting during nighttime driving.

6. The smart cockpit evaluation method according to claim 1, characterized in that: The step of constructing a third environment scenario library for evaluating the vehicle voice interaction function includes: Collecting noise sources inside and outside the vehicle to obtain sound data, wherein the noise sources include one or more of road noise, mechanical / power noise, and audio playback sound; Preprocessing the sound data to obtain target sound data; Extracting features from the target sound data to obtain a third environmental feature; Constructing an initial third environment classification model, and using the third environment characteristics as training data, inputting the initial third environment classification model to obtain a third target environment classification model; A third environment of the cockpit is obtained according to the third target environment classification model.

7. The smart cockpit evaluation method according to claim 6, characterized in that: The third scene in the third environment scene library includes: Noise-free conditions, including: Scenarios where the male / female driver uses Mandarin / dialect / local accent for voice interaction; A scenario where a male or female passenger in the front passenger seat uses Mandarin for voice interaction; A scene where a male / female / child voice in the left / right rear row uses Mandarin to interact with each other; In the presence of noise, including: When driving in an urban area, the car windows are open and there is no audio playing in the car, and the male / female driver in the main driving seat interacts with each other in Mandarin; When driving in an urban area, the car windows are closed and audio is playing in the car, and the male / female driver in the main driving position interacts with each other in Mandarin; During high-speed driving, the car windows are closed and audio is playing in the car, and the male / female driver in the main driving seat interacts with each other in Mandarin.

8. The smart cockpit evaluation method according to claim 1, characterized in that: The adjustment of the corresponding objective scoring criteria according to the subjective evaluation score and the objective evaluation score of each function includes: The objective evaluation criteria are repeatedly adjusted and the objective evaluation scores are re-obtained until the difference between the objective evaluation scores and the subjective evaluation scores is less than a preset threshold.

9. The smart cockpit evaluation method according to claim 1, characterized in that: The obtaining of subjective evaluation scores comprises: Obtaining and averaging evaluation scores of multiple mass consumers to obtain a first subjective evaluation score; Obtaining the evaluation scores of multiple experts and averaging them to obtain a second subjective evaluation score; The subjective evaluation score is obtained by weighting according to the preset weight, the first subjective evaluation score and the second subjective evaluation score.

10. A smart cockpit evaluation system, characterized in that: include: Environment scene building blocks for: Constructing a first environment scene library for evaluating a head-up display function of a vehicle, wherein the first environment scene library includes a plurality of first environment scenes of a cockpit; Building a second environment scene library for evaluating the 360-degree imaging function of the vehicle, wherein the second environment scene library includes several second environment scenes of the cockpit; Construct a third environment scenario library for evaluating the vehicle voice interaction function, wherein the third environment scenario library includes several third environment scenarios of the cockpit; Evaluation module for: According to a preset first objective scoring standard, obtaining an objective evaluation score of the vehicle head-up display function in each first environmental scene in the first environmental scene library, and obtaining a subjective evaluation score; According to the preset second objective scoring standard, obtain the objective evaluation score of the vehicle's 360-degree imaging function in each second environment scene in the second environment scene library, and obtain the subjective evaluation score; According to a preset third objective scoring standard, obtaining an objective evaluation score of the vehicle voice interaction function in each third environment scenario in the third environment scenario library, and obtaining a subjective evaluation score; The scoring standard adjustment module is used to adjust the corresponding objective scoring standard according to the subjective evaluation score and the objective evaluation score of each function.

Images