Vehicle competitiveness prediction method, device and equipment based on multi-dimensional nonlinear regression

Abstract

The invention discloses a vehicle competitiveness prediction method, device and equipment based on multi-dimensional nonlinear regression, and relates to the technical field of vehicle production and manufacturing, and the method comprises the steps: obtaining all information of a target vehicle, and calculating the score of the target vehicle in each evaluation dimension based on a preset evaluation mode, the evaluation dimension comprises an intelligent cabin, intelligent driving, luxury sense and traditional performance; constructing a vehicle comprehensive competitiveness evaluation model, and performing iterative calculation based on the evaluation dimension score of the target vehicle to obtain a final vehicle comprehensive competitiveness evaluation model; and according to the score of each evaluation dimension of the to-be-evaluated vehicle, in combination with the final vehicle comprehensive competitiveness evaluation model, calculating to obtain a comprehensive competitiveness score of the to-be-evaluated vehicle, and realizing comprehensive competitiveness prediction. According to the invention, the comprehensive competitiveness of the vehicle can be accurately evaluated and predicted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle production and manufacturing, in particular to a vehicle competitiveness prediction method, device and equipment based on multi-dimensional nonlinear regression. BACKGROUND

[0002] With the rapid development of the automobile industry, consumers' demand for vehicles is increasingly diversified and personalized. In addition to traditional indicators such as power performance and fuel economy, the comfort and technological sense of the intelligent cabin, the safety and convenience of intelligent driving, and the luxury of the vehicle are gradually increasing in weight in consumers' car purchase decisions. However, there is currently a lack of a unified and comprehensive evaluation system that cannot comprehensively and accurately measure the competitiveness of vehicles in various dimensions.

[0003] Existing evaluation methods often focus on a single or a few indicators, which cannot truly reflect the overall performance and market competitiveness of vehicles, making it difficult for consumers to make wise choices when purchasing vehicles, and for automobile enterprises to accurately grasp market demand and product positioning. Therefore, how to accurately evaluate and predict the comprehensive competitiveness of vehicles has become a problem that needs to be solved. SUMMARY

[0004] The present application provides a vehicle competitiveness prediction method, device and equipment based on multi-dimensional nonlinear regression, which can accurately evaluate and predict the comprehensive competitiveness of vehicles.

[0005] In a first aspect, the present application provides a vehicle competitiveness prediction method based on multi-dimensional nonlinear regression, which comprises: Obtaining all information of a target vehicle, and calculating the scores of the target vehicle in each evaluation dimension based on a preset evaluation method, wherein the evaluation dimensions include intelligent cabin, intelligent driving, luxury, and traditional performance; Constructing a vehicle comprehensive competitiveness evaluation model, and performing iterative calculation based on the evaluation dimension scores of the target vehicle to obtain a final vehicle comprehensive competitiveness evaluation model; According to the evaluation dimension scores of the vehicle to be evaluated, combining the final vehicle comprehensive competitiveness evaluation model, the comprehensive competitiveness score of the vehicle to be evaluated is calculated to realize comprehensive competitiveness prediction.

[0006] In combination with the first aspect, in an implementation, for the score of the intelligent cabin, the specific evaluation method is: According to the functional characteristics and use scenarios of the intelligent cabin, an evaluation standard is formulated, and the use experience of the intelligent cabin of the target vehicle is actively scored based on the evaluation standard to obtain an active evaluation score of the intelligent cabin; Using testing equipment and software, quantitatively test the performance indicators of the target vehicle's intelligent cockpit and obtain an objective evaluation score for the intelligent cockpit based on the test results; The weight coefficients of the active evaluation score and the objective evaluation score of the smart cockpit are determined, and the active evaluation score and the objective evaluation score of the smart cockpit are integrated based on the fuzzy comprehensive evaluation method to obtain the smart cockpit score of the target vehicle.

[0007] In conjunction with the first aspect, in one embodiment, the intelligent driving score is specifically evaluated as follows: Build a library of intelligent driving test scenarios that include a variety of complex road conditions, and set traffic participants and obstacles in each intelligent driving test scenario; In intelligent driving test scenarios, the intelligent driving system of the target vehicle is monitored and data collected in real time based on sensors. The performance of the intelligent driving system is evaluated from multiple intelligent driving evaluation dimensions, and scores for each intelligent driving evaluation dimension are obtained. According to the importance of each intelligent driving evaluation dimension, the principal component analysis method is used to determine the weight coefficient of each intelligent driving evaluation dimension, so as to calculate the intelligent driving score of the target vehicle.

[0008] In conjunction with the first aspect, in one embodiment, the luxury score is specifically evaluated as follows: Obtain price data for vehicles of different brands and models and take the natural logarithm of the prices; A linear regression model was established with the natural logarithm of price as the independent variable and the sense of luxury score as the dependent variable. Through regression analysis, the corresponding relationship between price and sense of luxury score was determined. According to the price of the target vehicle and the corresponding relationship between the price and the luxury score, the luxury score of the target vehicle is obtained.

[0009] In conjunction with the first aspect, in one embodiment, the specific evaluation method for the traditional performance score is: Standardize each traditional performance indicator of the target vehicle. Use the Z-score standardization method to convert the values ​​of each traditional performance indicator into a standard normal distribution with a mean of 0 and a standard deviation of 1. The data after standard normal distribution are transformed into natural logarithm to obtain the logarithmic score of each traditional performance index, thereby obtaining the traditional performance score of the target vehicle.

[0010] In conjunction with the first aspect, in one embodiment, the vehicle comprehensive competitiveness evaluation model is specifically: Comprehensive competitiveness score = α × (smart cockpit score) β +γ×(intelligent driving score×luxury score)+δ×ln(traditional performance score) Among them, α, β, γ, and δ represent the weight coefficients of the evaluation dimensions.

[0011] In conjunction with the first aspect, in one embodiment, the iterative calculation based on the evaluation dimension scores of the target vehicle to obtain the final vehicle comprehensive competitiveness evaluation model specifically includes: Based on the scores of each evaluation dimension of each target vehicle and the comprehensive competitiveness score of each target vehicle, an iterative algorithm is used to perform iterative calculations to determine the evaluation dimension weight coefficients in the vehicle comprehensive competitiveness evaluation model, thereby obtaining the final vehicle comprehensive competitiveness evaluation model.

[0012] In conjunction with the first aspect, in one embodiment, the comprehensive competitiveness score of the vehicle to be evaluated is calculated based on the scores of each evaluation dimension of the vehicle to be evaluated and combined with the final vehicle comprehensive competitiveness evaluation model to achieve comprehensive competitiveness prediction, specifically including: Calculate the scores of each evaluation dimension of the vehicle to be evaluated according to the preset evaluation method; Based on the calculated scores of each evaluation dimension and combined with the final vehicle comprehensive competitiveness evaluation model, the comprehensive competitiveness score of the vehicle to be evaluated is calculated to achieve comprehensive competitiveness prediction.

[0013] In a second aspect, an embodiment of the present application provides a vehicle competitiveness prediction device based on multidimensional nonlinear regression, the vehicle competitiveness prediction device based on multidimensional nonlinear regression comprising: A calculation module, which is used to obtain all information about the target vehicle and calculate the score of the target vehicle in various evaluation dimensions based on a preset evaluation method. The evaluation dimensions include smart cockpit, smart driving, luxury, and traditional performance; A construction module is used to construct a comprehensive vehicle competitiveness evaluation model and perform iterative calculations based on the evaluation dimension scores of the target vehicle to obtain a final comprehensive vehicle competitiveness evaluation model; The prediction module is used to calculate the comprehensive competitiveness score of the vehicle to be evaluated based on the scores of each evaluation dimension of the vehicle to be evaluated and combined with the final vehicle comprehensive competitiveness evaluation model to achieve comprehensive competitiveness prediction.

[0014] In a third aspect, an embodiment of the present application provides a vehicle competitiveness prediction device based on multidimensional nonlinear regression, wherein the vehicle competitiveness prediction device based on multidimensional nonlinear regression includes a processor, a memory, and a vehicle competitiveness prediction program based on multidimensional nonlinear regression stored on the memory and executable by the processor, wherein when the vehicle competitiveness prediction program based on multidimensional nonlinear regression is executed by the processor, the steps of the above-mentioned vehicle competitiveness prediction method based on multidimensional nonlinear regression are implemented.

[0015] The beneficial effects of the technical solutions provided in the embodiments of the present application include: (1) Comprehensiveness: This assessment comprehensively considers multiple factors, including intelligent cockpit, intelligent driving, luxury, and traditional performance, covering the vehicle's competitiveness in multiple dimensions, including technology, comfort, safety, and performance, and can comprehensively and objectively evaluate the vehicle's overall competitiveness; (2) Scientificity: By adopting advanced mathematical methods and statistical techniques such as fuzzy comprehensive evaluation method, each evaluation index is scientifically processed and weighted, making the evaluation model more scientific and reliable; (3) Practicality: It can not only provide consumers with a reference for car purchases and help them choose vehicles that meet their needs and budgets, but also provide a basis for automobile companies' product development, market positioning and marketing strategy formulation, thereby promoting innovation and development in the automobile industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the vehicle competitiveness prediction method based on multidimensional nonlinear regression in this application; Figure 2 This is a schematic diagram of the functional modules of the vehicle competitiveness prediction device based on multidimensional nonlinear regression in this application; Figure 3 This is a schematic diagram of the hardware structure of the vehicle competitiveness prediction device based on multidimensional nonlinear regression in this application. DETAILED DESCRIPTION

[0017] 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.

[0018] 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.

[0019] On the first aspect, the embodiments of the present application provide a vehicle competitiveness prediction method based on multidimensional nonlinear regression. By comprehensively considering factors in multiple dimensions such as smart cockpit, smart driving, luxury, traditional performance, etc., a reasonable evaluation model is established to accurately evaluate and predict the comprehensive competitiveness of the vehicle, providing consumers with a reference for car purchases, and also providing a basis for automobile companies' product development, market positioning and marketing strategy formulation.

[0020] In one embodiment, referring to Figure 1 , Figure 1This is a flow chart of the vehicle competitiveness prediction method based on multi-dimensional nonlinear regression in this application. Figure 1 As shown in Figure 2, the vehicle competitiveness prediction method based on multidimensional nonlinear regression includes: S1: Obtain all information of the target vehicle and calculate the score of the target vehicle in various evaluation dimensions based on a preset evaluation method. The evaluation dimensions include smart cockpit, smart driving, luxury, and traditional performance. S2: Construct a comprehensive vehicle competitiveness evaluation model and perform iterative calculations based on the evaluation dimension scores of the target vehicle to obtain the final comprehensive vehicle competitiveness evaluation model; S3: Based on the scores of each evaluation dimension of the vehicle to be evaluated and in combination with the final vehicle comprehensive competitiveness evaluation model, a comprehensive competitiveness score of the vehicle to be evaluated is calculated to achieve comprehensive competitiveness prediction.

[0021] Furthermore, the specific evaluation method for the smart cockpit score is as follows: a1: Develop evaluation criteria based on the functional characteristics and usage scenarios of the smart cockpit, and actively score the user experience of the target vehicle's smart cockpit based on the evaluation criteria to obtain an active evaluation score for the smart cockpit; a2: Use testing equipment and software to conduct quantitative tests on the performance indicators of the target vehicle's intelligent cockpit. Based on the test results, an objective evaluation score for the intelligent cockpit is obtained. a3: Determine the weight coefficients of the active evaluation score and the objective evaluation score of the smart cockpit, and fuse the active evaluation score and the objective evaluation score of the smart cockpit based on the fuzzy comprehensive evaluation method to obtain the smart cockpit score of the target vehicle.

[0022] Specifically, a multi-level evaluation team consisting of automotive industry experts, automotive media journalists, and ordinary consumers will be formed to develop detailed evaluation criteria based on the functional characteristics and usage scenarios of the smart cockpit, including but not limited to the user-friendly interface design, the rationality of operational logic, the accuracy and fluency of voice interaction, and the creation of an in-car atmosphere. Evaluation team members will conduct actual experience and score the target vehicle's smart cockpit according to the evaluation criteria, with a score range of 1 to 10, where 1 indicates very dissatisfied and 10 indicates very satisfied. For example, the scores of all evaluators will be aggregated and the average score calculated as the subjective evaluation score of the smart cockpit of target vehicle A. After statistical calculation, the subjective evaluation score of the smart cockpit of target vehicle A will be 7.5 points.

[0023] Next, specialized testing equipment and software (such as HATS voice testing equipment) are used to quantitatively test various performance indicators of the smart cockpit. For example, a voice recognition test system is used to evaluate the accuracy and response time of voice interaction; a high-definition camera and image analysis software are used to assess the screen display quality and color reproduction. Based on the test results, each indicator is scored according to pre-set evaluation criteria. For example, the voice recognition accuracy of target vehicle A was tested to be 92%, with a response time of 1.2 seconds. The screen display quality achieved color reproduction of 85%. Based on the test results and pre-set evaluation criteria, the objective evaluation score of target vehicle A's smart cockpit was 7.8.

[0024] Finally, the subjective and objective evaluation scores are combined using a fuzzy comprehensive evaluation method. First, weight coefficients for the subjective and objective evaluations are determined. These weight coefficients can be determined based on the actual situation using expert scoring or the analytic hierarchy process (AHP) method to obtain a comprehensive score for the intelligent cockpit. For example, if the weight coefficients for the subjective and objective evaluations are set to 0.4 and 0.6, respectively, the intelligent cockpit score for target vehicle A is 7.68.

[0025] Furthermore, the specific evaluation method for intelligent driving scores is as follows: b1: Build a library of intelligent driving test scenarios that include various complex road conditions, and set traffic participants and obstacles in each intelligent driving test scenario; b2: In an intelligent driving test scenario, sensors are used to monitor and collect data from the target vehicle's intelligent driving system in real time. The system's performance is then evaluated across multiple intelligent driving evaluation dimensions, resulting in scores for each dimension. b3: Based on the importance of each intelligent driving evaluation dimension, the principal component analysis method is used to determine the weight coefficient of each intelligent driving evaluation dimension, thereby calculating the intelligent driving score of the target vehicle.

[0026] Specifically, scenario testing will be conducted first, building a library of intelligent driving test scenarios covering a variety of complex road conditions, including urban roads, highways, and rural roads. In each test scenario, different traffic participants and obstacles are set up to simulate a real-world traffic environment. High-precision positioning equipment, lidar, cameras, and other sensors are used to monitor and collect data from the target vehicle's intelligent driving system in real time. For example, in an urban road scenario, target vehicle A has a collision rate of 0 per 100 kilometers, 1 violation per 100 kilometers, and an emergency braking distance of 38 meters. In a highway scenario, the vehicle travels 500 kilometers, with an average speed of 100 kilometers per hour and a travel time of 5 hours.

[0027] Next, an indicator evaluation is conducted to assess the performance of the intelligent driving system across multiple dimensions, including safety, comfort, and efficiency. Safety includes factors such as collision rate, number of violations, and emergency braking distance; comfort includes factors such as acceleration and deceleration smoothness, steering fluidity, and lane keeping accuracy; and efficiency includes factors such as mileage, average speed, and travel time. Principal component analysis is used to determine the weighting coefficients for each dimension based on its importance, and then the intelligent driving score is calculated. For example, using principal component analysis to determine the weighting coefficients for each dimension, the safety, comfort, and efficiency indicators are assigned weights of 0.4, 0.3, and 0.3, respectively. Based on the test data and weighting coefficients, the calculated intelligent driving score for target vehicle A is 8.2.

[0028] Furthermore, the specific evaluation method for the sense of luxury is as follows: c1: Obtain price data for vehicles of different brands and models, and take the natural logarithm of the price; c2: Using the natural logarithm of price as the independent variable and the sense of luxury score as the dependent variable, a linear regression model was established. Through regression analysis, the corresponding relationship between price and sense of luxury score was determined. c3: Based on the price of the target vehicle and the corresponding relationship between the price and the luxury score, the luxury score of the target vehicle is obtained.

[0029] Specifically, we collected price data of vehicles of different brands and models on the market and took the natural logarithm of the price. 10 (Vehicle price)). A linear regression model is established with the logarithm of price as the independent variable and the corresponding luxury score as the dependent variable. Through regression analysis, the quantitative relationship between price and luxury score is determined. Since doubling the price does not double the experience, the natural logarithm of the price is used to represent luxury, reducing the impact of excessive luxury caused by high prices. For example: Collect price data and luxury score data for 50 vehicles of different brands and models on the market, establish a linear regression model, and determine the quantitative relationship between price and luxury score through regression analysis. Assuming that the price of target vehicle A is 200,000 yuan, after regression analysis, its luxury score is 6.8 points.

[0030] Furthermore, for the traditional performance score, the specific evaluation method is as follows: d1: Standardize the traditional performance indicators of the target vehicle. Use the Z-score standardization method to convert the values ​​of each traditional performance indicator into a standard normal distribution with a mean of 0 and a standard deviation of 1. d2: Perform natural logarithm transformation on the data after standard normal distribution to obtain the logarithmic score of each traditional performance indicator, thereby obtaining the traditional performance score of the target vehicle.

[0031] Specifically, standardization is first performed on the traditional performance indicators of the vehicle (such as power performance, fuel economy, braking performance, handling stability, etc.). The Z-score standardization method is used to convert the values ​​of each traditional performance indicator into a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0032] Logarithmic transformation is then performed, with the normalized data subjected to a natural logarithm transformation. The sum of these values ​​yields the logarithmic score for traditional performance. Logarithmic transformation narrows the range of data values, making the differences between different performance indicators more distinct and facilitating subsequent comprehensive evaluation. For example, applying a natural logarithm transformation to the normalized data yields a logarithmic score for traditional performance of target vehicle A of 7.1.

[0033] In this application, the vehicle comprehensive competitiveness evaluation model is specifically: Comprehensive competitiveness score = α × (smart cockpit score) β +γ×(intelligent driving score×luxury score)+δ×ln(traditional performance score) Among them, α, β, γ, and δ represent the weight coefficients of the evaluation dimensions.

[0034] Taking the β power of the smart cockpit score reflects that "the user experience brought about by meeting the basic functions will increase exponentially, and the marginal experience will increase incrementally rather than linearly" (for example, the improvement in voice recognition rate from 90% to 95% is much greater than that from 80% to 85%).

[0035] Taking the product of intelligent driving and luxury reflects that luxury car owners have higher expectations for intelligent driving.

[0036] The above-mentioned vehicle comprehensive competitiveness evaluation model comprehensively considers the impact of smart cockpit, smart driving, luxury and traditional performance on the comprehensive competitiveness of the vehicle. By introducing the interaction term of smart driving and luxury, it better reflects the synergy between the two.

[0037] Furthermore, in one embodiment, an iterative calculation is performed based on the evaluation dimension scores of the target vehicle to obtain a final vehicle comprehensive competitiveness evaluation model, which specifically includes: Based on the scores of each evaluation dimension of each target vehicle and the comprehensive competitiveness score of each target vehicle, an iterative algorithm is used to perform iterative calculations to determine the evaluation dimension weight coefficients in the vehicle comprehensive competitiveness evaluation model, thereby obtaining the final vehicle comprehensive competitiveness evaluation model.

[0038] Specifically, the smart cockpit score, smart driving score, luxury score, and traditional performance score of each target vehicle are used as independent variables, and the comprehensive competitiveness score of each target vehicle is used as the dependent variable. A regression model is established to solve the weight coefficients α, β, γ, and δ, thereby obtaining the final vehicle comprehensive competitiveness evaluation model.

[0039] For example, the weight coefficients α=0.3, β=0.8, γ=0.4, and δ=0.5 are solved through an iterative algorithm.

[0040] Furthermore, in one embodiment, based on the scores of each evaluation dimension of the vehicle to be evaluated and in combination with the final vehicle comprehensive competitiveness evaluation model, a comprehensive competitiveness score of the vehicle to be evaluated is calculated to achieve comprehensive competitiveness prediction, specifically including: S301: Calculating scores of various evaluation dimensions of the vehicle to be evaluated according to the preset evaluation method; S302: Based on the calculated scores of each evaluation dimension and in combination with the final vehicle comprehensive competitiveness evaluation model, a comprehensive competitiveness score of the vehicle to be evaluated is calculated to achieve comprehensive competitiveness prediction.

[0041] Specifically, after obtaining the weighting coefficients, the vehicle's scores for each evaluation dimension (i.e., intelligent cockpit score, intelligent driving score, luxury score, and traditional performance logarithmic score) are substituted into the final comprehensive vehicle competitiveness evaluation model to calculate the vehicle's overall competitiveness score. Furthermore, vehicles can be graded and ranked based on their overall competitiveness scores, tailored to market demand and competitive dynamics, providing consumers with intuitive vehicle purchasing guidance.

[0042] This application constructs a vehicle comprehensive competitiveness evaluation model to build an evaluation model that comprehensively considers the impact of smart cockpit, smart driving, luxury and traditional performance on the comprehensive competitiveness of the vehicle. By introducing the interaction term of smart driving and luxury, it better reflects the synergy between the two, making the evaluation model more in line with the actual situation; by solving the weight coefficient: taking the obtained scores of each dimension as independent variables, the existing market competitiveness of the vehicle as the dependent variable, establishing a regression model, and solving the weight coefficient through an iterative algorithm, the accuracy and rationality of the weight coefficient are ensured, thereby ensuring the reliability of the vehicle comprehensive competitiveness evaluation results.

[0043] The vehicle competitiveness prediction method based on multidimensional nonlinear regression in the embodiment of the present application is comprehensive: it comprehensively considers factors such as smart cockpit, smart driving, luxury and traditional performance, covers the vehicle's competitiveness in multiple dimensions such as technology, comfort, safety, performance, etc., and can comprehensively and objectively evaluate the vehicle's comprehensive competitiveness; scientific: by adopting advanced mathematical methods and statistical techniques such as fuzzy comprehensive evaluation method, each evaluation indicator is scientifically processed and weighted, so that the evaluation model has high scientificity and reliability; practical: it can not only provide consumers with a reference for car purchases and help consumers choose vehicles that meet their needs and budgets, but also provide a basis for automobile companies' product research and development, market positioning and marketing strategy formulation, and promote innovation and development in the automobile industry.

[0044] In a second aspect, an embodiment of the present application also provides a vehicle competitiveness prediction device based on multidimensional nonlinear regression.

[0045] In one embodiment, referring to Figure 2 , Figure 2 This is a functional module diagram of the vehicle competitiveness prediction device based on multi-dimensional nonlinear regression in this application. Figure 2 As shown, the vehicle competitiveness prediction device based on multidimensional nonlinear regression includes: a calculation module, a construction module, and a prediction module.

[0046] The calculation module is used to obtain all the information of the target vehicle and calculate the score of the target vehicle in each evaluation dimension based on a preset evaluation method. The evaluation dimensions include smart cockpit, smart driving, luxury, and traditional performance; the construction module is used to construct a vehicle comprehensive competitiveness evaluation model and perform iterative calculations based on the evaluation dimension scores of the target vehicle to obtain the final vehicle comprehensive competitiveness evaluation model; the prediction module is used to calculate the comprehensive competitiveness score of the vehicle to be evaluated based on the scores of each evaluation dimension of the vehicle to be evaluated, combined with the final vehicle comprehensive competitiveness evaluation model, to achieve comprehensive competitiveness prediction.

[0047] On the third aspect, an embodiment of the present application provides a vehicle competitiveness prediction device based on multidimensional nonlinear regression. The vehicle competitiveness prediction device based on multidimensional nonlinear regression can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0048] Reference Figure 3 , Figure 3 Schematic diagram of the hardware structure of the vehicle competitiveness prediction device based on multidimensional nonlinear regression involved in the embodiment of the present application. In the embodiment of the present application, the vehicle competitiveness prediction device based on multidimensional nonlinear regression may include a processor, a memory, a communication interface and a communication bus.

[0049] The communication bus may be of any type and is used to interconnect the processor, memory, and communication interface.

[0050] Communication interfaces include input / output (I / O) interfaces, physical interfaces, and logical interfaces, which are used to interconnect components within the vehicle competitiveness prediction device based on multidimensional nonlinear regression, as well as interfaces used to interconnect the vehicle competitiveness prediction device based on multidimensional nonlinear regression with other devices (such as other computing devices or user devices). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user devices can be displays, keyboards, etc.

[0051] 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.

[0052] The processor may be a general-purpose processor that can invoke a vehicle competitiveness prediction program based on multidimensional nonlinear regression stored in a memory and execute the vehicle competitiveness prediction method based on multidimensional nonlinear regression 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 competitiveness prediction program based on multidimensional nonlinear regression is invoked can be referenced in the various embodiments of the vehicle competitiveness prediction method based on multidimensional nonlinear regression of the present application and will not be further described here.

[0053] Those skilled in the art will understand that Figure 3 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] Through the description of the above embodiments, 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, they 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 this application, or the part that contributes to the existing technology, can be embodied in the form of a software product. This computer software product 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 this application.

[0059] 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 competitiveness prediction method based on multidimensional nonlinear regression, characterized in that: The vehicle competitiveness prediction method based on multidimensional nonlinear regression includes: Obtain all information about the target vehicle and calculate the target vehicle's score in various evaluation dimensions based on a preset evaluation method, including smart cockpit, smart driving, luxury, and traditional performance; Construct a comprehensive vehicle competitiveness evaluation model and perform iterative calculations based on the evaluation dimension scores of the target vehicle to obtain the final comprehensive vehicle competitiveness evaluation model; According to the scores of each evaluation dimension of the vehicle to be evaluated, combined with the final vehicle comprehensive competitiveness evaluation model, the comprehensive competitiveness score of the vehicle to be evaluated is calculated to achieve comprehensive competitiveness prediction.

2. The vehicle competitiveness prediction method based on multidimensional nonlinear regression according to claim 1, characterized in that: The specific evaluation method for the smart cockpit score is as follows: Formulate evaluation criteria based on the functional characteristics and usage scenarios of the smart cockpit, and actively score the user experience of the smart cockpit of the target vehicle based on the evaluation criteria to obtain an active evaluation score for the smart cockpit; Using testing equipment and software, quantitatively test the performance indicators of the target vehicle's intelligent cockpit and obtain an objective evaluation score for the intelligent cockpit based on the test results; The weight coefficients of the active evaluation score and the objective evaluation score of the smart cockpit are determined, and the active evaluation score and the objective evaluation score of the smart cockpit are integrated based on the fuzzy comprehensive evaluation method to obtain the smart cockpit score of the target vehicle.

3. The vehicle competitiveness prediction method based on multidimensional nonlinear regression according to claim 1, characterized in that: The specific evaluation method for intelligent driving scores is as follows: Build a library of intelligent driving test scenarios that include a variety of complex road conditions, and set traffic participants and obstacles in each intelligent driving test scenario; In intelligent driving test scenarios, the intelligent driving system of the target vehicle is monitored and data collected in real time based on sensors. The performance of the intelligent driving system is evaluated from multiple intelligent driving evaluation dimensions, and scores for each intelligent driving evaluation dimension are obtained. According to the importance of each intelligent driving evaluation dimension, the principal component analysis method is used to determine the weight coefficient of each intelligent driving evaluation dimension, so as to calculate the intelligent driving score of the target vehicle.

4. The vehicle competitiveness prediction method based on multidimensional nonlinear regression according to claim 1, characterized in that: The specific evaluation method for the sense of luxury is as follows: Obtain price data for vehicles of different brands and models and take the natural logarithm of the prices; A linear regression model was established with the natural logarithm of price as the independent variable and the sense of luxury score as the dependent variable. Through regression analysis, the corresponding relationship between price and sense of luxury score was determined. According to the price of the target vehicle and the corresponding relationship between the price and the luxury score, the luxury score of the target vehicle is obtained.

5. The vehicle competitiveness prediction method based on multidimensional nonlinear regression according to claim 1, characterized in that: The specific evaluation method for traditional performance scores is as follows: Standardize each traditional performance indicator of the target vehicle. Use the Z-score standardization method to convert the values ​​of each traditional performance indicator into a standard normal distribution with a mean of 0 and a standard deviation of 1. The data after standard normal distribution are transformed into natural logarithm to obtain the logarithmic score of each traditional performance index, thereby obtaining the traditional performance score of the target vehicle.

6. The vehicle competitiveness prediction method based on multidimensional nonlinear regression according to claim 1, characterized in that: The vehicle comprehensive competitiveness evaluation model is specifically as follows: Comprehensive competitiveness score = α × (smart cockpit score) β +γ×(intelligent driving score×luxury score)+δ×ln(traditional performance score) Among them, α, β, γ, and δ represent the weight coefficients of the evaluation dimensions.

7. The vehicle competitiveness prediction method based on multidimensional nonlinear regression according to claim 6, characterized in that: The evaluation dimension scores of the target vehicle are iteratively calculated to obtain the final vehicle comprehensive competitiveness evaluation model, which specifically includes: Based on the scores of each evaluation dimension of each target vehicle and the comprehensive competitiveness score of each target vehicle, an iterative algorithm is used to perform iterative calculations to determine the evaluation dimension weight coefficients in the vehicle comprehensive competitiveness evaluation model, thereby obtaining the final vehicle comprehensive competitiveness evaluation model.

8. The vehicle competitiveness prediction method based on multidimensional nonlinear regression according to claim 7, characterized in that: The comprehensive competitiveness score of the vehicle to be evaluated is calculated based on the scores of each evaluation dimension of the vehicle to be evaluated and combined with the final vehicle comprehensive competitiveness evaluation model to achieve comprehensive competitiveness prediction, specifically including: Calculate the scores of each evaluation dimension of the vehicle to be evaluated according to the preset evaluation method; Based on the calculated scores of each evaluation dimension and combined with the final vehicle comprehensive competitiveness evaluation model, the comprehensive competitiveness score of the vehicle to be evaluated is calculated to achieve comprehensive competitiveness prediction.

9. A vehicle competitiveness prediction device based on multidimensional nonlinear regression, characterized in that: The vehicle competitiveness prediction device based on multidimensional nonlinear regression includes: A calculation module, which is used to obtain all information about the target vehicle and calculate the score of the target vehicle in various evaluation dimensions based on a preset evaluation method. The evaluation dimensions include smart cockpit, smart driving, luxury, and traditional performance; A construction module is used to construct a comprehensive vehicle competitiveness evaluation model and perform iterative calculations based on the evaluation dimension scores of the target vehicle to obtain a final comprehensive vehicle competitiveness evaluation model; The prediction module is used to calculate the comprehensive competitiveness score of the vehicle to be evaluated based on the scores of each evaluation dimension of the vehicle to be evaluated and combined with the final vehicle comprehensive competitiveness evaluation model to achieve comprehensive competitiveness prediction.

10. A vehicle competitiveness prediction device based on multidimensional nonlinear regression, characterized in that: The vehicle competitiveness prediction device based on multidimensional nonlinear regression includes a processor, a memory, and a vehicle competitiveness prediction program based on multidimensional nonlinear regression stored on the memory and executable by the processor, wherein when the vehicle competitiveness prediction program based on multidimensional nonlinear regression is executed by the processor, the steps of the vehicle competitiveness prediction method based on multidimensional nonlinear regression as described in any one of claims 1 to 8 are implemented.

Images