A method, device and electronic device for evaluating automobile family design

By obtaining the genes and calculating the characteristic identification coefficient of the car brand and evaluating the family design of new energy vehicles, the problems of declining brand characteristics and market competitiveness are solved, and the brand recognition and market share are improved.

CN117421827BActive Publication Date: 2024-11-05QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202311488481.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-09
Publication Date
2024-11-05
Estimated Expiration
2043-11-09

AI Technical Summary

Technical Problem

In the design of new energy vehicles, it is difficult for the existing technology to effectively evaluate and maintain the family design characteristics of the car brand, resulting in a decline in brand recognition and market competitiveness.

Method used

By obtaining the genes of the car brand, extracting identification information data, calculating identification coefficients, and generating feature identification coefficients, we can achieve the effectiveness of the family design of new automobile products, and ensure the continuation and inheritance of brand characteristics in the product iteration process.

Benefits of technology

It has improved the market share and brand vitality of automobile brands in the process of product iteration, ensured that new products had brand characteristics, and enhanced brand recognition and market competitiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117421827B_ABST
    Figure CN117421827B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of automobile design technology, and in particular, provides an evaluation method, device and electronic device for automobile family design. The method includes obtaining the brand gene of the automobile, and obtaining identification information data according to the brand gene; calculating the identification coefficient according to the identification information data; generating the characteristic identification coefficient of the automobile according to the identification coefficient. In the process of generating the characteristic identification coefficient, the effectiveness evaluation of the family design of new automobile products is realized in the present application, so as to produce new products with brand characteristics, and enable the family characteristics of automobile brands to be effectively continued and inherited in the process of product replacement, so as to ensure that the automobile brand maintains market share and brand vitality in the process of product iteration.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of automobile design, and in particular to an evaluation method, device and electronic equipment for automobile family design. Background Art

[0002] The technological innovation of the automobile industry and the shortage of fuel resources have led to the emergence of new energy vehicles, an epoch-making type of automobile. The appearance of early new energy vehicles was basically the same as that of fuel vehicles. As the requirements for new energy vehicles on speed, endurance and other performance gradually increased, new design directions began to emerge in their appearance.

[0003] Family design is applied to the development of new platform models and cross-family product design. The recognition of the front face design of the family of automobiles and the acceptance of the target group are explored from the user's perspective, so that the appearance designers can get timely feedback from the user group in the development of new products. Evaluating new design plans from the consumer's perspective avoids the subjectivity of designers in the process of designing cross-family and cross-platform products, maintains the continuity of brand characteristics in the design of cross-family and cross-platform new products, facilitates the construction of communication links between brands and consumers, and improves brand recognition and market competitiveness. Based on the inherent needs of stimulating the market and increasing sales, automobile manufacturers need to update the appearance of existing models in a timely manner. Summary of the invention

[0004] In view of this, the present invention provides an evaluation method, device and electronic equipment for automobile family design, which are used to extract representative family features from successive generations of automobile brand products, and produce new products with brand features, so that the automobile brand family features can be effectively continued and inherited during the product replacement process, so as to ensure that the automobile brand maintains its market share and brand vitality during the product iteration process, and improve the effectiveness evaluation of the family design of new automobile products.

[0005] In a first aspect, the present invention provides a method for evaluating automobile family design, the method comprising:

[0006] Acquire the brand gene of the car, and acquire identification information data according to the brand gene;

[0007] Calculating an identification coefficient according to the identification information data;

[0008] A characteristic recognition coefficient of the vehicle is generated according to the recognition coefficient.

[0009] Optionally, before obtaining the brand gene of the car and obtaining identification information data according to the brand gene, the process further includes:

[0010] Collect several front face pictures of electric vehicles of the same model and other brands as comparison samples, and collect front face pictures of reference fuel vehicles of the same model and brand as the target electric vehicle to be tested, and use them as reference samples;

[0011] According to the comparison of the electric vehicle front face pictures and the reference fuel vehicle front face pictures, a variety of perceptual words are collected.

[0012] Optionally, the brand gene includes a dominant gene; the identification information data includes dominant gene identification information data; and obtaining the identification information data according to the brand gene includes:

[0013] According to the dominant gene, a plurality of comparison front face pictures of electric vehicles and reference front face pictures of fuel vehicles are extracted;

[0014] A plurality of the comparison electric vehicle front face pictures, the reference fuel vehicle front face pictures and the target electric vehicle front face pictures are compared on the same screen through an eye tracking experiment to obtain dominant gene identification information data.

[0015] Optionally, the brand gene includes a recessive gene; the identification information data includes recessive gene identification information data; and obtaining the identification information data according to the brand gene includes:

[0016] Select a front face picture of the target electric vehicle to be tested, and a front face picture of a reference fuel vehicle of the same model and brand as the target electric vehicle to be tested;

[0017] According to the front face picture of the target electric vehicle to be tested and the front face picture of the reference fuel vehicle, corresponding perceptual words are selected through a questionnaire survey;

[0018] According to the scores corresponding to the perceptual words, the recessive gene identification information data of the target electric vehicle to be tested and the reference fuel vehicle are calculated.

[0019] Optionally, the calculating the identification coefficient according to the identification information data includes: calculating the dominant gene identification coefficient according to the dominant gene identification information data;

[0020] The formula of the dominant gene identification coefficient D is as follows:

[0021]

[0022] Among them, G n The average attention ratio of fuel vehicles is E n The average fixation ratio of the target electric vehicle to be tested in the eye tracking experiment is the reference fuel vehicle, and ΔE is the sum of the ratios of all target electric vehicles to be tested in the eye tracking experiment.

[0023] Optionally, the calculating the identification coefficient according to the identification information data includes: calculating the recessive gene identification coefficient according to the recessive gene identification information data;

[0024] The formula of the recessive gene identification coefficient R is as follows:

[0025]

[0026] Among them, N is the total number of implicit features, G represents the reference fuel vehicle sample, E represents the target electric vehicle sample to be tested, and μ is the data mean of the sample in the nth pair of perceptual words.

[0027] In a second aspect, the present invention provides an evaluation device for automobile family design, the device comprising:

[0028] An acquisition module, used to acquire the brand gene of the car, and acquire identification information data according to the brand gene;

[0029] A calculation module, used to calculate the identification coefficient according to the identification information data;

[0030] A generating module is used to generate a characteristic recognition coefficient of the vehicle according to the recognition coefficient.

[0031] Optionally, it also includes:

[0032] The collection module is used to collect a number of comparison electric vehicle front face pictures of the same model and other brands, and use them as comparison samples, as well as reference fuel vehicle front face pictures of the same model and brand corresponding to the target electric vehicle to be tested, and use them as reference samples; based on the target electric vehicle front face pictures to be tested and the reference fuel vehicle front face pictures, a variety of perceptual words are collected.

[0033] In a third aspect, the present invention provides a computer-readable storage medium, comprising a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the evaluation method for identifying automobile family design in the first aspect or any possible implementation of the first aspect.

[0034] In a fourth aspect, the present invention provides an electronic device comprising: one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, enable the device to execute the evaluation method for identifying automobile family design in the first aspect or any possible implementation of the first aspect.

[0035] In the technical solution provided by the present invention, the method includes obtaining the brand gene of the automobile, and obtaining identification information data based on the brand gene; calculating the identification coefficient based on the identification information data; generating the characteristic identification coefficient of the automobile based on the identification coefficient. In the process of generating the characteristic identification coefficient, the effectiveness evaluation of the family design of new automobile products is realized in the present application, so as to produce new products with brand characteristics, and enable the family characteristics of automobile brands to be effectively continued and inherited during the product replacement process, so as to ensure that the automobile brand maintains market share and brand vitality during the product iteration process. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A flow chart of a method for evaluating automobile family design provided by an embodiment of the present invention;

[0038] Figure 2 Picture samples of eye tracking experiments for obtaining dominant genes provided by the embodiments of the present invention;

[0039] Figure 3 A schematic diagram of a method for acquiring perceptual vocabulary provided by an embodiment of the present invention;

[0040] Figure 4 A heat map of an eye tracking experiment provided by an embodiment of the present invention;

[0041] Figure 5 A schematic diagram of an evaluation device for automobile family design provided by an embodiment of the present invention;

[0042] Figure 6 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 the present invention.

[0044] It should be clear that 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 the present invention.

[0045] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0046] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0047] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0048] Figure 1 A flowchart of the evaluation method for automobile family design provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0049] Step 11: Obtain the brand gene of the car, and obtain identification information data based on the brand gene.

[0050] The essence of a brand is that the brand owner's products, services or other advantages over competitors can bring equal or higher value to the target audience. For enterprises, "brand" is an intangible asset with economic value. Through long-term operation, publicity and promotion, it can generate abstract, unique and recognizable cognitive concepts in consumers' cognition, subtly influence the target population and produce reactions in consciousness and behavior.

[0051] Brand genes are embedded in the elements, information and corresponding services of products. They can represent the core values ​​and cultural concepts of the brand. They carry a variety of genetic information including genes of enterprises, products, culture, etc. and are a knowledge system with significant genetic and evolutionary variation characteristics.

[0052] The brand genes of products are divided into dominant genes and recessive genes: dominant genes have physical entity properties and can be perceived by human vision, touch, hearing, smell and other sensory systems, mainly through the product's appearance, color, material texture, auxiliary patterns, sound, smell and other dominant characteristic elements; recessive genes cannot be perceived by the human sensory system, but can be described and expressed through language or behavior. They are the extraction and condensation of the core values ​​and cultural concepts of the enterprise, and often constrain and guide the expression, inheritance and variation of dominant genes. Recessive genes and dominant genes map to each other and jointly determine the identification attributes of the product brand.

[0053] Brand genes drive family design. As the upper concept of family design, brand genes have dynamic and adaptable attributes. In the design of cross-platform products, there will be different forms of manifestation, but they will always give the target user group a relatively unified cognitive experience.

[0054] In the embodiment of the present invention, each step may be performed by an electronic device, such as a tablet computer, a portable PC, a desktop PC, etc.

[0055] In the embodiment of the present invention, the brand gene includes a dominant gene; the identification information data includes dominant gene identification information data; and obtaining the identification information data according to the brand gene includes:

[0056] Step 111: extract multiple comparison pictures of the front face of electric vehicles and reference pictures of the front face of fuel vehicles according to the dominant gene.

[0057] Step 112: compare the plurality of comparison electric vehicle front face pictures, the reference fuel vehicle front face pictures and the target electric vehicle front face pictures on the same screen through an eye tracking experiment to obtain dominant gene identification information data.

[0058] Figure 2 The picture samples of the eye tracking experiment for obtaining dominant genes provided by the embodiment of the present invention are as follows: Figure 2 As shown in the figure, the car models of the image samples are all SUV models. Each stimulus page of the eye tracking experiment contains a front face picture of a reference fuel car (G original brand picture), a front face picture of the target electric car to be tested (E original brand picture), both of which should be of the same model product brand, and three comparison electric car pictures of the same model of other brands (E comparison 1 picture, E comparison 2 picture and E comparison 3 picture). Figure 3 All the front face images involved in the experiment were decolorized and the car logos were erased to reduce the impact of the car logos on the recognition of front face features. The four electric vehicle samples on the right were arranged in a Latin square, and the experimental measurements were repeated four times to obtain valid experimental data.

[0059] For the first stage of the eye tracking experiment, the Latin square repeated intensity superposition process was used to analyze the automated optical inspection (AOI) and gaze hotspot data, and calculate the family feature recognition of the brand's new products in the generation change stage.

[0060] Latin square design is a technique to balance the order of experiments to reduce the impact of the experimental order on the experiment. It uses a Latin square as an aid, which is a square matrix consisting of several variables that need to be sorted. Its specific application process is as follows: When the number of treatments is an even number, the order is determined as follows: horizontal row: 1, 2, X, 3, X-1, 4, X-2... (X represents the number of quantities to be sorted), and the subsequent order is to add "1" to the number of the first order until a Latin square is formed.

[0061] Use Latin square design to balance the order of variable blocks and reduce the experimental error caused by the order. In Latin square design, the position of the experimental sample in the Latin square diagram will change each time.

[0062] As an effective means of obtaining users' understanding of design objects, eye tracking technology makes implicit knowledge that is difficult to express explicit, forming a knowledge system required for design. Through the analysis and conversion of data such as heat maps, average fixation time, fixation time, number of fixations, and areas of interest, the visual appeal of the front face styling features of the car to consumers is obtained, forming intuitive comparative data.

[0063] In the embodiment of the present invention, the eye tracking experiment data types include: average fixation duration, average number of fixation points, and AOI area of ​​interest division.

[0064] In the embodiment of the present invention, the brand gene includes a recessive gene; the identification information data includes recessive gene identification information data; and obtaining the identification information data according to the brand gene includes:

[0065] Step 113: Select a target electric vehicle to be tested and a reference fuel vehicle front face picture of the same model and brand as the target electric vehicle to be tested.

[0066] Step 114: According to the front face picture of the target electric vehicle to be tested and the front face picture of the reference fuel vehicle, corresponding perceptual words are selected through a questionnaire survey.

[0067] Step 115: Calculate the implicit gene identification information data of the target electric vehicle to be tested and the reference fuel vehicle according to the scores corresponding to the perceptual words.

[0068] Step 12: Calculate the recognition coefficient based on the recognition information data.

[0069] In the embodiment of the present invention, calculating the identification coefficient according to the identification information data includes: calculating the dominant gene identification coefficient according to the dominant gene identification information data.

[0070] For the experiment on the strength of brand dominant gene recognition, the experimental hypothesis is: the higher the ratio of the eye tracking time of the target electric vehicle to other electric vehicle samples, and the higher the characteristic recognition coefficient ratio of the target electric vehicle samples to other electric vehicle samples, the higher the characteristic recognition coefficient ratio should be, indicating that the characteristics are obvious enough and the family characteristics are significant enough. The experimental results are shown in Table 1.

[0071] Table 1

[0072]

[0073] It can be seen from Table 1 that the familial characteristics group C>group B>group A>group D.

[0074] The formula for the dominant gene identification coefficient D is as follows:

[0075]

[0076] Among them, G n The average attention ratio of fuel vehicles is E n The average fixation ratio of the target electric vehicle to be tested in the eye tracking experiment is compared with the fuel vehicle, and ΔE is the sum of the ratios of all target electric vehicle samples to be tested in the eye tracking experiment.

[0077] As shown in Tables 2 and 3, Exploration of the correlation between the two ratios:

[0078]

[0079] From Table 2 and Table 3, we can see that: the statistical analysis (SPSS) of multiple groups of data from the previous test The two sets of values ​​were subjected to correlation analysis, and the results were all greater than 0.8, showing a significant correlation, and the two-tailed test was less than 0.05, indicating that the hypothesis was correct and that the two had a certain positive correlation.

[0080] Therefore, it can be and The product of and expresses the recognition coefficient D of the dominant gene, where the larger the value of D is, the stronger the recognition of the dominant gene is.

[0081] In the embodiment of the present invention, calculating the identification coefficient according to the identification information data includes: calculating the recessive gene identification coefficient according to the recessive gene identification information data, and the values ​​of the four groups of samples are shown in Table 4.

[0082] Table 4

[0083]

[0084] It can be seen from Table 4 that the smaller the R value, the better the implicit feature recognition strength.

[0085] The formula for the recessive gene recognition coefficient R is as follows:

[0086]

[0087] Among them, N is the total number of implicit features, G represents the reference fuel vehicle sample, E represents the target electric vehicle sample to be tested, and μ is the data mean of the sample in the nth pair of perceptual words.

[0088] In the embodiment of the present invention, the recessive genes of the brand and the personalized genes unique to the brand in products on different platforms (i.e., the product intention characteristics of "fuel vehicles" and "electric vehicles", respectively) are analyzed, and the recessive feature recognition coefficient is obtained based on the difference in data.

[0089] In the embodiment of the present invention, the difference between dominant genes and recessive genes in the generation process is the main research point. The dominant gene difference is manifested as the dominant feature recognition coefficient D during the eye tracking experiment, and there is no need to clearly obtain the specific dominant gene of the target brand; the same is true for recessive genes.

[0090] Step 13: Generate a characteristic recognition coefficient of the car according to the recognition coefficient.

[0091] In the embodiment of the present invention, the feature identification coefficient I g Specific quantitative relationship with D and R:

[0092] I g ={D, R}

[0093] The larger the value of D, the stronger the recognition of the dominant gene; the smaller the value of R, the stronger the recognition of the recessive gene. Since the two support each other and jointly build the overall brand gene, their interaction has not yet been clearly defined, and here we use the collective method to represent the individual brand gene recognition.

[0094] In the embodiment of the present invention, before step 11, the following steps are further included:

[0095] Step S1, collecting a number of front face pictures of comparison electric vehicles of the same model and other brands, and using them as comparison samples, as well as front face pictures of reference fuel vehicles of the same model and brand corresponding to the target electric vehicle to be tested, and using them as reference samples.

[0096] In an embodiment of the present invention, the brightness and contrast of the front face picture of an electric vehicle and the reference fuel vehicle are adjusted to allow more details to be seen, and the pictures are decolored and the brightness is unified to avoid attention bias caused by the color and brightness difference, and vehicle logos, license plates and other signs are erased, and the effectiveness of the new product family design is tested.

[0097] Step S2: Collect multiple perceptual words by comparing the front face pictures of electric vehicles and referring to the front face pictures of fuel vehicles.

[0098] In the embodiment of the present invention, the perceptual vocabulary may be used to describe the intended style of an electric vehicle or a fuel vehicle. For example, the perceptual vocabulary includes but is not limited to domineering, implicit, simple, complex, steady, dynamic, mellow, sharp, innovative, and classic.

[0099] Figure 3 A schematic diagram of a method for acquiring perceptual vocabulary provided by an embodiment of the present invention, such as Figure 3 As shown in the figure, the ways to acquire perceptual vocabulary include linguistic perspective, user perspective and enterprise perspective. Among them, from the linguistic perspective: the semantic difference method is used as the theoretical and methodological basis, and the literature survey method is used to obtain the etymology of adjectives. The etymology is generally required to be broad enough to ensure that the domain semantic space can be sampled more comprehensively. On this basis, a series of filtering mechanisms are used to delete and filter the redundant and repeated adjective information in the semantic space. Then, a series of semantic adjective surveys are conducted on enterprise personnel, designers, and users to obtain adjectives suitable for describing car styling.

[0100] User perspective: Conduct an open-ended questionnaire survey on typical users to guide them to describe their understanding and feelings about the product brand, their evaluation and suggestions on the product appearance, and their experience using the product. Then, through a series of word frequency statistics and cluster analysis, we obtain the brand semantic description vocabulary.

[0101] Enterprise perspective: Interview enterprise managers, marketing personnel, etc. to obtain the understanding and feelings of the enterprise's internal brand semantic characteristics. In addition, the advertising slogans of enterprise products should be analyzed and studied to obtain the brand semantic characteristics reflected in the advertising slogans.

[0102] Kansei engineering is implemented as a means to obtain the core descriptors of a brand. By quantifying the intention evaluation of the subjects, Kansei engineering will include fuzzy images such as personal experience, memories, and imagination, and form specific images through conscious activities, and express them in concrete ways such as language, text, and patterns. It is a theory that concretizes the user's abstract sensory characteristic factors into quantitative data and applies them to product design.

[0103] Semantic differential method is used as a means to quantify implicit features. The semantic differential method extracts perceptual words that measure users' psychological feelings, reflects their abstract perceptions on the Likert scale, and uses statistical methods to analyze its rules. Usually, semantic scales are used to subjectively score perceptual words that are antonyms to each other, and quantitative data is constructed between product shape and perceptual words.

[0104] In the embodiment of the present invention, the replacement process from fuel vehicles to electric vehicles is taken as an example to illustrate the basic implementation method of the present invention. According to the brand gene and family design concept, if the products of a certain brand follow the family appearance design concept, then its platform models should be able to reflect certain family characteristics. Therefore, it is only necessary to consider the differences in the family design methods expressed by a certain brand in the same model during the replacement period from fuel vehicles to electric vehicles, so as to derive the advantages and disadvantages of the brand's family inheritance and expression in the product replacement appearance design. Here, the present invention selects four brands and their corresponding fuel models and electric models in SUV models to conduct eye tracking experiments. Through comparative identification, the clarity and effectiveness of their family design expression are judged to obtain user preferences and acceptance of different types of products of the same brand.

[0105] Figure 4 A heat map of an eye tracking experiment provided by an embodiment of the present invention, such as Figure 4 As shown, it is obtained from the eye tracking experiment, which can intuitively display the visual hotspots, and the recognition coefficient of the dominant gene of the new product can be calculated from the data.

[0106] In the embodiment of the present invention, Table 5 is an example of a questionnaire survey for obtaining recessive genes, and the descriptive words used for evaluation are selected from Kansei engineering theories and methods and are representative.

[0107] Table 5

[0108]

[0109] As shown in Table 5, using the Likert five-level or seven-level scale, the recessive gene description differences between the reference fuel vehicle and the target electric vehicle product to be tested are obtained through comparative evaluation, and the recognition coefficient of the recessive gene is obtained through data analysis.

[0110] The embodiments of the present invention help enterprises to make adaptive adjustments to family-based products in the process of designing new products, so that the family-based characteristics of enterprises can be continued. For mature brands, it helps to reduce the risk of product research and development in new fields, occupy market share in a timely manner, and ensure the leading position in the industry; for developing brands, it can help enterprises keep up with the market rhythm in a timely manner and achieve smooth transformation while continuing brand characteristics.

[0111] In the technical solution of the evaluation method for automobile family design provided by the present invention, the method includes obtaining the brand gene of the automobile, and obtaining identification information data based on the brand gene; calculating the identification coefficient based on the identification information data; generating the characteristic identification coefficient of the automobile based on the identification coefficient. In the process of generating the characteristic identification coefficient, the effectiveness evaluation of the family design of new automobile products is realized in the present application, so as to produce new products with brand characteristics, and enable the automobile brand family characteristics to be effectively continued and inherited during the product replacement process, so as to ensure that the automobile brand maintains market share and brand vitality during the product iteration process.

[0112] Figure 5 A schematic diagram of an evaluation device for automobile family design provided by an embodiment of the present invention, such as Figure 5 As shown, the device includes: an acquisition module 1, a calculation module 2 and a generation module 3.

[0113] The acquisition module 1 is connected to the calculation module 2, and the calculation module 2 is connected to the generation module 3.

[0114] The acquisition module 1 is used to acquire the brand gene of the car and obtain identification information data according to the brand gene; the calculation module 2 is used to calculate the identification coefficient according to the identification information data; the generation module 3 is used to generate the characteristic identification coefficient of the car according to the identification coefficient.

[0115] In the embodiment of the present invention, it also includes:

[0116] The collection module is used to collect a number of front face pictures of electric vehicles of the same model and other brands as comparison samples, and the front face pictures of reference fuel vehicles of the same model and brand corresponding to the target electric vehicle to be tested, and use them as reference samples; based on the front face pictures of the target electric vehicle to be tested and the reference fuel vehicle front face pictures, a variety of perceptual words are collected.

[0117] In the embodiment of the present invention, the brand gene includes a dominant gene; the identification information data includes dominant gene identification information data; the acquisition module 1 includes:

[0118] The extraction submodule 11 is used to extract multiple comparison electric vehicle front face pictures and reference fuel vehicle front face pictures according to the dominant gene; the acquisition submodule 12 compares the multiple comparison electric vehicle front face pictures, the reference fuel vehicle front face pictures and the target electric vehicle front face pictures on the same screen through an eye tracking experiment to obtain dominant gene identification information data.

[0119] In the embodiment of the present invention, the brand gene includes a recessive gene; the identification information data includes recessive gene identification information data; the acquisition module 1 includes:

[0120] The screening submodule 13 is used to select a front face picture of the target electric vehicle to be tested and a front face picture of a reference fuel vehicle of the same model and brand as the target electric vehicle to be tested; the selection submodule 14 is used to select corresponding perceptual words based on the front face pictures of the target electric vehicle to be tested and the reference fuel vehicle; the calculation submodule 15 is used to calculate the recessive gene identification information data of the target electric vehicle to be tested and the reference fuel vehicle based on the scores corresponding to the perceptual words.

[0121] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the computer-readable storage medium is controlled to execute an embodiment of the above-mentioned evaluation method for automobile family design.

[0122] Figure 6 A schematic diagram of an electronic device provided by an embodiment of the present invention, such as Figure 6 As shown, the electronic device 21 includes: a processor 211, a memory 212, and a computer program 213 stored in the memory 212 and executable on the processor 211. When the computer program 213 is executed by the processor 211, the evaluation method for automobile family design in the embodiment is implemented. To avoid repetition, they are not described one by one here.

[0123] The electronic device 21 includes, but is not limited to, a processor 211 and a memory 212. Those skilled in the art will appreciate that Figure 6 It is only an example of the electronic device 21 and does not constitute a limitation of the electronic device 21. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0124] The processor 211 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0125] The memory 212 may be an internal storage unit of the electronic device 21, such as a hard disk or memory of the electronic device 21. The memory 212 may also be an external storage device of the electronic device 21, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 21. Further, the memory 212 may also include both an internal storage unit of the electronic device 21 and an external storage device. The memory 212 is used to store computer programs and other programs and data required by network devices. The memory 212 may also be used to temporarily store data that has been output or is to be output.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for evaluating automobile family design, characterized in that: The method comprises: Acquire the brand gene of the car, and acquire identification information data according to the brand gene; Calculating an identification coefficient according to the identification information data; generating a characteristic recognition coefficient of the vehicle according to the recognition coefficient; The brand gene includes a dominant gene; the identification information data includes dominant gene identification information data; obtaining the identification information data according to the brand gene includes: Step 111, extracting a plurality of comparison electric vehicle front face pictures and reference fuel vehicle front face pictures according to the dominant gene; Step 112, a plurality of comparison electric vehicle front face pictures, reference fuel vehicle front face pictures and target electric vehicle front face pictures are compared on the same screen through an eye tracking experiment to obtain dominant gene identification information data; The brand gene includes a recessive gene; the identification information data includes recessive gene identification information data; and obtaining the identification information data according to the brand gene includes: Step 113: selecting a target electric vehicle to be tested and a reference fuel vehicle front face picture of the same model and brand as the target electric vehicle to be tested; Step 114, selecting corresponding perceptual words through a questionnaire survey according to the front face picture of the target electric vehicle to be tested and the front face picture of the reference fuel vehicle; Step 115, calculating the implicit gene identification information data of the target electric vehicle to be tested and the reference fuel vehicle according to the scores corresponding to the perceptual words; The calculating the identification coefficient according to the identification information data includes: Calculate the dominant gene identification coefficient based on the dominant gene identification information data; calculate the recessive gene identification coefficient based on the recessive gene identification information data; The formula for the dominant gene identification coefficient D is as follows: ; in, To refer to the average attention share of fuel vehicles, To refer to the average fixation ratio of the target electric vehicle in the eye tracking experiment, It is the sum of the proportions of all target electric vehicle samples in eye tracking; The formula for the recessive gene recognition coefficient R is as follows: ; Among them, N is the total number of implicit features, G represents the reference fuel vehicle sample, E represents the target electric vehicle sample to be tested, and μ is the data mean of the sample in the nth pair of perceptual words; The step of generating a characteristic recognition coefficient of the automobile according to the recognition coefficient comprises: The specific quantitative relationship between the characteristic identification coefficient Ig and D and R is: Ig = {D, R}; Among them, the larger the D value, the stronger the recognition of the explicit gene; the smaller the R value, the stronger the recognition of the recessive gene.

2. The evaluation method according to claim 1, characterized in that: Before obtaining the brand gene of the automobile and obtaining identification information data according to the brand gene, the method further includes: Collect several front face pictures of electric vehicles of the same model and other brands as comparison samples, and collect front face pictures of reference fuel vehicles of the same model and brand as the target electric vehicle to be tested, and use them as reference samples; A plurality of perceptual words are collected based on the front face picture of the target electric vehicle to be tested and the front face picture of the reference fuel vehicle.

3. An evaluation device for automobile family design, characterized in that: The device comprises: An acquisition module, used to acquire the brand gene of the car, and acquire identification information data according to the brand gene; A calculation module, used to calculate the identification coefficient according to the identification information data; A generating module, used for generating a characteristic identification coefficient of a car according to the identification coefficient; The brand gene includes a dominant gene; the identification information data includes dominant gene identification information data; the acquisition module is specifically used to extract a plurality of comparison electric vehicle front face pictures and reference fuel vehicle front face pictures according to the dominant gene; compare the plurality of comparison electric vehicle front face pictures, reference fuel vehicle front face pictures and target electric vehicle front face pictures on the same screen through an eye tracking experiment to obtain dominant gene identification information data; The brand gene includes a recessive gene; the identification information data includes recessive gene identification information data; the acquisition module is specifically used to select a target electric vehicle to be tested and a reference fuel vehicle front face picture of the same model and brand as the target electric vehicle to be tested; according to the front face picture of the target electric vehicle to be tested and the front face picture of the reference fuel vehicle, corresponding perceptual words are selected through a questionnaire survey; according to the scores corresponding to the perceptual words, the recessive gene identification information data of the target electric vehicle to be tested and the reference fuel vehicle are calculated; The calculation module is specifically used to calculate the dominant gene identification coefficient according to the dominant gene identification information data; calculate the recessive gene identification coefficient according to the recessive gene identification information data; The formula for the dominant gene identification coefficient D is as follows: ; in, To refer to the average attention share of fuel vehicles, To refer to the average fixation ratio of the target electric vehicle in the eye tracking experiment, It is the sum of the proportions of all target electric vehicle samples in eye tracking; The formula for the recessive gene recognition coefficient R is as follows: ; Among them, N is the total number of implicit features, G represents the reference fuel vehicle sample, E represents the target electric vehicle sample to be tested, and μ is the data mean of the sample in the nth pair of perceptual words; The generation module specifically includes the specific quantitative relationship between the feature identification coefficient Ig and D and R: Ig = {D, R}; Among them, the larger the D value, the stronger the recognition of the explicit gene; the smaller the R value, the stronger the recognition of the recessive gene.

4. The evaluation device according to claim 3, characterized in that Also includes: The collection module is used to collect a number of comparison electric vehicle front face pictures of the same model and other brands, and use them as comparison samples, as well as reference fuel vehicle front face pictures of the same model and brand corresponding to the target electric vehicle to be tested, and use them as reference samples; based on the target electric vehicle front face pictures to be tested and the reference fuel vehicle front face pictures, a variety of perceptual words are collected.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute an evaluation method for automobile family design according to any one of claims 1 to 2.

6. An electronic device, characterized in that: include: one or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, enable the device to execute an evaluation method for automobile family design as described in any one of claims 1 to 2.

Citation Information

Patent Citations

  • Automobile brand gene analyzing method based on front face style

    CN106096144A

  • Product preference image recognition system and method under visual cognition neural mechanism

    CN109567831A

  • Automobile front face brand familialization analysis method

    CN110533093A

  • KR20210028456A