Hybrid vehicle design method and system based on grey correlation

Abstract

The present application discloses a hybrid vehicle design method and system based on grey correlation, which belongs to the technical field of vehicle optimization design, wherein the method comprises: collecting consumers' emotional attribute sets for hybrid vehicles, and establishing corresponding product attribute sets. Then, the emotional attribute set is dimensionally simplified, and the product attribute set is decomposed. Then, a decision table is constructed, and the simplified emotional attribute set is used as the decision attribute set, and the product sub-attribute set is used as the conditional attribute set. The importance of each conditional attribute to each decision attribute is calculated using the importance algorithm. After that, a quality house matrix is ​​constructed, the importance is imported and the correlation relationship is obtained. Finally, the simplified emotional attribute set is used as the reference sequence set, and the product sub-attribute set is subjected to grey correlation analysis to obtain the grey correlation and ranking of each product sub-attribute, and the hybrid vehicle is designed and optimized accordingly.

Description

Technical Field

[0001] The present application belongs to the field of vehicle optimization design, and specifically relates to a hybrid vehicle design method and system based on grey correlation. Background Art

[0002] With the changing times and the development of science and technology, people pay more and more attention to the charm of new products and the subjective feelings that products bring to people. In a highly saturated consumer environment, companies must continue to develop new products to meet the rapidly changing market demand in order to continue to operate. Especially in today's era of user experience, corporate production has shifted from function-oriented to customer-oriented. Through the analysis of user emotional responses, the design team can better optimize the product to make it more in line with user expectations in terms of appearance, texture, interaction methods, etc.; how to help designers quickly obtain the key content of customer emotional preferences and provide designers with more complete product feature references has become one of the focuses of global design research institutes.

[0003] At present, in the traditional design method process, designers rely on personal preferences and aesthetic experience to make decisions and ignore customers' suggestions and ideas, which makes the designed car models unpopular with consumers and leads to losses. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a hybrid vehicle design method and system based on grey correlation, which can solve the problem that in the traditional design method process, designers ignore customers' suggestions and ideas, resulting in the designed car models being unpopular with consumers, thus leading to losses.

[0005] In order to solve the above technical problems, this application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a hybrid vehicle design method based on grey correlation, the method comprising:

[0007] Acquire consumers' emotional attribute set for hybrid vehicles, establish a product attribute set of the hybrid vehicle according to a morphological analysis method, perform dimensionality reduction on the emotional attribute set to obtain a reduced emotional attribute set, and decompose the product attribute set to obtain a product sub-attribute set;

[0008] Constructing a decision table, using the simplified sentiment attribute set and the product sub-attribute set as the decision attribute set and condition attribute set of the decision table respectively, and obtaining the importance of each condition attribute to each decision attribute in the decision table according to an importance algorithm;

[0009] Constructing a quality house matrix, wherein the quality house matrix uses the simplified emotional attribute set as a left wall and the product sub-attribute set as a ceiling, importing the importance into the quality house matrix, and obtaining the correlation relationship of the quality house matrix;

[0010] The simplified sentiment attribute set is used as a reference sequence set, and the product sub-attribute set is used as a comparison sequence set. According to the association relationship of the quality house matrix, a grey correlation degree analysis is performed on the comparison sequence set to obtain the grey correlation degree of each product sub-attribute in the product sub-attribute set;

[0011] According to the grey correlation degree of each product sub-attribute, the ranking of each product sub-attribute in the product sub-attribute set is obtained, so as to design a hybrid vehicle according to the ranking of each product sub-attribute.

[0012] As an optional implementation manner of the first aspect of the present application, the emotional attribute set of consumers for hybrid vehicles is obtained, a product attribute set of the hybrid vehicle is established according to a morphological analysis method, the emotional attribute set is dimensionally simplified to obtain a simplified emotional attribute set, and the product attribute set is decomposed to obtain a product sub-attribute set; specifically:

[0013] Acquire multiple emotional attributes of consumers toward hybrid vehicles, and filter the multiple emotional attributes to obtain the emotional attribute set;

[0014] According to the grey prediction model and by analyzing and sorting the sentiment attribute set, the top N sentiment attributes in the sentiment attribute set are selected to construct the simplified sentiment attribute set;

[0015] Acquire multiple hybrid vehicle model images of different types, and filter the multiple hybrid vehicle model images of different types to obtain a hybrid vehicle model image set;

[0016] performing a cluster analysis on the hybrid vehicle model image set, and dividing the hybrid vehicle model image set into a plurality of hybrid vehicle model image subsets;

[0017] Selecting one hybrid vehicle model image from each of the hybrid vehicle model image subsets to form a target hybrid vehicle model image set; deconstructing the target hybrid vehicle model image set to obtain the product attribute set;

[0018] In the product attribute set, each product attribute is decomposed into a plurality of product sub-attributes, and a product sub-attribute set is constructed according to the plurality of product sub-attributes.

[0019] As an optional implementation of the first aspect of the present application, the decision table is constructed, the simplified sentiment attribute set and the product sub-attribute set are used as the decision attribute set and the condition attribute set of the decision table respectively, and the importance of each condition attribute in the decision table to each decision attribute is obtained according to the importance algorithm; specifically:

[0020] Constructing a decision table, inputting the simplified sentiment attribute set as the decision attribute set into the decision table, and inputting the product sub-attribute set as the condition attribute set into the decision table;

[0021] The condition attribute set and the decision attribute set are processed according to an importance algorithm to obtain the importance of each condition attribute to each decision attribute in the decision table.

[0022] As an optional implementation of the first aspect of the present application, the importance algorithm is expressed by the following formula:

[0023] ,

[0024] in, Represents a conditional attribute set, Represents the first decision attributes, Represents a conditional attribute in a conditional attribute set. Represents conditional attributes right The importance of express right The dependency relationship, express right The dependency relationship, Represents conditional attributes The set composed of represents a finite non-empty set, express The number of elements of express exist The positive domain below, express The number of elements of express By the equivalence relation Decide on the division, represents the lower approximation set, yes A subset of yes The elements in Represents a set union operation.

[0025] As an optional implementation of the first aspect of the present application, the quality house matrix is ​​constructed, the quality house matrix uses the simplified emotional attribute set as the left wall and the product attribute set as the ceiling, imports the importance into the quality house matrix, and obtains the association relationship of the quality house matrix; specifically:

[0026] Constructing a quality house framework, inputting the simplified sentiment attribute set and the product sub-attribute set into the quality house framework as the left wall and ceiling of the quality house framework respectively, and importing the importance into the quality house framework to obtain the quality house matrix;

[0027] Acquire the link strength between each of the condition attributes and each of the decision attributes according to the data mining software, and obtain a link strength set corresponding to each of the condition attributes;

[0028] According to the link strength set corresponding to each of the condition attributes, the association relationship between the left wall and the ceiling in the house of quality matrix is ​​obtained.

[0029] As an optional implementation of the first aspect of the present application, the simplified emotional attribute set is used as a reference sequence set, the product sub-attribute set is used as a comparison sequence set, and the comparison sequence set is subjected to grey correlation analysis according to the correlation relationship of the quality house matrix to obtain the grey correlation degree of each product sub-attribute in the product sub-attribute set; specifically:

[0030] Normalizing the simplified sentiment attribute set and the product sub-attribute set, using the normalized simplified sentiment attribute set as a reference sequence set, and using the normalized product sub-attribute set as a comparison sequence set;

[0031] constructing a normalized matrix based on the reference sequence set and the comparison sequence set;

[0032] Calculating the absolute difference between each reference sequence and each comparison sequence in the normalized matrix according to a difference algorithm;

[0033] According to the grey relational degree algorithm, the absolute difference between each reference sequence and each comparison sequence is processed to obtain the grey relational degree of the comparison sequence set.

[0034] As an optional implementation of the first aspect of the present application, the product sub-attribute set is normalized as follows:

[0035] ,

[0036] in, Indicates the first Ledi The elements of the row, Indicates the product sub-attribute set Ledi The elements of the row, Indicates the product sub-attribute set The smallest element in the row, Indicates the product sub-attribute set The largest element in the row;

[0037] The normalization process of the simplified sentiment attribute set is as follows:

[0038] ,

[0039] in, Indicates the reference sequence set elements, Indicates the first elements, Indicates the first The absolute value of the elements, Indicates the total number of elements in the simplified sentiment attribute set;

[0040] The difference algorithm is expressed by the following formula:

[0041] ,

[0042] in, Indicates the first Ledi The elements of the row are the same as the reference sequence The absolute difference of the elements, Indicates the reference sequence set elements;

[0043] The grey relational degree algorithm is expressed by the following formula:

[0044]

[0045] ,

[0046] in, Indicates the product sub-attribute set The grey correlation degree of each product sub-attribute, Indicates the comparison sequence set Ledi Grey correlation coefficient of row elements, Indicates the minimum absolute difference in the comparison sequence set. Indicates the maximum absolute difference in the comparison sequence set. Represents the resolution factor.

[0047] In a second aspect, an embodiment of the present application provides a hybrid vehicle design system based on grey correlation, the system comprising:

[0048] Acquisition module: acquiring the emotional attribute set of consumers towards hybrid vehicles, and establishing the product attribute set of the hybrid vehicles according to the morphological analysis method;

[0049] The first processing module: performs dimension simplification on the sentiment attribute set to obtain a simplified sentiment attribute set, and decomposes the product attribute set to obtain a product sub-attribute set;

[0050] The first construction module: construct a decision table, use the simplified sentiment attribute set and the product sub-attribute set as the decision attribute set and condition attribute set of the decision table respectively, and obtain the importance of each condition attribute in the decision table to each decision attribute according to the importance algorithm;

[0051] The second construction module: constructing a quality house matrix, wherein the quality house matrix uses the simplified emotional attribute set as the left wall and the product sub-attribute set as the ceiling, imports the importance into the quality house matrix, and obtains the association relationship of the quality house matrix;

[0052] The second processing module: the simplified emotional attribute set is used as a reference sequence set, the product sub-attribute set is used as a comparison sequence set, and the comparison sequence set is subjected to grey correlation analysis according to the correlation relationship of the quality house matrix to obtain the grey correlation degree of each product sub-attribute in the product sub-attribute set;

[0053] Design module: according to the grey correlation degree of each product sub-attribute, obtain the ranking of each product sub-attribute in the product sub-attribute set, so as to design the hybrid vehicle according to the ranking of each product sub-attribute.

[0054] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0055] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0056] In the embodiments of the present application, compared with the prior art, the following technical effects are achieved:

[0057] (1) By quantitatively analyzing the relationship between consumer emotions and product attributes, the key factors that affect consumer emotions can be quickly identified, providing strong support for design optimization;

[0058] (2) Optimized hybrid vehicles can better meet consumers’ needs and expectations, improve product satisfaction and loyalty, and thus enhance market competitiveness;

[0059] (3) Avoid unnecessary waste of resources and reduce design costs by accurately locating product sub-attributes that need to be optimized;

[0060] (4) Products that meet consumer needs can enhance brand image and reputation, bringing long-term benefits to the company. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a flow chart of a hybrid vehicle design method based on grey correlation provided by some embodiments of the present application; DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0064] In the following, in conjunction with the accompanying drawings, a hybrid vehicle design method and system based on grey correlation provided by an embodiment of the present application are described in detail through specific embodiments and application scenarios.

[0065] Example

[0066] A hybrid vehicle design method based on grey correlation includes the following steps:

[0067] S100: Obtaining a set of consumers' emotional attributes for hybrid vehicles, establishing a product attribute set of hybrid vehicles according to a morphological analysis method, performing dimensionality reduction on the emotional attribute set to obtain a reduced emotional attribute set, and decomposing the product attribute set to obtain a product sub-attribute set;

[0068] It should be noted that the specific steps of S100 are as follows:

[0069] S110: Acquire multiple emotional attributes of consumers toward hybrid vehicles, and screen the multiple emotional attributes to obtain an emotional attribute set;

[0070] S120: analyzing and ranking the sentiment attribute set according to the grey prediction model, selecting the top N sentiment attributes in the sentiment attribute set, and constructing a simplified sentiment attribute set;

[0071] S130: Acquire multiple hybrid vehicle model images of different types, and filter the multiple hybrid vehicle model images of different types to obtain a hybrid vehicle model image set;

[0072] S140: performing group analysis on the hybrid vehicle model image set, and dividing the hybrid vehicle model image set into a plurality of hybrid vehicle model image subsets;

[0073] S150: selecting a hybrid vehicle image from each hybrid vehicle image subset to form a target hybrid vehicle image set; deconstructing the target hybrid vehicle image set to obtain a product attribute set;

[0074] S160: The product attributes are concentrated, each product attribute is decomposed into a plurality of product sub-attributes, and a product sub-attribute set is constructed based on the plurality of product sub-attributes.

[0075] It should be noted that the grey prediction model in S120 is expressed by the following formula:

[0076] ,

[0077] in, represents the accumulation matrix, express The transposed matrix of The first elements, Represents the first emotional attribute accumulation sequence elements, Indicates The first of the emotional attribute accumulation sequences elements, represents a constant vector, express The estimated value of represents the development coefficient, Indicates the first elements, Indicates The influence coefficient corresponding to each emotional attribute.

[0078] Furthermore, through market research, online questionnaires, social media analysis and other methods, consumers' emotional attributes of hybrid vehicles are widely collected; these emotional attributes include but are not limited to appearance, performance, endurance, price, environmental protection, sense of technology, etc. Then, these collected emotional attributes are screened, and attributes that are repeated, ambiguous or do not meet the research purpose are removed to obtain an emotional attribute set. The emotional attribute set is analyzed and sorted using a gray prediction model. The gray prediction model is a prediction method suitable for small samples, poor information, and uncertain systems, and can handle situations where some information is known and some information is unknown. Through analysis, the top N emotional attributes are selected, which usually represent the aspects that consumers are most concerned about or consider most important, so as to construct a simplified emotional attribute set. Multiple different types of hybrid vehicle images are obtained from various sources (such as automobile websites, social media, advertisements, etc.). These images should be able to fully reflect the appearance, design features, etc. of hybrid vehicles. Then, these images are screened, and images that are ambiguous, incomplete or do not meet the research standards are removed to obtain a hybrid vehicle image set. The hybrid vehicle image set is clustered, that is, the image set is divided into multiple subsets based on factors such as image similarity and design features. The images in each subset have common features or styles to some extent, which is helpful for subsequent analysis and deconstruction. A representative image is selected from each hybrid vehicle image subset to form the target hybrid vehicle image set. These images should be able to fully reflect the characteristics of each subset. Then, the target hybrid vehicle image set is deconstructed, that is, by analyzing the design elements, lines, colors, etc. in the image, the product attributes related to the hybrid vehicle, such as body lines, front face design, tail shape, etc., are extracted to obtain the product attribute set. Each attribute in the product attribute set is further decomposed into multiple sub-attributes. Through these sub-attributes, various aspects of the hybrid vehicle can be described and analyzed in more detail, thereby constructing a complete product sub-attribute set.

[0079] S200: construct a decision table, use the simplified sentiment attribute set and the product sub-attribute set as the decision attribute set and the condition attribute set of the decision table respectively, and obtain the importance of each condition attribute to each decision attribute in the decision table according to the importance algorithm;

[0080] It should be noted that the specific steps of S200 are as follows:

[0081] S210: construct a decision table, input the simplified sentiment attribute set as a decision attribute set into the decision table, and input the product sub-attribute set as a condition attribute set into the decision table;

[0082] S220: Process the condition attribute set and the decision attribute set according to the importance algorithm to obtain the importance of each condition attribute to each decision attribute in the decision table.

[0083] It should be noted that the importance algorithm in S220 is expressed by the following formula:

[0084] ,

[0085] in, Represents a conditional attribute set, Represents the first decision attributes, Represents a conditional attribute in a conditional attribute set. Represents conditional attributes right The importance of express right The dependency relationship, express right The dependency relationship, Represents conditional attributes The set composed of represents a finite non-empty set, express The number of elements of express exist The positive domain below, express The number of elements of express By the equivalence relation Decide on the division, represents the lower approximation set, yes A subset of yes The elements in Represents a set union operation.

[0086] Furthermore, a decision table is created. This table is a common tool in data analysis and is used to represent the relationship between different attributes. A decision table usually consists of two parts: a decision attribute set and a conditional attribute set. The simplified emotional attribute set obtained in the previous step is input into the decision table as the decision attribute set. These emotional attributes are the aspects that consumers pay the most attention to or consider the most important, representing consumers' expectations and needs. At the same time, the product sub-attribute set is input into the decision table as the conditional attribute set. These product sub-attributes are specific characteristics or design elements of hybrid vehicles, which directly or indirectly affect consumers' emotions. By constructing a decision table, we can clearly see the relationship between different product sub-attributes and consumer emotions, providing a basis for subsequent analysis. Afterwards, the conditional attribute set (i.e., product sub-attribute set) and the decision attribute set (i.e., simplified emotional attribute set) in the decision table are processed using the importance algorithm. The importance algorithm is a mathematical method used to evaluate the degree of influence of attributes on decision results. It can calculate the importance of each conditional attribute (product sub-attribute) to each decision attribute (reduced emotional attribute) based on the data in the decision table. The calculation of importance usually involves statistics and analysis of the decision table to determine which attributes have a significant impact on the decision results. Through calculation, we can get a ranking that indicates the importance of each product sub-attribute to each simplified emotional attribute. This ranking is of great significance for subsequent design optimization and decision making.

[0087] S300: Construct a quality house matrix. The quality house matrix uses the simplified emotional attribute set as the left wall and the product sub-attribute set as the ceiling. Import the importance into the quality house matrix to obtain the correlation relationship of the quality house matrix.

[0088] It should be noted that the specific steps of S300 are as follows:

[0089] S310: construct a quality house framework, input the simplified emotional attribute set and the product sub-attribute set as the left wall and ceiling of the quality house framework respectively into the quality house framework, and import the importance into the quality house framework to obtain the quality house matrix;

[0090] S320: Obtain the link strength between each condition attribute and each decision attribute according to the data mining software, and obtain a link strength set corresponding to each condition attribute;

[0091] S330: Obtain the association relationship between the left wall and the ceiling in the quality house moment according to the link strength set corresponding to each condition attribute.

[0092] Furthermore, the House of Quality (HOQ) is a tool used to convert customer needs into product design features. It usually includes multiple parts such as the left wall, ceiling, room, and basement. First, a House of Quality framework is constructed, and the simplified emotional attribute set is used as the left wall input of the House of Quality framework. The left wall represents the needs and expectations of consumers and is the basis of product design. The product sub-attribute set is used as the ceiling input of the House of Quality framework. The ceiling represents the design characteristics or sub-attributes of the product and is a specific means to meet consumer needs. The importance calculated in the previous step is imported into the House of Quality framework, which is usually done by filling in the importance values ​​in the room part (i.e., the core area of ​​the matrix). These importance values ​​represent the importance of each product sub-attribute in meeting consumer emotional needs. A complete House of Quality matrix is ​​obtained, which clearly shows the relationship between consumer needs and product design features. The link strength represents the degree of association between each condition attribute (i.e., product sub-attribute) and each decision attribute (i.e., simplified emotional attribute) in the House of Quality matrix. Data mining software is used to analyze the data in the House of Quality matrix to calculate the link strength between each condition attribute and each decision attribute. Through calculation, we can get a link strength set, which contains the link strength values ​​of all decision attributes corresponding to each conditional attribute. According to the link strength set calculated in the previous step, determine the association between the left wall (consumer emotional needs) and the ceiling (product design features or sub-attributes) in the quality house matrix. Sort or classify the associations according to the size of the link strength to identify which design features are most critical to meeting specific consumer needs. These associations provide important guidance for subsequent design optimization, helping us ensure that product design can accurately meet consumer expectations and needs.

[0093] S400: The simplified emotional attribute set is used as a reference sequence set, and the product sub-attribute set is used as a comparison sequence set. According to the correlation relationship of the quality house matrix, a grey correlation degree analysis is performed on the comparison sequence set to obtain the grey correlation degree of each product sub-attribute in the product sub-attribute set;

[0094] It should be noted that the specific steps of S400 are as follows:

[0095] S410: normalizing the simplified sentiment attribute set and the product sub-attribute set, using the normalized simplified sentiment attribute set as a reference sequence set, and using the normalized product sub-attribute set as a comparison sequence set;

[0096] S420: constructing a normalized matrix based on the reference sequence set and the comparison sequence set;

[0097] S430: calculating the absolute difference between each reference sequence and each comparison sequence in the normalized matrix according to a difference algorithm;

[0098] S440: According to the grey relational degree algorithm, the absolute difference between each reference sequence and each comparison sequence is processed to obtain the grey relational degree of the comparison sequence set.

[0099] It should be noted that the normalization process of the product sub-attribute set in S410 is as follows:

[0100] ,

[0101] in, Indicates the first Ledi The elements of the row, Indicates the product sub-attribute set Ledi The elements of the row, Indicates the product sub-attribute set The smallest element in the row, Indicates the product sub-attribute set The largest element in the row;

[0102] In S410, the normalization process of the simplified sentiment attribute set is expressed as follows:

[0103] ,

[0104] in, Indicates the reference sequence set elements, Indicates the first elements, Indicates the first The absolute value of the elements, Indicates the total number of elements in the simplified sentiment attribute set;

[0105] The difference algorithm in S430 is expressed by the following formula:

[0106] ,

[0107] in, Indicates the first Ledi The elements of the row are the same as the reference sequence The absolute difference of the elements, Indicates the reference sequence set elements;

[0108] The grey relational algorithm in S440 is expressed by the following formula:

[0109]

[0110] ,

[0111] in, Indicates the product sub-attribute set The grey correlation degree of each product sub-attribute, Indicates the first Ledi Grey correlation coefficient of row elements, Indicates the minimum absolute difference in the comparison sequence set. Indicates the maximum absolute difference in the comparison sequence set. Represents the resolution factor.

[0112] Furthermore, normalization is a data preprocessing technique used to convert data of different dimensions or different value ranges to the same scale for comparison and analysis. The simplified sentiment attribute set and product sub-attribute set are normalized; specific methods of normalization may include minimum-maximum normalization, Z-score normalization, etc. After normalization, two new data sets are obtained: the normalized simplified sentiment attribute set (as a reference sequence set) and the normalized product sub-attribute set (as a comparison sequence set). The normalization matrix is ​​a two-dimensional array that contains all the data after normalization. The normalization matrix is ​​constructed based on the reference sequence set and the comparison sequence set. The elements in the matrix are the normalized data values, which represent the relative size relationship between different attributes. The absolute difference represents the distance or degree of difference between two data points. The absolute difference between each reference sequence and each comparison sequence in the normalized matrix is ​​calculated according to the difference algorithm, which involves comparing each element in the matrix pair by pair and calculating the absolute value of the difference between them; the calculated absolute difference will be used in subsequent analysis to evaluate the degree of association between different attributes. Grey correlation is a mathematical method used to evaluate the similarity or degree of association between different sequences. The absolute difference between each reference sequence and each comparison sequence is processed according to the grey correlation algorithm to obtain the grey correlation of the comparison sequence set. The calculation of grey correlation usually involves weighting the absolute difference and calculating a correlation value between 0 and 1. The closer this value is to 1, the higher the degree of association between the two sequences; the closer it is to 0, the lower the degree of association. By calculating the grey correlation, we can evaluate the importance or contribution of different product sub-attributes to satisfying consumers' emotional needs.

[0113] S500: Obtaining the ranking of each product sub-attribute in the product sub-attribute set according to the grey correlation degree of each product sub-attribute, so as to design a hybrid vehicle according to the ranking of each product sub-attribute.

[0114] Furthermore, according to the grey correlation degree of each product sub-attribute, the product sub-attribute set is sorted to obtain the key factors that affect consumer emotions. According to the sorting results, the hybrid vehicle design is optimized, focusing on improving those product sub-attributes that are highly correlated with consumer emotions to meet consumer needs and expectations.

[0115] According to one of the embodiments, the beneficial effects are as follows:

[0116] (1) By obtaining consumers’ emotional attribute sets for hybrid vehicles and establishing product attribute sets using morphological analysis methods, this technology can accurately capture and analyze consumers’ specific emotional needs and preferences for hybrid vehicles.

[0117] (2) Dimensional simplification of the emotional attribute set can remove redundant information and retain key emotional factors, thereby more accurately guiding product design. At the same time, decomposing the product attribute set into product sub-attribute sets helps to analyze in detail the impact of each design element on consumer emotions.

[0118] (3) A decision table is constructed and the importance algorithm is used to calculate the importance of each condition attribute to each decision attribute, providing a quantitative decision basis for hybrid vehicle design. This helps to identify which design attributes have the greatest impact on consumer emotions, so that more attention can be paid to them during the design process.

[0119] (4) By constructing the House of Quality Matrix, this technology can clearly show the relationship between the simplified emotional attribute set and the product sub-attribute set. This helps designers to comprehensively consider the mutual influence of various attributes during the design process and ensure the coordination and consistency of the design scheme.

[0120] (5) Use grey correlation analysis to analyze the comparison sequence set, obtain the grey correlation of each product sub-attribute, and sort them according to the correlation. This helps designers identify which product sub-attributes are most critical to satisfying consumers' emotional needs, so as to prioritize these attributes when resources are limited.

[0121] (6) Based on the ranking results of product sub-attributes, this technology can provide clear guidance for the design of hybrid vehicles. Designers can adjust the design plan based on these ranking results to ensure that the hybrid vehicle can better meet the emotional needs and preferences of consumers.

[0122] It should be noted that the hybrid vehicle design method based on grey association provided in the embodiment of the present application can be executed by a hybrid vehicle design system based on grey association, or, or, a control module in the hybrid vehicle design system based on grey association for executing and loading a hybrid vehicle design method based on grey association. In the embodiment of the present application, a hybrid vehicle design system based on grey association is used to execute and load a hybrid vehicle design method based on grey association as an example to illustrate a hybrid vehicle design method based on grey association provided in the embodiment of the present application.

[0123] A hybrid vehicle design system based on grey correlation includes the following modules:

[0124] Acquisition module: Acquire consumers' emotional attribute set for hybrid vehicles and establish a product attribute set for hybrid vehicles based on morphological analysis methods;

[0125] The first processing module: dimensionality reduction of the sentiment attribute set to obtain a reduced sentiment attribute set, and decomposition of the product attribute set to obtain a product sub-attribute set;

[0126] The first construction module: construct a decision table, use the simplified sentiment attribute set and product sub-attribute set as the decision attribute set and condition attribute set of the decision table respectively, and obtain the importance of each condition attribute to each decision attribute in the decision table according to the importance algorithm;

[0127] The second building block: building a quality house matrix. The quality house matrix uses the simplified emotional attribute set as the left wall and the product sub-attribute set as the ceiling. Importing the importance into the quality house matrix, obtaining the correlation relationship of the quality house matrix;

[0128] The second processing module: simplify the sentiment attribute set into a reference sequence set, divide the product sub-attribute set into a comparison sequence set, perform grey correlation analysis on the comparison sequence set according to the correlation relationship of the quality house matrix, and obtain the grey correlation degree of each product sub-attribute in the product sub-attribute set;

[0129] Design module: according to the grey correlation degree of each product sub-attribute, the ranking of each product sub-attribute in the product sub-attribute set is obtained, so as to design the hybrid vehicle according to the ranking of each product sub-attribute.

[0130] A hybrid vehicle design system based on grey correlation in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), etc., which is not specifically limited in the embodiment of the present application.

[0131] A hybrid vehicle design system based on grey correlation in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0132] The hybrid vehicle design system based on grey correlation provided by the embodiment of the present application can realize Figure 1 In the method embodiment, each process of implementing a hybrid vehicle design method based on grey correlation is not described here to avoid repetition.

[0133] According to a hybrid vehicle design system based on grey association in this embodiment, the acquisition module collects the emotional attribute set of consumers for hybrid vehicles, which can directly and accurately reflect consumers' expectations and preferences for hybrid vehicles, capture consumers' true voices, and provide strong data support for subsequent product design. The first processing module simplifies and decomposes the emotional attribute set and the product attribute set, reduces the complexity of data processing, and improves the efficiency and accuracy of analysis. The decision table is constructed by the first construction module, and the importance of each product sub-attribute is evaluated by the importance algorithm, so that designers can clearly understand which attributes are most critical to consumers, so as to pay more attention to them in the design process. The quality house matrix constructed by the second construction module effectively associates the simplified emotional attribute set with the product sub-attribute set to form an intuitive association relationship diagram. This not only helps designers understand the intrinsic connection between consumer needs and product attributes, but also provides a basis for subsequent grey association analysis. The introduction of the quality house matrix makes the decision process more scientific and systematic, and helps to improve the pertinence and effectiveness of product design. The second processing module uses the grey association analysis method to quantitatively analyze the product sub-attribute set and obtain the grey association degree of each product sub-attribute. This method can comprehensively consider the mutual influence of multiple factors and avoid the one-sidedness of single factor analysis. Through the sorting of gray correlation, designers can clearly see the priority of each product sub-attribute in meeting consumer needs, so as to reasonably allocate resources and optimize product performance during the design process. The design module conducts targeted design of hybrid vehicles based on the sorting results of gray correlation. This method not only improves the scientificity and systematicness of product design, but also makes the product more able to meet the expectations and needs of consumers and enhances the market competitiveness of the product. By continuously optimizing the design of hybrid vehicles, companies can continuously improve product quality and user satisfaction, thereby standing out in the fierce market competition.

[0134] Optionally, an embodiment of the present application further provides an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, each process of the above-mentioned embodiment of a hybrid vehicle design method based on grey correlation is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0135] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned hybrid vehicle design method based on gray correlation is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0136] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0137] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0139] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A hybrid vehicle design method based on grey correlation, characterized in that: The method comprises: Acquire consumers' emotional attribute set for hybrid vehicles, establish a product attribute set of the hybrid vehicle according to a morphological analysis method, perform dimensionality reduction on the emotional attribute set to obtain a reduced emotional attribute set, and decompose the product attribute set to obtain a product sub-attribute set; Constructing a decision table, using the simplified sentiment attribute set and the product sub-attribute set as the decision attribute set and condition attribute set of the decision table respectively, and obtaining the importance of each condition attribute to each decision attribute in the decision table according to an importance algorithm; Constructing a quality house matrix, wherein the quality house matrix uses the simplified emotional attribute set as a left wall and the product sub-attribute set as a ceiling, importing the importance into the quality house matrix, and obtaining the correlation relationship of the quality house matrix; The simplified sentiment attribute set is used as a reference sequence set, and the product sub-attribute set is used as a comparison sequence set. According to the association relationship of the quality house matrix, a grey correlation degree analysis is performed on the comparison sequence set to obtain the grey correlation degree of each product sub-attribute in the product sub-attribute set; According to the grey correlation degree of each product sub-attribute, the ranking of each product sub-attribute in the product sub-attribute set is obtained, so as to design a hybrid vehicle according to the ranking of each product sub-attribute.

2. The hybrid vehicle design method based on grey correlation according to claim 1, characterized in that: The process of obtaining a consumer's emotional attribute set for hybrid vehicles, establishing a product attribute set for the hybrid vehicle according to a morphological analysis method, performing dimensionality reduction on the emotional attribute set to obtain a reduced emotional attribute set, and decomposing the product attribute set to obtain a product sub-attribute set is as follows: Acquire multiple emotional attributes of consumers toward hybrid vehicles, and filter the multiple emotional attributes to obtain the emotional attribute set; Analyze and sort the sentiment attribute set according to the grey prediction model, select the top N sentiment attributes in the sentiment attribute set, and construct the simplified sentiment attribute set; Acquire multiple hybrid vehicle model images of different types, and filter the multiple hybrid vehicle model images of different types to obtain a hybrid vehicle model image set; performing a cluster analysis on the hybrid vehicle model image set, and dividing the hybrid vehicle model image set into a plurality of hybrid vehicle model image subsets; Selecting one hybrid vehicle model image from each of the hybrid vehicle model image subsets to form a target hybrid vehicle model image set; Deconstructing the target hybrid vehicle model image set to obtain the product attribute set; In the product attribute set, each product attribute is decomposed into a plurality of product sub-attributes, and a product sub-attribute set is constructed according to the plurality of product sub-attributes.

3. The hybrid vehicle design method based on grey correlation according to claim 1, characterized in that: The construction of the decision table uses the simplified sentiment attribute set and the product sub-attribute set as the decision attribute set and condition attribute set of the decision table respectively, and obtains the importance of each condition attribute in the decision table to each decision attribute according to the importance algorithm; specifically: Constructing a decision table, inputting the simplified sentiment attribute set as the decision attribute set into the decision table, and inputting the product sub-attribute set as the condition attribute set into the decision table; The condition attribute set and the decision attribute set are processed according to an importance algorithm to obtain the importance of each condition attribute to each decision attribute in the decision table.

4. The hybrid vehicle design method based on grey correlation according to claim 3 is characterized in that: The importance algorithm is expressed by the following formula: ， in, Represents a conditional attribute set, Represents the first decision attributes, Represents a conditional attribute in a conditional attribute set. Represents conditional attributes right The importance of express right The dependency relationship, express right The dependency relationship, Represents conditional attributes The set composed of represents a finite non-empty set, express The number of elements of express exist The positive domain below, express The number of elements of express By the equivalence relation Decide on the division, represents the lower approximation set, yes A subset of yes The elements in Represents a set union operation.

5. The hybrid vehicle design method based on grey correlation according to claim 1, characterized in that: The quality house matrix is ​​constructed, the quality house matrix uses the simplified emotional attribute set as the left wall and the product attribute set as the ceiling, imports the importance into the quality house matrix, and obtains the association relationship of the quality house matrix; specifically: Constructing a quality house framework, inputting the simplified sentiment attribute set and the product sub-attribute set into the quality house framework as the left wall and ceiling of the quality house framework respectively, and importing the importance into the quality house framework to obtain the quality house matrix; Acquire the link strength between each of the condition attributes and each of the decision attributes according to the data mining software, and obtain a link strength set corresponding to each of the condition attributes; According to the link strength set corresponding to each of the condition attributes, the association relationship between the left wall and the ceiling in the house of quality matrix is ​​obtained.

6. The hybrid vehicle design method based on grey correlation according to claim 1, characterized in that: The simplified emotional attribute set is used as a reference sequence set, the product sub-attribute set is used as a comparison sequence set, and the comparison sequence set is subjected to grey correlation analysis according to the correlation relationship of the quality house matrix to obtain the grey correlation degree of each product sub-attribute in the product sub-attribute set; Specifically: Normalizing the simplified sentiment attribute set and the product sub-attribute set, using the normalized simplified sentiment attribute set as a reference sequence set, and using the normalized product sub-attribute set as a comparison sequence set; constructing a normalized matrix based on the reference sequence set and the comparison sequence set; Calculating the absolute difference between each reference sequence and each comparison sequence in the normalized matrix according to a difference algorithm; According to the grey relational degree algorithm, the absolute difference between each reference sequence and each comparison sequence is processed to obtain the grey relational degree of the comparison sequence set.

7. The hybrid vehicle design method based on grey correlation according to claim 6 is characterized in that: The normalization processing of the product sub-attribute set is expressed as follows: ， in, Indicates the first Ledi The elements of the row, Indicates the product sub-attribute set Ledi The elements of the row, Indicates the product sub-attribute set The smallest element in the row, Indicates the product sub-attribute set The largest element in the row; The normalization process of the simplified sentiment attribute set is as follows: ， in, Indicates the reference sequence set elements, Indicates the first elements, Indicates the first The absolute value of the elements, Indicates the total number of elements in the simplified sentiment attribute set; The difference algorithm is expressed by the following formula: ， in, Indicates the first Ledi The elements of the row are the same as the reference sequence The absolute difference of the elements, Indicates the reference sequence set elements; The grey relational degree algorithm is expressed by the following formula: ， in, Indicates the product sub-attribute set The grey correlation degree of each product sub-attribute, Indicates the first Ledi Grey correlation coefficient of row elements, Indicates the minimum absolute difference in the comparison sequence set. Indicates the maximum absolute difference in the comparison sequence set. Represents the resolution factor.

8. A hybrid vehicle design system based on grey correlation, capable of implementing a hybrid vehicle design method based on grey correlation as claimed in any one of claims 1 to 7, characterized in that: The system comprises: Acquisition module: acquiring the emotional attribute set of consumers towards hybrid vehicles, and establishing the product attribute set of the hybrid vehicles according to the morphological analysis method; The first processing module: performs dimension simplification on the sentiment attribute set to obtain a simplified sentiment attribute set, and decomposes the product attribute set to obtain a product sub-attribute set; The first construction module: construct a decision table, use the simplified sentiment attribute set and the product sub-attribute set as the decision attribute set and condition attribute set of the decision table respectively, and obtain the importance of each condition attribute in the decision table to each decision attribute according to the importance algorithm; The second construction module: constructing a quality house matrix, wherein the quality house matrix uses the simplified emotional attribute set as the left wall and the product sub-attribute set as the ceiling, imports the importance into the quality house matrix, and obtains the association relationship of the quality house matrix; The second processing module: the simplified emotional attribute set is used as a reference sequence set, the product sub-attribute set is used as a comparison sequence set, and the comparison sequence set is subjected to grey correlation analysis according to the correlation relationship of the quality house matrix to obtain the grey correlation degree of each product sub-attribute in the product sub-attribute set; Design module: according to the grey correlation degree of each product sub-attribute, obtain the ranking of each product sub-attribute in the product sub-attribute set, so as to design the hybrid vehicle according to the ranking of each product sub-attribute.

9. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein when the program or instruction is executed by the processor, the steps of a hybrid vehicle design method based on grey correlation as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the hybrid vehicle design method based on grey correlation as described in any one of claims 1 to 7 are implemented.

Images