Customized Recommendation Method, Device, Equipment and Storage Medium for Accelerator Pedal Characteristics

Abstract

The present invention relates to the technical field of accelerator pedal characteristic management, and discloses a customized recommendation method, device, equipment and storage medium for accelerator pedal characteristics. The method includes: extracting characteristic parameters of driving style parameters of a target user; performing clustering analysis on the characteristic parameters; determining the weight proportion of the characteristic parameters according to the driving style clustering center; generating target accelerator pedal characteristics according to the weight proportion and the initial accelerator pedal characteristics, and making a customized recommendation for the target accelerator pedal characteristics. Since the present invention performs clustering analysis on the characteristic parameters, then determines the weight proportion of the characteristic parameters according to the driving style clustering center, and then generates the target accelerator pedal characteristics based on the weight proportion and the initial accelerator pedal characteristics, compared with the prior art that recommends uniform accelerator pedal characteristics, it can customize and recommend accelerator pedal characteristics that match the user's driving style, thereby improving the user's driving experience.

Description

Technical Field

[0001] The present invention relates to the technical field of accelerator pedal characteristic management, and particularly to a customized recommendation method, device, equipment and storage medium for accelerator pedal characteristics. Background Art

[0002] In recent years, the service concept of personalized experience has been relatively maturely applied in vehicle production models, terminal sales, autonomous driving, route planning, etc. However, the performance of NEVs is currently mainly tuned by OEMs, belonging to a one-size-fits-all performance experience and energy management, failing to reflect the differences and particularities of individual users. It is difficult to highlight the highlights in performance development and meet the differentiated user needs. That is, the recommended accelerator pedal characteristics are all the same and cannot match the driving styles of users.

[0003] The above content is only used to assist in understanding the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of the present invention is to provide a customized recommendation method, device, equipment and storage medium for accelerator pedal characteristics, aiming to solve the technical problem that the prior art cannot recommend accelerator pedal characteristics that match the driving styles of users, resulting in a low driving experience for users.

[0005] To achieve the above purpose, the present invention provides a customized recommendation method for accelerator pedal characteristics, and the customized recommendation method for accelerator pedal characteristics includes the following steps:

[0006] Extract the characteristic parameters of the driving style parameters of the target user;

[0007] Perform cluster analysis on the characteristic parameters to obtain the corresponding driving style cluster centers;

[0008] Determine the weight ratio of the characteristic parameters according to the driving style cluster centers;

[0009] Generate target accelerator pedal characteristics according to the weight ratio and the initial accelerator pedal characteristics, and perform customized recommendation on the target accelerator pedal characteristics.

[0010] Optionally, the extraction of the characteristic parameters of the driving style parameters of the target user includes:

[0011] Construct a driving style hierarchical structure model for the driving style parameters of the target user through an analytic hierarchy process strategy;

[0012] Generate a driving style parameter comparison matrix according to the target parameter-scale relationship and the driving style hierarchical structure model;

[0013] Extract the driving style parameters according to the driving style parameter comparison matrix to obtain corresponding characteristic parameters.

[0014] Optionally, generating the driving style parameter comparison matrix according to the target parameter-scale relationship and the driving style hierarchy model includes:

[0015] Determine the relative importance degree of the driving style parameters according to the target orientation measurement data and the user's in-vehicle evaluation data;

[0016] Obtain the corresponding parameter scale values according to the target parameter-scale relationship and the relative importance degree;

[0017] Respectively calculate the ratios of the parameter scale values to obtain the corresponding scale numerical values;

[0018] Generate the driving style parameter comparison matrix according to the scale numerical values and the driving style hierarchy model.

[0019] Optionally, extracting the driving style parameters according to the driving style parameter comparison matrix to obtain corresponding characteristic parameters includes:

[0020] Perform hierarchical single sorting on the driving style parameters through the driving style parameter comparison matrix to obtain the corresponding driving style parameter sorting result;

[0021] Perform consistency verification on the driving style parameter sorting result;

[0022] When the parameter verification result passes the verification, extract the driving style parameters to obtain corresponding characteristic parameters.

[0023] Optionally, performing cluster analysis on the characteristic parameters through the target clustering analysis strategy to obtain the corresponding driving style cluster centers includes:

[0024] Obtain the starting acceleration condition of the target vehicle;

[0025] Generate the corresponding acceleration characteristic parameter curve according to the starting acceleration condition and the characteristic parameters;

[0026] Obtain the number of driving style categories;

[0027] Perform cluster analysis on the acceleration characteristic parameter curve through the target clustering analysis strategy according to the number of driving style categories to obtain the corresponding driving style cluster centers.

[0028] Optionally, determining the weight ratio of the characteristic parameters according to the driving style cluster centers includes:

[0029] Calculate the driving style cluster centers through the coefficient of variation algorithm to obtain the corresponding coefficient of variation;

[0030] Normalize the coefficient of variation to obtain the weight ratio of the characteristic parameters.

[0031] Optionally, calculating the driving style clustering center through the target correction coefficient strategy to obtain the corresponding correction coefficient includes:

[0032] Obtain a preset set of basic characteristic parameters;

[0033] Calculate the deviation of the characteristic parameters based on the preset set of basic characteristic parameters to obtain the characteristic parameter deviation;

[0034] Calculate the corresponding correction coefficient through the target correction coefficient strategy for the characteristic parameter deviation and the weight ratio;

[0035] Generate a target accelerator pedal characteristic according to the correction coefficient and the initial accelerator pedal characteristic, and perform customized recommendation for the target accelerator pedal characteristic.

[0036] Optionally, the target accelerator pedal characteristic includes a first accelerator pedal characteristic and a second accelerator pedal characteristic;

[0037] Generating a target accelerator pedal characteristic according to the correction coefficient and the initial accelerator pedal characteristic, and performing customized recommendation for the target accelerator pedal characteristic includes:

[0038] Perform multiplication calculation on the correction coefficient and the initial accelerator pedal characteristic parameters to obtain the first accelerator pedal characteristic;

[0039] Perform division calculation on the correction coefficient and the initial accelerator pedal characteristic to obtain the second accelerator pedal characteristic;

[0040] Perform customized recommendation for the first accelerator pedal characteristic and the second accelerator pedal characteristic.

[0041] In addition, to achieve the above object, the present invention also proposes a customized recommendation device for accelerator pedal characteristics, and the customized recommendation device for accelerator pedal characteristics includes:

[0042] An extraction module, configured to extract characteristic parameters of driving style parameters of a target user;

[0043] An analysis module, configured to perform clustering analysis on the characteristic parameters to obtain the corresponding driving style clustering center;

[0044] A determination module, configured to determine the weight ratio of the characteristic parameters according to the driving style clustering center;

[0045] A customized recommendation module, configured to generate a target accelerator pedal characteristic according to the weight ratio and the initial accelerator pedal characteristic, and perform customized recommendation on the target accelerator pedal characteristic.

[0046] In addition, to achieve the above object, the present invention also provides a customized recommendation device for accelerator pedal characteristics, where the customized recommendation device for accelerator pedal characteristics includes: a memory, a processor, and a customized recommendation program for accelerator pedal characteristics stored on the memory and executable on the processor, and the customized recommendation program for accelerator pedal characteristics is configured to implement the customized recommendation method for accelerator pedal characteristics as described above.

[0047] In addition, to achieve the above object, the present invention also provides a storage medium, on which a customized recommendation program for accelerator pedal characteristics is stored, and when the customized recommendation program for accelerator pedal characteristics is executed by a processor, it implements the customized recommendation method for accelerator pedal characteristics as described above.

[0048] The customized recommendation method for accelerator pedal characteristics proposed by the present invention extracts characteristic parameters of the driving style parameters of the target user; performs clustering analysis on the characteristic parameters through a target clustering analysis strategy to obtain corresponding driving style clustering centers; determines the weight ratio of the characteristic parameters according to the driving style clustering centers; generates a target accelerator pedal characteristic according to the weight ratio and the initial accelerator pedal characteristic, and performs customized recommendation on the target accelerator pedal characteristic; since the present invention performs clustering analysis on the characteristic parameters, then determines the weight ratio of the characteristic parameters according to the driving style clustering centers, and then generates a target accelerator pedal characteristic based on the weight ratio and the initial accelerator pedal characteristic, compared with the prior art that recommends the same accelerator pedal characteristics, it can customize and recommend accelerator pedal characteristics that match the user's driving style, thereby improving the user's driving experience. Description of the Drawings

[0049] Figure 1 It is a schematic structural diagram of a customized recommendation device for accelerator pedal characteristics in the hardware operating environment related to the embodiment solution of the present invention;

[0050] Figure 2 It is a schematic flowchart of the first embodiment of the customized recommendation method for accelerator pedal characteristics of the present invention;

[0051] Figure 3 It is a schematic flowchart of the second embodiment of the customized recommendation method for accelerator pedal characteristics of the present invention;

[0052] Figure 4 It is a schematic diagram of a driving style hierarchical structure model in an embodiment of the customized recommendation method for accelerator pedal characteristics of the present invention;

[0053] Figure 5Schematic flowchart of the third embodiment of the customized recommendation method for the characteristics of the accelerator pedal of the present invention;

[0054] Figure 6 Schematic diagram of the functional modules of the first embodiment of the customized recommendation device for the characteristics of the accelerator pedal of the present invention.

[0055] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0056] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] Refer to Figure 1 , Figure 1 Schematic diagram of the structure of the customized recommendation device for the characteristics of the accelerator pedal in the hardware operating environment related to the embodiment solution of the present invention.

[0058] As Figure 1 shown, the customized recommendation device for the characteristics of the accelerator pedal may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed Random Access Memory (RAM) memory or a stable Non-Volatile Memory (NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0059] Those skilled in the art can understand that Figure 1 the structure shown in

[0060] does not constitute a limitation on the customized recommendation device for the characteristics of the accelerator pedal, and may include more or fewer components than shown, or combine some components, or have different component arrangements. Figure 1 As

[0061] In Figure 1 In the customized recommendation device for the accelerator pedal characteristics shown, the network interface 1004 is mainly used for data communication with the network integrated platform workstation; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the customized recommendation device for the accelerator pedal characteristics of the present invention can be arranged in the customized recommendation device for the accelerator pedal characteristics. The customized recommendation device for the accelerator pedal characteristics calls the customized recommendation program for the accelerator pedal characteristics stored in the memory 1005 through the processor 1001 and executes the customized recommendation method for the accelerator pedal characteristics provided in the embodiments of the present invention.

[0062] Based on the above hardware structure, an embodiment of the customized recommendation method for the accelerator pedal characteristics of the present invention is proposed.

[0063] Referring to Figure 2 , Figure 2 is a schematic flowchart of the first embodiment of the customized recommendation method for the accelerator pedal characteristics of the present invention.

[0064] In the first embodiment, the customized recommendation method for the accelerator pedal characteristics includes the following steps:

[0065] Step S10, extract the characteristic parameters of the driving style parameters of the target user.

[0066] It should be noted that the execution subject of this embodiment is the customized recommendation device for the accelerator pedal characteristics, and it can also be other devices that can achieve the same or similar functions, such as the vehicle control unit, etc. This embodiment does not limit this. In this embodiment, the vehicle control unit is taken as an example for illustration.

[0067] It should be understood that the driving style parameters refer to the style parameters of the target user driving the vehicle. The driving style parameters include parameters such as Gin, Gmax, Gj, Gave, Gstd, Gtime, Vmax, Vave, Vstd, and Vtime. The specific units and specific meanings of the above driving style parameters are described in reference to Table 1, specifically:

[0068] Serial number Driving style parameter Unit Meaning description 1 Gin m / s^3 Acceleration impulse 2 Gmax m / s^2 Maximum acceleration 3 Gj m / s^3 Maximum value of acceleration change 4 Gave m / s^2 Average acceleration 5 Gstd - Standard deviation of acceleration 6 Gtime s Acceleration rise time 7 Vmax Km / h Maximum vehicle speed 8 Vave Km / h 9 Average vehicle speed - Vstd 10 Standard deviation of vehicle speed s Vtime

[0069] It can be understood that the characteristic parameters refer to the parameters with a relatively high degree of importance affecting the user's driving style. The characteristic parameters can be Gin, Gmax, and Gj. The driving style refers to the style of the target user when driving the vehicle. The driving style includes a comfortable driving style, a sporty driving style, and other types of driving styles. Specifically, the driving style parameters of the target user are extracted to obtain the characteristic parameters.

[0070] Step S20: Conduct clustering analysis on the feature parameters to obtain the corresponding driving style clustering centers.

[0071] It can be understood that the driving style clustering centers are specifically obtained by clustering the feature parameters through a target clustering analysis strategy, and the target clustering analysis strategy refers to a distance-based clustering analysis strategy. This target clustering analysis strategy can be the K-means analysis strategy, specifically: dividing the feature data into a predetermined K categories based on minimizing the error function, using distance as the similarity rating index, that is, the closer the distance, the higher the corresponding similarity. The driving style clustering centers refer to the centers after clustering the feature parameters of the driving style, and these driving style clustering centers can be three-class clustering centers or four-class clustering centers.

[0072] Furthermore, step S20 includes: obtaining the starting acceleration condition of the target vehicle; generating a corresponding acceleration feature parameter curve based on the starting acceleration condition and the feature parameters; obtaining the number of driving style categories; and conducting clustering analysis on the acceleration feature parameter curve through the target clustering analysis strategy according to the number of driving style categories to obtain the corresponding driving style clustering centers.

[0073] It should be understood that the starting acceleration condition refers to the condition when the target user just starts the vehicle for acceleration, and the acceleration feature parameter curve refers to the curve of the feature parameters under the starting acceleration condition. Through this acceleration feature parameter curve, the change trend of the feature parameters in a set time period can be reflected.

[0074] It can be understood that the number of driving style categories refers to the number of categories for clustering the feature parameters of the driving style. This number of driving style categories can be three-class driving style or four-class driving style. When the number of driving style categories is three-class driving style, clustering analysis is conducted on the acceleration feature parameter curve through the target clustering analysis strategy to obtain three-class clustering centers. Similarly, when the number of driving style categories is four-class driving style, clustering analysis is conducted on the acceleration feature parameter curve through the target clustering analysis strategy to obtain four-class clustering centers.

[0075] Step S30: Determine the weight proportion of the feature parameters according to the driving style clustering centers.

[0076] It should be understood that the weight proportion refers to the weight ratio of the feature parameters in the driving style. For example, if the feature parameters are Gin, Gmax, and Gj, the weight proportion of Gin determined through the driving style clustering centers is 36%, the weight proportion of Gmax is 22%, and the weight proportion of Gj is 42%.

[0077] Step S40: Generate a target acceleration pedal characteristic according to the weight proportion and the initial acceleration pedal characteristic, and make a customized recommendation for the target acceleration pedal characteristic.

[0078] It is understandable that the initial accelerator pedal characteristic refers to the conventional accelerator pedal characteristic, that is, the same accelerator pedal characteristic is recommended when different users drive the vehicle. The target accelerator pedal characteristic refers to the accelerator pedal characteristic that best fits the driving style of the target user. The target accelerator pedal characteristic is a customized accelerator pedal characteristic for the target user. Specifically, the initial accelerator pedal characteristic is modified by a correction coefficient to obtain the target accelerator pedal characteristic.

[0079] Further, step S40 includes: obtaining a preset basic feature parameter set; calculating a deviation of the feature parameter according to the preset basic feature parameter set to obtain a feature parameter deviation; calculating the feature parameter deviation through a target correction coefficient strategy to obtain a corresponding correction coefficient; generating a target accelerator pedal characteristic according to the correction coefficient and the initial accelerator pedal characteristic, and making a customized recommendation for the target accelerator pedal characteristic.

[0080] It is understandable that the preset basic feature parameter set refers to a set composed of the basic values of the feature parameters. For example, the basic feature parameter of Gj is Base Gj 、the basic feature parameter of Gin is Base Gin and the basic feature parameter of Gmax is Base Gmax , and then the feature parameter deviation is calculated through the preset basic feature parameter set. For example, the feature parameter deviation σ Gj of Gj = Gj / Base Gj 、the feature parameter deviation σ Gin of Gin = Gin / Base Gin and the feature parameter deviation σ Gmax of Gmax = Gmax / Base Gmax .

[0081] It should be understood that the target correction coefficient strategy refers to the strategy for correcting the coefficient of the driving style clustering center, that is, the correction coefficient is calculated through the target correction coefficient strategy. The specific calculation formula is the correction coefficient k = w1*σ Gmax +w2*σ Gj +w3*σ Gin , and the calculated correction coefficients are 0.807, 0996, and 1.205 respectively. Then, the initial accelerator pedal characteristic is corrected by the correction coefficient.

[0082] Further, generate a target accelerator pedal characteristic according to the correction coefficient and the initial accelerator pedal characteristic, and perform a customized recommendation on the target accelerator pedal characteristic, including: performing a multiplication calculation on the correction coefficient and the initial accelerator pedal characteristic to obtain a first accelerator pedal characteristic; performing a division calculation on the correction coefficient and the initial accelerator pedal characteristic to obtain a second accelerator pedal characteristic; and performing a customized recommendation on the first accelerator pedal characteristic and the second accelerator pedal characteristic.

[0083] It should be understood that there are two ways to correct the initial accelerator pedal characteristic by the correction coefficient. One is to adjust it by multiplication calculation, and the other is to adjust it by division. The first accelerator pedal characteristic refers to the characteristic after the correction coefficient adjusts the initial accelerator pedal characteristic by multiplication calculation, while the second accelerator pedal characteristic is the characteristic after the correction coefficient adjusts the initial accelerator pedal characteristic by division. Both the first accelerator pedal characteristic and the second accelerator pedal characteristic belong to the target accelerator pedal characteristic, and then a customized recommendation is made on the first accelerator pedal characteristic and the second accelerator pedal characteristic.

[0084] In this embodiment, the characteristic parameters of the driving style parameters of the target user are extracted; the characteristic parameters are clustered and analyzed through the target clustering analysis strategy to obtain the corresponding driving style clustering center; the weight ratio of the characteristic parameters is determined according to the driving style clustering center; the target accelerator pedal characteristic is generated according to the weight ratio and the initial accelerator pedal characteristic, and a customized recommendation is made on the target accelerator pedal characteristic. Since this embodiment performs clustering analysis on the characteristic parameters, then determines the weight ratio of the characteristic parameters according to the driving style clustering center, and then generates the target accelerator pedal characteristic based on the weight ratio and the initial accelerator pedal characteristic, compared with the prior art that recommends the same accelerator pedal characteristic, it can customize and recommend the accelerator pedal characteristic that matches the user's driving style, thereby improving the user's driving experience.

[0085] In one embodiment, as Acceleration time described, a second embodiment of the customized recommendation method for the accelerator pedal characteristic of the present invention is proposed based on the first embodiment. The step S10 includes:

[0086] Step S101, construct a driving style hierarchical structure model for the driving style parameters of the target user through an analytic hierarchy process strategy.

[0087] It should be understood that the Analytic Hierarchy Process (AHP) refers to a strategy of dividing parameters into different levels and conducting qualitative and quantitative analyses. Specifically, it combines quantitative analysis with qualitative analysis, uses the decision maker's experience to judge the relative importance between the criteria for measuring whether each goal can be achieved, reasonably gives the weight of each criterion for each decision-making scheme, and uses the weights to find the superiority and inferiority order of each scheme. In this embodiment, the corresponding characteristic parameters are selected through the Analytic Hierarchy Process.

[0088] It can be understood that the driving style hierarchy model refers to a structural model constructed through driving style parameters. Through this driving style hierarchy model, the importance between different driving style parameters can be determined. The driving style parameter with a higher importance is ranked higher in the driving style hierarchy model. Refer to Figure 3 , Figure 4 is a schematic diagram of the driving style hierarchy model, specifically the driving style parameters and characteristic parameters. The driving style parameters are placed according to the illustrated positions, with the characteristic parameters on the upper layer and the driving style parameters on the bottom layer.

[0089] Step S102, generate a driving style parameter comparison matrix according to the target parameter-scale relationship and the driving style hierarchy model.

[0090] It can be understood that the target parameter-scale relationship refers to the relationship between each parameter and the set scale. Specifically, it is set according to the importance of the driving style parameter relative to the user's driving style. For example, the importance of the driving style parameter is as follows: the i parameter and the j parameter are equally important, and the scale is set to 1; the i parameter is slightly more important than the j parameter, and the scale is set to 3; the i parameter is relatively more important than the j parameter, and the scale is set to 5, etc. And the driving style parameter comparison matrix is generated based on the above relationship. Specifically:

[0091]

[0092] Among them, a ij , a ji and a ii are the specific data of the driving style parameter comparison matrix. The i parameter and the j parameter are any driving style parameters in the driving style hierarchy model. The importance between the i parameter and the j parameter is between 2n - 1 and 2n + 1. For example, when the i parameter is Gj, the j parameter is any driving style parameter including Gj, such as Gin or Gmax.

[0093] Further, step S102 includes: determining the relative importance degree of driving style parameters according to the target orientation measurement data and the user's real vehicle evaluation data; obtaining the corresponding parameter scale values according to the target parameter-scale relationship and the relative importance degree; respectively performing ratio calculations on the parameter scale values to obtain the corresponding scale numerical values; and generating a driving style parameter comparison matrix according to the scale numerical values and the driving style hierarchy model.

[0094] It should be understood that the relative importance degree refers to the importance degree of driving style parameters to the user's driving style. For example, the acceleration G is a direct experience of the user's driving demand, and the vehicle speed V is a display form. Relatively speaking, the acceleration G can better reflect the driving demand. Therefore, the acceleration G is more important than the vehicle speed V with respect to the user's driving style. Then, the importance degree of each parameter in the acceleration G is determined through the target orientation measurement data and the user's real vehicle evaluation data. Specifically, it is obtained through the target orientation measurement data and the user's real vehicle evaluation data that there is a completely positive correlation between the user's driving style and Gj. Therefore, Gj has the most important influence on the driving style relative to other driving style parameters. Since Gin = Gmax / Gtime, it can be inferred from this relational expression that Gin, Gmax, and Gtime have the same importance degree on the driving style.

[0095] It can be understood that after obtaining the parameter scale values, ratio calculations are performed between the parameter scale values to obtain the corresponding scale numerical values. For example, if Gj is slightly more important than Gin, then the scale numerical value = Gj / Gin = 1 / 3. Then, a driving style parameter comparison matrix is generated according to the scale numerical values and the driving style hierarchy model. Referring to Table 2, specifically:

[0096] Figure 4 Gj Gin ... Gmax Vmax Vave 1 3 3 ... 9 9 Gj 1 / 3 1 1 ... 8 8 Gin 1 / 3 1 1 ... 8 8 ... ... ... ... ... ... ... Gmax 1 / 9 1 / 8 1 / 8 1 / 5 1 1 Vmax 1 / 9 1 / 8 1 / 8 1 / 5 1 1

[0097] Step S103, extracting the corresponding characteristic parameters for the driving style parameters according to the driving style parameter comparison matrix.

[0098] It should be understood that after obtaining the driving style parameter comparison matrix, the weight coefficients of the influence of each driving style parameter on the driving style parameter are obtained through this driving style parameter comparison matrix. Then, the corresponding characteristic parameters are extracted through this weight coefficient. The characteristic parameters are Gj, Gin, and Gmax.

[0099] Further, step S103 includes: performing hierarchical single sorting on the driving style parameters through the driving style parameter comparison matrix to obtain the corresponding driving style parameter sorting result; performing consistency verification on the driving style parameter sorting result; and when the parameter verification result passes the verification, extracting the corresponding characteristic parameters for the driving style parameters.

[0100] It can be understood that after obtaining the driving style parameter comparison matrix, the column vectors of the driving style parameter comparison matrix are normalized by using the simplified calculation method of the maximum eigenvalue and eigenvector of the positive reciprocal matrix. Then, the parameters in the processed matrix are summed, and the sum result is normalized to obtain the corresponding weight coefficients. Then, the weight coefficients are subjected to a single-layer ranking of the hierarchy to obtain the corresponding driving style parameter ranking result. Referring to Table 3, specifically:

[0101] Vave Gj Gin ... Gmax Vmax 0.288 0.147 0.147 ... 0.019 0.019

[0102] It can be understood that after obtaining the driving style parameter ranking result, a consistency check is performed on the driving style parameter ranking result. When the check passes, the three driving style parameters with the largest weight coefficients in the driving style parameter ranking result are extracted, and these three driving style parameters are used as characteristic parameters.

[0103] In this embodiment, the driving style parameters of the target user are constructed through an analytic hierarchy process strategy to obtain a driving style hierarchy model; a driving style parameter comparison matrix is generated according to the target parameter-scale relationship and the driving style hierarchy model; the driving style parameters are extracted according to the driving style parameter comparison matrix to obtain corresponding characteristic parameters; since this embodiment constructs a driving style hierarchy model of the driving style parameters of the target user through an analytic hierarchy process strategy, then generates a driving style parameter comparison matrix according to the target parameter-scale relationship and the driving style hierarchy model, and then extracts characteristic parameters from the driving style parameters based on the driving style parameter comparison matrix, it can effectively improve the accuracy of obtaining the characteristic parameters.

[0104] In one embodiment, as Vave described, based on the first embodiment, the third embodiment of the customized recommendation method for the accelerator pedal characteristics of the present invention is proposed. The step S30 includes:

[0105] Step S301, calculate the driving style clustering center through the coefficient of variation algorithm to obtain the corresponding coefficient of variation.

[0106] It should be understood that the coefficient of variation algorithm refers to an important index for depicting the trend driving style clustering center, which reflects the differences and fluctuations of the values. The coefficient of variation of the driving style clustering center is calculated through the coefficient of variation algorithm. For example, the coefficient of variation of Gj is 0.432, the coefficient of variation of Gin is 0.363, and the coefficient of variation of Gmax is 0.221.

[0107] Step S302, normalize the coefficient of variation to obtain the weight proportion of the characteristic parameters.

[0108] It can be understood that the weight ratio refers to the weight ratio of the feature parameters in the driving style. The weight ratio can be obtained by normalizing the coefficient of variation, and the weight ratios of the three parameters Gj, Gin, and Gmax in the driving style recognition are obtained. The weight ratio of Gin is 36%, the weight ratio of Gmax is 22%, and the weight ratio of Gj is 42%.

[0109] In this embodiment, the coefficient of variation algorithm is used to calculate the clustering center of the driving style to obtain the corresponding coefficient of variation; the coefficient of variation is normalized to obtain the weight ratio of the feature parameters. Since this embodiment calculates the clustering center of the driving style through the coefficient of variation algorithm, the corresponding coefficient of variation, and then normalizes the variation parameter, it can effectively improve the accuracy of obtaining the weight ratio of the feature parameters, and further improve the rationality of customizing the recommended acceleration pedal characteristics.

[0110] In addition, an embodiment of the present invention also provides a storage medium, on which a customized recommendation program for the acceleration pedal characteristics is stored. When the customized recommendation program for the acceleration pedal characteristics is executed by a processor, the steps of the customized recommendation method for the acceleration pedal characteristics as described above are implemented.

[0111] Since this storage medium adopts all the technical solutions of the above-mentioned all embodiments, it at least has all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, and will not be elaborated here one by one.

[0112] In addition, referring to Figure 5 Figure 6 , an embodiment of the present invention also provides a customized recommendation device for the acceleration pedal characteristics. The customized recommendation device for the acceleration pedal characteristics includes:

[0113] An extraction module, configured to extract the feature parameters of the driving style parameters of the target user.

[0114] An analysis module, configured to perform clustering analysis on the feature parameters to obtain the corresponding driving style clustering center.

[0115] A determination module, configured to determine the weight ratio of the feature parameters according to the driving style clustering center.

[0116] A customized recommendation module, configured to generate target acceleration pedal characteristics according to the weight ratio and the initial acceleration pedal characteristics, and perform customized recommendation on the target acceleration pedal characteristics.

[0117] In this embodiment, the characteristic parameters of the driving style parameters of the target user are extracted; the characteristic parameters are subjected to clustering analysis through a target clustering analysis strategy to obtain corresponding driving style clustering centers; the weight ratio of the characteristic parameters is determined according to the driving style clustering centers; a target accelerator pedal characteristic is generated according to the weight ratio and the initial accelerator pedal characteristic, and the target accelerator pedal characteristic is customized and recommended; since in this embodiment, clustering analysis is performed on the characteristic parameters, then the weight ratio of the characteristic parameters is determined according to the driving style clustering centers, and then a target accelerator pedal characteristic is generated based on the weight ratio and the initial accelerator pedal characteristic, compared with the prior art that recommends the same accelerator pedal characteristics, it can customize and recommend accelerator pedal characteristics that match the user's driving style, thereby improving the user's driving experience.

[0118] It should be noted that the above-described work process is only illustrative and does not limit the protection scope of the present invention. In actual applications, those skilled in the art can select some or all of them according to actual needs to achieve the purpose of the solution of this embodiment, and no limitation is made here.

[0119] In addition, for the technical details not described in detail in this embodiment, reference can be made to the customized recommendation method for accelerator pedal characteristics provided in any embodiment of the present invention, which will not be elaborated here.

[0120] In one embodiment, the extraction module 10 is further configured to construct a driving style hierarchical structure model for the driving style parameters of the target user through an analytic hierarchy process strategy; generate a driving style parameter comparison matrix according to the target parameter-scale relationship and the driving style hierarchical structure model; extract the driving style parameters according to the driving style parameter comparison matrix to obtain corresponding characteristic parameters.

[0121] In one embodiment, the extraction module 10 is further configured to determine the relative importance degree of the driving style parameters according to the target orientation measurement data and the user's real vehicle evaluation data; obtain corresponding parameter scale values according to the target parameter-scale relationship and the relative importance degree; respectively perform ratio calculations on the parameter scale values to obtain corresponding scale numerical values; generate a driving style parameter comparison matrix according to the scale numerical values and the driving style hierarchical structure model.

[0122] In one embodiment, the extraction module 10 is further configured to perform a hierarchical single sorting on the driving style parameters through the driving style parameter comparison matrix to obtain a corresponding driving style parameter sorting result; perform a consistency check on the driving style parameter sorting result; when the parameter check result is passed, extract the driving style parameters to obtain corresponding characteristic parameters.

[0123] In one embodiment, the analysis module 20 is further configured to obtain the starting acceleration condition of the target vehicle; generate a corresponding acceleration characteristic parameter curve according to the starting acceleration condition and the characteristic parameters; obtain the number of driving style categories; and perform clustering analysis on the acceleration characteristic parameter curve through a target clustering analysis strategy according to the number of driving style categories to obtain corresponding driving style clustering centers.

[0124] In one embodiment, the determination module 30 is further configured to calculate the driving style clustering center through a coefficient of variation algorithm to obtain a corresponding coefficient of variation; and perform normalization processing on the coefficient of variation to obtain the weight ratio of the characteristic parameters.

[0125] In one embodiment, the recommendation module 40 is further configured to obtain a preset basic characteristic parameter set; calculate a deviation of the characteristic parameters according to the preset basic characteristic parameter set to obtain a characteristic parameter deviation; and calculate a corresponding correction coefficient through a target correction coefficient strategy for the characteristic parameter deviation and the weight ratio.

[0126] In one embodiment, the recommendation module 40 is further configured to the target accelerator pedal characteristics include first accelerator pedal characteristics and second accelerator pedal characteristics; perform multiplication calculation on the correction coefficient and the initial accelerator pedal characteristics to obtain the first accelerator pedal characteristics; perform division calculation on the correction coefficient and the initial accelerator pedal characteristics to obtain the second accelerator pedal characteristics; and perform customized recommendation on the first accelerator pedal characteristics and the second accelerator pedal characteristics.

[0127] For other embodiments or implementation methods of the customized recommendation device for the accelerator pedal characteristics of the present invention, reference may be made to the above method embodiments, and details are not repeated here.

[0128] In addition, it should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0129] The serial numbers of the embodiments of the present invention above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0130] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a Read Only Memory (ROM) / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, integrated platform workstation, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0131] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A customized recommendation method for accelerator pedal characteristics, characterized in that, The customized recommendation method for the accelerator pedal characteristics includes the following steps: Extract the characteristic parameters of the driving style parameters of the target user; Perform cluster analysis on the characteristic parameters to obtain the corresponding driving style cluster centers; Determine the weight ratio of the characteristic parameters according to the driving style cluster centers; Generate the target accelerator pedal characteristics according to the weight ratio and the initial accelerator pedal characteristics, and make a customized recommendation for the target accelerator pedal characteristics; The determination of the weight ratio of the characteristic parameters according to the driving style cluster centers includes: Calculate the driving style cluster centers through the coefficient of variation algorithm to obtain the corresponding coefficients of variation; Perform normalization processing on the coefficients of variation to obtain the weight ratio of the characteristic parameters; The generation of the target accelerator pedal characteristics according to the weight ratio and the initial accelerator pedal characteristics, and the customized recommendation of the target accelerator pedal characteristics include: Obtain the preset basic characteristic parameter set; Calculate the deviation of the characteristic parameters of the target user according to the preset basic characteristic parameter set to obtain the characteristic parameter deviation; Calculate the characteristic parameter deviation and the weight ratio through the target correction coefficient strategy to obtain the corresponding correction coefficients; Generate the target accelerator pedal characteristics according to the correction coefficients and the initial accelerator pedal characteristics, and make a customized recommendation for the target accelerator pedal characteristics.

2. The customized recommendation method for the accelerator pedal characteristics according to claim 1, wherein The extraction of the characteristic parameters of the driving style parameters of the target user includes: Construct the driving style parameters of the target user through the analytic hierarchy process strategy to obtain the driving style hierarchy model; Generate the driving style parameter comparison matrix according to the target parameter-scale relationship and the driving style hierarchy model; Extract the driving style parameters according to the driving style parameter comparison matrix to obtain the corresponding characteristic parameters.

3. The customized recommendation method for the accelerator pedal characteristics according to claim 2, characterized in that The generation of the driving style parameter comparison matrix according to the target parameter-scale relationship and the driving style hierarchy model includes: Determine the relative importance degree of the driving style parameters according to the target orientation measurement data and the user's real vehicle evaluation data; Obtain the corresponding parameter scale values according to the target parameter-scale relationship and the relative importance degree; Perform ratio calculations on the parameter scale values respectively to obtain the corresponding scale values; Generate the driving style parameter comparison matrix according to the scale values and the driving style hierarchy model.

4. The customized recommendation method for the accelerator pedal characteristics according to claim 2, wherein The extraction of the corresponding characteristic parameters by extracting the driving style parameters according to the driving style parameter comparison matrix includes: Perform hierarchical single sorting on the driving style parameters through the driving style parameter comparison matrix to obtain the corresponding driving style parameter sorting results; Perform consistency verification on the driving style parameter sorting results; When the parameter verification result is verified to pass, extract the driving style parameters to obtain the corresponding characteristic parameters.

5. The customized recommendation method for the accelerator pedal characteristics according to claim 1, wherein The cluster analysis of the characteristic parameters to obtain the corresponding driving style cluster centers includes: Obtain the starting acceleration condition of the target vehicle; Generate the corresponding acceleration characteristic parameter curve according to the starting acceleration condition and the characteristic parameters; Obtain the number of driving style categories; Cluster analysis is performed on the acceleration characteristic parameter curve according to the number of driving style categories through a target clustering analysis strategy to obtain corresponding driving style clustering centers.

6. The customized recommendation method for the accelerator pedal characteristics according to claim 1, wherein The target accelerator pedal characteristics include first accelerator pedal characteristics and second accelerator pedal characteristics; Generate target accelerator pedal characteristics according to the correction coefficient and the initial accelerator pedal characteristics, and perform customized recommendation on the target accelerator pedal characteristics, including: Perform multiplication calculation on the correction coefficient and the initial accelerator pedal characteristics to obtain first accelerator pedal characteristics; Perform division calculation on the correction coefficient and the initial accelerator pedal characteristics to obtain second accelerator pedal characteristics; Perform customized recommendation on the first accelerator pedal characteristics and the second accelerator pedal characteristics.

7. A customized recommendation device for accelerator pedal characteristics, characterized in that The customized recommendation device for accelerator pedal characteristics includes: An extraction module, configured to extract characteristic parameters of driving style parameters of a target user; An analysis module, configured to perform cluster analysis on the characteristic parameters to obtain corresponding driving style clustering centers; A determination module, configured to determine the weight ratio of the characteristic parameters according to the driving style clustering centers; A customized recommendation module, configured to generate target accelerator pedal characteristics according to the weight ratio and the initial accelerator pedal characteristics, and perform customized recommendation on the target accelerator pedal characteristics; The determination module is further configured to calculate the corresponding coefficient of variation through a coefficient of variation algorithm for the driving style clustering centers; perform normalization processing on the coefficient of variation to obtain the weight ratio of the characteristic parameters; The customized recommendation module is further configured to obtain a preset basic characteristic parameter set; calculate a characteristic parameter deviation according to the preset basic characteristic parameter set for the characteristic parameters of the target user; calculate a corresponding correction coefficient through a target correction coefficient strategy for the characteristic parameter deviation and the weight ratio; generate target accelerator pedal characteristics according to the correction coefficient and the initial accelerator pedal characteristics, and perform customized recommendation on the target accelerator pedal characteristics.

8. A customized recommendation device for accelerator pedal characteristics, characterized in that, The customized recommendation device for accelerator pedal characteristics includes: a memory, a processor, and a customized recommendation program for accelerator pedal characteristics stored on the memory and executable on the processor, and the customized recommendation program for accelerator pedal characteristics is configured to implement the customized recommendation method for accelerator pedal characteristics according to any one of claims 1 to 6.

9. A storage medium, characterized in that, A customized recommendation program for accelerator pedal characteristics is stored on the storage medium, and when the customized recommendation program for accelerator pedal characteristics is executed by a processor, it implements the customized recommendation method for accelerator pedal characteristics according to any one of claims 1 to 6.

Images