Vehicle control methods, devices, vehicles, storage media, and software products

Abstract

This invention discloses a vehicle control method, device, vehicle, storage medium, and program product. The method includes: acquiring historical driving parameters of the vehicle during a user's driving over a historical time period; extracting features from the historical driving parameters to obtain user driving characteristics; identifying the user's driving characteristics based on a style recognition model to obtain the user's driving style; and controlling vehicle operation based on the user's driving style in response to detecting user driving, thereby assisting the user in driving. This invention solves the technical problem of poor effectiveness in assisting user driving based on driving style in related technologies.

Description

Technical Field

[0001] This invention relates to the field of vehicle control, and more specifically, to a vehicle control method, apparatus, vehicle, storage medium, and program product. Background Technology

[0002] Today, with the development of electronic technology, the driving experience of automobiles has received widespread attention. Different users may have different driving habits and corresponding driving styles. In order to improve the user's driving experience, different on-board devices or vehicle driving parameters can be controlled according to the user's driving style. However, currently, when determining the driving style of different users, a single classification model is usually used to classify the user's driving habits to form the user's driving style. As a result, the actual determined driving style may not meet the user's expectations, and the actual effect of assisting the user to drive the vehicle based on the identified driving style is not ideal.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a vehicle control method, device, vehicle, storage medium, and program product to at least solve the technical problem in the related art that the effect of assisting users in driving vehicles based on their driving style is poor.

[0005] According to one aspect of the present invention, a vehicle control method is provided, comprising: acquiring historical driving parameters of a vehicle during a historical time period; extracting features from the historical driving parameters to obtain user driving features; identifying the user driving features based on a style recognition model to obtain the user's driving style, wherein the style recognition model includes multiple style classifiers, different style classifiers have different classification weights for classifying different preset driving styles, the preset driving styles include the user driving style, the user driving style is used to characterize the style obtained by summarizing multiple classification results obtained by the style classifiers classifying the user driving features based on the classification weights, and the classification results are used to characterize the degree of matching between the user driving features and different preset driving styles under different style classifiers; and controlling the vehicle operation based on the user driving style in response to detecting that the user is driving the vehicle, so as to assist the user in driving the vehicle.

[0006] Furthermore, the user's driving characteristics are identified based on the style recognition model to obtain the user's driving style, including: evaluating the importance of the user's driving characteristics according to a preset evaluation method to obtain the first importance index of the user's driving characteristics to historical driving parameters; selecting at least one target driving characteristic from the user's driving characteristics based on the first importance index; and inputting the target driving characteristic into the style recognition model to obtain the user's driving style.

[0007] Furthermore, the importance of user driving features is assessed according to a preset evaluation method to obtain the first importance index of user driving features relative to historical driving parameters. This includes: aligning user driving features and historical driving parameters to obtain a first observation value corresponding to the user driving features and a second observation value corresponding to the historical driving parameters; determining the correlation coefficient between user driving features and historical driving parameters based on the first and second observation values; and inputting user driving features into an ensemble learning model based on the correlation coefficient to obtain the first importance index.

[0008] Furthermore, controlling vehicle operation based on the user's driving style includes: obtaining vehicle control parameters matching the user's driving style from a parameter library, wherein the parameter library is used to store the correlation between the user's driving style and the vehicle control parameters; outputting the vehicle control parameters in the operation interface and receiving parameter adjustment instructions from the user; adjusting the vehicle control parameters based on the parameter adjustment instructions to obtain target control parameters; and controlling vehicle operation based on the target control parameters.

[0009] Furthermore, based on the style recognition model, the user's driving characteristics are identified to obtain the user's driving style, including: dividing multiple classification results based on preset driving styles to obtain multiple classification result sets, wherein the preset driving styles corresponding to the classification results contained in the same classification result set are the same; merging the classification results in each classification result combination based on the classification weights corresponding to the classification results in each classification result set to obtain a target classification result, wherein the target classification result is used to characterize the degree of matching between the user's driving characteristics and the preset driving styles corresponding to the classification result sets; and determining the user's driving style from the preset driving styles based on the target classification result.

[0010] Furthermore, the above method also includes: obtaining sample driving parameters corresponding to at least one preset driving style; extracting features from the sample driving parameters to obtain at least one sample driving feature; inputting the sample driving feature into an initial recognition model to obtain an initial recognition result corresponding to the sample driving parameters; and adjusting the initial recognition model based on the initial recognition result and the preset driving style to obtain a style recognition model.

[0011] Further, the sample driving features are input into the initial recognition model to obtain the initial recognition result corresponding to the sample driving parameters, including: evaluating the importance of the sample driving features according to a preset evaluation method to obtain the second importance index of the sample driving features to the sample driving parameters; ranking the second importance indexes, and selecting at least one target sample feature from the sample driving features based on the ranking result, wherein the second importance index corresponding to the target sample feature is greater than the second importance index corresponding to other sample features in the sample driving features excluding the target sample feature; inputting the target sample feature into the initial recognition model to obtain the initial recognition result.

[0012] Furthermore, the initial recognition model includes at least multiple initial classifiers, and the initial recognition result includes multiple initial classification results obtained by classifying the target sample features by the multiple initial classifiers. Based on the initial recognition results and a preset driving style, the initial recognition model is adjusted to obtain a style recognition model, including: matching the multiple initial classification results with the preset driving style to obtain multiple first matching results; adjusting the initial classifiers based on the multiple first matching results to obtain multiple style classifiers; matching the multiple style classification results with the preset driving style to obtain multiple second matching results, wherein the style classification results are used to characterize the classification results obtained by inputting the target sample features into the style classifiers; determining the classification weights of the style classifiers relative to the preset driving style based on the multiple second matching results; and constructing a style recognition model based on the classification weights and the multiple style classifiers.

[0013] According to one aspect of the present invention, a vehicle control device is also provided, characterized in that it includes: a parameter acquisition module, used to acquire historical driving parameters of the vehicle when a user drives the vehicle within a historical time period; a feature extraction module, used to extract features from the historical driving parameters to obtain user driving features; a style recognition module, used to identify the user driving features based on a style recognition model to obtain the user's driving style, wherein the style recognition model includes multiple style classifiers, different style classifiers have different classification weights for classifying different preset driving styles, the preset driving styles include the user driving style, the user driving style is used to characterize the style obtained by summarizing multiple classification results obtained by the style classifiers classifying the user driving features based on the classification weights, and the classification results are used to characterize the degree of matching between the user driving features and different preset driving styles under different style classifiers; and a vehicle control module, used to control the vehicle operation based on the user driving style in response to detecting that the user is driving the vehicle, so as to assist the user in driving the vehicle.

[0014] Furthermore, the style recognition module includes: an importance assessment unit, used to assess the importance of user driving features according to a preset assessment method to obtain the first importance index of user driving features to historical driving parameters; a feature selection unit, used to select at least one target driving feature from user driving features based on the first importance index; and a style recognition unit, used to input the target driving feature into the style recognition model to obtain the user driving style.

[0015] Furthermore, the importance assessment unit is also used to: align user driving characteristics and historical driving parameters to obtain a first observation value corresponding to the user driving characteristics and a second observation value corresponding to the historical driving parameters; determine the correlation coefficient between the user driving characteristics and the historical driving parameters based on the first and second observation values; and input the user driving characteristics into the ensemble learning model based on the correlation coefficient to obtain the first importance index.

[0016] Furthermore, the vehicle control module includes: a parameter acquisition unit, used to acquire vehicle control parameters matching the user's driving style from a parameter library, wherein the parameter library is used to store the correlation between the user's driving style and the vehicle control parameters; an instruction receiving unit, used to output the vehicle control parameters in the operation interface and receive parameter adjustment instructions from the user; a parameter adjustment unit, used to adjust the vehicle control parameters based on the parameter adjustment instructions to obtain the target control parameters; and a vehicle control unit, used to control the vehicle operation based on the target control parameters.

[0017] Furthermore, the style recognition module includes: a result segmentation unit, used to segment multiple classification results based on a preset driving style to obtain multiple classification result sets, wherein the preset driving styles corresponding to the classification results contained in the same classification result set are the same; a result merging unit, used to merge the classification results in each classification result combination based on the classification weights corresponding to the classification results in each classification result set to obtain a target classification result, wherein the target classification result is used to characterize the degree of matching between the user's driving characteristics and the preset driving style corresponding to the classification result set; and a style determination unit, used to determine the user's driving style from the preset driving styles based on the target classification result.

[0018] Furthermore, the above-mentioned device also includes: a sample acquisition module for acquiring sample driving parameters corresponding to at least one preset driving style; a feature extraction module for extracting features from the sample driving parameters to obtain at least one sample driving feature; an initial recognition module for inputting the sample driving feature into an initial recognition model to obtain an initial recognition result corresponding to the sample driving parameters; and a model adjustment module for adjusting the initial recognition model based on the initial recognition result and the preset driving style to obtain a style recognition model.

[0019] Furthermore, the initial identification module includes: a sample feature evaluation unit, used to evaluate the importance of sample driving features according to a preset evaluation method, and obtain the second importance index of the sample driving features to the sample driving parameters; a sample feature selection unit, used to rank the second importance index, and select at least one target sample feature from the sample driving features based on the ranking result, wherein the second importance index corresponding to the target sample feature is greater than the second importance index corresponding to other sample features in the sample driving features excluding the target sample feature; and a sample identification unit, used to input the target sample feature into the initial identification model to obtain the initial identification result.

[0020] Furthermore, the initial recognition model includes at least multiple initial classifiers, and the initial recognition result includes multiple initial classification results obtained by classifying the target sample features by the multiple initial classifiers. The model adjustment module includes: a first matching unit, used to match the multiple initial classification results with a preset driving style to obtain multiple first matching results; a classifier adjustment unit, used to adjust the initial classifiers based on the multiple first matching results to obtain multiple style classifiers; a second matching unit, used to match the multiple style classification results with a preset driving style to obtain multiple second matching results, wherein the style classification results are used to characterize the classification results obtained by inputting the target sample features into the style classifiers; a weight determination unit, used to determine the classification weights of the style classifiers relative to the preset driving style based on the multiple second matching results; and a model construction unit, used to construct a style recognition model based on the classification weights and multiple style classifiers.

[0021] According to another aspect of the present invention, a vehicle is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention during runtime.

[0022] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0023] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0024] According to another aspect of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0025] According to another aspect of the present invention, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of the present invention.

[0026] In this embodiment of the invention, the following methods are employed: acquiring historical driving parameters of a vehicle during a user's driving over a historical time period; extracting features from the historical driving parameters to obtain user driving features; identifying the user driving features based on a style recognition model to obtain the user's driving style; and controlling vehicle operation based on the user's driving style in response to detecting the user driving the vehicle, thereby assisting the user in driving. This is achieved by using multiple style classifiers configured in the style recognition model to classify the user driving features, and then summarizing the classification results output by the style classifiers according to the classification weights between different style classifiers and different style types to obtain a user driving style with a high degree of matching with the user. This effectively improves the accuracy of the determined user driving style and enhances the effect of using the driving parameters corresponding to that user driving style to assist the user in driving the vehicle, thereby improving the user's driving experience and solving the technical problem of poor effectiveness of assisting the user in driving the vehicle based on the user's driving style in related technologies. Attached Figure Description

[0027] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0028] Figure 1 This is a flowchart illustrating a vehicle control method according to an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram illustrating a target driving feature selection process according to an embodiment of this application;

[0030] Figure 3 This is a schematic diagram illustrating a process for determining an importance index according to an embodiment of this application;

[0031] Figure 4 This is a structural block diagram of a vehicle control device according to an embodiment of this application. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Example 1

[0035] According to an embodiment of the present invention, a method embodiment for vehicle control is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0036] Figure 1 This is a flowchart illustrating a vehicle control method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0037] Step S102: Obtain the historical driving parameters of the vehicle during the user's driving process within the historical time period.

[0038] In one optional embodiment, considering that a user's driving style may differ at different times due to personal habits, living environment, and other factors, the vehicle control system can first determine whether the user's current driving style has changed in order to accurately determine the user's driving style. For example, it can obtain usage data of the in-vehicle devices the user typically uses while driving, driving data generated during driving, and other parameters, and determine whether these parameters have changed significantly. If not, it can be preliminarily determined that the user's current driving style has not changed; if so, it can be considered that the user's current driving style has changed. If it is determined that the user's current driving style may have changed, or if the driving style of the user currently driving the vehicle is not found in the database used to store the driving styles of different users, the vehicle control system can identify the user's current driving style and control the vehicle operation according to the user's driving style to assist the user in driving the vehicle. Based on this, when determining a user's current driving style, the vehicle control system can first acquire historical driving parameters generated by the user during driving within a historical time period, such as the past month or the last five driving periods. These parameters include equipment usage data such as the usage time of the vehicle's air conditioning and the volume of the audio system, as well as vehicle driving data such as vehicle speed, acceleration, and accelerator pedal opening. This ensures that the acquired historical driving parameters can sufficiently and comprehensively reflect the user's current driving style, thereby improving the accuracy of identifying the user's driving style based on historical driving parameters.

[0039] Step S104: Extract features from historical driving parameters to obtain user driving features.

[0040] In one optional embodiment, after obtaining the historical driving parameters of the user driving the vehicle, the vehicle control system can further extract features from the historical driving parameters to obtain user driving features that match the user's driving style. For example, 44 feature components can be extracted from the historical driving parameters to describe the driving style.

[0041] In one optional embodiment, considering that there may be a lot of noisy data in the acquired historical driving parameters, the corresponding user driving features extracted from the historical driving parameters will also contain a lot of noisy data. Therefore, after feature extraction from the historical parameters, the extracted user driving features can also be denoised. For example, the Euclidean distance between different user driving features can be determined, and discrete points can be determined from the data points corresponding to different user driving features based on the Euclidean distance, so as to remove the user driving features corresponding to the discrete points, thereby obtaining more accurate user driving features.

[0042] The formula for determining the Euclidean distance can be:

[0043]

[0044] Where d(Q, C) can refer to the Euclidean distance between data point Q and data point C, and q i and c i Let be the i-th feature components of data point Q and data point C, respectively, and n be the total number of features.

[0045] Step S106: Based on the style recognition model, identify the user's driving characteristics to obtain the user's driving style.

[0046] The style recognition model includes multiple style classifiers. Different style classifiers have different classification weights for classifying different preset driving styles. The preset driving styles include user driving styles. The user driving style is used to represent the style obtained by summarizing multiple classification results obtained by the style classifiers for classifying user driving features based on classification weights. The classification results are used to represent the degree of matching between user driving features and different preset driving styles under different style classifiers.

[0047] In one optional embodiment, after extracting the user driving features corresponding to the historical driving parameters, the vehicle control system can input the user driving features into a pre-trained style recognition model to determine the user's current driving style, that is, to determine the aforementioned user driving style.

[0048] In one optional embodiment, to ensure the accuracy of the determined user driving style, multiple pre-trained style classifiers can be configured in the style recognition model. Different style classifiers have different recognition focuses; for example, style classifier A can primarily identify a preset driving style A, while style classifier B can primarily identify a preset driving style B. That is, the parameters configured in different style classifiers are different, and the classification weights for different preset driving styles vary. The user driving style identified by the style recognition model can be one of the preset driving styles. When using the style recognition model to identify user driving features, the user driving features can be input into the multiple style classifiers to obtain multiple classification results. That is, under different style classifiers, the degree of matching between the user driving features and different preset driving styles is determined. Then, the classification weights corresponding to each style classifier are used to summarize the multiple classification results to determine the user driving style that matches the user driving features from the multiple preset driving styles.

[0049] In step S108, in response to detecting that the user is driving the vehicle, the vehicle operation is controlled based on the user's driving style to assist the user in driving the vehicle.

[0050] After identifying a user's driving style, the vehicle control system can store the user's identity information and the identified driving style in a preset style database. When a user is detected driving the vehicle, the vehicle control system can identify the user's identity information, retrieve the user's driving style that matches the identity information from the style database, and control the vehicle's operation according to the user's driving style. For example, it can control different on-board devices to operate according to specified parameters, control the vehicle's speed to maintain a stable speed range, etc., to assist the user in driving the vehicle and thus provide the user with a better driving experience.

[0051] In this embodiment of the invention, the following methods are employed: acquiring historical driving parameters of a vehicle during a user's driving over a historical time period; extracting features from the historical driving parameters to obtain user driving features; identifying the user driving features based on a style recognition model to obtain the user's driving style; and controlling vehicle operation based on the user's driving style in response to detecting the user driving the vehicle, thereby assisting the user in driving. This is achieved by using multiple style classifiers configured in the style recognition model to classify the user driving features, and then summarizing the classification results output by the style classifiers according to the classification weights between different style classifiers and different style types to obtain a user driving style with a high degree of matching with the user. This effectively improves the accuracy of the determined user driving style and enhances the effect of using the driving parameters corresponding to that user driving style to assist the user in driving the vehicle, thereby improving the user's driving experience and solving the technical problem of poor effectiveness of assisting the user in driving the vehicle based on the user's driving style in related technologies.

[0052] Furthermore, the user's driving characteristics are identified based on the style recognition model to obtain the user's driving style, including: evaluating the importance of the user's driving characteristics according to a preset evaluation method to obtain the first importance index of the user's driving characteristics to historical driving parameters; selecting at least one target driving characteristic from the user's driving characteristics based on the first importance index; and inputting the target driving characteristic into the style recognition model to obtain the user's driving style.

[0053] In one optional embodiment, considering that a large number of features may be extracted from driving parameters, but only a portion of these features may actually be related to the user's driving style, when using a style recognition model to identify the user's driving features to determine the user's driving style, the importance of the extracted user features can be evaluated first to determine the importance of different user driving features relative to historical driving parameters, i.e., to determine the aforementioned first importance index. The larger the importance index, the closer the relationship between the user driving feature and the historical driving parameters, and the more accurate the user driving style determined by the user driving feature. Based on this, after obtaining the first importance index of different user driving features relative to historical driving parameters, the vehicle control system can select at least one target driving feature that can reflect the user's driving style from the user driving features according to the first importance index, and then input the target driving feature into the aforementioned style recognition model to determine the user's current driving style.

[0054] Furthermore, the importance of user driving features is assessed according to a preset evaluation method to obtain the first importance index of user driving features relative to historical driving parameters. This includes: aligning user driving features and historical driving parameters to obtain a first observation value corresponding to the user driving features and a second observation value corresponding to the historical driving parameters; determining the correlation coefficient between user driving features and historical driving parameters based on the first and second observation values; and inputting user driving features into an ensemble learning model based on the correlation coefficient to obtain the first importance index.

[0055] In one optional embodiment, to accurately assess the importance of user driving features relative to historical driving parameters, the vehicle control system can first align the extracted user driving features and historical driving parameters to obtain a first observation value corresponding to the user driving features and a second observation value corresponding to the historical driving parameters. Then, using the correlation coefficient method, based on the first and second observation values, the correlation coefficient between the user driving features and historical driving parameters is determined. This correlation coefficient is then used to sequentially input the user driving features into one or more preset ensemble learning models, such as random forest models, extreme boosting tree models, and XGBoot models, to obtain the index results output by different ensemble learning models. Finally, the different index results are summarized to obtain the importance index of different user driving features relative to historical driving parameters. It should be noted that the aforementioned correlation coefficient method, random forest model, and other information can be referenced from related technologies and will not be elaborated or limited here.

[0056] For ease of understanding, Figure 2 This is a schematic diagram illustrating a target driving feature selection process according to an embodiment of this application, such as... Figure 2As shown, historical driving parameters and corresponding user driving features can be obtained first. Then, the correlation coefficient between user driving features and historical driving parameters can be determined using the Pearson correlation coefficient method. The user driving features are then sequentially input into the random forest model using this correlation coefficient to output importance indicators corresponding to different user features. Next, it is determined whether the importance indicator meets the preset indicator conditions, such as whether the importance indicator is greater than a preset threshold or whether it is the maximum value among multiple importance indicators. If it meets the conditions, the user driving feature corresponding to the importance indicator can be determined as the target driving feature; if it does not meet the conditions, the user driving feature corresponding to the importance indicator can be discarded.

[0057] Furthermore, controlling vehicle operation based on the user's driving style includes: obtaining vehicle control parameters matching the user's driving style from a parameter library, wherein the parameter library is used to store the correlation between the user's driving style and the vehicle control parameters; outputting the vehicle control parameters in the operation interface and receiving parameter adjustment instructions from the user; adjusting the vehicle control parameters based on the parameter adjustment instructions to obtain target control parameters; and controlling vehicle operation based on the target control parameters.

[0058] The aforementioned parameter library can be used to store the relationship between different user driving styles and corresponding vehicle control parameters. The vehicle control parameters can be control parameters compiled and summarized by the vehicle control system based on historical driving parameters, or control parameters set by the user. There is no limitation here. Different vehicle control parameters can also be configured for different users with the same driving style.

[0059] In one optional embodiment, when controlling the vehicle according to the user's driving style, the vehicle control system can first obtain vehicle control parameters matching the user's driving style from a preset parameter library, and then output these parameters to the user through a preset operation interface, such as an in-vehicle screen. The user can view and adjust these parameters in the operation interface. When the vehicle control system detects the user's adjustment of the vehicle control parameters, it can generate a corresponding parameter adjustment command and use this command to adjust the obtained vehicle control parameters to obtain the target control parameters. Finally, the vehicle is controlled using these target control parameters, thereby making the vehicle's operation more in line with the user's expectations. While adjusting to obtain the target control parameters, the target control parameters can also be selectively updated to the aforementioned parameter library for future use.

[0060] Furthermore, based on the style recognition model, the user's driving characteristics are identified to obtain the user's driving style, including: dividing multiple classification results based on preset driving styles to obtain multiple classification result sets, wherein the preset driving styles corresponding to the classification results contained in the same classification result set are the same; merging the classification results in each classification result combination based on the classification weights corresponding to the classification results in each classification result set to obtain a target classification result, wherein the target classification result is used to characterize the degree of matching between the user's driving characteristics and the preset driving styles corresponding to the classification result sets; and determining the user's driving style from the preset driving styles based on the target classification result.

[0061] In one optional embodiment, when classifying and recognizing user driving features using multiple style classifiers in the style recognition model, the multiple classification results can first be divided according to different preset driving styles to obtain multiple classification result sets. The preset driving styles corresponding to the classification results within the same classification result set are the same; the difference lies in the classification weights of different style classifiers for that preset driving style. After dividing the classification result sets, the classification results in each set can be merged according to the splitting weights corresponding to different classification results to obtain the target classification result corresponding to the preset driving style. This indicates the degree of matching between the user driving features and the preset driving styles corresponding to the classification result sets. Finally, based on the target classification results of different classification result sets, i.e., the degree of matching between the user driving features and different preset driving styles, the vehicle control system can determine the driving style with the highest degree of matching from the different preset driving styles and use it as the aforementioned user driving style.

[0062] Furthermore, the above method also includes: obtaining sample driving parameters corresponding to at least one preset driving style; extracting features from the sample driving parameters to obtain at least one sample driving feature; inputting the sample driving feature into an initial recognition model to obtain an initial recognition result corresponding to the sample driving parameters; and adjusting the initial recognition model based on the initial recognition result and the preset driving style to obtain a style recognition model.

[0063] In one optional embodiment, when training the style recognition model, corresponding sample driving parameters can be obtained for different preset driving styles. Then, feature extraction is performed on the sample driving parameters to obtain at least one sample driving feature. The sample driving feature is then input into the initial recognition model to obtain the initial recognition result corresponding to the sample driving parameters. Finally, the initial recognition result and the corresponding preset driving style are used to adjust the initial recognition model to obtain a style recognition model with higher recognition accuracy.

[0064] Further, the sample driving features are input into the initial recognition model to obtain the initial recognition result corresponding to the sample driving parameters, including: evaluating the importance of the sample driving features according to a preset evaluation method to obtain the second importance index of the sample driving features to the sample driving parameters; ranking the second importance indexes, and selecting at least one target sample feature from the sample driving features based on the ranking result, wherein the second importance index corresponding to the target sample feature is greater than the second importance index corresponding to other sample features in the sample driving features excluding the target sample feature; inputting the target sample feature into the initial recognition model to obtain the initial recognition result.

[0065] Similar to the aforementioned process of identifying user driving features, when inputting sample driving features into the initial identification model for identification, the importance of the sample driving features can be assessed first by evaluating the user driving features to obtain a second importance index of the sample driving features relative to the sample driving parameters. Then, the sample driving features are sorted according to this second importance index, and one or more target sample features are selected from the sample driving features based on the sorting results. The second importance index corresponding to the target sample feature is greater than the second importance index corresponding to the other sample driving features in the sample driving features excluding the target sample feature. Finally, the target sample feature is input into the initial identification model to obtain the aforementioned initial identification result.

[0066] Furthermore, the initial recognition model includes at least multiple initial classifiers, and the initial recognition result includes multiple initial classification results obtained by classifying the target sample features by the multiple initial classifiers. Based on the initial recognition results and a preset driving style, the initial recognition model is adjusted to obtain a style recognition model, including: matching the multiple initial classification results with the preset driving style to obtain multiple first matching results; adjusting the initial classifiers based on the multiple first matching results to obtain multiple style classifiers; matching the multiple style classification results with the preset driving style to obtain multiple second matching results, wherein the style classification results are used to characterize the classification results obtained by inputting the target sample features into the style classifiers; determining the classification weights of the style classifiers relative to the preset driving style based on the multiple second matching results; and constructing a style recognition model based on the classification weights and the multiple style classifiers.

[0067] In one optional embodiment, the initial recognition model may include multiple initial classifiers, and the initial recognition result includes multiple initial classification results obtained by different initial classifiers classifying sample driving features. When adjusting the initial recognition model using the initial recognition results and preset driving styles, different initial classification results can be matched with the preset driving styles to obtain multiple first matching results. Then, the initial classifiers can be adjusted using these multiple first matching results to obtain the multiple style classifiers. After adjusting the style classifiers, the previously selected target sample features can be input into the style classifiers to obtain the style classification results. After matching the style classification results with the preset style types to obtain second matching results, the classification weights of different style classifiers for the preset style type can be determined based on the second matching results. For example, if the output of style classifier A shows a 50% probability that the target sample feature belongs to the corresponding preset driving style, the initial weight of the style classifier for the preset driving style can be determined to be 0.5. If the output of style classifier B shows a 60% probability that the target sample feature belongs to the corresponding preset driving style... If the initial weight of the style classifier for the preset driving style is 0.6, then the initial weight of the style classifier for the preset driving style can be determined to be 0.9. If the output of the style classifier shows that there is a 90% probability that the feature of the target sample belongs to the corresponding preset driving style, then the initial weight of the style classifier for the preset driving style can be determined to be 0.9. By integrating the initial weights of different style classifiers, the classification weight of different style classifiers for the preset driving style can be obtained. For example, the classification weight of style classifier A for the preset driving style type can be 0.25, the classification weight of style classifier B for the preset driving style type can be 0.3, and the classification weight of style classifier A for the preset driving style type can be 0.45.

[0068] After determining the classification weights of different style classifiers for different preset driving styles, the style recognition model can be constructed using these classification weights and the aforementioned multiple style classifiers, thereby ensuring the accuracy of the style recognition model.

[0069] For ease of understanding, Figure 3 This is a schematic diagram illustrating a user driving style determination process according to an embodiment of this application, such as... Figure 3As shown, when determining a user's driving style, historical driving parameters can be obtained first, and these parameters can be preprocessed, such as by denoising. Then, feature extraction can be performed on the preprocessed historical driving parameters to obtain the aforementioned user driving features. The importance of these user driving features can be evaluated to select at least one target driving feature. Finally, the target driving feature is input into a style recognition model, and multiple style classifiers are used to identify the target driving feature to obtain multiple style classification results. Then, the classification weights of different style classifiers for different driving styles are used to summarize the multiple style classification results to determine the user driving style that matches the target driving feature.

[0070] Example 2

[0071] According to one aspect of the present invention, a vehicle control device is also provided in accordance with the above-described vehicle control method. Figure 4 This is a structural block diagram of a vehicle control device according to an embodiment of this application, such as... Figure 4 As shown, the device includes: a parameter acquisition module 402, a feature extraction module 404, a style recognition module 406, and a vehicle control module 408.

[0072] The system includes the following modules: Parameter Acquisition Module 402 acquires historical driving parameters of the vehicle during a historical time period; Feature Extraction Module 404 extracts features from the historical driving parameters to obtain user driving characteristics; Style Recognition Module 406 identifies user driving characteristics based on a style recognition model to obtain the user's driving style. The style recognition model includes multiple style classifiers, each with different classification weights for different preset driving styles. The preset driving styles include the user's driving style, which represents the style obtained by summarizing multiple classification results based on the classification weights of the style classifiers. The classification results represent the degree of matching between user driving characteristics and different preset driving styles under different style classifiers. Vehicle Control Module 408 responds to the detection of user driving the vehicle by controlling the vehicle's operation based on the user's driving style to assist the user in driving.

[0073] Furthermore, the style recognition module includes: an importance assessment unit, used to assess the importance of user driving features according to a preset assessment method to obtain the first importance index of user driving features to historical driving parameters; a feature selection unit, used to select at least one target driving feature from user driving features based on the first importance index; and a style recognition unit, used to input the target driving feature into the style recognition model to obtain the user driving style.

[0074] Furthermore, the importance assessment unit is also used to: align user driving characteristics and historical driving parameters to obtain a first observation value corresponding to the user driving characteristics and a second observation value corresponding to the historical driving parameters; determine the correlation coefficient between the user driving characteristics and the historical driving parameters based on the first and second observation values; and input the user driving characteristics into the ensemble learning model based on the correlation coefficient to obtain the first importance index.

[0075] Furthermore, the vehicle control module includes: a parameter acquisition unit, used to acquire vehicle control parameters matching the user's driving style from a parameter library, wherein the parameter library is used to store the correlation between the user's driving style and the vehicle control parameters; an instruction receiving unit, used to output the vehicle control parameters in the operation interface and receive parameter adjustment instructions from the user; a parameter adjustment unit, used to adjust the vehicle control parameters based on the parameter adjustment instructions to obtain the target control parameters; and a vehicle control unit, used to control the vehicle operation based on the target control parameters.

[0076] Furthermore, the style recognition module includes: a result segmentation unit, used to segment multiple classification results based on a preset driving style to obtain multiple classification result sets, wherein the preset driving styles corresponding to the classification results contained in the same classification result set are the same; a result merging unit, used to merge the classification results in each classification result combination based on the classification weights corresponding to the classification results in each classification result set to obtain a target classification result, wherein the target classification result is used to characterize the degree of matching between the user's driving characteristics and the preset driving style corresponding to the classification result set; and a style determination unit, used to determine the user's driving style from the preset driving styles based on the target classification result.

[0077] Furthermore, the above-mentioned device also includes: a sample acquisition module for acquiring sample driving parameters corresponding to at least one preset driving style; a feature extraction module for extracting features from the sample driving parameters to obtain at least one sample driving feature; an initial recognition module for inputting the sample driving feature into an initial recognition model to obtain an initial recognition result corresponding to the sample driving parameters; and a model adjustment module for adjusting the initial recognition model based on the initial recognition result and the preset driving style to obtain a style recognition model.

[0078] Furthermore, the initial identification module includes: a sample feature evaluation unit, used to evaluate the importance of sample driving features according to a preset evaluation method, and obtain the second importance index of the sample driving features to the sample driving parameters; a sample feature selection unit, used to rank the second importance index, and select at least one target sample feature from the sample driving features based on the ranking result, wherein the second importance index corresponding to the target sample feature is greater than the second importance index corresponding to other sample features in the sample driving features excluding the target sample feature; and a sample identification unit, used to input the target sample feature into the initial identification model to obtain the initial identification result.

[0079] Furthermore, the initial recognition model includes at least multiple initial classifiers, and the initial recognition result includes multiple initial classification results obtained by classifying the target sample features by the multiple initial classifiers. The model adjustment module includes: a first matching unit, used to match the multiple initial classification results with a preset driving style to obtain multiple first matching results; a classifier adjustment unit, used to adjust the initial classifiers based on the multiple first matching results to obtain multiple style classifiers; a second matching unit, used to match the multiple style classification results with a preset driving style to obtain multiple second matching results, wherein the style classification results are used to characterize the classification results obtained by inputting the target sample features into the style classifiers; a weight determination unit, used to determine the classification weights of the style classifiers relative to the preset driving style based on the multiple second matching results; and a model construction unit, used to construct a style recognition model based on the classification weights and multiple style classifiers.

[0080] Example 3

[0081] Embodiments of this application also provide a vehicle, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention during runtime.

[0082] Example 4

[0083] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0084] Example 5

[0085] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0086] Example 6

[0087] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of the present invention.

[0088] Example 7

[0089] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of the present invention.

[0090] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0091] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0092] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0093] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0095] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0096] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A vehicle control method, characterized in that, include: The historical driving parameters of the vehicle are obtained during the user's driving of the vehicle within a historical time period. Feature extraction is performed on the historical driving parameters to obtain the user's driving characteristics; The user's driving characteristics are identified based on a style recognition model to obtain the user's driving style. The style recognition model includes multiple style classifiers, and different style classifiers have different classification weights for different preset driving styles. The preset driving style includes the user's driving style. The user's driving style is used to represent the style obtained by summarizing multiple classification results obtained by the style classifiers for classifying the user's driving characteristics based on the classification weights. The classification results are used to represent the degree of matching between the user's driving characteristics and different preset driving styles under different style classifiers. In response to detecting that the user is driving the vehicle, the vehicle operation is controlled based on the user's driving style to assist the user in driving the vehicle.

2. The method according to claim 1, characterized in that, The user's driving characteristics are identified based on a style recognition model to obtain the user's driving style, including: The importance of the user's driving characteristics is evaluated according to a preset evaluation method to obtain the first importance index of the user's driving characteristics to the historical driving parameters; Based on the first importance index, at least one target driving feature is selected from the user driving features; The target driving features are input into the style recognition model to obtain the user's driving style.

3. The method according to claim 2, characterized in that, The importance of the user's driving characteristics is assessed according to a preset evaluation method to obtain the first importance index of the user's driving characteristics to the historical driving parameters, including: Data alignment is performed on the user driving characteristics and the historical driving parameters to obtain a first observation value corresponding to the user driving characteristics and a second observation value corresponding to the historical driving parameters; Based on the first observation and the second observation, determine the correlation coefficient between the user's driving characteristics and the historical driving parameters; Based on the correlation coefficient, the user's driving characteristics are input into the ensemble learning model to obtain the first importance index.

4. The method according to claim 1, characterized in that, Controlling the vehicle's operation based on the user's driving style includes: Obtain vehicle control parameters that match the user's driving style from the parameter library, wherein the parameter library is used to store the association between the user's driving style and the vehicle control parameters; The system outputs the vehicle control parameters in the user interface and receives parameter adjustment instructions from the user. The vehicle control parameters are adjusted based on the parameter adjustment command to obtain the target control parameters; The vehicle is controlled to operate based on the target control parameters.

5. The method according to claim 1, characterized in that, The user's driving characteristics are identified based on a style recognition model to obtain the user's driving style, including: The multiple classification results are divided based on the preset driving style to obtain multiple classification result sets, wherein the preset driving style is the same for the classification results contained in the same classification result set. Based on the classification weights corresponding to the classification results in each classification result set, the classification results in each classification result combination are merged to obtain a target classification result, wherein the target classification result is used to characterize the degree of matching between the user's driving characteristics and the preset driving style corresponding to the classification result set; The user's driving style is determined from the preset driving styles based on the target classification results.

6. The method according to claim 1, characterized in that, The method further includes: Obtain sample driving parameters corresponding to at least one preset driving style; Feature extraction is performed on the sample driving parameters to obtain at least one sample driving feature; The sample driving features are input into the initial recognition model to obtain the initial recognition result corresponding to the sample driving parameters; The initial recognition model is adjusted based on the initial recognition result and the preset driving style to obtain the style recognition model.

7. The method according to claim 6, characterized in that, The sample driving features are input into the initial recognition model to obtain the initial recognition result corresponding to the sample driving parameters, including: The importance of the sample driving features is evaluated according to a preset evaluation method to obtain a second importance index of the sample driving features to the sample driving parameters; The second importance index is sorted, and at least one target sample feature is selected from the sample driving features based on the sorting result, wherein the second importance index corresponding to the target sample feature is greater than the second importance index corresponding to other sample features in the sample driving features excluding the target sample feature; Input the target sample features into the initial recognition model to obtain the initial recognition result.

8. The method according to claim 6, characterized in that, The initial recognition model includes at least multiple initial classifiers, and the initial recognition result includes multiple initial classification results obtained by the multiple initial classifiers classifying the target sample features. The initial recognition model is adjusted based on the initial recognition result and the preset driving style to obtain the style recognition model, including: The multiple initial classification results are matched with the preset driving style to obtain multiple first matching results; The initial classifier is adjusted based on the multiple first matching results to obtain multiple style classifiers; Multiple style classification results are matched with the preset driving style to obtain multiple second matching results, wherein the style classification results are used to characterize the classification results obtained by inputting the target sample features into the style classifier; The classification weight of the style classifier relative to the preset driving style is determined based on the multiple second matching results; The style recognition model is constructed based on the classification weights and the multiple style classifiers.

9. A vehicle control device, characterized in that, include: The parameter acquisition module is used to acquire the historical driving parameters of the vehicle when the user drives the vehicle within a historical time period. The feature extraction module is used to extract features from the historical driving parameters to obtain user driving features; A style recognition module is used to identify the user's driving characteristics based on a style recognition model to obtain the user's driving style. The style recognition model includes multiple style classifiers, and different style classifiers have different classification weights for different preset driving styles. The preset driving styles include the user's driving style. The user's driving style is used to characterize the style obtained by summarizing multiple classification results of the user's driving characteristics based on the classification weights. The classification results are used to characterize the degree of matching between the user's driving characteristics and different preset driving styles under different style classifiers. A vehicle control module is used to control the operation of the vehicle based on the user's driving style in response to detecting that the user is driving the vehicle, so as to assist the user in driving the vehicle.

10. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images