Driving style identification method and apparatus, data processing method and apparatus, and device

Abstract

A driving style identification method and apparatus, a data processing method and apparatus, and a device, relating to the technical field of intelligent driving. The driving style identification method comprises: on the basis of historical driving behavior data from a current user, identifying a target driving style of the current user from among a plurality of driving styles, and on the basis of driving environment information and navigation information acquired during movement, and the target driving style, controlling an autonomous mobile device to travel. The plurality of driving styles are obtained on the basis of performing cluster analysis on driving behavior data from a plurality of users. By means of the method, accurate identification and personalized adaptation of driving styles of users can be realized, and the user experience is improved.

Description

Methods, data processing methods, devices and equipment for identifying driving styles Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a method, data processing method, device and equipment for recognizing driving style. Background Technology

[0002] Users can drive autonomous mobile devices. Different users typically have different driving styles.

[0003] In related technologies, autonomous mobile devices are typically equipped with intelligent driving systems. During operation, the autonomous mobile device can drive according to the general driving style set by the intelligent driving system. For example, for an intelligent driving vehicle, the following distance can be set to 3 meters in the general driving style.

[0004] However, in the above methods, the general driving style cannot be well matched with the user's personal driving style, resulting in a poor user experience. Summary of the Invention

[0005] This application provides a driving style recognition method, data processing method, apparatus, and device to solve the problem that the general driving styles in the prior art cannot match the user's personal driving style well, resulting in a poor user experience.

[0006] In a first aspect, this application provides a method for recognizing driving styles, applied to autonomous mobile devices, the method comprising:

[0007] Based on the current user's historical driving behavior data, the target driving style of the current user is identified from multiple driving styles, which are obtained based on cluster analysis of the driving behavior data of multiple users;

[0008] The autonomous mobile device is controlled to drive based on driving environment information, navigation information, and the target driving style acquired during the movement.

[0009] In one possible implementation, identifying the current user's target driving style from multiple driving styles based on the current user's historical driving behavior data includes:

[0010] Based on the historical driving behavior data, determine the historical feature vector;

[0011] Obtain the driving feature vectors corresponding to the multiple driving styles;

[0012] Based on the historical feature vector, a matching process is performed on the driving feature vectors corresponding to the multiple driving styles to determine the target driving style.

[0013] In one possible implementation, determining the historical feature vector based on the historical driving behavior data includes:

[0014] Based on preset quantitative indicators and / or preset feature processing models, feature extraction is performed on the historical driving behavior data to obtain the historical feature vector.

[0015] The preset quantitative index is determined based on the driving behavior of the multiple users in at least one driving scenario, including cutting in, starting and stopping, congestion, following other vehicles, and turning; the preset feature processing model is used to extract features from the users' driving behavior data to obtain feature vectors.

[0016] In one possible implementation, the step of extracting features from the historical driving behavior data based on the preset quantitative indicators and / or preset feature processing model to obtain the historical feature vector includes:

[0017] Based on the preset quantitative indicators, feature extraction is performed on the historical driving behavior data to obtain a first historical feature vector, and the first historical feature vector is determined as the historical feature vector; or,

[0018] Based on a preset feature processing model, features are extracted from the historical driving behavior data to obtain a second historical feature vector, and the second historical feature vector is determined as the historical feature vector; or,

[0019] Based on the preset quantitative indicators, features are extracted from the historical driving behavior data to obtain a first historical feature vector. Based on the preset feature processing model, features are extracted from the historical driving behavior data to obtain a second historical feature vector. The first historical feature vector and the second historical feature vector are then concatenated to obtain the historical feature vector.

[0020] In one possible implementation, controlling the autonomous mobile device to drive based on driving environment information, navigation information, and the target driving style acquired during the movement includes:

[0021] Configure the target driving style in the intelligent driving model of the autonomous mobile device;

[0022] The driving environment information and navigation information are processed by an intelligent driving model to obtain a driving decision scheme;

[0023] The autonomous mobile device is controlled to drive according to the driving decision-making scheme;

[0024] The driving decision-making scheme includes at least one of the following: planning driving route, handling lane cutting, choosing lane change timing, following distance, turning speed, and time interval between starting and starting with the autonomous mobile device in front.

[0025] In one possible implementation, the driving environment information includes motion state information of the autonomous mobile device, motion state of surrounding traffic participants, and road traffic information; and / or,

[0026] The navigation information includes map information, location information of autonomous mobile devices, and path trajectory information.

[0027] In one possible implementation, the method further includes:

[0028] Receive the multiple driving styles sent by the server;

[0029] The multiple driving styles are displayed in the visual interface of the autonomous mobile device.

[0030] In one possible implementation, the method further includes:

[0031] Receive style descriptions for each driving style sent by the server;

[0032] Accordingly, displaying the multiple driving styles in the visual interface of the autonomous mobile device includes:

[0033] The multiple driving styles and their corresponding style descriptions are displayed in the visual interface of the autonomous mobile device.

[0034] In one possible implementation, the method further includes:

[0035] The system receives a style description report of the current user sent by the server; the style description report includes at least one of the following: overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving smoothness, average vehicle speed, relative driving index, and personality traits.

[0036] In response to the current user's first upload operation, a style description report of the current user is uploaded to a shared cloud platform, which is used for interaction among users of multiple autonomous mobile devices.

[0037] In one possible implementation, the method further includes:

[0038] In response to the second upload operation of the current user, the operating information of the target driving style is uploaded to the shared cloud platform. The operating information includes the target driving style and at least one of the following: the mileage, average energy consumption, and operating time of the target driving style.

[0039] In one possible implementation, the method further includes:

[0040] The autonomous mobile device is controlled to drive based on the new driving style downloaded by the current user from the shared cloud platform, as well as driving environment information and navigation information obtained during the movement.

[0041] Secondly, this application provides a data processing method for driving style, the method comprising:

[0042] Acquire driving behavior data from multiple users;

[0043] Cluster analysis was performed on the driving behavior data of the multiple users to obtain at least one cluster.

[0044] Add corresponding driving styles to each of the at least one cluster to determine multiple driving styles;

[0045] The multiple driving styles are distributed to at least one autonomous mobile device.

[0046] In one possible implementation, the step of performing cluster analysis on the driving behavior data of the multiple users to obtain at least one cluster includes:

[0047] For each user, a feature vector corresponding to the user is obtained based on the user's driving behavior data, and the feature vector includes at least one piece of data related to driving style;

[0048] Cluster analysis is performed on the feature vectors of the multiple users to obtain at least one cluster.

[0049] In one possible implementation, any cluster corresponds to a driving style with a corresponding style description, which is used to interpret the driving style.

[0050] The delivery of the multiple driving styles to at least one autonomous mobile device includes:

[0051] The plurality of driving styles and the style description corresponding to each driving style are sent to the at least one autonomous mobile device.

[0052] In one possible implementation, the method further includes:

[0053] Acquire the current user's driving behavior data sent by the autonomous mobile device;

[0054] Based on preset quantitative indicators, the relative driving index of the current user is determined according to the driving behavior data of the multiple users and the driving behavior data of the current user. The relative driving index is used to represent the ranking of the current user among the multiple users.

[0055] The preset quantitative indicators are determined based on the user's driving behavior in at least one of the following driving scenarios: cutting in, starting and stopping, traffic jams, following other vehicles, and turning.

[0056] In one possible implementation, the method further includes:

[0057] Obtain the target personality traits corresponding to the multiple driving styles;

[0058] The target personality traits corresponding to each driving style are added to the style description corresponding to that driving style.

[0059] In one possible implementation, the method further includes:

[0060] Based on the personality traits and driving styles of the multiple users, a style mapping relationship is established. The style mapping relationship includes the target personality trait corresponding to each driving style. The target personality trait is the personality trait that appears most frequently among the users corresponding to the driving style.

[0061] Accordingly, obtaining the target personality traits corresponding to the multiple driving styles includes:

[0062] Based on the style mapping relationship, the target personality traits corresponding to each driving style are retrieved by querying.

[0063] In one possible implementation, the method further includes:

[0064] Based on the current user's target driving style and the style mapping relationship, a style description report corresponding to the current user's target driving style is determined. The style description report includes at least one of the following: overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving stability, average vehicle speed, relative driving index, and personality traits.

[0065] Send the current user's style description report to the autonomous mobile device.

[0066] Thirdly, the device itself provides a driving style recognition device, the device comprising:

[0067] The first acquisition module is used to identify the target driving style of the current user from multiple driving styles based on the current user's historical driving behavior data. The multiple driving styles are obtained based on cluster analysis of the driving behavior data of multiple users.

[0068] The first processing module is used to control the autonomous mobile device to drive based on the driving environment information, navigation information and the target driving style obtained during the movement.

[0069] Fourthly, the system itself provides a data processing device for driving styles, the device comprising:

[0070] The second acquisition module is used to acquire driving behavior data from multiple users;

[0071] The analysis module is used to perform cluster analysis on the driving behavior data of the multiple users to obtain at least one cluster.

[0072] The second processing module is used to add corresponding driving style labels to the at least one cluster to determine multiple driving styles.

[0073] The sending module is used to send the multiple driving styles to at least one autonomous mobile device.

[0074] Fifthly, this application provides an electronic device, including: a processor, a memory, and a communication interface;

[0075] The memory stores computer-executed instructions;

[0076] The processor executes computer execution instructions stored in the memory to implement the method as described in any of the first aspects.

[0077] Sixthly, this application provides an autonomous mobile device, including: an electronic device as described in the fifth aspect.

[0078] In a seventh aspect, this application provides a server, including: a processor, a memory, and a communication interface;

[0079] The memory stores computer-executed instructions;

[0080] The processor executes computer execution instructions stored in the memory to implement the method as described in any of the second aspects.

[0081] Eighthly, this application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, are used to implement the method described in either the first or second aspect above.

[0082] Ninthly, this application provides a program product comprising: a computer program that, when the program product is run on a computer, causes the computer to perform the method described in either the first or second aspect above.

[0083] In a tenth aspect, this application provides a computer program that, when executed by a processor, performs the method described in either the first or second aspect above.

[0084] This application provides a driving style identification method, data processing method, apparatus, and device. It includes identifying the current user's target driving style from multiple driving styles based on the user's historical driving behavior data. These multiple driving styles are obtained through cluster analysis of driving behavior data from multiple users. Then, the autonomous mobile device can be controlled to drive based on driving environment information, navigation information, and the target driving style acquired during movement. In this process, by analyzing the current user's historical driving behavior data, a suitable target driving style can be identified, thereby providing a more personalized driving experience and improving the user experience. Attached Figure Description

[0085] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0086] Figure 1 is a schematic diagram of the application scenario provided in the embodiments of this application;

[0087] Figure 2 is a flowchart illustrating an embodiment of the driving style recognition method provided in this application;

[0088] Figure 3 is a flowchart illustrating Embodiment 2 of the driving style recognition method provided in this application;

[0089] Figure 4 is a logic block diagram for determining driving decisions provided in an embodiment of this application;

[0090] Figure 5 is a flowchart illustrating an embodiment of the data processing method for driving style provided in this application;

[0091] Figure 6 is a flowchart illustrating Embodiment 2 of the data processing method for driving style provided in this application;

[0092] Figure 7 is a schematic diagram of a clustering result provided in an embodiment of this application;

[0093] Figure 8 is a flowchart illustrating Embodiment 3 of the data processing method for driving style provided in this application;

[0094] Figure 9 is a flowchart illustrating Embodiment 4 of the data processing method for driving style provided in this application;

[0095] Figure 10 is a flowchart illustrating Embodiment 5 of the data processing method for driving style provided in this application;

[0096] Figure 11 is a flowchart illustrating Embodiment Six of the data processing method for driving style provided in this application;

[0097] Figure 12 is a flowchart illustrating Embodiment 3 of the driving style recognition method provided in this application;

[0098] Figure 13 is a flowchart illustrating Embodiment 4 of the driving style recognition method provided in this application;

[0099] Figure 14 is a structural schematic diagram of a first embodiment of the driving style recognition device provided in this application;

[0100] Figure 15 is a structural schematic diagram of Embodiment 2 of the driving style recognition device provided in this application;

[0101] Figure 16 is a structural schematic diagram of a first embodiment of the data processing device for driving style provided in this application;

[0102] Figure 17 is a structural schematic diagram of Embodiment 2 of the data processing device for driving style provided in this application;

[0103] Figure 18 is a schematic diagram of the structure of the electronic device provided in an embodiment of this application;

[0104] Figure 19 is a schematic diagram of the server structure provided in an embodiment of this application. Detailed Implementation

[0105] In the embodiments of this application, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0106] In the embodiments of this application, the term "multiple" refers to two or more, and other quantifiers are similar.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of related data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0108] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0109] Figure 1 is a schematic diagram of the application scenario provided in the embodiments of this application. Referring to Figure 1, the autonomous mobile device can be equipped with an intelligent driving system. The autonomous mobile device can identify the current user's target driving style from multiple driving styles obtained by clustering analysis of driving behavior data of multiple users based on the current user's driving behavior data, and control the autonomous mobile device to drive according to the target driving style.

[0110] Optionally, autonomous mobile devices can be flying cars, intelligent driving vehicles, mobile robots, intelligent ships, or other mobile devices equipped with intelligent driving systems.

[0111] For example, intelligent driving vehicles can be equipped with driver assistance systems. The intelligent driving vehicle can identify the target driving style of the current user A as driving style 1 from driving style 1, driving style 2, ... and driving style N through the current user A's driving behavior data, and control the intelligent driving vehicle to drive according to driving style 1.

[0112] In related technologies, autonomous mobile devices equipped with intelligent driving systems drive according to a pre-set general driving style in the intelligent driving system, such as driving at a set following distance of 3 meters. However, the general driving style cannot match the user's personal driving style well, resulting in a poor user experience.

[0113] To address the aforementioned problems, the inventors, in their research on how to identify a user's individual driving style, discovered that autonomous mobile devices typically record the user's historical driving behavior data during the user's driving history. This historical driving behavior data can effectively reflect the user's driving preferences. For example, historical driving behavior data can reveal whether a user's driving style is more sporty, allowing for efficient traversal of a road, or more comfortable, enabling very smooth acceleration and deceleration, thus providing a relaxing experience for passengers. Therefore, driving according to a universally applicable driving style set in the intelligent driving system often fails to meet the user's driving needs. Based on this, after numerous experiments, the inventors discovered that, based on the current user's historical driving behavior data, the target driving style of the current user can be identified from multiple driving styles derived from cluster analysis of driving behavior data from multiple users. Furthermore, based on driving environment information, navigation information, and the target driving style acquired during the journey, the autonomous mobile device can be controlled to meet the user's driving needs. Therefore, this application proposes a driving style identification method to solve the problem of universally applicable driving styles failing to match individual user driving styles, resulting in a poor user experience.

[0114] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0115] Figure 2 is a flowchart illustrating an embodiment of the driving style recognition method provided in this application. Referring to Figure 2, this method is applied to autonomous mobile devices and includes:

[0116] S201. Based on the current user's historical driving behavior data, identify the current user's target driving style from multiple driving styles. The multiple driving styles are obtained based on cluster analysis of the driving behavior data of multiple users.

[0117] The execution subject in this application embodiment can be an electronic device or a driving style recognition device installed in an electronic device. The driving style recognition device can be implemented through software or a combination of software and hardware. The driving style recognition device can be a processor in the electronic device. For ease of understanding, the following description uses an electronic device as the execution subject; the electronic device can be a control unit in an autonomous mobile device.

[0118] In this step, the electronic device can acquire the current user's historical driving behavior data and, based on this data, identify the current user's target driving style from multiple driving styles obtained through cluster analysis of driving behavior data from multiple users. Specifically, it can determine historical feature vectors based on the current user's historical driving behavior data, obtain driving feature vectors corresponding to multiple driving styles, and then match these historical feature vectors with the corresponding driving feature vectors to determine the target driving style.

[0119] For ease of understanding, the following explanation will use intelligent driving vehicles as an example of autonomous mobile devices.

[0120] Optionally, driving behavior data may include training data for training the end-to-end system. The end-to-end system can perform imitation learning on the training data, thereby enabling it to output driving decisions based on information such as images and point clouds. The end-to-end system can be an autonomous driving system or a driver assistance system, possessing an intelligent driving model.

[0121] Specifically, driving behavior data can include at least one of the following: speed data, acceleration and deceleration patterns, steering behavior, braking habits, driving time and road conditions, fuel consumption data, driving routes, driving events, and environmental conditions. This data can be collected through onboard sensors and smart devices.

[0122] For example, based on cluster analysis of driving behavior data from multiple users, three clustering results can be obtained: driving style 1, driving style 2, and driving style 3. Driving style 1 corresponds to driving feature vector 1, driving style 2 corresponds to driving feature vector 2, and driving style 3 corresponds to driving feature vector 3. Based on the current user's historical driving behavior data, a historical feature vector A can be determined. Then, by matching historical feature vector A with the driving feature vectors corresponding to the three driving styles, the target driving style can be determined as driving style 1.

[0123] S202. Control the autonomous mobile device to drive based on the driving environment information, navigation information and target driving style obtained during the movement.

[0124] In this step, the electronic device can control the autonomous mobile device to drive in accordance with the target driving style based on the identified target driving style, combined with the driving environment information and navigation information obtained by the autonomous mobile device during driving.

[0125] In one alternative implementation, the identified target driving style can be configured in the intelligent driving model of the autonomous mobile device. The intelligent driving model processes the driving environment information and navigation information obtained during the autonomous mobile device's driving process to obtain a driving decision scheme, and then controls the autonomous mobile device's driving according to the driving decision scheme.

[0126] Optionally, the target driving style can be configured in the intelligent driving model of the autonomous mobile device using any of the following methods.

[0127] Method 1: Responding to the current user's selection operation in the visual interface of the autonomous mobile device. For example, the electronic device can respond to user A's selection operation in the human-machine interface of the intelligent driving vehicle and configure the identified driving style 1 in the intelligent driving model of the intelligent driving vehicle.

[0128] Method 2: Responding to the current user's voice command. For example, an electronic device can respond to user A's voice command "Apply my personalized driving style" and configure the recognized driving style 1 in the intelligent driving model of the intelligent driving vehicle.

[0129] Information about the driving environment can include the motion status information of autonomous mobile devices (speed, direction, etc.), the motion status of surrounding traffic participants (speed, direction, etc.), and road traffic information (traffic lights, speed limits, traffic flow, etc.).

[0130] Navigation information can include map information, location information of autonomous mobile devices, path trajectory information, and navigation trajectory information.

[0131] The driving decision-making scheme may include, but is not limited to, at least one of the following: planning driving route, handling lane cutting, choosing lane change timing, following distance, turning speed, and the time interval between starting and starting with the autonomous mobile device in front.

[0132] For example, electronic devices can be configured in the intelligent driving model of an intelligent driving vehicle using driving style 1. The intelligent driving model processes the driving environment and navigation information acquired during the vehicle's operation to obtain a driving decision plan. This plan may include handling of lane-cutting incidents, and the autonomous mobile device can then be controlled according to this plan. For instance, when faced with a vehicle cutting in front of the driver in violation of traffic rules, the intelligent driving vehicle, after integrating driving environment and navigation information, can accelerate to increase the safe distance from the vehicle cutting in front, ensuring the safety of both the vehicle and the driver.

[0133] In this embodiment, the electronic device can identify the user's target driving style from multiple driving styles by analyzing the user's historical driving behavior data. These driving styles are derived based on cluster analysis of driving behavior data from multiple users. Subsequently, the autonomous mobile device can be controlled to drive based on driving environment information, navigation information, and the target driving style acquired during movement. In the above process, the user's target driving style can be identified based on the user's historical driving behavior data, thereby providing the user with a more personalized driving experience and improving the user experience.

[0134] Based on the embodiment shown in Figure 2, the above-mentioned method for recognizing driving styles will be further described in detail below with reference to Figure 3.

[0135] Figure 3 is a flowchart illustrating a second embodiment of the driving style recognition method provided in this application. Referring to Figure 3, the method may include:

[0136] S301. Determine the historical feature vector based on historical driving behavior data.

[0137] In this step, the electronic device can extract historical feature vectors from the historical driving behavior data of the current user.

[0138] In one optional implementation, features can be extracted from historical driving behavior data based on preset quantitative indicators and / or preset feature processing models to obtain historical feature vectors.

[0139] Among them, the preset quantitative indicators are determined based on the driving behavior of multiple users in at least one driving scenario, such as cutting in, starting and stopping, congestion, following other vehicles, and turning; the preset feature processing model is used to extract features from the users' driving behavior data to obtain feature vectors.

[0140] Specifically, pre-set quantitative indicators can be achieved through an expert scoring system combined with engineering technicians' analysis of driving scenarios. For key scenarios such as cutting in, stop-and-go traffic, congestion, following other vehicles, and turning, corresponding numerical indicators can be formulated. For example, in the cutting in scenario, the focus can be on the closest distance between the intelligent driving vehicle (this vehicle) and other vehicles during the interaction; in the stop-and-go scenario, the focus can be on how long after the vehicle in front starts moving that this vehicle also begins to move.

[0141] Specifically, the preset feature processing model can be a pre-trained deep learning model or an artificial intelligence (AI) model.

[0142] Optionally, features can be extracted from historical driving behavior data based on preset quantitative indicators to obtain a first historical feature vector, and this first historical feature vector can be determined as the historical feature vector; or,

[0143] Based on a pre-defined feature processing model, features are extracted from historical driving behavior data to obtain a second historical feature vector, which is then determined as the historical feature vector; or,

[0144] Based on preset quantitative indicators, features are extracted from historical driving behavior data to obtain a first historical feature vector. Based on a preset feature processing model, features are extracted from historical driving behavior data to obtain a second historical feature vector. The first historical feature vector and the second historical feature vector are then concatenated to obtain a historical feature vector.

[0145] For example, based on preset quantitative indicators, features can be extracted from historical driving behavior data to obtain a first historical feature vector. Based on a preset feature processing model, features can be extracted from historical driving behavior data to obtain a second historical feature vector. The first and second historical feature vectors can contain different feature sets to analyze and understand the user's driving behavior from different perspectives. The first and second historical feature vectors can then be concatenated to obtain a historical feature vector.

[0146] For example, the first historical feature vector may include speed features, steering features, braking features, distance maintenance features, and time features; wherein, speed features may include average speed, maximum speed, and the frequency of acceleration and deceleration; steering features may include the frequency of steering angle changes and speed during turning; braking features may include the frequency of brake use and braking force; distance maintenance may include the average distance to the vehicle in front and the closest distance to other vehicles; and time features may include driving time period (such as peak hours, night driving, etc.), driving duration, and how long after the vehicle in front started moving that this vehicle also started moving.

[0147] Specifically, for User 1, features can be extracted from User 1's historical driving behavior data based on preset quantitative indicators to obtain a first historical feature vector. This first historical feature vector can include distance-keeping features and time features. The distance-keeping feature can be determined based on preset quantitative indicator 1, and the time feature can be determined based on preset quantitative indicator 2. Preset quantitative indicator 1 can be based on the closest distance between the monitored intelligent driving vehicle and other vehicles in a lane-cutting scenario, thus extracting the distance-keeping feature from User 1's historical driving behavior data. This distance-keeping feature can be defined as a closest distance of 0.3m to other vehicles. Preset quantitative indicator 2 can be based on how long after the preceding vehicle starts moving in a start-stop scenario that the monitored vehicle also begins to move, thus extracting the time feature from User 1's historical driving behavior data. This time feature can be defined as the monitored vehicle starting to move 2 seconds after the preceding vehicle starts moving.

[0148] For example, the second historical feature vector may include behavioral patterns, environmental response features, and fuel consumption features; wherein, behavioral patterns may include the number and conditions of rapid acceleration and braking, environmental response features may include driving adjustments for different weather conditions (such as rainy days and snowy days), and fuel consumption features may include average fuel consumption and fuel consumption changes under different driving conditions.

[0149] Specifically, for User 1, features can be extracted from User 1's historical driving behavior data based on a preset feature processing model to obtain a second historical feature vector. This second historical feature vector can include environmental response features and fuel consumption features. Environmental response features could be User 1's average speed reduction of 20% in rainy weather, while fuel consumption features could be User 1's average fuel consumption of 7 liters / 100 kilometers on urban roads. The preset feature processing model is a pre-set mathematical model that can output the required feature vector. Each feature can be output through a single model, or all features can be output through a single model.

[0150] Optionally, when concatenating the first historical feature vector and the second historical feature vector, the second historical feature vector can be concatenated based on the first historical feature vector; or the first historical feature vector can be concatenated based on the second historical feature vector.

[0151] S302. Obtain the driving feature vectors corresponding to multiple driving styles. The multiple driving styles are obtained based on cluster analysis of driving behavior data of multiple users.

[0152] In this step, based on the multiple driving styles obtained from cluster analysis of driving behavior data of multiple users, the driving feature vector corresponding to each driving style can be further obtained.

[0153] For example, based on the three driving styles obtained from the cluster analysis of driving behavior data of multiple users, we can obtain the driving feature vectors corresponding to the three driving styles, namely driving feature vector 1 corresponding to driving style 1, driving feature vector 2 corresponding to driving style 2, and driving feature vector 3 corresponding to driving style 3.

[0154] In one alternative implementation, each cluster obtained from the clustering can represent a driving style, which can be a high-dimensional vector. For example, driving style 1 can be represented by a 64-dimensional high-dimensional vector, which can be the center of cluster 1, representing the average or geometric center of all data points in the cluster.

[0155] S303. Based on the historical feature vector, perform matching processing on the driving feature vectors corresponding to multiple driving styles to determine the target driving style.

[0156] In this step, the historical feature vectors and the driving feature vectors corresponding to multiple driving styles can be matched to determine the target driving style.

[0157] In practice, the driving style corresponding to the driving feature vector that is consistent with the historical feature vector can be determined as the target driving style from among the driving feature vectors corresponding to multiple driving styles; or, if there is no driving feature vector consistent with the historical feature vector among the driving feature vectors corresponding to multiple driving styles, the driving style corresponding to the target feature vector with the highest similarity to the historical feature vector can be determined as the target driving style from among the driving feature vectors corresponding to multiple driving styles.

[0158] Optionally, the target feature vector with the highest similarity to the historical feature vector can be selected from the driving feature vectors corresponding to multiple driving styles using any of the similarity measurement methods such as cosine similarity, Euclidean distance, and Manhattan distance.

[0159] For example, among the three driving feature vectors corresponding to the three driving styles, the driving style 1 corresponding to driving feature vector 1 that is consistent with the historical feature vector can be determined as the target driving style.

[0160] For example, the Euclidean distance metric can be used to select the target feature vector with the highest similarity to the historical feature vector from the three driving feature vectors corresponding to the three driving styles. Then, the driving style corresponding to the target feature vector can be determined as the target driving style. Here, the target feature vector can be driving feature vector 1, and the target driving style can be driving style 1 corresponding to driving feature vector 1.

[0161] It should be noted that if the target feature vector selected from the driving feature vectors corresponding to multiple driving styles through the similarity measurement method includes at least two different driving feature vectors, then the driving styles corresponding to at least two different driving feature vectors can be recommended to the current user through the interactive interface, and the target driving style can be determined based on the user's selection.

[0162] Furthermore, if the target feature vector selected from multiple driving styles using a similarity metric contains at least two different driving feature vectors, the driving styles corresponding to these two different feature vectors can be fused to obtain a new driving style. Specifically, a weighted average can be applied to the driving feature vectors corresponding to different driving styles, with the weights set based on the frequency of use of each driving style or user preference. The new driving style can also be uploaded to a server or stored in the autonomous mobile device as a candidate driving style.

[0163] S304. Configure the target driving style in the intelligent driving model of the autonomous mobile device.

[0164] In this step, the electronic device can respond to the user's selection operation in the visual interface of the autonomous mobile device and configure the target driving style in the intelligent driving model of the autonomous mobile device.

[0165] In one alternative implementation, the correspondence between the driving feature vector of the target driving style and adjustable parameters in the intelligent driving model can be identified. Adjustable parameters may include speed control, acceleration and deceleration response, steering sensitivity, braking force, and distance maintenance. These parameters can be adjusted using the driving feature vector to ensure that the model's behavior is consistent with the target driving style.

[0166] In another alternative implementation, the intelligent driving model can be designed with a modular structure, allowing different driving styles to be loaded and switched as independent modules. Through an open Application Programming Interface (API), the target driving style module can be integrated into the model, allowing for flexible style switching under different driving conditions.

[0167] S305: The intelligent driving model processes driving environment information and navigation information to obtain driving decision-making schemes.

[0168] In this step, the intelligent driving model configured with the target driving style can process driving environment information and navigation information during the operation of the autonomous mobile device to obtain driving decision-making schemes. These driving decision-making schemes include, but are not limited to, at least one of the following: route planning, lane-cutting handling, lane-change timing selection, following distance, turning speed, and the time interval between the start of the vehicle ahead and the autonomous mobile device ahead.

[0169] Route planning refers to selecting the optimal route based on factors such as current geographical location, destination, real-time traffic conditions, and road restrictions.

[0170] For example, driving style 1 is sporty, driving style 2 is comfortable, and driving style 3 is aggressive. Considering a scenario where an intelligent driving vehicle is traveling from the city center to the airport, different driving styles, through the intelligent driving model, process driving environment and navigation information, and the resulting planned driving path might be as follows:

[0171] A planned driving route for a sporty driving style could include selecting a route that provides a smooth driving experience, primarily via highways and expressways to maintain high speed and stability. For example, an intelligent driving vehicle could choose to immediately enter a ring road after departing from the city center, bypassing low-speed areas and traffic lights in the city to ensure a high average speed throughout the journey.

[0172] The planned driving route corresponding to the comfort style can include prioritizing passenger smoothness and comfort, and choosing to avoid bumpy sections and busy traffic areas. For example, the intelligent driving vehicle can choose a route through well-greened streets to avoid highway noise and congestion, while also choosing to pass through some quiet residential areas to provide a more comfortable driving experience.

[0173] A more aggressive approach to route planning could include choosing the shortest route, even if it involves navigating congested areas. For example, a smart vehicle could choose a straight path through the city center, utilize real-time traffic information for quick lane changes and overtaking, or opt for side streets or shortcuts to quickly traverse densely populated areas, thus reducing travel time.

[0174] Cut-in handling refers to deciding whether to yield or maintain lane position when encountering other vehicles attempting to cut into the current lane, based on real-time traffic conditions and vehicle dynamics, in order to ensure driving safety and smooth flow.

[0175] For example, driving style 1 is sporty, driving style 2 is comfortable, and driving style 3 is aggressive. Different driving styles are processed by the intelligent driving model using driving environment and navigation information, resulting in the following cut-off handling:

[0176] The lane-cutting handling corresponding to the sporty driving style can include: when encountering other vehicles attempting to cut into the current lane, selectively yielding based on real-time traffic conditions to avoid unnecessary deceleration and acceleration. For example, when the intelligent driving vehicle detects a vehicle attempting to cut in, it can slightly decelerate, increase the distance from the vehicle in front, and make enough space for the vehicle to smoothly cut in, thereby maintaining the smoothness of the overall traffic flow.

[0177] The comfort mode's handling of lane-cutting situations can include: proactively yielding when encountering lane-cutting to avoid discomfort caused by sudden braking or acceleration. For example, when a vehicle in the adjacent lane intends to cut in, the intelligent driving vehicle can slow down in advance, maintain a large safe distance, and make enough space for the vehicle to safely insert itself, thereby ensuring a comfortable experience for passengers.

[0178] Aggressive lane-cutting responses could include maintaining lane position and not yielding when encountering a lane-cutting situation, unless a potential collision risk is detected. For example, when a vehicle attempts to cut in, the autonomous vehicle can maintain its current speed or slightly accelerate to prevent other vehicles from cutting in, thus maintaining driving speed and rhythm.

[0179] Lane change timing is a decision made on multi-lane roads based on the speed and position of surrounding vehicles and the navigation requirements of the destination, to optimize driving efficiency or avoid obstacles.

[0180] For example, driving style 1 is sporty, driving style 2 is comfortable, and driving style 3 is aggressive. Different driving styles are processed by the intelligent driving model using driving environment and navigation information, resulting in lane change timing selections as follows:

[0181] The timing of lane changes corresponding to a sporty driving style can include: on multi-lane roads, choosing to change lanes when traffic flow is relatively stable and there is sufficient space, based on the speed and position of surrounding vehicles, in order to optimize driving efficiency. For example, when the intelligent driving vehicle detects a slow-moving vehicle in the lane ahead, it can smoothly change lanes while ensuring sufficient space in the adjacent lane, in order to maintain a high driving speed and smoothness.

[0182] The lane-changing timing selection corresponding to the comfort mode can include: when changing lanes, it prefers to choose a time when there is less traffic and the lane-changing process is smoothest. For example, when the intelligent driving vehicle needs to change lanes to follow navigation instructions, the intelligent driving vehicle can wait for there to be a large gap between adjacent lanes and fewer vehicles, and then change lanes slowly and smoothly.

[0183] Aggressive lane-changing timing options could include using a small gap to quickly change lanes and reach the destination faster. For example, when an autonomous vehicle detects an obstacle or slow-moving vehicle in the lane ahead, it can quickly analyze the traffic speed and spacing in adjacent lanes and choose to change lanes in the shortest possible time to avoid deceleration and maintain speed.

[0184] Following distance is a dynamic adjustment of the safe distance between the vehicle and the vehicle in front, based on the current driving speed, road conditions, and traffic density, to ensure sufficient reaction time and driving safety.

[0185] For example, driving style 1 is sporty, driving style 2 is comfortable, and driving style 3 is aggressive. Different driving styles are processed by the intelligent driving model using driving environment and navigation information to obtain following distances as follows:

[0186] The following distance corresponding to a sporty driving style can include: selecting an appropriate following distance based on the current driving speed and road conditions while maintaining a smooth driving experience. For example, when the intelligent driving vehicle is traveling at 100 km / h on a highway, it can choose to maintain a following distance of 50 meters to ensure sufficient reaction time while maintaining a high speed.

[0187] The following distance corresponding to the comfort mode can include: selecting a larger following distance to consider driving smoothness. For example, when the intelligent driving vehicle is traveling at 100 km / h on a highway, it can choose to maintain a following distance of 70 meters to smoothly adjust its speed when traffic changes, thereby ensuring a comfortable experience for passengers.

[0188] An aggressive driving style might correspond to a shorter following distance when prioritizing speed and efficiency. For example, when a self-driving vehicle is traveling at 100 km / h on a highway, it could choose to maintain a following distance of 30 meters to quickly change lanes and overtake in heavy traffic, thus maintaining speed and rhythm.

[0189] Turning speed is the appropriate speed selected when turning, based on the road curvature and vehicle dynamics, to ensure vehicle stability and passenger comfort.

[0190] For example, driving style 1 is sporty, driving style 2 is comfortable, and driving style 3 is aggressive. Different driving styles are processed by the intelligent driving model using driving environment and navigation information to obtain turning speeds as follows:

[0191] The cornering speed corresponding to a sporty driving style can include: while maintaining a smooth driving experience, selecting a higher cornering speed based on road curvature and vehicle dynamics to ensure driving stability. For example, when an intelligent driving vehicle is turning on a highway ramp with minimal curvature, it can choose to pass through at a speed of 40 km / h.

[0192] The cornering speed corresponding to the comfort mode can include: selecting a lower cornering speed considering passenger comfort and ride smoothness. For example, when the intelligent driving vehicle is turning on the same highway ramp, the vehicle can choose to pass through at a speed of 30 km / h to reduce lateral acceleration and ensure a comfortable experience for passengers.

[0193] Aggressive driving style can correspond to cornering speeds that prioritize speed and efficiency, such as choosing higher cornering speeds. For example, when a smart driving vehicle is turning on the same ramp, it can choose to pass through at 50 km / h to complete the turn more quickly and maintain speed and rhythm.

[0194] The time interval between the start-up of the autonomous mobile device in front is determined when the vehicle restarts at a traffic light or while the vehicle is stopped, in order to optimize traffic flow efficiency and driving safety.

[0195] For example, driving style 1 is sporty, driving style 2 is comfortable, and driving style 3 is aggressive. Different driving styles are processed by the intelligent driving model using driving environment and navigation information. The resulting time interval between the start-up of the vehicle and the autonomous mobile device ahead can be as follows:

[0196] The start-up interval corresponding to a sporty driving style can include selecting a shorter start-up interval to respond quickly to changes in traffic signals. For example, when the traffic light turns green, after the vehicle in front starts moving, the autonomous driving vehicle can start moving within 1 second to ensure rapid following of the vehicle in front and optimize traffic flow efficiency.

[0197] The start-up interval for the comfort mode can include: selecting an appropriate start-up interval while considering passenger comfort and driving smoothness. For example, when the traffic light turns green, after the vehicle in front starts moving, the intelligent driving vehicle can start moving within 2 seconds to ensure a smooth start and avoid passengers feeling sudden acceleration.

[0198] The start-up interval for an aggressive driving style could include selecting a shorter start-up interval to respond quickly and reach normal driving speed. For example, when the traffic light turns green and the vehicle in front starts moving, the autonomous vehicle could start moving within 0.5 seconds to quickly reach normal driving speed and maintain speed and rhythm.

[0199] Optionally, driving environment information may include, but is not limited to, motion status information of the autonomous mobile device, motion status of surrounding traffic participants, and road traffic information; and / or, navigation information may include, but is not limited to, map information, location information of the autonomous mobile device, and path trajectory information.

[0200] For example, an intelligent driving model equipped with Driving Style 1 can process driving environment and navigation information during the operation of the intelligent driving vehicle to obtain driving decision-making plans. These plans include considerations for lane-cutting and the time interval between the vehicle in front and the vehicle ahead.

[0201] S306. Control the autonomous mobile device to drive according to the driving decision plan.

[0202] For example, during the operation of an intelligent driving vehicle, precise control of the vehicle can be achieved based on the lane-cutting handling and the time interval between the start of the vehicle in front in the driving decision-making scheme.

[0203] For example, when a self-driving vehicle is traveling on a highway, it detects a car attempting to cut in from the adjacent lane. Based on the decision to handle the cut-in, the vehicle safely creates space by slightly slowing down and adjusting its distance from the vehicle in front, ensuring smooth and safe driving. Simultaneously, when encountering traffic lights, the self-driving vehicle can optimize its actions based on the time interval between its start and the vehicle in front. When the red light turns green, the vehicle detects that the vehicle in front has begun to move and quickly and smoothly starts moving within one second.

[0204] In this embodiment, the electronic device can analyze the current user's historical driving behavior data to determine historical feature vectors. Then, it acquires driving feature vectors corresponding to multiple driving styles, obtained through cluster analysis of the driving behavior data of multiple users. Based on the historical feature vectors, a matching process is performed on these driving style-corresponding driving feature vectors to determine the target driving style. The target driving style can be configured into the intelligent driving model of the autonomous mobile device. Furthermore, the intelligent driving model can process driving environment information and navigation information, generate driving decision-making schemes, and control the driving of the autonomous mobile device. In the above process, by analyzing the current user's historical driving behavior data and determining the target driving style, a personalized driving experience can be provided to the user, making the response and behavior of the autonomous mobile device more in line with the user's driving habits and preferences, thereby improving the user experience.

[0205] Figure 4 is a logical block diagram of determining driving decisions provided in an embodiment of this application. Referring to Figure 4, the target driving style can be configured in the end-to-end system. The end-to-end system can comprehensively process driving environment information, navigation information, and the target driving style to generate a driving decision scheme. The target driving style is obtained by clustering and analyzing the driving behavior data of multiple users, and an appropriate driving style category is selected from the clustering results.

[0206] During the training phase of the end-to-end system, each input data segment not only includes driving environment and navigation information but also needs to be associated with the corresponding driving style. Simultaneously, the end-to-end system also needs to introduce ground truth trajectory values ​​as a supervision signal. By comparing the difference between the predicted behavioral trajectory output by the model and the ground truth trajectory values, a loss function (LOSS) (such as mean squared error, trajectory similarity loss, etc.) is calculated to optimize the model parameters.

[0207] In this embodiment of the application, by clustering and analyzing multi-user driving behavior data, diverse driving styles can be identified, enabling the end-to-end system to flexibly configure target driving styles, meet the personalized needs of different users, and significantly improve the adaptability of driving decisions and user experience.

[0208] Furthermore, by integrating driving environment information, navigation information, and target driving style for collaborative processing, the end-to-end system enhances its perception and decision-making capabilities in complex scenarios, ensuring that the generated driving decisions are both safe and adaptable to different scenarios. In addition, by introducing ground truth trajectory values ​​as a supervisory signal during end-to-end system training and dynamically optimizing model parameters using a loss function, the system's output behavioral trajectories can be ensured to match real driving data, effectively improving the accuracy and reliability of driving decisions and ensuring they match the configured driving style, thus significantly enhancing the user's driving experience.

[0209] Figure 5 is a flowchart illustrating an embodiment of the data processing method for driving style provided in this application. Referring to Figure 5, this method, applied to a server, may include:

[0210] S501: Obtain driving behavior data from multiple users.

[0211] In this step, the server can obtain driving behavior data from multiple users in at least one of the following ways.

[0212] Method 1: The sensing devices (such as cameras, lidar, millimeter-wave radar, accelerometers) equipped on autonomous mobile devices can record the driving behavior data of multiple users in real time. This driving behavior data can be uploaded to the server through the vehicle networking system, or transferred to a removable storage medium and then uploaded to the server.

[0213] Method 2: Obtain driving behavior data from multiple users from open, shared data platforms. These platforms typically offer datasets from multiple sources for technical personnel to study. Through APIs or data download services, the server can access the data on these platforms to obtain driving behavior data from multiple users.

[0214] S502. Perform cluster analysis on the driving behavior data of multiple users to obtain at least one cluster.

[0215] In this step, the server performs cluster analysis on the driving behavior data of multiple users to obtain at least one cluster. Specifically, for each user, the server can obtain a feature vector corresponding to the user based on the user's driving behavior data. This feature vector may include at least one piece of data related to driving style. Furthermore, cluster analysis can be performed on the feature vectors of multiple users to obtain at least one cluster.

[0216] Optionally, for each user, features can be extracted from driving behavior data based on preset quantitative indicators and / or preset feature processing models to obtain feature vectors;

[0217] Among them, the preset quantitative indicators are determined based on the driving behavior of multiple users in at least one driving scenario, including but not limited to cutting in, starting and stopping, congestion, following other vehicles, and turning; the preset feature processing model is used to extract features from the users' driving behavior data to obtain feature vectors.

[0218] Similarly, based on preset quantitative indicators, features can be extracted from historical driving behavior data to obtain a first historical feature vector, and this first historical feature vector can be determined as the historical feature vector; or,

[0219] Based on a pre-defined feature processing model, features are extracted from historical driving behavior data to obtain a second historical feature vector, which is then determined as the historical feature vector; or,

[0220] Based on preset quantitative indicators, features are extracted from historical driving behavior data to obtain a first historical feature vector. Based on a preset feature processing model, features are extracted from historical driving behavior data to obtain a second historical feature vector. The first historical feature vector and the second historical feature vector are then concatenated to obtain a historical feature vector.

[0221] It should be understood that for each user, the aforementioned historical driving behavior data is essentially also the user's driving behavior data; the user's feature vector can be a first historical feature vector, a second historical feature vector, or a combined vector obtained by concatenating the first historical feature vector and the second historical feature vector.

[0222] Optionally, the clustering algorithm used for clustering analysis of driving behavior data from multiple users can include any one of the following: K-means clustering, hierarchical clustering, and DBSCAN clustering. After the clustering analysis is completed, each cluster can represent a typical driving style.

[0223] For example, the K-means clustering algorithm can be used to perform cluster analysis on the feature vectors corresponding to the driving behavior data of 100 users, resulting in 3 clusters, which represent 3 driving styles.

[0224] S503. Add corresponding driving styles to at least one cluster to determine multiple driving styles.

[0225] In this step, you can add a driving style to each cluster in the clustering results to obtain multiple driving styles.

[0226] Since driving behavior data belonging to the same category usually have similar behavioral styles, algorithm experts can use the clustering results to add a driving style that matches the behavioral style of each cluster.

[0227] For example, three clusters obtained through the K-means clustering algorithm can be assigned corresponding driving style names and other information to create three driving styles. Cluster 1 can correspond to driving style 1, cluster 2 to driving style 2, and cluster 3 to driving style 3. Driving style 1 can be sporty, driving style 2 can be comfortable, and driving style 3 can be aggressive.

[0228] S504: Deploy multiple driving styles to at least one autonomous mobile device.

[0229] In one specific implementation, each driving style sent by the server to at least one autonomous mobile device may also include configuration parameters or configuration files for that driving style. These configuration parameters or configuration files may include, but are not limited to, speed control parameters, steering sensitivity, following distance and distance maintenance, response time to obstacles, and reaction to traffic signals.

[0230] For example, the server can issue driving style 1, driving style 2, and driving style 3 to at least one intelligent driving vehicle. Driving style 1 can also include configuration parameters for driving style 1, which may include a maximum speed of 120 km / h, a 0-100 km / h acceleration time of 7 seconds, and a minimum safe distance of 50 meters from the vehicle in front when driving at high speed. Driving style 2 can also include configuration parameters for driving style 2, which may include a maximum speed of 100 km / h, a 0-100 km / h acceleration time of 10 seconds, and a minimum safe distance of 70 meters from the vehicle in front when driving at high speed. Driving style 3 can also include configuration parameters for driving style 4, which may include a maximum speed of 140 km / h, a 0-100 km / h acceleration time of 3 seconds, and a minimum safe distance of 30 meters from the vehicle in front when driving at high speed.

[0231] In this embodiment, the server can acquire driving behavior data from multiple users and perform cluster analysis on this data to identify at least one cluster. Subsequently, each cluster can be assigned a corresponding driving style, thereby determining multiple driving styles. Finally, the server can distribute multiple driving styles to at least one autonomous mobile device. In the above process, by acquiring and analyzing driving behavior data from multiple users through the server and distributing the results to the autonomous mobile device, a personalized driving experience can be achieved. This enables the autonomous mobile device to determine a target driving style that matches the current user's driving preferences and habits based on the user's historical driving behavior data, thereby improving user satisfaction.

[0232] In one possible design, the method for recognizing driving styles may also include: the autonomous mobile device can receive multiple driving styles from the server and display the multiple driving styles in the visualization interface of the autonomous mobile device.

[0233] Optionally, users can select a target driving style from multiple driving styles in the visual interface, fine-tune the target driving style through the visual interface, and set personalized parameters such as acceleration, cornering sensitivity and braking intensity to create a unique driving style for experience.

[0234] Furthermore, after selecting a target driving style in the visual interface, users can fine-tune it based on their actual driving experience during the trial. The visual interface provides real-time data feedback, such as speed, acceleration, and energy consumption, to help users make further adjustments. In addition, the system can intelligently recommend the most suitable driving style on the visual interface based on the current driving environment and road conditions.

[0235] In this embodiment, the autonomous mobile device can receive multiple driving styles from the server and display them on its visual interface for the user to choose from. Users can freely select and adjust their driving style according to their personal preferences, thereby obtaining a more personalized driving experience.

[0236] Figure 6 is a flowchart illustrating a second embodiment of the data processing method for driving style provided in this application. Referring to Figure 6, based on the embodiment shown in Figure 5, step S502 may include:

[0237] S601. For each user, obtain the user's corresponding feature vector based on the user's driving behavior data. The feature vector includes at least one piece of data related to driving style.

[0238] In this step, for each user, feature vectors can be obtained by extracting features from the user's driving behavior data based on preset quantitative indicators and / or preset feature processing models.

[0239] Specifically, the preset quantitative indicators are determined based on the driving behavior of multiple users in at least one driving scenario, including but not limited to cutting in, starting and stopping, congestion, following other vehicles, and turning.

[0240] For example, for User 1, features can be extracted from User 1's historical driving behavior data based on preset quantitative indicators to obtain a first historical feature vector. The first historical feature vector may include multiple numerical indicators determined based on preset quantitative indicators. For example, the first historical feature vector may include numerical indicators determined based on preset quantitative indicator 1 and preset quantitative indicator 2. Preset quantitative indicator 1 may be based on the closest distance between the intelligent driving vehicle and other vehicles in a lane-cutting scenario, thus extracting numerical indicator 1 from User 1's historical driving behavior data. Numerical indicator 1 could be 0.3m. Preset quantitative indicator 2 may be based on how long after the preceding vehicle starts moving in a start-stop scenario that the vehicle also starts moving, thus extracting numerical indicator 2 from User 1's historical driving behavior data. Numerical indicator 2 could be 2 seconds after the preceding vehicle starts moving that the vehicle also starts moving.

[0241] Specifically, the preset feature processing model is used to extract features from the user's driving behavior data to obtain feature vectors.

[0242] For example, for user A's driving behavior data, a first historical feature vector can be extracted based on preset quantitative indicators, and a second historical feature vector can be extracted based on preset feature processing models. The first historical feature vector and the second historical feature vector are concatenated to obtain a combined vector, which serves as user A's final feature vector.

[0243] Furthermore, if only preset quantitative indicators or preset feature processing models are used to extract features from user A's driving behavior data, resulting in a feature vector, this feature vector can be either a first historical feature vector or a second historical feature vector.

[0244] S602. Perform cluster analysis on the feature vectors of multiple users to obtain at least one cluster.

[0245] In this step, cluster analysis can be performed on the feature vectors corresponding to the driving behavior data of multiple users to obtain at least one cluster.

[0246] In one specific implementation, each cluster can correspond to a driving style, which can be represented by the center of the cluster. The vector representing the cluster center can be used as the driving feature vector of that driving style.

[0247] In this embodiment, the server acquires driving behavior data from multiple users and generates a feature vector for each user. These feature vectors undergo cluster analysis to identify at least one cluster. Each cluster is assigned a specific driving style, thus determining multiple driving styles. Finally, the server can distribute multiple driving styles to at least one autonomous mobile device. Through this process, the autonomous mobile device can determine the target driving style that best matches the user's driving preferences and habits based on the user's current historical driving behavior data, providing a personalized driving experience.

[0248] Figure 7 is a schematic diagram of a clustering result provided in an embodiment of this application. Referring to Figure 7, the autonomous driving training data may include driving behavior data of multiple users. Through preset quantitative indicators in the expert scoring system, feature vectors can be extracted from the driving behavior data of multiple users. Then, cluster analysis is performed on the feature vectors to obtain at least one cluster. By adding corresponding driving styles to each of the at least one cluster, multiple driving styles can be determined.

[0249] For example, the identified driving styles can include a sporty and aggressive driving style, a sporty and comfortable driving style, a comfortable and conservative driving style, ..., and a cautious and conservative driving style. Specifically, User 1 (Driver 1) can have a sporty and aggressive driving style, User 2 (Driver 2) can have a sporty and comfortable driving style, User 3 (Driver 3) can have a comfortable and conservative driving style, and User N (Driver N) can have a cautious and conservative driving style.

[0250] In one possible design, any cluster corresponds to a driving style with a corresponding style description. The style description is used to interpret the driving style. Then, step S504, which involves sending multiple driving styles to at least one autonomous mobile device, may include sending multiple driving styles and a style description corresponding to each driving style to at least one autonomous mobile device.

[0251] In one alternative implementation, algorithm experts can add qualitative style descriptions to the driving style corresponding to each cluster based on the clustering results, thereby enabling the interpretation of that driving style.

[0252] For example, Driving Style 1 is Sporty, described as offering quick acceleration and responsive steering, tending to maintain moderate to high speeds. It prioritizes a balance between handling and efficiency when cornering or changing lanes, making it ideal for users seeking driving pleasure. Driving Style 2 is Comfort, described as emphasizing smooth driving with linear and gentle acceleration and braking, actively maintaining a safe distance from the vehicle in front, and reducing sharp turns or frequent lane changes. It is suitable for family trips or long-distance driving where high comfort is required. Driving Style 3 is Aggressive, described as frequently overtaking and changing lanes with larger acceleration and braking amplitudes, tending to drive close to the road speed limit, and responding quickly to dynamic changes in traffic flow. It is suitable for time-sensitive tasks or scenarios requiring high traffic efficiency.

[0253] In another optional implementation, the style description corresponding to the driving style may also include at least one of the following: overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving smoothness, and average vehicle speed.

[0254] The probability of overtaking can refer to the frequency with which a user performs overtaking maneuvers during driving. For example, an aggressive driver might overtake every 10 minutes on a highway to quickly pass slower vehicles, while a comfort-oriented driver might only overtake when it is safe and necessary to ensure driving safety.

[0255] Traffic efficiency refers to how efficiently a vehicle traverses a certain distance within a unit of time. For example, an aggressive traveler might maintain high traffic efficiency on busy city roads, arriving at their destination 10 minutes faster than average during peak hours, while a comfort-oriented traveler might prioritize a smooth ride, even if the journey takes slightly longer.

[0256] Driving smoothness refers to the ability of an autonomous mobile device to maintain a stable state during driving, including the smoothness of acceleration, braking, and steering. For example, an aggressive driver might frequently engage in rapid acceleration and sharp turns, resulting in lower driving smoothness. A comfort-oriented driver might maintain a steady speed and gentle cornering during long journeys to ensure passenger comfort.

[0257] Average speed can refer to the average speed of an autonomous mobile device over a period of time. For example, an aggressive user might maintain an average speed of 60 km / h on a road with a speed limit of 60 km / h to enjoy driving while obeying traffic rules, while a comfort-oriented user might maintain a speed of 40 km / h to ensure passenger comfort and safety.

[0258] Acceleration frequency can refer to the frequency with which a user accelerates while driving. For example, an aggressive driver might accelerate every 5 minutes on city roads to quickly speed up between traffic lights, while a comfort-oriented driver might accelerate only once every 15 minutes to maintain a smooth driving experience.

[0259] Lane change frequency can refer to how often a user changes lanes while driving. For example, an aggressive driver might change lanes every 2 minutes on congested city roads to find the fastest route, while a comfort-oriented driver might only change lanes when necessary throughout the trip.

[0260] It should be noted that the indicators included in the style description corresponding to driving style, such as overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving smoothness, and average speed, can be calculated based on the average value of the clustering results. These average values ​​provide a representative perspective for describing driving style, enabling each style to reflect the typical characteristics of each cluster in the clustering analysis results, thus providing a more accurate and comprehensive interpretation of driving style.

[0261] In this embodiment of the application, the server can generate a style description including qualitative and / or quantitative indicators for each driving style corresponding to each cluster, and send the style description to the autonomous mobile device, so that the autonomous mobile device can select and adapt to the driving style that matches the user's preferences and habits based on the user's historical behavior, thereby providing a personalized driving experience.

[0262] Similarly, in one possible design, the driving style recognition method may also include: the autonomous mobile device can receive the style description of each driving style sent, and display multiple driving styles and the style description corresponding to each driving style in the visualization interface of the autonomous mobile device.

[0263] Optionally, a detailed description of each driving style can be displayed through a visual interface, allowing users to better understand the characteristics and applicable scenarios of each style. Furthermore, users can select their target driving style based on qualitative and / or quantitative indicators (such as acceleration frequency, average vehicle speed, etc.) in the style description, combined with their own driving preferences and needs.

[0264] In this embodiment, the autonomous mobile device can receive and display multiple driving styles and their corresponding detailed descriptions, providing users with an intuitive selection experience through a visual interface. This process not only allows users to easily understand and compare the characteristics of different driving styles, but also enables them to select a target driving style based on personal preferences, thereby achieving a personalized driving experience.

[0265] Figure 8 is a flowchart illustrating a third embodiment of the data processing method for driving style provided in this application. Referring to Figure 8, based on the above embodiments, the data processing method for driving style may further include:

[0266] S801. Obtain the current user's driving behavior data sent by the autonomous mobile device.

[0267] For example, a server can receive driving behavior data of the current user A sent by an autonomous mobile device.

[0268] S802. Based on preset quantitative indicators, determine the relative driving indicators of the current user according to the driving behavior data of multiple users and the driving behavior data of the current user.

[0269] In this step, the server can analyze the driving behavior data of multiple users and the current user's driving behavior data, and determine the current user's relative driving index based on preset quantitative indicators. The relative driving index is used to represent the current user's ranking among multiple users. The preset quantitative indicators are determined based on the user's driving behavior in at least one driving scenario, including but not limited to cutting in, stop-and-go traffic, congestion, following other vehicles, and turning.

[0270] Optionally, numerical indicators can be extracted from the current user's driving behavior data and the driving behavior data of multiple users based on preset quantitative indicators. The ranking of the current user among multiple users can be determined based on the comprehensive position of the current user's numerical indicators among the numerical indicators of multiple users.

[0271] For example, the current user's ranking among multiple users can be obtained through the following steps ①②③.

[0272] Step 1: For each driving scenario, the server can extract numerical metrics based on preset quantitative indicators. For example, in a lane-cutting scenario, the frequency of lane-cutting is extracted from the driving behavior data of the current user A and multiple users.

[0273] Step 2: The server can compare the current user A's numerical metrics with those of multiple other users to generate a relative ranking. For example, in a queue-jumping scenario, the server can compare the current user A's queue-jumping frequency with that of other users. Through a ranking algorithm, the server can determine the current user A's position within the overall user group. Assume that the current user A's queue-jumping frequency is in the top 20% of all users, meaning that the current user A queues up more frequently than 80% of other users.

[0274] Step 3: The server can comprehensively analyze the relative rankings in various scenarios to generate a relative driving index, which can be the current user's overall driving score. The current user A's overall driving score can be calculated using a weighted average or other statistical methods to provide a comprehensive assessment of the current user A's overall driving style and determine the current user A's relative driving index among multiple users, such as being in the top 10% for aggressive driving or in the top 5% for comfortable driving.

[0275] Optionally, after determining the current user's relative driving score among multiple users, the server can choose to send the relative driving score directly to the current user's mobile device or terminal device. Alternatively, the server can integrate the relative driving score into a driving style description report and send that report to the current user. This allows the current user to clearly understand their overall driving score, thereby helping them better understand their driving style. The terminal device can be the current user's smartphone, laptop, smartwatch, or mobile phone.

[0276] In this embodiment, the server can acquire the current user's driving behavior data sent by the autonomous mobile device. Based on preset quantitative indicators, it analyzes the driving behavior data of multiple users and the current user's data to determine the current user's relative driving index. Through the relative driving index, users can understand their ranking within a larger user group, helping them identify the relative position of their driving style and motivating them to improve their driving behavior to achieve a higher ranking or better driving performance.

[0277] Figure 9 is a flowchart illustrating Embodiment 4 of the data processing method for driving style provided in this application. Referring to Figure 9, based on Embodiment 3 above, the data processing method for driving style may further include:

[0278] S901: Obtain target personality traits corresponding to multiple driving styles.

[0279] In this step, the server can obtain the target personality traits of the driving style corresponding to each cluster.

[0280] Personality traits can be personalized characteristics inferred by the server after analyzing driving behavior data. These personality traits may include, but are not limited to: adventurous, cautious, patient, and confident.

[0281] In one optional implementation, the server can pre-train a personality analysis model specifically for inferring personality traits. This model analyzes each user's driving behavior data to obtain their personality traits. For any given cluster corresponding to a driving style, the most frequently occurring personality trait among users belonging to that driving style can be selected as the target personality trait for that driving style. Optionally, this personality analysis model can be merged with a pre-defined feature processing model into a comprehensive model that outputs both the user's personality trait and feature vectors based on their driving behavior data.

[0282] For example, personality traits can also be categorized into personality types by selecting one personality description from each of the following four personality dimensions. Dimension 1 includes introversion and extroversion, Dimension 2 includes sensing and intuition, Dimension 3 includes thinking and feeling, and Dimension 4 includes judging and perceiving.

[0283] For example, the server can analyze the driving behavior data of multiple users and infer that the target personality trait of driving style 1 (cluster 1) is adventurous, the target personality trait of driving style 2 (cluster 2) is cautious, and the target personality trait of driving style 3 (cluster 3) is patient.

[0284] S902. Add the target personality traits corresponding to each driving style to the style description corresponding to the driving style.

[0285] For example, the server can add the adventurous personality trait corresponding to driving style 1 to style description 1 corresponding to driving style 1, add the cautious personality trait corresponding to driving style 2 to style description 2 corresponding to driving style 2, and add the patient personality trait corresponding to driving style 3 to style description 3 corresponding to driving style 3.

[0286] In this embodiment, the server can obtain multiple target personality traits corresponding to different driving styles and add each target personality trait corresponding to a driving style to its corresponding style description. By combining personality traits with driving styles, the server can help users better understand the relationship between driving behavior and personality traits, providing personalized feedback to users.

[0287] Based on the embodiment shown in Figure 9, the above-described data processing method for driving style will be further described in detail below with reference to Figure 10.

[0288] Figure 10 is a flowchart illustrating Embodiment 5 of the data processing method for driving style provided in this application. Referring to Figure 10, based on Embodiment 4 above, the data processing method for driving style may include:

[0289] S1001. Establish style mapping relationships based on the personality traits and driving styles of multiple users.

[0290] In this step, the server can establish a style mapping relationship based on the personality traits and driving styles of multiple users. The style mapping relationship includes the target personality trait corresponding to each driving style, which is the personality trait that appears most frequently among users corresponding to that driving style.

[0291] Optionally, while acquiring driving behavior data from multiple users, the server can also acquire the personality traits of each user. These personality traits can be selected by the user through a visual interface on their mobile device.

[0292] For example, the visual interface of an intelligent driving vehicle can offer users a variety of personality traits to choose from. Each user can upload their driving behavior data along with their own personality traits to the server. For instance, user 1 can select their adventurous personality trait when uploading their driving behavior data to the server.

[0293] When the server performs cluster analysis on the driving behavior data of multiple users to obtain at least one cluster and further obtains the driving style corresponding to each cluster, the personality trait that appears most frequently among the users corresponding to that driving style can be selected as the target personality trait corresponding to that driving style. A style mapping relationship is then established based on each driving style and the target personality trait corresponding to that driving style.

[0294] For example, based on the personality traits and driving styles of multiple users, a style mapping relationship can be established, and some of the correspondences are shown in Table 1:

[0295] Table 1

[0296] S1002. Based on the style mapping relationship, query and obtain the target personality characteristics corresponding to each driving style.

[0297] For example, based on the style mapping relationship, we can query to obtain the target personality traits corresponding to driving style 1 as adventurous, driving style 2 as cautious, and driving style 3 as patient.

[0298] S1003. Add the target personality traits corresponding to each driving style to the style description corresponding to the driving style.

[0299] For example, the adventurous personality traits, the cautious personality traits, and the patient personality traits can be added to style description 1, style description 2, and style description 3 respectively.

[0300] In this embodiment, the server can establish a style mapping relationship based on the personality traits and driving styles of multiple users. Through this style mapping relationship, the server can query and obtain the target personality traits corresponding to each driving style, and integrate these target personality traits into the corresponding driving style description. This helps users gain a deeper understanding of the connection between their driving behavior and personality traits, providing personalized feedback and suggestions to improve the user experience.

[0301] Figure 11 is a flowchart illustrating Embodiment Six of the data processing method for driving style provided in this application. Referring to Figure 11, based on Embodiment Five above, the data processing method for driving style may include:

[0302] S1101. Based on the current user's target driving style and style mapping relationship, determine the style description report corresponding to the current user's target driving style.

[0303] In this step, the server can obtain the current user's target driving style, determine the target personality traits corresponding to the target driving style based on a pre-established style mapping relationship, and add the target personality traits to the style description corresponding to the target driving style to create a style description report unique to the current user. This style description report may include at least one of the following: overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving smoothness, average vehicle speed, relative driving indicators, and personality traits.

[0304] For example, based on the historical driving behavior data of current user A, the target driving style for current user A is identified as Driving Style 1 from multiple driving styles. Based on the pre-established style mapping relationship, the target personality trait corresponding to Driving Style 1 can be determined to be adventurous. The adventurous personality trait is added to Style Description 1 corresponding to Driving Style 1, creating a style description report specific to current user A. The style description report may include: current user A's driving style is aggressive; they can maintain an average speed of 50 km / h on roads with a speed limit of 60 km / h; they accelerate every 4 minutes on urban roads; current user A's aggressiveness is in the top 10% among users with adventurous personality traits; and their personality trait is adventurous.

[0305] In one alternative implementation, besides style mapping to determine the target personality traits of the current user, a more detailed personality trait can be obtained through a personality trait inference model. This model can accept various inputs, such as driving style, detailed driving data, and age. Based on these inputs, the model can infer and output more accurate personality traits. The personality trait inference model can be a pre-trained deep learning model or an artificial intelligence model.

[0306] For example, the personality trait inference model is an artificial intelligence (AI) model. This AI model can analyze the current user A's behavioral patterns under different driving conditions, such as acceleration and braking habits, turning speed, and reactions to different weather and traffic conditions. Furthermore, the AI ​​model can consider the impact of the current user A's age on driving habits and risk preferences. By integrating these factors, the AI ​​model can output more detailed and personalized personality traits about the current user A. For instance, the personality traits output by the AI ​​model for the current user A could be: the current user A tends to drive quickly in good weather and with less traffic, exhibiting a high risk preference; in bad weather, the user reduces speed and prioritizes safety; and the user is easily impatient during long traffic jams.

[0307] S1102. Send the current user's style description report to the autonomous mobile device.

[0308] For example, the server can send a style description report of the current user A to the current user A's intelligent driving vehicle.

[0309] In this embodiment, the server can determine the corresponding style description report based on the current user's target driving style and style mapping relationship, and then send the current user's style description report to the autonomous mobile device. In this way, the current user can receive personalized driving feedback, helping them better understand the connection between their driving behavior and personality traits. Furthermore, the style description report can include detailed driving behavior analysis, such as overtaking probability, traffic efficiency, and acceleration frequency, thereby providing specific improvement suggestions to the current user, enhancing the user experience, and enabling the current user to experience higher levels of intelligence and personalization when using the autonomous mobile device.

[0310] Figure 12 is a flowchart illustrating a third embodiment of the driving style recognition method provided in this application. Referring to Figure 12, after the service sends a style description report of the current user to the autonomous mobile device, the driving style recognition method may further include:

[0311] S1201, Receive the style description report of the current user sent by the server.

[0312] In this step, the electronic device can receive a style description report of the current user sent by the server. The style description report includes at least one of the following: overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving smoothness, average vehicle speed, relative driving index, and personality traits.

[0313] For example, an electronic device can receive a style description report of the current user A sent by a server. The style description report may include information such as the current user A's driving style being aggressive, maintaining an average speed of 50 km / h on roads with a speed limit of 60 km / h, accelerating every 4 minutes on urban roads, and the current user A being in the top 10% of users with adventurous personality traits, and having an adventurous personality trait.

[0314] S1202. In response to the current user's first upload operation, upload the current user's style description report to the shared cloud platform.

[0315] In this step, the electronic device can respond to the current user's first upload operation by uploading the current user's style description report to a shared cloud platform, which is used for interaction among users of multiple autonomous mobile devices.

[0316] A shared cloud platform can serve as a centralized data exchange center, allowing users of multiple independent mobile devices to interact and share data. Specifically, this can include actions such as liking, commenting, exchanging information, and sharing.

[0317] For example, a shared cloud platform can be an internet community where users can upload their own style description reports for other users in the community to comment on, like, and so on.

[0318] Optionally, the current user's first upload operation can be triggered in various ways, such as manual operation by the user on the electronic device, or preset automatic upload conditions (such as periodic uploads or uploads after a specific event).

[0319] In this embodiment, after receiving the current user's style description report from the server, the electronic device can, in response to the current user's manual operation, upload the current user's style description report to the shared cloud platform. By uploading the style description report to the shared cloud platform, personalized driving styles can be shared and interacted with, thereby enhancing user engagement and overall experience.

[0320] Figure 13 is a flowchart illustrating a fourth embodiment of the driving style recognition method provided in this application. Referring to Figure 13, based on the embodiment shown in Figure 12, the driving style recognition method may further include:

[0321] S1301, In response to the second upload operation of the current user, upload the operating information of the target driving style to the shared cloud platform.

[0322] In this step, the electronic device can respond to the user's second upload operation by uploading the operating information of the target driving style to the shared cloud platform. The operating information includes the target driving style and at least one of the following: the mileage, average energy consumption, and operating time of the target driving style.

[0323] Optionally, after the electronic device has controlled the autonomous mobile device to drive and run for a period of time based on the driving environment information, navigation information and target driving style acquired during the movement, it can respond to the user's second upload operation and upload the operation information of the target driving style to the shared cloud platform.

[0324] Similarly, the second upload operation can have the same triggering method as the first upload operation, such as manual operation by the user on the electronic device, preset automatic upload conditions (such as periodic uploads or uploads after a specific event), etc.

[0325] For example, if the target driving style is driving style 1, after a week of operation, an intelligent driving vehicle equipped with driving style 1 can respond to manual operation by user A and upload its operational information to the shared cloud platform. This information includes driving style 1, the distance traveled (200 km), average energy consumption (7 liters / 100 km), and operating time (48 hours). Optionally, if the intelligent driving vehicle's power source is electricity, the average energy consumption can be expressed in kilowatt-hours per 100 km.

[0326] In another alternative implementation, a target driving style determined based on historical driving behavior data corresponds to a driving style vector. The electronic device can respond to the current user's third upload operation by uploading the driving style vector separately to the shared cloud platform. Furthermore, the electronic device can also upload the driving style vector simultaneously with the target driving style's operational information uploaded to the shared cloud platform in response to the current user's second upload operation. The driving style vector can be obtained through consistency matching, similarity matching, or vector fusion methods.

[0327] It should be noted that since style data (such as driving style and style description) only includes style-related features (such as driving style vectors) and does not include specific driving scenarios or map information, nor does it contain personal privacy data, it can be shared without any other anonymization processing, making it easy to share without exposing personal information.

[0328] S1302. Control the autonomous mobile device to drive based on the new driving style downloaded by the current user from the shared cloud platform, as well as the driving environment information, navigation information, and new driving style obtained during the movement.

[0329] In this step, the electronic device can acquire the new driving style downloaded by the current user from the shared cloud platform and configure the new driving style in the intelligent driving model of the autonomous mobile device. Then, it can control the autonomous mobile device to drive by using the driving environment information and navigation information acquired during the movement of the autonomous mobile device.

[0330] In one alternative implementation, after the current user experiences a new driving style, they can provide feedback on the new driving style in the shared cloud platform, including actions such as liking, commenting, communicating, and sharing.

[0331] In this embodiment, the electronic device can respond to the current user's second upload operation by uploading operational information of the target driving style to the shared cloud platform. By uploading operational information, the current user can share the actual performance of their driving style with other users on the shared cloud platform, enhancing the current user's sense of participation and interaction with other users.

[0332] Furthermore, the driving style recognition method provided in this application allows the current user to browse driving styles shared by other users on a shared cloud platform, giving the current user more choices. The current user can select a driving style of interest to download. After downloading, the user can configure and experience the new driving style on their own mobile device to explore different driving experiences and improve user satisfaction.

[0333] Figure 14 is a structural schematic diagram of an embodiment of the driving style recognition device provided in this application. Referring to Figure 14, the driving style recognition device 10 includes:

[0334] The first acquisition module 11 is used to identify the target driving style of the current user from multiple driving styles based on the current user's historical driving behavior data. The multiple driving styles are obtained based on cluster analysis of the driving behavior data of multiple users.

[0335] The first processing module 12 is used to control the autonomous mobile device to drive based on the driving environment information, navigation information and the target driving style obtained during the movement.

[0336] The driving style recognition device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0337] In one possible implementation, the first acquisition module 11 is specifically used for:

[0338] Based on the historical driving behavior data, determine the historical feature vector;

[0339] Obtain the driving feature vectors corresponding to the multiple driving styles;

[0340] Based on the historical feature vector, a matching process is performed on the driving feature vectors corresponding to the multiple driving styles to determine the target driving style.

[0341] In one possible implementation, the first acquisition module 11 is specifically used for:

[0342] Based on preset quantitative indicators and / or preset feature processing models, feature extraction is performed on the historical driving behavior data to obtain the historical feature vector.

[0343] The preset quantitative index is determined based on the driving behavior of the multiple users in at least one driving scenario, including cutting in, starting and stopping, congestion, following other vehicles, and turning; the preset feature processing model is used to extract features from the users' driving behavior data to obtain feature vectors.

[0344] In one possible implementation, the first acquisition module 11 is specifically used for:

[0345] Based on the preset quantitative indicators, feature extraction is performed on the historical driving behavior data to obtain a first historical feature vector, and the first historical feature vector is determined as the historical feature vector; or,

[0346] Based on a preset feature processing model, features are extracted from the historical driving behavior data to obtain a second historical feature vector, and the second historical feature vector is determined as the historical feature vector; or,

[0347] Based on the preset quantitative indicators, features are extracted from the historical driving behavior data to obtain a first historical feature vector. Based on the preset feature processing model, features are extracted from the historical driving behavior data to obtain a second historical feature vector. The first historical feature vector and the second historical feature vector are then concatenated to obtain the historical feature vector.

[0348] In one possible implementation, the first processing module 12 is specifically used for:

[0349] Configure the target driving style in the intelligent driving model of the autonomous mobile device;

[0350] The driving environment information and navigation information are processed by an intelligent driving model to obtain a driving decision scheme;

[0351] The autonomous mobile device is controlled to drive according to the driving decision-making scheme;

[0352] The driving decision-making scheme includes at least one of the following: planning driving route, handling lane cutting, choosing lane change timing, following distance, turning speed, and time interval between starting and starting with the autonomous mobile device in front.

[0353] In one possible implementation, the driving environment information includes motion state information of the autonomous mobile device, motion state of surrounding traffic participants, and road traffic information; and / or,

[0354] The navigation information includes map information, location information of autonomous mobile devices, and path trajectory information.

[0355] Figure 15 is a structural schematic diagram of a second embodiment of the driving style recognition device provided in this application. Based on the embodiment shown in Figure 14, and referring to Figure 15, the driving style recognition device 10 further includes:

[0356] Receiver module 13 is used to receive the multiple driving styles sent by the server;

[0357] Display module 14 is used to display the multiple driving styles in the visualization interface of the autonomous mobile device.

[0358] In one possible implementation, the receiving module 13 is further configured to receive a style description for each driving style sent by the server;

[0359] Accordingly, the display module 14 is specifically used for:

[0360] The multiple driving styles and their corresponding style descriptions are displayed in the visual interface of the autonomous mobile device.

[0361] In one possible implementation, the receiving module 13 is further configured to receive a style description report of the current user sent by the server; the style description report includes at least one of the following: overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving smoothness, average vehicle speed, relative driving index, and personality traits.

[0362] The first processing module 12 is further configured to, in response to the first upload operation of the current user, upload the style description report of the current user to the shared cloud platform, which is used for interaction among users of multiple autonomous mobile devices.

[0363] In one possible implementation, the first processing module 12 is further configured to, in response to the second upload operation of the current user, upload the operation information of the target driving style to the shared cloud platform, wherein the operation information includes the target driving style and at least one of the following: the mileage, average energy consumption, and operation time of the target driving style.

[0364] In one possible implementation, the first processing module 12 is further configured to control the autonomous mobile device to drive based on the new driving style downloaded by the current user from the shared cloud platform, as well as driving environment information, navigation information, and the new driving style obtained during the movement.

[0365] The driving style recognition device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0366] Figure 16 is a schematic diagram of a first embodiment of the data processing device for driving style provided in this application. Referring to Figure 16, the data processing device 20 for driving style includes:

[0367] The second acquisition module 21 is used to acquire driving behavior data of multiple users;

[0368] Analysis module 22 is used to perform cluster analysis on the driving behavior data of the multiple users to obtain at least one cluster.

[0369] The second processing module 23 is used to add corresponding driving style labels to the at least one cluster to determine multiple driving styles.

[0370] The sending module 24 is used to send the multiple driving styles to at least one autonomous mobile device.

[0371] The data processing device for driving style provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be repeated here.

[0372] In one possible implementation, the analysis module 22 is specifically used for:

[0373] For each user, a feature vector corresponding to the user is obtained based on the user's driving behavior data, and the feature vector includes at least one piece of data related to driving style;

[0374] Cluster analysis is performed on the feature vectors of the multiple users to obtain at least one cluster.

[0375] In one possible implementation, any cluster corresponds to a driving style with a corresponding style description, which is used to interpret the driving style.

[0376] The sending module 24 is specifically used for:

[0377] The plurality of driving styles and the style description corresponding to each driving style are sent to the at least one autonomous mobile device.

[0378] In one possible implementation,

[0379] The second acquisition module 21 is further configured to acquire the current user's driving behavior data sent by the autonomous mobile device;

[0380] The second processing module 23 is further configured to determine the relative driving index of the current user based on a preset quantitative indicator, according to the driving behavior data of the multiple users and the driving behavior data of the current user, wherein the relative driving index is used to represent the ranking of the current user among the multiple users;

[0381] The preset quantitative indicators are determined based on the user's driving behavior in at least one of the following driving scenarios: cutting in, starting and stopping, traffic jams, following other vehicles, and turning.

[0382] In one possible implementation,

[0383] The second acquisition module 21 is also used to acquire target personality traits corresponding to the multiple driving styles;

[0384] The second processing module 23 is further configured to add the target personality traits corresponding to each driving style to the style description corresponding to the driving style.

[0385] Figure 17 is a schematic diagram of a second embodiment of the data processing device for driving style provided in this application. Based on the embodiment shown in Figure 16, and referring to Figure 17, the data processing device 20 for driving style further includes:

[0386] The third processing module 25 is used to establish a style mapping relationship based on the personality characteristics and driving styles of the multiple users. The style mapping relationship includes a target personality characteristic corresponding to each driving style. The target personality characteristic is the personality characteristic that appears most frequently among the users corresponding to the driving style.

[0387] Accordingly, the second acquisition module 21 is specifically used for:

[0388] Based on the style mapping relationship, the target personality traits corresponding to each driving style are retrieved by querying.

[0389] In one possible implementation,

[0390] The third processing module 25 is further configured to determine a style description report corresponding to the current user's target driving style based on the current user's target driving style and the style mapping relationship. The style description report includes at least one of the following: overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving stability, average vehicle speed, relative driving index, and personality traits.

[0391] The sending module 24 is also used to send the current user's style description report to the autonomous mobile device.

[0392] The data processing device for driving style provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be repeated here.

[0393] Figure 18 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Referring to Figure 18, the electronic device 30 may include a processor 31, a memory 32, and a communication interface 34. Exemplarily, the processor 31, the memory 32, and the communication interface 34 are interconnected via a bus 33.

[0394] The memory 32 stores computer-executed instructions;

[0395] The processor 31 executes the computer execution instructions stored in the memory 32, causing the processor 31 to perform the driving style processing method provided in the above method embodiments.

[0396] The electronic device provided in this application embodiment can execute the technical solutions shown in the above embodiments. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0397] This application provides an autonomous mobile device, including the electronic device shown in FIG18, to implement the driving style recognition method in the above embodiments. Its implementation principle and beneficial effects are similar and will not be described again here.

[0398] Figure 19 is a schematic diagram of the server structure provided in an embodiment of this application. Referring to Figure 19, the server 40 may include a processor 41, a memory 42, and a communication interface 44. Exemplarily, the processor 41, the memory 42, and the communication interface 44 are interconnected via a bus 43.

[0399] The memory 42 stores computer-executed instructions;

[0400] The processor 41 executes computer execution instructions stored in the memory 42, causing the processor 41 to perform the data processing method for driving style provided in the above method embodiments.

[0401] The server provided in this application embodiment can execute the technical solutions shown in the above method embodiments. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0402] This application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method described in the above-described method embodiments.

[0403] This application provides a program product, including a computer program, which, when run on a computer, causes the computer to execute the method described in the above-described method embodiments.

[0404] This application provides a computer program that, when executed by a processor, performs the methods described in the above-described method embodiments.

[0405] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0406] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0407] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0408] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0409] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0410] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0411] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0412] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0413] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for recognizing driving style, characterized in that, Applied to autonomous mobile devices, the method includes: Based on the current user's historical driving behavior data, the target driving style of the current user is identified from multiple driving styles, which are obtained based on cluster analysis of the driving behavior data of multiple users; The autonomous mobile device is controlled to drive based on driving environment information, navigation information, and the target driving style acquired during the movement.

2. The method according to claim 1, characterized in that, The process of identifying the current user's target driving style from multiple driving styles based on the current user's historical driving behavior data includes: Based on the historical driving behavior data, determine the historical feature vector; Obtain the driving feature vectors corresponding to the multiple driving styles; Based on the historical feature vector, a matching process is performed on the driving feature vectors corresponding to the multiple driving styles to determine the target driving style.

3. The method according to claim 2, characterized in that, The step of determining the historical feature vector based on the historical driving behavior data includes: Based on preset quantitative indicators and / or preset feature processing models, feature extraction is performed on the historical driving behavior data to obtain the historical feature vector. The preset quantitative index is determined based on the driving behavior of the multiple users in at least one driving scenario, including cutting in, starting and stopping, congestion, following other vehicles, and turning; the preset feature processing model is used to extract features from the users' driving behavior data to obtain feature vectors.

4. The method according to claim 3, characterized in that, The step of extracting features from the historical driving behavior data based on the preset quantitative indicators and / or preset feature processing model to obtain the historical feature vector includes: Based on the preset quantitative indicators, feature extraction is performed on the historical driving behavior data to obtain a first historical feature vector, and the first historical feature vector is determined as the historical feature vector; or, Based on a preset feature processing model, features are extracted from the historical driving behavior data to obtain a second historical feature vector, and the second historical feature vector is determined as the historical feature vector; or, Based on the preset quantitative indicators, features are extracted from the historical driving behavior data to obtain a first historical feature vector. Based on the preset feature processing model, features are extracted from the historical driving behavior data to obtain a second historical feature vector. The first historical feature vector and the second historical feature vector are then concatenated to obtain the historical feature vector.

5. The method according to any one of claims 1-4, characterized in that, The step of controlling the autonomous mobile device to drive based on driving environment information, navigation information, and the target driving style acquired during the movement includes: Configure the target driving style in the intelligent driving model of the autonomous mobile device; The driving environment information and navigation information are processed by an intelligent driving model to obtain a driving decision scheme; The autonomous mobile device is controlled to drive according to the driving decision-making scheme; The driving decision-making scheme includes at least one of the following: planning driving route, handling lane cutting, choosing lane change timing, following distance, turning speed, and time interval between starting and starting with the autonomous mobile device in front.

6. The method according to any one of claims 1-5, characterized in that, The driving environment information includes the motion status information of the autonomous mobile device, the motion status of surrounding traffic participants, and road traffic information; and / or, The navigation information includes map information, location information of autonomous mobile devices, and path trajectory information.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: Receive the multiple driving styles sent by the server; The multiple driving styles are displayed in the visual interface of the autonomous mobile device.

8. The method according to claim 7, characterized in that, The method further includes: Receive style descriptions for each driving style sent by the server; Accordingly, displaying the multiple driving styles in the visual interface of the autonomous mobile device includes: The multiple driving styles and their corresponding style descriptions are displayed in the visual interface of the autonomous mobile device.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: The system receives a style description report of the current user sent by the server; the style description report includes at least one of the following: overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving smoothness, average vehicle speed, relative driving index, and personality traits. In response to the current user's first upload operation, a style description report of the current user is uploaded to a shared cloud platform, which is used for interaction among users of multiple autonomous mobile devices.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: In response to the second upload operation of the current user, the operating information of the target driving style is uploaded to the shared cloud platform. The operating information includes the target driving style and at least one of the following: the mileage, average energy consumption, and operating time of the target driving style.

11. The method according to claim 9 or 10, characterized in that, The method further includes: The autonomous mobile device is controlled to drive based on the new driving style downloaded by the current user from the shared cloud platform, as well as driving environment information and navigation information obtained during the movement.

12. A data processing method for driving style, characterized in that, The method includes: Acquire driving behavior data from multiple users; Cluster analysis was performed on the driving behavior data of the multiple users to obtain at least one cluster. Add corresponding driving styles to each of the at least one cluster to determine multiple driving styles; The multiple driving styles are distributed to at least one autonomous mobile device.

13. The method according to claim 12, characterized in that, The clustering analysis of the driving behavior data of the multiple users yields at least one cluster, including: For each user, a feature vector corresponding to the user is obtained based on the user's driving behavior data, and the feature vector includes at least one piece of data related to driving style; Cluster analysis is performed on the feature vectors of the multiple users to obtain at least one cluster.

14. The method according to any one of claim 12 or 13, characterized in that, Each cluster corresponds to a driving style with a corresponding style description, which is used to interpret the driving style; The delivery of the multiple driving styles to at least one autonomous mobile device includes: The plurality of driving styles and the style description corresponding to each driving style are sent to the at least one autonomous mobile device.

15. The method according to any one of claims 12-14, characterized in that, The method further includes: Acquire the current user's driving behavior data sent by the autonomous mobile device; Based on preset quantitative indicators, the relative driving index of the current user is determined according to the driving behavior data of the multiple users and the driving behavior data of the current user. The relative driving index is used to represent the ranking of the current user among the multiple users. The preset quantitative indicators are determined based on the user's driving behavior in at least one of the following driving scenarios: cutting in, starting and stopping, traffic jams, following other vehicles, and turning.

16. The method according to claim 14, characterized in that, The method further includes: Obtain the target personality traits corresponding to the multiple driving styles; The target personality traits corresponding to each driving style are added to the style description corresponding to that driving style.

17. The method according to claim 16, characterized in that, The method further includes: Based on the personality traits and driving styles of the multiple users, a style mapping relationship is established. The style mapping relationship includes the target personality trait corresponding to each driving style. The target personality trait is the personality trait that appears most frequently among the users corresponding to the driving style. Accordingly, obtaining the target personality traits corresponding to the multiple driving styles includes: Based on the style mapping relationship, the target personality traits corresponding to each driving style are retrieved by querying.

18. The method according to claim 17, characterized in that, The method further includes: Based on the current user's target driving style and the style mapping relationship, a style description report corresponding to the current user's target driving style is determined. The style description report includes at least one of the following: overtaking probability, traffic efficiency, acceleration frequency, lane change frequency, driving stability, average vehicle speed, relative driving index, and personality traits. Send the current user's style description report to the autonomous mobile device.

19. A driving style recognition device, characterized in that, The device includes: The first acquisition module is used to identify the target driving style of the current user from multiple driving styles based on the current user's historical driving behavior data. The multiple driving styles are obtained based on cluster analysis of the driving behavior data of multiple users. The first processing module is used to control the autonomous mobile device to drive based on the driving environment information, navigation information and the target driving style obtained during the movement.

20. A data processing device for driving style, characterized in that, The device includes: The second acquisition module is used to acquire driving behavior data from multiple users; The analysis module is used to perform cluster analysis on the driving behavior data of the multiple users to obtain at least one cluster. The second processing module is used to add corresponding driving style labels to the at least one cluster to determine multiple driving styles. The sending module is used to send the multiple driving styles to at least one autonomous mobile device.

21. An electronic device, characterized in that, include: Processor, memory, and communication interface; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 11.

22. An autonomous mobile device, characterized in that, include: The electronic device as claimed in claim 21.

23. A server, characterized in that, include: Processor, memory, and communication interface; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 12 to 18.

24. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when executed by a processor, are used to implement the method described in any one of claims 1 to 18.

25. A program product, characterized in that, include: A computer program that, when the program product is run on a computer, causes the computer to perform the method described in any one of claims 1 to 18.

26. A computer program, characterized in that, When the computer program is executed by a processor, it is used to perform the method described in any one of claims 1 to 18.

Images