Service mode recommendation method and device for intelligent driving and electronic equipment

Abstract

The invention provides a service mode recommendation method and device for intelligent driving, electronic equipment, a computer readable storage medium and a computer program product. The method comprises: determining a user type of a driver of a target vehicle; obtaining a user state of a driver of the target vehicle in a current driving process and travel information of the target vehicle in the current driving process; performing prediction processing on the user type of the driver of the target vehicle, the user state of the driver of the target vehicle in the current driving process and the travel information of the target vehicle in the current driving process through a service mode prediction model to obtain an optimal service mode of intelligent driving; and applying the optimal service mode in the intelligent driving process of the target vehicle. Through the method and the device, personification requirements of different drivers under different conditions can be met, namely, the intelligent driving effect can be improved.

Description

Technical Field

[0001] The present application relates to vehicle technology, and in particular to a method, device, electronic device, computer-readable storage medium and computer program product for recommending a service mode for intelligent driving. Background Art

[0002] Intelligent driving technology, also known as autonomous driving or unmanned driving technology, is a technology that enables vehicles to drive autonomously. Intelligent driving technology covers multiple technical fields, including computers, modern sensor technology, information fusion, communication technology, artificial intelligence, and automatic control. These technologies together constitute the core of the intelligent driving system, enabling it to perceive and identify the surrounding environment, road conditions, and traffic signs, and make corresponding driving decisions based on them.

[0003] At present, the intelligent driving in the industry has basically been able to provide assisted driving in scenes such as highways, urban areas, and community parking lots, and intelligent driving is gradually moving towards full-scene assistance. The major goal of intelligent driving to provide assistance in various scenes is to implement anthropomorphic behavior. However, in the solutions provided by related technologies, intelligent driving usually uses a fixed service model, which makes it impossible to meet the anthropomorphic needs of different drivers in different situations, that is, the effect of intelligent driving is poor. Summary of the invention

[0004] The present application provides a service mode recommendation method, device, electronic device, computer-readable storage medium and computer program product for intelligent driving, which can meet the anthropomorphic needs of different drivers in different situations, that is, can improve the effect of intelligent driving.

[0005] The technical solution of this application is implemented as follows:

[0006] The present application provides a method for recommending a service mode for intelligent driving, including:

[0007] determining a user type of a driver of a target vehicle;

[0008] Acquire the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process;

[0009] The service mode prediction model is used to predict the user type of the driver of the target vehicle, the user state of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process to obtain the optimal service mode of intelligent driving;

[0010] The optimal service mode is applied during the intelligent driving process of the target vehicle.

[0011] The present application provides a service mode recommendation device for intelligent driving, comprising:

[0012] A user type determination module, used to determine the user type of the driver of the target vehicle;

[0013] A real-time acquisition module, used to acquire the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process;

[0014] A service mode prediction module, used to predict the user type of the driver of the target vehicle, the user state of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process through a service mode prediction model to obtain an optimal service mode for intelligent driving;

[0015] An application module is used to apply the optimal service mode during the intelligent driving process of the target vehicle.

[0016] The present application provides an electronic device, including:

[0017] A memory for storing executable instructions;

[0018] The processor is used to implement the service mode recommendation method for intelligent driving provided in the present application when executing the executable instructions stored in the memory.

[0019] The present application provides a computer-readable storage medium storing executable instructions for causing a processor to execute instructions to implement the service mode recommendation method for intelligent driving provided in the present application.

[0020] The present application provides a computer program product, which includes executable instructions for causing a processor to execute and implement the service mode recommendation method for intelligent driving provided by the present application.

[0021] This application has the following beneficial effects:

[0022] This application determines the user type of the driver of the target vehicle; obtains the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process; predicts and processes the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process through a service mode prediction model to obtain the optimal service mode for intelligent driving; and applies the optimal service mode during the intelligent driving process of the target vehicle. This application comprehensively considers the user type, user status, and travel information to determine the optimal service mode, and applies the optimal service mode during the intelligent driving process of the target vehicle, which can meet the driver's current different expectations for comfort, efficiency, and peace of mind for intelligent driving, that is, it can improve the effect of intelligent driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a schematic diagram of the architecture of the intelligent driving service mode recommendation system provided in an embodiment of the present application;

[0025] Figure 2 is a structural schematic diagram of a vehicle-mounted device provided in an embodiment of the present application;

[0026] Figure 3A This is a first flow chart of the service mode recommendation method for intelligent driving provided in an embodiment of the present application;

[0027] Figure 3B This is a second flow chart of the service mode recommendation method for intelligent driving provided in an embodiment of the present application;

[0028] Figure 4 It is a schematic diagram of the architecture of the service mode prediction model provided in the embodiment of the present application;

[0029] Figure 5 is a schematic diagram of a service mode selection interface provided in an embodiment of the present application;

[0030] Figure 6 It is a schematic diagram of the architecture of the user type prediction model provided in the embodiment of the present application;

[0031] Figure 7 3 is a schematic diagram of a third process of the service mode recommendation method for intelligent driving provided in an embodiment of the present application;

[0032] Figure 8 It is a flow chart of the operation scheme of the intelligent driving service mode recommendation method provided in the embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0034] In the following description, reference is made to "some embodiments", which describes a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. In the following description, reference is made to the term "multiple" to mean at least two.

[0035] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0037] The embodiments of the present application provide a method, device, electronic device, computer-readable storage medium, and computer program product for recommending a service mode for intelligent driving, which can meet the anthropomorphic needs of different drivers in different situations, that is, can improve the effect of intelligent driving. The following describes an exemplary application of the electronic device provided by the embodiments of the present application. The electronic device provided by the embodiments of the present application can be implemented as a vehicle-mounted device or as a server.

[0038] See also Figure 1 , Figure 1 It is an architectural diagram of the intelligent driving service mode recommendation system 100 provided in an embodiment of the present application. The vehicle-mounted device 400 is connected to the server 200 via the network 300, wherein the network 300 can be a wide area network or a local area network, or a combination of the two.

[0039] In some embodiments, taking the electronic device as an on-board device as an example, the service mode recommendation method for intelligent driving provided in the embodiment of the present application can be implemented by the on-board device. For example, the on-board device 400 is locally deployed with a service mode prediction model. The on-board device 400 determines the user type of the driver of the target vehicle (referring to the vehicle where the on-board device 400 is located); obtains the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process; predicts and processes the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process through the service mode prediction model to obtain the optimal service mode for intelligent driving; and applies the optimal service mode during the intelligent driving process of the target vehicle. In the above manner, the on-board device 400 implements the service mode recommendation of the whole process locally, without transmitting the data to the remote server for processing, which can greatly reduce the time and delay of data transmission, thereby improving the real-time processing and improving the response speed; at the same time, it is not limited by network conditions, which is particularly important for scenarios where the network environment is unstable or the network cannot be connected, such as scenarios where the vehicle is traveling in remote mountainous areas without a network.

[0040] In some embodiments, the service mode recommendation method for intelligent driving provided in the embodiments of the present application can be implemented by the vehicle-mounted device and the server in collaboration. For example, the vehicle-mounted device 400 obtains the user status of the driver of the target vehicle during the current driving process and the travel information of the target vehicle during the current driving process, and sends the user status of the driver of the target vehicle during the current driving process and the travel information of the target vehicle during the current driving process to the server 200; the server 200 predicts and processes the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process through the service mode prediction model to obtain the optimal service mode of intelligent driving, wherein the user type of the driver of the target vehicle can be sent to the server 200 by the vehicle-mounted device 400, or can be pre-determined by the server 200 and stored locally in the server 200; the server 200 sends instructions to the vehicle-mounted device 400 according to the optimal service mode, so that the vehicle-mounted device 400 applies the optimal service mode during the intelligent driving process of the target vehicle. In the above method, the server 200 usually has powerful computing power and storage resources, and can quickly calculate the optimal service mode; the vehicle-mounted device 400 is mainly responsible for data collection, data transmission and control, without the need to undertake complex computing tasks or deploy service mode prediction models, which can reduce the local pressure on the vehicle-mounted device 400.

[0041] Take the electronic device provided in the embodiment of the present application as an example, which is a vehicle-mounted device. Figure 2 , Figure 2is a structural diagram of a vehicle-mounted device 400 provided in an embodiment of the present application, Figure 2 The vehicle-mounted device 400 shown includes: at least one processor 410, a memory 450, at least one network interface 420 and a user interface 430. The various components in the vehicle-mounted device 400 are coupled together via a bus system 440. It is understood that the bus system 440 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 440 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 440 is not described in detail. Figure 2 Various buses are labeled as bus system 440 .

[0042] Processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0043] The user interface 430 includes one or more output devices 431 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as microphones, touch screen displays, cameras, other input buttons and controls.

[0044] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices that are physically remote from the processor 410.

[0045] The memory 450 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.

[0046] In some embodiments, memory 450 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

[0047] Operating system 451, including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0048] A network communication module 452, used to reach other electronic devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 include: Bluetooth, Wireless Compatibility Certification (WiFi), and Universal Serial Bus (USB), etc.;

[0049] a presentation module 453 for enabling presentation of information via one or more output devices 431 (e.g., display screen, speaker, etc.) associated with the user interface 430 (e.g., a user interface for operating peripherals and displaying content and information);

[0050] The input processing module 454 is used to detect one or more user inputs or interactions from one of the one or more input devices 432 and translate the detected inputs or interactions.

[0051] In some embodiments, the service mode recommendation device for intelligent driving provided in the embodiments of the present application can be implemented in software. Figure 2 The service mode recommendation device 455 for intelligent driving stored in the memory 450 is shown, which can be software in the form of a program and a plug-in, etc., including the following software modules: a user type determination module 4551, a real-time acquisition module 4552, a service mode prediction module 4553, and an application module 4554. These modules are logical, so they can be arbitrarily combined or further split according to the functions implemented. The functions of each module will be explained below.

[0052] The service mode recommendation method for intelligent driving provided by the embodiment of the present application will be explained in combination with the exemplary application and implementation of the electronic device provided by the embodiment of the present application.

[0053] See also Figure 3A , Figure 3A is a flow chart of a method for recommending a service mode for intelligent driving provided in an embodiment of the present application. The method for recommending a service mode for intelligent driving provided in an embodiment of the present application can be implemented by an electronic device, such as an on-board device or a server. Figure 3A The steps shown are explained.

[0054] In step 101 , the user type of the driver of the target vehicle is determined.

[0055] When recommending a service mode for a target vehicle, it is necessary to determine the user type of the driver of the target vehicle. For example, the driver of the target vehicle may manually set his or her own user type, or the user type of the driver of the target vehicle may be automatically predicted by other means.

[0056] It is worth noting that the user type of the driver of the target vehicle is one of the preset multiple user types. The embodiment of the present application does not limit the preset user type, as shown in Table 1:

[0057] Table 1 User type table

[0058]

[0059] In step 102, the user status of the driver of the target vehicle during the current driving process and the travel information of the target vehicle during the current driving process are obtained.

[0060] Here, the user status of the driver of the target vehicle during the current driving process is obtained, wherein the user status may include at least one of a physiological state and a psychological state. For example, the user status may include fatigue level, concentration level, emotional state, etc. At the same time, the travel information of the target vehicle during the current driving process is obtained, including travel information such as whether navigation is set on the vehicle map, whether the current route is a common commuting route, etc.

[0061] It is worth noting that the user status of the driver of the target vehicle during the current driving process and the travel information of the target vehicle during the current driving process can be obtained through the cockpit system of the target vehicle. For example, the user status of the driver of the target vehicle during the current driving process is obtained through the driver monitoring system (Driver Monitoring System, DMS) or the passenger monitoring system (Occupancy Monitoring System, OMS) in the cockpit system; the travel information of the target vehicle during the current driving process is obtained through the navigation system in the cockpit system.

[0062] In step 103, the service mode prediction model is used to predict the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process to obtain the optimal service mode of intelligent driving.

[0063] Here, the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process are used as inputs of the service mode prediction model, and the service mode output by the service mode prediction model is determined as the optimal service mode. The optimal service mode is the most suitable service mode for the current situation. Among them, the optimal service mode is one of the multiple service modes preset by the intelligent driving function, such as conservative mode, sports mode, etc. The conservative mode usually pays more attention to driving safety and stability, and provides the driver with more detailed interactive information to help the driver drive, while the sports mode usually pays more attention to driving efficiency, and provides the driver with more concise interactive information to avoid disturbing the driver.

[0064] For example, if the user type of the target vehicle's driver is aggressive, the user state of the target vehicle's driver during the current driving process is focused (here the attention level is used as an example), and the travel information of the target vehicle during the current driving process indicates that the current route is a common commuting route, then the sport mode is more likely to be adopted to pursue higher driving efficiency; if the user type of the target vehicle's driver is conservative, the user state of the target vehicle's driver during the current driving process is distracted, and the travel information of the target vehicle during the current driving process indicates that the current route is not a common commuting route, then the conservative mode is more likely to be adopted to ensure safety as much as possible. The service mode prediction model can learn the implicit rules between the user type, user state, travel information and service mode in the above examples, and then output an accurate and appropriate optimal service mode.

[0065] It is worth noting that the service mode prediction model is an artificial neural network model. The embodiment of the present application does not limit the specific architecture of the service mode prediction model. For example, it can be a three-layer artificial neural network model, such as Figure 4 As shown, in Figure 4 In the example, the output of the service mode prediction model includes the probability corresponding to the conservative mode and the probability corresponding to the motion mode, and the service mode corresponding to the largest probability can be determined as the optimal service mode.

[0066] In step 104, the optimal service mode is applied during the intelligent driving process of the target vehicle.

[0067] After the optimal service mode is predicted by the service mode prediction model, the optimal service mode is applied during the intelligent driving process of the target vehicle, thereby realizing intelligent recommendation of service modes, automatically applying the optimal service mode without the driver's awareness, and improving the driver's intelligent driving experience.

[0068] Of course, in some embodiments, the optimal service mode can also be applied during the intelligent driving process of the target vehicle when a confirmation operation for the optimal service mode is received. For example, when the optimal service mode is different from the service mode currently being applied by the target vehicle, the relevant information (such as name, description information) of the optimal service mode can be displayed on the vehicle display screen of the target vehicle, and the two options of "Confirm" and "Reject" can be displayed at the same time. When a trigger operation (such as a click operation) for the "Confirm" option is received, the optimal service mode is applied during the intelligent driving process of the target vehicle. In this way, the applied service mode is changed after the driver confirms, which can avoid causing confusion to the driver.

[0069] In some embodiments, the above-mentioned application of the optimal service mode during the intelligent driving process of the target vehicle can be achieved in the following manner: when the recommendation function of the service mode is turned on, the optimal service mode is applied during the intelligent driving process of the target vehicle; the service mode recommendation method for intelligent driving also includes: when the recommendation function of the service mode is turned off, a preset standard service mode is applied during the intelligent driving process of the target vehicle.

[0070] As an example, the present application embodiment provides the following Figure 5 The service mode selection interface shown in FIG. 1 can be displayed on a vehicle display screen and can support the driver to freely turn on or off the service mode recommendation function. For example, when the service mode recommendation function is turned on (for example, the driver clicks Figure 5 ), execute the above steps 101 to 104, so as to realize the intelligent recommendation of the service mode; when the recommendation function of the service mode is turned off (for example, the driver clicks Figure 5 The "Standard" option in the target vehicle's navigation menu is used to directly apply the preset standard service mode during the intelligent driving process of the target vehicle, wherein one of the multiple service modes can be selected in advance as the standard service mode (the standard service mode can be set when the target vehicle leaves the factory or manually set by the driver of the target vehicle). In this way, the driver can choose whether to use the recommended function of the service mode according to his own needs. For example, if the driver is accustomed to the standard service mode, the recommended function of the service mode can be turned off; if the driver expects the intelligent driving to be more intelligent, the recommended function of the service mode can be turned on.

[0071] In some embodiments, the optimal service mode includes at least one of a driving mode and an interaction mode; the above-mentioned application of the optimal service mode in the intelligent driving process of the target vehicle can be achieved in the following manner: when the optimal service mode includes a driving mode, the target vehicle is driven according to the driving mode in the optimal service mode; when the optimal service mode includes an interaction mode, interaction is performed with the driver of the target vehicle according to the interaction mode in the optimal service mode.

[0072] Here, each service mode of intelligent driving includes at least one of a driving mode (or driving style) and an interaction mode (or interaction style), wherein the driving mode determines the driving strategy used to drive the vehicle, for example, the driving mode includes an aggressive driving mode and a conservative driving mode, the driving strategy used in the aggressive driving mode improves driving efficiency by accelerating, changing lanes, etc., and the driving strategy used in the conservative driving mode improves safety by maintaining a constant speed, driving in a fixed lane, etc.; the interaction mode determines the interaction strategy used to interact with the driver, for example, the interaction mode includes a detailed interaction mode and a simplified interaction mode, the interaction strategy used in the detailed interaction mode is to notify the driver of all kinds of information during driving (such as the target vehicle, the surrounding vehicles of the target vehicle, traffic lights, etc.), and the interaction strategy used in the simplified interaction mode only notifies the driver of key information during driving (such as lane departure warning, blind spot monitoring, etc. that affect safety) or does not remind the driver. Of course, the above classification is only an example and does not constitute a limitation on the embodiments of the present application. For example, the interaction mode can also be distinguished by the mode used during interaction (such as voice reminder, screen reminder, etc.).

[0073] Based on this, when the optimal service mode includes a driving mode, the target vehicle is driven according to the driving mode in the optimal service mode; when the optimal service mode includes an interactive mode, the driver of the target vehicle is interacted with according to the interactive mode in the optimal service mode. In the above manner, by applying the driving mode in the optimal service mode, the driving experience can be optimized so that the driver can obtain a more comfortable and expected driving experience; by applying the interactive mode in the optimal service mode, the driver can be provided with the desired reminder, helping the driver to discover potential dangers in time and take corresponding measures, thereby improving driving safety and avoiding disturbing the driver.

[0074] In some embodiments, the above steps 101 to 104 may be performed periodically to ensure that the optimal service mode applied is in line with the current situation.

[0075] like Figure 3AAs shown, the embodiment of the present application determines the user type of the driver of the target vehicle; obtains the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process; predicts and processes the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process through the service mode prediction model to obtain the optimal service mode for intelligent driving; and applies the optimal service mode during the intelligent driving process of the target vehicle. The embodiment of the present application comprehensively considers the user type, user status, and travel information to determine the optimal service mode, and applies the optimal service mode during the intelligent driving process of the target vehicle, which can meet the driver's current different expectations for comfort, efficiency, and peace of mind for intelligent driving, that is, it can improve the effect of intelligent driving.

[0076] In some embodiments, see Figure 3B , Figure 3B is a flow chart of a method for recommending a service mode for intelligent driving provided in an embodiment of the present application. Figure 3A The illustrated step 101 can be implemented through steps 201 to 204 , which will be described in conjunction with each step.

[0077] In step 201, driving characteristic information of a driver of a target vehicle for intelligent driving is obtained.

[0078] Here, the user type of the driver of the target vehicle may be determined by means of model prediction, which will be described in detail below.

[0079] On the one hand, the driving characteristic information of the driver of the target vehicle for intelligent driving is obtained. The driving characteristic information can be configured by the driver himself, which can reflect the driver's own use of intelligent driving to a certain extent and help to accurately predict the user type.

[0080] The driving characteristic information may include at least one of the driver's driving skills, the driver's familiarity with intelligent driving, and the driver's driving style preference. The embodiment of the present application does not limit the method of obtaining the driving characteristic information. For example, the questionnaire may be displayed in the vehicle machine APP of the target vehicle or the APP of the terminal device (such as a mobile phone) used by the driver of the target vehicle, so as to obtain the driving characteristic information manually filled in by the driver in the questionnaire.

[0081] In step 202, cockpit information of the historical driving process is obtained through the cockpit system of the target vehicle.

[0082] Here, the cockpit information of the historical driving process is obtained through the cockpit system of the target vehicle, wherein the historical driving process refers to the driving process before the current driving process. It is worth noting that the cockpit information here reflects the cockpit condition, and the cockpit condition will largely affect the user type of the driver. For example, if the historical routes of the target vehicle are mostly common commuting routes, the user type tends to be aggressive.

[0083] In some embodiments, the cockpit information of the historical driving process includes at least one of the following: the user status of the driver of the target vehicle during the historical driving process, the trip information of the target vehicle during the historical driving process, the driving environment information of the target vehicle during the historical driving process, and the intelligent driving usage information of the target vehicle during the historical driving process. Among them, the driving environment information includes at least one of the time and weather conditions, and the intelligent driving usage information is used to characterize whether the intelligent driving function is turned on. Through the above-mentioned cockpit information, the cockpit condition of the target vehicle during the historical driving process can be accurately and comprehensively reflected, which helps to accurately predict the user type based on the cockpit condition.

[0084] In step 203, the interactive behavior of the driver of the target vehicle during the historical driving process is obtained.

[0085] Here, the interactive behaviors of the driver of the target vehicle in the historical driving process are obtained. The interactive behaviors generally refer to the operations performed by the driver, and the operations performed by the driver are largely related to his user type.

[0086] In some embodiments, the interactive behavior includes at least one of the following: driving behavior; selection behavior for a service mode. The driving behavior here refers to the driving behavior performed by the driver when taking over the target vehicle, such as sudden acceleration, sudden braking, etc. The driving behavior can be used to determine the user type. For example, a driver who often performs driving behaviors such as sudden acceleration and sudden braking is more likely to be an aggressive type; the selection behavior for a service mode refers to the driver's manual selection of the service mode to be applied to the target vehicle. The selection behavior can be used to determine the user type. For example, a driver who often selects the sports mode is more likely to be an aggressive type.

[0087] In step 204, the driving characteristic information of the driver of the target vehicle, the cockpit information of the historical driving process, and the interactive behavior of the driver of the target vehicle in the historical driving process are predicted and processed by the user type prediction model to obtain the user type of the driver of the target vehicle.

[0088] Here, the driving characteristic information of the driver of the target vehicle, the cockpit information of the historical driving process, and the interactive behavior of the driver of the target vehicle in the historical driving process are used as inputs of the user type prediction model, and the user type output by the user type prediction model is determined as the user type of the driver of the target vehicle.

[0089] It is worth noting that the user type prediction model is an artificial neural network model. The embodiment of the present application does not limit the specific architecture of the user type prediction model. For example, it can be a three-layer artificial neural network model, such as Figure 6 As shown, in Figure 6 In the example, the output of the user type prediction model includes the probability corresponding to the conservative type and the probability corresponding to the aggressive type, and the user type corresponding to the largest probability can be determined as the user type of the driver of the target vehicle.

[0090] It is worth noting that, when the driver of the target vehicle does not change, the user type of the driver of the target vehicle obtained through step 204 can be continuously used when predicting the service mode, thereby saving costs. The reason is that the user type of a certain user usually does not change much over time; alternatively, steps 201 to 204 can be performed periodically to ensure the accuracy of the user type of the driver of the target vehicle.

[0091] In some embodiments, before predicting and processing the driving characteristic information of the driver of the target vehicle, the cockpit information of the historical driving process, and the interactive behavior of the driver of the target vehicle in the historical driving process through the user type prediction model, the intelligent driving service mode recommendation method also includes: training the user type prediction model according to a first training data set; wherein the first training data set includes the driving characteristic information of the driver of the sample vehicle, the cockpit information acquired through the cockpit system of the sample vehicle during the sample driving process, the interactive behavior of the driver of the sample vehicle during the sample driving process, and the labeled user type of the driver of the sample vehicle; wherein the trained user type prediction model is used to predict and process the driving characteristic information of the driver of the target vehicle, the cockpit information of the historical driving process, and the interactive behavior of the driver of the target vehicle in the historical driving process.

[0092] Before the model inference phase of the user type prediction model, the user type prediction model may be trained in a model training phase.

[0093] The first training data set required for the model inference stage includes the driving characteristic information of the driver of the sample vehicle, the cockpit information obtained by the cockpit system of the sample vehicle during the sample driving process, the interactive behavior of the driver of the sample vehicle during the sample driving process, and the labeled user type of the driver of the sample vehicle, wherein the sample vehicle and the target vehicle can be the same vehicle or different vehicles, and the labeled user type can be the user type manually labeled for the driver of the sample vehicle, so as to ensure its accuracy. In the model inference stage, the driving characteristic information of the driver of the sample vehicle, the cockpit information obtained by the cockpit system of the sample vehicle during the sample driving process, and the interactive behavior of the driver of the sample vehicle during the sample driving process are predicted and processed by the user type prediction model to obtain the user type to be compared of the driver of the sample vehicle, and then, the loss value is calculated according to the labeled user type of the driver of the sample vehicle and the user type to be compared, and the loss value is back-propagated in the user type prediction model to update the model parameters of the user type prediction model in the back-propagation process, thereby realizing the training of the user type prediction model.

[0094] After the model training phase is completed, the model inference phase can be entered, that is, the trained user type prediction model is used to predict the target vehicle's driver's driving characteristic information, cockpit information during historical driving, and the target vehicle's driver's interactive behavior during historical driving to obtain the target vehicle's driver's user type. In the above manner, the user type prediction model can effectively learn the implicit rules between driving characteristic information, cockpit information, interactive behavior, and user type during the model training phase, so that the user type of the target vehicle's driver can be more accurately predicted during the model inference phase.

[0095] It is worth noting that the above training method for the user type prediction model is also applicable to the service mode prediction model. The second training data set of the service mode prediction model may include the user type of the driver of the sample vehicle, the user status of the driver of the sample vehicle during the sample driving process, the travel information of the sample vehicle during the sample driving process, and the labeled service mode of the sample vehicle during the sample driving process. The labeled service mode may be a manually labeled service mode that is most suitable for the sample driving process, thereby ensuring its accuracy. After the service mode prediction model is trained according to the second training data set, the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process are predicted and processed by the trained service mode prediction model to obtain the optimal service mode for intelligent driving.

[0096] In some embodiments, before training the user type prediction model based on the first training data set, the service mode recommendation method for intelligent driving also includes: performing at least one of the following processing: data cleaning of the first training data set; normalization of the first training data set; feature abstraction of the first training data set.

[0097] Before training the user type prediction model according to the first training data set of the user type prediction model, the first training data set may be preprocessed. The preprocessing may include at least one of the following methods:

[0098] 1) Perform data cleaning on the first training data set. Data cleaning may include at least one of filling missing values, removing outliers (noise values), and deduplication. For example, missing values ​​may be predicted by linear regression and filled by the mean; outliers may be removed by the interquartile range (IQR); and deduplication may be quickly and accurately achieved using a hash table. Data cleaning can significantly improve the quality of the first training data set, which helps the user type prediction model to more accurately and reliably learn the data patterns implicit in the first training data set during the model training phase.

[0099] 2) Normalize the first training data set. For example, the data of different dimensions in the first training data set can be standardized by the minimum-maximum standardization (Min-Max standardization) method to make it suitable for modeling. Through normalization, the dimensional differences between different data in the first training data set can be eliminated, so that different data are in the same numerical range, which helps to speed up the model convergence speed and significantly improve the model training efficiency; at the same time, it is convenient to compare and analyze the importance of different data, and improve the performance and interpretability of the user type prediction model.

[0100] 3) Perform feature abstraction processing on the first training data set. For example, the feature distribution defined in the first training data set is grouped by a Gaussian mixture model (GMM), thereby realizing feature abstraction processing. Feature abstraction processing can improve the data representation capability of the first training data set, and enable the user type prediction model to learn more representative features during the training process, which helps the user type prediction model to better generalize when facing new samples. In addition, it can also reduce the sensitivity of the user type prediction model to noise data, thereby improving the robustness of the user type prediction model.

[0101] It is worth noting that the above preprocessing method for the first training data set is also applicable to the second training data set.

[0102] like Figure 3BAs shown, the embodiment of the present application obtains the target vehicle's driver's driving characteristic information for intelligent driving; obtains the target vehicle's cockpit information of the historical driving process through the cockpit system; obtains the target vehicle's driver's interactive behavior during the historical driving process; and predicts the target vehicle's driver's driving characteristic information, cockpit information of the historical driving process, and the target vehicle's driver's interactive behavior during the historical driving process through the user type prediction model to obtain the target vehicle's driver's user type. In this way, the user type of the target vehicle's driver is accurately predicted by model prediction, avoiding the problem that the user type manually set by the driver may be inaccurate, which helps to more accurately predict the optimal service mode.

[0103] See also Figure 7 , Figure 7 This is a flow chart of a method for recommending a service mode for intelligent driving provided in an embodiment of the present application. Figure 7 The steps shown are explained.

[0104] Step S1: data collection.

[0105] Step S1 includes step S1-1, step S1-2 and step S1-3. Among them, step S1-1 is the collection of APP questionnaire information (corresponding to the driving characteristic information above). For example, a user car purchase survey can be conducted in step S1-1-1, a smart driving experience survey can be conducted in step S1-1-2, and other types of surveys can be conducted in step S1-1-3. The information obtained through these surveys is collectively referred to as APP questionnaire information; step S1-2 is the collection of cockpit information. For example, the user status of the driver can be obtained through OMS or DMS in step S1-2-1, the driving environment information can be obtained in step S1-2-2, the trip information can be obtained in step S1-2-3, and other cockpit information can be obtained in step S1-2-4; step S1-3 is the collection of interactive behaviors. For example, the driver's selection behavior for the service mode can be obtained in step S1-3-1, and the driving behavior of the driver taking over the vehicle can be obtained in step S1-3-2.

[0106] Step S2: data processing (or data preprocessing).

[0107] Step S2 includes step S2-1, step S2-2 and step S2-3, wherein step S2-1 is data cleaning, step S2-2 is data standardization (ie, normalization processing), and step S2-3 is feature abstraction.

[0108] Step S3: construct user portrait.

[0109] For example, after the data processing in step S2, a user type prediction model is trained according to the obtained training data set, and the user type (ie, user portrait) of the driver of the vehicle is predicted by the trained user type prediction model.

[0110] Step S4: Service mode prediction model.

[0111] After obtaining the user type of the driver of the vehicle, the user type of the driver of the vehicle can be used as the input of the service mode prediction model, so that the service mode prediction model can make real-time recommendations in step S4-1, that is, predict the optimal service mode, and apply the optimal service mode during the intelligent driving process of the vehicle. If a problem occurs during the application of the optimal service mode (for example, the vehicle cannot be driven to the destination according to the optimal service mode), it can be fed back to the driver in step S4-2 to remind the driver to make adaptive adjustments in step S4-3, such as manually taking over the vehicle by the driver; or, adaptive adjustments can be made directly in step S4-3, such as automatically changing the applied service mode from the optimal service mode to the standard service mode.

[0112] like Figure 7 As shown, the embodiments of the present application intelligently provide the most suitable driving style and interaction style for the driver when the driver uses the intelligent driving function, solving the different expectations of the driver for comfort, efficiency, and security of intelligent driving under multiple variable factors such as different driving tasks, different familiarity with intelligent driving, and different mood states.

[0113] See also Figure 8 , Figure 8 This is a flow chart of the operation scheme of the intelligent driving service mode recommendation method provided in the embodiment of the present application, which will be combined with Figure 8 The steps shown are explained.

[0114] Step S5: The new car rolls off the assembly line.

[0115] Here, the new car off-line means that the vehicle has been completed and can be delivered to the user. In the process of the new car off-line, the service mode applied by the intelligent driving can be configured as the standard service mode by default in step S5-1.

[0116] Step S6: The user activates the recommendation function of the service mode.

[0117] For example, if the user is not satisfied with the standard service mode, the user can start the recommended function of the service mode through the vehicle computer, thereby triggering the vehicle background unlocking switch to be enabled in step S6-1. The switch here refers to the switch of the recommended function of the service mode.

[0118] Step S7: The recommendation function of the service mode is run.

[0119] Here, the service mode recommendation function is automatically executed, thereby recommending the optimal service mode in real time in step S7-1.

[0120] The following is a description of an exemplary structure of the intelligent driving service mode recommendation device 455 provided in the embodiment of the present application implemented as a software module. In some embodiments, Figure 2 As shown, the software modules in the service mode recommendation device 455 for intelligent driving stored in the memory 450 may include: a user type determination module 4551, used to determine the user type of the driver of the target vehicle; a real-time acquisition module 4552, used to obtain the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process; a service mode prediction module 4553, used to predict the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process through a service mode prediction model to obtain the optimal service mode for intelligent driving; an application module 4554, used to apply the optimal service mode in the intelligent driving process of the target vehicle.

[0121] In some embodiments, the user type determination module 4551 is also used to: obtain the driving characteristic information of the driver of the target vehicle for intelligent driving; obtain the cockpit information of the historical driving process through the cockpit system of the target vehicle; obtain the interactive behavior of the driver of the target vehicle in the historical driving process; predict and process the driving characteristic information of the driver of the target vehicle, the cockpit information of the historical driving process, and the interactive behavior of the driver of the target vehicle in the historical driving process through the user type prediction model to obtain the user type of the driver of the target vehicle.

[0122] In some embodiments, the service mode recommendation device 455 for intelligent driving also includes a first training module, which is used to: train a user type prediction model based on a first training data set; wherein the first training data set includes driving characteristic information of the driver of the sample vehicle, cockpit information acquired through the cockpit system of the sample vehicle during the sample driving process, the interactive behavior of the driver of the sample vehicle during the sample driving process, and the labeled user type of the driver of the sample vehicle; wherein the trained user type prediction model is used to predict and process the driving characteristic information of the driver of the target vehicle, the cockpit information of the historical driving process, and the interactive behavior of the driver of the target vehicle during the historical driving process.

[0123] In some embodiments, the service mode recommendation device 455 for intelligent driving also includes a preprocessing module for performing at least one of the following processing: data cleaning of the first training data set; normalization of the first training data set; and feature abstraction of the first training data set.

[0124] In some embodiments, the service mode recommendation device 455 for intelligent driving also includes a second training module, which is used to: train the service mode prediction model according to a second training data set; wherein the second training data set includes the user type of the driver of the sample vehicle, the user status of the driver of the sample vehicle during the sample driving process, the travel information of the sample vehicle during the sample driving process, and the labeled service mode of the sample vehicle during the sample driving process; wherein the trained service mode prediction model is used to predict the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process.

[0125] In some embodiments, the application module 4554 is also used to: when the recommendation function of the service mode is turned on, apply the optimal service mode during the intelligent driving process of the target vehicle; the intelligent driving service mode recommendation device 455 also includes a default module, which is used to: when the recommendation function of the service mode is turned off, apply the preset standard service mode during the intelligent driving process of the target vehicle.

[0126] In some embodiments, the optimal service mode includes at least one of a driving mode and an interaction mode; the application module 4554 is also used to: when the optimal service mode includes a driving mode, drive the target vehicle according to the driving mode in the optimal service mode; when the optimal service mode includes an interaction mode, interact with the driver of the target vehicle according to the interaction mode in the optimal service mode.

[0127] The embodiment of the present application provides a computer program product or a computer program, which includes executable instructions, and the executable instructions are stored in a computer-readable storage medium. The processor of the electronic device reads the executable instructions from the computer-readable storage medium, and the processor executes the executable instructions, so that the electronic device implements the service mode recommendation method for intelligent driving described in the embodiment of the present application.

[0128] An embodiment of the present application provides a computer-readable storage medium storing executable instructions, wherein executable instructions are stored. When the executable instructions are executed by a processor, the processor will implement the service mode recommendation method for intelligent driving provided in the embodiment of the present application.

[0129] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.

[0130] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0131] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0132] As an example, the executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0133] The above are only embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A method for recommending a service mode for intelligent driving, characterized in that: include: determining a user type of a driver of a target vehicle; Acquire the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process; The service mode prediction model is used to predict the user type of the driver of the target vehicle, the user state of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process to obtain the optimal service mode of intelligent driving; The optimal service mode is applied during the intelligent driving process of the target vehicle.

2. The method according to claim 1, characterized in that Determining the user type of the driver of the target vehicle includes: Acquiring driving characteristic information of the driver of the target vehicle for intelligent driving; Acquiring cockpit information of the historical driving process through the cockpit system of the target vehicle; Obtaining the interactive behavior of the driver of the target vehicle during the historical driving process; The user type prediction model is used to predict the driving characteristic information of the driver of the target vehicle, the cockpit information of the historical driving process, and the interactive behavior of the driver of the target vehicle in the historical driving process to obtain the user type of the driver of the target vehicle.

3. The method according to claim 2, characterized in that Before predicting the driving characteristic information of the driver of the target vehicle, the cockpit information of the historical driving process, and the interactive behavior of the driver of the target vehicle in the historical driving process by the user type prediction model, the method further includes: The user type prediction model is trained according to a first training data set; wherein the first training data set includes driving characteristic information of a driver of a sample vehicle, cockpit information acquired by a cockpit system of the sample vehicle during a sample driving process, interactive behavior of the driver of the sample vehicle during the sample driving process, and a labeled user type of the driver of the sample vehicle; The trained user type prediction model is used to predict the driving characteristic information of the driver of the target vehicle, the cockpit information of the historical driving process, and the interactive behavior of the driver of the target vehicle in the historical driving process.

4. The method according to claim 3, characterized in that Before training the user type prediction model according to the first training data set, the method further includes: Perform at least one of the following actions: Performing data cleaning on the first training data set; Normalizing the first training data set; Perform feature abstraction processing on the first training data set.

5. The method according to claim 1, characterized in that Before predicting the user type of the driver of the target vehicle, the user status of the driver of the target vehicle during the current driving process, and the trip information of the target vehicle during the current driving process by the service mode prediction model, the method further includes: The service mode prediction model is trained according to a second training data set; wherein the second training data set includes the user type of the driver of the sample vehicle, the user state of the driver of the sample vehicle during the sample driving process, the trip information of the sample vehicle during the sample driving process, and the labeled service mode of the sample vehicle during the sample driving process; Among them, the trained service mode prediction model is used to predict the user type of the driver of the target vehicle, the user status of the driver of the target vehicle in the current driving process, and the travel information of the target vehicle in the current driving process.

6. The method according to claim 1, characterized in that The applying the optimal service mode during the intelligent driving process of the target vehicle includes: When the recommendation function of the service mode is turned on, applying the optimal service mode during the intelligent driving process of the target vehicle; The method further comprises: When the recommendation function of the service mode is turned off, a preset standard service mode is applied during the intelligent driving process of the target vehicle.

7. The method according to claim 1, characterized in that The optimal service mode includes at least one of a driving mode and an interaction mode; and applying the optimal service mode during the intelligent driving process of the target vehicle includes: When the optimal service mode includes a driving mode, driving the target vehicle according to the driving mode in the optimal service mode; When the optimal service mode includes an interaction mode, interaction is performed with the driver of the target vehicle according to the interaction mode in the optimal service mode.

8. A service mode recommendation device for intelligent driving, characterized in that: include: A user type determination module, used to determine the user type of the driver of the target vehicle; A real-time acquisition module, used to acquire the user status of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process; A service mode prediction module, used to predict the user type of the driver of the target vehicle, the user state of the driver of the target vehicle during the current driving process, and the travel information of the target vehicle during the current driving process through a service mode prediction model to obtain an optimal service mode for intelligent driving; An application module is used to apply the optimal service mode during the intelligent driving process of the target vehicle.

9. An electronic device, characterized in that: include: A memory for storing executable instructions; A processor, configured to implement the method according to any one of claims 1 to 7 when executing the executable instructions stored in the memory.

10. A computer-readable storage medium, characterized in that: Executable instructions are stored, and when executed by a processor, the method described in any one of claims 1 to 7 is implemented.

Images