Vehicle control parameter configuration method and system

Abstract

The present invention discloses a method and system for configuring vehicle control parameters. The method includes: a cloud-based system inputs training data sets for various driving scenarios into a deep learning model corresponding to the driving scenario to classify and learn driving habits, outputs control parameters corresponding to different driving habits in the corresponding driving scenario, and stores them in a model database; a cloud-based system determines the control parameters for each driver in each scenario based on their actuator data and the model database, establishes a control parameter library for each driver based on the determined information, and transmits it to the corresponding vehicle-side system; the vehicle-side system queries whether a local target control parameter library for the current driver exists based on the current driver's identity information; if so, queries the target control parameter library for the corresponding target control parameter based on the current driving scenario and executes the corresponding target control parameter. This method can largely solve the problem that planning and control in different scenarios cannot adapt to the driving habits of different drivers.

Description

Technical Field

[0001] The present invention relates to the automotive field, and in particular to a vehicle control parameter configuration method and system. Background Art

[0002] With the development of the automotive industry, cars have become an indispensable means of transportation. Among them, assisted driving features enhance the driver's driving efficiency and reliability. Currently, L2 and L2+ ADAS assisted driving technologies are relatively mature, with a vehicle penetration rate of 25%. A typical function of L2+ ADAS assisted driving is NGP (Navigate Assist).

[0003] The existing NGP function uses a fixed set of strategies and cannot adjust to the driving habits of different drivers. For example, different people have different starting acceleration processes, different braking processes, and different driving speeds on open roads. The planning and control of NGP in different scenarios cannot adapt to the driving habits of different drivers, which in turn causes drivers to dislike the function. Summary of the Invention

[0004] In view of the above situation, it is necessary to provide a vehicle control parameter configuration method and system to address the problem that the planning and control of NGP in different scenarios in the existing technology cannot adapt to the driving habits of different drivers.

[0005] The present invention discloses a vehicle control parameter configuration method, comprising:

[0006] Acquiring, through the cloud, a training data set under a plurality of different driving scenarios, wherein the training data set includes actuator data of a plurality of drivers during a vehicle driving process;

[0007] The cloud inputs the training data sets for each driving scenario into the deep learning model of the corresponding driving scenario to classify and learn driving habits, and outputs the control parameters corresponding to different driving habits in the corresponding driving scenario;

[0008] The cloud stores each driving habit and corresponding control parameters in each driving scenario in a model database;

[0009] The cloud determines the control parameters of each driver in each scenario based on the actuator data of each driver and the model database, and establishes a control parameter library for each driver based on the determined information;

[0010] The cloud sends the control parameter library of each driver to the corresponding driver's vehicle for storage;

[0011] The vehicle side collects vehicle data, which includes the identity information of the current driver and the current driving scene;

[0012] The vehicle end queries whether a target regulation and control parameter library of the current driver is stored locally according to the identity information of the current driver;

[0013] If so, the vehicle side queries the target control parameter library for the corresponding target control parameter according to the current driving scenario, and performs the control operation according to the target control parameter.

[0014] Furthermore, the above vehicle control parameter configuration method, wherein, after the step of the vehicle end querying whether a target control parameter library of the current driver is stored locally based on the identity information of the current driver, further comprises:

[0015] When the target control parameter library of the current driver does not exist locally, the vehicle side uses the system default control parameters.

[0016] Furthermore, in the above-mentioned vehicle control parameter configuration method, wherein the vehicle data also includes current actuator data, after the step of the vehicle end querying whether a target control parameter library of the current driver is stored locally based on the identity information of the current driver, the method further includes:

[0017] When the target control parameter library of the current driver does not exist locally, the vehicle terminal sends the vehicle data to the cloud;

[0018] When the cloud obtains the vehicle data preset by the current driver

[0019] The cloud matches the regulation and control parameters of the current driver in various scenarios from the model database according to the vehicle data, and establishes a regulation and control parameter library of the current driver.

[0020] Furthermore, in the above-mentioned vehicle control parameter configuration method, the step of determining the control parameters for each driver in each scenario based on the actuator data of each driver and the model database on the cloud includes:

[0021] The cloud inputs the actuator data of each driver in each driving scenario into the deep learning model of the corresponding scenario to classify the driving habits, and outputs the driving habit type of each driver in each driving scenario;

[0022] The cloud searches the model database for corresponding regulatory parameters based on the driver's driving habits in various scenarios.

[0023] Furthermore, in the above-mentioned vehicle control parameter configuration method, before the step of establishing the control parameter library of each driver according to the determined information in the cloud, the method further includes:

[0024] The cloud obtains the identity information of each of the drivers;

[0025] The step of establishing a control parameter library for each driver according to the determined information in the cloud includes:

[0026] The cloud establishes a control parameter library for each driver based on the determined information and the identity information of each driver, wherein the established control parameter library is indexed by the driver's identity information.

[0027] The present invention also discloses a vehicle control parameter configuration system, including a cloud side and a vehicle side, wherein the cloud side includes:

[0028] A first acquisition module is configured to acquire a training data set under a plurality of different driving scenarios, wherein the training data set includes actuator data of a plurality of drivers during a vehicle driving process;

[0029] The model classification module is used to input the training data sets under various driving scenarios into the deep learning model of the corresponding driving scenario to classify and learn driving habits, and output the corresponding control parameters for different driving habits in the corresponding driving scenario;

[0030] A first storage module is used to store various driving habits and corresponding control parameters in various driving scenarios in a model database;

[0031] a first establishing module, configured to determine, based on the actuator data of each driver and the model database, a regulation and control parameter for each driver in each scenario, and to establish a regulation and control parameter library for each driver based on the determined information;

[0032] The sending module is used to send the control parameter library of each driver to the corresponding driver's vehicle for storage;

[0033] The vehicle end includes:

[0034] The second acquisition module is used to acquire vehicle data sent by the current vehicle end, wherein the vehicle data includes the identity information of the current driver and the current driving scene;

[0035] A query module, configured to query whether a target regulation and control parameter library of the current driver is stored locally according to the identity information of the current driver;

[0036] The first execution module is configured to query the target regulation and control parameter library for corresponding target regulation and control parameters according to the current driving scenario, and execute regulation and control operations according to the target regulation and control parameters.

[0037] Furthermore, the vehicle control parameter configuration system mentioned above, the vehicle side also includes:

[0038] The second execution module is configured to execute the default control parameters of the vehicle-side system when the target control parameter library of the current driver does not exist locally.

[0039] Furthermore, in the above-mentioned vehicle control parameter configuration system, the vehicle data also includes current actuator data, and the cloud also includes:

[0040] A third acquisition module is configured to acquire a preset amount of vehicle data of the current driver when the target regulation parameter library of the current driver does not exist locally;

[0041] The second establishing module is used to match the regulation and control parameters of the current driver in various scenarios from the model database according to the vehicle data, and establish a regulation and control parameter library of the current driver.

[0042] Furthermore, the above-mentioned vehicle control parameter configuration system, the cloud also includes:

[0043] A fourth acquisition module, configured to acquire identity information of each driver;

[0044] The step of establishing a control parameter library for each driver according to the determined information includes:

[0045] A control parameter library for each driver is established based on the determined information and the identity information of each driver, wherein the established control parameter library is indexed by the driver's identity information.

[0046] In the present invention, the cloud collects different actuator data of multiple drivers in different driving scenarios. After obtaining a large amount of actuator data for different scenarios, the driving habits are classified and learned through a deep learning model to obtain the control parameters corresponding to different driving habits in different driving scenarios, and a control parameter library is established for each driver and sent to the corresponding vehicle end. When the vehicle end uses the NGP function, the vehicle end obtains the identity information of the current driver and the current driving scenario, and queries whether there is a target control parameter library for the current driver locally based on the identity information of the current driver. If so, the corresponding target control parameters in the target control parameter library are queried based on the current driving scenario, and the operation is completed based on the target control parameters. This method can solve the problem that the planning and control of NGP in different scenarios cannot fit the driving habits of different drivers to the greatest extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flow chart of a method for configuring vehicle control parameters in an embodiment of the present invention;

[0048] Figure 2 This is a line graph showing the changes in different speeds during the braking process in an embodiment of the present invention;

[0049] Figure 3 This is a structural block diagram of a vehicle control parameter configuration system in an embodiment of the invention. DETAILED DESCRIPTION

[0050] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0051] These and other aspects of the embodiments of the present invention will become apparent with reference to the following description and accompanying drawings. While some specific implementations of the embodiments of the present invention are disclosed in detail in these descriptions and accompanying drawings to illustrate some ways of implementing the principles of the embodiments of the present invention, it should be understood that the scope of the embodiments of the present invention is not limited thereby. On the contrary, the embodiments of the present invention encompass all variations, modifications, and equivalents that fall within the spirit and scope of the appended claims.

[0052] See also Figure 1 , which is a vehicle control parameter configuration method in an embodiment of the present invention, includes steps S11 to S18.

[0053] In step S11 , the cloud obtains a plurality of training data sets under different driving scenarios, wherein the training data sets include actuator data of a plurality of drivers during vehicle driving.

[0054] The multiple driving scenarios are defined based on the surrounding environment and vehicle status during driving. For example, scenario 1 is the acceleration process when starting with no preceding vehicle; scenario 2 is the braking process when no preceding vehicle is in sight; scenario 3 is the following vehicle process, etc. The actuator data is the operating data of the actuator collected during driving, such as vehicle speed, acceleration, and vehicle distance.

[0055] This training dataset can be implemented by collecting actuator data from the vehicle with the user's consent. Specifically, the vehicle uses a personal identifier to identify the user online and obtain the driver's identity information. Actuator data from different driving scenarios is collected during driving, processed, filtered, and sent to a cloud-based database for storage. The cloud-based database stores the actuator data, driving scenarios, and driver identity information in a corresponding manner. For example, Table 1 shows the contents of the cloud-based database, which records multiple pieces of actuator data over time for different scenarios.

[0056]

[0057]

[0058] In step S12, the cloud inputs the training data sets under each driving scenario into the deep learning model of the corresponding driving scenario to classify and learn driving habits, and outputs the control parameters corresponding to different driving habits under the corresponding driving scenario.

[0059] For example, different deep learning models can be used for different driving scenarios to classify and learn driving habits. Driving habits are defined based on the user's driving behavior in a specific driving scenario. For example, when braking with no vehicle ahead, a user's driving habits can be categorized into four types: extremely fast, extremely slow, fast first then slow, and moderate.

[0060] Figure 2 This graph shows the speed variations during the braking process, explaining the different braking habits of different drivers. Series 1 represents extremely fast braking, corresponding to deceleration to a stop; Series 2 shows a fast-then-slow braking process, where the user applies the brakes hard initially, then gradually reduces the pressure to a stop; and Series 3 represents an extremely slow braking process, where the user applies the brakes gently throughout the process. While each person's braking process is unique, filtering multiple data sets can be used to identify the general trends in individual braking speed variations, allowing for the training of corresponding control parameters.

[0061] Furthermore, in practical applications, the trained control parameters need to be subjected to simulation experiments and field tests to verify their safety. For example, in one implementation of the present invention, the control parameter generation process for different scenarios is as follows:

[0062] (1) The cloud mines and analyzes all actuator data for different scenarios one by one, fits and classifies actuator data for a certain type (e.g., 100 types) of driving habits, and learns and trains the corresponding NGP control parameters. The upper and lower limits of the factory control parameters are used to filter out the control parameters that meet the requirements.

[0063] (2) Car manufacturers use simulation software to simulate various scenarios and conduct extensive tests on the selected NGP regulatory parameters to determine their safety;

[0064] (3) After a large number of simulations, the car manufacturer sets up various scenarios and lets testers get on the car to test the corresponding various regulatory parameters in turn. If the test is qualified, it will be put into use.

[0065] In this embodiment, a database can be established in the cloud to store user identities and actuator data for different driving scenarios. With the user's consent, the vehicle uses a personal identifier to identify the user online and collects actuator data from different driving scenarios. After processing and filtering, the data is stored in the cloud database. This large amount of actuator data from different scenarios is analyzed and mined, classified to a certain extent, and trained to obtain corresponding regulatory parameters. The manufacturer conducts extensive simulation and real-vehicle testing on each of the different regulatory parameters for the same scenario. Once the safety issues are confirmed, the adaptive navigation function is enabled.

[0066] In step S13, the cloud stores each driving habit and corresponding regulation parameters in each driving scenario in a model database.

[0067] In step S14, the cloud determines the control parameters corresponding to the different driving habits of each driver in each scenario based on the actuator data of each driver and the model database, and establishes a control parameter library for each driver based on the determined information.

[0068] In step S15, the cloud sends the control parameter library of each driver to the corresponding driver's vehicle for storage.

[0069] Specifically, the model database stores the results of driving habit classification and learning by each deep learning model. The multiple driving scenarios, various driving habits, and regulatory parameters are correspondingly stored in the cloud.

[0070] The various control parameters in the model database are obtained through learning and training based on a large number of actuator data of drivers. In order to facilitate the subsequent use of the control parameters by each driver, this embodiment establishes a corresponding control parameter library for each driver and sends it to the corresponding vehicle end. The control parameter library of each driver stores control parameters corresponding to multiple driving scenarios.

[0071] The step of determining the control parameters of each driver in each scenario in the cloud based on the actuator data of each driver and the model database includes:

[0072] Input the actuator data of each driver in each driving scenario into the deep learning model under the corresponding scenario to classify driving habits, and output the driving habit type of each driver in each driving scenario;

[0073] The corresponding regulation parameters are queried in the model database according to the driving habit type of the driver in each scenario.

[0074] Furthermore, the cloud can also store the control parameter database of each driver in the user database of the cloud. It can be understood that in order to facilitate distinction and quick search, the control parameter database of each driver is stored with the identity information of the person as index information.

[0075] Step S16: The vehicle side collects vehicle data, which includes the identity information of the current driver and the current driving scene.

[0076] In step S17, the vehicle side queries whether a target regulation and control parameter library of the current driver is stored locally based on the identity information of the current driver.

[0077] Step S18: If yes, the vehicle side queries the target control parameter library for the corresponding target control parameter according to the current driving scenario, and performs control operations according to the target control parameter.

[0078] In specific applications, the vehicle needs to enable the NGP function and NGP adaptation function to establish a connection between the vehicle and the cloud. After the NGP function and NGP adaptation function are enabled on the vehicle, the vehicle obtains vehicle data through the scene recognizer, person recognizer, and actuator. That is, the scene recognizer on the vehicle side identifies and obtains the current driving scene, the person recognizer obtains the current driver's identity information, and the actuator can also obtain the current actuator data.

[0079] Furthermore, the vehicle side can also send the real-time acquired vehicle data to cloud storage, so as to facilitate the subsequent update of the control parameter library of the current driver in the user database.

[0080] The vehicle side queries the local library of target control parameters for the current driver based on their identity information. If so, the vehicle side searches the library for the corresponding target control parameters based on the current driving scenario and sends them to the actuator. The actuator then completes the operation based on these target control parameters.

[0081] The process of using the NGP adaptation function on the vehicle side is as follows:

[0082] (1) Enable the NGP function and NGP adaptation function on the vehicle side;

[0083] (2) Identify the driver's identity and determine whether the driver has a regulatory parameter library;

[0084] (3) If so, the parameters adapted to each driving scenario will be sent and updated to the vehicle-side NGP. New users can only use the factory default regulatory parameters;

[0085] (4) NGP sends instructions to the chassis actuator based on the regulated parameters, and the actuator completes the operation.

[0086] It is understandable that when the target control parameter library of the current driver does not exist locally on the vehicle side, the method further includes:

[0087] The vehicle terminal sends vehicle data to the cloud in real time;

[0088] When the cloud obtains a preset amount of vehicle data of the current driver, the cloud matches the regulation and control parameters of the current driver in various scenarios from the model database based on the vehicle data, and establishes a regulation and control parameter library for the current driver.

[0089] For new users, the vehicle sends the driver's identity information, along with the driving scenarios and corresponding actuator data identified during a period of time, to the cloud. After collecting a certain amount of vehicle data (e.g., two weeks of data), the cloud determines the user's driving habits in different driving scenarios based on the actuator data in the vehicle data. Based on the driving habits in each scenario, the cloud then searches the model database for the corresponding control parameters and establishes a control parameter library for the user.

[0090] Furthermore, since the user's driving habits may change over time, the current control parameters may not be suitable for the user after a period of time. Therefore, in one embodiment of the present invention, the control parameter library of each user is updated regularly, that is, the car manufacturer opens the NGP adaptation function on the vehicle side to obtain the vehicle data of each driver in real time, and updates the control parameter library of each driver at a certain frequency (for example, every half a month) based on the obtained vehicle data. In specific implementation, the actuator data of the driver under different driving scenarios obtained regularly can be fitted into a set of data (for example, taking the average value); the fitted actuator data under each driving scenario is matched with the model database to obtain matching control parameters, and the matched control parameters are used to overwrite the corresponding control parameters in the control parameter library of the corresponding person.

[0091] See also Figure 3 , a vehicle control parameter configuration system according to an embodiment of the present invention, includes a cloud side 100 and a vehicle side 200, wherein the cloud side 100 includes:

[0092] A first acquisition module 101 is configured to acquire a plurality of training data sets under different driving scenarios, wherein the training data sets include actuator data of a plurality of drivers during vehicle driving;

[0093] The model classification module 102 is used to input the training data sets under each driving scenario into the deep learning model of the corresponding driving scenario to classify and learn driving habits, and output the control parameters corresponding to different driving habits under the corresponding driving scenario;

[0094] The first storage module 103 is used to store various driving habits and corresponding control parameters in various driving scenarios in the model database;

[0095] a first establishing module 104 for determining, based on the actuator data of each driver and the model database, a regulation and control parameter for each driver in each scenario, and establishing a regulation and control parameter library for each driver based on the determined information;

[0096] The sending module 105 is used to send the control parameter library of each driver to the corresponding driver's vehicle terminal for storage;

[0097] The vehicle end 200 includes:

[0098] The second acquisition module 201 is used to acquire vehicle data sent by the current vehicle end, wherein the vehicle data includes the identity information of the current driver and the current driving scene;

[0099] A query module 202 is configured to query whether a target regulation and control parameter library of the current driver is stored locally according to the identity information of the current driver;

[0100] The first execution module 203 is configured to query the target regulation and control parameter library for corresponding target regulation and control parameters according to the current driving scenario, and execute regulation and control operations according to the target regulation and control parameters.

[0101] Furthermore, in the above vehicle control parameter configuration system, the vehicle end 200 further includes:

[0102] The second execution module is configured to execute the default control parameters of the vehicle-side system when the target control parameter library of the current driver does not exist locally.

[0103] Furthermore, in the above-mentioned vehicle control parameter configuration system, the vehicle data also includes current actuator data, and the cloud 100 also includes:

[0104] a third acquisition module, configured to acquire a preset amount of vehicle data of the current driver when the target control parameter library of the current driver does not exist locally, the vehicle data including driving scenes identified during driving and corresponding actuator data;

[0105] The second establishing module is used to match the regulation and control parameters of the current driver in various scenarios from the model database according to the vehicle data, and establish a regulation and control parameter library of the current driver.

[0106] Furthermore, in the above-mentioned vehicle control parameter configuration system, the cloud 100 further includes:

[0107] A fourth acquisition module, configured to acquire identity information of each driver;

[0108] The step of establishing a control parameter library for each driver according to the determined information includes:

[0109] A control parameter library for each driver is established based on the determined information and the identity information of each driver, wherein the established control parameter library is indexed by the driver's identity information.

[0110] The vehicle control parameter configuration system provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding content in the aforementioned method embodiment.

[0111] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system or apparatus (e.g., a computer-based system, a system including a processor, or other system that can retrieve and execute instructions from an instruction execution system or apparatus), or in conjunction with such instruction execution systems or apparatuses. For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system or apparatus, or in conjunction with such instruction execution systems or apparatuses.

[0112] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0113] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement the hardware: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0114] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0115] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A vehicle control parameter configuration method, characterized in that: include: Acquiring, through the cloud, a training data set under a plurality of different driving scenarios, wherein the training data set includes actuator data of a plurality of drivers during a vehicle driving process; The cloud inputs the training data sets for each driving scenario into the deep learning model of the corresponding driving scenario to classify and learn driving habits, and outputs the control parameters corresponding to different driving habits in the corresponding driving scenario; The cloud stores each driving habit and corresponding control parameters in each driving scenario in a model database; The cloud determines the control parameters of each driver in each scenario based on the actuator data of each driver and the model database, and establishes a control parameter library for each driver based on the determined information; The cloud sends the control parameter library of each driver to the corresponding driver's vehicle for storage; The vehicle side collects vehicle data, which includes the identity information of the current driver and the current driving scene; The vehicle end queries whether a target regulation and control parameter library of the current driver is stored locally according to the identity information of the current driver; If so, the vehicle side queries the target control parameter library for the corresponding target control parameter according to the current driving scenario, and performs the control operation according to the target control parameter.

2. The vehicle control parameter configuration method according to claim 1, characterized in that: After the step of querying whether the target regulation and control parameter library of the current driver is stored locally based on the identity information of the current driver, the vehicle side also includes: When the target control parameter library of the current driver does not exist locally, the vehicle side uses the system default control parameters.

3. The vehicle control parameter configuration method according to claim 1, characterized in that: The vehicle data also includes current actuator data, and after the step of querying whether a target control parameter library of the current driver is stored locally based on the identity information of the current driver, the vehicle side also includes: When the target control parameter library of the current driver does not exist locally, the vehicle terminal sends the vehicle data to the cloud; When the cloud obtains a preset amount of vehicle data of the current driver; The cloud matches the regulation and control parameters of the current driver in various scenarios from the model database according to the vehicle data, and establishes a regulation and control parameter library of the current driver.

4. The vehicle control parameter configuration method according to claim 1, wherein: The step of determining, by the cloud, the control parameters of each driver in each scenario based on the actuator data of each driver and the model database includes: The cloud inputs the actuator data of each driver in each driving scenario into the deep learning model of the corresponding scenario to classify the driving habits, and outputs the driving habit type of each driver in each driving scenario; The cloud searches the model database for corresponding regulatory parameters based on the driver's driving habits in various scenarios.

5. The vehicle control parameter configuration method according to claim 1, characterized in that: Before the step of establishing the control parameter library of each driver according to the determined information, the cloud further includes: The cloud obtains the identity information of each of the drivers; The step of establishing a control parameter library for each driver according to the determined information in the cloud includes: The cloud establishes a control parameter library for each driver based on the determined information and the identity information of each driver, wherein the established control parameter library is indexed by the driver's identity information.

6. A vehicle control parameter configuration system, characterized in that: Including the cloud and the vehicle side, the cloud side includes: A first acquisition module is configured to acquire a training data set under a plurality of different driving scenarios, wherein the training data set includes actuator data of a plurality of drivers during a vehicle driving process; The model classification module is used to input the training data sets under various driving scenarios into the deep learning model of the corresponding driving scenario to classify and learn driving habits, and output the corresponding control parameters for different driving habits in the corresponding driving scenario; A first storage module is used to store various driving habits and corresponding control parameters in various driving scenarios in a model database; a first establishing module, configured to determine, based on the actuator data of each driver and the model database, a regulation and control parameter for each driver in each scenario, and to establish a regulation and control parameter library for each driver based on the determined information; The sending module is used to send the control parameter library of each driver to the corresponding driver's vehicle for storage; The vehicle end includes: The second acquisition module is used to acquire vehicle data sent by the current vehicle end, wherein the vehicle data includes the identity information of the current driver and the current driving scene; A query module, configured to query whether a target regulation and control parameter library of the current driver is stored locally according to the identity information of the current driver; The first execution module is configured to query the target regulation and control parameter library for corresponding target regulation and control parameters according to the current driving scenario, and execute regulation and control operations according to the target regulation and control parameters.

7. The vehicle control parameter configuration system according to claim 6, characterized in that: The vehicle end further includes: The second execution module is configured to execute the default control parameters of the vehicle-side system when the target control parameter library of the current driver does not exist locally.

8. The vehicle control parameter configuration system according to claim 6, characterized in that: The vehicle data also includes current actuator data, and the cloud also includes: A third acquisition module is configured to acquire a preset amount of vehicle data of the current driver when the target regulation parameter library of the current driver does not exist locally; The second establishing module is used to match the regulation and control parameters of the current driver in various scenarios from the model database according to the vehicle data, and establish a regulation and control parameter library of the current driver.

9. The vehicle control parameter configuration system according to claim 6, characterized in that: The cloud also includes: A fourth acquisition module, configured to acquire identity information of each driver; The step of establishing a control parameter library for each driver according to the determined information includes: A control parameter library for each driver is established based on the determined information and the identity information of each driver, wherein the established control parameter library is indexed by the driver's identity information.

Images