Vehicle control method and device, vehicle control unit and readable storage medium

Abstract

The embodiment of the invention provides a vehicle control method and device, a vehicle control unit and a readable storage medium, and relates to the technical field of vehicles. The method comprises the steps that first driving information generated when a user operates a vehicle is collected; determining target driving habit information from a driving habit information set based on the first driving information; determining an information matching degree between the first driving information and the target driving habit information; under the condition that the information matching degree is greater than or equal to the preset matching degree, function setting of the vehicle is adjusted based on the target driving habit information, and the target driving habit information corresponding to the current user can be determined through first driving information generated by operation of the user on the vehicle; and when the matching degree of the target driving habit information and the first driving information meets the requirement, the target driving habit information is applied to the vehicle to adjust various settings of the vehicle, so that the vehicle meets the vehicle using habit of the current user, and the vehicle using efficiency and safety of the user are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and particularly to a vehicle control method, device, vehicle controller and readable storage medium. Background Art

[0002] With the popularization of automobiles, a car is often used by multiple people, which results in the need for the driver to manually adjust various settings of the in-vehicle environment, such as seat position, music player, navigation software, etc. each time the vehicle is used. This is not only troublesome but also affects the comfort and safety of the driver.

[0003] In the related art, the user can set multiple user IDs for the vehicle and set the corresponding setting parameters for each user ID. After the user gets in the car, they can manually log in to their corresponding user ID, and the vehicle retrieves the setting parameters corresponding to the user ID and applies them to facilitate the use of the vehicle by different drivers.

[0004] However, the current solution requires the driver to perform complex operations to apply the parameter settings suitable for themselves on the vehicle, and the convenience of use is poor, resulting in a still poor efficiency of the user setting the vehicle parameters. Summary of the Invention

[0005] In view of this, the present invention aims to provide a vehicle control method, device, vehicle controller and readable storage medium to solve the problem of low efficiency of user setting vehicle parameters in the prior art.

[0006] To achieve the above object, the technical solution of the present invention is realized as follows:

[0007] In a first aspect, the present invention provides a vehicle control method, the method comprising:

[0008] Collecting first driving information generated by a user operating the vehicle;

[0009] Based on the first driving information, determining target driving habit information from a driving habit information set;

[0010] Determining an information matching degree between the first driving information and the target driving habit information;

[0011] When the information matching degree is greater than or equal to a preset matching degree, adjusting the function settings of the vehicle based on the target driving habit information.

[0012] Optionally, the adjusting the function settings of the vehicle based on the target driving habit information includes:

[0013] Removing the operation items corresponding to the first driving information from the operation item set corresponding to the target driving habit information to obtain a to-be-applied operation item set;

[0014] Adjust the function settings of the vehicle based on the set of operation items to be applied.

[0015] Optionally, the collection of the first driving information generated by the user operating the vehicle includes:

[0016] Collect in real time the operation items of the user for the vehicle to obtain an operation item sequence;

[0017] Extract features from the operation item sequence to obtain the continuously updated first driving information over time.

[0018] Optionally, the operation items include at least one of in-vehicle environment data, driving state data, parking state data, and driving environment data.

[0019] Optionally, the method further includes:

[0020] Obtain the historical driving information corresponding to the user; wherein, the time span between the historical driving information and the first driving information satisfies a preset time period;

[0021] Combine the historical driving information and the first driving information to obtain a driving information sequence;

[0022] Extract features from the operation items of the driving information sequence to obtain the driving habit information to be updated;

[0023] Update the target driving habit information based on the driving habit information to be updated.

[0024] Optionally, the extracting features from the operation items of the driving information sequence to obtain the driving habit information to be updated includes:

[0025] Determine a plurality of driving habit score values based on each operation item of the driving information sequence;

[0026] Obtain the driving habit labels corresponding to the driving habit score values;

[0027] Generate the driving habit information to be updated based on the driving habit labels.

[0028] Optionally, the adjusting the function settings of the vehicle based on the target driving habit information includes:

[0029] Input the first driving information into a target neural network model to obtain a plurality of candidate operation items output by the target neural network model;

[0030] Determine a target operation item from the plurality of candidate operation items based on the target driving habit information;

[0031] Adjust the function settings of the vehicle based on the target operation item.

[0032] In a second aspect, the present invention provides a vehicle control device, which includes:

[0033] An acquisition module, configured to acquire first driving information generated by a user operating the vehicle;

[0034] A determination module, configured to determine target driving habit information from a driving habit information set based on the first driving information;

[0035] A matching degree module, configured to determine the information matching degree between the first driving information and the target driving habit information;

[0036] A setting module, configured to adjust the function settings of the vehicle based on the target driving habit information when the information matching degree is greater than or equal to a preset matching degree.

[0037] Optionally, the setting module includes:

[0038] An item set sub-module, configured to remove the operation item corresponding to the first driving information from the operation item set corresponding to the target driving habit information to obtain a to-be-applied operation item set;

[0039] An adjustment sub-module, configured to adjust the function settings of the vehicle based on the to-be-applied operation item set.

[0040] Optionally, the acquisition module includes:

[0041] An operation item sequence sub-module, configured to acquire in real time the operation items of the user for the vehicle to obtain an operation item sequence;

[0042] A driving information sub-module, configured to perform feature extraction on the operation item sequence to obtain the continuously updated first driving information over time.

[0043] Optionally, the device further includes:

[0044] A historical driving information module, configured to acquire the historical driving information corresponding to the user; wherein, the time span between the historical driving information and the first driving information satisfies a preset time period;

[0045] A driving information sequence module, configured to combine the historical driving information and the first driving information to obtain a driving information sequence;

[0046] A to-be-updated driving habit information module, configured to perform feature extraction on the operation items of the driving information sequence to obtain to-be-updated driving habit information;

[0047] An update module, configured to update the target driving habit information based on the driving habit information to be updated.

[0048] Optionally, the driving habit information module to be updated includes:

[0049] A score value sub-module, configured to determine a plurality of driving habit score values based on each operation item of the driving information sequence;

[0050] A label sub-module, configured to obtain the driving habit label corresponding to the driving habit score value;

[0051] A driving habit information generation sub-module to be updated, configured to generate the driving habit information to be updated based on the driving habit label.

[0052] Optionally, the setting module includes:

[0053] A candidate operation item sub-module, configured to input the first driving information into a target neural network model to obtain a plurality of candidate operation items output by the target neural network model;

[0054] A target operation item determination sub-module, configured to determine a target operation item from the plurality of candidate operation items based on the target driving habit information;

[0055] A function adjustment sub-module, configured to adjust the function settings of the vehicle based on the target operation item.

[0056] In a third aspect, the present invention provides a vehicle controller, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above vehicle control method is implemented.

[0057] In a fourth aspect, the present invention provides a readable storage medium. When the instructions in the readable storage medium are executed by the processor of the vehicle controller, the vehicle controller can execute the above vehicle control method.

[0058] In a fifth aspect, the present invention provides a vehicle, which includes the above vehicle controller.

[0059] Compared with the prior art, the vehicle control method, device, vehicle controller, and readable storage medium according to the present invention have the following advantages:

[0060] In summary, the embodiments of the present invention provide a vehicle control method, including: collecting first driving information generated by a user operating a vehicle; determining target driving habit information from a set of driving habit information based on the first driving information; determining the information matching degree between the first driving information and the target driving habit information; and when the information matching degree is greater than or equal to a preset matching degree, adjusting the function settings of the vehicle based on the target driving habit information. It is possible to determine the target driving habit information corresponding to the current user through the first driving information generated by the user's operation of the vehicle, and when the matching degree between the target driving habit information and the first driving information meets the requirements, apply the target driving habit information to adjust the various settings of the vehicle on the vehicle to make it conform to the current user's vehicle usage habits, so that the vehicle can adapt to the vehicle usage habits of multiple different users without the user's awareness, reduce the operation frequency of the user when using the vehicle, and help improve the efficiency and safety of the user using the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings, which form a part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions thereof of the invention are used to explain the invention and do not constitute an improper limitation of the invention. In the drawings:

[0062] Figure 1 It is a flowchart of the steps of a vehicle control method provided by an embodiment of the present invention;

[0063] Figure 2 It is a schematic diagram of an application mode provided by an embodiment of the present invention;

[0064] Figure 3 It is a flowchart of user switching provided by an embodiment of the present invention;

[0065] Figure 4 It is a flowchart of the steps of another vehicle control method provided by an embodiment of the present invention;

[0066] Figure 5 It is a schematic diagram of the generation process of driving habit information provided by an embodiment of the present invention;

[0067] Figure 6 It is a block diagram of the structure of a vehicle control device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0069] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0070] Referring to Figure 1 , a flowchart of the steps of a vehicle control method provided by an embodiment of the present invention is shown.

[0071] Step 101, collect first driving information generated by a user operating a vehicle.

[0072] In an embodiment of the present invention, after the vehicle is started or unlocked, operation items of the user on the vehicle can be collected, and first driving information is generated based on the operation items. Among them, the operation items can include any information generated by the user operating the vehicle. For example, the operation items can include information capable of describing the interaction process between the user and the vehicle (such as the speed at which the user opens and closes the car door, the pressure applied to the driver's seat, the way of operating the human-machine interaction system, the speed of turning the steering wheel, the speed of stepping on the accelerator pedal, etc.), environmental information around the vehicle (such as road condition data, vehicle positioning data, weather data near the vehicle, vehicle ambient temperature, point cloud data around the vehicle, image data around the vehicle, etc.).

[0073] Specifically, starting from when the user unlocks or starts the vehicle, operation items of the user on the vehicle can be continuously collected. When the collected operation items meet a preset determination condition, first driving information is generated based on the collected operation items. The preset determination condition can include at least one of, but is not limited to, a time condition, a quantity condition, etc. The time condition is used to indicate the duration of collecting the operation items, and the quantity condition is used to indicate the quantity of the collected operation items.

[0074] In an embodiment of the present invention, the directly collected operation items can be used as the first driving information, or the operation items can be processed to generate the first driving information. Among them, the above processing can include one or more of, but is not limited to, cleaning, feature extraction, labeling, normalization, etc.

[0075] Since different users have different driving habits. For example, some users like aggressive driving, while others like gentle driving. Reflected in the driving information, the driving information generated by some users during driving has a relatively high accelerator pedal stepping speed, while the driving information generated by other users during driving has a relatively low accelerator pedal stepping speed. Therefore, in an embodiment of the present invention, the user of the currently driven vehicle can also be authenticated by collecting the first driving information generated during this trip.

[0076] Further, in order to further improve the accuracy of authentication, in an embodiment of the present invention, in addition to generating first driving information based on the operation items, first driving information can also be generated based on the operation items and other information. The above other information can include, but is not limited to, biometric information, password information, etc. Among them, the biometric information can include, but is not limited to, face information, retina information, fingerprint information, weight information, height information, etc.; the password information can include, but is not limited to, account password information, voice verification information, radio frequency key information, mobile terminal identification information, gesture recognition information, etc.

[0077] In addition, the first driving information may further include any other data type that can reflect the differences between users, and those skilled in the art can flexibly select according to the actual situation, and the embodiments of the present invention do not make specific limitations.

[0078] Step 102: Determine target driving habit information from the driving habit information set based on the first driving information.

[0079] In the embodiments of the present invention, each user can enter driving habit information in advance, and all the driving habit information can form a driving habit information set. The first driving information is matched with each driving habit information in the driving habit information set to determine the driving habit information corresponding to the first driving information.

[0080] When a user uses a vehicle, the first driving information of the user can be collected. The first driving information is collected by the vehicle, and based on the matching result between the first driving information and the driving habit information, the corresponding target driving habit information is determined from the driving habit information set.

[0081] In the embodiments of the present invention, if the corresponding target driving habit information can be matched through the first driving information, it can be determined that the user identity of the currently driving vehicle is verified and subsequent operations can be further performed. In addition to using operation items for identity verification, in order to improve the accuracy of identity authentication, user identification information may also be included in the first driving information. The user identification information may include, but is not limited to, one or more types of information such as biometric information, password identification information, and radio frequency identification information. In addition to matching the first driving information with the driving habit information, the user identification information is also matched with the corresponding type of information in the preset identification information library, and when both the first driving information and the user identification information are verified, the driving habit information matched by the first driving information is determined as the target driving habit information to improve the accuracy of user identity verification based on the first driving information, and thus the accuracy of the target identity information determined based on the first driving information.

[0082] Further, if the first driving information fails to match successfully with any of the already stored driving habit information, a driving habit information addition prompt can be sent to the user through the vehicle's human-machine interaction system, mobile terminal, etc., asking the user whether to add the first driving information as the driving habit information of a new user. After the user confirms the addition, the first driving information can be used as the driving habit information corresponding to a new user identity, and the corresponding relationship between the two is established.

[0083] In the embodiments of the present invention, the driving habit information can be set by the user himself / herself, or can be collected by the vehicle based on the user's operations on the vehicle. For example, the driving habit information can include the settings of the vehicle's human-machine interaction system by the user (such as screen brightness, volume, launched applications, etc.), the settings of the vehicle's driving system (such as driving mode, steering mode, drive mode, lighting usage method, etc.), the settings of the in-vehicle navigation system (such as common destinations, common routes, etc.), the functional settings of the vehicle cockpit (such as electric seat settings, air conditioning settings, interior lighting settings, rearview mirror settings, etc.). In the embodiments of the present invention, the driving habit information can include any settings controllable by the vehicle, and the embodiments of the present invention do not make limitations.

[0084] It should be noted that the driving habit information can be directly collected when the user is driving the vehicle, or can be obtained after processing the operation items collected when the user is driving the vehicle. Among them, the above processing can include taking the highest frequency operation, taking the average value operation, a driving habit output model based on a neural network, etc., and the embodiments of the present invention do not make specific limitations.

[0085] It is easy to understand that as the number of times the user drives the vehicle corresponding to the driving habit information increases, the latest driving data of the user can be collected in each trip, and the driving habit information can be continuously updated and improved based on the latest driving data, so that the driving habit information of each user becomes more accurate and rich.

[0086] Step 103, determine the information matching degree between the first driving information and the target driving habit information.

[0087] After obtaining the target driving habit information, the first driving information can be matched with the target driving habit information, so as to determine the information matching degree between the two, in order to improve the accuracy of applying the target driving habit information.

[0088] In one embodiment, both the first driving information and the target driving habit information can be composed of multiple operation items. When matching the first driving information with the target driving habit information, the operation items included in the first driving information can be matched with the same operation items included in the target driving habit information, so as to determine the information matching degree between the two. For example, the first driving information may include 20 operation items, and the target driving habit information may include 100 operation items. Among them, there are 15 overlapping operation items between the first driving information and the target driving habit information. Among these 15 overlapping operation items, 12 operation items are the same. Then, the information matching degree between the two can be determined as 12 / 15 = 80%. It should be noted that in order to avoid the influence of too few overlapping operation items on the accuracy of the information matching degree, a preset number of items (such as 20) can be set, and when the number of operation items included in the first driving information is greater than or equal to the preset number of items, the information matching degree between the first driving information and the target driving habit information can be determined, so as to improve the accuracy of the information matching degree to a certain extent.

[0089] In another embodiment, the first driving information and the target driving habit information can be obtained by processing such as feature extraction of the operation items, which can reflect the feature information of the operation items. In this case, the first driving information and the target driving information can be directly compared to determine the information matching degree between the two, so as to improve the comparison speed between the first driving information and the target driving information. For example, if the first driving information is a feature vector A with a dimension of 20, and the target driving habit information is a feature vector B with a dimension of 20, then the feature vector A and the feature vector B can be directly compared, and the feature similarity between the feature vector A and the feature vector B can be determined as the information matching degree.

[0090] Step 104, when the information matching degree is greater than or equal to the preset matching degree, adjust the function settings of the vehicle based on the target driving habit information.

[0091] In the embodiments of the present invention, a preset matching degree (such as 60%) can be set, and when the information matching degree is greater than or equal to the preset matching degree, the function settings of the vehicle are adjusted based on the target driving habit information. Among them, the preset matching degree can be flexibly set by technicians and users according to actual needs, and the embodiments of the present invention do not make specific limitations.

[0092] In the embodiments of the present invention, the operation items corresponding to the target driving habit information may include the correspondence between item identifiers and item parameters, and may also include setting execution logics. Among them, the correspondence between items and item parameters can be used to independently set a certain function of the vehicle. For example, the rearview mirror angle, the steering wheel height, the media volume, etc.; the setting execution logic can be used to control the execution logic of a certain function of the vehicle. For example, the lighting usage logic, the driving mode switching logic, the throttle response logic, etc.

[0093] For example, the target driving habit information may include the adjustment angle corresponding to the adjustment parameter of the electric rearview mirror, where the adjustment parameter of the electric rearview mirror is the item identifier and the adjustment angle is the corresponding item parameter. The target driving habit information may include the setting execution logic of the automatic windshield wiper. The setting execution logic of the automatic windshield wiper can be established according to the user's operation of the windshield wiper on rainy days to simulate the user's habit of using the windshield wiper.

[0094] Specifically, the specific content of a setting execution logic may be composed of one or more setting execution entries. A setting execution entry may include an item identifier, an item parameter, a setting condition, etc. Among them, the setting condition can be used to determine the timing of adjusting the item identifier to the item parameter.

[0095] For example, a setting execution logic may be composed of two setting execution entries A and B. The item identifier included in the setting execution entry A may be the tire pressure, the setting parameter is 2.5 bar, and the setting condition is that the ambient temperature is less than or equal to 10 degrees Celsius; the item identifier included in the setting execution entry B may be the tire pressure, the setting parameter is 2.0 bar, and the setting condition is that the ambient temperature is greater than or equal to 30 degrees Celsius.

[0096] Refer to Figure 2 , Figure 2 shows a schematic diagram of an application method provided by the embodiments of the present invention. As Figure 2 shown, the user can pre-enter user information. When the user starts a journey, the user can manually perform identity authentication to determine the user ID corresponding to the current user, or can obtain the first driving information when the user starts a journey. The first driving information may include operation items, biometric information, radio frequency identification information, etc. Automatic identity authentication is performed through the first driving information to determine the user ID corresponding to the current user, and the target driving habit information corresponding to the user ID is obtained. Among them, the target driving habit information may include in-vehicle environment settings, driving settings, etc. After further verifying the target driving habit information, the target driving habit information can be applied to the vehicle.

[0097] Further, during a single trip, the user driving the vehicle may also change. For example, during a long - distance drive to ensure driving safety, the user in the driver's seat may change. Therefore, in the embodiments of the present invention, the target driving habit information can also be re - determined after the user changes, and the newly determined target driving habit information can be applied so that the vehicle settings can be adapted to the user habits of the current vehicle driver in real - time. Specifically, it can be detected whether the user has changed through methods such as seat pressure and biometric recognition. If the user has changed, the first driving information can be re - obtained, and the target driving habit information can be re - determined and applied based on the re - obtained first driving information. The user can also manually switch the user ID and re - obtain the corresponding target driving habit information according to the switched user ID.

[0098] Refer to Figure 3 , Figure 3 which shows a user switching flowchart provided by the embodiments of the present invention. As Figure 3 shown, after the start of a single trip, User 1 drives the vehicle first. At this time, the first driving information of User 1 can be collected, and automatic authentication can be performed based on the first driving information of User 1. After identity authentication, the user ID of User 1 is determined, and the corresponding driving habit information 1 is obtained and applied. During this trip, at a certain moment, User 2 takes over the driving. At this time, the first driving information of User 2 can be collected, and automatic authentication can be performed based on the first driving information of User 2. After identity authentication, the user ID of User 2 is determined, and the corresponding driving habit information 2 is obtained and applied, and so on. During the above process, the user can also directly manually switch the user ID.

[0099] In summary, the embodiments of the present invention provide a vehicle control method, including: collecting the first driving information generated by the user operating the vehicle; determining the target driving habit information from the driving habit information set based on the first driving information; determining the information matching degree between the first driving information and the target driving habit information; and when the information matching degree is greater than or equal to the preset matching degree, adjusting the function settings of the vehicle based on the target driving habit information. The target driving habit information corresponding to the current user can be determined through the first driving information generated by the user's operation of the vehicle, and when the matching degree between the target driving habit information and the first driving information meets the requirements, the target driving habit information is applied to the vehicle to adjust various settings of the vehicle to conform to the current user's vehicle - using habits, so that the vehicle can be adapted to the vehicle - using habits of multiple different users without the user's awareness, reducing the operation frequency of the user when using the vehicle, and helping to improve the efficiency and safety of the user using the vehicle.

[0100] Refer to Figure 4 , Figure 4 which shows another flowchart of the steps of the vehicle control method provided by the embodiments of the present invention.

[0101] Step 201, collect in real time the operation items of the user for the vehicle to obtain an operation item sequence.

[0102] Since the user will continuously operate the vehicle when using the vehicle, new operation items will be continuously generated. Therefore, in order to improve the accuracy of identity verification based on the first driving information, the latest first driving information can be continuously generated based on all the currently collected operation items over time.

[0103] Specifically, after the user uses the vehicle, the operation items of the user for the vehicle can be collected in real time, and the operation items can be combined according to the collection time of the operation items to obtain an operation item sequence.

[0104] For example, after user A gets in the car, first fastens the seat belt, then adjusts the rearview mirror, then adjusts the seat, and then starts the vehicle. Correspondingly, after the user starts the vehicle, the following operation item sequence can be obtained:

[0105] [Fasten seat belt, adjust rearview mirror, adjust seat, start vehicle]

[0106] After user B gets in the car, first adjusts the seat, then fastens the seat belt, then starts the vehicle, and then adjusts the rearview mirror. Correspondingly, after the user adjusts the rearview mirror, the following operation item sequence can be obtained:

[0107] [Adjust seat, fasten seat belt, start vehicle, adjust rearview mirror]

[0108] It should be noted that the above operation item sequence is only for simplified description, and the operation items can include not only item identifiers, but also item parameters corresponding to the item identifiers. For example, "Adjust seat: 5CM forward".

[0109] Optionally, in the embodiments of the present invention, the operation items may include, but are not limited to, in-vehicle environment setting information, vehicle driving state information, parking state information, and driving environment information.

[0110] The in-vehicle environment setting information may include, but is not limited to, in-vehicle lighting settings, seat settings, steering wheel settings, air conditioning settings, window settings, the usage frequency of the in-vehicle radio, the usage duration of the in-vehicle radio, the usage of music software (the selection frequency of playlists), the usage frequency of the navigation software, the usage frequency of the air conditioning in different seasons and weather conditions, the usage duration of the air conditioning in different seasons and weather conditions, etc.; the vehicle driving state information may include, but is not limited to, the average vehicle speed, the average vehicle acceleration / deceleration, the hard acceleration acceleration, the hard braking acceleration, the cornering speed, the lateral acceleration, the lane change frequency, the gear shift frequency, the warm-up time, the idle time, the usage duration of the low / high beam lights, the usage frequency of the low / high beam lights, the steering frequency, the usage frequency of the turn signals, the usage time of the turn signals, the correct usage frequency of the turn signals, the frequency and duration of mobile phone usage, the usage frequency of the assisted driving function, the traffic rule violation information; the parking state information may include, but is not limited to, the handbrake setting, the parking gear setting, the parking window state, the parking lighting setting, the parking frequency, the parking duration, etc.; the driving environment information may include, but is not limited to, the driving time, the driving road condition information, the road congestion information, the driving road information, the driving terrain information, the driving weather information, the driving mileage, etc.

[0111] Step 202, perform feature extraction on the operation item sequence to obtain the first driving information that is continuously updated over time.

[0112] After generating the operation item sequence or adding new data to the operation sequence, feature extraction can be performed on the operation item sequence to obtain the first driving information that is continuously updated over time. Thus, the first driving information can more and more accurately reflect the user's vehicle usage habits as time goes by.

[0113] Specifically, the ways to perform feature extraction on the operation item sequence to obtain the first driving information may include using an RNN (Recurrent Neural Network) or its variants (such as LSTM, GRU, etc.), leveraging the memory ability of the neural network to encode the data sequence into a fixed-length vector while retaining the sequence order information and element information; using a Transformer or its variants (such as BERT, GPT, etc.), leveraging the self-attention mechanism to encode the data sequence into a fixed-length vector while retaining the sequence order information and element information; using a CNN (Convolutional Neural Network) or its variants (such as TextCNN, WaveNet, etc.), leveraging the convolutional kernel and pooling layer to encode the data sequence into a fixed-length vector while retaining the local information and global information of the sequence. Those skilled in the art can also select other ways to perform feature extraction on the operation item sequence to obtain the first driving information as needed, and the embodiments of the present invention do not make specific limitations.

[0114] In an embodiment of the present invention, by collecting in real time the operation items of a user for a vehicle, an operation item sequence is obtained, and feature extraction is performed on the operation item sequence to obtain first driving information that is continuously updated over time. This can not only make the first driving information contain more and more feature data as the user operates the vehicle, continuously improving the first driving information, but also enable the first driving information to contain not only the features of the operation items but also the time-domain features of the sequence in which the operation items are generated, which helps to improve the accuracy of identity verification using the first driving information.

[0115] Optionally, step 202 may include:

[0116] Sub-step 2021, determining the driving habit score values corresponding to each element in the operation item sequence.

[0117] To determine a corresponding driving habit score value for each operation item, specifically, the corresponding score value rule can be obtained according to the item identifier of the operation item, and then the item parameters corresponding to the operation item are calculated according to this scoring rule to obtain the driving habit score value corresponding to the operation item. Among them, the above-mentioned score value rule can be flexibly set by those skilled in the art according to actual needs, and the embodiments of the present invention do not make specific limitations. It should be noted that the above elements may represent an operation item in the operation item sequence or a set of multiple operation items in the operation item sequence.

[0118] Sub-step 2022, obtaining the driving habit label corresponding to the driving habit score value.

[0119] In an embodiment of the present invention, each type of driving habit score value may correspond to a label bin, and through this label bin, the driving habit label corresponding to the driving habit score value can be determined.

[0120] Sub-step 2023, generating the first driving information based on the driving habit label.

[0121] In an embodiment of the present invention, after determining all the driving habit labels corresponding to the driving information sequence, these driving habit labels can be combined to obtain the first driving information corresponding to the operation item sequence. Among them, the above combination methods may include but are not limited to splicing, feature extraction, feature fusion, etc., and the embodiments of the present invention do not make specific limitations.

[0122] Step 203, based on the first driving information, determining target driving habit information from the set of driving habit information.

[0123] In an embodiment of the present invention, the first driving information can be obtained by feature extraction based on operation items. Correspondingly, the target driving habit information can also be obtained by extracting from operation history data. To ensure the accuracy of the comparison result, the generation method of the target driving habit information can be the same as that of the first driving information. For example, if the target driving habit information is obtained by tagging operation history data, the first driving information can also be obtained by tagging operation items in the same way.

[0124] Specifically, the first driving information can be compared with each authentication information to obtain the information similarity between the first driving information and each driving habit information, and the driving habit information with an information similarity greater than or equal to the preset similarity is determined as the target driving habit information.

[0125] Step 204, determine the information matching degree between the first driving information and the target driving habit information.

[0126] In an embodiment of the present invention, since the first driving information will gradually become richer with the operation items generated during the use of the vehicle, therefore, the target driving habit information can be first determined from each driving habit information according to the first driving information with less data volume (that is, the first driving information determined when the amount of collected operation items is less), and then the target driving habit information is secondarily matched according to the first driving information with more data volume (that is, the first driving information determined when the amount of collected operation items is more), so as to verify the target driving habit information and improve the accuracy of applying the target driving habit information.

[0127] Specifically, after determining the target driving habit information, at a preset time interval, the first driving information and the target driving habit information can be continuously compared to obtain the continuously updated information matching degree between the two. Since the driving habit information contains a large amount of data, to improve the system operation efficiency and comparison efficiency, the target driving habit information can be determined through the above step 203, and after determining the target driving habit information, only the first driving information and the target driving habit information are subjected to subsequent continuous comparison operations, reducing the amount of data to be compared and improving the comparison efficiency.

[0128] This step can refer to step 103, and the embodiments of the present invention will not be elaborated herein.

[0129] Step 205, when the information matching degree is greater than or equal to the preset matching degree, adjust the function settings of the vehicle based on the target driving habit information.

[0130] This step can refer to step 104, and the embodiments of the present invention will not be elaborated herein.

[0131] Optionally, to avoid conflicts with the settings already completed by the current user during this trip when applying the target driving habit information, step 205 may include:

[0132] Step A1, remove the operation items corresponding to the first driving information from the set of operation items corresponding to the target driving habit information to obtain a set of operation items to be applied.

[0133] In the embodiment of the present invention, the operation items included in the first driving information are the operation items that the user has adjusted during this trip. To avoid overwriting the items already set by the user during this trip when applying the target driving habit information, the operation items included in the first driving information can be removed from the target driving habit information to obtain a set of operation items to be applied.

[0134] Step A2, adjust the function settings of the vehicle based on the set of operation items to be applied.

[0135] For example, the set of operation items corresponding to the first driving information may include operation item A, operation item B, and operation item C, and the set of operation items corresponding to the target driving habit information may include operation item A, operation item C, operation item D, and operation item E. Then, the set of operation items to be applied obtained by removing the operation items corresponding to the first driving information from the set of operation items corresponding to the target driving habit information may include operation item D and operation item E. Furthermore, operation item D and operation item E can be applied to the vehicle to complete the application of the target operation items.

[0136] By removing the operation items corresponding to the first driving information from the set of operation items corresponding to the target driving habit information to obtain a set of operation items to be applied and adjusting the function settings of the vehicle based on the set of operation items to be applied, it is possible to avoid affecting the items already set by the user during this trip when applying the target driving habit information, which helps to improve the user experience.

[0137] Optionally, step 205 may further include:

[0138] Step B1, input the first driving information into the target neural network model to obtain a plurality of candidate operation items output by the target neural network model.

[0139] Since there is usually a correlation between the operations performed by the user on the vehicle. For example, in a hot driving environment, there is a high probability that the user will turn on the air conditioner after closing the windows; when driving during working hours, the user usually sets the destination of the in-vehicle navigation to the workplace, and when driving after work, the user usually sets the destination of the in-vehicle navigation to home. Therefore, a target neural network model can be pre-trained. By combining the first driving information of the user on the vehicle during this trip through the target neural network model, the vehicle settings that the user is about to perform can be predicted.

[0140] Specifically, a large number of historical driving information corresponding to users can be used to generate training samples. The training samples can include a set of sample operation items of a certain user within a period of time, and the reference operation items executed by the user after the set of sample operation items. During the training process, the set of sample operation items can be used as the input of the neural network model to obtain the predicted operation items output by the neural network model. Then, based on the predicted operation items and the reference operation items corresponding to the set of operation items, the model loss is calculated, and the parameters of the neural network model are adjusted based on the model loss. The training of the neural network model is completed in the way of gradient descent to obtain the target neural network model. The training method of the target neural network model in the embodiments of the present invention is not specifically limited, and those skilled in the art can select a suitable method to train the target neural network model according to actual needs.

[0141] It should be noted that the target neural network model can be trained based on the historical operation information corresponding to a single user, or based on the historical operation information of multiple users, so that the candidate operation items output by the target neural network model can reflect more common user usage habits, and each user can use the same set of target neural network models to determine the target operation items, which helps to reduce the training cost of the target neural network model.

[0142] Step B2, determine the target operation item from the multiple candidate operation items based on the target driving habit information.

[0143] After obtaining multiple candidate operation items, the multiple candidate operation items can be matched with the target driving habit information, and one or more target operation items that match the operation items in the target driving habit information can be determined from the multiple candidate operation items, and the vehicle can be controlled based on the target operation items.

[0144] For example, if multiple operation items include operation item A: setting the navigation destination to the company, operation item B: setting the navigation destination to the nearest gas station, and operation item C: setting the navigation destination to the airport. And in the target driving habit information, there is an operation item of setting the navigation destination to the nearest gas station. After matching the target driving habit information with the above multiple candidate operation items, it can be determined that the target operation item is the above operation item B.

[0145] Step B3, adjust the function settings of the vehicle based on the target operation item.

[0146] By inputting the first driving information into the target neural network model, multiple candidate operation items output by the target neural network model are obtained. Based on the target driving habit information, the target operation item is determined from the multiple candidate operation items. It is possible to predict the operations that the user needs to perform next according to the real-time updated first driving information, and adjust the vehicle settings according to the prediction results, which helps to further improve the convenience of the user operating the vehicle.

[0147] Step 206, obtain the historical driving information corresponding to the user; wherein, the time span between the historical driving information and the first driving information satisfies a preset time period.

[0148] In the embodiments of the present invention, the target driving habit information corresponding to a certain user can also be continuously updated according to the first driving information collected in each trip, so that the target driving habit information gradually becomes more perfect as the user continuously uses it, and further improves the accuracy of controlling the vehicle function settings based on the target driving habit information.

[0149] Specifically, the historical driving information corresponding to the user can be obtained. The historical driving information can include the driving information collected in one or more historical trips of the user. The preset time period can include but is not limited to one day, one week, one month, one quarter, etc. The embodiments of the present invention will not elaborate. The preset time period can be flexibly set by technicians or users. For example, when the preset time period is one month, if the acquisition time of the first driving information of the current user is August 2, 2023, the driving information collected in the historical trips of the user from July 2, 2023 to August 2, 2023 can be obtained as the above historical driving information.

[0150] It should be noted that in the embodiments of the present invention, the historical driving information can be composed of operation items or obtained by feature extraction of operation items. The embodiments of the present invention do not make specific limitations.

[0151] Step 207, combine the historical driving information and the first driving information to obtain a driving information sequence.

[0152] In an embodiment of the present invention, since the historical driving information may include driving information corresponding to multiple trips, the multiple driving information in the historical driving information and the first driving information can be combined to obtain a driving information sequence composed of driving information corresponding to multiple trips respectively.

[0153] Step 208: Extract features from the operation items of the driving information sequence to obtain the driving habit information to be updated.

[0154] In an embodiment of the present invention, since the driving information sequence has respective operation items corresponding to both the first driving information and the historical driving information, the formed driving information sequence is composed of the operation items of the first driving information and the historical driving information. Features can be extracted from the operation items in the driving information sequence, so as to obtain the driving habit information to be updated.

[0155] Optionally, in an embodiment of the present invention, the driving information sequence can also be processed in the following manner to obtain the corresponding updated driving habit information. Step 208 may include:

[0156] Sub-step 2081: Determine a plurality of driving habit score values based on the respective operation items of the driving information sequence.

[0157] In one implementation manner, a corresponding driving habit score value can be determined according to each operation item. Specifically, the score value rule corresponding to the operation item can be obtained according to the item identifier corresponding to the operation item, and then the item parameters corresponding to the operation item are calculated according to the score system rule to obtain the driving habit score value corresponding to the operation item. Among them, the above score value rule can be flexibly set by technicians according to actual needs, and the embodiment of the present invention does not make specific limitations.

[0158] For example, the item identifier of an operation item is the average throttle pedal depression depth, the item parameter of this operation item is 20%, and the corresponding score value rule is: S=(1 - D)*10. Where S represents the driving habit score value corresponding to the above operation item, and D represents the item parameter. In the case where the item parameter is 20%, the driving habit score value is 8.

[0159] In another implementation manner, the score values corresponding to each operation item can be calculated first, and then the score values corresponding to the operation items classified into the same item are weighted to obtain the driving habit score value corresponding to the item classification. Among them, the item classification of the operation item may include but is not limited to in-vehicle environment setting, vehicle driving state, parking state, driving environment, etc.

[0160] Sub-step 2082: Obtain the driving habit label corresponding to the driving habit score value.

[0161] In an embodiment of the present invention, each type of driving habit score value may correspond to a label binning, and through this label binning, the driving habit label corresponding to the driving habit score value can be determined.

[0162] For example, if the label binning rule corresponding to the vehicle driving state is as follows:

[0163] Score value (0，10) [10，20) [20，30) [30，40) [40，50] Label Very gentle Gentle Average Aggressive Very aggressive

[0164] When the driving habit score value corresponding to the vehicle driving state is 15, it can be determined that the driving habit label corresponding to this driving habit score value is "gentle".

[0165] Sub-step 2083, generating the to-be-updated driving habit information based on the driving habit label.

[0166] In an embodiment of the present invention, after determining all the driving habit labels corresponding to the driving information sequence, these driving habit labels can be combined to obtain the to-be-updated driving habit information corresponding to the driving information sequence. Among them, the above combination methods may include but are not limited to splicing, feature extraction, feature fusion, etc., and the embodiments of the present invention do not make specific limitations.

[0167] It should be noted that in an embodiment of the present invention, the process of extracting features from the operation item sequence to obtain the first driving information that is continuously updated over time can also adopt a method similar to the method of generating the to-be-updated driving habit information through the driving habit score value. Specifically, the first score value generated by each operation item in the operation item sequence can be generated, the first label corresponding to each first score value can be determined, and then the first driving information that is continuously updated over time can be generated according to the first label.

[0168] By determining multiple driving habit score values based on each operation item of the driving information sequence, obtaining the driving habit label corresponding to the driving habit score value, and generating the to-be-updated driving habit information based on the driving habit label, the to-be-updated driving habit information of the driving information sequence can be quickly determined, thereby improving the efficiency of updating the target driving habit information. At the same time, the to-be-updated driving habit information can be described by multiple driving habit score values, which helps to improve the accuracy of the target driving habit information updated based on the to-be-updated driving habit information.

[0169] Step 209, updating the target driving habit information based on the to-be-updated driving habit information.

[0170] In an embodiment of the present invention, after obtaining the to-be-updated driving habit information, the target driving habit information can be updated based on the to-be-updated driving habit information, so that the target driving habit information becomes more and more accurate as the user continuously uses the vehicle.

[0171] The target driving habit information can be updated by replacing the original target driving habit information with the to-be-updated driving habit information. The target driving habit information can also be corrected with the to-be-updated driving habit information to complete the update of the target driving habit information.

[0172] It should be noted that for newly established users who do not yet have corresponding driving habit information, in this case, the driving habit information corresponding to the user can be directly generated based on the first driving information collected during the first trip after the user is established. The specific generation of this driving habit information can be similar to the method of generating the to-be-updated driving habit information in the above steps, and the embodiments of the present invention will not elaborate. Refer to Figure 5 , Figure 5 shows a schematic diagram of a driving habit information generation process provided by an embodiment of the present invention. As Figure 5 shown, the first driving information may include in-vehicle environment data, driving state data, parking state data, driving environment data, etc. By generating driving habit tags from the first driving information, such as Figure 5 the driving habit tags 1 to 5 shown in, and then generating driving information based on the driving habit tags, and finally storing the driving habit information and establishing a corresponding relationship with the user.

[0173] In summary, the embodiments of the present invention provide another vehicle control method, including: collecting first driving information generated by a user operating a vehicle; determining target driving habit information from a driving habit information set based on the first driving information; determining the information matching degree between the first driving information and the target driving habit information; and adjusting the function settings of the vehicle based on the target driving habit information when the information matching degree is greater than or equal to a preset matching degree. The target driving habit information corresponding to the current user can be determined through the first driving information generated by the user's operation of the vehicle, and when the matching degree between the target driving habit information and the first driving information meets the requirements, the target driving habit information is applied to the vehicle to adjust various settings of the vehicle to conform to the current user's driving habits, so that the vehicle can adapt to the driving habits of multiple different users without the user's awareness, reduce the operation frequency of the user when using the vehicle, and help improve the efficiency and safety of the user using the vehicle.

[0174] Based on the above embodiments, the embodiments of the present invention further provide a vehicle control device.

[0175] Refer to Figure 6 , Figure 6 shows a structural block diagram of a vehicle control device provided by an embodiment of the present invention:

[0176] A collection module 601, configured to collect first driving information generated by a user operating a vehicle;

[0177] A determination module 602, configured to determine target driving habit information from a set of driving habit information based on the first driving information;

[0178] A matching degree module 603, configured to determine the information matching degree between the first driving information and the target driving habit information;

[0179] A setting module, configured to adjust the function settings of the vehicle based on the target driving habit information when the information matching degree is greater than or equal to a preset matching degree.

[0180] Optionally, the setting module includes:

[0181] An item set sub-module, configured to remove the operation items corresponding to the first driving information from the set of operation items corresponding to the target driving habit information to obtain a set of operation items to be applied;

[0182] An adjustment sub-module, configured to adjust the function settings of the vehicle based on the set of operation items to be applied.

[0183] Optionally, the acquisition module includes:

[0184] An operation item sequence sub-module, configured to collect in real time the operation items of the user for the vehicle to obtain an operation item sequence;

[0185] A driving information sub-module, configured to perform feature extraction on the operation item sequence to obtain the continuously updated first driving information over time.

[0186] Optionally, the device further includes:

[0187] A historical driving information module, configured to obtain the historical driving information corresponding to the user; wherein, the time span between the historical driving information and the first driving information satisfies a preset time period;

[0188] A driving information sequence module, configured to combine the historical driving information and the first driving information to obtain a driving information sequence;

[0189] A driving habit information to be updated module, configured to perform feature extraction on the operation items of the driving information sequence to obtain driving habit information to be updated;

[0190] An update module, configured to update the target driving habit information based on the driving habit information to be updated.

[0191] Optionally, the driving habit information to be updated module includes:

[0192] A scoring value sub-module, configured to determine a plurality of driving habit scoring values based on each operation item of the driving information sequence;

[0193] A label sub-module, configured to obtain a driving habit label corresponding to the driving habit score value;

[0194] A to-be-updated driving habit information generation sub-module, configured to generate the to-be-updated driving habit information based on the driving habit label.

[0195] Optionally, the setting module includes:

[0196] A to-be-selected operation item sub-module, configured to input the first driving information into a target neural network model to obtain a plurality of to-be-selected operation items output by the target neural network model;

[0197] A target operation item determination sub-module, configured to determine a target operation item from the plurality of to-be-selected operation items based on the target driving habit information;

[0198] A function adjustment sub-module, configured to adjust the function settings of the vehicle based on the target operation item.

[0199] In summary, the embodiment of the present invention provides a vehicle control device, including: a collection module, configured to collect first driving information generated by a user operating a vehicle; a determination module, configured to determine target driving habit information from a driving habit information set based on the first driving information; a matching degree module, configured to determine an information matching degree between the first driving information and the target driving habit information; a setting module, configured to, when the information matching degree is greater than or equal to a preset matching degree, adjust the function settings of the vehicle based on the target driving habit information. It is possible to determine the target driving habit information corresponding to the current user through the first driving information generated by the user operating the vehicle, and when the matching degree between the target driving habit information and the first driving information meets the requirements, apply the target driving habit information to adjust various settings of the vehicle on the vehicle to make it conform to the vehicle usage habits of the current user, so as to enable the vehicle to adapt to the vehicle usage habits of multiple different users without the user's perception, reduce the operation frequency of the user when using the vehicle, and help improve the efficiency and safety of the user using the vehicle.

[0200] The embodiment of the present invention further provides a vehicle controller, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the above vehicle control method.

[0201] The embodiment of the present invention further provides a readable storage medium, when the instructions in the readable storage medium are executed by the processor of the vehicle controller, enabling the vehicle controller to execute the above vehicle control method.

[0202] The embodiment of the present invention further provides a vehicle, including the above vehicle controller.

[0203] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing device embodiments and will not be elaborated herein.

[0204] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

[0205] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present invention and should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A vehicle control method, characterized in that, The method includes: Collecting first driving information generated by a user operating a vehicle; Based on the first driving information, determining target driving habit information from a driving habit information set; Determining the information matching degree between the first driving information and the target driving habit information; When the information matching degree is greater than or equal to a preset matching degree, adjusting the function settings of the vehicle based on the target driving habit information.

2. The method according to claim 1, characterized in that, The adjusting the function settings of the vehicle based on the target driving habit information includes: Removing the operation items corresponding to the first driving information from the operation item set corresponding to the target driving habit information to obtain an operation item set to be applied; Adjusting the function settings of the vehicle based on the operation item set to be applied.

3. The method according to claim 1, characterized in that, The collecting first driving information generated by a user operating a vehicle includes: Collecting in real time the operation items of the user for the vehicle to obtain an operation item sequence; Performing feature extraction on the operation item sequence to obtain the first driving information that is continuously updated over time.

4. The method according to claim 3, characterized in that, The operation items include at least one of in-vehicle environment data, driving state data, parking state data, and driving environment data.

5. The method according to claim 1, characterized in that, The method further includes: Obtaining the historical driving information corresponding to the user; wherein, the time span between the historical driving information and the first driving information satisfies a preset time period; Combining the historical driving information and the first driving information to obtain a driving information sequence; Performing feature extraction on the operation items of the driving information sequence to obtain to-be-updated driving habit information; Updating the target driving habit information based on the to-be-updated driving habit information.

6. The method according to claim 5, characterized in that, The performing feature extraction on the operation items of the driving information sequence to obtain to-be-updated driving habit information includes: Determining a plurality of driving habit score values based on the respective operation items of the driving information sequence; Obtaining the driving habit labels corresponding to the driving habit score values; Generating the to-be-updated driving habit information based on the driving habit labels.

7. The method according to claim 1, characterized in that, The adjusting the function settings of the vehicle based on the target driving habit information includes: Inputting the first driving information into a target neural network model to obtain a plurality of candidate operation items output by the target neural network model; Determining target operation items from the plurality of candidate operation items based on the target driving habit information; Adjusting the function settings of the vehicle based on the target operation items.

8. A vehicle control device, characterized in that, The device includes: A collecting module, configured to collect first driving information generated by a user operating a vehicle; A determining module, configured to determine target driving habit information from a driving habit information set based on the first driving information; A matching degree module, configured to determine the information matching degree between the first driving information and the target driving habit information; A setting module, configured to adjust the function settings of the vehicle based on the target driving habit information when the information matching degree is greater than or equal to a preset matching degree.

9. A vehicle controller, characterized in that, The vehicle controller includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the vehicle control method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that, When the instructions in the readable storage medium are executed by the processor of the vehicle controller, the vehicle controller is enabled to execute the vehicle control method according to any one of claims 1 to 7.

Images