Training method and device of model for controlling vehicle horn, vehicle and storage medium

Abstract

The embodiment of the invention discloses a training method and device of a model for controlling a vehicle horn, a vehicle and a storage medium. According to the scheme, vehicle data sent by a sound source vehicle are received, the vehicle data comprise horn data and driving data when the sound source vehicle is in a driving state, then evaluation data for the vehicle data are obtained from an evaluation vehicle, the distance between the evaluation vehicle and the sound source vehicle is within a preset distance range, and finally the evaluation data are sent to the sound source vehicle. And training a preset neural network model based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn. Therefore, the accuracy of vehicle horn adjustment can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a training method, device, vehicle, and storage medium for a model that controls a vehicle horn. Background Technology

[0002] Vehicle horns are an important component of vehicles, including automobiles. They play multiple roles in various scenarios, such as issuing warning signals and responding to vehicle control signals, in driving and anti-theft situations. However, with the development of transportation and the increasing number of vehicles, noise pollution from car horns has become increasingly serious, affecting customer experience and significantly impacting surrounding residents.

[0003] In related technologies, to address the noise pollution problem of car horns, vehicle horn control typically involves pre-setting fixed horn volumes for several fixed scenarios, then using cameras or location information to determine the surrounding environment and achieve adaptive horn control. However, the driving environment in these fixed scenarios is uncertain, leading to inaccuracies in horn adjustment. Summary of the Invention

[0004] This application provides a training method, apparatus, vehicle, and storage medium for a model of controlling a vehicle horn, which can improve the accuracy of vehicle horn adjustment.

[0005] This application provides a method for training a model to control a vehicle horn, applied to a cloud server. The method includes:

[0006] The system receives vehicle data sent by the sound source vehicle. The vehicle data includes horn data and driving data when the sound source vehicle is in motion. The horn data includes at least horn volume and horn frequency. The driving data includes at least the position, speed, gear, ambient volume and ambient audio of the sound source vehicle.

[0007] Evaluation data for the vehicle data is obtained from the evaluation vehicle, wherein the evaluation vehicle is a vehicle whose distance from the sound source vehicle is within a preset distance range;

[0008] The preset neural network model is trained based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn.

[0009] This application also provides a method for training a model that controls a vehicle horn, used for evaluating vehicles, the method comprising:

[0010] When the evaluation vehicle is in motion, vehicle data of the sound source vehicle is received from the cloud server.

[0011] In response to an evaluation event of the vehicle data, evaluation data is obtained;

[0012] The evaluation data is sent to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data.

[0013] Accordingly, this application also provides a training device for a model controlling a vehicle horn, applied to a cloud server, the device comprising:

[0014] The first receiving unit is used to receive vehicle data sent by the sound source vehicle. The vehicle data includes horn data and driving data when the sound source vehicle is in motion. The horn data includes at least horn volume and horn frequency. The driving data includes at least the position, speed, gear, ambient volume and ambient audio of the sound source vehicle.

[0015] The first acquisition unit is used to acquire evaluation data for the vehicle data from the evaluation vehicle, wherein the evaluation vehicle is a vehicle whose distance from the sound source vehicle is within a preset distance range;

[0016] The training unit is used to train a preset neural network model based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn.

[0017] Accordingly, this application also provides a training device for a model controlling a vehicle horn, used for evaluating vehicles, the device comprising:

[0018] The second receiving unit is used to receive vehicle data of the sound source vehicle sent by the cloud server when the evaluation vehicle is in a driving state.

[0019] The third acquisition unit is used to obtain evaluation data in response to an evaluation event of the vehicle data;

[0020] The second sending unit is used to send the evaluation data to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data.

[0021] Accordingly, this application also provides a vehicle horn control system, including:

[0022] The cloud server is used to train a preset neural network model based on the vehicle data of the sound source vehicle and the evaluation data of the evaluation vehicle, so as to obtain the target neural network model.

[0023] A sound source vehicle is used to collect vehicle data and send the vehicle data to a cloud service, so that the cloud server can train a target neural network model based on the vehicle data and the evaluation data, obtain the target neural network model, and control the horn through the target neural network model.

[0024] The vehicle evaluation tool is used to evaluate the vehicle data, obtain the evaluation data, and send the evaluation data to the cloud server.

[0025] Accordingly, this application also provides a cloud server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the training method for the model of controlling the vehicle horn as described above.

[0026] Accordingly, this application also provides a vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the training method for the model of controlling the vehicle horn as described above.

[0027] Accordingly, embodiments of this application also provide a computer-readable storage medium storing a computer program executable by a cloud server or a vehicle. When the computer program is run on the cloud server or the vehicle, it causes the cloud server or the vehicle to perform the steps of the training method for the model of controlling the vehicle horn as described above.

[0028] This solution receives vehicle data from the sound source vehicle, including horn data and driving data when the vehicle is in motion. Then, it obtains evaluation data from an evaluation vehicle, ensuring the distance between the evaluation vehicle and the sound source vehicle is within a preset range. Finally, based on the vehicle data and the evaluation data, it trains a preset neural network model to obtain a target neural network model for controlling the vehicle horn. This improves the accuracy of vehicle horn adjustment. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram illustrating an application scenario of a vehicle horn control system provided in an embodiment of this application.

[0031] Figure 2This is a schematic diagram of a vehicle horn control system provided in an embodiment of this application.

[0032] Figure 3 This is a schematic diagram of a network model for training a model that controls a vehicle horn, as provided in an embodiment of this application.

[0033] Figure 4 This is a flowchart illustrating a training method for a model that controls a vehicle horn, as provided in an embodiment of this application.

[0034] Figure 5 A flowchart illustrating another training method for a model of controlling a vehicle horn provided in this application embodiment.

[0035] Figure 6 A flowchart illustrating another training method for a model of controlling a vehicle horn provided in this application embodiment.

[0036] Figure 7 This is a structural block diagram of a training device for a model of controlling a vehicle horn, provided in an embodiment of this application.

[0037] Figure 8 A structural block diagram of a training device for another model of controlling a vehicle horn provided in an embodiment of this application.

[0038] Figure 9 A structural block diagram of a training device for another model of controlling a vehicle horn provided in an embodiment of this application.

[0039] Figure 10 This is a schematic diagram of the structure of a cloud server provided in an embodiment of this application.

[0040] Figure 11 This is a schematic diagram of the vehicle structure provided in an embodiment of this application. Detailed Implementation

[0041] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] To address the aforementioned issues, this application provides a training method, apparatus, vehicle, and storage medium for a model controlling a vehicle horn. Specifically, the training method for the vehicle horn model in this application can be performed using a vehicle or a cloud server. The vehicle can include automobiles, etc. The cloud server can be a standalone physical cloud server, a cloud server cluster or distributed system composed of multiple physical cloud servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0043] For example, please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario of a vehicle horn control system provided in an embodiment of this application. Figure 1 The vehicle horn control system includes a cloud server, a sound source vehicle, and an evaluation vehicle. The system may include a sound source vehicle, at least one cloud server, and at least one evaluation vehicle. The evaluation vehicle and the cloud server can communicate via a network; the sound source vehicle and the cloud server can also communicate via a network.

[0044] For further details, please refer to Figure 2 , Figure 3 This is a schematic diagram of a vehicle horn control system provided in an embodiment of this application.

[0045] The cloud server may include: a raw speaker database, a speaker evaluation and allocation library, a corrected speaker database, and an artificial neural network.

[0046] The system comprises several components: a raw horn database for receiving vehicle data uploaded by the sound source vehicle, including its location, speed, gear, ambient volume, ambient audio, horn volume, and horn frequency; a horn evaluation database for pairing other vehicles within 100 meters of the sound source vehicle, with successfully paired vehicles evaluating the sound source vehicle's horn; a corrected horn database for receiving evaluation data from evaluating vehicles, including its location, paired vehicle location, evaluation level, speed, gear, ambient volume, ambient audio, horn volume, and horn frequency; and Artificial Neural Networks (ANNs), also known as Neural Networks (NNs) or Connection Models, for processing the input data and outputting horn control information.

[0047] Artificial neural networks are mathematical models that mimic the behavioral characteristics of animal neural networks to perform distributed parallel information processing.

[0048] For example, please see Figure 3 , Figure 3 This is a schematic diagram of a network model for training a model that controls a vehicle horn, as provided in an embodiment of this application. Figure 3 The artificial neural network shown consists of an input layer, a hidden layer, and an output layer. The input layer consists of four-dimensional data, which can be vehicle speed, gear position, ambient volume, and audio. The output layer consists of two-dimensional data, which can be the comfortable horn volume and audio in the environment.

[0049] Specifically, the cloud server can receive vehicle data uploaded by the sound source vehicle through the original horn database, match the evaluation vehicle within a preset distance range of the sound source vehicle through the horn rating matching library, and then send the vehicle data to the evaluation vehicle; by correcting the horn database, it receives the evaluation data after the evaluation vehicle has been evaluated, and preprocesses the evaluation data, and trains the artificial neural network with the preprocessed data to obtain the target neural network model.

[0050] The sound source vehicle may include: MCU module (Microcontroller Unit), VCU module (Vehicle Control Unit), BCS module (Brake Control System), GPS module (Global Positioning System), sound sensor module, steering wheel switch module, horn control module, woofer module and tweeter module.

[0051] The MCU module refers to a chip-level computer that appropriately reduces the frequency and specifications of the Central Processing Unit (CPU) and integrates peripheral interfaces such as memory, timer, USB, A / D (Analog / Digital) conversion, and even LCD (Liquid Crystal Display) driver circuits onto a single chip, forming a chip-level computer that can perform different combinations of control for different applications.

[0052] The VCU module is the core electronic control unit for vehicle control decisions. It is typically only equipped in new energy vehicles and not required in traditional fuel vehicles. It outputs information such as gear position to the MCU module. The BCS module enables the vehicle to decelerate or even stop as required by the driver, providing speed information to the MCU module. The GPS module provides vehicle location information to the cloud server. The sound sensor collects the volume and audio of ambient sounds and outputs them to the MCU module. The steering wheel switch module outputs horn control commands to the MCU module. The horn control module receives horn volume and audio signals from the MCU module and determines whether to use the tweeter or woofer module based on the audio signal. The woofer module handles horn sounds in the 20-2000Hz range, while the tweeter module handles horn sounds in the 2000-20000Hz range.

[0053] Specifically, the sound source vehicle can collect vehicle data through various modules and send the vehicle data to the cloud service, so that the cloud server can train a target neural network model based on the vehicle data and the evaluation data, obtain the target neural network model, and control the horn through the target neural network model.

[0054] The vehicle evaluation system may include an IDC (Information and Entertainment Domain Controller) module. This module can display a horn evaluation form on the screen for the driver to rate, including horn volume and frequency. The evaluation levels can include five categories: '--', '-', '0', '+', and '++'.

[0055] The five rating levels are as follows: '--': Volume or audio needs to be significantly reduced; '-': Volume or audio needs to be reduced; '0': Volume or audio is appropriate; '+': Volume or audio needs to be increased; '++': Volume or audio needs to be significantly increased.

[0056] Specifically, the vehicle evaluation system can receive vehicle data sent by the cloud server, display the vehicle data, allow drivers to evaluate the vehicle data, obtain the evaluated data, and then send the evaluation data back to the cloud server.

[0057] The above Figure 2 The example given is merely a system architecture instance for implementing embodiments of the present invention, and embodiments of the present invention are not limited to those described above. Figure 2 The system structure shown is illustrated, and various embodiments of the present invention are proposed based on this system architecture.

[0058] For example, the training method for the vehicle horn control model provided in this application embodiment can be applied to a cloud server. The cloud server can receive vehicle data sent by the sound source vehicle. The vehicle data includes horn data and driving data when the sound source vehicle is in motion. The horn data includes at least the horn volume and horn frequency. The driving data includes at least the position, speed, gear, ambient volume, and ambient audio of the sound source vehicle. Evaluation data for the vehicle data is obtained from an evaluation vehicle, which is a vehicle whose distance from the sound source vehicle is within a preset distance range. Based on the vehicle data and the evaluation data, a preset neural network model is trained to obtain a target neural network model for controlling the vehicle horn.

[0059] For example, the training method for the model of controlling the vehicle horn provided in this application embodiment can be applied to a sound source vehicle. When the sound source vehicle is in motion, it can collect vehicle data, including driving data and horn data; send the vehicle data to a cloud server so that the cloud server can train a target neural network model based on the vehicle data and evaluation data of vehicle feedback; obtain the target neural network model from the cloud server; and use the target neural network model to output target horn control information based on the driving data.

[0060] For example, the training method for the model of controlling a vehicle horn provided in this application embodiment can be applied to evaluating vehicles. When the evaluation vehicle is in a driving state, it can receive vehicle data of the sound source vehicle sent by the cloud server; in response to the evaluation event of the vehicle data, it can obtain evaluation data; and send the evaluation data to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data.

[0061] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the preferred order of the embodiments.

[0062] This application provides a training method for a model that controls a vehicle horn. This method can be executed by a cloud server. This application uses the example of a training method for a model that controls a vehicle horn being executed by a cloud server to illustrate the method.

[0063] Please see Figure 4 , Figure 4 This is a flowchart illustrating a training method for a model controlling a vehicle horn, provided in an embodiment of this application. The specific process of this training method for the model controlling a vehicle horn can be as follows:

[0064] 101. Receive vehicle data sent by the sound source vehicle.

[0065] The sound source vehicle refers to a moving vehicle that requires adaptive horn control. Sound source vehicles can include new energy vehicles, etc. Vehicle data can at least include horn data and driving data when the sound source vehicle is in motion.

[0066] New energy vehicles refer to automobiles that use unconventional vehicle fuels as their power source, or use conventional vehicle fuels but employ new on-board power devices, resulting in vehicles with advanced technological principles and new technologies and structures. New energy vehicles can include hybrid vehicles and pure electric vehicles.

[0067] The driving state of a vehicle refers to its operating state under different conditions. For example, the driving state of a vehicle can include: starting, low-speed driving, high-speed driving, constant speed driving, acceleration mode, deceleration mode, or braking, etc.

[0068] The horn data may include the horn volume and horn frequency of the vehicle from which the sound originates; the driving data may include the vehicle's position, speed, gear, ambient volume, ambient audio, horn volume, and horn frequency.

[0069] In some embodiments, the position of the sound source vehicle refers to the real-time position of the sound source vehicle during driving; the vehicle speed refers to the real-time driving speed of the sound source vehicle during driving; the gear refers to the real-time gear of the sound source vehicle during driving; the ambient volume refers to the sound volume of the surrounding environment of the sound source vehicle during driving; the ambient audio refers to the sound audio of the surrounding environment of the sound source vehicle during driving; the horn volume refers to the sound volume of the horn played by the sound source vehicle during driving; and the horn frequency refers to the sound frequency of the horn played by the sound source vehicle during driving.

[0070] Volume refers to the level of sound intensity, measured in dB (decibels); sound frequency is measured in Hz (hertz).

[0071] The evaluation vehicle refers to the vehicle used to evaluate the vehicle data of the sound source vehicle. The evaluation vehicle may include vehicles that are within a preset distance range from the sound source vehicle.

[0072] In some embodiments, a cloud server can match the evaluation vehicle corresponding to the sound source vehicle. Based on the location of the sound source vehicle, vehicles within a preset distance range of that location can be matched as evaluation vehicles for which the vehicle data of the sound source vehicle needs to be evaluated.

[0073] For example, if the preset distance range is 100 meters, then based on the location of the sound source vehicle, vehicles within 100 meters of that location will be matched as evaluation vehicles.

[0074] 102. Obtain evaluation data for vehicle data from the evaluated vehicles.

[0075] Once a matching evaluation vehicle is identified, the vehicle data of the sound source vehicle can be sent to the evaluation vehicle, allowing the driver of the evaluation vehicle to evaluate the vehicle data.

[0076] In some embodiments, the step "obtaining evaluation data for vehicle data from the evaluated vehicle" includes:

[0077] Vehicle data is sent to the evaluation vehicle so that the driver of the evaluation vehicle can evaluate the vehicle data and obtain evaluation data.

[0078] Receive evaluation data sent by the vehicles being evaluated.

[0079] Specifically, the system sends vehicle data of the sound source vehicle to the evaluation vehicle that has been successfully matched with the sound source vehicle. The driver of the evaluation vehicle then evaluates the horn signal of the sound source vehicle based on this data, and feeds the evaluation result back to the cloud server. The cloud server can then obtain the evaluation data corresponding to the evaluation vehicle.

[0080] 103. Based on vehicle data and evaluation data, train the preset neural network model to obtain the target neural network model for controlling the vehicle horn.

[0081] Among them, the preset neural network model refers to Figure 2 Artificial neural networks in [the context of] ...

[0082] In some embodiments, to improve the efficiency of vehicle horn control, the step of "training a preset neural network model based on vehicle data and evaluation data to obtain a target neural network model for controlling the vehicle horn" may include the following operations:

[0083] Obtain the location and speed of the vehicle being evaluated.

[0084] The location of the evaluated vehicle, the speed of the evaluated vehicle, and the evaluation data are added to the vehicle data to obtain the corrected data;

[0085] The corrected data is preprocessed to obtain the processed data.

[0086] The pre-defined neural network model is trained based on the processed data to obtain the target neural network model.

[0087] The location of the evaluated vehicle refers to its position when it is in motion, and the speed of the evaluated vehicle refers to its speed when it is in motion.

[0088] Specifically, the location, speed, and evaluation data of the evaluated vehicle are added to the vehicle data to obtain the corrected data, which includes: vehicle data, the location of the evaluated vehicle, the speed of the evaluated vehicle, and the evaluation data.

[0089] In some embodiments, the horn data in the vehicle data may include at least: horn volume and horn frequency; the driving data in the vehicle data may include at least: the location of the sound source vehicle, the speed and gear of the sound source vehicle, and the ambient volume and ambient audio of the sound source vehicle; and the evaluation data for the vehicle may include at least the evaluation level. Therefore, the step "preprocessing the corrected data to obtain processed data" may include the following operations:

[0090] Calculate the target distance between the sound source vehicle and the evaluation vehicle based on the location of the sound source vehicle and the location of the evaluation vehicle.

[0091] Obtain the rating coefficient corresponding to the rating level;

[0092] The first speaker volume is calculated based on the grade coefficient, speaker volume, and target distance;

[0093] The first horn frequency is calculated based on the grade coefficient, horn frequency, vehicle speed corresponding to the sound source vehicle, and vehicle speed corresponding to the evaluation vehicle.

[0094] For example, the location of the sound source vehicle (i.e., the location corresponding to the sound source vehicle) can be P1, and the location of the evaluation vehicle (i.e., the location corresponding to the evaluation vehicle) can be P2. Calculate the distance between P1 and P2 to obtain r, and then determine the target distance between the sound source vehicle and the evaluation vehicle as r.

[0095] In this embodiment of the application, the evaluation level may include 5 categories, namely: '-

[0096] -', '-', '0', '+', '++'. Among them, '--' corresponds to the rank coefficient μ. -- =0.7; the rank coefficient μ corresponding to '-' - =0.9; the grade coefficient μ0 corresponding to '0' is 1; the grade coefficient μ0 corresponding to '+' is 0.9. + =1.1; '++' corresponds to the grade coefficient

[0097] μ ++ =1.3.

[0098] Wherein, the first horn volume is the horn volume that the evaluated vehicle considers comfortable, and the first horn frequency is the horn frequency that the evaluated vehicle considers comfortable.

[0099] The first speaker volume is calculated based on the grade coefficient, speaker volume, and target distance, and can be calculated according to the first formula. Specifically, the first formula is as follows:

[0100]

[0101] Among them, L 评价车辆 This is the first horn volume, which is the horn volume that the vehicle considers comfortable; L 声源车辆 The volume of the horn emitted by the vehicle from which the sound originates; μ 评价等级 is the rating coefficient; r is the distance between the sound source vehicle and the evaluation vehicle.

[0102] The first horn frequency is calculated based on the grade coefficient, horn frequency, the speed of the vehicle corresponding to the sound source, and the speed of the vehicle corresponding to the evaluation. This can be calculated using the second formula. Specifically, the second formula is as follows:

[0103]

[0104] Among them, f 评价车辆 This is the first horn frequency, which is also the horn frequency used to evaluate the vehicle's comfort level; f 声源车辆 The frequency of the horn emitted by the vehicle is the sound source; v refers to the speed of sound in the air; v 声源车辆 This refers to the speed of the vehicle from which the sound originates; v 评价车辆 This refers to evaluating the vehicle's speed.

[0105] In some embodiments, the step "training a preset neural network model based on the processed data to obtain a target neural network model" may include the following operations:

[0106] Based on the vehicle speed, gear, ambient volume, ambient audio, first horn volume, and first horn frequency corresponding to the sound source vehicle, the model parameters of the preset neural network model are adjusted to obtain the target neural network model.

[0107] In this embodiment, the input to the preset neural network model is four-dimensional data, and the output is two-dimensional data. The input four-dimensional data may include: vehicle speed, gear position, ambient volume, and ambient audio, and the output two-dimensional data may include horn volume and horn frequency.

[0108] The training process of the preset neural network model may include: First, inputting the vehicle speed, gear, ambient volume, and ambient audio of the sound source vehicle into the preset neural network model. The preset neural network model calculates a horn volume and horn frequency based on the vehicle speed, gear, ambient volume, and ambient audio. Then, the calculated horn volume and horn frequency are compared with the first horn volume and first horn frequency. The parameters of the preset neural network model are adjusted according to the comparison results to obtain the trained neural network model, which serves as the target neural network model.

[0109] The target neural network model can receive inputs such as vehicle speed, gear, ambient volume, and ambient audio, process them, and output the corresponding horn volume and horn frequency.

[0110] In some embodiments, after the neural network model is trained, the target neural network model can be synchronously updated to the sound source vehicle so that the sound source vehicle can adaptively control the horn through the target neural network model.

[0111] This application discloses a training method for a model controlling a vehicle horn. The method includes: receiving vehicle data sent by a sound source vehicle, the vehicle data including horn data and driving data when the sound source vehicle is in motion, the horn data including at least horn volume and horn frequency, and the driving data including at least the location, speed, gear, ambient volume, and ambient audio of the sound source vehicle; obtaining evaluation data for the vehicle data from an evaluation vehicle, the evaluation vehicle being a vehicle whose distance from the sound source vehicle is within a preset distance range; and training a preset neural network model based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn. This achieves real-time data acquisition, real-time driver evaluation, and real-time network model training, thereby significantly increasing the number of training samples for the model. Furthermore, as the number of horn samples increases, the horn output becomes more accurate.

[0112] This application provides another method for training a model that controls a vehicle horn. This method can be executed by a sound source vehicle. This application uses the example of a method for training a model that controls a vehicle horn being executed by a sound source vehicle to illustrate the method.

[0113] Please see Figure 5 , Figure 5 This is a flowchart illustrating another method for training a model to control a vehicle horn, provided in an embodiment of this application. The specific process of this method for training the model to control a vehicle horn is as follows:

[0114] 201. Collect vehicle data of the sound source vehicle while it is in motion.

[0115] In this embodiment of the application, when the sound source vehicle is in motion, the vehicle data of the sound source vehicle can be collected in real time. The vehicle data may include the driving data and horn data of the sound source vehicle.

[0116] The driving state of the sound source vehicle refers to its operating state under different conditions. For example, the driving state of the sound source vehicle may include: starting, low-speed driving, high-speed driving, constant speed driving, acceleration, deceleration, or braking.

[0117] The driving data may include the location of the sound source vehicle (i.e., the real-time location of the sound source vehicle during driving), the speed of the sound source vehicle (i.e., the real-time speed of the sound source vehicle during driving), the gear (i.e., the real-time gear of the sound source vehicle during driving), the horn volume (the real-time gear of the sound source vehicle during driving), and the horn frequency (the audio of the sound source vehicle playing the horn during driving).

[0118] In some embodiments, the sound source vehicle may include a control module and sensors, then the step "collecting vehicle data of the sound source vehicle" may include the following operations:

[0119] The control module obtains the vehicle speed, position, gear, horn volume and horn frequency of the sound source vehicle.

[0120] The sensor module acquires the ambient volume and ambient audio corresponding to the sound source vehicle.

[0121] The control module may specifically include: a GPS module, a BCS module, a VCU module, and an MCU module. The control module obtains information about the sound source vehicle, such as its speed, location, gear, horn volume, and horn frequency. This information may include the following:

[0122] The GPS module obtains the location of the vehicle from which the sound source is located; the BCS module obtains the vehicle speed; the VCU module obtains the gear position; and the MCU module obtains the horn volume and horn frequency.

[0123] The sensors may include sound sensors. The sensor module acquires the ambient volume and ambient audio corresponding to the sound source vehicle, and may include the following:

[0124] Ambient volume and ambient audio are acquired through sound sensors.

[0125] In some embodiments, the vehicle data of the sound source vehicle can be collected at the same time. For example, the vehicle speed, position, gear, horn volume and frequency, ambient volume and ambient audio of the sound source vehicle can be collected at the same time.

[0126] 202. Send vehicle data to the cloud server so that the cloud server can train the target neural network model based on the vehicle data and the evaluation data of the vehicle feedback.

[0127] Furthermore, the sound source vehicle can send the collected vehicle data to the cloud server, so that the cloud server can train a preset neural network model based on the vehicle data and the evaluation data fed back by the evaluation vehicle to obtain the target neural network model. For details, please refer to the description of the above embodiments, which will not be repeated here.

[0128] In some embodiments, the sound source vehicle can be matched with the corresponding evaluation vehicle. Then, while sending vehicle data to the cloud server, the information of the matched evaluation vehicle can be sent to the cloud server so that the cloud server can send the vehicle data of the sound source vehicle to the evaluation vehicle for evaluation.

[0129] Among them, the sound source vehicle can match vehicles within a preset distance range of its own location as evaluation vehicles for which the vehicle data of the sound source vehicle needs to be evaluated.

[0130] For example, if the preset distance range is 100 meters, the sound source vehicle can match vehicles within 100 meters of its own location as the evaluation vehicle.

[0131] 203. Obtain the target neural network model from the cloud server.

[0132] After training the target neural network model, the cloud server can synchronously update the target neural network model to the source vehicle. For example, the code of the target neural network model can be burned into the MCU module of the source vehicle, so that the source vehicle can synchronously obtain the trained target neural network model.

[0133] 204. The target neural network model is used to output target horn control information based on driving data.

[0134] In some embodiments, the driving data may include at least: the vehicle speed, gear, ambient volume, and ambient audio of the sound source vehicle. To obtain accurate horn control information for the sound source vehicle, the step "outputting target horn control information based on the driving data using a target neural network model" may include the following operations:

[0135] Input the vehicle speed, gear, ambient volume, and ambient audio of the sound source vehicle into the target neural network model;

[0136] Based on the target neural network model, the vehicle speed, gear, ambient volume and ambient audio of the sound source vehicle are processed to output the target horn volume and target horn frequency.

[0137] Based on the target speaker volume and target speaker frequency, the target speaker control information is obtained.

[0138] Specifically, the vehicle speed, gear, ambient volume, and ambient noise level of the sound source vehicle can be input into the target neural network model. The target neural network model processes the input data and outputs the target horn volume and target horn frequency.

[0139] The target horn volume and target horn frequency refer to the appropriate horn volume and frequency corresponding to the vehicle speed, gear, ambient volume, and ambient audio of the input sound source vehicle. Therefore, the target horn volume and target horn frequency can be used as the target horn control information for the sound source vehicle.

[0140] In some embodiments, in order to control the vehicle horn based on environmental information about the location of the sound source vehicle, the method may further include the following steps:

[0141] Receive the horn playback command and determine the target horn module from multiple horn modules of the sound source vehicle according to the target horn frequency;

[0142] The target speaker module plays music based on the target speaker volume and frequency.

[0143] The horn playback command instructs the horn to play. This horn playback command can be triggered by the driver of the vehicle from which the sound originates, for example, by pressing the horn switch. Alternatively, the horn playback command can be triggered in other ways, which will not be listed here.

[0144] In this embodiment, the sound source vehicle may include multiple horn modules, with different horn modules used to play different horn frequencies.

[0145] For example, a sound source vehicle may include a tweeter module and a woofer module. The woofer module is used to process horn sounds in the range of approximately 20-2000 Hz, while the tweeter module is used to process horn sounds in the range of approximately 2000-20000 Hz.

[0146] The process of determining the target horn module from multiple horn modules of the sound source vehicle based on the target horn frequency may include: selecting a horn module from the multiple horn modules that is used to process the target horn frequency as the target horn module.

[0147] For example, if the target speaker frequency is 200Hz, then a subwoofer module can be selected as the target speaker module, and the subwoofer module can then play music based on the target speaker volume and frequency.

[0148] This application discloses a training method for a model controlling a vehicle horn. The method includes: collecting vehicle data (including driving data and horn data) of the vehicle while it is in motion; sending the vehicle data to a cloud server so that the cloud server can train a target neural network model based on the vehicle data and evaluation data from vehicle feedback; obtaining the target neural network model from the cloud server; and using the target neural network model to output target horn control information based on the driving data. By combining factors such as the surrounding environment, vehicle speed, and gear position of the vehicle, appropriate horn volume and frequency can be output, thus improving horn control effectiveness.

[0149] This application provides another method for training a model that controls a vehicle horn. This method can be performed by an evaluation vehicle. This application uses the example of a method for training a model that controls a vehicle horn being performed by an evaluation vehicle to illustrate the method.

[0150] Please see Figure 6 , Figure 6 This is a flowchart illustrating another method for training a model to control a vehicle horn, provided in an embodiment of this application. The specific process of this method for training the model to control a vehicle horn is as follows:

[0151] 301. When evaluating a vehicle in motion, receive vehicle data of the sound source vehicle sent by the cloud server.

[0152] In this embodiment of the application, when the evaluation vehicle is in motion, it can receive vehicle data of the corresponding sound source vehicle sent by the cloud server.

[0153] The vehicle data may include the location, speed, gear, ambient volume, ambient audio, horn volume, and horn frequency of the vehicle from which the sound originates.

[0154] 302. In response to evaluation events related to vehicle data, obtain evaluation data.

[0155] The vehicles being evaluated may include in-vehicle display devices, such as displays.

[0156] After receiving vehicle data from the source vehicle, the IDC module can generate a horn evaluation form based on the vehicle data. The horn evaluation form is then displayed on the in-vehicle display device, allowing the driver of the vehicle being evaluated to post their evaluation in the horn evaluation form. For example, the driver can enter an evaluation level in the evaluation form as evaluation data.

[0157] Among them, the evaluation event of vehicle data refers to the driver's evaluation operation on the vehicle data.

[0158] 303. Send evaluation data to the cloud server so that the cloud server can train the target neural network model based on the evaluation data and vehicle data.

[0159] Furthermore, after the driver evaluation of the vehicle is completed, the evaluation data can be sent to the cloud server, which can then train a preset neural network model based on the evaluation data and the vehicle data of the sound source vehicle, thereby obtaining the target neural network model.

[0160] This application discloses a training method for a model controlling a vehicle horn. The method includes: receiving vehicle data of the sound source vehicle sent by a cloud server when the vehicle is in motion; obtaining evaluation data in response to an evaluation event of the vehicle data; and sending the evaluation data to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data. Therefore, by collecting evaluation data of the vehicle in real time to train the neural network model for horn control, the efficiency of vehicle horn control can be improved.

[0161] To facilitate better implementation of the training method for the vehicle horn control model provided in this application embodiment, this application embodiment also provides a training device for the vehicle horn control model based on the above-described training method. The meanings of the terms used are the same as in the above-described training method for the vehicle horn control model, and specific implementation details can be found in the description of the method embodiment.

[0162] Please see Figure 7 , Figure 7 A structural block diagram of a training device for a model of controlling a vehicle horn, provided in an embodiment of this application, is applied to a cloud server. The device includes:

[0163] The first receiving unit 401 is used to receive vehicle data sent by the sound source vehicle. The vehicle data includes horn data and driving data when the sound source vehicle is in motion. The horn data includes at least horn volume and horn frequency. The driving data includes at least the position, speed, gear, ambient volume and ambient audio of the sound source vehicle.

[0164] The first acquisition unit 402 is used to acquire evaluation data for the vehicle data from the evaluation vehicle, wherein the evaluation vehicle is a vehicle whose distance from the sound source vehicle is within a preset distance range;

[0165] The training unit 403 is used to train a preset neural network model based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn.

[0166] In some embodiments, the training unit 404 may include:

[0167] The acquisition subunit is used to acquire the position and speed of the evaluation vehicle corresponding to the evaluation vehicle.

[0168] A subunit is added to add the location of the evaluated vehicle, the speed of the evaluated vehicle, and the evaluation data to the vehicle data to obtain the corrected data.

[0169] The processing subunit is used to preprocess the corrected data to obtain processed data;

[0170] The training subunit is used to train the preset neural network model based on the processed data to obtain the target neural network model.

[0171] In some embodiments, the evaluation data includes at least an evaluation level, and the processing subunit may specifically be used for:

[0172] Calculate the target distance between the sound source vehicle and the evaluation vehicle based on the location corresponding to the sound source vehicle and the location corresponding to the evaluation vehicle;

[0173] Obtain the grade coefficient corresponding to the evaluation grade;

[0174] The first speaker volume is calculated based on the grade coefficient, the speaker volume, and the target distance;

[0175] The first horn frequency is calculated based on the grade coefficient, the horn frequency, the vehicle speed corresponding to the sound source vehicle, and the vehicle speed corresponding to the evaluation vehicle.

[0176] In some embodiments, the training subunit can be specifically used for:

[0177] The input to the preset neural network model is obtained based on the vehicle speed corresponding to the sound source vehicle, the gear position, the ambient volume, and the ambient audio.

[0178] The output of the preset neural network model is obtained based on the volume and frequency of the first speaker.

[0179] Based on the input and the output, the model parameters of the preset neural network model are adjusted to obtain the target neural network model.

[0180] In some embodiments, the first acquisition unit 402 may include:

[0181] The first sending subunit is used to send the vehicle data to the evaluation vehicle so that the driver of the evaluation vehicle can evaluate the vehicle data and obtain the evaluation data.

[0182] The first receiving subunit is used to receive the evaluation data sent by the evaluation vehicle.

[0183] This application discloses a training device for a model controlling a vehicle horn. A first receiving unit 401 receives vehicle data sent by a sound source vehicle. The vehicle data includes horn data and driving data when the sound source vehicle is in motion. The horn data includes at least horn volume and horn frequency. The driving data includes at least the location, speed, gear, ambient volume, and ambient audio of the sound source vehicle. A first acquisition unit 402 acquires evaluation data for the vehicle data from an evaluation vehicle located within a preset distance range from the sound source vehicle. A training unit 403 trains a preset neural network model based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn. This achieves real-time data acquisition, real-time driver evaluation, and real-time network model training, significantly increasing the number of training samples. Furthermore, as the number of horn samples increases, the horn output becomes more accurate.

[0184] This application also provides a training device for a vehicle horn control model based on the above-described training method for the vehicle horn control model.

[0185] Please see Figure 8 , Figure 8 A structural block diagram of another training device for controlling a vehicle horn model provided in this application embodiment, applied to a sound source vehicle, the device comprising:

[0186] The acquisition unit 501 is used to acquire vehicle data of the sound source vehicle when the sound source vehicle is in motion, the vehicle data including driving data and horn data.

[0187] The first sending unit 502 is used to send the vehicle data to the cloud server so that the cloud server can train a target neural network model based on the vehicle data and the evaluation data of the vehicle feedback.

[0188] The second acquisition unit 503 is used to acquire the target neural network model from the cloud server;

[0189] The output unit 504 is used to output target horn control information based on the driving data using the target neural network model.

[0190] In some embodiments, the driving data includes at least: the vehicle speed, gear, ambient volume, and ambient audio of the sound source vehicle, and the output unit 504 may include:

[0191] An input subunit is used to input the vehicle speed, gear, ambient volume, and ambient audio of the sound source vehicle into the target neural network model.

[0192] The second processing subunit is used to process the vehicle speed, gear, ambient volume and ambient audio of the sound source vehicle based on the target neural network model, and output the target horn volume and target horn frequency.

[0193] A determination subunit is used to obtain the target speaker control information based on the target speaker volume and the target speaker frequency.

[0194] In some embodiments, the device may further include:

[0195] The third receiving unit is used to receive the horn playback command and determine the target horn module from the multiple horn modules of the sound source vehicle according to the target horn frequency.

[0196] The playback unit is used to play music through the target speaker module according to the target speaker volume and the target speaker frequency.

[0197] In some embodiments, the sound source vehicle includes a control module and sensors, and the acquisition unit 501 may include:

[0198] The first acquisition subunit is used to acquire, through the control module, the vehicle speed, position, gear, horn volume and horn frequency of the sound source vehicle.

[0199] The second acquisition subunit is used to acquire the ambient volume and ambient audio corresponding to the sound source vehicle through the sensor module.

[0200] This application discloses a training device for a model controlling a vehicle horn. A data acquisition unit 501 collects vehicle data, including driving data and horn data, from the sound source vehicle while it is in motion. A first sending unit 502 sends the vehicle data to a cloud server, enabling the cloud server to train a target neural network model based on the vehicle data and evaluation data from vehicle feedback. A second acquisition unit 503 retrieves the target neural network model from the cloud server. An output unit 504 uses the target neural network model to output target horn control information based on the driving data. By combining factors such as the surrounding environment, speed, and gear of the sound source vehicle, appropriate horn volume and frequency are output, improving horn control effectiveness.

[0201] This application also provides a training device for a vehicle horn control model based on the above-described training method for the vehicle horn control model.

[0202] Please see Figure 9 , Figure 9 A structural block diagram of a training device for a model of controlling a vehicle horn, provided in an embodiment of this application, is used for evaluating vehicles. The device includes:

[0203] The second receiving unit 601 is used to receive vehicle data of the sound source vehicle sent by the cloud server when the evaluation vehicle is in a driving state.

[0204] The third acquisition unit 602 is used to acquire evaluation data in response to an evaluation event of the vehicle data;

[0205] The second sending unit 603 is used to send the evaluation data to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data.

[0206] This application discloses a training device for a model controlling a vehicle horn. A second receiving unit 601 receives vehicle data of the sound source vehicle sent by a cloud server when the evaluated vehicle is in motion. A third acquiring unit 602 obtains evaluation data in response to an evaluation event of the vehicle data. A second sending unit 603 sends the evaluation data to the cloud server, enabling the cloud server to train a target neural network model based on the evaluation data and the vehicle data. Thus, by collecting evaluation data from the evaluated vehicle in real time to train the neural network model for horn control, the efficiency of vehicle horn control can be improved.

[0207] This application also provides a cloud server, such as... Figure 10 As shown, Figure 10This is a schematic diagram of the structure of a cloud server provided in an embodiment of this application. Specifically, it illustrates the structure of the cloud server involved in this embodiment:

[0208] The cloud server may include components such as a processor 701 with one or more processing cores, a memory 702 with one or more computer-readable storage media, and a power supply 703. Those skilled in the art will understand that... Figure 10 The cloud server architecture shown does not constitute a limitation on cloud servers and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. Wherein:

[0209] The processor 701 is the control center of the cloud server. It connects to various parts of the cloud server via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 702, and by calling data stored in the memory 702, it performs various functions and processes data of the cloud server, thereby providing overall monitoring of the cloud server. Optionally, the processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 701.

[0210] The memory 702 can be used to store software programs and modules. The processor 701 executes various functional applications and data processing by running the software programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the cloud server, etc. In addition, the memory 702 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 702 may also include a memory controller to provide the processor 701 with access to the memory 702.

[0211] The cloud server also includes a power supply 703 that supplies power to the various components. Preferably, the power supply 703 can be logically connected to the processor 701 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 703 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0212] Although not shown, the cloud server may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 701 in the cloud server loads the executable files corresponding to the processes of one or more applications into the memory 702 according to the following instructions, and the processor 701 runs the applications stored in the memory 702 to realize various functions, as follows:

[0213] The system receives vehicle data sent by the sound source vehicle. The vehicle data includes horn data and driving data when the sound source vehicle is in motion. The horn data includes at least the horn volume and horn frequency. The driving data includes at least the position, speed, gear, ambient volume, and ambient audio of the sound source vehicle. The system obtains evaluation data for the vehicle data from an evaluation vehicle, which is a vehicle whose distance from the sound source vehicle is within a preset distance range. Based on the vehicle data and the evaluation data, the system trains a preset neural network model to obtain a target neural network model for controlling the vehicle horn.

[0214] This application embodiment receives vehicle data sent by a sound source vehicle, including horn data and driving data when the sound source vehicle is in motion. Then, evaluation data based on the vehicle data is obtained from an evaluation vehicle. Finally, a preset neural network model is trained based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn. This improves the accuracy of vehicle horn adjustment.

[0215] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0216] As can be seen from the above, the cloud server device in this embodiment can implement the training method steps of the model for controlling vehicle horns, which can improve the accuracy of vehicle horn adjustment.

[0217] Accordingly, this application also provides a vehicle. For example... Figure 11 As shown, Figure 11 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle 800 includes a processor 801 with one or more processing cores, a memory 802 with one or more computer-readable storage media, and a computer program stored on the memory 802 and executable on the processor. The processor 801 is electrically connected to the memory 802. Those skilled in the art will understand that... Figure 11 The vehicle structure shown does not constitute a limitation on the vehicle and may include structures larger than those shown. Figure 11 It can show more or fewer parts, or combine certain parts, or arrange different parts.

[0218] The processor 801 is the control center of the vehicle 800. It connects various parts of the vehicle 800 through various interfaces and lines. By running or loading software programs and / or modules stored in the memory 802, and calling data stored in the memory 802, it executes various functions of the vehicle 800 and processes data, thereby performing overall monitoring of the vehicle 800.

[0219] In this embodiment, the processor 801 in the vehicle 800 loads the instructions corresponding to the processes of one or more application programs into the memory 802 according to the following steps, and the processor 801 runs the application programs stored in the memory 802 to realize various functions:

[0220] When the vehicle from which the sound source is located is in motion, vehicle data of the vehicle is collected, including driving data and horn data.

[0221] Send vehicle data to the cloud server so that the cloud server can train the target neural network model based on the vehicle data and the evaluation data of the vehicle feedback.

[0222] Obtain the target neural network model from the cloud server;

[0223] The target neural network model is used to output target horn control information based on driving data.

[0224] This embodiment of the application collects vehicle data (including driving data and horn data) of the sound source vehicle while it is in motion; sends the vehicle data to a cloud server so that the cloud server can train a target neural network model based on the vehicle data and evaluation data of the vehicle's feedback; retrieves the target neural network model from the cloud server; and uses the target neural network model to output target horn control information based on the driving data. In this way, by combining factors such as the surrounding environment, vehicle speed, and gear position of the sound source vehicle, appropriate horn volume and frequency can be output, thereby improving the horn control effect.

[0225] or,

[0226] When evaluating whether a vehicle is in motion, the system receives vehicle data from the sound source vehicle sent by the cloud server.

[0227] In response to evaluation events involving vehicle data, evaluation data is obtained;

[0228] The evaluation data is sent to the cloud server so that the cloud server can train the target neural network model based on the evaluation data and vehicle data.

[0229] This application embodiment receives vehicle data of the sound source vehicle from a cloud server when the evaluation vehicle is in motion; in response to an evaluation event of the vehicle data, it obtains evaluation data; and sends the evaluation data to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data. Therefore, by collecting evaluation data of the evaluation vehicle in real time to train a neural network model for horn control, the efficiency of vehicle horn control can be improved.

[0230] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0231] Optional, such as Figure 11 As shown, the vehicle 800 may further include a display 803 and an input unit 804. The processor 801 is electrically connected to both the display 803 and the input unit 804. Those skilled in the art will understand that... Figure 11 The vehicle structure shown does not constitute a limitation on the vehicle and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0232] The display 803 can be used to display a graphical user interface (GUI) and receive operation commands generated by the user interacting with the GUI. The display 803 may include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user, as well as various GUIs of the vehicle. These GUIs can be composed of graphics, guidance information, icons, videos, and any combination thereof. Optionally, the display panel can be configured using a liquid crystal display (LCD), an organic light-emitting diode (OLED), or other similar devices. The touch panel can be used to collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel), generate corresponding operation commands, and execute the corresponding program. Optionally, the touch panel may include a touch detection device and a touch controller.

[0233] The touch detection device detects the user's touch location and the signal generated by the touch operation, transmitting the signal to the touch controller. The touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 801. It can also receive and execute commands from the processor 801. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it transmits the information to the processor 801 to determine the type of touch event. Subsequently, the processor 801 provides corresponding visual output on the display panel based on the type of touch event. In this embodiment, the touch panel and display panel can be integrated into the display 803 to achieve input and output functions. However, in some embodiments, the touch panel and display panel can be implemented as two independent components to achieve input and output functions. That is, the display 803 can also be used as part of the input unit 804 to achieve input functions.

[0234] The input unit 804 can be used to receive input numbers, characters, or user characteristic information (such as fingerprints, iris, facial information, etc.), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

[0235] In some embodiments, the vehicle may also include radio frequency circuitry, which can be used to transmit and receive radio frequency signals to establish wireless communication with network devices or other vehicles, and to transmit and receive signals with network devices or other vehicles.

[0236] In some embodiments, the vehicle may further include an audio circuit that provides an audio interface between the user and the vehicle horn control device via a speaker and a microphone. The audio circuit converts received audio data into electrical signals, transmits them to the speaker, and the speaker converts them into sound signals for output. Conversely, the microphone converts collected sound signals into electrical signals, which are then received by the audio circuit, converted back into audio data, processed by the audio data output processor 801, and transmitted via radio frequency circuitry to, for example, another vehicle horn control device, or output to memory 802 for further processing. The audio circuit may also include an earphone jack to provide communication between a peripheral headset and the vehicle horn control device.

[0237] although Figure 11 Figure 11 As not shown in the diagram, vehicle 800 may also include cameras, sensors, wireless fidelity modules, Bluetooth modules, etc., which will not be elaborated here.

[0238] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0239] As can be seen from the above, the vehicle provided in this embodiment can collect vehicle data of the sound source vehicle when the sound source vehicle is in motion. The vehicle data includes driving data and horn data. The vehicle data is sent to the cloud server so that the cloud server can train a target neural network model based on the vehicle data and the evaluation data of the vehicle feedback. The target neural network model is obtained from the cloud server. The target neural network model is used to output target horn control information based on the driving data.

[0240] or,

[0241] When evaluating a vehicle in motion, the system receives vehicle data from the sound source vehicle sent by the cloud server; in response to evaluation events of the vehicle data, it obtains evaluation data; and sends the evaluation data to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data.

[0242] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0243] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of computer programs that can be loaded by a processor to execute steps in any of the training methods for controlling a vehicle horn model provided in embodiments of this application. For example, the computer program can execute the following steps:

[0244] Receive vehicle data sent by the sound source vehicle. The vehicle data includes horn data and driving data when the sound source vehicle is in motion. The horn data includes at least the horn volume and horn frequency. The driving data includes at least the position, speed, gear, ambient volume and ambient audio of the sound source vehicle.

[0245] Evaluation data is obtained from the evaluation vehicle, which is a vehicle whose distance from the sound source vehicle is within a preset distance range.

[0246] The preset neural network model is trained based on vehicle data and evaluation data to obtain the target neural network model for controlling the vehicle horn.

[0247] This embodiment of the application receives vehicle data sent by a sound source vehicle, including horn data and driving data when the sound source vehicle is in motion. Then, evaluation data based on the vehicle data is obtained from an evaluation vehicle, wherein the distance between the evaluation vehicle and the sound source vehicle is within a preset distance range. Finally, a preset neural network model is trained based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn. This improves the accuracy of vehicle horn adjustment.

[0248] or,

[0249] When the vehicle from which the sound source is located is in motion, vehicle data of the vehicle is collected, including driving data and horn data.

[0250] Send vehicle data to the cloud server so that the cloud server can train the target neural network model based on the vehicle data and the evaluation data of the vehicle feedback.

[0251] Obtain the target neural network model from the cloud server;

[0252] The target neural network model is used to output target horn control information based on driving data.

[0253] This embodiment of the application collects vehicle data (including driving data and horn data) of the sound source vehicle while it is in motion; sends the vehicle data to a cloud server so that the cloud server can train a target neural network model based on the vehicle data and evaluation data of the vehicle's feedback; retrieves the target neural network model from the cloud server; and uses the target neural network model to output target horn control information based on the driving data. In this way, by combining factors such as the surrounding environment, vehicle speed, and gear position of the sound source vehicle, appropriate horn volume and frequency can be output, thereby improving the horn control effect.

[0254] or,

[0255] When evaluating whether a vehicle is in motion, the system receives vehicle data from the sound source vehicle sent by the cloud server.

[0256] In response to evaluation events involving vehicle data, evaluation data is obtained;

[0257] The evaluation data is sent to the cloud server so that the cloud server can train the target neural network model based on the evaluation data and vehicle data.

[0258] This application embodiment receives vehicle data of the sound source vehicle from a cloud server when the evaluation vehicle is in motion; in response to an evaluation event of the vehicle data, it obtains evaluation data; and sends the evaluation data to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data. Therefore, by collecting evaluation data of the evaluation vehicle in real time to train a neural network model for horn control, the efficiency of vehicle horn control can be improved.

[0259] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0260] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0261] Since the computer program stored in the storage medium can execute the steps in any of the training methods for controlling a vehicle horn model provided in the embodiments of this application, the beneficial effects that any of the training methods for controlling a vehicle horn model provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0262] The above provides a detailed description of the training method, apparatus, vehicle, and storage medium for a model of controlling a vehicle horn provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A training method for a model controlling a vehicle horn, characterized in that, Applied to cloud servers, the method includes: The system receives vehicle data sent by the sound source vehicle. The vehicle data includes horn data and driving data when the sound source vehicle is in motion. The horn data includes at least horn volume and horn frequency. The driving data includes at least the position, speed, gear, ambient volume and ambient audio of the sound source vehicle. Evaluation data for the vehicle data is obtained from the evaluation vehicle, wherein the evaluation vehicle is a vehicle whose distance from the sound source vehicle is within a preset distance range; The preset neural network model is trained based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn.

2. The method according to claim 1, characterized in that, The step of training a preset neural network model based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn includes: Obtain the location and speed of the evaluated vehicle; The location and speed of the evaluated vehicle, along with the evaluation data, are added to the vehicle data to obtain the corrected data. The corrected data is preprocessed to obtain processed data; The preset neural network model is trained based on the processed data to obtain the target neural network model.

3. The method according to claim 2, characterized in that, The evaluation data includes at least the evaluation level; The preprocessing of the corrected data to obtain processed data includes: Calculate the target distance between the sound source vehicle and the evaluation vehicle based on the location corresponding to the sound source vehicle and the location corresponding to the evaluation vehicle; Obtain the grade coefficient corresponding to the evaluation grade; The first speaker volume is calculated based on the grade coefficient, the speaker volume, and the target distance; The first horn frequency is calculated based on the grade coefficient, the horn frequency, the vehicle speed corresponding to the sound source vehicle, and the vehicle speed corresponding to the evaluation vehicle.

4. The method according to claim 3, characterized in that, The step of training the preset neural network model based on the processed data to obtain the target neural network model includes: Based on the vehicle speed, gear position, ambient volume, ambient audio, first horn volume, and first horn frequency of the sound source vehicle, the model parameters of the preset neural network model are adjusted to obtain the target neural network model.

5. The method according to claim 1, characterized in that, The step of obtaining evaluation data for the vehicle data from the evaluated vehicle includes: The vehicle data is sent to the evaluation vehicle so that the driver of the evaluation vehicle can evaluate the vehicle data and obtain the evaluation data. Receive the evaluation data sent by the evaluation vehicle.

6. A training method for a model controlling a vehicle horn, characterized in that, Applied to vehicle evaluation, the method includes: When the evaluation vehicle is in motion, vehicle data of the sound source vehicle is received from the cloud server. In response to an evaluation event of the vehicle data, evaluation data is obtained; The evaluation data is sent to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data.

7. A training device for a model of controlling a vehicle horn, characterized in that, The device, applied to a cloud server, includes: The first receiving unit is used to receive vehicle data sent by the sound source vehicle. The vehicle data includes horn data and driving data when the sound source vehicle is in motion. The horn data includes at least horn volume and horn frequency. The driving data includes at least the position, speed, gear, ambient volume and ambient audio of the sound source vehicle. The first acquisition unit is used to acquire evaluation data for the vehicle data from the evaluation vehicle, wherein the evaluation vehicle is a vehicle whose distance from the sound source vehicle is within a preset distance range; The training unit is used to train a preset neural network model based on the vehicle data and the evaluation data to obtain a target neural network model for controlling the vehicle horn.

8. A training device for a model of controlling a vehicle horn, characterized in that, The device is used for evaluating vehicles and includes: The second receiving unit is used to receive vehicle data of the sound source vehicle sent by the cloud server when the evaluation vehicle is in a driving state. The third acquisition unit is used to obtain evaluation data in response to an evaluation event of the vehicle data; The second sending unit is used to send the evaluation data to the cloud server so that the cloud server can train a target neural network model based on the evaluation data and the vehicle data.

9. A vehicle horn control system, characterized in that, include: The cloud server is used to train a preset neural network model based on the vehicle data of the sound source vehicle and the evaluation data of the evaluation vehicle, so as to obtain the target neural network model. A sound source vehicle is used to collect vehicle data and send the vehicle data to a cloud service, so that the cloud server can train a target neural network model based on the vehicle data and the evaluation data, obtain the target neural network model, and control the horn through the target neural network model. The vehicle evaluation tool is used to evaluate the vehicle data, obtain the evaluation data, and send the evaluation data to the cloud server.

10. A cloud server, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method as claimed in any one of claims 1 to 5.

11. A vehicle, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method as claimed in claim 6.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program executable by a cloud server or a vehicle, which, when run on the cloud server or the vehicle, causes the cloud server or the vehicle to perform the steps of the method according to any one of claims 1 to 6.

Images