Vehicle warning sound volume self-adaptive adjustment method, device, equipment and program product

Abstract

This invention discloses a method, device, equipment, and program product for adaptive adjustment of vehicle warning volume, including: acquiring the current vehicle status, current driving scenario, current ambient noise level, and the status of road users outside the target vehicle; determining the current warning type based on the current vehicle status, and determining the corresponding warning volume range based on the current warning type; constructing a multi-objective decision model with the optimization objectives of maximizing warning recognition probability and minimizing auditory discomfort probability, and determining the optimal warning volume value within the warning volume range based on the multi-objective decision model; and adjusting the current warning volume of the target vehicle according to the optimal warning volume value. This invention achieves precise adaptation of warning volume to the vehicle's surrounding environment, taking into account both the recognizability of the warning sound and the auditory experience of other road users, improving the accuracy of vehicle warning volume adjustment, ensuring road traffic safety, and can be applied to the field of vehicle control technology.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a method, device, equipment, and program product for adaptive adjustment of vehicle warning volume. Background Technology

[0002] Currently, some vehicles emit warning sounds when driving at low speeds, reversing, turning, or experiencing emergency malfunctions to alert other road users to the vehicle's movements. However, traditional solutions mostly use warning sounds at a fixed volume, without considering the impact of environmental noise. This results in poor warning effectiveness in construction zones and noisy areas. Blindly increasing the warning volume may cause discomfort to other road users.

[0003] The above problems urgently need to be addressed. Summary of the Invention

[0004] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0005] Therefore, one objective of this invention is to provide a vehicle warning volume adaptive adjustment method. This method determines the corresponding warning volume range based on the current warning type, and optimizes the warning volume value within the warning volume range based on a multi-objective decision model to maximize the warning recognition probability and minimize the probability of auditory discomfort. This achieves accurate adaptation of the warning volume to the vehicle's surrounding environment, takes into account the recognizability of the warning sound and the auditory experience of other road users, improves the accuracy of vehicle warning volume adjustment, and ensures road traffic safety.

[0006] Another objective of this invention is to provide a vehicle warning volume adaptive adjustment device.

[0007] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include: On one hand, embodiments of the present invention provide a method for adaptive adjustment of vehicle warning volume, comprising the following steps: The current vehicle status, current driving scenario, current ambient noise level, and status of road users outside the target vehicle are obtained. The current warning type is determined based on the current vehicle status, and the corresponding warning volume range is determined based on the current warning type; A multi-objective decision model is constructed with the optimization objectives of maximizing the probability of warning recognition and minimizing the probability of auditory discomfort. Based on the multi-objective decision model, the optimal warning volume value is determined within the warning volume range. Adjust the current warning volume of the target vehicle according to the optimal warning volume value; The multi-objective decision model includes a warning recognition probability prediction sub-model, an auditory discomfort probability prediction sub-model, and a multi-objective optimization function. The warning recognition probability prediction sub-model is used to predict the warning recognition probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of the road participant. The auditory discomfort probability prediction sub-model is used to predict the auditory discomfort probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of the road participant. The multi-objective optimization function is used to perform a weighted summation of the warning recognition probability and the auditory discomfort probability according to a dynamic weight coefficient to obtain the priority score corresponding to different warning volume values. The dynamic weight coefficient is determined according to the current driving scenario.

[0008] Furthermore, in one embodiment of the present invention, obtaining the current vehicle state, current driving scenario, current ambient noise level, and the state of road participants outside the target vehicle specifically includes: The current vehicle status is obtained through vehicle body control; The vehicle acquires road image information around the target vehicle through an onboard camera device, acquires radar detection information around the target vehicle through an onboard radar device, and acquires the current ambient noise level through a light sensor. The current driving scenario is identified based on the road image information; Based on the road image information, identify several road participants outside the target vehicle, and determine the position, speed, and attitude of each road participant based on the radar detection information to obtain the state of the road participants.

[0009] Furthermore, in one embodiment of the present invention, the step of determining the current warning type based on the current vehicle status and determining the corresponding warning volume range based on the current warning type specifically includes: The current warning type is determined based on the current vehicle status and the preset vehicle warning rules; Determine the corresponding standard alarm volume value and volume fluctuation ratio based on the current alarm type; The warning volume range is determined based on the standard warning volume value and the volume fluctuation ratio.

[0010] Furthermore, in one embodiment of the present invention, determining the optimal warning volume value within the warning volume range based on the multi-objective decision model specifically includes: The corresponding volume interval step size is determined based on the current driving scenario, and multiple alternative warning volume values ​​are determined based on the volume interval step size and the warning volume range. The current ambient noise level, the status of the road participants, and the candidate warning volume values ​​are input into the pre-trained warning recognition probability prediction sub-model to obtain the warning recognition probability corresponding to the candidate warning volume values. The current ambient noise level, the status of the road participants, and the alternative warning volume values ​​are input into the pre-trained auditory discomfort probability prediction sub-model to obtain the auditory discomfort probability corresponding to the alternative warning volume values. Based on the multi-objective optimization function, the warning recognition probability and the hearing discomfort probability are weighted and summed according to the warning recognition weight and the hearing discomfort weight to obtain the priority score corresponding to the candidate warning volume value; The candidate warning volume value with the highest priority score is determined as the optimal warning volume value.

[0011] Furthermore, in one embodiment of the present invention, the multi-objective optimization function is:

[0012] in, Indicates priority score, and These represent the probability of warning recognition and the probability of auditory discomfort, respectively. and These represent the warning recognition weight and auditory discomfort weight determined based on the current driving scenario, respectively. .

[0013] Furthermore, in one embodiment of the present invention, the warning recognition probability prediction sub-model is trained through the following steps: The sample environmental noise volume, sample road participant status, and sample warning volume are obtained in the test scenario, and the corresponding warning recognition probability labels are determined by manual annotation. The sample environmental noise volume, the sample road participant status, and the sample warning volume are input into a pre-built convolutional neural network to obtain the predicted warning recognition probability. The loss value is determined based on the predicted warning recognition probability and the warning recognition probability label; The parameters of the convolutional neural network are updated using the backpropagation algorithm based on the loss value to obtain the trained warning recognition probability prediction sub-model.

[0014] Furthermore, in one embodiment of the present invention, the auditory discomfort probability prediction sub-model is trained through the following steps: The sample environmental noise volume, the status of participants on the sample road, and the sample warning volume were obtained in the test scenario, and the corresponding auditory discomfort probability labels were determined by manual annotation. The sample environmental noise volume, the sample road participant status, and the sample warning volume are input into an initialized gradient boosting decision tree to obtain the predicted probability of auditory discomfort. The residual value is determined based on the predicted probability of auditory discomfort and the label of the probability of auditory discomfort; Train a target decision tree to fit the residual values, and update the gradient boosting decision tree based on the target decision tree; When the number of iterations exceeds a preset threshold or the residual value is lower than a preset residual threshold, training stops, and the current gradient boosting decision tree is used as the trained sub-model for predicting the probability of auditory discomfort.

[0015] On the other hand, embodiments of the present invention provide a vehicle warning volume adaptive adjustment device, comprising: The data acquisition module is used to acquire the current vehicle status, current driving scenario, current ambient noise level, and the status of road participants outside the target vehicle. The volume range determination module is used to determine the current warning type based on the current vehicle status, and to determine the corresponding warning volume range based on the current warning type; The optimal volume value determination module is used to construct a multi-objective decision model with the optimization objectives of maximizing the warning recognition probability and minimizing the auditory discomfort probability, and to determine the optimal warning volume value within the warning volume range based on the multi-objective decision model. The warning volume adjustment module is used to adjust the current warning volume of the target vehicle according to the optimal warning volume value; The multi-objective decision model includes a warning recognition probability prediction sub-model, an auditory discomfort probability prediction sub-model, and a multi-objective optimization function. The warning recognition probability prediction sub-model is used to predict the warning recognition probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of the road participant. The auditory discomfort probability prediction sub-model is used to predict the auditory discomfort probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of the road participant. The multi-objective optimization function is used to perform a weighted summation of the warning recognition probability and the auditory discomfort probability according to a dynamic weight coefficient to obtain the priority score corresponding to different warning volume values. The dynamic weight coefficient is determined according to the current driving scenario.

[0016] On the other hand, embodiments of the present invention provide an electronic device, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-described vehicle warning volume adaptive adjustment method.

[0017] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described adaptive adjustment method for vehicle warning volume.

[0018] On the other hand, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the above-described adaptive adjustment method for vehicle warning volume.

[0019] The advantages and beneficial effects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention: This invention acquires the current vehicle status, current driving scenario, current ambient noise level, and the status of road users outside the target vehicle. Based on the current vehicle status, it determines the current warning type and the corresponding warning volume range. A multi-objective decision model is constructed with the optimization objectives of maximizing warning recognition probability and minimizing auditory discomfort probability. Based on the multi-objective decision model, the optimal warning volume value is determined within the warning volume range, and the current warning volume of the target vehicle is adjusted according to the optimal warning volume value. This invention determines the corresponding warning volume range based on the current warning type, and uses the multi-objective decision model to optimize the warning volume value within this range to maximize the warning recognition probability and minimize the auditory discomfort probability. This achieves precise adaptation of the warning volume to the vehicle's surrounding environment, taking into account both the recognizability of the warning sound and the auditory experience of other road users, improving the accuracy of vehicle warning volume adjustment, and ensuring road traffic safety. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the steps of a vehicle warning volume adaptive adjustment method provided in an embodiment of the present invention; Figure 2 This is a structural block diagram of a vehicle warning volume adaptive adjustment device provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0024] The vehicle warning volume adaptive adjustment method provided in this invention can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical 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, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the vehicle warning volume adaptive adjustment method, but is not limited to the above forms.

[0025] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0026] It should be noted that in various specific embodiments of the present invention, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user parking space location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of the present invention require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to a confirmation page. Only after obtaining the user's separate permission or consent is the necessary user-related data for the normal operation of the embodiments of the present invention acquired.

[0027] Reference Figure 1 This invention provides a method for adaptive adjustment of vehicle warning volume, specifically including the following steps: S101. Obtain the current vehicle status, current driving scenario, current ambient noise level, and status of road users outside the target vehicle. S102. Determine the current warning type based on the current vehicle status, and determine the corresponding warning volume range based on the current warning type; S103. Construct a multi-objective decision-making model with the optimization objectives of maximizing the probability of warning recognition and minimizing the probability of auditory discomfort, and determine the optimal warning volume value within the warning volume range based on the multi-objective decision-making model. S104. Adjust the current warning volume of the target vehicle according to the optimal warning volume value; The multi-objective decision-making model includes a warning recognition probability prediction sub-model, an auditory discomfort probability prediction sub-model, and a multi-objective optimization function. The warning recognition probability prediction sub-model is used to predict the warning recognition probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of road participants. The auditory discomfort probability prediction sub-model is used to predict the auditory discomfort probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of road participants. The multi-objective optimization function is used to perform a weighted summation of the warning recognition probability and the auditory discomfort probability according to the dynamic weight coefficient to obtain the priority score corresponding to different warning volume values. The dynamic weight coefficient is determined according to the current driving scenario.

[0028] According to the embodiments of the present invention, the corresponding warning volume range is determined based on the current warning type. Based on the multi-objective decision model, the optimal warning volume value is obtained within the warning volume range to maximize the warning recognition probability and minimize the probability of auditory discomfort. This achieves accurate adaptation of the warning volume to the vehicle's surrounding environment, takes into account the recognizability of the warning sound and the auditory experience of other road users, improves the accuracy of vehicle warning volume adjustment, and ensures road traffic safety.

[0029] As a further optional implementation, the current vehicle status, current driving scenario, current ambient noise level, and status of road users outside the target vehicle are obtained, specifically including: S1011. Obtain the current vehicle status through vehicle body control; S1012. Obtain road image information around the target vehicle through the vehicle-mounted camera device, obtain radar detection information around the target vehicle through the vehicle-mounted radar device, and obtain the current ambient noise volume through the light sensor. S1013. Identify the current driving scenario based on road image information; S1014. Identify several road participants outside the target vehicle based on road image information, and determine the position, speed and attitude of each road participant based on radar detection information to obtain the road participant status.

[0030] Specifically, the current vehicle status, including vehicle speed, accelerator pedal travel, brake pedal travel, steering wheel angle, and battery parameters, is obtained through the vehicle controller to determine the type of vehicle warning to be triggered. Based on road image information, scenarios such as urban roads, highways, tunnels, and rural roads are identified, and the scene granularity is refined by combining vehicle speed and traffic density to obtain the current driving scenario. The ambient noise level is collected in real time through noise monitoring sensors outside the vehicle. Based on road image information, the participant types (motor vehicles, non-motor vehicles, and pedestrians) of several road participants are identified, and then the position, speed, and attitude of each road participant are determined by combining radar detection information. If necessary, V2X communication data can be used to supplement the information to finally obtain the status of road participants around the target vehicle.

[0031] As a further optional implementation, the current warning type is determined based on the current vehicle status, and the corresponding warning volume range is determined based on the current warning type, specifically including: S1021. Determine the current warning type based on the current vehicle status and preset vehicle warning rules; S1022. Determine the corresponding standard value and volume fluctuation ratio of the current warning volume based on the current warning type; S1023. Determine the warning volume range based on the standard warning volume value and the volume fluctuation ratio.

[0032] Specifically, based on the vehicle status and preset vehicle warning rules, the corresponding warning type is matched. For example: when the vehicle is in reverse gear and no nearby obstacle is detected, a regular reversing warning is triggered; when the vehicle is in reverse gear and the radar detects an obstacle within 3 meters, a reversing warning is triggered; when the vehicle's turn signal is activated and the vehicle speed is below 30 km / h, a low-speed turning warning is triggered; when the vehicle's turn signal is activated and the vehicle speed is above 30 km / h, a high-speed turning warning is triggered; when the vehicle is driving in a residential area or school zone and the vehicle speed is below 20 km / h, a pedestrian alert warning is triggered. For each type of warning, there are pre-set basic standard values ​​and fluctuation rules. For example, the standard volume value for the reversing regular warning is 60 decibels, with a fluctuation ratio of ±15%; the standard volume value for the reversing warning is 70 decibels, with a fluctuation ratio of ±20%; the standard volume value for the low-speed turning warning is 65 decibels, with a fluctuation ratio of ±10%; the standard volume value for the high-speed turning warning is 75 decibels, with a fluctuation ratio of ±10%; and the standard volume value for the pedestrian warning is 55 decibels, with a fluctuation ratio of ±15%.

[0033] Based on standard values ​​and fluctuation ratios, the specific volume ranges for each warning type are calculated as follows: the volume range for the standard reversing warning is 51 to 69 dB; the volume range for the reversing warning is 56 to 84 dB; the volume range for the low-speed turning warning is 58.5 to 71.5 dB; the volume range for the high-speed turning warning is 67.5 to 82.5 dB; the volume range for the pedestrian warning is 46.75 to 63.25 dB; and the volume range for the silent mode warning is 40.5 to 49.5 dB.

[0034] As a further optional implementation, the optimal warning volume value is determined within the warning volume range based on a multi-objective decision-making model, specifically including: S1031. Determine the corresponding volume interval step size according to the current driving scenario, and determine multiple alternative warning volume values ​​based on the volume interval step size and the warning volume range. S1032. Input the current ambient noise level, the status of road participants and the alternative warning volume values ​​into the pre-trained warning recognition probability prediction sub-model to obtain the warning recognition probability corresponding to the alternative warning volume values. S1033. Input the current ambient noise volume, the status of road participants, and the alternative warning volume values ​​into the pre-trained auditory discomfort probability prediction sub-model to obtain the auditory discomfort probability corresponding to the alternative warning volume values. S1034. Based on the multi-objective optimization function, the warning recognition probability and the hearing discomfort probability are weighted and summed according to the warning recognition weight and the hearing discomfort weight to obtain the priority score corresponding to the candidate warning volume value. S1035. Determine the candidate warning volume value with the highest priority score as the optimal warning volume value.

[0035] Specifically, the corresponding volume interval step size is determined based on the current driving scenario. Considering that human hearing is most sensitive to volume changes of 3-5 decibels, and taking into account the noise environment of different scenarios, the following step size rules are set: In quiet scenarios (nighttime residential areas, rural roads, hospital / school access roads), the volume interval step size is set to 2 decibels; in normal urban scenarios (city roads, ordinary streets), the volume interval step size is set to 3 decibels; in noisy scenarios (traffic congestion, construction areas, highway driving), the volume interval step size is set to 5 decibels; and in emergency scenarios (sudden appearance of obstacles, pedestrians entering the lane), the volume interval step size is set to 8 decibels. A larger volume interval step size reduces the computational load of the multi-objective decision-making model, thus enabling more timely adjustment of the warning volume.

[0036] It should be noted that when the ambient noise suddenly changes (such as driving from a city road into a construction area), the system will automatically switch the corresponding step size rule within 1 second. When the state of the person being alerted changes (such as changing from looking at the vehicle to being distracted), the system will automatically increase the step size by 1-2 steps from the current alternative values. When the vehicle is driving in a mixed scene (such as a construction area next to a city road), the system will take the average step size of the scene (such as 3+5=8 / 2=4 dB) as the temporary step size.

[0037] Multiple alternative warning volume values ​​are determined based on the volume interval step and the warning volume range. For example, for the volume range of 51 dB to 69 dB for the regular reversing warning, if the volume interval step is 2 dB, then 51 / 53 / 55 / 57 / 59 / 61 / 63 / 65 / 67 / 69 dB can be taken as alternative warning volume values. If the volume interval step is 3 dB, then 51 / 54 / 57 / 60 / 63 / 66 / 69 dB can be taken as alternative warning volume values.

[0038] The current ambient noise level, the status of road users, and the alternative warning volume values ​​are input into pre-trained warning recognition probability prediction sub-models and auditory discomfort probability prediction sub-models, respectively, to obtain the warning recognition probability and auditory discomfort probability corresponding to the alternative warning volume values. Then, the warning recognition probability and auditory discomfort probability are input into a multi-objective optimization function, and the priority score corresponding to the alternative warning volume value is calculated by combining the warning recognition weight and auditory discomfort weight determined according to the current driving scenario. Finally, the alternative warning volume value with the highest priority score is determined as the optimal warning volume value.

[0039] As an optional implementation, the multi-objective optimization function is:

[0040] in, Indicates priority score, and These represent the probability of warning recognition and the probability of auditory discomfort, respectively. and These represent the warning recognition weight and auditory discomfort weight determined based on the current driving scenario, respectively. .

[0041] Specifically, the optimization objective of the multi-objective optimization function in this embodiment of the invention is to maximize the priority score of the warning volume value. The priority score is positively correlated with the warning recognition probability and negatively correlated with the probability of auditory discomfort. Therefore, it can balance the recognizability of the warning sound with the auditory experience of other road users, achieving a balance between the two. The priority of the two objectives, warning recognition weight and auditory discomfort weight, can be flexibly adjusted according to different scenarios. For example, in quiet scenarios, more emphasis is placed on auditory comfort, while in emergency scenarios, more emphasis is placed on the warning recognition rate. For instance, in emergency scenarios, the warning recognition weight is 0.8, and the auditory discomfort weight is -0.2; in quiet scenarios, the warning recognition weight is 0.4, and the auditory discomfort weight is -0.6.

[0042] The warning recognition probability prediction sub-model and the auditory discomfort probability prediction sub-model in this embodiment of the invention can both be implemented using various prediction models. For example, a neural network model can be used to fit the mapping relationship between ambient noise volume, road participant status, and warning volume value and the warning recognition probability and auditory discomfort probability. Alternatively, a gradient boosting decision tree can be used to fit the warning recognition probability and auditory discomfort probability under different combinations of variables such as ambient noise volume, road participant status, and warning volume value, ultimately obtaining the warning recognition probability prediction sub-model and the auditory discomfort probability prediction sub-model. The training process of the warning recognition probability prediction sub-model and the auditory discomfort probability prediction sub-model will be explained below using neural network models and gradient boosting decision trees as examples, respectively.

[0043] As an optional implementation, the warning recognition probability prediction sub-model is trained through the following steps: S201. Obtain the ambient noise volume, participant status, and warning volume of the sample road in the test scenario, and determine the corresponding warning recognition probability label through manual annotation. S202. Input the sample environmental noise volume, the sample road participant status, and the sample warning volume into a pre-built convolutional neural network to obtain the predicted warning recognition probability. S203. Determine the loss value based on the predicted warning recognition probability and the warning recognition probability label; S204. Update the parameters of the convolutional neural network based on the loss value using the backpropagation algorithm to obtain the trained warning recognition probability prediction sub-model.

[0044] Specifically, the system acquires sample ambient noise levels, sample road participant states, and sample warning volumes in the test scenario. It then statistically analyzes the warning recognition performance of each road participant in the scenario to determine the warning recognition probability label. After acquiring a sufficient number of training samples, the sample ambient noise levels, sample road participant states, and sample warning volumes are input into a pre-built convolutional neural network to obtain the predicted warning recognition probability. The loss value is determined based on the predicted warning recognition probability and the warning recognition probability label. The parameters of the convolutional neural network are updated using the backpropagation algorithm based on the loss value, completing one iteration of training. Training stops when the number of iterations reaches a preset threshold or the loss value falls below the preset threshold, resulting in a well-trained warning recognition probability prediction sub-model.

[0045] As an optional implementation, the auditory discomfort probability prediction sub-model is trained through the following steps: S301. Obtain the ambient noise volume, participant status, and warning volume of the sample road in the test scenario, and determine the corresponding auditory discomfort probability label through manual annotation. S302. Input the sample environmental noise volume, the sample road participant status, and the sample warning volume into the initialized gradient boosting decision tree to obtain the predicted probability of auditory discomfort. S303. Determine the residual value based on the predicted probability of hearing discomfort and the label of the probability of hearing discomfort; S304. Train the target decision tree to fit the residual values, and update the gradient boosting decision tree based on the target decision tree; S305. When the number of iterations exceeds the preset threshold or the residual value is lower than the preset threshold, stop training and use the current gradient boosting decision tree as the trained sub-model for predicting the probability of auditory discomfort.

[0046] Specifically, the system acquires sample ambient noise levels, sample road participant states, and sample warning volumes in the test scenario, and statistically analyzes the auditory comfort of each road participant in the scenario to determine the auditory discomfort probability label. After acquiring a sufficient number of training samples, the sample ambient noise levels, sample road participant states, and sample warning volumes are input into an initialized gradient boosting decision tree to obtain the predicted auditory discomfort probability. The residual value is determined based on the predicted auditory discomfort probability and the auditory discomfort probability label. A target decision tree is trained to fit the residual value, and this target decision tree is multiplied by a preset learning rate and then superimposed onto the gradient boosting decision tree to complete the update of the gradient boosting decision tree and enter the next iteration. When the number of iterations exceeds a preset threshold or the residual value is lower than a preset residual threshold, training stops, and the current gradient boosting decision tree is used as the trained auditory discomfort probability prediction sub-model.

[0047] In some optional embodiments, when adjusting the current warning volume of the target vehicle according to the optimal warning volume value, a buffer mechanism is employed to achieve a smooth transition in the warning volume adjustment, that is, gradually increasing / decreasing from the current warning volume to the optimal warning volume value. Furthermore, the brightness of the warning lights can be adjusted simultaneously when adjusting the warning volume; however, this will not be elaborated upon in the embodiments of the present invention.

[0048] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention determine the corresponding warning volume range based on the current warning type, and optimize the warning volume value within this range using a multi-objective decision model to maximize the warning recognition probability and minimize the probability of auditory discomfort. This achieves precise adaptation of the warning volume to the vehicle's surrounding environment, taking into account both the recognizability of the warning sound and the auditory experience of other road users, improving the accuracy of vehicle warning volume adjustment, and ensuring road traffic safety.

[0049] Reference Figure 2 This invention provides a vehicle warning volume adaptive adjustment device, comprising: The data acquisition module is used to acquire the target vehicle's current vehicle status, current driving scenario, current ambient noise level, and the status of road users outside the target vehicle. The volume range determination module is used to determine the current warning type based on the current vehicle status, and to determine the corresponding warning volume range based on the current warning type; The optimal volume value determination module is used to construct a multi-objective decision model with the optimization objectives of maximizing the warning recognition probability and minimizing the auditory discomfort probability, and to determine the optimal warning volume value within the warning volume range based on the multi-objective decision model. The warning volume adjustment module is used to adjust the current warning volume of the target vehicle according to the optimal warning volume value; The multi-objective decision-making model includes a warning recognition probability prediction sub-model, an auditory discomfort probability prediction sub-model, and a multi-objective optimization function. The warning recognition probability prediction sub-model is used to predict the warning recognition probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of road participants. The auditory discomfort probability prediction sub-model is used to predict the auditory discomfort probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of road participants. The multi-objective optimization function is used to perform a weighted summation of the warning recognition probability and the auditory discomfort probability according to the dynamic weight coefficient to obtain the priority score corresponding to different warning volume values. The dynamic weight coefficient is determined according to the current driving scenario.

[0050] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0051] Reference Figure 3 This invention provides an electronic device, comprising: At least one processor; At least one memory for storing at least one program; When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned vehicle warning volume adaptive adjustment method.

[0052] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0053] This invention also provides a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described adaptive adjustment method for vehicle warning volume.

[0054] This invention provides a computer-readable storage medium that can execute a vehicle warning volume adaptive adjustment method provided in the method embodiment of this invention. It can execute any combination of the implementation steps of the method embodiment and has the corresponding functions and beneficial effects of the method.

[0055] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described adaptive adjustment method for vehicle warning volume.

[0056] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0057] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0058] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0059] The terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0060] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0061] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0062] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0063] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0064] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0065] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0066] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0067] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0068] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for adaptive adjustment of vehicle warning volume, characterized in that, Includes the following steps: The current vehicle status, current driving scenario, current ambient noise level, and status of road users outside the target vehicle are obtained. The current warning type is determined based on the current vehicle status, and the corresponding warning volume range is determined based on the current warning type; A multi-objective decision model is constructed with the optimization objectives of maximizing the probability of warning recognition and minimizing the probability of auditory discomfort. Based on the multi-objective decision model, the optimal warning volume value is determined within the warning volume range. Adjust the current warning volume of the target vehicle according to the optimal warning volume value; The multi-objective decision model includes a warning recognition probability prediction sub-model, an auditory discomfort probability prediction sub-model, and a multi-objective optimization function. The warning recognition probability prediction sub-model is used to predict the warning recognition probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of the road participant. The auditory discomfort probability prediction sub-model is used to predict the auditory discomfort probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of the road participant. The multi-objective optimization function is used to perform a weighted summation of the warning recognition probability and the auditory discomfort probability according to a dynamic weight coefficient to obtain the priority score corresponding to different warning volume values. The dynamic weight coefficient is determined according to the current driving scenario.

2. The vehicle warning volume adaptive adjustment method according to claim 1, characterized in that, The acquisition of the target vehicle's current vehicle status, current driving scenario, current ambient noise level, and the status of road participants outside the target vehicle specifically includes: The current vehicle status is obtained through vehicle body control; The vehicle acquires road image information around the target vehicle through an onboard camera device, acquires radar detection information around the target vehicle through an onboard radar device, and acquires the current ambient noise level through a light sensor. The current driving scenario is identified based on the road image information; Based on the road image information, identify several road participants outside the target vehicle, and determine the position, speed, and attitude of each road participant based on the radar detection information to obtain the state of the road participants.

3. The vehicle warning volume adaptive adjustment method according to claim 1, characterized in that, The step of determining the current warning type based on the current vehicle status and determining the corresponding warning volume range based on the current warning type specifically includes: The current warning type is determined based on the current vehicle status and the preset vehicle warning rules; Determine the corresponding standard alarm volume value and volume fluctuation ratio based on the current alarm type; The warning volume range is determined based on the standard warning volume value and the volume fluctuation ratio.

4. The vehicle warning volume adaptive adjustment method according to claim 1, characterized in that, The determination of the optimal warning volume value within the warning volume range based on the multi-objective decision model specifically includes: The corresponding volume interval step size is determined based on the current driving scenario, and multiple alternative warning volume values ​​are determined based on the volume interval step size and the warning volume range. The current ambient noise level, the status of the road participants, and the candidate warning volume values ​​are input into the pre-trained warning recognition probability prediction sub-model to obtain the warning recognition probability corresponding to the candidate warning volume values. The current ambient noise level, the status of the road participants, and the alternative warning volume values ​​are input into the pre-trained auditory discomfort probability prediction sub-model to obtain the auditory discomfort probability corresponding to the alternative warning volume values. Based on the multi-objective optimization function, the warning recognition probability and the hearing discomfort probability are weighted and summed according to the warning recognition weight and the hearing discomfort weight to obtain the priority score corresponding to the candidate warning volume value; The candidate warning volume value with the highest priority score is determined as the optimal warning volume value.

5. The vehicle warning volume adaptive adjustment method according to claim 1, characterized in that, The multi-objective optimization function is: in, Indicates priority score, and These represent the probability of warning recognition and the probability of auditory discomfort, respectively. and These represent the warning recognition weight and auditory discomfort weight determined based on the current driving scenario, respectively. .

6. The vehicle warning volume adaptive adjustment method according to claim 1, characterized in that, The warning recognition probability prediction sub-model is trained through the following steps: The sample environmental noise volume, sample road participant status, and sample warning volume are obtained in the test scenario, and the corresponding warning recognition probability labels are determined by manual annotation. The sample environmental noise volume, the sample road participant status, and the sample warning volume are input into a pre-built convolutional neural network to obtain the predicted warning recognition probability. The loss value is determined based on the predicted warning recognition probability and the warning recognition probability label; The parameters of the convolutional neural network are updated using the backpropagation algorithm based on the loss value to obtain the trained warning recognition probability prediction sub-model.

7. The vehicle warning volume adaptive adjustment method according to claim 1, characterized in that, The auditory discomfort probability prediction sub-model is trained through the following steps: The sample environmental noise volume, the status of participants on the sample road, and the sample warning volume were obtained in the test scenario, and the corresponding auditory discomfort probability labels were determined by manual annotation. The sample environmental noise volume, the sample road participant status, and the sample warning volume are input into an initialized gradient boosting decision tree to obtain the predicted probability of auditory discomfort. The residual value is determined based on the predicted probability of auditory discomfort and the label of the probability of auditory discomfort; Train a target decision tree to fit the residual values, and update the gradient boosting decision tree based on the target decision tree; When the number of iterations exceeds a preset threshold or the residual value is lower than a preset residual threshold, training stops, and the current gradient boosting decision tree is used as the trained sub-model for predicting the probability of auditory discomfort.

8. A vehicle warning volume adaptive adjustment device, characterized in that, include: The data acquisition module is used to acquire the current vehicle status, current driving scenario, current ambient noise level, and the status of road participants outside the target vehicle. The volume range determination module is used to determine the current warning type based on the current vehicle status, and to determine the corresponding warning volume range based on the current warning type; The optimal volume value determination module is used to construct a multi-objective decision model with the optimization objectives of maximizing the warning recognition probability and minimizing the auditory discomfort probability, and to determine the optimal warning volume value within the warning volume range based on the multi-objective decision model. The warning volume adjustment module is used to adjust the current warning volume of the target vehicle according to the optimal warning volume value; The multi-objective decision model includes a warning recognition probability prediction sub-model, an auditory discomfort probability prediction sub-model, and a multi-objective optimization function. The warning recognition probability prediction sub-model is used to predict the warning recognition probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of the road participant. The auditory discomfort probability prediction sub-model is used to predict the auditory discomfort probability corresponding to different warning volume values ​​by combining the current ambient noise volume and the state of the road participant. The multi-objective optimization function is used to perform a weighted summation of the warning recognition probability and the auditory discomfort probability according to a dynamic weight coefficient to obtain the priority score corresponding to different warning volume values. The dynamic weight coefficient is determined according to the current driving scenario.

9. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a vehicle warning volume adaptive adjustment method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements a vehicle warning volume adaptive adjustment method as described in any one of claims 1 to 7.

Images