Vehicle warning tone playing method and system and vehicle

Abstract

The embodiment of the invention provides a vehicle prompt tone playing method and system and a vehicle, and the method comprises the steps: obtaining an initial prompt tone and a prompt scene corresponding to the initial prompt tone, and determining a first audio feature and a second audio feature according to the collected first physiological data and prompt scene of a driver in the vehicle driving process; and adjusting the initial prompt tone according to the first audio feature and the second audio feature to obtain and play a target prompt tone. The first audio feature is determined by acquiring the first physiological data of the driver in the vehicle driving process, the prompt tone can be dynamically adjusted based on the state of the driver, and the second audio feature is determined based on the first physiological data and the prompt scene to establish a feature constraint mechanism for the prompt tone. Therefore, the prompt tone better conforms to the driving state of the driver, and meanwhile, the prompt effect of the prompt tone on the driver is ensured.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle prompt sound playing method, system and vehicle. Background Art

[0002] With the development of smart cockpits, the number of in-car prompt sounds is gradually increasing. The sound processing during vehicle driving generally makes the in-car media audio data adaptively change with the environment, or the navigation broadcast content adaptively changes according to the fatigue driving status. There is no mention of the adaptive changes of the in-car alarm prompt sound, and the changes in audio data mainly follow the driving environment and the driver's fatigue status during driving. It does not take into account the differences in music preferences of different drivers and the differences in the perception of sound under different emotional states.

[0003] Providing the driver with a method for customizing the vehicle's internal sounds associated with vehicle accessories and events, on the one hand, makes the operation more complicated and inefficient, and increases the driver's memory burden; on the other hand, for safety reasons, the in-vehicle alarm sound will be subject to regulatory restrictions on playback volume, duration, frequency, etc., and using sounds customized entirely by the driver will have certain safety risks. The mapping relationship is only changed according to the driver's preferences, and the sound itself will not adapt to the driver's usage scenarios, different emotional states, and different environments. After the driver gets used to this prompt tone that does not adapt to the usage scenarios, different emotional states, and different environments, the reminder effect of this prompt tone on the driver will gradually weaken. In addition, there is a lack of a prompt tone feature constraint mechanism related to the prompt scenario and safety level, which cannot enable the driver to quickly judge the safety urgency of the prompt tone. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide a vehicle prompt sound playing method, system and vehicle that overcome the above problems or at least partially solve the above problems.

[0005] According to a first aspect of the present invention, a vehicle prompt sound playing method is provided, the method comprising: Obtaining an initial prompt sound of the vehicle and a prompt scene corresponding to the initial prompt sound; collecting first physiological data of the driver during the driving of the vehicle; determining a first audio feature according to the first physiological data; determining a second audio feature according to the first physiological data and the prompt scenario; Adjusting the initial prompt tone according to the first audio feature and the second audio feature to obtain a target prompt tone; Play the target prompt tone.

[0006] Optionally, obtaining an initial prompt tone of the vehicle includes: Get the current driver's identity information; Determine the corresponding audio preference features according to the identity information; the audio preference features at least include: music style features and volume features; The initial prompt sound is determined by performing feature matching in an initial prompt sound database according to the music style feature and / or the volume feature.

[0007] Optionally, the first physiological data includes: at least one of the driver's sight direction, the fixation time of the sight direction, facial information, body information, and ambient sound information; The determining a first audio feature according to the first physiological data includes: The first audio feature is determined according to the line of sight direction, the gaze time in the line of sight direction, and / or the facial information, the body information, and / or the ambient sound information.

[0008] Optionally, the first audio feature includes: at least one of an audio rhythm feature, an audio melody feature, and an audio volume feature; The determining the first audio feature according to the sight direction, the gaze time of the sight direction, and / or the facial information, the body information, and / or the ambient sound information includes: Determining the attention level according to the sight direction and the gaze time, and the audio rhythm feature matching the attention level; and / or, Determining an emotional state based on the facial information and the body information, and the audio melody features matching the emotional state; and / or, An ambient noise level and the audio volume feature matching the noise level are determined according to the ambient sound information.

[0009] Optionally, the determining of the second audio feature according to the first physiological data and the prompting scene includes: Determining the safety level of the initial prompt sound according to the prompt scene, the driver's sight direction, and / or the gaze time in the sight direction; The second audio feature is determined according to the security level.

[0010] Optionally, the second audio feature includes the number of audio beats; The determining the second audio feature according to the security level includes: Determine the area where the current vehicle is located according to the prompt scene of the initial prompt sound and determine the corresponding function restriction strategy; the function restriction strategy includes a limited range of the number of audio beat points; Within the limited range, the number of audio beat points is determined according to the security level.

[0011] Optionally, the adjusting the initial prompt tone according to the first audio feature and the second audio feature to obtain a target prompt tone includes: Selecting a preset number of the first audio features and the second audio features, adjusting the initial prompt sound, and obtaining a target prompt sound; or Based on the priorities of the first audio feature and the second audio feature, an audio feature whose priority meets a first preset condition is selected to adjust the initial prompt tone to obtain a target prompt tone.

[0012] Optionally, after playing the target prompt tone, the method further includes: Acquiring a second physiological characteristic of the driver to the target prompt sound after playing the target prompt sound; When the second physiological characteristic meets the preset condition, the voice feedback corresponding to the target prompt tone is output According to a second aspect of the present invention, a vehicle prompt sound playback system is provided; the vehicle prompt sound playback system is used to execute the steps in the vehicle prompt sound playback method described in the first aspect above.

[0013] According to a third aspect of the present invention, a vehicle is provided, comprising the steps of the vehicle prompt sound playing method described in the first aspect, or comprising the vehicle prompt sound playing system described in the second aspect.

[0014] The embodiments of the present invention include the following advantages: In an embodiment of the present invention, by acquiring an initial prompt sound and a prompt scene corresponding to the initial prompt sound, a first audio feature and a second audio feature are determined according to the first physiological data of the driver and the prompt scene collected during the driving of the vehicle; the initial prompt sound is adjusted according to the first audio feature and the second audio feature, and a target prompt sound is obtained and played. By acquiring the first physiological data of the driver during the driving of the vehicle to determine the first audio feature, the prompt sound can be dynamically adjusted based on the driver's state, and the second audio feature is determined based on the first physiological data and the prompt scene to establish a feature constraint mechanism for the prompt sound, so that the prompt sound is more in line with the driver's driving state while ensuring the reminder effect of the prompt sound on the driver.

[0015] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] Figure 1 It is a flowchart of a method for playing a vehicle prompt tone according to an embodiment of the present invention; Figure 2 is a mapping relationship diagram between audio features and physiological data provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the steps of another vehicle prompt sound playing method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0019] The terms "first", "second", etc. in the specification and claims of the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0020] With the development of smart cockpits, the number of in-car prompt sounds is gradually increasing. The sound processing during vehicle driving generally makes the in-car media audio data adaptively change with the environment, or the navigation broadcast content adaptively changes according to the fatigue driving status. There is no mention of the adaptive changes of the in-car alarm prompt sound, and the changes in audio data mainly follow the driving environment and the driver's fatigue status during driving. It does not take into account the differences in music preferences of different drivers and the differences in the perception of sound under different emotional states.

[0021] Providing the driver with a method for customizing the vehicle's internal sounds associated with vehicle accessories and events, on the one hand, makes the operation more complicated and inefficient, and increases the driver's memory burden; on the other hand, for safety reasons, the in-vehicle alarm sound will be subject to regulatory restrictions on playback volume, duration, frequency, etc., and using sounds customized entirely by the driver will have certain safety risks. The mapping relationship is only changed according to the driver's preferences, and the sound itself will not adapt to the driver's usage scenarios, different emotional states, and different environments. After the driver gets used to this prompt tone that does not adapt to the usage scenarios, different emotional states, and different environments, the reminder effect of this prompt tone on the driver will gradually weaken. In addition, there is a lack of a prompt tone feature constraint mechanism related to the prompt scenario and safety level, which cannot enable the driver to quickly judge the safety urgency of the prompt tone.

[0022] How to dynamically adjust the audio data of the prompt sound according to changes in driver attention, driver feedback, differences in the driver's music preferences, and differences in the driver's perception of sound under different emotional states, and establish a feature constraint mechanism to ensure that the prompt sound is effective in reminding the driver is an urgent problem to be solved.

[0023] In conjunction with the accompanying drawings, a vehicle prompt sound playing method, system and vehicle provided by the embodiments of the present invention are described in detail through specific embodiments and their application scenarios.

[0024] Reference Figure 1 , shows a flow chart of a method for playing a vehicle prompt tone according to an embodiment of the present invention, which may specifically include the following steps: Step 101, obtaining an initial prompt sound of the vehicle and a prompt scene corresponding to the initial prompt sound; When the vehicle ECU (Electronic Control Unit) determines that a prompt sound needs to be played based on the data provided by sensors such as the speed sensor, steering sensor, collision sensor installed on the vehicle or the driver's operation, it will send a command to play the prompt sound to the sound module or speaker.

[0025] In this embodiment, the initial prompt sound of the vehicle and the prompt scene corresponding to the initial prompt sound can be obtained according to the instruction to play the prompt sound.

[0026] Specifically, the vehicle's environment information and fault information can be collected according to the vehicle sensor, and the vehicle's environment information includes at least weather conditions, geographical location, and traffic conditions. According to the weather conditions, geographical location, traffic conditions, and vehicle fault information, the prompt scene corresponding to the initial prompt sound can be obtained.

[0027] Step 102, collecting first physiological data of the driver during the driving of the vehicle; During the driving process of the vehicle, the driver's physiological data is collected through the vehicle's built-in cameras, eye trackers, physiological sensors and other devices.

[0028] In actual applications, the driver's facial information, line of sight direction and gaze time can be obtained through the vehicle's built-in cameras and eye trackers; the driver's body information can be collected through physiological sensors, including: the driver's heart rate, skin electrical response and other body data; the in-car ambient sound information can be collected through a microphone, and the ambient sound information at least includes: the noise decibel of the ambient sound and the distribution of the main frequency bands.

[0029] The real-time driving state of the driver during driving can be determined based on the above physiological data. Different driving states have different sensitivities to prompt sounds with different audio characteristics.

[0030] Step 103, determining a first audio feature according to the first physiological data; In actual applications, the driver has different sensitivities to prompt sounds with different first audio features under different driving conditions. Therefore, the first audio feature determined by the driver's physiological data can ensure that the audio features of the prompt sound after subsequent processing can be quickly perceived by the driver under different driving conditions.

[0031] Step 104, determining a second audio feature according to the first physiological data and the prompt scenario; Different prompt tones are issued in different prompt scenarios. The prompt scenario of the prompt tone indicates the safety urgency of the prompt tone to a certain extent. In a more urgent situation, if the audio characteristics of the prompt tone cannot enable the driver to quickly perceive and then take corresponding actions, it will seriously threaten the safety of the driver and the drivers in the car. Therefore, it is necessary to determine the audio characteristics that are sensitive to the driver in different prompt scenarios, and then constrain the prompt tone to improve the reminder effect of the prompt tone on the driver.

[0032] Step 105, adjusting the initial prompt tone according to the first audio feature and the second audio feature to obtain a target prompt tone; In an embodiment of the present invention, the first audio feature represents an audio feature that is in line with the driver's habits and is sensitive to the prompt sound under different driving conditions. The second audio feature represents an audio feature that the driver can quickly perceive and then make corresponding operations in scenarios with different safety urgency levels. The initial prompt sound is adjusted according to the first audio feature and the second audio feature to obtain the target prompt sound. The prompt sound can be dynamically adjusted based on the driver's state, and then the prompt sound audio data can be dynamically adjusted according to changes in the driver's attention, driver feedback, differences in the driver's music preferences, and differences in the driver's perception of sound under different emotional states. A feature constraint mechanism is established according to the prompt sound prompt scenario, so that the prompt sound can allow the driver to quickly perceive and then make corresponding operations, thereby ensuring the reminder effect of the prompt sound on the driver.

[0033] Step 106: play the target prompt tone.

[0034] The target prompt sound played includes a first audio feature that matches the driver's driving state and a second audio feature that matches the prompt scenario, so that the target prompt sound ensures that the driver can quickly and sensitively perceive the target prompt sound and make corresponding responses under different driving states.

[0035] A vehicle prompt sound playback method provided by an embodiment of the present invention obtains an initial prompt sound and a prompt scene corresponding to the initial prompt sound, determines a first audio feature and a second audio feature according to the first physiological data of the driver and the prompt scene collected during vehicle driving; adjusts the initial prompt sound according to the first audio feature and the second audio feature, and obtains and plays a target prompt sound. By obtaining the first physiological data of the driver during vehicle driving to determine the first audio feature, the prompt sound can be dynamically adjusted based on the driver's state, and the second audio feature is determined based on the first physiological data and the prompt scene to establish a feature constraint mechanism for the prompt sound, so that the prompt sound is more in line with the driver's driving state while ensuring the prompt sound's reminder effect on the driver.

[0036] In one embodiment of the present invention, the step of obtaining an initial prompt tone of the vehicle includes: Get the current driver's identity information; Determine the corresponding audio preference features according to the identity information; the audio preference features at least include: music style features and volume features; The initial prompt sound is determined by performing feature matching in an initial prompt sound database according to the music style feature and / or the volume feature.

[0037] In an embodiment of the present invention, the identity of the driver in the vehicle can be determined through an in-vehicle camera or an associated vehicle owner account, and the audio preference characteristics corresponding to the identity information can be determined based on the identity information. Then, feature matching is performed in the initial prompt sound database based on the audio preference characteristics to filter out the initial prompt sound that meets the audio preference of the identity information.

[0038] In actual applications, different drivers have different favorite music styles and customary volumes, so the audio preference features corresponding to the identity information include at least music style features and volume features. The initial prompt sound with matching features can be screened out based on the music style features and volume features, so that the initial prompt sound meets the driver's preferences.

[0039] In an optional embodiment of the present invention, the audio preference characteristics may be determined by acquiring historical music records of a music software account that matches the identity information, or by presetting the audio preference characteristics of the identity information in the vehicle system.

[0040] In one embodiment of the present invention, the first physiological data includes: at least one of the driver's sight direction, the fixation time of the sight direction, facial information, body information, and ambient sound information; The determining a first audio feature according to the first physiological data includes: The first audio feature is determined according to the line of sight direction, the gaze time in the line of sight direction, and / or the facial information, the body information, and / or the ambient sound information.

[0041] In an embodiment of the present invention, the driver's facial information, line of sight direction and gaze time can be obtained through the vehicle's built-in camera and eye tracker; the driver's body information can be collected through physiological sensors, including: the driver's heart rate, skin electrical response and other body data; the in-car ambient sound information can be collected through a microphone, and the ambient sound information at least includes: the noise decibel of the ambient sound and the main frequency band distribution.

[0042] The line of sight direction, gaze time, facial information, body information, and ambient sound information can be used to determine the driver's real-time status through corresponding processing methods. Therefore, the first audio feature can be determined based on the line of sight direction, gaze time, and / or facial information, body information, and / or ambient sound information, and the prompt sound can be adjusted based on the first audio feature. Furthermore, the prompt sound audio data can be dynamically adjusted based on changes in the driver's attention, driver feedback, differences in the driver's music preferences, and differences in the driver's perception of sound under different emotional states.

[0043] In one embodiment of the present invention, the first audio feature includes: at least one of an audio rhythm feature, an audio melody feature, and an audio volume feature; The determining the first audio feature according to the sight direction, the gaze time of the sight direction, and / or the facial information, the body information, and / or the ambient sound information includes: Determining the attention level according to the sight direction and the gaze time, and the audio rhythm feature matching the attention level; and / or, Determining an emotional state based on the facial information and the body information, and the audio melody features matching the emotional state; and / or, An ambient noise level and the audio volume feature matching the noise level are determined according to the ambient sound information.

[0044] The vehicle's built-in cameras and eye trackers can be used to collect the driver's gaze direction and gaze time. By analyzing the driver's gaze direction and gaze time, the driver's concentration level and whether the driver is focused on the driving task can be determined. Based on the driver's attention level, the audio rhythm features that are sensitive to the driver in the current state can be determined.

[0045] After collecting the driver's heart rate, galvanic skin response, facial expressions and other physical information through physiological sensors, the collected physical information can be processed according to facial expression recognition technology and speech emotion recognition technology to judge the driver's emotional state, and then match the audio melody features suitable for the current emotional state based on the emotional state.

[0046] In actual applications, different emotional states are suitable for different audio melody characteristics. When the driver is anxious, use soft and soothing audio melodies to relieve the driver's tension; when the driver is happy, choose lively and cheerful melodies to enhance the driver's driving interest; when the driver is calm, use melodies familiar to the driver to bring the car and the driver closer together.

[0047] The microphone collects the noise decibels of the ambient sound in the car, analyzes the main frequency band distribution of the ambient sound, and then determines the ambient noise level. Based on the ambient noise level, the audio volume characteristics suitable for the current ambient sound state are matched to ensure that the driver can hear the prompt sound accurately and clearly and respond.

[0048] In actual applications, the driver's volume preference under different environmental noises can be comprehensively judged based on the driver's age and usual volume preference, as well as survey data on the hearing of different age groups, and then the audio volume characteristics suitable for the current ambient sound state can be matched based on the ambient noise level.

[0049] Specifically, in a quiet environment, the volume of the prompt sound is reduced, and the frequency can be appropriately integrated with the ambient frequency band; in a noisy environment, the volume of the prompt sound is increased, and the audio frequency band needs to be distinguished from the ambient frequency band in order to highlight the prompt sound. The threshold range of integration and distinction can be changed according to the safety urgency. The higher the urgency, the greater the distinction between the prompt audio band and the ambient audio band, and the lower the urgency, the smaller the distinction between the prompt audio band and the ambient audio band. This frequency band distinction mainly refers to the driver's perception, which can be achieved through sound wave interference. At the same time, it can be dynamically changed on the standard decibel line according to the hearing conditions of different drivers.

[0050] In an optional embodiment of the present invention, a matching mapping relationship between the dynamic change data obtained based on the physiological data and the audio feature may be preset to determine the first audio feature matching the first physiological data.

[0051] Reference Figure 2 , Figure 2 A mapping diagram between audio features and physiological data provided by an embodiment of the present invention: According to the driver's personality preference, the driver's preferred music style, timbre, frequency, volume and other audio characteristics are matched; According to the safety urgency of the scene, the audio features such as the number of beat points and beat speed are determined; Determine audio features such as rhythmic intensity and music richness based on the driver's attention level; Match and determine audio features such as timbre, volume, melody, etc. according to the driver's emotional state; The audio characteristics such as allocation and frequency band are determined according to the environmental noise and the driver's hearing condition.

[0052] Since different drivers have different physical conditions and real-time driving conditions, the corresponding audio features are quickly determined by establishing a matching mapping relationship between dynamically changing data and audio features. This allows the prompt sound audio data to be dynamically adjusted based on changes in driver attention, driver feedback, differences in the driver's music preferences, and differences in the driver's perception of sound under different emotional states. A feature constraint mechanism can also be established to ensure the prompt sound's reminder effect on the driver.

[0053] In practical applications, physical condition can include the driver's age and hearing level. Young people have better hearing conditions, and the volume can be lower than the standard line in a quiet environment; middle-aged and elderly people have poorer hearing conditions, and the volume can be appropriately higher than the standard line in a quiet environment, and the same applies to noisy environments.

[0054] In practical applications, the matching mapping relationship can be adjusted according to the driver's needs, and this application does not make any specific limitations on this.

[0055] In one embodiment of the present invention, determining the second audio feature according to the first physiological data and the prompt scene includes: Determining the safety level of the initial prompt sound according to the prompt scene, the driver's sight direction, and / or the gaze time in the sight direction; The second audio feature is determined according to the security level.

[0056] When obtaining the initial prompt sound of the vehicle, the prompt scene corresponding to the initial prompt sound will also be obtained. The prompt scene of the prompt sound indicates the safety urgency of the prompt sound to a certain extent. When the prompt scene of the initial prompt sound of the vehicle is a failure of a driving-related device, the safety urgency of the vehicle prompt sound is high. The determined second audio feature needs to ensure that the driver can quickly perceive and make corresponding processing. Therefore, if the audio feature of the prompt sound cannot enable the driver to quickly perceive and make corresponding operations when the safety urgency of the prompt sound is urgent, it will seriously threaten the safety of the driver and the drivers in the car.

[0057] In an embodiment of the present invention, the driver's line of sight direction and / or the gaze time in the line of sight direction are collected through a line of sight tracker and related vehicle control status. Based on the driver's line of sight direction and / or the gaze time in the line of sight direction, it is judged whether the driver's attention is highly focused on the driving task. The safety urgency of the scene is comprehensively judged in combination with the prompt scene. When the safety urgency of the scene is high, the audio rhythm is stronger and richer; when the safety urgency of the scene is low, the audio rhythm is weaker, more concise and clear, and the playback time is changed in real time according to the change of the driver's attention.

[0058] Specifically, before the initial prompt sound is played, when it is determined that the driver's attention is not highly focused on the driving task, the scene safety urgency can be set to high; conversely, before the alarm sound is played, if it is determined that the driver's attention is highly focused on the driving task, the scene safety urgency can be lowered to ensure the prompt sound's reminder effect on the driver.

[0059] In actual applications, the second audio feature emphasizes the matching of the number of audio beat points with the safety urgency. The scene safety urgency of the whole vehicle can be divided into high, medium and low. When the scene safety urgency is high, the number of audio beat points is "ding~ding~ding"; when the scene safety urgency is medium, the number of audio beat points is "ding~~ding~~"; when the scene safety urgency is low, the number of audio beat points is "ding~~~". Specifically, it can be defined according to actual conditions: one "~" is indicated at an interval of 50ms, and the interval between two "~" is "100ms". This feature is solidified and only matches the scene safety urgency. The number of beat points can be adjusted according to the driver's needs or the relevant requirements for prompt sounds in the area where the vehicle is located.

[0060] In an optional embodiment of the present invention, the scene safety urgency can be comprehensively judged based on physiological data and prompt scenarios, and the prompt scenarios can be divided into scene safety urgency levels. When the scene safety urgency level of the current prompt scenario is high, it is judged whether the driver's attention is highly focused on the driving task. If so, the scene safety urgency level is lowered, otherwise the scene safety urgency level is increased; then the corresponding second audio feature is determined based on the adjusted scene safety urgency level matching.

[0061] In one embodiment of the present invention, the second audio feature includes the number of audio beat points; The determining the second audio feature according to the security level includes: Determine the area where the current vehicle is located according to the prompt scene of the initial prompt sound and determine the corresponding function restriction strategy; the function restriction strategy includes a limited range of the number of audio beat points; Within the limited range, the number of audio beat points is determined according to the security level.

[0062] In an embodiment of the present invention, the second audio feature includes at least the number of beat points, and the audio feature is positively correlated with the safety urgency of the scene. The higher the safety urgency of the scene, the more beat points and the faster the speed; the lower the safety urgency of the scene, the fewer beat points and the slower the speed, thereby ensuring that the driver loses sensitivity to the safety urgency of the scene due to changes in the audio feature, thereby ensuring the reminder effect of the prompt sound on the driver.

[0063] In different regions, the restrictions on prompt sounds are different. In this embodiment, the functional constraint strategy of the region where the vehicle is located can be determined according to the prompt sound requirements of the region where the vehicle is located or the functional constraint strategy database preset in different regions, and the second audio feature can be adjusted according to the functional constraint strategy. Specifically, the second audio feature can also include playback time, volume, playback time, frequency band range, etc., and the functional constraint strategy can also include playback time limit, volume limit, playback time limit, frequency band range limit, etc.

[0064] Optionally, the function constraint strategy can be adjusted according to changes in the prompt sound requirements of the area where the vehicle is located or driver feedback to establish a more complete feature constraint mechanism to ensure the prompt sound has a reminder effect on the driver.

[0065] In an embodiment of the present invention, the adjusting the initial prompt tone according to the first audio feature and the second audio feature to obtain the target prompt tone includes: Selecting a preset number of the first audio features and the second audio features, adjusting the initial prompt sound, and obtaining a target prompt sound; or Based on the priorities of the first audio feature and the second audio feature, an audio feature whose priority meets a first preset condition is selected to adjust the initial prompt tone to obtain a target prompt tone.

[0066] In an embodiment of the present invention, after obtaining the first audio feature and the second audio feature based on the physiological data and the prompt scene matching, the initial prompt sound can be adjusted by integrating all the first audio features and the second audio features to improve the richness of the initial prompt sound, so that the prompt sound audio data can be dynamically adjusted according to the driver's attention changes, the driver's feedback, the driver's music preference differences and the driver's perception of sound in different emotional states. Alternatively, different priorities are preset for the first audio feature and the second audio feature, and audio features that meet the priority conditions are screened out, and the audio features that meet the priority conditions are highlighted in the adjusted initial prompt sound, so that the target prompt sound can dynamically adjust the prompt sound based on the driver's state while establishing a feature constraint mechanism to ensure the prompt sound's reminder effect on the driver.

[0067] In actual applications, the first audio feature includes at least an audio rhythm feature, an audio melody feature, and an audio volume feature, and the second audio feature includes at least the number of audio beat points. The priority of the number of audio beat points is set to 10, the priority of the audio rhythm feature is set to 7, the priority of the audio melody feature is set to 6, and the priority of the audio volume feature is set to 5. You can choose to highlight the audio features with a priority higher than 5 in the initial prompt sound to obtain the target prompt sound, or you can highlight all the audio features in the initial prompt sound to obtain the target prompt sound. The priority of different audio features can be set according to the driver's needs or the actual prompt effect, and this application does not impose any restrictions on this.

[0068] Optionally, during the playback of the target prompt tone, the driver's attention level and related driving operations are monitored in real time, and the playback duration of the target prompt tone, the number of audio beats, audio rhythm, audio volume and other audio features are dynamically controlled. For example, after the target prompt tone is issued, if the driver's attention level gradually returns to the driving task and performs related driving operations, and the safety urgency gradually decreases, the target prompt tone can gradually reduce the number of audio beats, slow down the audio rhythm, soften the tone or melody, and gradually transition to stop playing; after the target prompt tone is issued, if the driver immediately performs related driving operations or it is clearly known that the driver has understood the broadcast of the target prompt tone, the target prompt tone can be stopped immediately.

[0069] Reference Figure 3 , Figure 3 A schematic diagram of the steps of another vehicle prompt tone playing method provided by an embodiment of the present invention: Step S1, determining the driver's identity and obtaining audio features that match the driver's preferences; An audio feature matching the driver's preference is acquired according to the driver's identity, and then an initial prompt tone matching the audio feature is determined from an initial prompt tone database.

[0070] Step S2, determining an initial prompt tone and obtaining an audio instruction to be played; Step S3, judging the driver's attention level, when the driver's attention level is focused, determining the audio features with weak rhythm, clear and concise; when the driver's attention level is not focused, determining the audio features with strong rhythm, rich changes; In an embodiment of the present application, the driver's attention level includes whether the driver is focused on the driving task. When the driver's attention level is focused, that is, when the driver is focused on the driving task, an audio feature with a weak sense of rhythm, clear and concise is determined. At this time, the audio feature reminder intensity is low, which can avoid causing interference to the driver; when the driver's attention level is not focused, that is, when the driver is not focused on the driving task, an audio feature with a strong sense of rhythm and rich changes is determined. At this time, the audio feature reminder intensity is high, aiming to draw the driver's attention back to the driving task.

[0071] Step S4, judging the emotional state of the driver, when the emotional state of the driver is pleasant, determining the audio features of lively and cheerful melodies; when the emotional state of the driver is anxious, determining the audio features of soft and soothing melodies; The driver's emotional state in different scenarios is judged to match the corresponding audio features, and the timbre of the sound is dynamically adjusted to match the audio features with the driver's emotional state. This can better help the driver stay relaxed in anxious scenarios and maintain a better state in pleasant scenarios.

[0072] Step S5, determining the ambient noise level, when the ambient noise level is quiet, determining the audio features of reduced decibels and fusion of the frequency band with the environment; when the ambient noise level is loud, determining the audio features of increased decibels and differentiation of the frequency band with the environment; By matching audio features with ambient noise, the volume and audio frequency band selection can be more targeted and more suitable for different environments. In a quiet environment, the audio features with reduced decibels and appropriate frequency integration with the ambient frequency band are matched; in a noisy environment, the audio features with increased decibels and audio frequency bands that need to be distinguished from the ambient frequency band are matched to highlight the target prompt sound.

[0073] Optionally, the driver's volume preference under different environmental noises can be comprehensively judged based on the driver's age and usual volume preference, as well as survey data on hearing of different age groups, and then the audio volume characteristics suitable for the current ambient sound state can be matched based on the ambient noise level, so that the audio characteristics of the prompt sound can be matched with the driver's hearing condition, thereby satisfying the hearing preferences of different groups of people.

[0074] Step S6: adjust the initial audio and play the target prompt tone.

[0075] After the corresponding audio features are obtained based on the driver's attention level, emotional state, and ambient noise, all audio features are fused to improve the richness of the initial prompt sound, so that the prompt sound audio data can be dynamically adjusted according to the driver's attention changes, driver feedback, differences in the driver's music preferences, and differences in the driver's perception of sound under different emotional states, or the highest priority audio features are highlighted so that the target prompt sound can dynamically adjust the prompt sound based on the driver's state while establishing a feature constraint mechanism to ensure the prompt sound's reminder effect on the driver.

[0076] By obtaining the initial prompt sound and the prompt scene corresponding to the initial prompt sound, the first audio feature and the second audio feature are determined according to the first physiological data of the driver and the prompt scene collected during the driving of the vehicle; the initial prompt sound is adjusted according to the first audio feature and the second audio feature to obtain and play the target prompt sound. By obtaining the first physiological data of the driver during the driving of the vehicle to determine the first audio feature, the prompt sound can be dynamically adjusted based on the driver's state, and the second audio feature is determined based on the first physiological data and the prompt scene to establish a feature constraint mechanism for the prompt sound, so that the prompt sound is more in line with the driver's driving state while ensuring the reminder effect of the prompt sound on the driver.

[0077] In one embodiment of the present invention, after playing the target prompt tone, the method further includes: Acquiring a second physiological characteristic of the driver to the target prompt sound after playing the target prompt sound; When the second physiological characteristic meets the preset condition, the voice feedback corresponding to the target prompt sound is output.

[0078] While the target prompt sound is being played, the driver's voice and facial data can be collected in real time through the microphone and the in-vehicle camera, the prompt sound that confuses the driver can be identified, and corresponding voice feedback or prominent visual feedback can be given.

[0079] Specifically, after some alarm sounds are issued, when it is recognized that the driver's expression is confused and the emotion changes from positive to negative, or when the voice recognition detects that the driver is complaining and is not clear about what happened, the driver can be given voice feedback in real time to explain the current situation and the reason for the target prompt sound, and visual feedback can be highlighted to alleviate the driver's negative emotions caused by doubts.

[0080] In an optional embodiment of the present invention, after playing the target prompt sound, the driver's attention level and related driving operations are monitored in real time, and the playing duration, number of beats, speed, tone and other audio characteristics of the target prompt sound are dynamically controlled.

[0081] In actual applications, after the target prompt sound is issued, the driver's attention level gradually returns to the driving task and performs relevant driving operations, and the safety urgency of the scene gradually decreases. The prompt sound can gradually reduce the beat points, slow down the speed, soften the tone or melody, and gradually stop playing; after the template prompt sound is issued, if the driver immediately performs relevant driving operations or it is clearly known that the driver has understood the alarm situation, the alarm sound can be stopped immediately.

[0082] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0083] An embodiment of the present invention further provides a vehicle prompt sound playing system, which is used to execute the steps in the above-mentioned vehicle prompt sound playing method.

[0084] In an embodiment of the present invention, an adaptive system can be constructed in which the in-vehicle alarm prompt audio matches the scene safety urgency, the driver's personality preference, the driver's attention level, the driver's emotional state, the ambient noise, and the driver's hearing condition. The system consists of two parts: one is the functional constraint layer, which emphasizes the matching of audio beat points, beat speed and safety urgency. For example, the safety urgency of the whole vehicle scene is divided into high, medium and low. When the scene safety urgency is high, the number of audio beat points is "ding~ding~ding", when the scene safety urgency is medium, the number of audio beat points is "ding~~ding~~", and when the scene safety urgency is low, the number of audio beat points is "ding~~~". Specifically, it can be defined according to actual conditions: one "~" is indicated with an interval of 50ms, and the interval between two "~" is "100ms". This feature is solidified and only matches the safety urgency of the scene; the other part is the dynamic change layer, which emphasizes the matching of music style, timbre, frequency, etc. with the driver's music preference, the strength of rhythm, the matching of audio richness with the driver's attention level, the matching of timbre, volume, melody with the driver's emotional state, and the matching of decibels, frequency bands with ambient noise and the driver's hearing conditions. The audio features of the dynamically changing layer can be updated in a timely manner according to the driver's perceived differences and preferences, and real-time monitoring can be carried out to determine whether the characteristic changes of the audio meet the driver's expectations under different conditions, including but not limited to the improvement of the driver's attention level, the improvement of the driver's emotional state, and whether the decibel level of the volume is appropriate. The adaptive system can also be continuously optimized based on the collected data.

[0085] By obtaining the initial prompt sound and the prompt scene corresponding to the initial prompt sound, the first audio feature and the second audio feature are determined according to the first physiological data of the driver and the prompt scene collected during the driving of the vehicle; the initial prompt sound is adjusted according to the first audio feature and the second audio feature to obtain and play the target prompt sound. By obtaining the first physiological data of the driver during the driving of the vehicle to determine the first audio feature, the prompt sound can be dynamically adjusted based on the driver's state, and the second audio feature is determined based on the first physiological data and the prompt scene to establish a feature constraint mechanism for the prompt sound, so that the prompt sound is more in line with the driver's driving state while ensuring the reminder effect of the prompt sound on the driver.

[0086] As for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0087] The embodiment of the present invention further provides a vehicle, comprising the steps in the vehicle prompt sound playing method described above, or comprising the vehicle prompt sound playing system described above. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0088] Finally, it should be noted that the driver information (including but not limited to driver equipment information, driver personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the driver or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for drivers to choose to authorize or refuse.

[0089] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0090] The above is a detailed introduction to a vehicle prompt sound playback method, a vehicle prompt sound playback system and a corresponding vehicle provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A vehicle prompt sound playing method, characterized in that: The method comprises: Obtaining an initial prompt sound of the vehicle and a prompt scene corresponding to the initial prompt sound; collecting first physiological data of the driver during the driving of the vehicle; determining a first audio feature according to the first physiological data; determining a second audio feature according to the first physiological data and the prompt scenario; Adjusting the initial prompt tone according to the first audio feature and the second audio feature to obtain a target prompt tone; Play the target prompt tone.

2. The method according to claim 1, characterized in that The obtaining of the initial prompt tone of the vehicle comprises: Get the current driver's identity information; Determine the corresponding audio preference features according to the identity information; the audio preference features at least include: music style features and volume features; The initial prompt sound is determined by performing feature matching in an initial prompt sound database according to the music style feature and / or the volume feature.

3. The method according to claim 1, characterized in that The first physiological data includes: at least one of the driver's sight direction, the fixation time of the sight direction, facial information, body information, and ambient sound information; The determining a first audio feature according to the first physiological data includes: The first audio feature is determined according to the line of sight direction, the gaze time in the line of sight direction, and / or the facial information, the body information, and / or the ambient sound information.

4. The method according to claim 3, characterized in that: The first audio feature includes: at least one of an audio rhythm feature, an audio melody feature, and an audio volume feature; The determining the first audio feature according to the sight direction, the gaze time of the sight direction, and / or the facial information, the body information, and / or the ambient sound information includes: Determining the attention level according to the sight direction and the gaze time, and the audio rhythm feature matching the attention level; and / or, Determining an emotional state based on the facial information and the body information, and the audio melody features matching the emotional state; and / or, An ambient noise level and the audio volume feature matching the noise level are determined according to the ambient sound information.

5. The method according to claim 1, characterized in that The determining of the second audio feature according to the first physiological data and the prompting scene includes: Determining the safety level of the initial prompt sound according to the prompt scene, the driver's sight direction, and / or the gaze time in the sight direction; The second audio feature is determined according to the security level.

6. The method according to claim 5, characterized in that The second audio feature includes the number of audio beats; The determining the second audio feature according to the security level includes: Determine the area where the current vehicle is located according to the prompt scene of the initial prompt sound and determine the corresponding function restriction strategy; the function restriction strategy includes a limited range of the number of audio beat points; Within the limited range, the number of audio beat points is determined according to the security level.

7. The method according to claim 1, characterized in that The adjusting the initial prompt tone according to the first audio feature and the second audio feature to obtain a target prompt tone includes: Selecting a preset number of the first audio features and the second audio features, adjusting the initial prompt sound, and obtaining a target prompt sound; or Based on the priorities of the first audio feature and the second audio feature, an audio feature whose priority meets a first preset condition is selected to adjust the initial prompt tone to obtain a target prompt tone.

8. The method according to claim 1, after playing the target prompt tone, further comprising: Acquiring a second physiological characteristic of the driver to the target prompt sound after playing the target prompt sound; When the second physiological characteristic meets the preset condition, the voice feedback corresponding to the target prompt sound is output.

9. A vehicle prompt sound playing system, characterized in that: The vehicle prompt sound playing system is used to execute the steps in the vehicle prompt sound playing method as described in any one of claims 1 to 8.

10. A vehicle, characterized in that: It includes the vehicle prompt sound playing method as described in any one of claims 1 to 8, or includes the vehicle prompt sound playing system as described in claim 9.

Images