CN112951227B - Vehicle voice control method - Google Patents
Vehicle voice control method Download PDFInfo
- Publication number
- CN112951227B CN112951227B CN202110128255.6A CN202110128255A CN112951227B CN 112951227 B CN112951227 B CN 112951227B CN 202110128255 A CN202110128255 A CN 202110128255A CN 112951227 B CN112951227 B CN 112951227B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- area
- control
- audio signal
- instruction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000005236 sound signal Effects 0.000 claims abstract description 128
- 238000012937 correction Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 16
- 230000000694 effects Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L2021/02161—Number of inputs available containing the signal or the noise to be suppressed
- G10L2021/02166—Microphone arrays; Beamforming
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
Abstract
The invention discloses a vehicle voice control method, which comprises the following steps: step one, determining an area for sending out an audio signal; step two, identifying the audio signal, judging the attribute of the passenger sending the audio signal, and judging the control instruction corresponding to the audio signal; step three, judging whether the control instruction is an executable instruction according to the area for sending out the audio, the attribute of the passenger sending out the audio signal and the control instruction corresponding to the audio signal; and step four, when the control instruction is an executable instruction, controlling the vehicle to execute the control instruction.
Description
Technical Field
The invention belongs to the technical field of voice control of vehicles, and particularly relates to a vehicle voice control method.
Background
Along with the development of vehicle technology, more and more vehicles are equipped with voice control function for the driver can control the vehicle through pronunciation when driving, can promote the intelligent degree of vehicle when guaranteeing driving safety, can also promote the driving enjoyment.
To achieve voice control of a vehicle, manufacturers typically install microphones in the driving area of the vehicle so that the vehicle can perform corresponding operations based on audio signals received by the microphones. However, in practical use, since the microphone is only installed in the driving area, when the co-driver or the rear passenger wants to perform voice control, the audio signal cannot be accurately received by the microphone due to the too far distance, and thus, the situation that voice cannot be recognized or recognition errors occur may occur. Therefore, this vehicle voice control method can only accurately perform the audio signal emitted by the driver, and does not perform well for the audio signals emitted by the co-driver and rear passengers.
In order to improve the voice control effect of the co-driver and the rear passengers on the vehicles, some vehicles are additionally provided with microphones in the co-driver area and the rear passenger area respectively, audio signals in the cockpit are received through the three microphones, and corresponding operations are executed according to the received audio signals, so that the driver, the co-driver and the rear passengers can accurately control various functions of the vehicles through the sent audio signals.
But the voice control effect of the vehicle is improved by the method of additionally installing the microphone, so that the voice control effect of the vehicle can only receive the audio signals in the cockpit more accurately, and the difference between the driver and other passengers in the vehicle can not be distinguished. Slightly insufficient in humanization and intelligence. If the co-driver or the rear passenger gives out an instruction for influencing the running of the vehicle during the running process of the vehicle, for example, if the co-driver or the rear passenger gives out a control instruction for adjusting the rearview mirror or controlling the swinging of the windshield wiper, the vehicle can cause harm to running safety after executing the control instruction.
In addition, the current voice control system runs in the whole course after the vehicle is started, and some special conditions are inevitably met in the running process of the vehicle, so that the safety of the vehicle driving is temporarily reduced, and if the rear passengers or passengers in the copilot area perform voice control on the vehicle at the moment, some activities for improving comfortableness or entertainment are performed, the normal driving of the driver can be influenced, and dangerous conditions are caused.
Disclosure of Invention
One of the objects of the present invention is to provide a vehicle voice control method capable of determining whether to execute the instruction according to an emission area of an audio signal, a passenger attribute of the audio emission area, and an instruction authority of the area; the vehicle voice control method can ensure the driving safety of the vehicle while realizing the vehicle voice control.
The second object of the present invention is to determine whether the running state of the vehicle satisfies the full-area control state according to the running state index of the vehicle, and to ignore the control instructions issued from the co-driver zone and the rear passenger zone when the running state of the vehicle does not satisfy the full-area control state, so as to further improve the driving safety of the vehicle.
The technical scheme provided by the invention is as follows:
a vehicle voice control method, comprising:
step one, determining an area for sending out an audio signal;
step two, identifying the audio signal, judging the attribute of the passenger sending the audio signal, and judging the control instruction corresponding to the audio signal;
step three, judging whether the control instruction is an executable instruction according to the area for sending out the audio, the attribute of the passenger sending out the audio signal and the control instruction corresponding to the audio signal;
and step four, when the control instruction is an executable instruction, controlling the vehicle to execute the control instruction.
Preferably, the audio signal emitting area includes a main driving area, a co-driving area, and a rear passenger area.
Preferably, the passenger attribute information includes a sex and an age of a passenger.
Preferably, before the third step, the method further includes setting instruction authority corresponding to the area where the audio signal is sent; when the control instruction sent by the area sending the audio signal is in the range of the corresponding instruction authority, performing the step three; otherwise, the control instruction is ignored.
Preferably, the instruction authority corresponding to the main driving area is the whole vehicle control authority;
the instruction authority corresponding to the copilot region at least comprises: video/audio play rights, navigation rights or co-pilot seat adjustment rights;
the instruction authority corresponding to the rear passenger area at least comprises: video/audio playback rights and rear-end audio control rights.
Preferably, in the fourth step, the method further includes:
judging whether the running state of the current vehicle meets the full-area control state or not;
when the control instruction is an executable instruction and the vehicle running state meets the full-area control state, controlling the vehicle to execute the control instruction; otherwise, the control instructions sent by the co-driving area and the rear passenger area are ignored.
Preferably, whether the running state of the vehicle satisfies the full area control state is determined according to the running state index of the vehicle;
wherein, the running state index of the vehicle is:
wherein delta represents the centroid deflection angle of the vehicle, V represents the vehicle speed and V max The vehicle speed represents the maximum vehicle speed, sr represents the wheel slip rate, eta represents a correction coefficient, and lambda represents a driving environment coefficient;
wherein, when Rs > 0.6, the running state of the vehicle satisfies the full-area control state;
when Rs is less than or equal to 0.6, the formal state of the vehicle does not satisfy the full-area control state.
Preferably, when the value of the absolute value delta is less than 8, the value range of eta is 1.15 to 1.10;
when the delta is more than or equal to 8, the value range of eta is 0.85 to 0.9.
Preferably, the driving environment coefficient is:
wherein lambda is 0 Represents a reference environmental coefficient, I represents the light intensity of the driving environment, I 0 Represents the reference light intensity, T represents the driving environment temperature, T 0 Indicating a reference temperature.
Preferably, when the road surface is an icy or snowy road surface, lambda 0 The value range of (2) is 0.5-0.6;
lambda when the road surface is a non-icy road surface 0 The range of the value of (2) is 0.9-1.0.
The beneficial effects of the invention are as follows:
the vehicle voice control method provided by the invention can determine whether to execute the instruction according to the emission area of the audio signal, the attribute of the passenger in the audio emission area and the instruction authority of the area; the vehicle voice control method can ensure the driving safety of the vehicle while realizing the vehicle voice control.
The vehicle voice control method provided by the invention can determine whether the running state of the vehicle meets the full-area control state according to the running state index of the vehicle, and when the running state of the vehicle does not meet the full-area control state, control instructions sent by the copilot area and the rear passenger area are ignored, so that the driving safety of the vehicle is further improved.
Drawings
Fig. 1 is a schematic diagram of a vehicle voice control system according to the present invention.
Detailed Description
The present invention is described in further detail below with reference to the drawings to enable those skilled in the art to practice the invention by referring to the description.
The invention provides a vehicle voice control method which is realized based on a vehicle voice control system.
As shown in fig. 1, the vehicle voice control system includes: a main microphone 102, a sub microphone 102, a rear microphone 103, a delay processing module 104, a position determination module 105, an audio noise reduction module 106, an audio execution module 107, a software processing module 108, a sound quality discriminating module 109, and an application execution module 110.
The main microphone 102 is disposed in the main driving area, and is used for recording the audio signal and driving noise of the passengers. The secondary microphone 102 is disposed in the secondary driving area, and is used for recording the audio signal and driving noise of the passengers. The rear microphone 103 is provided in the rear passenger area for recording an audio signal of a passenger and driving noise.
The delay processing module 104 is configured to perform phase processing on the recorded three sets of audio signals, correct phase delays of the three sets of audio signals, and integrate phases of the three sets of audio signals into the same phase. Because the distances between the three microphones and passengers who send out audio signals are different, the three microphones can generate sequence when recording the audio signals, so that phase differences appear among the recorded three groups of audio signals to generate phase delay, and the delay processing module is required to process the phase.
The delay processing module 104 is also configured to send the phase differences of the three groups of audio signals to the position determining module 105, and send the three groups of audio signals with the same phase after being sorted to the audio noise reduction module 106.
The position determination module 105 is configured to receive the phase differences of the three sets of audio signals, determine an area where a passenger who sends the audio signals is located according to the phase differences, generate area information according to the determined area, and send the area information to the audio execution module 107.
The audio noise reduction module 106 is configured to receive three sets of audio signals with the same phase, perform noise reduction processing on the received three sets of audio signals to obtain a pure audio signal, and send the obtained pure audio signal to the audio execution module 107.
The audio execution module 107 is configured to receive the area information and the clean audio signal, send the received area information and clean audio signal to the software processing module 108, and determine whether the clean audio signal needs to be detected according to the area information, and send the clean audio signal to the sound quality distinguishing module 109 if the clean audio signal needs to be detected.
The software processing module 108 is configured to receive the clean audio signal and the area information, and convert the received clean audio signal into a control command that can be recognized by the vehicle. And transmits the location information and the control instruction to the application execution module 110.
The voice quality distinguishing module 109 is configured to receive and analyze the clean audio signal, obtain attribute information of the sounding passenger, and send the obtained attribute information to the application executing module 110.
The application execution module 110 is used for receiving the region information, the control instruction and attribute information of the sounding passenger. Judging whether the control authority of the area comprises a designated authority according to the area information and the control instruction, wherein the designated authority is the authority for executing the control instruction. If the permission is included, the attribute information and the control instruction of the sounding passenger are comprehensively analyzed, and the analysis result is sent to each corresponding execution module of the vehicle, the vehicle execution module comprises a vehicle-mounted sound entertainment unit, a seat adjusting unit and the like, the embodiment of the invention is not particularly limited to the above, the vehicle-mounted sound entertainment unit is used for searching and playing music and the like according to the control instruction, and the embodiment of the invention is not particularly limited to the above.
The audio signal is an electric signal, and expresses the tone, intensity and tone of the voice command sent by the person through frequency, amplitude and phase.
In the embodiment of the invention, the vehicle collects the audio signals sent by passengers through three microphones at the same time. The three microphones are used for collecting the audio signals, so that the range of receiving the audio signals is enlarged, and the aim that passengers in three different areas can carry out voice control on the vehicle is fulfilled.
After the three groups of microphones collect the audio signals sent by passengers, the collected audio signals are sent to the delay processing module.
The vehicle determines the area where the passenger who sends out the audio signal is located according to the received audio signal.
The vehicle can judge which microphone receives the audio signals first according to the phase difference of the three groups of audio signals, and can determine the area of the passenger sending the audio signals according to the area of the microphone. Because the setting areas of the microphones are different, the source areas of the audio signals are distinguished, the purpose of distinguishing a driver from other passengers in the vehicle can be achieved, the audio signals sent by the passengers can be firstly collected by the microphone closest to the passenger, and therefore phase differences can occur in three groups of audio signals received by the vehicle, and the areas can be determined based on the phase differences among the audio signals.
In the embodiment of the invention, after the delay processing module receives the audio signals collected by the three groups of microphones, the phase difference of the received three groups of audio signals is sent to the position judging module, the position judging module judges the area where the passenger who starts the audio signals is located according to the received phase difference, generates area information according to the judged area, and sends the area information to the audio executing module.
Further, since the microphone collects the driving noise of the vehicle while collecting the audio signal, in order to improve the recognition effect of the vehicle on the audio signal, the collected audio signal is subjected to noise reduction, and the noise reduction process is as follows:
and after receiving the audio signals collected by the three groups of microphones, the delay processing module obtains three groups of audio signals with the same phase through phase processing. And the delay processing module sends the three groups of audio signals with the same phase to the audio noise reduction module. And after the audio noise reduction module receives three groups of audio signals with the same phase, the three groups of audio signals are subjected to superposition processing to obtain a group of audio signals, and the superimposed group of audio signals are subjected to noise reduction processing in a mode of increasing the signal to noise ratio, so that the noise reduction effect is achieved, and the pure audio signals are obtained.
In an actual scene, in order to better distinguish a driver from other passengers in a vehicle, two different execution modes can occur for the vehicle according to different areas where the passengers sending out audio signals are located, and when the area where the passengers sending out audio signals are located is a passenger area or a rear passenger area, the method specifically comprises the following steps:
when the vehicle determines that the area emitting the audio signal is a co-driver area or a rear passenger area, the audio signal is detected, and attribute information of a passenger emitting the audio signal is obtained.
Wherein the attribute information includes at least gender and age.
At least one of tone, intensity and pitch of the passenger's voice is determined based on the phase, frequency and intensity of the audio signal, and information that can be used to distinguish gender or age is determined, so that attribute information of the passenger can be obtained based on the tone, intensity and pitch. The attribute information is acquired for the purpose of playing music, navigating scenic spots, etc. when the audio signal sent by the passenger is a certain type of instruction and no content is specifically executed, and the embodiment of the invention is not limited to the specific one. The vehicle can analyze its interest according to the age and sex of the passenger, and perform a corresponding operation within the range of its interest. For example, when the passenger sends out an audio signal of "play music", the vehicle can play songs within the interest range of the passenger according to the acquired attribute information, for example, the vehicle acquires the attribute information of the passenger as a female aged 5-10 years, and the child song is preferentially played when the instruction of playing the songs is correspondingly executed. The voice control function of the vehicle is more intelligent.
In the embodiment of the invention, after the audio execution module receives the region information and the clean audio signal, when the received region information shows that the region where the passenger sending the audio signal is located is a co-driver region or a rear passenger region, the audio execution module sends the received clean audio signal to the sound quality judgment module, and the sound quality judgment module judges the attribute information of the co-driver or rear passenger sending the audio signal according to the received clean audio signal. And after judging the attribute information, the tone quality judging module sends the attribute information to the application executing module.
Because the audio signals collected by the microphone cannot be identified by each execution module of the vehicle, the vehicle needs to convert the collected audio signals into control instructions which can be identified by each execution module, so that each execution module of the vehicle can execute corresponding operations according to the control instructions, and the voice control function of the vehicle is realized. The control instruction may be a text signal or a program code, which is not limited in particular in the embodiment of the present invention. The process of converting the audio signal into identifiable control instructions is:
the audio execution module sends the received region information and the clean audio signal to the software processing module. After receiving the pure audio signal and the area information, the software processing module analyzes the pure audio signal, converts the audio signal into a control instruction, and then sends the received area information and the control instruction obtained by conversion to the application execution module.
When the vehicle determines that the control authority of the co-driving area or the rear passenger area comprises the appointed authority, the vehicle is controlled according to the control instruction corresponding to the audio signal, wherein the appointed authority is the authority for executing the control instruction.
In the embodiment of the invention, the vehicle voice control system can set different control authorities for passengers in different areas, the authorities in the control authorities are exclusive authorities of the passengers in the areas, the authorities outside the control authorities are forbidden authorities of the passengers in the areas, and the control instruction is selectively executed according to the set control authorities, so that the driver in the vehicle is more effectively distinguished from other passengers, the driving safety is ensured, and the humanization and the intelligence are obviously improved.
Wherein, the exclusive authority of the copilot area includes: video/audio play authority, navigation authority, co-pilot seat adjustment authority, etc., which are not particularly limited in the embodiment of the present invention.
The prohibition rights of the copilot include: the control authority of the main driving seat, the control authority of the vehicle window, the rearview mirror and the like affecting the driving safety, the related control authority related to the privacy of the driver such as the vehicle information and the owner information, the related function control authority of the rear-row sound equipment and the like, and the embodiment of the invention is not particularly limited to the above.
The control authority of the rear passenger area is as follows: video/audio playing authority, rear-row sound function control authority, etc., which are not particularly limited in this embodiment of the present invention.
The forbidden authority of the rear passenger zone comprises: the embodiments of the present invention are not limited specifically as such, and dialing bluetooth phone authority, navigation authority, control authority of main driving and co-driving seats, control authority affecting driving safety such as windows and rearview mirrors, or related control authority related to privacy of drivers such as vehicle information and owner information, etc.
When the vehicle judges that the authority of the control instruction corresponding to the audio signal sent by the passenger belongs to the unique authority of the area, the control instruction is executed, and the specific process of determining and executing is as follows:
the application execution module is used for storing the exclusive authority and the forbidden authority of each area in advance, judging according to the received control instruction and the area information after receiving the attribute information sent by the tone quality judging module and the area information and the control instruction sent by the software processing module, comprehensively analyzing the received attribute information, the received area information and the received control instruction by the application execution module when the authority of the control instruction is within the exclusive authority of the area, and correspondingly controlling the vehicle according to the analysis result.
Furthermore, when information prompt is needed, if the regional information is displayed as an audio signal sent by the co-driver zone, the information is prompted on the vehicle-mounted display screen in a text display mode, so that the co-driver can accurately acquire the prompt information through the vehicle-mounted display screen; and if the area information is displayed as an audio signal sent by a rear passenger area, prompting by adopting two modes of vehicle-mounted sound voice broadcasting and vehicle-mounted display screen text display. The vehicle information prompting process comprises the following steps: after the vehicle generates the prompt text, when the prompt information is required to be displayed for the copilot, all the prompt text is acquired and displayed on the vehicle-mounted display screen, and when the prompt information is required to be displayed for the rear passengers, keywords in the prompt text are extracted and displayed on the vehicle-mounted display screen. Furthermore, the keywords can be converted into audio signals during display, and voice broadcasting is performed through the vehicle-mounted sound equipment.
When the vehicle determines that the control authority of the co-driving area or the rear passenger area does not comprise the designated authority, the control instruction corresponding to the audio signal is ignored.
When the vehicle judges that the authority of the control instruction corresponding to the audio signal sent by the passenger does not belong to the control authority of the area, the authority of the control instruction of the audio signal is indicated to be the forbidden authority of the area, the control instruction is ignored, and the specific process of the determination is as follows:
the application execution module is used for storing the forbidden authorities of the co-driving area and the rear passenger area in advance, judging according to the received control instruction and the area information after receiving the attribute information sent by the tone quality judging module and the area information and the control instruction sent by the software processing module, and stopping the operation of the corresponding control instruction by the application execution module when the authority of the control instruction is within the forbidden authority of the area.
Further, when the vehicle determines that the authority of the control instruction belongs to the prohibition authority, a corresponding prohibition reason is generated according to the prohibition authority, and prompt of the prohibition reason is performed through a vehicle-mounted display screen and/or a vehicle-mounted sound box and the like.
And when the vehicle determines that the area is the main driving area, executing the step of controlling the vehicle according to the control instruction corresponding to the audio signal.
The main driving has the whole vehicle control right, and the control right of the main driving comprises: the embodiments of the present invention are not limited in particular, and the video/audio play authority, navigation authority, main driving and co-driving seat adjustment authority, control authority affecting driving safety such as windows and rearview mirrors, related control authority related to privacy of drivers such as vehicle information and owner information, or related function control authority related to front and rear sound.
In another embodiment, after the audio execution module receives the region information and the clean audio signal, when the received region information shows that the region where the passenger who sends the audio signal is located is the main driving region, the audio execution module sends the received two information to the software processing module. After receiving the clean audio signal and the area information, the software processing module analyzes the clean audio signal, converts the audio signal into a control instruction which can be identified by the application execution module, and then sends the received area information and the control instruction obtained by conversion to the application execution module. Because the main driving has the whole vehicle control authority, the application execution module directly controls the vehicle according to the received control instruction.
After three microphones in the vehicle collect the audio signals in the cockpit, the area where the sounding passengers are located and the control authority of the area are determined according to the three groups of audio signals, if the control instruction corresponding to the audio signals is in the control authority of the control instruction, the control instruction is executed, and if the control instruction is not in the control authority of the control instruction, the control instruction is not executed. The vehicle is divided into the areas and different control authorities are set for different areas, so that the control instruction is selectively executed, the voice control effect of the vehicle is improved, meanwhile, drivers and other passengers in the vehicle are effectively distinguished, the driving safety is ensured, and the vehicle is obviously improved in humanization and intelligence.
Further, when the received audio signal of the main driving is a certain type of instruction and no specific execution content is available, the application execution module executes corresponding operations according to the prestored interest of the main driving.
Still further, when information prompt is needed, if the area is the main driving, the prompt is performed in a voice playing mode, wherein the prompt of the main driving is to acquire all prompt characters, convert all the prompt characters into audio signals and perform voice broadcasting through the vehicle-mounted sound equipment.
As a further preferred embodiment of the present invention, the vehicle condition monitoring and processing module further includes a vehicle condition monitoring and processing module for acquiring new information of a running condition of the vehicle and driving environment information of the vehicle by installing a sensor on the vehicle or by a vehicle CAN bus, including: the vehicle state monitoring and processing module is electrically connected with the application execution module 110, and the application execution module 110 synthesizes the vehicle state information and the regional information of the emitted audio, the control instruction and the attribute information of the sounding passengers to carry out comprehensive judgment and execute voice control on the vehicle. The specific method comprises the following steps:
judging whether the running state of the current vehicle meets the full-area control state according to the vehicle state; when the voice frequency command can be executed according to the voice frequency emitting area information, the control command and the attribute information of the sounding passenger, and the running state of the vehicle meets the full area control state, controlling the vehicle to execute the voice frequency control command; otherwise, the control instructions sent by the co-driving area and the rear passenger area are ignored, and only the control instructions sent by the main driving area can be independently executed.
In one embodiment of the present invention, whether the running state of the vehicle satisfies the full area control state is determined according to the running state index of the vehicle;
wherein, the running state index of the vehicle is:
wherein delta represents the centroid deflection angle of the vehicle, and the unit is degree; v represents the speed of the vehicle, V max The maximum vehicle speed is expressed, and the unit is Km/h; sr represents the wheel slip ratio, eta represents a correction coefficient, and lambda represents a driving environment coefficient. Maximum vehicle speed V max The speed limit of the road section on which the vehicle is located can be set.
Wherein, when Rs > 0.6, the running state of the vehicle satisfies the full-area control state; when Rs is less than or equal to 0.6, the formal state of the vehicle does not satisfy the full-area control state.
The calculation method of the wheel slip ratio comprises the following steps:
where v 'is the theoretical vehicle speed, v is the actual speed, v' =rw, r is the radius of the driving wheels of the vehicle, and w is the angular speed of the driving wheels.
When the delta is less than 8, the value range of eta is 1.15 to 1.10; preferably, η=1.15 is set.
When the delta is more than or equal to 8, the value range of eta is 0.85 to 0.9; preferably, η=0.85 is set.
Wherein, the driving environment coefficient is:
wherein lambda is 0 Represents a reference environmental coefficient, I represents the light intensity of the driving environment, I 0 Represents the reference light intensity, T represents the driving environment temperature, T 0 The reference temperature is expressed in degrees celsius.
Wherein lambda is when the road surface is ice and snow road surface 0 The value range of (2) is 0.5-0.6; lambda when the road surface is a non-icy road surface 0 The range of the value of (2) is 0.9-1.0. According to experience, I 0 The range of the value of (C) is 150-200 Lux, T 0 The value range of (2) is 20-25 ℃.
In another embodiment, whether the road surface is an icy road surface or not may be obtained based on big data recognition after the camera collects the road surface image.
In summary, the vehicle voice control method provided by the invention can determine whether to execute the instruction according to the emission area of the audio signal, the attribute of the passenger in the audio emission area and the instruction authority of the area; the vehicle voice control method can ensure the driving safety of the vehicle while realizing the vehicle voice control. The invention can also determine whether the running state of the vehicle meets the full-area control state according to the running state index of the vehicle, and when the running state of the vehicle does not meet the full-area control state, the control instructions sent by the copilot area and the rear passenger area are ignored, so that the driving safety of the vehicle is further improved.
Although embodiments of the present invention have been disclosed above, it is not limited to the details and embodiments shown and described, it is well suited to various fields of use for which the invention would be readily apparent to those skilled in the art, and accordingly, the invention is not limited to the specific details and illustrations shown and described herein, without departing from the general concepts defined in the claims and their equivalents.
Claims (7)
1. A vehicle voice control method, characterized by comprising:
step one, determining an area for sending out an audio signal;
step two, identifying the audio signal, judging the attribute of the passenger sending the audio signal, and judging the control instruction corresponding to the audio signal;
step three, judging whether the control instruction is an executable instruction according to the area for sending out the audio, the attribute of the passenger sending out the audio signal and the control instruction corresponding to the audio signal;
step four, when the control instruction is an executable instruction, controlling a vehicle to execute the control instruction;
wherein the area for sending out the audio signal comprises a main driving area, a copilot area and a rear passenger area;
in the fourth step, further includes:
judging whether the running state of the current vehicle meets the full-area control state or not;
when the control instruction is an executable instruction and the vehicle running state meets the full-area control state, controlling the vehicle to execute the control instruction; otherwise, ignoring control instructions sent by the copilot area and the rear passenger area;
determining whether the running state of the vehicle meets the full-area control state according to the running state index of the vehicle;
wherein, the running state index of the vehicle is:
wherein delta represents the centroid deflection angle of the vehicle, V represents the vehicle speed and V max The vehicle speed represents the maximum vehicle speed, sr represents the wheel slip rate, eta represents a correction coefficient, and lambda represents a driving environment coefficient;
wherein, when Rs > 0.6, the running state of the vehicle satisfies the full-area control state;
when Rs is less than or equal to 0.6, the running state of the vehicle does not satisfy the all-region control state.
2. The vehicle voice control method according to claim 1, wherein the passenger attribute includes a sex and an age of a passenger.
3. The vehicle voice control method according to claim 2, characterized by further comprising, before the third step, setting instruction authority corresponding to the area from which the audio signal is emitted; when the control instruction sent by the area sending the audio signal is in the range of the corresponding instruction authority, performing the step three; otherwise, the control instruction is ignored.
4. The vehicle voice control method according to claim 3, characterized in that,
the instruction authority corresponding to the main driving area is the whole vehicle control authority;
the instruction authority corresponding to the copilot region at least comprises: video/audio play rights, navigation rights or co-pilot seat adjustment rights;
the instruction authority corresponding to the rear passenger area at least comprises: video/audio playback rights and rear-end audio control rights.
5. The vehicle voice control method according to claim 4, characterized in that,
when the delta is less than 8, the value range of eta is 1.15 to 1.10;
when the delta is more than or equal to 8, the value range of eta is 0.85 to 0.9.
6. The vehicle voice control method according to claim 5, characterized in that the driving environment coefficient is:
wherein lambda is 0 Represents a reference environmental coefficient, I represents the light intensity of the driving environment, I 0 Represents the reference light intensity, T represents the driving environment temperature, T 0 Indicating a reference temperature.
7. The vehicle voice control method according to claim 6, characterized in that,
lambda when the road surface is ice and snow road surface 0 The value range of (2) is 0.5-0.6;
lambda when the road surface is a non-icy road surface 0 The range of the value of (2) is 0.9-1.0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110128255.6A CN112951227B (en) | 2021-01-29 | 2021-01-29 | Vehicle voice control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110128255.6A CN112951227B (en) | 2021-01-29 | 2021-01-29 | Vehicle voice control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112951227A CN112951227A (en) | 2021-06-11 |
| CN112951227B true CN112951227B (en) | 2023-11-28 |
Family
ID=76239939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110128255.6A Active CN112951227B (en) | 2021-01-29 | 2021-01-29 | Vehicle voice control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112951227B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115158197B (en) * | 2022-07-21 | 2023-05-09 | 重庆蓝鲸智联科技有限公司 | Vehicle-mounted intelligent cabin entertainment control system based on sound source positioning |
| CN117633754A (en) * | 2022-08-09 | 2024-03-01 | 中兴通讯股份有限公司 | Rights management method, intelligent cabin, vehicle and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105867179A (en) * | 2016-03-29 | 2016-08-17 | 乐视控股（北京）有限公司 | Vehicle-borne voice control method, device and equipment |
| CN108327667A (en) * | 2018-02-06 | 2018-07-27 | 奇瑞汽车股份有限公司 | Vehicle audio control method and device |
| CN108520747A (en) * | 2018-03-29 | 2018-09-11 | 浙江吉利汽车研究院有限公司 | A kind of on-vehicle control apparatus with speech identifying function |
| CN110154894A (en) * | 2019-05-29 | 2019-08-23 | 辽宁工业大学 | A kind of vehicle security drive method for early warning based on pavement behavior |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6555648B2 (en) * | 2017-03-30 | 2019-08-07 | マツダ株式会社 | Vehicle driving support system |
-
2021
- 2021-01-29 CN CN202110128255.6A patent/CN112951227B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105867179A (en) * | 2016-03-29 | 2016-08-17 | 乐视控股（北京）有限公司 | Vehicle-borne voice control method, device and equipment |
| CN108327667A (en) * | 2018-02-06 | 2018-07-27 | 奇瑞汽车股份有限公司 | Vehicle audio control method and device |
| CN108520747A (en) * | 2018-03-29 | 2018-09-11 | 浙江吉利汽车研究院有限公司 | A kind of on-vehicle control apparatus with speech identifying function |
| CN110154894A (en) * | 2019-05-29 | 2019-08-23 | 辽宁工业大学 | A kind of vehicle security drive method for early warning based on pavement behavior |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112951227A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112951227B (en) | Vehicle voice control method | |
| US10598504B2 (en) | Vehicle control device and vehicle comprising the same | |
| KR101984922B1 (en) | Method for platooning of vehicles and vehicle | |
| EP3424791B1 (en) | Vehicle control device mounted on vehicle and method for controlling the vehicle | |
| KR102026697B1 (en) | Driving system and vehicle | |
| KR101974871B1 (en) | Vehicle control device mounted on vehicle and method for controlling the vehicle | |
| US20200324697A1 (en) | Vehicle engine sound control system and control method based on driver propensity using artificial intelligence | |
| CN107867227A (en) | Vehicle parking assistance device | |
| JP5537769B2 (en) | Method for operating a night view system in a vehicle and corresponding night view system | |
| KR102011008B1 (en) | System and method for detecing a road state | |
| KR101969805B1 (en) | Vehicle control device and vehicle comprising the same | |
| CN107867296A (en) | Controller of vehicle on vehicle and the method for controlling the vehicle | |
| CN105691299A (en) | Vehicle driving assistance apparatus and vehicle | |
| US11325520B2 (en) | Information processing apparatus and information processing method, and control apparatus and image processing apparatus | |
| US10549779B2 (en) | Vehicle control device mounted on vehicle and method for controlling vehicle | |
| KR20190072235A (en) | Vehicle control device mounted on vehicle and method for controlling the vehicle | |
| US20200385025A1 (en) | Information processing apparatus, mobile apparatus, information processing method, and program | |
| CN110366852B (en) | Information processing apparatus, information processing method, and recording medium | |
| KR20210143344A (en) | Vehicle control device and control method of the device | |
| US20190186941A1 (en) | Vehicle control device mounted on vehicle and method for controlling the vehicle | |
| KR101716248B1 (en) | Audio apparatus, vehicle having the same and control method thereof | |
| CN113711306A (en) | Voice control of vehicle systems | |
| JP2019100130A (en) | Vehicle control device and computer program | |
| CN104340145A (en) | Driving system capable of playing Chinese ancient culture and art content | |
| KR20190050335A (en) | Vehicle and method for controlling thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |