CN113147675A - Control system and control method for automobile door - Google Patents
Control system and control method for automobile door Download PDFInfo
- Publication number
- CN113147675A CN113147675A CN202110594837.3A CN202110594837A CN113147675A CN 113147675 A CN113147675 A CN 113147675A CN 202110594837 A CN202110594837 A CN 202110594837A CN 113147675 A CN113147675 A CN 113147675A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- control command
- information
- door control
- automobile
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 claims abstract description 43
- 238000012706 support-vector machine Methods 0.000 claims description 25
- 230000003993 interaction Effects 0.000 claims description 16
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000007123 defense Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000037433 frameshift Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/20—Means to switch the anti-theft system on or off
- B60R25/25—Means to switch the anti-theft system on or off using biometry
- B60R25/257—Voice recognition
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/01—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles operating on vehicle systems or fittings, e.g. on doors, seats or windscreens
Abstract
The application discloses a control system of an automobile door, which comprises a microphone, a position detection device, an automobile door control device and a first processor, the voice information of the user is received by a microphone arranged outside the automobile door, after the voice information is recognized by the first processor to obtain the automobile door control command, when the position detection device detects that the user is in a first preset range of the automobile door, the vehicle running state information is acquired to judge whether the safety precondition for executing the automobile door control command is met, when the automobile door control command is met, the automobile door control device controls the automobile door to execute the automobile door control command, so that the automobile door can be automatically opened and closed according to the voice information of the user on the premise that the user is at the designated position and the opening and closing automobile door is in a safe state, the hands and feet of the user are liberated, the false triggering is avoided, and the automobile door is opened and closed without contact outside the automobile. The application also discloses a control method of the automobile door, which has the beneficial effects.
Description
Technical Field
The application relates to the technical field of automobiles, in particular to a control system and a control method for an automobile door.
Background
With the continuous development of the automobile industry technology, the number of automatic parts in an automobile is gradually increased, and drivers and passengers can also operate some parts of the automobile through a more intelligent and convenient method, for example, on the basis of the traditional manual opening and closing of the existing automobile door control, a one-key switch, a kick type switch and other control methods are evolved, so that a user can conveniently open and close a backup door under some special conditions. However, the one-touch switch still requires manual operation by the user, and the kick switch has a certain risk in the case where the floor surface is slippery or the like. The existing automobile door control modes can not realize the non-contact opening and closing control of the automobile door outside the automobile.
Disclosure of Invention
The application aims to provide a control system and a control method of an automobile door, which are used for realizing the opening and closing control of the automobile door outside an automobile without contact.
In order to solve the above technical problem, the present application provides a control system for an automobile door, including: the system comprises a microphone, a position detection device, a vehicle door control device and a first processor, wherein the microphone is arranged outside a vehicle door and used for receiving voice information of a user, the position detection device is arranged outside the vehicle door and used for detecting the position relation of the user relative to the vehicle door, and the first processor is respectively connected with the microphone, the position detection device and the vehicle door control device;
the first processor is used for acquiring vehicle running state information and judging whether a safety precondition for executing the vehicle door control command is met or not according to the vehicle running state information after recognizing the voice information to obtain a vehicle door control command and determining that the user is located in a first preset range of the vehicle door according to a detection result of the position detection device, and if the safety precondition is met, the vehicle door control device controls the vehicle door to execute the vehicle door control command.
Optionally, the first processor recognizes the voice information to obtain a vehicle door control command, and specifically includes:
and the first processor identifies the Mel filter bank characteristic parameters of the voice information based on a pre-trained support vector machine model adopting a Gaussian kernel function, and compares the Mel filter bank characteristic parameters with the Mel filter bank characteristic parameters of a pre-stored vehicle door control command sample to obtain a vehicle door control command corresponding to the voice information.
Optionally, the system further comprises a human-computer interaction device connected with the first processor;
and the first processor is further used for receiving the voice information of the newly added vehicle door control command, updating the support vector machine model according to the voice information of the newly added vehicle door control command and receiving the vehicle door control command corresponding to the voice information of the newly added vehicle door control command through the human-computer interaction device after receiving the instruction of the newly added vehicle door control command.
Optionally, the first processor pre-stores a mel filter bank characteristic parameter of the voice information of the instruction of the new additional vehicle door control command;
after receiving the instruction of the new vehicle door control command, the first processor receives the voice information of the new vehicle door control command and updates the support vector machine model, and the method specifically includes:
after recognizing the voice information of the command of the newly added vehicle door control command, the first processor controls the human-computer interaction device to send prompt information for receiving the command so as to prompt the user to provide the voice information of the newly added vehicle door control command;
and when the consistency of the voice information of the newly added vehicle door control command provided by the user twice within the preset time is calculated to be within a preset range, the first processor updates the support vector machine model by using the voice information of the newly added vehicle door control command.
Optionally, the vehicle operating state information specifically includes: vehicle speed information and vehicle theft status information;
correspondingly, if the vehicle door control command is to open the vehicle door, the safety precondition is that the vehicle speed is zero and the vehicle anti-theft state information is in an unprotected state;
and if the door control command is to close the automobile door, the safety precondition is that the automobile speed is zero.
Optionally, the vehicle operating state information specifically includes: the vehicle speed information, the vehicle anti-theft state information and the vehicle keyless entrance guard system detection information;
the detection information of the vehicle keyless entry system comprises automobile intelligent key authentication information and key position information;
correspondingly, if the door control command is to open the automobile door, the security precondition is that the automobile speed is zero, the automobile intelligent key authentication information is authenticated and the key position information is that the automobile intelligent key is located in a second preset range, or the automobile speed is zero and the automobile anti-theft state information is in an unprotected state;
and if the door control command is to close the automobile door, the safety precondition is that the automobile speed is zero.
Optionally, the vehicle operating state information specifically includes: the system comprises vehicle speed information, vehicle anti-theft state information, vehicle keyless access control system detection information and vehicle door state information;
the detection information of the vehicle keyless entry system comprises automobile intelligent key authentication information and key position information;
correspondingly, if the door control command is to open the automobile door, the security precondition is that the automobile speed is zero, the automobile intelligent key authentication information is authenticated and the key position information is that the automobile intelligent key is located in a second preset range, or the automobile speed is zero and the automobile anti-theft state information is in an unprotected state;
if the door control command is to close the automobile door, the safety precondition is that the automobile speed is zero;
and if the vehicle door control command is stop operation, the safety precondition is that the vehicle door state information is an operation state and the vehicle speed is zero.
Optionally, the number of the automobile doors provided with the microphones is multiple;
the first processor recognizes the voice information to obtain a vehicle door control command, and specifically comprises the following steps:
the first processor determines the sending position of the voice information according to the voice information received by the microphones, determines a target vehicle door according to the sending position, and identifies the semantic content of the voice information to obtain a vehicle door control command of the target vehicle door.
Optionally, the obtaining of the vehicle running state information by the first processor specifically includes:
and the first processor acquires the vehicle running state information through a vehicle controller local area network.
In order to solve the above technical problem, the present application further provides a control method of an automobile door, based on any one of the above control systems of an automobile door, including:
the method comprises the steps that after a first processor identifies that a microphone receives voice information of a user to obtain a vehicle door control command and determines that the user is located in a first preset range of a vehicle door of a vehicle according to a detection result of a position detection device, vehicle running state information is obtained, and whether a safety precondition for executing the vehicle door control command is met or not is judged according to the vehicle running state information;
if yes, the first processor controls the automobile door to execute the door control command through a door control device.
The control system of the automobile door comprises a microphone, a position detection device, an automobile door control device and a first processor, the voice information of the user is received by a microphone arranged outside the automobile door, after the voice information is recognized by the first processor to obtain the automobile door control command, when the position detection device detects that the user is in a first preset range of the automobile door, the vehicle running state information is acquired to judge whether the safety precondition for executing the automobile door control command is met, when the automobile door control command is met, the automobile door control device controls the automobile door to execute the automobile door control command, so that the automobile door can be automatically opened and closed according to the voice information of the user on the premise that the user is at the designated position and the opening and closing automobile door is in a safe state, the hands and feet of the user are liberated, the false triggering is avoided, and the automobile door is opened and closed without contact outside the automobile.
The application also provides a control method of the automobile door, which has the beneficial effects and is not repeated herein.
Drawings
For a clearer explanation of the embodiments or technical solutions of the prior art of the present application, the drawings needed for the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a control system of an automobile door according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a keyless entry system according to an embodiment of the present application;
wherein 101 is a microphone, 102 is a position detection device, 103 is a vehicle door control device, and 104 is a first processor; a base station 201 and a transponder 202.
Detailed Description
The core of the application is to provide a control system and a control method of an automobile door, which are used for realizing the switch control of the automobile door outside an automobile without contact.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a schematic structural diagram of a control system of an automobile door according to an embodiment of the present disclosure.
As shown in fig. 1, a control system of an automobile door provided in an embodiment of the present application includes: the system comprises a microphone 101 arranged outside a vehicle door and used for receiving voice information of a user, a position detection device 102 arranged outside the vehicle door and used for detecting the position relation of the user relative to the vehicle door, a door control device 103, and a first processor 104 connected with the microphone 101, the position detection device 102 and the door control device 103 respectively;
the first processor 104 is configured to, after recognizing the voice information to obtain a door control command and determining that the user is located within a first preset range of the vehicle door according to a detection result of the position detection device 102, obtain vehicle operation state information and determine whether a security precondition for executing the door control command is satisfied according to the vehicle operation state information, and if so, control the vehicle door to execute the door control command through the door control device 103.
In a specific implementation, the vehicle door for which the control system of the vehicle door provided by the embodiment of the present application is applied may be one or more of all doors of the vehicle.
For a car door to be controlled, one or more microphones 101 may be mounted outside the car door. For example, for a car back door, the microphone 101 may be mounted in a back door license plate recess. To reduce the effect of wind noise on the collection of voice information, a cotton-padded sleeve may be added to the head of the microphone 101.
If it is desired to perform voice control of a plurality of vehicle doors, microphones 101 need to be installed outside the plurality of vehicle doors, and it is necessary to solve the problem of how to determine which vehicle door the user wants to control. The first processor 104 recognizes the voice information to obtain the door control command, and specifically may obtain the door control command for the target door for the semantic content of the voice information recognized by the first processor 104, that is, the voice information that needs to be provided for the vehicle door to be controlled when providing the voice information, such as "open the left front door", is agreed with the user in advance. Or, the car door to be controlled by the user may be determined according to the decibel size of the voice information received by the different microphones 101, and the first processor 104 may recognize the voice information to obtain the car door control command, specifically, the first processor 104 may determine the issuing position of the voice information according to the voice information received by each microphone 101, determine the target car door according to the issuing position, and recognize the semantic content of the voice information to obtain the car door control command for the target car door.
The first processor 104 is connected to the microphone 101, the position detection device 102, and the door control device 103, and is configured to receive a signal transmitted back from the microphone 101, perform signal processing, feature parameter extraction, pattern recognition, and the like on the signal, and is provided with a storage unit to store a pre-trained speech recognition model and other local data, and is further configured to determine whether to control the door of the vehicle by combining a recognition result of the user speech information, a detection result of the position detection device 102, and the acquired vehicle operating state information, and if the control is possible, output a control logic for the door of the vehicle to be controlled, and perform corresponding control through the door control device 103.
Specifically, the first processor 104 receives the voice information of the user through communication with the microphone 101, and needs to perform subsequent operations after recognizing the voice information to obtain a door control instruction. The first processor 104 may recognize semantic content of the obtained voice information by using a pre-trained neural network model, and extract keywords related to the door control command from the semantic content, thereby obtaining the door control command. In order to reduce the voice control cost, the first processor 104 may train the neural network model only by using the voice information corresponding to the door control command, so that it is only necessary to capture the voice information (such as "backup door", "left front door", "open/open", "close/close", "stop", etc.) in the sample set of the pre-stored voice information of the door control command without using a depth model. In addition, in order to improve the security, the first processor 104 may also perform voiceprint recognition on the voice information of the user, and perform a subsequent operation only when the user is determined to be the user with the door voice control authority through the voiceprint recognition result.
The position detection device 102 is provided for a vehicle door to be controlled, and specifically, an infrared sensor or an ultrasonic radar may be used. For example, for a car back door, an infrared sensor or an ultrasonic radar may be installed on the left side, the middle part, and the right side of a rear bumper of a car, so as to detect the position relationship between a user and a car door to be controlled. The position relationship of the user relative to the automobile door mainly refers to the distance between the user and the automobile door, and the first preset range can be 50 centimeters, namely whether the user is located within 50 centimeters of the automobile door to be controlled is detected to serve as a necessary condition for judging the authority of controlling the automobile door. Based on the position relation detection, the voice information containing the vehicle door control command can be effectively prevented from being received by mistake, and the safety level is improved.
When the door control command is obtained through recognition and the user is determined to be located within the first preset range of the automobile door, the first processor 104 obtains the vehicle running state information again to determine whether the vehicle running state at the current moment meets the safety precondition for executing the door control command. Specifically, the first processor 104 may further be provided with a vehicle controller area network (CAN bus) transceiver module to receive vehicle operation state information in the vehicle controller area network of the entire vehicle. The first processor 104 obtains vehicle operation state information including, but not limited to, vehicle speed information and vehicle anti-theft state information through the vehicle controller area network. If the safety precondition is judged only through the vehicle speed information and the vehicle anti-theft state information, if the vehicle door control command is to open the vehicle door, the safety precondition is that the vehicle speed is zero and the vehicle anti-theft state information is in an un-fortification state; if the door control command is to close the door of the automobile, the safety precondition is that the speed of the automobile is zero.
After the first processor 104 judges that the safety precondition for executing the door control command is satisfied, the door control device 103 controls the vehicle door to execute the door control command. The door control device 103 may specifically include a driving rod, a driving motor and a gear, and is configured to receive the control signal from the first processor 104 and drive the bicycle door corresponding to the door control command to open, stop, close, and the like.
The control system of the automobile door provided by the embodiment of the application can further comprise a loudspeaker which is arranged on the automobile door and connected with the first processor 104, and is used for outputting prompt tones to the user under the control of the first processor 104, for example, voice prompt is carried out on the user after the door control command is recognized and after the safety precondition is verified. For example, for a back door of an automobile, the loudspeaker can be specifically arranged in a back door license plate concave part.
It is mentioned in the above embodiments that, in order to reduce the voice control cost, the first processor 104 may train the neural network model using only the voice information corresponding to the door control command. The control system of the vehicle door according to the embodiment of the present application provides a specific implementation manner of performing voice recognition based on a support vector machine model, and specifically, in the voice recognition model pre-trained by the first processor 104, a Mel Filter Bank (FBank) parameter is used as a feature parameter of a voice instruction, and the support vector machine is used for performing model training to recognize voice information of a user. The first processor 104 recognizes the voice message to obtain a car door control command, specifically:
the first processor 104 identifies the mel filter bank characteristic parameters of the voice information based on a pre-trained support vector machine model adopting a Gaussian kernel function, and compares the mel filter bank characteristic parameters with the mel filter bank characteristic parameters of the pre-stored vehicle door control command sample to obtain the vehicle door control command corresponding to the voice information.
The calculation process of the mel filter bank characteristic parameters specifically comprises the following steps:
pre-emphasis processing is carried out on voice information of a user, high-frequency components of signals are increased, and the recognition effect is improved;
framing and windowing are carried out on the voice information, so that subsequent Fourier transform is facilitated; the frame length of the sub-frame is 20ms, the frame shift is 10ms, a certain overlap is reserved between two adjacent frames, and information loss caused by windowing to two ends of each frame signal is prevented. Then, a Hamming window is adopted to carry out windowing processing on the signal, and the calculation formula of the Hamming window is as follows:
wherein N is the number of sampling points.
Carrying out Fourier transform on the voice information after preprocessing and framing and windowing to obtain a frequency spectrum of a signal;
and (4) the frequency spectrum passes through a Mel filter bank to realize the conversion of the Mel scale. The Mel filter bank is derived according to the different characteristics of the response of human ear hearing to different frequency bands, converts the traditional frequency scale into Mel scale, and is more in line with the hearing characteristics of human ear, and the calculation formula is as follows:
wherein f (m) is defined as:
wherein, f (M) is the center frequency of the mth triangular band-pass filter in the filter bank, the maximum value is M, and M is the number of the triangular filters; f. ofh，flRespectively the lowest and highest frequencies of the filter, and f is the sampling frequency. Inverse function B of B (f)-1(f) The calculation formula is as follows:
and squaring the converted frequency spectrum of the Mel scale, and performing logarithm operation to obtain the final characteristic parameters of the Mel filter bank.
The support vector machine model is trained based on a pre-stored pre-training data set. The pre-training data set includes a car door control command sample, and specifically may include keywords such as "trunk/trunk", "tail door", "open/open", "close/close", "stop/stop", and the like. Meanwhile, the voice information of different personnel can be collected so as to improve the diversity of the car door control command samples. The door control command samples in the pre-training data set may include, but are not limited to, the above keywords, and may also be customized by the user.
And respectively extracting characteristic parameters of a Mel filter set from the vehicle door control command sample of the pre-training data set by adopting a support vector machine model as a voice recognition model, and preparing a classification label for the vehicle door control command sample to obtain a classified vehicle door control command sample. And taking the Mel filter bank characteristic parameters of the classified vehicle door control command samples as the input of the support vector machine model, calculating by adopting a Gaussian kernel function, reducing the calculated amount on the premise of ensuring the prediction precision of the model, and finally training to obtain the support vector machine model which is put into use.
The first processor 104, after receiving the voice message, invokes the trained support vector machine model to detect whether the voice message contains the voice message of the vehicle control command, and obtains the recognized classification label. Specifically, if the vehicle door control command such as "open/close/stop" is recognized, the first processor 104 enters the flow of determining the user position and determining and executing the security precondition; if no pre-stored keyword is identified, no operation is performed.
By utilizing the control system of the automobile door, the identification of the key words of the door control command can be realized under the condition of small calculated amount, the identification efficiency is improved, and the voice identification cost is reduced.
Fig. 2 is a schematic structural diagram of a keyless entry system according to an embodiment of the present application.
On the basis, the door control command self-defining function can be provided for the user in order to meet the habit of the user and provide richer control modes. Specifically, the control system of the automobile door provided by the embodiment of the application further comprises a human-computer interaction device connected with the first processor 104;
the first processor 104 is further configured to receive voice information of the new door control command and update the support vector machine model according to the voice information of the new door control command after receiving the instruction of the new door control command, and receive the door control command corresponding to the voice information of the new door control command through the human-computer interaction device.
In a specific implementation, the first processor 104 may receive an instruction of a new door control command through the human-computer interaction device. The man-machine interaction device can be a touch screen arranged in a central control area of the automobile, or a display screen and mechanical keys, and the function can also be integrated in the original central control man-machine interaction device of the automobile. The first processor 104 may receive the voice information of the new door control command through the human-computer interaction device or the microphone 101, and receive the door control command corresponding to the voice information of the new door control command, which is input by the user.
In order to ensure the performability of the door control command corresponding to the voice information of the newly-added door control command, the first processor 104 can display the door control command which can be set for a user through the man-machine interaction device, indicate the door control command which is already being executed and the door control command which is not being executed, enable the user to select to put the door control command which is not being executed into use and provide the voice information of the corresponding newly-added door control command, or enable the user to change the voice information corresponding to the door control command which is already being executed. For example, in a factory setting, the door control commands that have been executed may include only "open a door" and "close a door", and the corresponding voice messages are "open a door" and "close a door"; when the user selects the newly added door control command of 'stopping the operation of a certain door' and inputs the corresponding voice message of 'stopping the operation of the certain door', the first processor 104 updates the support vector machine model by using the voice message, learns and memorizes the characteristic parameters of the Mel filter bank of the voice message, and adds the control logic corresponding to the voice message to the door control logic already in execution; when the user selects "open a door" and inputs the voice message "open a door" to be replaced, the first processor 104 updates the support vector machine model using the voice message, learns the mel filter bank characteristic parameters that memorize the voice message, and modifies the voice message corresponding to a door control command "open a door" in the door control logic that is already in execution.
Optionally, if the microphone 101 is used to receive the voice information of the new door control command, the first processor 104 prestores the mel filter bank characteristic parameters of the voice information of the instruction of the new door control command;
after receiving the instruction of the new door control command, the first processor 104 receives the voice information of the new door control command to update the support vector machine model, and specifically includes:
after recognizing the voice information of the command of the newly added vehicle door control command, the first processor 104 controls the human-computer interaction device to send out prompt information for receiving the command so as to prompt a user to provide the voice information of the newly added vehicle door control command;
the first processor 104 updates the support vector machine model with the voice information of the newly added door control command when it is calculated that the consistency of the voice information of the newly added door control command provided twice by the user within the preset time is within the preset range.
In one embodiment, the pre-training data set includes voice information of instructions for adding new door control commands, such as "add instruction" and "custom instruction". When the user provides the voice information of the command of the newly added door control command, the first processor 104 recognizes the command of the newly added door control command and enters the process of the newly added door control command. In order to improve the system security, the identity of the user can be verified before a vehicle door control command is newly added, for example, the user is required to dictate a preset password or the password is input through a human-computer interaction device; or performing Passive Key Entry (PKE) authentication by using the automobile intelligent key, and if the user carries the automobile intelligent key corresponding to the target vehicle, considering that the user has the authority of a newly-added automobile door control command after the authentication of the Passive key Entry system is completed.
As shown in fig. 2, the keyless entry system generally comprises a base station 201 and a transponder 202, wherein the base station 201 is composed of a base station microprocessor, a low frequency transmitting module, and a high frequency receiving module; the transponder 202 is an automobile intelligent key and consists of a key microprocessor, a low-frequency receiving module and a high-frequency transmitting module. The base station microprocessor, the low-frequency transmitting module and the high-frequency receiving module of the base station 201 are arranged in an automobile and are connected with a Body Controller (BCM) through a Local Interconnect Network (LIN), the base station 201 continuously transmits a low-frequency message with the code of 125kHz through the low-frequency transmitting module to detect and awaken a transponder 202 in a specified range of the base station 201, the transponder 202 in the specified range can receive the message through the low-frequency receiving module and process and verify the coded data field, if the verification and the identification of the automobile intelligent key are successful, the high-frequency signal feedback information with the code of 433MHz is transmitted through the high-frequency transmitting module, so that the authentication is realized through a keyless access control system, and the position of the automobile intelligent key compared with the automobile can be identified.
After the user authority authentication is completed, the first processor 104 may control the speaker to prompt the user to "please input a new instruction", receive the voice information of the newly added door control command dictated by the user through the microphone 101 or the human-computer interaction device, and calculate the mel filter bank characteristic parameters of the voice information of the newly added door control command.
Before the support vector machine model is updated by using the voice information of the newly added vehicle door control command, the Mel filter bank characteristic parameters of the voice information of the newly added vehicle door control command can be identified and compared with the Mel filter bank characteristic parameters of the vehicle door control command in the pre-training data set, so that the repeated vehicle door control command in the pre-training data set is prevented. If no repeated door control command is recognized, the first processor 104 controls the loudspeaker to prompt the user to 'please input a new command again', and reads the repeated voice information of the user. And calculating the characteristic parameters of the Mel filter bank of the voice information repeatedly input by the user. If the repeated voice information of the user is not received within the preset time after the user inputs the voice information of the newly added vehicle door control command for the first time, the first processor 104 controls the loudspeaker to prompt the user of the failure information of inputting the new command. After receiving the voice information repeatedly input by the user, the first processor 104 calculates the consistency of the voice information of the newly added door control command provided by the user twice within the preset time, specifically, calculates the consistency of the characteristic parameters of the mel filter set of the voice information of the two newly added door control commands, so as to determine whether the user inputs the same voice information. Specifically, a Pearson correlation coefficient of a characteristic parameter of a Mel filter bank of voice information of two newly added car door control commands can be calculated, which is defined as a quotient of covariance and standard deviation between two variables, and the calculation formula is as follows:
where ρ isX,YFor the pearson correlation coefficient between X and Y, E (×) represents the mathematical expectation, cov (×) represents the covariance, and σ (×) represents the standard deviation.
When the Pearson correlation coefficient of the Mel filter bank characteristic parameters of the voice information of the two newly added vehicle door control commands is larger than or equal to a set threshold value (adjustable), the newly added vehicle door control commands are considered to be effective, and the Mel filter bank characteristic parameters of the voice information of the two newly added vehicle door control commands are written into a pre-training data set. If the Pearson correlation coefficient of the characteristic parameters of the Mel filter bank of the voice information of the two newly added vehicle door control commands is smaller than the set threshold, the newly added vehicle door control commands are considered invalid, and the first processor 104 controls the loudspeaker to prompt the user that the instructions are inconsistent and please re-input.
And when the control command of the newly added vehicle door is effective, retraining the support vector machine model based on the new pre-training data set to obtain a new support vector machine model and covering the original support vector machine model.
The control system of the automobile door provided by the embodiment of the application can support the user-defined automobile door control command, and adapts to habits of different users through the interactive feedback of the loudspeaker and the user.
In the above embodiment, when the first processor 104 recognizes that the door control command is obtained and determines that the user is within the first preset range of the vehicle door, the door control command is considered as a valid input, and the flow of the judgment of the security precondition and the execution of the door control command is entered. If the first processor 104 recognizes the door control command but does not detect that the user is within the first predetermined range of the door of the vehicle, the door control command is considered as an external interference input.
The first processor 104 obtains vehicle running state information such as vehicle speed information and vehicle anti-theft state information through the vehicle controller local area network, and the vehicle running state information is used as a basis for judging the security precondition. In order to further reduce the situation of false identification, the keyless entry system introduced in the above embodiment is combined to authenticate the user identity through the keyless entry system.
The vehicle operation state information specifically includes: the vehicle speed information, the vehicle anti-theft state information and the vehicle keyless entrance guard system detection information;
the detection information of the vehicle keyless entry system comprises automobile intelligent key authentication information and key position information;
correspondingly, if the door control command is to open the door of the automobile, the security precondition is that the speed of the automobile is zero, the authentication information of the intelligent key of the automobile is authenticated and the key position information is that the intelligent key of the automobile is located in a second preset range, or the speed of the automobile is zero and the anti-theft state information of the automobile is in an unprotected state;
if the door control command is to close the door of the automobile, the safety precondition is that the speed of the automobile is zero.
The above embodiments can be referred to for the way of performing car smart key authentication and key position identification by the keyless entry system, and are not described herein again.
The detection of the car key is within a second preset range, specifically, the car key is within the second preset range of the car, or within the second preset range of the base station 201 of the keyless entry system. The second preset range may be five meters, that is, if a user holds the car smart key within a range of five meters of the car and another user is within a range of 50 cm of the car door to be voice-controlled, the authentication of the item of information is detected by the car keyless entry system.
When the door control command is not only to open and close the door, which may involve controlling the operating state of the door (e.g., switching from the operating state to the stopped state, or adjusting the rate of opening and closing), in another embodiment, the vehicle operating state information specifically includes: the system comprises vehicle speed information, vehicle anti-theft state information, vehicle keyless access control system detection information and vehicle door state information;
the detection information of the vehicle keyless entry system comprises automobile intelligent key authentication information and key position information;
correspondingly, if the door control command is to open the door of the automobile, the security precondition is that the speed of the automobile is zero, the authentication information of the intelligent key of the automobile is authenticated and the key position information is that the intelligent key of the automobile is located in a second preset range, or the speed of the automobile is zero and the anti-theft state information of the automobile is in an unprotected state;
if the door control command is to close the door of the automobile, the safety precondition is that the speed is zero;
if the door control command is stop operation, the safety precondition is that the door state information is an operation state and the vehicle speed is zero.
Based on this, the logic table for determining and controlling the security precondition can be as shown in table 1.
TABLE 1 judgment control logic table for security preconditions
If the keyless entry system passes the authentication and the vehicle speed is zero, the first processor 104 controls the target vehicle door to open when the target vehicle door is in a closed or stopped state and the vehicle door control command is open.
If the keyless entry system fails to authenticate, the user position is detected effectively, the vehicle security state is in a state of defense solution or preset defense (i.e., a state from defense solution to defense solution), and the vehicle speed is zero, the first processor 104 may also control the target vehicle door to open when the target vehicle door is in a closed or stopped state and the vehicle door control command is open.
If the authentication of the keyless entry system is not passed, the whole vehicle is in a defense or alarm state, and at the moment, the first processor 104 does not drive the target vehicle door to be opened from closing.
When the vehicle speed is not zero, the first processor 104 does not drive the target vehicle door from closing to opening no matter whether the keyless entry system is effective in authentication or not and the anti-theft state is in any mode.
When the door control command is closed or stopped, the first processor 104 only determines the vehicle speed information, and responds to the command if the vehicle speed information is zero.
On the basis of the above detailed descriptions of the various embodiments corresponding to the control system of the vehicle door, the present application also discloses a control method of the vehicle door corresponding to the above system, which can be based on any one of the above control systems of the vehicle door, and the method comprises the following steps:
the first processor acquires vehicle running state information and judges whether a safety precondition for executing a vehicle door control command is met or not according to the vehicle running state information after recognizing that a microphone receives voice information of a user to obtain the vehicle door control command and determining that the user is located in a first preset range of a vehicle door according to a detection result of a position detection device;
if yes, the first processor controls the automobile door to execute a door control command through the door control device.
Since the embodiment of the method portion corresponds to the embodiment of the system portion, please refer to the description of the embodiment of the system portion for the embodiment of the method portion, which is not repeated here.
The above detailed description is provided for a control system and a control method of an automobile door provided by the present application. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The method disclosed by the embodiment corresponds to the system disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the system part for description. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A control system for a vehicle door, comprising: the system comprises a microphone, a position detection device, a vehicle door control device and a first processor, wherein the microphone is arranged outside a vehicle door and used for receiving voice information of a user, the position detection device is arranged outside the vehicle door and used for detecting the position relation of the user relative to the vehicle door, and the first processor is respectively connected with the microphone, the position detection device and the vehicle door control device;
the first processor is used for acquiring vehicle running state information and judging whether a safety precondition for executing the vehicle door control command is met or not according to the vehicle running state information after recognizing the voice information to obtain a vehicle door control command and determining that the user is located in a first preset range of the vehicle door according to a detection result of the position detection device, and if the safety precondition is met, the vehicle door control device controls the vehicle door to execute the vehicle door control command.
2. The control system of claim 1, wherein the first processor recognizes the voice message to obtain a door control command, and specifically:
and the first processor identifies the Mel filter bank characteristic parameters of the voice information based on a pre-trained support vector machine model adopting a Gaussian kernel function, and compares the Mel filter bank characteristic parameters with the Mel filter bank characteristic parameters of a pre-stored vehicle door control command sample to obtain a vehicle door control command corresponding to the voice information.
3. The control system of claim 2, further comprising a human interaction device coupled to the first processor;
and the first processor is further used for receiving the voice information of the newly added vehicle door control command, updating the support vector machine model according to the voice information of the newly added vehicle door control command and receiving the vehicle door control command corresponding to the voice information of the newly added vehicle door control command through the human-computer interaction device after receiving the instruction of the newly added vehicle door control command.
4. The control system according to claim 3, wherein the first processor prestores Mel filter bank characteristic parameters of the voice information of the instruction of the new door control command;
after receiving the instruction of the new vehicle door control command, the first processor receives the voice information of the new vehicle door control command and updates the support vector machine model, and the method specifically includes:
after recognizing the voice information of the command of the newly added vehicle door control command, the first processor controls the human-computer interaction device to send prompt information for receiving the command so as to prompt the user to provide the voice information of the newly added vehicle door control command;
and when the consistency of the voice information of the newly added vehicle door control command provided by the user twice within the preset time is calculated to be within a preset range, the first processor updates the support vector machine model by using the voice information of the newly added vehicle door control command.
5. The control system according to claim 1, characterized in that the vehicle operation state information specifically includes: vehicle speed information and vehicle theft status information;
correspondingly, if the vehicle door control command is to open the vehicle door, the safety precondition is that the vehicle speed is zero and the vehicle anti-theft state information is in an unprotected state;
and if the door control command is to close the automobile door, the safety precondition is that the automobile speed is zero.
6. The control system according to claim 1, characterized in that the vehicle operation state information specifically includes: the vehicle speed information, the vehicle anti-theft state information and the vehicle keyless entrance guard system detection information;
the detection information of the vehicle keyless entry system comprises automobile intelligent key authentication information and key position information;
correspondingly, if the door control command is to open the automobile door, the security precondition is that the automobile speed is zero, the automobile intelligent key authentication information is authenticated and the key position information is that the automobile intelligent key is located in a second preset range, or the automobile speed is zero and the automobile anti-theft state information is in an unprotected state;
and if the door control command is to close the automobile door, the safety precondition is that the automobile speed is zero.
7. The control system according to claim 1, characterized in that the vehicle operation state information specifically includes: the system comprises vehicle speed information, vehicle anti-theft state information, vehicle keyless access control system detection information and vehicle door state information;
the detection information of the vehicle keyless entry system comprises automobile intelligent key authentication information and key position information;
correspondingly, if the door control command is to open the automobile door, the security precondition is that the automobile speed is zero, the automobile intelligent key authentication information is authenticated and the key position information is that the automobile intelligent key is located in a second preset range, or the automobile speed is zero and the automobile anti-theft state information is in an unprotected state;
if the door control command is to close the automobile door, the safety precondition is that the automobile speed is zero;
and if the vehicle door control command is stop operation, the safety precondition is that the vehicle door state information is an operation state and the vehicle speed is zero.
8. The control system according to claim 1, wherein the number of the vehicle doors provided with the microphones is plural;
the first processor recognizes the voice information to obtain a vehicle door control command, and specifically comprises the following steps:
the first processor determines the sending position of the voice information according to the voice information received by the microphones, determines a target vehicle door according to the sending position, and identifies the semantic content of the voice information to obtain a vehicle door control command of the target vehicle door.
9. The control system of claim 1, wherein the first processor obtains the vehicle operating state information by:
and the first processor acquires the vehicle running state information through a vehicle controller local area network.
10. A control method of an automobile door, characterized in that the control system of an automobile door based on any one of claims 1 to 9, comprises:
the method comprises the steps that after a first processor identifies that a microphone receives voice information of a user to obtain a vehicle door control command and determines that the user is located in a first preset range of a vehicle door of a vehicle according to a detection result of a position detection device, vehicle running state information is obtained, and whether a safety precondition for executing the vehicle door control command is met or not is judged according to the vehicle running state information;
if yes, the first processor controls the automobile door to execute the door control command through a door control device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110594837.3A CN113147675A (en) | 2021-05-28 | 2021-05-28 | Control system and control method for automobile door |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110594837.3A CN113147675A (en) | 2021-05-28 | 2021-05-28 | Control system and control method for automobile door |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113147675A true CN113147675A (en) | 2021-07-23 |
Family
ID=76875393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110594837.3A Pending CN113147675A (en) | 2021-05-28 | 2021-05-28 | Control system and control method for automobile door |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113147675A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114059889A (en) * | 2021-11-01 | 2022-02-18 | 广州小鹏自动驾驶科技有限公司 | Method for opening scissor door and vehicle |
| CN114633721A (en) * | 2022-03-21 | 2022-06-17 | 中国第一汽车股份有限公司 | Vehicle unlocking method and device, electronic equipment and storage medium |
| CN115092092A (en) * | 2021-11-23 | 2022-09-23 | 长城汽车股份有限公司 | Opening method, device and equipment of vehicle storage cabinet and vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005042529A (en) * | 2003-07-09 | 2005-02-17 | Yasuo Yamakoshi | Unlocking/locking device for car, safe and entrance door |
| US20050275505A1 (en) * | 1999-07-23 | 2005-12-15 | Himmelstein Richard B | Voice-controlled security system with smart controller |
| CN202806675U (en) * | 2012-07-30 | 2013-03-20 | 北京汽车股份有限公司 | Automobile and keyless entry system thereof |
| CN105059243A (en) * | 2015-09-17 | 2015-11-18 | 上海卓易科技股份有限公司 | Automatic automobile door and window locking system and method |
| CN106627490A (en) * | 2016-10-27 | 2017-05-10 | 奇瑞汽车股份有限公司 | Automobile trunk opening-closing control system and method based on identity recognition and speech recognition |
| CN108340876A (en) * | 2018-01-24 | 2018-07-31 | 江苏德瑞博新能源汽车制造有限公司 | A kind of new-energy automobile keyless access system |
| CN110525379A (en) * | 2019-09-10 | 2019-12-03 | 奇瑞汽车股份有限公司 | A kind of pure electric automobile speech unlocking system and method |
| CN112298104A (en) * | 2019-07-31 | 2021-02-02 | 比亚迪股份有限公司 | Vehicle control method and device, storage medium, electronic equipment and vehicle |
-
2021
- 2021-05-28 CN CN202110594837.3A patent/CN113147675A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050275505A1 (en) * | 1999-07-23 | 2005-12-15 | Himmelstein Richard B | Voice-controlled security system with smart controller |
| JP2005042529A (en) * | 2003-07-09 | 2005-02-17 | Yasuo Yamakoshi | Unlocking/locking device for car, safe and entrance door |
| CN202806675U (en) * | 2012-07-30 | 2013-03-20 | 北京汽车股份有限公司 | Automobile and keyless entry system thereof |
| CN105059243A (en) * | 2015-09-17 | 2015-11-18 | 上海卓易科技股份有限公司 | Automatic automobile door and window locking system and method |
| CN106627490A (en) * | 2016-10-27 | 2017-05-10 | 奇瑞汽车股份有限公司 | Automobile trunk opening-closing control system and method based on identity recognition and speech recognition |
| CN108340876A (en) * | 2018-01-24 | 2018-07-31 | 江苏德瑞博新能源汽车制造有限公司 | A kind of new-energy automobile keyless access system |
| CN112298104A (en) * | 2019-07-31 | 2021-02-02 | 比亚迪股份有限公司 | Vehicle control method and device, storage medium, electronic equipment and vehicle |
| CN110525379A (en) * | 2019-09-10 | 2019-12-03 | 奇瑞汽车股份有限公司 | A kind of pure electric automobile speech unlocking system and method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114059889A (en) * | 2021-11-01 | 2022-02-18 | 广州小鹏自动驾驶科技有限公司 | Method for opening scissor door and vehicle |
| CN115092092A (en) * | 2021-11-23 | 2022-09-23 | 长城汽车股份有限公司 | Opening method, device and equipment of vehicle storage cabinet and vehicle |
| CN114633721A (en) * | 2022-03-21 | 2022-06-17 | 中国第一汽车股份有限公司 | Vehicle unlocking method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113147675A (en) | Control system and control method for automobile door | |
| US5774858A (en) | Speech analysis method of protecting a vehicle from unauthorized accessing and controlling | |
| US20080249774A1 (en) | Method and apparatus for speech speaker recognition | |
| US20100088093A1 (en) | Voice Command Acquisition System and Method | |
| CN104575492A (en) | Voiceprint recognition method, device and keyless safety lock system and implementing method | |
| US11355124B2 (en) | Voice recognition method and voice recognition apparatus | |
| CN105957523A (en) | Vehicular system control method and device | |
| CN110027409B (en) | Vehicle control device, vehicle control method, and computer-readable recording medium | |
| CN109910818A (en) | A kind of VATS Vehicle Anti-Theft System based on human body multiple features fusion identification | |
| CN112093602B (en) | Elevator voice control method and device | |
| CN106971714A (en) | A kind of speech de-noising recognition methods and device applied to robot | |
| CN112298104A (en) | Vehicle control method and device, storage medium, electronic equipment and vehicle | |
| CN110566081A (en) | Trunk opening and closing control method and device | |
| CN114183032A (en) | Control method and system of vehicle door | |
| EP0761514A1 (en) | Method of controlling vehicles with prevention of unauthorised access based on speech analysis, and a system for applying the proposed method | |
| CN116918301A (en) | Device operation based on dynamic classifier | |
| JP2009025982A (en) | Vehicle theft prevention system | |
| KR20150086908A (en) | Vehicle control apparatus and method using voice or gesture | |
| CN109544745A (en) | A kind of intelligent door lock control method, apparatus and system | |
| CN116890786A (en) | Vehicle lock control method, device and medium | |
| CN206107186U (en) | Vehicle unblock system based on fingerprint identification | |
| CN109598823B (en) | Identity recognition method based on multiple sensors | |
| CN215006766U (en) | Entrance guard and ignition system based on multiple biological recognition technology | |
| CN107848489B (en) | Activating vehicle actions with a mobile device | |
| CN112937435B (en) | Reminding device for turning off vehicle starting system and vehicle with reminding device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210723 |
|
| RJ01 | Rejection of invention patent application after publication |