Voice recognition-based vehicle door control method, device, apparatus, and storage medium

Abstract

Embodiments of the present application provide a vehicle door control method and device based on voice recognition, a storage medium and an equipment. When the recognition result of the voice module is a preset recognition result, the prompt flag is changed from a first preset flag to a second preset flag, and a preset voice prompt is played through the prompt module. When the prompt flag is the second preset flag, and the driving state of the vehicle and the door state of the vehicle meet the door control condition, the door of the vehicle is controlled to be always open through the control module, and the door protection mechanism is started. When the duration of the prompt flag being the second preset flag exceeds a preset duration, the prompt flag is restored to the first preset flag from the second preset flag, and the door protection mechanism is cancelled. Through the voice module, the control module and the prompt module, the embodiments of the present application can effectively solve the problems that passengers are difficult to reach the door button in the peak period, and the oral prompt may be ignored, and ensure that the passengers can get off the vehicle in time and safely.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of public transportation, in particular to a vehicle door control method and device based on voice recognition, an electronic device and a storage medium. BACKGROUND

[0002] As a widely used public transportation tool, the driver usually opens the door after stopping at each station to allow passengers to get on and off the bus. However, since the driver's seat is located at the front of the vehicle, it is difficult for them to observe the needs of passengers behind them, which may result in some passengers failing to get off the bus in time, especially when the driver closes the door after thinking that no one needs to get off. To address this issue, current measures include installing a "get-off button" on the back door of the bus, which passengers can press to alert the driver that someone wants to get off, or directly telling the driver verbally. Some buses are also equipped with cameras, and the driver can observe the passengers' getting-off situation through the front vehicle-mounted television monitor.

[0003] However, during peak hours, the bus is often very crowded, and many passengers are far from the back door, making it difficult to reach the get-off button and may not be within the camera's range, which results in passengers missing the station during the process of rushing to the back door. At this time, passengers can only alert the driver verbally, but due to the distance and the noise inside the bus, such alerts may be ignored, resulting in passengers missing the station, or even passengers being pinched during the process of getting off. SUMMARY

[0004] The embodiments of the present application provide a vehicle door control method based on voice recognition to solve the problem that the get-off alert sound from passengers far from the door is easily ignored by the driver, resulting in passengers being pinched when getting off the bus.

[0005] Correspondingly, the embodiments of the present application also provide a vehicle door control device based on voice recognition, an electronic device and a storage medium to ensure the implementation and application of the above method.

[0006] To solve the above problem, the embodiments of the present application disclose a vehicle door control method based on voice recognition, applied to a vehicle, the vehicle comprising a voice module, a control module and a prompt module, the method comprising:

[0007] When the recognition result of the voice module is a preset recognition result, the prompt flag bit is changed from a first preset flag bit to a second preset flag bit, and a preset voice prompt is played through the prompt module;

[0008] When the prompt flag is the second preset flag, and the driving state of the vehicle and the door state of the vehicle meet a door control condition, then the control module controls the vehicle door to be always open, and a door protection mechanism is started;

[0009] When the duration that the prompt flag is the second preset flag exceeds a preset duration, then the prompt flag is restored from the second preset flag to the first preset flag, and the door protection mechanism is cancelled.

[0010] Optionally, when the prompt flag is the second preset flag, and the driving state of the vehicle and the door state of the vehicle meet a door control condition, then the control module controls the vehicle door to be always open, and a door protection mechanism is started, including:

[0011] When the prompt flag is the second preset flag, then the driving state of the vehicle and the door state of the vehicle are determined;

[0012] When the driving state of the vehicle and the door state of the vehicle meet a door control condition, then the control module controls the vehicle door to be always open, and the door protection mechanism is started.

[0013] Optionally, before the driving state of the vehicle and the door state of the vehicle meet a door control condition, then the control module controls the vehicle door to be always open, and the door protection mechanism is started, the method further includes:

[0014] The driving state of the vehicle is determined according to the driving speed of the vehicle;

[0015] The door state of the vehicle is determined according to the number of times that the door opening button of the vehicle is pressed;

[0016] When the driving speed of the vehicle is a preset speed, and the number of times that the door opening button of the vehicle is pressed is at least once, then the driving state of the vehicle and the door state of the vehicle meet the door control condition.

[0017] Optionally, the vehicle further includes a plurality of voice input devices, the voice module includes a voice library, the voice input devices are connected to the voice module, and before the recognition result of the voice module is a preset recognition result, then the prompt flag is changed from a first preset flag to a second preset flag, and a preset voice prompt is played by the prompt module, the method further includes:

[0018] When the voice module receives voice audio sent by the voice input device, the voice audio is subjected to noise reduction processing to obtain noise reduction audio;

[0019] performing speech recognition on the noise-reduced audio to obtain a plurality of audio keywords;

[0020] matching the plurality of audio keywords with target keywords in the speech vocabulary to determine whether the target keywords in the speech vocabulary exist in the noise-reduced audio;

[0021] if the target keywords in the speech vocabulary exist in the noise-reduced audio, determining that the recognition result of the speech module is the preset recognition result;

[0022] if the target keywords in the speech vocabulary do not exist in the noise-reduced audio, determining that the recognition result of the speech module is not the preset recognition result.

[0023] Optionally, the speech module is connected to the prompt module and the control module; the playing of the preset voice prompt by the prompt module comprises: when the prompt module receives a playing signal sent by the speech module, the voice prompt is played.

[0024] the control of the vehicle door always open by the control module comprises: when the control module receives an always open signal sent by the speech module, the vehicle door is controlled to be always open.

[0025] Optionally, the speech vocabulary comprises a vocabulary corresponding to a plurality of languages, and before the speech recognition on the noise-reduced audio to obtain a plurality of audio keywords, the method further comprises:

[0026] performing speech recognition on the noise-reduced audio to determine a target language corresponding to the noise-reduced audio;

[0027] determining, in the speech vocabulary, a vocabulary corresponding to the target language as a target vocabulary.

[0028] Optionally, the matching of the plurality of audio keywords with target keywords in the speech vocabulary to determine whether the target keywords in the speech vocabulary exist in the noise-reduced audio comprises:

[0029] matching the plurality of audio keywords with target keywords in the target vocabulary to determine whether the target keywords in the target vocabulary exist in the noise-reduced audio.

[0030] Optionally, the method further comprises:

[0031] if the duration of the prompt flag bit being the second preset flag bit does not exceed the preset duration, performing a preset operation on a door closing button of the vehicle to cancel the door closing protection mechanism.

[0032] Optionally, the voice module is connected with a station reporting system, and the method further comprises:

[0033] When the voice module receives a first electric signal sent by the station reporting system, the voice module is started; the first electric signal is used to represent that the vehicle arrives at a station;

[0034] When the voice module receives a second electric signal sent by the station reporting system, the voice module is closed, and the vehicle door is controlled to be always closed by the control module; the second electric signal is used to represent that the vehicle departs from the station.

[0035] The embodiment of the application further discloses a vehicle door control device based on voice recognition, applied to a vehicle, wherein the vehicle comprises a voice module, a control module and a prompt module, and the device comprises:

[0036] A prompt flag changing module is configured to change the prompt flag from a first preset flag to a second preset flag when the recognition result of the voice module is a preset recognition result, and play a preset voice prompt through the prompt module;

[0037] A vehicle door control condition meeting module is configured to control the vehicle door to be always opened through the control module when the prompt flag is the second preset flag and the driving state of the vehicle and the vehicle door state of the vehicle meet a vehicle door control condition, and start a door closing protection mechanism;

[0038] A prompt flag restoring module is configured to restore the prompt flag from the second preset flag to the first preset flag when the duration of the prompt flag being the second preset flag exceeds a preset duration, and cancel the door closing protection mechanism.

[0039] Optionally, the vehicle door control condition meeting module comprises:

[0040] A determining module is configured to determine the driving state of the vehicle and the vehicle door state of the vehicle when the prompt flag is the second preset flag;

[0041] A meeting module is configured to control the vehicle door to be always opened through the control module when the driving state of the vehicle and the vehicle door state of the vehicle meet a vehicle door control condition, and start the door closing protection mechanism.

[0042] Optionally, the device further comprises:

[0043] A driving state determining module is configured to determine the driving state of the vehicle according to the driving speed of the vehicle;

[0044] The vehicle door state determining module is configured to determine a vehicle door state of the vehicle according to a number of times that a door opening button of the vehicle is pressed.

[0045] The vehicle door control condition determining module is configured to determine that the vehicle door control condition is met when the driving state of the vehicle and the vehicle door state of the vehicle meet the vehicle door control condition when the driving speed of the vehicle is the preset speed and the number of times that the door opening button of the vehicle is pressed is at least once.

[0046] Optionally, the vehicle further comprises a plurality of voice input devices, and the voice module comprises a voice library, the voice input devices are connected to the voice module, and the device further comprises:

[0047] The noise reduction processing module is configured to perform noise reduction processing on the voice audio received by the voice module to obtain noise reduction audio.

[0048] The voice recognition module is configured to perform voice recognition on the noise reduction audio to obtain a plurality of audio keywords.

[0049] The target keyword determining module is configured to match the plurality of audio keywords with target keywords in the voice library to determine whether the target keywords in the voice library exist in the noise reduction audio.

[0050] The first recognition result module is configured to determine that the recognition result of the voice module is the preset recognition result if the target keywords in the voice library exist in the noise reduction audio.

[0051] The second recognition result module is configured to determine that the recognition result of the voice module is not the preset recognition result if the target keywords in the voice library do not exist in the noise reduction audio.

[0052] Optionally, the voice module is connected to the prompt module and the control module respectively, and the prompt flag changing module comprises a voice prompt playing module configured to play the voice prompt when the prompt module receives a playing signal sent by the voice module.

[0053] The vehicle door control condition meeting module comprises a vehicle door control module configured to control the vehicle door to be always open when the control module receives an always-on signal sent by the voice module.

[0054] Optionally, the voice library comprises a plurality of language libraries corresponding to a plurality of languages, and the device comprises:

[0055] The target language determining module is configured to perform voice recognition on the noise reduction audio to determine a target language corresponding to the noise reduction audio.

[0056] The target vocabulary determination module is configured to determine a vocabulary corresponding to the target language in the speech vocabulary as a target vocabulary.

[0057] Optionally, the target keyword determination module comprises:

[0058] The matching module is configured to match the plurality of audio keywords with target keywords in the target vocabulary, and determine whether the target keywords in the target vocabulary exist in the noise-reduced audio.

[0059] Optionally, the device further comprises:

[0060] The door closing protection mechanism cancellation module is configured to perform a preset operation on a door closing button of the vehicle to cancel the door closing protection mechanism if the prompt flag bit is not longer than the second preset flag bit for the preset time length.

[0061] Optionally, the speech module is connected with a station reporting system, and the device further comprises:

[0062] The first electric signal module is configured to turn on the speech module when the speech module receives a first electric signal sent by the station reporting system; the first electric signal is used to represent that the vehicle arrives at a station.

[0063] The second electric signal module is configured to turn off the speech module and control the doors of the vehicle to be always closed through the control module when the speech module receives a second electric signal sent by the station reporting system; the second electric signal is used to represent that the vehicle departs from a station.

[0064] The embodiments of the present application also disclose an electronic device, comprising: a processor; and a memory having executable code stored thereon, when the executable code is executed, causing the processor to perform the speech recognition-based vehicle door control method according to any one of the embodiments of the present application.

[0065] The embodiments of the present application also disclose one or more machine readable media having executable code stored thereon, when the executable code is executed, causing a processor to perform the speech recognition-based vehicle door control method according to any one of the embodiments of the present application.

[0066] Compared with the prior art, the embodiments of the present application have the following advantages:

[0067] In the embodiment of the present application, when the recognition result of the voice module is a preset recognition result, the prompt flag bit is changed from a first preset flag bit to a second preset flag bit, and a preset voice prompt is played through the prompt module; when the prompt flag bit is the second preset flag bit and the driving state of the vehicle and the door state of the vehicle meet the door control condition, the door of the vehicle is controlled to be always open through the control module, and the door protection mechanism is started; when the duration of the prompt flag bit being the second preset flag bit exceeds a preset duration, the prompt flag bit is restored from the second preset flag bit to the first preset flag bit, and the door protection mechanism is cancelled.

[0068] In the embodiment of the present application, when the recognition result of the voice module is a preset recognition result, the prompt flag bit is changed from a first preset flag bit to a second preset flag bit, and a preset voice prompt is played through the prompt module; when the prompt flag bit is the second preset flag bit and the driving state of the vehicle and the door state of the vehicle meet the door control condition, the door of the vehicle is controlled to be always open through the control module, and the door protection mechanism is started; when the duration of the prompt flag bit being the second preset flag bit exceeds a preset duration, the prompt flag bit is restored from the second preset flag bit to the first preset flag bit, and the door protection mechanism is cancelled. BRIEF DESCRIPTION OF DRAWINGS

[0069] Figure 1 is a schematic diagram of an application environment of the present application;

[0070] Figure 2 is a step flowchart of an embodiment of a door control method based on voice recognition of the present application;

[0071] Figure 3 is a step flowchart of another embodiment of a door control method based on voice recognition of the present application;

[0072] Figure 4 is a structural block diagram of an embodiment of a door control device based on voice recognition of the present application;

[0073] Figure 5 is a structural schematic diagram of the device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0074] In order to make the above objectives, features and advantages of the present application more apparent, more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0075] Referring to Figure 1 , a schematic diagram of an application environment of the present application is shown, a vehicle door control method based on voice recognition of the present application is applied to a vehicle, the vehicle comprising a voice module, a control module and a prompt module. Specifically, the voice module is used to identify the passenger's request to get off, the control module is used to control the opening and closing of the vehicle door, and the prompt module is arranged in the cab and used to remind the driver that there is a passenger who needs to get off.

[0076] In the embodiment of the present application, an offline voice recognition technology is used to train specific keywords for getting off. When the vehicle arrives at the station and a passenger utters a keyword for getting off or waiting for a while, the voice module will recognize it and give a voice prompt in the cab through the prompt module, so that the request of the passenger who is far away from the door in a crowded situation can be received by the driver, and the control module keeps the door open to ensure that the passenger will not sit through the station or be pinched by the door, thereby improving the safety and the riding experience.

[0077] Referring to Figure 2 , a step flow chart of an embodiment of the vehicle door control method based on voice recognition of the present application is shown, comprising the following steps:

[0078] Step 201, when the recognition result of the voice module is a preset recognition result, the prompt flag bit is changed from a first preset flag bit to a second preset flag bit, and a preset voice prompt is played through the prompt module;

[0079] In the embodiment of the present application, an offline voice module will be installed in the bus, which can be connected with multiple input ends (such as microphones), the input ends can be arranged at various positions inside the vehicle cabin, and the number of input ends can be set according to the actual situation, and the number and position of the input ends are not limited in the embodiment of the present application.

[0080] In the process of driving the bus, the voice module is in a default closed state, and the prompt flag is in a default first preset flag. When the bus is preparing to enter a station, the bus's stop announcing system sends a first electrical signal to the voice module, and the voice module is in an open state. After the voice module is opened, it identifies whether there is a preset keyword triggering. When the voice module successfully identifies the preset keyword, it is considered that the identification result of the voice module is a preset identification result, and the system immediately changes the prompt flag from the first preset flag to a second preset flag. At the same time, the prompt module in the driver's cabin immediately plays a pre-recorded voice prompt, such as "a passenger will get off the bus", and the purpose of the voice prompt is to remind the driver to pay attention to the request of the passenger behind to get off the bus, so as to ensure that the driver can respond in time.

[0081] In the embodiments of the present application, the "first preset flag" is set to 0, and the "second preset flag" is set to 1. This is only an example to distinguish the difference and relationship between the first preset flag and the second preset flag, and the embodiments of the present application are not limited thereto.

[0082] In step 202, when the prompt flag is the second preset flag, and the driving state of the vehicle and the door state of the vehicle meet the door control condition, the control module controls the vehicle door to be always open, and a door protection mechanism is started.

[0083] In the embodiments of the present application, when the voice module identifies the request related to getting off the bus spoken by the passenger, the prompt flag is kept as the second preset flag. In this process, the system needs to obtain the driving state of the vehicle to determine whether the vehicle is in the process of entering the station or has been stopped. If the vehicle is still in the process of entering the station, the control module will not control the vehicle door to be always open. If the vehicle has been stopped, the control module will control the vehicle door to be always open.

[0084] In actual application, the driving state of the vehicle is usually determined by the GPS of the stop announcing system and the driving speed of the vehicle. However, there may be too many vehicles entering the station at the same time, resulting in the situation that the vehicle has not entered the station but has been stopped. In this case, an error signal that the vehicle has entered the station and has been stopped is often given, which leads to the vehicle door being opened without entering the station, which affects the safety of the passengers on the vehicle.

[0085] To solve this problem, the embodiments of the present application not only determine the door control condition by the driving state of the vehicle, but also further confirm whether the door control condition is met by the door state of the vehicle. Specifically, whether the control module automatically controls the vehicle door to be always open and starts the door protection mechanism is determined by whether the driver actively opens the vehicle door. If the driver actively opens the vehicle door, it means that the current position can allow the passenger to normally get off the bus.

[0086] Therefore, in the case that the prompt flag is the second preset flag, it means that the passenger on the vehicle has a demand to get off. At this time, the system will comprehensively consider the driving state of the vehicle and the door state, and only in the case that the door control condition is met, the vehicle door will be controlled to be always open by the control module, and the door closing protection mechanism will be started. The purpose of the door closing protection mechanism is to prevent the driver from mistakenly triggering the vehicle door closing button, to avoid the passenger who gets off not reacting in time and being pinched or closed on the vehicle, so as to ensure the safety of the passenger and the smoothness of the ride.

[0087] The prompt flag is changed from the first preset flag to the second preset flag only after the voice module recognizes the get-off instruction. In this way, whether to control the vehicle door to be always open and start the door closing protection mechanism can be determined in combination with the driving state of the vehicle and the door state of the vehicle, and the driver will not be repeatedly prompted during this period, preventing the passenger from continuously issuing a get-off instruction and affecting the normal driving of the driver due to frequent prompts.

[0088] Step 203: When the duration of the prompt flag being the second preset flag exceeds a preset duration, the prompt flag is restored from the second preset flag to the first preset flag, and the door closing protection mechanism is canceled.

[0089] In actual application, the request of the passenger to get off is usually instant, and once the passenger gets off, the vehicle should be able to quickly recover to the default state in order to prepare to respond to the next possible request. If the prompt flag remains unchanged for a long time, it may cause unnecessary occupation of system resources, affecting the normal operation of other functions. At this time, a preset duration can be set to ensure that the passenger's demand has been met or no longer needed within the preset duration, for example, the preset duration can be set to 3 seconds, which is not limited in the embodiments of the application. At the same time, the door closing protection mechanism in the embodiments of the application is to prevent the vehicle door from being accidentally closed to cause injury when the passenger gets off. However, once it is determined that the passenger has safely gotten off, continuing to maintain the door closing protection mechanism may cause the vehicle door to be unable to normally close, affecting the normal operation of the bus.

[0090] Therefore, in the embodiments of the application, after the prompt flag is changed from the first preset flag to the second preset flag, timing will be automatically started, and when the timing exceeds the preset duration, the prompt flag will be automatically restored from the second preset flag to the first preset flag, and the door closing protection mechanism will be canceled. By automatically restoring the prompt flag and canceling the door closing protection mechanism, the vehicle can be restored to normal operation when no additional protection is needed, improving the operation efficiency, and also ensuring the safety of the passenger.

[0091] Further, in the embodiment of the present application, the prompt flag is not directly related to the switch of the voice module, and the prompt flag is determined by whether the voice module recognizes the getting-off instruction. Therefore, when the vehicle enters the station, the voice module is turned on, but there is no getting-off instruction from the passenger during this period, at this time the prompt flag is always the first preset flag, and when the prompt flag is the first preset flag, the driver will not be prompted by the prompt module that there is a passenger to get off, the vehicle door will not be controlled to be always open by the control module, and the door closing protection mechanism will not be turned on.

[0092] In the embodiment of the present application, when the preset voice prompt is recognized by the voice module, the prompt flag is changed from the first preset flag to the second preset flag, and the preset voice prompt is played by the prompt module to remind the driver that there is a passenger to get off; when the prompt flag is the second preset flag and the driving state of the vehicle and the door state of the vehicle meet the door control condition, the control module controls the vehicle door to be always open, and the door closing protection mechanism is turned on to ensure that the vehicle door remains open before the passenger gets off; when the duration of the prompt flag being the second preset flag exceeds the preset duration, the prompt flag returns to the first preset flag, and the door closing protection mechanism is cancelled to ensure that the vehicle door can be normally closed after the passenger gets off. In the embodiment of the present application, the voice module, the control module and the prompt module can effectively solve the problem that the passenger cannot touch the getting-off button during the peak period and the oral prompt may be ignored, and as long as the vehicle is in a non-starting state, the vehicle door will be immediately controlled to be opened, and the driver will be informed by the synchronous voice that there is a passenger to get off, so that the driver pays attention to the rear passenger, the door closing protection is triggered to prevent the driver from pressing the switch due to the delayed reaction, the passenger is prevented from being pinched, and the passenger can get off in time and safely.

[0093] In another embodiment of the present application, the step 202, when the prompt flag is the second preset flag and the driving state of the vehicle and the door state of the vehicle meet the door control condition, the control module controls the vehicle door to be always open, and the door closing protection mechanism is turned on, including:

[0094] When the prompt flag is the second preset flag, it is determined that the driving state of the vehicle and the door state of the vehicle meet the door control condition.

[0095] When the driving state of the vehicle and the door state of the vehicle meet the door control condition, the control module controls the vehicle door to be always open, and the door closing protection mechanism is turned on.

[0096] In the embodiment of the present application, the prompt flag being the second preset flag means that the passenger has a demand to get off the vehicle. At this time, the driving state and the door state of the vehicle need to be considered comprehensively to determine whether the current door opening environment is safe. The door of the vehicle needs to be kept open by the control module under the premise that the environment is safe, and the door closing protection mechanism needs to be started in the state that the door is kept open.

[0097] For example, if the vehicle is still driving or has not completely stopped, opening the door can be dangerous to the passenger and the pedestrian. At this time, it is considered that the current door opening environment is not safe, that is, the driving state of the vehicle does not meet the door control condition. If the vehicle has completely stopped and the door has been opened by the driver, opening the door will not be dangerous to the passenger and the pedestrian. At this time, it is considered that the current door opening environment is safe, that is, the driving state and the door state of the vehicle both meet the door control condition.

[0098] Therefore, in order to ensure the safety, accuracy and efficiency of the door control operation, when the prompt flag is the second preset flag, the driving state and the door state of the vehicle need to be obtained in the embodiment of the present application, which also optimizes the passenger experience and improves the overall operation efficiency of the public transport system.

[0099] In another embodiment of the present application, before the step 202, when the driving state of the vehicle and the door state of the vehicle meet the door control condition, the method further comprises:

[0100] determining the driving state of the vehicle according to the driving speed of the vehicle;

[0101] determining the door state of the vehicle according to the number of times that the door opening button of the vehicle is pressed;

[0102] when the driving speed of the vehicle is a preset speed and the number of times that the door opening button of the vehicle is pressed is at least once, it is determined that the driving state of the vehicle and the door state of the vehicle meet the door control condition.

[0103] In the embodiments of the present application, the running state of the vehicle is determined by the GPS of the station reporting system and the running speed of the vehicle, so as to determine whether the current vehicle belongs to the running state or the stable stopping state. However, in actual application, there may be too many vehicles entering the station at the same time, resulting in the case that the vehicle has not entered the station but has been stopped by braking. In this case, an error signal that the vehicle has entered the station and is stable is often given, and then the door of the vehicle is opened in the case that the vehicle has not entered the station, which affects the safety of passengers on the vehicle. To solve this problem, the number of times that the door opening button of the vehicle is pressed is further used to determine the door state of the vehicle, so as to further confirm whether the running state and the door state of the vehicle satisfy the door control condition.

[0104] The number of times that the door opening button of the vehicle is pressed can be used to determine whether the driver has opened the door voluntarily. If the door opening button of the vehicle is pressed at least once, it is considered that the driver has opened the door voluntarily, and at this time, opening the door will not cause danger to passengers and pedestrians.

[0105] In the actual running process of the vehicle, when the vehicle has been stable, the following cases may occur, which belong to the case that the running state and the door state of the vehicle satisfy the door control condition.

[0106] Case one: the door button is pressed at least once, and the door belongs to the opened state.

[0107] If the door button is pressed at least once, and it is detected that the door has been opened all the time (that is, the door has been kept in the opened state all the time), the system may consider that the door state has satisfied the door control condition. In this case, the system will continue to keep the door opened all the time, and ensure that the door protection mechanism is in the activated state, so as to prevent the door from being closed accidentally.

[0108] Case two: the door button is pressed at least once, and the door belongs to the closed state.

[0109] If the door button is pressed at least once, the driver closes the door after opening the door. At this time, the vehicle has not started running, and the vehicle still belongs to the stable stopping state, but a passenger requests to get off the vehicle by voice, at this time, the door is automatically controlled to be opened all the time, and the door protection mechanism is opened, so as to ensure that the passenger can get off the vehicle safely.

[0110] Case three: the door button is pressed at least once, and the door belongs to the closing state.

[0111] If the door button is pressed at least once, but it is detected that the door is in the closing process, the system may pause the closing operation of the door, and reopen the door to keep the door opened all the time, and open the door protection mechanism, so as to ensure that the passenger can get off the vehicle safely.

[0112] As can be seen from the above three scenarios, it is only meaningful to consider the vehicle door status when the vehicle has come to a complete stop. Therefore, in this embodiment, it is possible to first determine whether the vehicle's driving state meets the door control conditions. Then, if the vehicle's driving state meets the door control conditions, it is further determined whether the vehicle door status meets the door control conditions. This ensures that the door will not be opened when the vehicle has not come to a complete stop or is still in motion, thereby avoiding the safety risks caused by the accidental opening of the door. After determining that the vehicle has come to a complete stop, the door status is considered, which can reduce unnecessary door operations caused by misjudging the vehicle status, such as when the vehicle has come to a complete stop but has not fully entered the station, thus avoiding the door from opening under inappropriate circumstances.

[0113] In another embodiment of this application, the vehicle further includes multiple voice input devices, the voice module includes a voice dictionary, the voice input devices are connected to the voice module, and before step 201, when the recognition result of the voice module is a preset recognition result, the prompt flag is changed from a first preset flag to a second preset flag, and a preset voice prompt is played through the prompt module, the method further includes:

[0114] When the voice module receives voice audio sent by the voice input device, it performs noise reduction processing on the voice audio to obtain noise-reduced audio.

[0115] The noise-reduced audio is subjected to speech recognition to obtain multiple audio keywords;

[0116] The multiple audio keywords are matched with the target keywords in the speech lexicon to determine whether the target keywords in the speech lexicon exist in the noise-reduced audio.

[0117] If the target keyword in the speech lexicon exists in the noise-reduced audio, then the recognition result of the speech module is determined to be the preset recognition result;

[0118] If the target keyword in the speech lexicon is not present in the noise-reduced audio, then the recognition result of the speech module is determined to be different from the preset recognition result.

[0119] like Figure 1 As shown, the voice input device is connected to the voice module. In this embodiment, multiple voice input devices are used to obtain the voice audio of passengers in the vehicle, and then the voice audio is transmitted to the voice module for voice recognition to determine whether the passenger has requested to get off the vehicle.

[0120] The voice module in the embodiment of the present application uses an offline voice recognition method, and a fixed voice library is specially trained. Only the keywords in the voice library can trigger. Compared with the speed of online voice content recognition, the speed is faster and more sensitive. The related words other than the keywords in the voice library are regarded as invalid words, and the voice module shields the invalid words.

[0121] In actual application, the voice environment in the public vehicle is generally noisy. Therefore, in the offline voice recognition algorithm, the audio is processed for noise reduction. When the passenger gets off, the voice is subconsciously raised, so that the voice is more prominent in the surrounding environment. As long as the signal-to-noise ratio (SNR) between the voice of the passenger and the surrounding noise reaches a certain threshold, the microphone installed in the vehicle compartment can accurately capture and recognize the key off instruction. This recognition strategy based on signal-to-noise ratio ensures that the system can reliably execute the off request of the passenger even in a noisy public bus environment.

[0122] In audio processing, the signal-to-noise ratio refers to the ratio of the intensity of the effective sound signal to the intensity of the background noise. A high signal-to-noise ratio means that the signal intensity is much greater than the noise intensity, so the effective signal can be more easily identified and extracted from the background noise. On the contrary, a low signal-to-noise ratio means that the signal is masked by noise and it is difficult to clearly identify the signal.

[0123] Specifically, when the voice module receives the voice audio sent by the voice input device, the voice audio is first processed for noise reduction to remove background noise and improve the accuracy of voice recognition. Then, the noise-reduced audio is subjected to voice recognition to extract a plurality of audio keywords. These keywords are important words or phrases in the voice, which are helpful for determining the voice content. The extracted audio keywords are matched with target keywords in a voice library. The voice library contains pre-set keywords or phrases, which are related to the off request of the passenger. If the target keywords in the voice library exist in the noise-reduced audio, it is determined that the recognition result of the voice module is the pre-set recognition result, i.e. the passenger has made an off request. If the target keywords in the voice library do not exist in the noise-reduced audio, it is determined that the recognition result of the voice module is not the pre-set recognition result, i.e. the off request of the passenger is not detected.

[0124] In the prior art, the driver is reminded by a "get-off button", and the passenger's request to get off is detected by a monitor of the rear door of the vehicle. In the embodiment of the application, the offline voice recognition method realized by the voice input device and the voice module can detect the passenger's request to get off by directly processing the voice audio of the passenger after the passenger simply speaks the request, without the passenger searching for or pressing the "get-off button", and without the driver continuously observing the passenger's getting-off situation through the vehicle monitor, effectively solving the limitation of determining the passenger's request to get off in the prior art, better controlling the door of the vehicle, and further improving the overall service quality and passenger satisfaction of the public transport system.

[0125] In the embodiment of the application, the voice input device can be a microphone installed inside the bus, which can be distributed at different positions in the vehicle cabin to capture the voice of the passenger from various directions. Those skilled in the art can set it according to actual needs, which is not limited in the embodiment of the application.

[0126] In another embodiment of the application, the voice module is connected with the prompt module and the control module respectively; the playing of the preset voice prompt by the prompt module comprises: playing the voice prompt when the prompt module receives a playing signal sent by the voice module;

[0127] The control of the door of the vehicle to be always open by the control module comprises: controlling the door of the vehicle to be always open when the control module receives an always-open signal sent by the voice module.

[0128] As shown in Figure 1 The voice module interacts with the prompt module and the control module, and the prompt module and the control module do not interact. In the embodiment of the application, when the voice module recognizes the request of the passenger to get off (i.e., the recognition result is the preset recognition result), it will send a playing signal to the prompt module. After the prompt module receives the signal, it will play a preset voice prompt, such as "there is a passenger who will get off", to convey to the driver that there is a passenger who needs to get off, so that the driver can take corresponding actions in time. Similarly, when the voice module recognizes the request of the passenger to get off, it will also send an always-open signal to the control module under the condition that the running state of the vehicle and the state of the door meet the door control condition. After the control module receives the signal, it will control the door of the vehicle to be always open, ensuring that the passenger can safely and smoothly get off, avoiding inconvenience or danger caused by the closing of the door.

[0129] For the vehicle door, there are only two states of opening and closing, so the control of the vehicle door can be realized by simple high and low level. The "always open signal" in the embodiment of the application can be simply understood as a high level to control the vehicle door to be always open. Correspondingly, when the vehicle door needs to be closed, a low level can be sent to the control module to control the vehicle door to be closed.

[0130] In another embodiment of the application, the voice vocabulary library includes vocabulary libraries corresponding to multiple languages. Before the voice recognition of the noise-reduced audio is performed to obtain multiple audio keywords, the method further includes:

[0131] Performing voice recognition on the noise-reduced audio to determine a target language corresponding to the noise-reduced audio.

[0132] Determining, in the voice vocabulary library, a vocabulary library corresponding to the target language as a target vocabulary library.

[0133] In the embodiment of the application, in order to adapt to passengers with different language backgrounds, the voice vocabulary library includes vocabulary libraries corresponding to multiple languages. Before voice recognition is performed, the system first performs voice recognition on the noise-reduced audio to determine a target language used in the voice audio. Once the target language is determined, the system selects a vocabulary library corresponding to the target language in the voice vocabulary library for subsequent keyword matching and recognition, which ensures that the system can accurately understand the request to get off issued by passengers speaking different languages.

[0134] In the embodiment of the application, multi-language support not only includes different official languages, but also includes various dialects to adapt to a wider user group, such as Mandarin, English, Cantonese, Spanish, French, etc., and various regional dialects. Those skilled in the art can set them according to actual needs, and the embodiment of the application is not limited.

[0135] In another embodiment of the application, in order to ensure that the voice recognition system can continuously adapt to new passenger needs and dialect changes, it is very important to regularly check and update the vocabulary library for voice recognition. Over time, the needs of passengers may change, and they may use new vocabulary or expressions to express the request to get off, therefore, the vocabulary library needs to be updated continuously to include these new expressions, to ensure that these changes can be understood and responded to. Feedback from actual use can also be collected to understand which vocabulary or phrases are frequently used, and which may need to be updated or added, for example, if a passenger frequently uses a specific vocabulary to express getting off, but this vocabulary is not in the current vocabulary library, then this vocabulary should be added.

[0136] In another embodiment of the present application, the matching of the plurality of audio keywords with the target keywords in the voice library to determine whether the target keywords in the voice library exist in the noise-reduced audio comprises:

[0137] The matching of the plurality of audio keywords with the target keywords in the target library to determine whether the target keywords in the target library exist in the noise-reduced audio.

[0138] In the embodiment of the present application, a plurality of audio keywords are first extracted from the noise-reduced audio, which are important words or phrases in the voice and are helpful to determine the voice content; and then the audio keywords are matched with the target keywords in the target library, which is selected according to the target language determined in advance and contains keywords and phrases related to the request for getting off in the language. Through the matching process, it is determined whether the target keywords in the target library exist in the noise-reduced audio. If so, it is confirmed that the passenger has made a request for getting off.

[0139] The matching of the audio keywords with the target keywords in the target library makes it convenient for the passenger to make a request for getting off in a language familiar to him, without worrying about language barriers. Moreover, the matching is performed through the preset target library, without the need to perform matching in a voice library containing multiple languages, which simplifies the operation process of voice recognition, makes the system more easily maintained and upgraded, and reduces the resource consumption due to processing invalid instructions through the accurate matching process in the target library, so that the computing resources can be more efficiently utilized, thereby optimizing the passenger's riding experience and enhancing the service quality of the public transportation system.

[0140] In another embodiment of the present application, the method further comprises:

[0141] If the duration of the prompt flag bit being the second preset flag bit does not exceed the preset duration, a preset operation is performed on the door closing button of the vehicle to cancel the door closing protection mechanism.

[0142] In the embodiment of the present application, during the period when the prompt flag bit is the second preset flag bit, the voice module is still in the open state, but the voice module will pause and not perform recognition, to prevent the passenger from repeatedly making a request for getting off and causing frequent broadcasting in a short period of time, thereby interfering with the driver's driving. Therefore, after the preset duration, the voice module will work again to identify whether there is a trigger keyword.

[0143] In the embodiments of the present application, the door protection mechanism can be automatically released, and a double insurance operation of manual release can be further set. In the case that the door protection mechanism has not been cancelled, but the driver has determined that there is no danger and wants to start the vehicle, the driver can manually release the door protection mechanism by performing a preset operation on the door button of the vehicle. For example, the door protection mechanism can be cancelled by pressing the door button twice in half a second, or the door protection mechanism can be cancelled by pressing the door button for 1 second. The skilled in the art can set it according to the actual situation, and the embodiments of the present application are not limited.

[0144] In another embodiment of the present application, the voice module is connected with a station reporting system, and the method further comprises:

[0145] When the voice module receives a first electric signal sent by the station reporting system, the voice module is turned on; the first electric signal is used to represent that the vehicle is arriving at a station;

[0146] When the voice module receives a second electric signal sent by the station reporting system, the voice module is turned off, and the vehicle door is controlled to be always closed by the control module; the second electric signal is used to represent that the vehicle is leaving the station.

[0147] As shown in Figure 1 The voice module is connected with a station reporting system provided by the bus, and the station reporting system provides information of the vehicle arriving at and leaving the station to the voice module. Therefore, in the embodiments of the present application, the opening and closing of the voice module is related to the information of the vehicle arriving at and leaving the station. The voice module is turned on when the vehicle arrives at the station, and is turned off when the vehicle leaves the station, so as to prevent the passengers from triggering the voice module by chatting during the driving process, and reduce the power consumption of the voice module.

[0148] Specifically, when the voice module receives a first electric signal sent by the station reporting system, the voice module is turned on. The first electric signal is used to represent that the vehicle is arriving at a station, i.e., the vehicle has approached or arrived at a certain station. The purpose of turning on the voice module is to enable the voice module to receive and process the voice request of the passenger at a suitable time, especially the request of getting off the vehicle. When the vehicle arrives at the station, the passenger may have the demand of getting off the vehicle, so the voice module needs to be in the working state. When the voice module receives a second electric signal sent by the station reporting system, the voice module is turned off. The second electric signal is used to represent that the vehicle is leaving the station, i.e., the vehicle has started to leave the current station. The purpose of turning off the voice module is to avoid the voice module needing to process unnecessary voice requests during the driving process of the vehicle, reduce the burden of the voice module, and also ensure that the driver will not be disturbed by the voice prompt during the driving.

[0149] Moreover, when the voice module is turned off, the voice module also controls the vehicle door to be always closed through the control module, which means that after the vehicle leaves the station, the vehicle door will be locked in the closed state to ensure the safety during the driving of the vehicle.

[0150] In the embodiment of the present application, the first electric signal and the second electric signal are determined according to the indication information provided by the station reporting system. The existing buses are all monitored in real time by GPS to determine whether the vehicle is arriving at or leaving from a station. The driver can also actively trigger the arrival information or the departure information to prompt the passengers or trigger the voice module. The voice module will automatically start as soon as it receives the first electric signal indicating the arrival at the station, and will automatically shut down as soon as it receives the second electric signal indicating the departure from the station.

[0151] The embodiment of the present application can determine the start and stop of the voice module through the information provided by the station reporting system, prevent the passengers from triggering the voice module by mistake during the driving of the vehicle, and reduce the power consumption of the voice module. The voice module is used for recognition. When the preset voice prompt is recognized, the prompt flag bit is changed from the first preset flag bit to the second preset flag bit, and the preset voice prompt is played through the prompt module to remind the driver that someone wants to get off the vehicle. Through the offline voice recognition technology and the preset voice library, the system can accurately recognize the request of the passenger to get off the vehicle, and reduce the possibility of misrecognition. The voice library contains multiple languages and dialects, which ensures that the system can serve passengers with different language backgrounds and improves the inclusiveness of the system. When the prompt flag bit is the second preset flag bit, and the driving state and the door state of the vehicle meet the door control condition, the control module controls the door to be always open, and starts the door protection mechanism, so that the door remains open before the passenger gets off the vehicle. When the time length of the prompt flag bit being the second preset flag bit exceeds the preset time length, the prompt flag bit returns to the first preset flag bit, and the door protection mechanism is cancelled, so that the door can be normally closed after the passenger gets off the vehicle. The voice module, the control module and the prompt module can effectively solve the problems that the passengers cannot reach the get-off button during the peak period, and the oral prompt may be ignored. As long as the vehicle is in a non-starting state, the door will be immediately controlled to be opened, and the driver will be informed through the voice that there is a passenger who wants to get off the vehicle, so that the driver pays attention to the passengers behind him, and the door protection is triggered to prevent the driver from pressing the switch too late during the door closing operation, avoid the passengers from being pinched, and ensure that the passengers can get off the vehicle in time and safely.

[0152] When there are many people in the vehicle, it is difficult for the passengers to reach the back door, and they cannot press the get-off button at the back door. The camera monitoring the back door cannot easily capture the passengers, and the request of the passengers to get off the vehicle is easy to be ignored due to the long distance or other noises in the vehicle. Therefore, the offline voice module can be installed in the vehicle to recognize the request of the passengers to get off the vehicle and deliver the request to the driver, so that the passengers will not overtake the station or be pinched by the door.

[0153] Reference Figure 3 is a step flow chart of another embodiment of the vehicle door control method based on voice recognition of the present application, comprising the following steps:

[0154] S301, the voice module is closed by default, and the prompt flag is 0 by default (first preset flag).

[0155] S302, it is judged whether the vehicle is ready to enter the station. If the vehicle does not enter the station, the voice module remains closed, and the prompt flag is 0 (first preset flag); otherwise, S303 is entered.

[0156] S303, when the vehicle is ready to enter the station, the bus stop announcement system sends a first electrical signal to the voice module, the voice module is opened, and it starts to identify whether there is a trigger keyword, as follows:

[0157] S3031, the voice module identifies whether there is a series of related request words such as “there is still a passenger”, “there is still a passenger”, “there is still a passenger”, “stop for a moment”, “open the door” and the like.

[0158] S3032, when a passenger speaks a related request which is identified, it is judged whether the driving state and the door state of the vehicle meet the door control condition. If the door control condition is not met, S304 is executed; if the door control condition is met, S305 is executed.

[0159] S304, if the door control condition is not met (the vehicle is still in the station), the voice module sends a playing signal to the prompt module in the cab to play a pre-recorded voice prompt “there is a passenger who will get off the bus”, and the prompt flag is changed to 1 (second preset flag), and is automatically restored to 0 (first preset flag) after timing for 3s (preset time length). During the period when the prompt flag is 1 (second preset flag), the voice module does not identify to prevent the passenger from repeatedly causing frequent broadcasting in a short time and interfering with the driver.

[0160] S305, if the door control condition is met (the vehicle has stopped stably, and the door opening button of the vehicle has been pressed at least once), a pre-recorded voice prompt is played, and the voice module interacts with the control module to control the door state. As follows:

[0161] S3051, the voice module sends a playing signal to the prompt module in the cab to play a pre-recorded voice prompt “there is a passenger who will get off the bus”, and the prompt flag is changed to 1 (second preset flag), and is automatically restored to 0 (first preset flag) after timing for 3s (preset time length), the logic is the same as S304, to prevent frequent broadcasting in a short time.

[0162] S3052, the voice module sends a normally open signal to the control module at the same time, if the rear door is already opened at this time, it remains unchanged; if the rear door is being closed or has been closed, the rear door is automatically opened to prevent the passenger from being pinched or closed inside.

[0163] S306, when the prompt flag is 1 (the second preset flag), the voice module sends a trigger signal to the control module to trigger the door closing protection mechanism. The driver needs to press the door closing button twice within half a second to cancel the door closing protection mechanism to prevent the door closing operation from being performed when the driver is not timely. When the prompt flag becomes 0 (the first preset flag), a cancel signal is also sent to the control module to cancel the door closing protection mechanism.

[0164] S307, when the vehicle starts to leave the station, the station reporting system sends a second electrical signal to the voice module, and the voice module is turned off.

[0165] The information provided by the station reporting system can be used to determine the opening and closing of the voice module to prevent the passenger from triggering the voice module by mistake during the vehicle driving process, and to reduce the power consumption of the voice module. The voice module is used for recognition, and when the preset voice prompt is recognized, the prompt flag is changed from the first preset flag to the second preset flag, and the preset voice prompt is played through the prompt module to remind the driver that someone wants to get off. Through the offline voice recognition technology and the preset voice library, the system can accurately recognize the passenger's request to get off, and the possibility of misrecognition is reduced. The voice library contains multiple languages and dialects to ensure that the system can serve passengers with different language backgrounds and improve the inclusiveness of the system. When the prompt flag is the second preset flag, and the driving state and the door state of the vehicle meet the door control condition, the control module controls the door to be always open, and the door closing protection mechanism is started to ensure that the door remains open before the passenger gets off. When the duration of the prompt flag being the second preset flag exceeds the preset duration, the prompt flag returns to the first preset flag, and the door closing protection mechanism is canceled to ensure that the door can be normally closed after the passenger gets off. The voice module, the control module and the prompt module can effectively solve the problem that the passenger cannot reach the get-off button during the peak period, and the oral prompt may be ignored. As long as the vehicle is in a non-starting state, the door will be immediately opened, and the driver will be informed that there is a passenger who wants to get off, so that the driver can pay attention to the rear passengers. At the same time, the door closing protection is triggered to prevent the driver from pressing the switch when the driver is not timely, to avoid the passenger being pinched, and to ensure that the passenger can get off in time and safely.

[0166] It should be noted that, for the method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present application are not limited to the action order described, because according to the embodiments of the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present application.

[0167] ReferenceFigure 4 , shows a structural block diagram of an embodiment of a voice recognition based vehicle door control device of the present application, and can specifically include the following modules:

[0168] The prompt flag changing module 401 is configured to change the prompt flag from a first preset flag to a second preset flag when the recognition result of the voice module is a preset recognition result, and play a preset voice prompt through the prompt module.

[0169] The vehicle door control condition meeting module 402 is configured to control the vehicle door to be always open through the control module and start a door closing protection mechanism when the prompt flag is the second preset flag and the driving state of the vehicle and the vehicle door state of the vehicle meet a vehicle door control condition.

[0170] The prompt flag restoring module 403 is configured to restore the prompt flag from the second preset flag to the first preset flag and cancel the door closing protection mechanism when the duration of the prompt flag being the second preset flag exceeds a preset duration.

[0171] In another embodiment of the present application, the vehicle door control condition meeting module 402 includes:

[0172] The determining module is configured to determine the driving state of the vehicle and the vehicle door state of the vehicle when the prompt flag is the second preset flag.

[0173] The meeting module is configured to control the vehicle door to be always open through the control module and start the door closing protection mechanism when the driving state of the vehicle and the vehicle door state of the vehicle meet a vehicle door control condition.

[0174] In another embodiment of the present application, the device further includes:

[0175] The driving state determining module is configured to determine the driving state of the vehicle according to the driving speed of the vehicle.

[0176] The vehicle door state determining module is configured to determine the vehicle door state of the vehicle according to the number of times the door opening button of the vehicle is pressed.

[0177] The vehicle door control condition determining module is configured to determine that the driving state of the vehicle and the vehicle door state of the vehicle meet the vehicle door control condition when the driving speed of the vehicle is a preset speed and the number of times the door opening button of the vehicle is pressed is at least once.

[0178] In another embodiment of the present application, the vehicle further comprises a plurality of voice input devices, the voice module comprises a voice library, the voice input devices are connected to the voice module, and the device further comprises:

[0179] a noise reduction processing module, configured to perform noise reduction processing on the voice audio received by the voice module to obtain noise reduction audio;

[0180] a voice recognition module, configured to perform voice recognition on the noise reduction audio to obtain a plurality of audio keywords;

[0181] a target keyword judgment module, configured to match the plurality of audio keywords with target keywords in the voice library to determine whether the noise reduction audio contains the target keywords in the voice library;

[0182] a first recognition result module, configured to determine that the recognition result of the voice module is the preset recognition result if the noise reduction audio contains the target keywords in the voice library;

[0183] a second recognition result module, configured to determine that the recognition result of the voice module is not the preset recognition result if the noise reduction audio does not contain the target keywords in the voice library.

[0184] In another embodiment of the present application, the voice module is connected to the prompt module and the control module respectively; the prompt flag change module 401 comprises a voice prompt playing module, configured to play the voice prompt when the prompt module receives a playing signal sent by the voice module;

[0185] The vehicle door control condition meeting module 402 comprises a vehicle door control module, configured to control the vehicle door to be always open when the control module receives a normally open signal sent by the voice module.

[0186] In another embodiment of the present application, the voice library comprises a plurality of language corresponding libraries, and the device comprises:

[0187] a target language determination module, configured to perform voice recognition on the noise reduction audio to determine a target language corresponding to the noise reduction audio;

[0188] a target library determination module, configured to determine a library corresponding to the target language as a target library in the voice library.

[0189] In another embodiment of the present application, the target keyword judgment module comprises:

[0190] The matching module is configured to match the plurality of audio keywords with target keywords in the target library to determine whether the target keywords in the target library exist in the noise-reduced audio.

[0191] In another embodiment of the present application, the device further comprises:

[0192] The door closing protection mechanism canceling module is configured to perform a preset operation on a door closing button of the vehicle to cancel the door closing protection mechanism if the prompt flag bit is not longer than the second preset flag bit for the preset time length.

[0193] In another embodiment of the present application, the voice module is connected with a station reporting system, and the device further comprises:

[0194] The first electric signal module is configured to turn on the voice module when the voice module receives a first electric signal sent by the station reporting system, and the first electric signal is used to indicate that the vehicle is arriving at a station.

[0195] The second electric signal module is configured to turn off the voice module and control the doors of the vehicle to be always closed by the control module when the voice module receives a second electric signal sent by the station reporting system, and the second electric signal is used to indicate that the vehicle is leaving a station.

[0196] For the device embodiment, it is basically similar to the method embodiment, so the description is relatively simple, and the relevant parts are described in the part of the method embodiment.

[0197] The present application also provides a non-volatile readable storage medium, which stores one or more modules (programs), and when the one or more modules are applied to a device, the device can execute instructions of each method step in the embodiments of the present application.

[0198] The embodiments of the present application provide one or more machine readable media, which store instructions, and when executed by one or more processors, make an electronic device execute the method in one or more of the above embodiments. In the embodiments of the present application, the electronic device includes terminal devices, servers (clusters) and other types of devices.

[0199] The embodiments of the present disclosure can be implemented as a device configured in a desired manner using any appropriate hardware, firmware, software, or any combination thereof, which can include terminal devices, servers (clusters) and other electronic devices. Figure 5 An exemplary device 500 that can be used to implement various embodiments described in the present application is schematically shown.

[0200] For one embodiment, Figure 5An example apparatus 500 is shown having one or more processors 502, a control module (chipset) 504 coupled to at least one of the processor(s) 502, a memory 506 coupled to the control module 504, a non-volatile memory (NVM) / storage device 508 coupled to the control module 504, one or more input / output devices 510 coupled to the control module 504, and a network interface 512 coupled to the control module 504.

[0201] The processor(s) 502 can include one or more single core or multicore processors, which can include any combination of general-purpose processors or dedicated processors (such as graphics processors, application processors, baseband processors, etc.). In some embodiments, the apparatus 500 can function as a terminal device, a server (cluster), etc. as described in embodiments of the present application.

[0202] In some embodiments, the apparatus 500 can include one or more computer- readable media (such as the memory 506 or the NVM / storage device 508) having instructions 514 and one or more processors 502 incorporated with the one or more computer-readable media configured to execute the instructions 514 to implement modules to perform the actions described in the present disclosure.

[0203] For one embodiment, the control module 504 can include any suitable interface controllers to provide for any suitable interface to at least one of the processor(s) 502 and / or any suitable device or component in communication with the control module 504.

[0204] The control module 504 can include a memory controller module to provide an interface to the memory 506. The memory controller module can be a hardware module, a software module, and / or a firmware module.

[0205] The memory 506 can be used, for example, to load and store data and / or instructions 514 for the apparatus 500. For one embodiment, the memory 506 can include any suitable volatile memory, such as suitable DRAM. In some embodiments, the memory 506 can include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0206] For one embodiment, the control module 504 can include one or more input / output controllers to provide an interface to the NVM / storage device 508 and the input / output device(s) 510.

[0207] For example, NVM / storage 508 can be used to store data and / or instructions 514. NVM / storage 508 can include any suitable non-volatile memory (e.g., flash memory) and / or can include any suitable non-volatile storage device(s) (e.g., hard disk drive(s) (HDD(s)), compact disk (CD) drive(s), and / or digital versatile disk (DVD) drive(s)).

[0208] NVM / storage 508 can include storage resources that are physically part of the device on which the apparatus 500 is installed or that is accessed remotely and / or via a network by the device. For example, NVM / storage 508 can be accessed via input / output device(s) 510 through a network.

[0209] Input / output device(s) 510 can provide an interface between apparatus 500 and any suitable device for the receipt, processing, and / or transmission of data between the apparatus 500 and any other suitable device. Input / output device(s) 510 can include communication components, audio components, sensor components, and / or the like. Network interface 512 can provide an interface between apparatus 500 and one or more networks, and the apparatus 500 can communicate wirelessly with one or more components of a wireless network according to any of one or more wireless network standards and / or protocols, such as to access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, 5G, and / or the like, or a combination thereof.

[0210] For one embodiment, at least one of processor(s) 502 can be packaged together with logic of one or more controllers of control module 504 (e.g., a memory controller module). For one embodiment, at least one of processor(s) 502 can be packaged together with logic of one or more controllers of control module 504 to form a system in a package (SiP). For one embodiment, at least one of processor(s) 502 can be integrated on the same die with logic of one or more controllers of control module 504. For one embodiment, at least one of processor(s) 502 can be integrated on the same die with logic of one or more controllers of control module 504 to form a system on a chip (SoC).

[0211] In various embodiments, the apparatus 500 can be, but is not limited to, a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.) or the like. In various embodiments, the apparatus 500 can have more or fewer components, and / or different architectures. For example, in some embodiments, the apparatus 500 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including touch screen displays), non- volatile memory port, multiple antennas, a graphics chip, an application specific integrated circuit (ASIC), and a speaker.

[0212] In the detection device, a master control chip can be used as a processor or a control module, sensor data, position information, etc. are stored in a memory or NVM / storage device, a sensor group can be used as an input / output device, and a communication interface can include a network interface.

[0213] For the apparatus embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts are described in the method embodiment.

[0214] Each of the embodiments in the specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can be referred to each other.

[0215] The embodiments of the present application are described with reference to flowcharts and / or block diagrams according to the method, terminal device (system), and computer program product of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable based on voice recognition vehicle door control terminal device processor to produce a machine, so that the instructions executed by the computer or other programmable based on voice recognition vehicle door control terminal device processor produce a device for implementing the functions specified in the flowcharts and / or blocks. Figure 1 The device for implementing the functions specified in one or more flows and / or blocks. Figure 1 The device for implementing the functions specified in one or more flows and / or blocks.

[0216] These computer program instructions can also be stored in a computer readable memory that can guide the computer or other programmable based on voice recognition vehicle door control terminal device to work in a specific way, so that the instructions stored in the computer readable memory produce a product including instruction devices, which implement the functions specified in the flowcharts and / or blocks. Figure 1 The device for implementing the functions specified in one or more flows and / or blocks. Figure 1 The device for implementing the functions specified in one or more flows and / or blocks.

[0217] These computer program instructions can also be loaded into a computer or other programmable voice recognition based vehicle door control terminal device to cause a series of operational steps to be performed on the computer or other programmable terminal device to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal device provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0218] While preferred embodiments of the application have been described, a wide variety of modifications, alterations, and permutations can be made by those of ordinary skill in the art now that the general nature of the application is known. Accordingly, it is intended that the appended claims be interpreted as including all such alterations and modifications.

[0219] Finally, it is to be understood that the phraseology or terminology employed herein, such as "first" and "second", etc., are for descriptive purposes only and should not be construed to be limiting unless otherwise indicated. Furthermore, the terms "comprise", "include", or "contain" or variants thereof, do not exclude the presence of other elements or steps than those listed in a process, method, article, or apparatus. The terms "comprise", "comprising", "include", "including" and "contain", "containing" as well as variants thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, article, or apparatus that comprises a list of elements is not necessarily limited to only those elements in the list, but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0220] The above provides a voice recognition based vehicle door control method and device, an electronic device and a storage medium, and the principles and implementation modes of the present application are described by applying specific examples. The above description of the embodiments is only intended to help understand the method and core idea of the present application; for those skilled in the art, the specific implementation modes and application ranges can be changed according to the idea of the present application. In summary, the content of the specification should not be understood as limiting the present application.

Claims

1. A vehicle door control method based on voice recognition, characterized in that, Applied to a vehicle, the vehicle including a voice module, a control module, and a prompting module, the method includes: When the recognition result of the voice module is the preset recognition result, the prompt flag is changed from the first preset flag to the second preset flag, and the preset voice prompt is played through the prompt module; When the prompt flag is the second preset flag, and the vehicle's driving state and the vehicle's door state meet the door control conditions, the control module controls the vehicle's door to remain open and activates the door closing protection mechanism. When the duration of the prompt flag being the second preset flag exceeds a preset duration, the prompt flag is restored from the second preset flag to the first preset flag, and the door closing protection mechanism is canceled.

2. The method according to claim 1, characterized in that, When the indicator flag is the second preset flag, and the vehicle's driving state and the vehicle's door state meet the door control conditions, the control module controls the vehicle's door to remain open and activates the door closing protection mechanism, including: When the prompt flag is the second preset flag, the driving status of the vehicle and the status of the vehicle door are determined. When the vehicle's driving state and the vehicle's door state meet the door control conditions, the control module controls the vehicle's door to remain open and activates the door closing protection mechanism.

3. The method according to claim 2, characterized in that, Before the method further includes controlling the vehicle door to remain open and activating the door closing protection mechanism by means of the control module when the vehicle's driving state and the vehicle door state meet the door control conditions, the method also includes: The driving status of the vehicle is determined based on its driving speed; The vehicle door status is determined based on the number of times the vehicle's door opening button is pressed. When the vehicle's driving speed is a preset speed and the vehicle's door opening button is pressed at least once, it is determined that the vehicle's driving state and the vehicle's door state meet the door control conditions.

4. The method according to claim 1, characterized in that, The vehicle also includes multiple voice input devices. The voice module includes a voice dictionary. The voice input devices are connected to the voice module. Before changing the prompt flag from the first preset flag to the second preset flag and playing the preset voice prompt through the prompt module when the recognition result of the voice module is a preset recognition result, the method further includes: When the voice module receives voice audio sent by the voice input device, it performs noise reduction processing on the voice audio to obtain noise-reduced audio. The noise-reduced audio is subjected to speech recognition to obtain multiple audio keywords; The multiple audio keywords are matched with the target keywords in the speech lexicon to determine whether the target keywords in the speech lexicon exist in the noise-reduced audio. If the target keyword in the speech lexicon exists in the noise-reduced audio, then the recognition result of the speech module is determined to be the preset recognition result; If the target keyword in the speech lexicon is not present in the noise-reduced audio, then the recognition result of the speech module is determined to be different from the preset recognition result.

5. The method according to claim 1, characterized in that, The voice module is connected to the prompt module and the control module respectively; the step of playing a preset voice prompt through the prompt module includes: when the prompt module receives a playback signal sent by the voice module, it plays the voice prompt. The step of controlling the vehicle door to be permanently open via the control module includes: when the control module receives a permanently open signal sent by the voice module, controlling the vehicle door to be permanently open.

6. The method according to claim 4, characterized in that, The speech lexicon includes lexicons corresponding to multiple languages. Before performing speech recognition on the noise-reduced audio to obtain multiple audio keywords, the method further includes: Speech recognition is performed on the noise-reduced frequency to determine the target language corresponding to the noise-reduced frequency; The vocabulary corresponding to the target language in the speech vocabulary is determined as the target vocabulary.

7. The method according to claim 6, characterized in that, The step of matching multiple audio keywords with target keywords in the speech lexicon to determine whether the target keywords in the speech lexicon exist in the noise-reduced audio includes: The audio keywords are matched with the target keywords in the target dictionary to determine whether the target keywords in the target dictionary exist in the noise-reduced audio.

8. The method according to claim 1, characterized in that, The method further includes: If the duration of the prompt flag being the second preset flag does not exceed the preset duration, then a preset operation is performed on the vehicle's door closing button to cancel the door closing protection mechanism.

9. The method according to claim 1, characterized in that, The voice module is connected to the station announcement system, and the method further includes: When the voice module receives the first electrical signal from the station announcement system, the voice module is activated; the first electrical signal is used to indicate that the vehicle has arrived at the station. When the voice module receives the second electrical signal from the station announcement system, it shuts down the voice module and controls the vehicle door to remain closed via the control module; the second electrical signal is used to indicate that the vehicle has left the station.

10. A vehicle door control device based on voice recognition, characterized in that, Applied to a vehicle, the vehicle including a voice module, a control module, and a prompting module, the device includes: The prompt flag changing module is used to change the prompt flag from the first preset flag to the second preset flag when the recognition result of the voice module is a preset recognition result, and to play a preset voice prompt through the prompt module. The door control condition satisfaction module is used to control the vehicle door to be always open and activate the door closing protection mechanism when the prompt flag is the second preset flag and the vehicle's driving state and the vehicle's door state meet the door control conditions. The prompt flag restoration module is used to restore the prompt flag from the second preset flag to the first preset flag and cancel the door closing protection mechanism when the duration of the prompt flag being the second preset flag exceeds a preset duration.

11. An electronic device, characterized in that, include: processor; and A memory having executable code stored thereon, which, when executed, causes the processor to perform the voice recognition-based door control method as described in any one of claims 1-9.

12. One or more machine-readable media having executable code stored thereon, which, when executed, causes a processor to perform the voice recognition-based door control method as described in any one of claims 1-9.

Images