Parking method and system, electronic equipment and storage medium

Through voice and biometric technology, parking control without keys or mobile phones is achieved, solving the problems of cumbersome control and poor safety of existing remote parking systems, and improving the recognition and security of automatic parking.

CN118928368APending Publication Date: 2024-11-12吉咖智能机器人有限公司
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411187337.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing remote parking system relies on a physical remote control or mobile phone, and has cumbersome control and poor security. The automatic parking function cannot be used when the key is out of power or malfunctions, which has poor recognition.

Method used

Use voice information and biometric technology (such as face, fingerprint, retina) for user identity verification, combined with voice recognition and voiceprint recognition, to achieve parking control without keys or mobile phones, and to achieve legality through voice commands and biological information outside the car Verify to ensure accurate identification of user identity and parking intention.

Benefits of technology

It realizes simple, safe and reliable parking control without physical keys or mobile phones, improves the recognition and security of automatic parking, and ensures that the parking function can still be used normally when the key is insufficient or has a fault.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928368A_ABST
    Figure CN118928368A_ABST
Patent Text Reader

Abstract

The invention relates to a parking method and system, electronic equipment and a storage medium. The method comprises the steps that in response to received voice information from a user outside a vehicle, whether the user meets a preset condition or not is determined based on first type information in the voice information; detecting second type information in the voice information, wherein the second type information is associated with the parking intention of the user; and controlling the vehicle to park in response to determining that the user meets the preset condition and detecting the second type of information. The parking function does not need to be matched with a key or a mobile phone. The system can adopt one or two or a combination of a plurality of biological information such as face, fingerprint, palm print and retina to be matched with voice information, all the biological information adopts a human biological recognition technology, and the recognition technologies and the vehicle control are mutually matched and cooperatively used, so that the inconvenience caused by the need of matching of a physical key and a mobile phone in the prior art is broken through, and the system is high in recognizability and good in safety.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure generally relates to the field of autonomous driving, and in particular to a parking method, system, electronic device, and storage medium. Background Art

[0002] With the development of science and technology, cars have transformed from simple means of transportation to smart devices, and smart driving and smart control of cars are the current development direction of cars; among them, remote parking technology is one of the important developments in recent years. Remote parking is mainly to solve the problem of inconvenience in opening the door when the vehicle is parked in the middle parking space. The existing remote parking system mainly relies on physical remote controls or mobile phone applications, which are not convenient in some cases. In the prior art, the control scheme that uses keys for legitimacy verification has not completely gotten rid of the traditional key-controlled parking, and the control is more cumbersome. When the key is out of power or fails, the automatic parking function cannot be used. The current automatic parking control has poor recognition and poor safety.

[0003] Therefore, in order to solve the above problems, there is an urgent need to provide a new parking control that does not rely on keys or mobile phones and can realize human-vehicle interaction outside the car, and the control is relatively simple, safe, and reliable. Summary of the invention

[0004] According to an exemplary embodiment of the present disclosure, a parking control solution is provided to at least partially solve the problems existing in the prior art.

[0005] In a first aspect of the present disclosure, a parking method is provided. The method includes: in response to receiving a voice message from a user outside a vehicle, determining whether the user meets a preset condition based on first type information in the voice message; detecting second type information in the voice message, the second type information being associated with the user's parking intention; and in response to determining that the user meets the preset condition and detecting the second type information, controlling the vehicle to park.

[0006] In some embodiments, the voice message from the user is received in response to determining that one or more modules of the vehicle are not powered off.

[0007] In some embodiments, in response to receiving voice information from a user outside a vehicle, determining whether the user meets a preset condition based on a first type of information in the voice information includes: in response to receiving biological information from the user outside the vehicle, the biological information including one or more of the following: face, fingerprint, palm print, and retina; determining whether the user meets the preset condition based on the first type of information and the biological information; and in response to determining that the recognition degree of the first type of information and the biological information is greater than a predetermined threshold, determining that the preset condition is met.

[0008] In some embodiments, the method may further include: copying the voice information; and acquiring the first type of information and the second type of information based on the voice information and the copied voice information. That is, in response to receiving a voice message from a user outside the vehicle, the voice information is copied into two copies for acquiring the first type of information and the second type of information respectively.

[0009] In some embodiments, the method may also include: in response to receiving voice information from a user outside the vehicle, determining whether the user meets a preset condition based on a first type of information in the voice information includes: training a voiceprint recognition model based on the first type of information; and using the voiceprint recognition model to determine whether the user meets the preset condition.

[0010] In some embodiments, the method may further include: determining whether the interior of the vehicle includes a person; and in response to determining that the interior of the vehicle does not include a person, controlling the vehicle to park.

[0011] In some embodiments, the method may further include: performing voice information preprocessing in response to voice information, the preprocessing including: noise reduction and gain control; extracting features to be trained based on the preprocessed voice information; training an acoustic model based on the extracted features to be trained to output target information; generating multiple text sequences based on the target information using a language model and a dictionary; taking the probability of the text sequence evaluated by the language model and generated by the dictionary as the evaluation result of the language model; selecting the text sequence with the highest probability as the result of determining whether the user is a legitimate user; and post-processing the result to identify the user's parking intention.

[0012] In some embodiments, the method may further include: in response to determining that the user satisfies the preset condition and detecting the second type of information, controlling the vehicle to park may include: in response to determining that at least one of the control-related conditions, safety-related conditions, and physical state conditions for the vehicle is satisfied, controlling the vehicle to park. Specifically, the vehicle may be controlled to park in response to determining that the following items are satisfied: the user outside the vehicle is a legitimate user; the user outside the vehicle intends to park; the cabin-parking integrated controller is fault-free and the parking peripheral hardware is fault-free; the vehicle controller is fault-free; the control actuator is fault-free; the posture control function of the vehicle controller is turned on and not activated; the vehicle state of the vehicle controller is normal; and all vehicle doors and trunk lids are closed and the vehicle is stationary.

[0013] In some embodiments, the method may further include: if any or all of the voiceprint, face, fingerprint, palmprint, and retinal recognition degrees are greater than a predetermined threshold, the user is determined to be a legitimate user. For example, if one of the voiceprint, face, fingerprint, palmprint, and retinal recognition degrees is greater than 70%, the user is determined to be a legitimate user; for another example, if all of the voiceprint, face, fingerprint, palmprint, and retinal recognition degrees are greater than 70%, the user is determined to be a legitimate user.

[0014] In some embodiments, the method may further include: in response to the vehicle being in sleep mode, the A2B chip is not powered off, and the external AMP and the MIC are not powered off.

[0015] In some embodiments, the method may also include: in response to a conversation between a user and an off-vehicle MIC, the off-vehicle MIC obtains the user's audio stream and transmits it to the cabin domain control; after the cabin domain control obtains the audio stream, it copies it into two audio sources and transmits them to the voiceprint recognition module and the speech recognition module respectively.

[0016] In some embodiments, the method may further include: the voiceprint recognition module uses the voiceprint recognition model to verify the legitimacy of the sound outside the vehicle and identify the user's identity. At the same time, the voiceprint recognition module uses the voiceprint data collected from the user's sound source to train the voiceprint recognition model.

[0017] In some embodiments, the method may also include: a speech recognition module performs intention recognition on sounds outside the vehicle, including preprocessing: preprocessing the collected speech signals, including: noise reduction and gain control, to improve the accuracy of speech recognition; feature extraction: extracting useful features from the preprocessed speech signals; acoustic model: using the extracted features to train the acoustic model, which can map speech features to phonemes or words; decoder: the decoder uses the output of the acoustic model, combined with the language model and dictionary, to generate a series of possible text sequences; language model: the language model is used to evaluate the probability of the text sequence generated by the decoder, and the model is an n-gram model or a neural network model; search strategy: based on the evaluation results of the language model, the search strategy selects the most likely text sequence as the recognition result; post-processing: post-processing the recognition results; result output: output the recognized user intent.

[0018] In some embodiments, the method may further include: a parking function, which includes the entire process of parking environment perception, target detection and tracking, parking space detection, path planning, and control, and outputs control instructions to the vehicle controller, which may specifically include:

[0019] Environmental perception: First, the surrounding environment is perceived through various on-board sensors to obtain obstacle information and road information around the vehicle; target detection and tracking: through the target detection algorithm, other vehicles, pedestrians, and obstacle targets are identified from the perceived environmental information, and these targets are tracked through the target tracking algorithm; parking space detection: through the parking space detection algorithm, available parking spaces are identified from the perceived environmental information; path planning: according to the current vehicle status and the position of the target parking space, a path planning algorithm is used to plan a path from the current position to the target parking space.

[0020] In some embodiments, the method may further include: if there is an obstacle on the planned path, braking to a stop and waiting for the obstacle to leave before continuing to park; if the obstacle persists for more than a predetermined threshold, exiting the remote control parking and requesting the user to take over.

[0021] In some embodiments, the method may further include: path planning may use an algorithm to calculate the costs of N paths and select the one with the lowest cost.

[0022] In some embodiments, the method may further include: the vehicle controller controls the actuator to perform lateral and longitudinal control, light control, and remote control parking.

[0023] In a second aspect of the present disclosure, a parking device is provided. The device includes: a legitimate user identification module, configured to, in response to receiving voice information from a user outside a vehicle, determine whether the user meets a preset condition based on first type information in the voice information; a parking intention identification module, configured to detect second type information in the voice information, the second type information being associated with the user's parking intention; and a parking control module, configured to control the vehicle to park in response to determining that the user meets the preset condition and detecting the second type information; the parking device is used to execute the parking method described in any embodiment of the first aspect of the present disclosure.

[0024] In a third aspect of the present disclosure, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to the first aspect of the present disclosure.

[0025] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and when the program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0026] In a fifth aspect of the present disclosure, a computer program product is provided, which includes a computer program / instructions, and when the computer program / instructions are executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0027] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure, wherein:

[0029] Figure 1 A schematic diagram illustrating an example environment in which various embodiments of the present disclosure can be implemented;

[0030] Figure 2 A schematic block diagram of a parking method according to multiple embodiments of the present disclosure is shown;

[0031] Figure 3 A schematic block diagram of a control system architecture according to multiple embodiments of the present disclosure is shown;

[0032] Figure 4 A schematic diagram showing three modes in path planning according to multiple embodiments of the present disclosure is shown.

[0033] Figure 5 A schematic block diagram of a parking device according to multiple embodiments of the present disclosure is shown;

[0034] Figure 6 A block diagram of a computing device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0035] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0036] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below. It should be understood that the parking mentioned herein may include parking in or parking out.

[0037] As mentioned above, the control scheme of the prior art that uses keys for legitimacy verification has not completely gotten rid of the traditional key-controlled parking, and the control is more cumbersome. In addition, the automatic parking function cannot be used when the key is out of power or fails. The current automatic parking control has problems such as poor recognition and poor safety. Therefore, in order to solve the above problems, it is urgent to provide a new parking control that does not rely on keys or mobile phones and realizes human-vehicle interaction outside the car, and has relatively simple control, high recognition, high safety, and strong reliability.

[0038] Each embodiment of the present disclosure uses only sound outside the vehicle, and can also use biological information such as one or two or more combinations of face, fingerprint, palm print, retina and voice information. All use human biometric technology, and each recognition technology cooperates with each other and with vehicle control, breaking the inconvenience of the previous need for physical keys and mobile phones. It has high recognition and good security, improves control efficiency and improves user experience. The present disclosure copies the voice information into two copies and transmits them simultaneously as the sound source for identifying legitimate users and identifying intentions. The two copies are obtained simultaneously and in a timely manner, which improves efficiency and prevents sound loss.

[0039] The following will combine Figures 1 to 6 Exemplary embodiments of the present disclosure are schematically introduced.

[0040] Figure 1 A schematic diagram of an example environment 100 in which multiple embodiments of the present disclosure can be implemented is shown. A vehicle 101 is schematically shown in the environment 100, and the vehicle 101 can perform corresponding operations in response to voice input from a user outside the vehicle. For example, a legitimate user can input a voice command outside the vehicle, and the vehicle 101 recognizes the legitimate user and performs a parking operation according to the user's voice input command. The parking operation may include, for example, parking in or parking out.

[0041] In some embodiments, the vehicle 101 may be any type of vehicle that can carry people and / or objects and move through a power system such as an engine, including but not limited to cars, trucks, buses, electric vehicles, motorcycles, RVs, trains, etc. In some embodiments, one or more vehicles 101 in the environment 100 may be vehicles with certain autonomous driving capabilities, which are also referred to as unmanned vehicles. In some embodiments, the vehicle 101 may also be a vehicle without autonomous driving capabilities.

[0042] In some embodiments, continue to refer to Figure 1 , the vehicle 101 can be communicatively coupled to the computing device 103. Although shown as a separate entity, the computing device 103 can be embedded in the vehicle 101. The computing device 103 can also be an entity external to the vehicle 101 and can communicate with the vehicle 101 via a wireless network. The computing device 103 can be any device with computing capabilities. As a non-limiting example, the computing device 103 can be any type of fixed computing device, mobile computing device, or portable computing device, including but not limited to a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a multimedia computer, a mobile phone, etc.; all or part of the components of the computing device 103 can be distributed in the cloud. The computing device 103 includes at least a processor, a memory, and other components that are typically present in a general-purpose computer to implement computing, storage, communication, control, and the like. The computing device 103 can perform all or part of the operations according to the various embodiments of the present disclosure, which will be described in detail below.

[0043] It should be understood that Figure 1 Only one example environment in which the vehicle may be traveling is shown. In addition to traveling on outdoor roads, the vehicle 101 may also be traveling in various environments such as tunnels, outdoor parking lots, inside buildings (e.g., indoor parking lots), residential areas, and parks. Figure 1 To describe the embodiments of the present disclosure.

[0044] Figure 2 FIG. 2 shows a schematic diagram of a parking method 200 according to an embodiment of the present disclosure. For example, the method 200 may be performed as follows: Figure 1 The method 200 is executed by the computing device 103 shown. It should be understood that the method 200 may also include additional blocks not shown and / or may omit the blocks shown, and the scope of the present disclosure is not limited in this respect.

[0045] exist Figure 2In the illustrated embodiment, a parking method is provided, including: in box 201, in response to receiving a voice message from a user outside the vehicle, determining whether the user meets a preset condition based on the first type of information in the voice message. In one embodiment, in response to receiving a voice message from a user outside the vehicle, determining whether the user is a legitimate user based on the first type of information in the voice message; in box 202, detecting the second type of information in the voice message, the second type of information being associated with the user's parking intention. Specifically, the second type of information in the voice message can be determined, the second type of information being associated with the user's parking intention; and in box 203, in response to determining that the user meets the preset condition and detecting the second type of information, controlling the vehicle to park. For example, in response to determining that the user is a legitimate user, the vehicle can be controlled to park based on the second type of information.

[0046] In one embodiment, a voice message may be received from a user in response to determining that one or more modules of the vehicle are not powered off.

[0047] In some embodiments, the first type of information may, for example, reflect various types of information of the unique identity of the user. In one example, the first type of information may be embodied as voiceprint information. Voiceprint information is a biometric technology that identifies an individual by analyzing the characteristics of a person's voice. In other embodiments. The second information may, for example, be parking intention information, that is, the willingness or need of the driver or passenger of the vehicle 101 to park. This information may come from the driver's voice command. The recognition of parking intention information helps the system to make judgments in advance, thereby improving parking efficiency and user experience.

[0048] In some embodiments, in response to receiving biometric information from a user outside the vehicle; determining whether the user is a legitimate user based on the first type of information and the biometric information; in response to determining that the recognition degree of the first type of information and the biometric information is greater than a predetermined threshold, determining that the user is a legitimate user. It should be understood that the first type of information and the biometric information may overlap or may be different types of information. When they are different types of information, the accuracy and security of determining a legitimate user are higher. In some embodiments, the biometric information may be one or a combination of two or more of face, fingerprint, palm print, and retina.

[0049] In some embodiments, in response to receiving a voice message from a user outside the vehicle, the voice message may be copied, and first type information and second type information may be obtained based on the voice message and the copied voice message. Specifically, in response to receiving a voice message from a user outside the vehicle, the voice message may be copied into two copies for use as first type information and second type information or for extracting first type information and second type information. For example, see Figure 3After the cabin domain control obtains the audio stream, it copies it into two sound sources, so that voice recognition and voiceprint recognition can be obtained simultaneously and in a timely manner; the external sound enters the SOC through the A2B chip, and the audio DSP integrated in the SOC copies and diverts the sound.

[0050] In some embodiments, in response to the first type of information, a voiceprint recognition model is trained; the voiceprint recognition model is used to determine whether the user is a legitimate user. A noise elimination algorithm can be used to process environmental noise to improve the accuracy of voiceprint recognition, and the voiceprint recognition model can be used to learn the user's voiceprint data to accurately identify the user's identity, and the ID of the identified user's identity is compared with the voiceprint ID pre-stored in the cabin-motor integrated controller. If the comparison is successful, the user is considered a legitimate user; if it is unsuccessful, it is considered an illegitimate user.

[0051] In some embodiments, the further step includes: determining whether there is a person inside the vehicle; and in response to determining that there is no person inside the vehicle, controlling the vehicle to park.

[0052] In some embodiments, the method further includes: performing voice information preprocessing in response to the voice information, wherein the preprocessing includes: noise reduction and gain control, which can improve the accuracy of voice recognition.

[0053] In some embodiments, it also includes: extracting useful features (such as Mel-frequency cepstral coefficients MFCC, etc.) based on the preprocessed speech information; training an acoustic model based on the extracted useful features and outputting it (the acoustic model can map speech features to phonemes or words); generating multiple text sequences based on the output of the acoustic model (the decoder uses the output of the acoustic model), in combination with a language model and a dictionary; evaluating the probability of the generated text sequence based on the language model (usually using an n-gram model or a neural network model) as an evaluation result of the language model; in response to the evaluation result of the language model, selecting the text sequence with the highest probability as the result of determining whether the user is a legitimate user; post-processing the result (such as punctuation prediction, semantic understanding, etc.), and outputting the identified user's parking intention.

[0054] In some embodiments, it also includes: responding to the user outside the vehicle being a legitimate user; responding to the user outside the vehicle intending to park; responding to the cabin-parking integrated controller (for example, including SOC chip, MCU chip, peripheral chip) being fault-free and the parking peripheral hardware (for example, external AMP, MIC, parking camera, USS being fault-free) being fault-free; responding to the vehicle controller (for example, SOC chip, MCU chip, peripheral chip) being fault-free; responding to the control actuator (for example, steering actuator, brake actuator, power actuator, body electronic actuator) being fault-free; responding to the posture control function (for example, ESP, ABS, etc.) of the vehicle controller being turned on and not activated; responding to the vehicle status of the vehicle controller being normal; responding to all doors and trunk lids of the vehicle being closed and the vehicle being in a stationary state; executing automatic parking in or out function.

[0055] In the above embodiments, SOC, namely System on a Chip, is an integrated circuit that integrates all or part of the functions of a computer or other electronic system into a single chip; MCU, namely Microcontroller Unit, also known as a single-chip microcomputer, is an integrated circuit chip that appropriately reduces the frequency and specifications of the central processing unit CPU, and integrates peripheral interfaces such as memory, timer, USB, A / D conversion, UART, PLC, DMA or LCD driver circuits on a single chip to form a chip-level computer, which performs different combination controls for different application scenarios; peripheral chips usually refer to chips used for specific functions, such as sensor interfaces, communication interfaces, etc., in addition to the core processor (such as SOC or MCU); AMP, namely Audio Power Amplifier (audio power amplifier) ​​is used to amplify the power of audio signals to drive speakers; MIC is Microphone, which is used to receive sound and convert it into electrical signals; parking camera usually refers to a camera installed on the outside of the vehicle to assist the driver in parking operations; USS is UltraSonicSensor, which is used to measure distance or detect the existence of objects, and is usually used in parking assistance systems; ESP is Electronic Stability Program, which is a control system that can prevent skidding and side skidding. Its main function is to control the longitudinal and lateral stability of the vehicle to ensure that the vehicle drives according to the driver's consciousness; ABS is Anti-lock Braking System (anti-lock braking system), which can automatically adjust the wheel braking force during braking to prevent the wheels from locking in order to achieve the best braking effect; steering actuator refers to the actuator used to control the vehicle steering, responding to the steering command issued by the vehicle control system; brake actuator is the actuator that controls the vehicle braking system, responding to the braking command to slow down or stop; power actuator is usually the control mechanism of the engine or motor in the vehicle, used to respond to acceleration or deceleration commands; body electronic actuator is used to control the actuators of other electronic systems of the body (such as windows, door locks, etc.).

[0056] In some embodiments, the method further includes: in response to any or all of the voiceprint, face, fingerprint, palmprint, and retinal recognition being greater than a predetermined threshold, the user is judged to be a legitimate user. For example, if one of the voiceprint, face, fingerprint, palmprint, and retinal recognition is greater than 70%, the user is judged to be a legitimate user; for another example, if all of the voiceprint, face, fingerprint, palmprint, and retinal recognition are greater than 70%, the user is judged to be a legitimate user. In another embodiment, the method may further include: in response to the voiceprint, face, fingerprint, palmprint, and retinal recognition being greater than 80%, the user is judged to be a legitimate user. In yet another embodiment, the method further includes in response to the voiceprint, face, fingerprint, palmprint, and retinal recognition being greater than 90%, the user is judged to be a legitimate user.

[0057] In some embodiments, the method further includes: in response to the continuous iterative training of the training model, the result size of the user recognition of the vehicle can be changed and improved, for example, the recognition degree is increased from greater than 90% to greater than 95% after training for more than a predetermined number of times as the judgment result of a legitimate user, thereby improving safety. With the continuous iteration and optimization of the training model, the user recognition of the vehicle can be significantly improved. For example, in the initial stage, the vehicle may only be able to achieve a recognition degree of 80% or 90% to determine whether the user outside the vehicle is a legitimate user. However, as the number of training times increases, this recognition degree can be gradually improved. After the model has been iteratively trained for more than 100 times, the recognition degree can be increased from greater than 90% to greater than 95% as a benchmark for judging legitimate users. This means that the vehicle's identification system will be more accurate and can more accurately identify legitimate users, thereby greatly improving the safety of the vehicle.

[0058] The process of improving user recognition involves optimization in multiple aspects. First, the quality and diversity of training data are crucial to the learning effect of the model. By collecting more diverse and more realistic user data, the model can better learn the characteristics of different users, thereby improving recognition. Secondly, the selection and optimization of the algorithm is also key. The use of advanced machine learning algorithms, such as deep learning algorithms, can more effectively extract features from data and build more accurate recognition models. In addition, the iterative training process of the model also needs to be carefully designed, including the adjustment of the learning rate, the division of training batches, etc., to ensure that the model can gradually learn more accurate user characteristics.

[0059] When the user recognition rate of the vehicle is increased to more than 95%, the safety of the vehicle will be significantly improved. Legitimate users will be able to be identified more quickly and accurately, so that they can enjoy more convenient and safe vehicle services. At the same time, the probability of illegal users being misidentified as legitimate users will be greatly reduced, further ensuring the safety of the vehicle.

[0060] In one embodiment, in response to determining whether voiceprint and / or facial and / or fingerprint and / or palmprint and / or retinal recognition has failed, when one or more of the voiceprint and / or facial and / or fingerprint and / or palmprint and / or retinal recognitions have failed, the remaining valid recognitions are used for automatic parking control.

[0061] In some embodiments, after the vehicle goes into sleep mode, the A2B chip is not powered off, and the external AMP and MIC are not powered off. Specifically, the A2B (Audio Bus) chip is commonly used for high-speed digital audio transmission in car audio systems. Even if the vehicle is in sleep mode, the A2B chip may need to remain powered in order to maintain connection with certain key systems (such as entertainment systems, communication systems, etc.). This helps to quickly restore the functions of the audio system when the vehicle is reawakened, providing a seamless user experience. The external AMP is responsible for amplifying the audio signal to drive the speaker. In some designs, in order to maintain the standby state of the vehicle audio system or to implement certain specific functions (such as vehicle safety alarms), the external AMP may need to continue to be powered after the vehicle goes into sleep mode. Keeping the AMP powered can ensure a quick response to audio needs when needed, and also helps protect the audio system from potential damage. The MIC is used to receive sound and convert it into electrical signals, and is an important part of vehicle communication systems (such as Bluetooth phones, voice control systems, etc.). Keeping the MIC powered after the vehicle goes into sleep mode ensures a quick response when voice commands or phone calls are received.

[0062] In some embodiments, the user uses the MIC outside the vehicle to talk, and the MIC outside the vehicle obtains the user's audio stream and transmits it to the cabin domain control; after the cabin domain control obtains the audio stream, it copies it into two audio sources and transmits them to the voiceprint recognition module and the speech recognition module respectively. Specifically, when the user uses the MIC outside the vehicle to talk, the MIC outside the vehicle captures the user's voice and converts it into a digital audio stream. In order to ensure the clarity and quality of the audio stream, the MIC usually adopts advanced noise reduction and echo cancellation technology to eliminate environmental noise and echoes that may be generated inside the vehicle. At this time, once the audio stream is captured, it can be transmitted to the cabin domain control (also known as the body domain controller or central controller) through the vehicle's communication bus (such as CAN bus, LIN bus or Ethernet). The cabin domain control is a key component in the vehicle, responsible for coordinating and managing the functions and data exchanges of multiple subsystems. After receiving the audio stream, the cabin domain control will perform a series of processing operations. First, it will check the quality and integrity of the audio stream to ensure the accuracy of subsequent recognition. Then, the cabin domain control will copy the audio stream into two audio sources for simultaneous transmission to the voiceprint recognition module and the speech recognition module.

[0063] In one embodiment, the voiceprint recognition module can be a software or hardware component specifically used to identify the user's voice characteristics. It receives the audio stream transmitted by the cabin domain control and extracts the voice features (such as frequency, pitch, speaking speed, etc.) therein. The voiceprint recognition module then compares these features with the pre-stored user voiceprint model to verify the user's identity. If the comparison is successful, the voiceprint recognition module sends a signal to the vehicle control system indicating that the user is a legitimate user and authorizes it to perform subsequent operations. The speech recognition module can be used to parse the instructions or information in the user's voice. It also receives the audio stream transmitted by the cabin domain control and applies advanced speech recognition algorithms to parse the voice content. Once the speech recognition module successfully parses the user's instructions or information, it converts it into instructions or signals that the vehicle control system can understand and sends it to the corresponding actuator (such as steering actuator, brake actuator, etc.) to execute the user's request.

[0064] In one embodiment, the voiceprint recognition module uses the voiceprint recognition model to verify the legitimacy of the sound outside the vehicle and identify the user's identity. At the same time, the voiceprint recognition module uses the voiceprint data collected from the user's sound source to train the voiceprint recognition model. Specifically, the voiceprint recognition model can accurately verify the legitimacy of the sound outside the vehicle, effectively identify and verify the user's identity, and ensure that only authorized users can interact with the vehicle. At the same time, in order to continuously improve the accuracy and reliability of voiceprint recognition, the voiceprint recognition module will continue to collect voiceprint data from the user's sound source, and use this data to train and optimize the voiceprint recognition model to ensure that the system can better adapt to various complex environments and provide users with a safer and smarter interactive experience.

[0065] In some embodiments, parking may include the entire process of parking perception, planning, and control, and output control instructions to the vehicle controller (acceleration and deceleration, steering angle, and exterior lighting control). Specifically, it may include, first, environmental perception, sensing the surrounding environment through various on-board sensors (such as ultrasonic radars and surround-view cameras), and obtaining obstacle information and road information around the vehicle. Secondly, target detection and tracking are performed, that is, other vehicles, pedestrians, and obstacle targets are identified from the perceived environmental information through a target detection algorithm, and these targets are tracked through a target tracking algorithm. Next, parking space detection is performed, and available parking spaces can be identified from the perceived environmental information through a parking space detection algorithm; finally, path planning is performed, and a path planning algorithm can be used to plan a path from the current position to the target parking space based on the current state of the vehicle and the position of the target parking space.

[0066] In some embodiments, when an obstacle is detected on the planned parking path (for example, at a point on the vehicle's expected trajectory in the next 5 seconds), the system will immediately activate the emergency braking mechanism to safely stop the vehicle to avoid a collision with the obstacle. At the same time, the system will continue to monitor the status of the obstacle. Once the obstacle leaves, the parking function will automatically resume and continue to perform the remaining parking operations. However, if the obstacle does not leave within a specific period of time (for example, it continues to exist for 3 minutes), the system will determine that the obstacle is a long-term obstruction. At this time, it will automatically exit the remote parking mode and issue a prompt to request the user to take over the vehicle so that this special situation can be handled manually to ensure the safety and smoothness of the parking process.

[0067] In some embodiments, path planning can use an algorithm (such as an A* algorithm) to calculate the cost of N paths and select the one with the lowest cost. When performing path planning, the system can use an efficient algorithm (such as an A* algorithm) to calculate the cost of multiple potential paths. The A* algorithm can generate multiple feasible parking paths by considering factors such as the current position, target position, obstacle distribution, and physical limitations of the vehicle (such as turning radius). Then, the system will calculate the cost of these paths, which may include the weighted sum of factors such as path length, number of turns, and estimated time. After comprehensive evaluation, the system will select the path with the lowest cost as the optimal solution to ensure that the parking process is both efficient and safe. In one embodiment, based on the control algorithm, control instructions (such as acceleration and deceleration, steering angle, and exterior lighting control) can be output according to the planned path to complete parking.

[0068] Figure 3 A schematic block diagram of a system framework according to an embodiment of the present disclosure is shown, and the system working process is schematically described in conjunction with the schematic block diagram. The process is not intended to limit the implementation of the present disclosure described and / or required in other embodiments, and is only a schematic description of the execution method. In this embodiment, the system working process is exemplarily introduced by taking the example of a vehicle in a dormant state in a parking space and preparing to automatically park out.

[0069] Figure 3 The figure shows the complex connection relationship between the cabin controller (located on the left side of the figure) and the vehicle controller (located on the right side of the figure). Both are electrically coupled to the CAN bus through the CAN Transiver, achieving efficient data transmission and communication.

[0070] Reference Figure 3In the cabin-parking controller, the CAN transiver is closely connected with the SOC (system-on-chip) and MCU (microcontroller) modules. This module is rich in functions, covering multiple key functions such as voice recognition, voiceprint recognition, parking judgment, and parking control. The integration of these functions enables the cabin-parking controller to intelligently identify and execute parking commands, providing a convenient and safe parking experience.

[0071] In addition, SOC and MCU modules can also have sophisticated connections with multiple other components. They can be connected to Serializers, multiple A2B (Automotive Audio Bus) chips, USS (Ultrasonic Sensor) chips, and Deserializers through interfaces such as MIPI (Mobile Industry Processor Interface), TDM (Time Division Multiplexing), and GPIO (General Purpose Input Output). The collaborative work of these components enables the processing and transmission of audio, video, and sensor data.

[0072] Continue to refer to Figure 3 , Serializer, A2B, USS chips and Deserializers are also connected to Screens (display), AMP (amplifier), USS*12 (probably refers to 12 ultrasonic sensors) and surround view cameras respectively. This design not only provides all-round vehicle environment monitoring, but also provides users with intuitive parking assistance information through the display. At the same time, AMP connects the Speakers inside the car and the Speakers outside the car, and these speakers are further connected to the Mic inside the car and the Mic outside the car, forming a complete audio input and output system.

[0073] like Figure 3 As shown in the figure, in the steering vehicle controller part, the CAN Transiver is also connected to the SOC and MCU modules. This module is connected to the steering actuator, brake actuator, power actuator and body electronic actuator through the CAN / LIN Transiver. These actuators are responsible for controlling various dynamic behaviors of the vehicle, such as steering, braking, acceleration, etc., and are the key parts of vehicle motion control. The following exemplary specific embodiments can be used Figure 3 The system shown is implemented.

[0074] In this embodiment, after the vehicle goes into sleep mode, A2B is not powered off, and the external AMP and MIC are not powered off; next, the user uses the MIC outside the vehicle to talk, and the MIC outside the vehicle obtains the user's audio stream. The audio stream can be, for example: XX (usually the name of the vehicle computer, which can be customized by interacting with the vehicle computer), Hello, please help me park out of the parking space; further, after the cabin parking domain control obtains the audio stream, it is copied into 2 audio sources, so that voice recognition and voiceprint recognition can be obtained simultaneously and in a timely manner; the external sound can enter the SOC through the A2B chip, and the audio DSP integrated in the SOC will copy and divert the sound.

[0075] In this embodiment, next, voiceprint recognition verifies the legitimacy of the sound outside the vehicle and identifies the identity of the user; wherein voiceprint recognition can collect the user's voiceprint data, which will be used to train the voiceprint recognition model, and then use the noise elimination algorithm to process the environmental noise to improve the accuracy of voiceprint recognition; further, the voiceprint recognition model is used to learn the user's voiceprint data to accurately identify the user's identity; then, the ID of the identified user's identity is compared with the voiceprint ID pre-stored in the cabin-parking integrated controller. If the comparison is successful, the user is regarded as a legitimate user; if unsuccessful, it is regarded as an illegal user.

[0076] Next, the speech recognition recognizes the intention of the sound outside the car; among them, preprocessing can be performed first, and the collected speech signal can be preprocessed, including noise reduction, gain control, etc., to improve the accuracy of speech recognition; then, useful features such as Mel Frequency Cepstral Coefficients (MFCC) are extracted from the preprocessed speech signal. Next, the extracted features are used to train the acoustic model, which can map the speech features to phonemes or words; then, the decoder uses the output of the acoustic model, combined with the language model and dictionary, to generate a series of possible text sequences; further, the language model is used to evaluate the probability of the text sequence generated by the decoder, usually using an n-gram model or a neural network model; then, based on the evaluation results of the language model, the search strategy selects the most likely text sequence as the recognition result. Finally, the recognition result is post-processed, such as punctuation prediction, semantic understanding, etc., and then the recognized user intent is output.

[0077] In some embodiments, the following preconditions can be used to determine parking: the user outside the vehicle is identified as a legitimate user through voiceprint recognition; the user's intention of remote parking outside the vehicle is identified through voice recognition, where the natural semantics of the user is recognized as "Hello XX, please help me park out of the parking space"; the cabin parking integrated controller has no faults (including SOC chip, MCU chip, peripheral chip) and its counterparts have no faults (external AMP, MIC, parking camera, USS have no faults); the vehicle controller has no faults (including SOC chip, MCU chip, peripheral chip), and its counterparts have no faults (steering actuator, brake actuator, power actuator, body electronic actuator); the posture control function of the vehicle controller is turned on and not activated (such as ESP, ABS, etc.); the vehicle status of the vehicle controller is normal: the four doors and two covers are closed, the vehicle is in a stationary state,

[0078] When all the above preconditions are met, it is determined that the conditions for remote parking by voice control outside the vehicle are met, and then the parking exit function is executed.

[0079] In this embodiment, the parking function may include parking perception (including environmental perception, target detection and tracking, parking space detection), path planning, control execution of the entire process, and output of control instructions to the vehicle controller (acceleration and deceleration, steering angle, and exterior lighting control). For environmental perception, various on-board sensors (such as ultrasonic radar and surround-view cameras) can be used to perceive the surrounding environment and obtain obstacle information and road information around the vehicle.

[0080] For target detection and tracking, the target detection algorithm can be used to identify other vehicles, pedestrians, obstacles and other targets from the perceived environmental information, and the target tracking algorithm can be used to track these targets.

[0081] For parking space detection, the parking space detection algorithm can be used to identify available parking spaces from the perceived environmental information.

[0082] For path planning, a path from the current position to the target parking space can be planned according to the current vehicle status and the position of the target parking space through the path planning algorithm. If there is an obstacle on the planned path (the trajectory point in the next 5 seconds), the car will stop and wait for the obstacle to leave before continuing to park. If the obstacle persists for 3 minutes, the remote control parking will be exited and the user will be requested to take over.

[0083] For path planning, you can use the A* algorithm to calculate the cost of N paths and select the one with the lowest cost. Figure 4Schematic diagram of the three modes in path planning. Path planning has three mode options: collision-free, comfortable, and executable. Specifically for the vehicle's operating scenario, it may be straight-ahead parking, left-turn parking, or right-turn parking (for example, when the driver stands on the left side of the vehicle to park, the path does not meet the executable conditions, so a right-turn parking is required).

[0084] For control execution, the control algorithm can output control instructions (acceleration and deceleration, steering angle, and exterior lighting control) to the vehicle controller according to the planned path to control the vehicle's driving and achieve automatic parking. In this way, remote parking control is completed.

[0085] Figure 5 FIG. 5 shows a schematic block diagram of a parking device 500 according to an embodiment of the present disclosure. Figure 5 As shown, the device 500 includes: a legal user identification module 501, which is configured to determine whether the user is a legal user based on the first type of information in the voice information in response to receiving voice information from the user outside the vehicle; a parking intention identification module 502, which is configured to determine the second type of information in the voice information, and the second type of information is associated with the user's parking intention; and a parking control module 503, which controls the vehicle to park based on the second type of information in response to determining that the user is a legal user; the parking device is used to execute the parking method of any of the aforementioned embodiments.

[0086] In some embodiments, the device 500 is also configured to respond to receiving biometric information from a user outside the vehicle, the biometric information including one or more of the following: face, fingerprint, palm print, and retina; determine whether the user is a legitimate user based on the first type of information and the biometric information; and in response to determining that the recognition degree of the first type of information and the biometric information is greater than a predetermined threshold, determine that the user is a legitimate user.

[0087] In some embodiments, the device 500 is further configured to: in response to receiving a voice message from a user outside the vehicle, copy the voice message into two copies for respectively obtaining the first type of information and the second type of information.

[0088] In some embodiments, the apparatus 500 is further configured to: train a voiceprint recognition model based on the first type of information; and use the voiceprint recognition model to determine whether the user is a legitimate user.

[0089] In some embodiments, the apparatus 500 is further configured to: determine whether the interior of the vehicle includes a person; and in response to determining that the interior of the vehicle includes no person, control the vehicle to park.

[0090] In some embodiments, the apparatus 500 is further configured to: perform voice information preprocessing in response to the voice information, the preprocessing including: noise reduction and gain control.

[0091] In some embodiments, the device 500 is further configured to: extract features to be trained based on the preprocessed speech information; train an acoustic model based on the extracted features to be trained to output target information; generate multiple text sequences based on the target information using a language model and a dictionary; use the probability of the text sequence evaluated by the language model and generated by the dictionary as the evaluation result of the language model; select the text sequence with the highest probability as the result of determining whether the user is a legitimate user; and post-process the result to identify the user's parking intention.

[0092] In some embodiments, the device 500 is also configured to: control the vehicle to park in response to determining that the following items are met: the user outside the vehicle is a legitimate user; the user outside the vehicle intends to park; the cabin-parking integrated controller has no faults and the parking peripheral hardware has no faults; the vehicle controller has no faults; the control actuator has no faults; the posture control function of the vehicle controller is turned on and not activated; the vehicle status of the vehicle controller is normal; and all doors and trunk lids of the vehicle are closed and the vehicle is in a stationary state.

[0093] Figure 6 1 is a schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure. The electronic device 600 can be used to implement Figure 2 The operations in the method 200 shown may be used to at least partially implement Figure 1 103 shown in . Electronic device 600 is intended to represent various forms of digital computers, such as car computers, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0094] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0095] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0096] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the method 200 in any other appropriate manner (e.g., by means of firmware).

[0097] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0098] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0099] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0100] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0101] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0102] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0103] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0104] The technical effects of the present disclosure should not be limited to the description in this article, but should also cover what can be reasonably judged by those skilled in the art based on the scheme of the present disclosure, which is not elaborated in this article.

[0105] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A parking method, characterized in that: include: In response to receiving a voice message from a user outside the vehicle, determining whether the user meets a preset condition based on first type information in the voice message; detecting a second type of information in the voice information, the second type of information being associated with the user's parking intention; as well as In response to determining that the user satisfies the preset condition and detecting the second type of information, the vehicle is controlled to park.

2. The method according to claim 1, characterized in that The method comprises: In response to determining that one or more modules of the vehicle are not powered off, receiving the voice message from the user.

3. The method according to claim 1, characterized in that: In response to receiving a voice message from a user outside the vehicle, determining whether the user meets a preset condition based on first type information in the voice message includes: In response to receiving biometric information from a user outside the vehicle, the biometric information includes one or more of the following: face, fingerprint, palm print, and retina; determining whether the user meets a preset condition based on the first type of information and the biological information; and In response to determining that the recognition degree between the first type of information and the biological information is greater than a predetermined threshold, it is determined that the preset condition is satisfied.

4. The method according to claim 1 or 2, characterized in that: Also includes: Copying the voice information; as well as The first type information and the second type information are acquired based on the voice information and the copied voice information.

5. The method according to claim 1 or 2, characterized in that: In response to receiving a voice message from a user outside the vehicle, determining whether the user meets a preset condition based on first type information in the voice message includes: Training a voiceprint recognition model based on the first type of information; and The voiceprint recognition model is used to determine whether the user meets the preset condition.

6. The method according to claim 1 or 2, characterized in that: Also includes: determining whether the interior of the vehicle includes a person; and In response to determining that no person is included in the vehicle, the vehicle is controlled to park.

7. The method according to claim 1 or 2, characterized in that: Also includes: Performing voice information preprocessing on the voice information, the preprocessing including: noise reduction and gain control; Extract features to be trained based on the preprocessed speech information; Training the acoustic model based on the extracted features to be trained to output target information; Based on the target information, generate multiple text sequences using a language model and a dictionary; Taking the language model evaluation and the probability of the text sequence generated by the dictionary as the evaluation result of the language model; Selecting the text sequence with the highest probability as the result of determining whether the user is a legitimate user; and The results are post-processed to identify the user's parking intention.

8. The method according to claim 1 or 2, characterized in that: In response to determining that the user satisfies the preset condition and detecting the second type of information, controlling the vehicle to park includes: In response to determining that at least one of a control-related condition, a safety-related condition, and a physical state condition for the vehicle is satisfied, the vehicle is controlled to park.

9. A parking system, characterized in that: include: a legitimate user identification module, configured to, in response to receiving a voice message from a user outside the vehicle, determine whether the user meets a preset condition based on first type information in the voice message; a parking intention recognition module configured to detect a second type of information in the voice information, the second type of information being associated with the user's parking intention; as well as The parking control module is configured to control the vehicle to park in response to determining that the user meets the preset condition and detecting the second type of information.

10. An electronic device, comprising: one or more processors; as well as A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method according to any one of claims 1 to 8.

Citation Information

Cited By

  • Vehicle parking-out control method and device, vehicle and computer readable medium

    CN122474054A