Vehicle sound control method and device, vehicle and computer storage medium

Abstract

This invention relates to a vehicle voice control method, device, vehicle, and computer storage medium, belonging to the field of vehicle intelligent control technology. The vehicle voice control method includes: upon receiving a vehicle control command, collecting the voiceprint features, sound field features, and dynamic environmental features of the vehicle's environment from the voiceprint feature; calculating the voiceprint similarity between the voiceprint features and the user's voiceprint features, and calculating the sound field similarity between the sound field features and the vehicle's sound field features; determining the relative position of the user and the vehicle, and the relative movement intention of the vehicle control command, based on the dynamic environmental features; determining the matching degree between the vehicle control command and the vehicle based on the voiceprint similarity, sound field similarity, relative position, and relative movement intention; and controlling the vehicle in response to the vehicle control command when the matching degree is greater than or equal to a preset matching degree threshold. This invention enables precise vehicle voice control in multi-vehicle scenarios.

Description

Technical Field

[0001] This invention relates to the field of vehicle intelligent control technology, and in particular to a vehicle voice control method, device, vehicle, and computer storage medium. Background Technology

[0002] With the widespread adoption of voice interaction technology in vehicles, many vehicles are able to perform related operations through user commands.

[0003] In existing technologies, voice control of vehicles is usually achieved through single features such as voiceprint recognition, voice command recognition, and distance perception. However, when multiple vehicles of the same model are in an area where the acoustic perception range overlaps, the voice control command issued by the user may be received by all vehicles, leading to serious problems such as multiple vehicles responding or executing incorrectly. This not only affects the user experience but may also cause safety hazards.

[0004] This demonstrates that existing technologies cannot provide precise voice control for target vehicles in multi-vehicle application scenarios. Summary of the Invention

[0005] In view of this, it is necessary to provide a vehicle voice control method, device, vehicle, and computer storage medium to solve the problem that existing technologies cannot accurately control the target vehicle with voice in multi-vehicle application scenarios.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides a vehicle voice control method, comprising: When a vehicle control command is received, the voiceprint characteristics, sound field characteristics, and dynamic environmental characteristics of the vehicle's environment are collected. Calculate the voiceprint similarity between voiceprint features and vehicle user voiceprint features, calculate the sound field similarity between sound field features and vehicle sound field features, and determine the relative position of vehicle user and vehicle, as well as the relative movement intention of vehicle control commands and vehicle based on dynamic environmental features. The matching degree between the vehicle control command and the vehicle is determined based on voiceprint similarity, sound field similarity, relative position, and relative motion intention. When the matching degree is greater than or equal to the preset matching degree threshold, the vehicle is controlled in response to the vehicle control command.

[0007] In one possible implementation, dynamic environmental characteristics of the vehicle's environment are collected, including: Determine the relative position of the user terminal pre-bound to the vehicle and the vehicle; Analyze the frequency shift characteristics of vehicle control commands, and determine the relative motion intention of the vehicle control commands and the vehicle based on the frequency shift characteristics.

[0008] In one possible implementation, the matching degree between vehicle control commands and vehicles is determined based on voiceprint similarity, sound field similarity, relative position, and relative motion intention, including: Based on preset weights, the similarity of voiceprint, similarity of sound field, relative position, and relative motion intention are weighted and calculated to obtain the matching degree between the vehicle control command and the vehicle. Among them, the weights of sound field similarity and relative position are greater than the weights of voiceprint similarity and relative motion intention.

[0009] In one possible implementation, when the matching degree is greater than or equal to a preset matching degree threshold, the vehicle voice control method includes: Control the vehicle to emit sound and / or light alerts.

[0010] In one possible implementation, controlling the vehicle in response to a vehicle control command includes: After the vehicle issues an audible and / or visual alert, if a preset user action command is collected by the vehicle-mounted image acquisition device within a preset time period, the vehicle will be controlled in response to the vehicle control command.

[0011] In one possible implementation, the vehicle voice control method also includes: The preset matching threshold is adjusted based on the risk level of the vehicle control password. The higher the risk level of the vehicle control password, the larger the preset matching threshold.

[0012] In one possible implementation, upon receiving a vehicle control command, the voiceprint characteristics, sound field characteristics, and dynamic environmental characteristics of the vehicle's surroundings are collected, including: Parse vehicle control passwords. When the vehicle control password contains the vehicle's dynamic password, collect the voiceprint features, sound field features, and dynamic environmental features of the vehicle's environment. If the vehicle control password does not contain the vehicle's dynamic password, ignore the vehicle control password.

[0013] In a second aspect, the present invention also provides a vehicle voice control device, comprising: The feature acquisition module is used to acquire the voiceprint features, sound field features, and dynamic environmental features of the vehicle's environment when a vehicle control command is received. The feature calculation module is used to calculate the voiceprint similarity between the voiceprint feature and the vehicle user's voiceprint feature, calculate the sound field similarity between the sound field feature and the vehicle's sound field feature, and determine the relative position of the vehicle user and the vehicle, as well as the relative movement intention of the vehicle control command and the vehicle based on the dynamic environment features. The command execution module is used to determine the matching degree between the vehicle control command and the vehicle based on voiceprint similarity, sound field similarity, relative position, and relative motion intention. When the matching degree is greater than or equal to the preset matching degree threshold, the vehicle is controlled in response to the vehicle control command.

[0014] Thirdly, the present invention also provides a vehicle, including a memory and a processor, wherein, Memory, used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the vehicle voice control method of any of the above implementations.

[0015] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps in the vehicle voice control method of any of the above implementations.

[0016] The beneficial effects of this invention are as follows: The vehicle voice control method provided by this invention, upon receiving a vehicle control command, collects the voiceprint features, sound field features, and dynamic environmental features of the vehicle's environment, calculates the voiceprint similarity between the voiceprint features and the vehicle user's voiceprint features, calculates the sound field similarity between the sound field features and the vehicle's sound field features, and determines the relative position between the vehicle user and the vehicle, as well as the relative movement intention between the vehicle control command and the vehicle, based on the dynamic environmental features. By collecting voiceprint and sound field features of the vehicle control command and combining them with the dynamic environmental features of the vehicle's environment to determine the relative position between the vehicle user and the vehicle, as well as the relative movement intention between the control command and the vehicle, multi-dimensional features are collected simultaneously. This effectively prevents the problem of inaccurate vehicle voice control due to single features, especially when the environmental noise is high, and can more accurately determine the controlled vehicle corresponding to the vehicle control command. Furthermore, based on voiceprint similarity, sound field similarity, relative position, and relative motion intention, the matching degree between vehicle control commands and vehicles is determined. When the matching degree is greater than or equal to a preset matching degree threshold, the vehicle is controlled in response to the vehicle control command. In the case of multi-vehicle scenarios, by calculating the matching degree between vehicle control commands and vehicles, the vehicle to which the vehicle control command is targeted is determined, fundamentally eliminating the problem of multiple vehicles of the same model simultaneously responding incorrectly to voice control commands. This provides a practical solution for reliable voice control interaction in dense scenarios, especially for intelligent connected vehicles, car sharing, and fleet management. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a vehicle voice control method provided in an embodiment of the present invention; Figure 2 A flowchart illustrating a dynamic environment feature extraction method provided in an embodiment of the present invention; Figure 3 A flowchart illustrating a password determination method provided in an embodiment of the present invention; Figure 4 A timing diagram of a vehicle voice control method provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of a vehicle voice control device provided in an embodiment of the present invention; Figure 6 This is a structural schematic diagram of a vehicle provided in an embodiment of the present invention. Detailed Implementation

[0019] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0021] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] A specific embodiment of the present invention, such as Figure 1 As shown, a vehicle voice control method is disclosed, including: S101, when a vehicle control command is received, the voiceprint characteristics, sound field characteristics, and dynamic environmental characteristics of the vehicle's environment are collected.

[0024] In this embodiment of the invention, the provided vehicle voice control method is proposed for vehicles capable of voice command control. The vehicle is equipped with a sound receiving device, such as an array microphone, containing at least four microphones arranged at the front, rear, left, and right of the vehicle (e.g., on exterior door handles, rearview mirrors, and taillights), used to pick up far-field voice commands and support sound source localization and sound field analysis. The vehicle can receive control commands from inside or outside the vehicle through the sound receiving device and then execute corresponding operations. When multiple vehicles of the same model are in adjacent positions, to prevent vehicle control from being effective on multiple vehicles simultaneously, or from being ineffective on the target vehicle, upon receiving a vehicle control command, it is necessary to first collect the voiceprint characteristics of the vehicle control command, the sound field characteristics of the vehicle receiving the control command, and the dynamic environmental characteristics of the vehicle's surroundings. Specifically, voiceprint characteristics refer to the unique and relatively stable acoustic attributes of each person's voice; these characteristics enable voiceprints to be used for personal identification. Based on the four elements of speech (pitch, intensity, duration, and timbre) and their decomposed into more than ninety features, voiceprint mapping can intuitively display these differences. Sound field characteristics refer to the sound field formed by a sound source radiating in a space surrounded by interfaces with different acoustic impedances. Sound waves reflect multiple times at interfaces such as walls, ceilings, and floors, forming direct sound, early reflections, and late reverberation. After the sound source stops emitting sound, the sound gradually decays due to reflection, forming reverberation. Its duration is quantified by reverberation time, which depends on the room volume and sound absorption coefficient. By extracting voiceprint and sound field characteristics, it is possible to preliminarily determine whether the vehicle control command matches the vehicle user. Voiceprint differences only determine whether the control command belongs to the vehicle owner from the speaker's perspective. From the perspective of the control command received by the vehicle, because the internal environment of each vehicle may differ, sound will form different sound fields when propagating inside the vehicle. Therefore, the sound field of the control command received by the vehicle when different users control the vehicle by voice will be different. For users with similar voices, their voiceprint characteristics may be the same or similar, but the sound field of the control command of a user not bound to the vehicle will be different from that of the control command of a user bound to the vehicle, effectively preventing mis-control due to similar voices. The dynamic characteristics of the vehicle's environment are used to represent the distance between the user and the vehicle, the relationship between the vehicle control password and the vehicle, etc. The specific extraction method will be described in detail later in this invention.

[0025] S102, calculate the voiceprint similarity between the voiceprint features and the vehicle user's voiceprint features, calculate the sound field similarity between the sound field features and the vehicle's sound field features, and determine the relative position of the vehicle user and the vehicle, as well as the relative movement intention of the vehicle control command and the vehicle based on the dynamic environment features.

[0026] In this embodiment of the invention, the vehicle has a pre-set user whose voiceprint is used for voice control of the vehicle. The vehicle's sound field characteristics are also extracted in advance for comparison with the sound field characteristics of the vehicle control commands. Specifically, when the user uses the vehicle for the first time, they record voice messages at multiple locations inside and outside the vehicle, and their voiceprint characteristics are extracted. Simultaneously, a microphone array is used to collect the sound field impulse response generated by specific test sounds inside the vehicle, generating unique sound field characteristics for that vehicle. Then, the voiceprint similarity between the voiceprint characteristics and the vehicle user's voiceprint characteristics is calculated, as is the sound field similarity between the sound field characteristics and the vehicle's sound field characteristics. This is used for subsequent calculations of the matching degree between the vehicle control commands and the vehicle. Furthermore, based on dynamic environmental characteristics, the relative position between the vehicle user and the vehicle, as well as the relative movement intention between the vehicle control commands and the vehicle, can be determined, adding a dimension to the judgment of the matching degree between the vehicle control commands and the vehicle, thus improving the accuracy of the vehicle control commands.

[0027] S103 determines the matching degree between the vehicle control command and the vehicle based on voiceprint similarity, sound field similarity, relative position, and relative motion intention. When the matching degree is greater than or equal to the preset matching degree threshold, the vehicle is controlled in response to the vehicle control command.

[0028] In this embodiment of the invention, when determining whether a vehicle control command is for the vehicle, it is necessary to determine the matching degree between the vehicle control command and the vehicle based on voiceprint similarity, sound field similarity, relative position, and relative motion intention, and compare the matching degree with a preset matching degree threshold. When the matching degree is greater than or equal to the preset matching degree threshold, it indicates that the vehicle control command may be for the vehicle, and the vehicle is controlled in response to the vehicle control command.

[0029] The vehicle voice control method provided by this invention, upon receiving a vehicle control command, collects the voiceprint features, sound field features, and dynamic environmental features of the vehicle's environment from the voiceprint features of the vehicle control command. It also calculates the voiceprint similarity between the voiceprint features and the vehicle user's voiceprint features, and the sound field similarity between the sound field features and the vehicle's sound field features. Based on the dynamic environmental features, it determines the relative position between the vehicle user and the vehicle, as well as the relative movement intention between the vehicle control command and the vehicle. By collecting voiceprint and sound field features from the vehicle control command and combining this with the dynamic environmental features of the vehicle's environment to determine the relative position between the vehicle user and the vehicle, as well as the relative movement intention between the control command and the vehicle, multi-dimensional features are collected simultaneously. This effectively prevents inaccurate vehicle voice control due to a single feature, especially when the ambient noise is high, enabling more accurate identification of the controlled vehicle corresponding to the vehicle control command. Furthermore, based on voiceprint similarity, sound field similarity, relative position, and relative motion intention, the matching degree between vehicle control commands and vehicles is determined. When the matching degree is greater than or equal to a preset matching degree threshold, the vehicle is controlled in response to the vehicle control command. In the case of multi-vehicle scenarios, by calculating the matching degree between vehicle control commands and vehicles, the vehicle to which the vehicle control command is targeted is determined, fundamentally eliminating the problem of multiple vehicles of the same model simultaneously responding incorrectly to voice control commands. This provides a practical solution for reliable voice control interaction in dense scenarios, especially for intelligent connected vehicles, car sharing, and fleet management.

[0030] In some possible embodiments of the present invention, such as Figure 2 As shown, the dynamic environmental characteristics of the vehicle's surroundings are collected, including: S201, determine the relative position of the user terminal pre-bound to the vehicle and the vehicle; S202, Analyze the frequency shift characteristics of the vehicle control command, and determine the relative motion intention of the vehicle control command and the vehicle based on the frequency shift characteristics.

[0031] In this embodiment of the invention, when determining the dynamic environmental characteristics of the vehicle's location, if the vehicle control command is specific to the vehicle, the vehicle owner should be nearby. Therefore, the relative position between the user terminal pre-bound to the vehicle and the vehicle, including distance and orientation, can be determined. Specifically, the relative position can be determined by communicating with the vehicle terminal via the user terminal's Bluetooth device or other short-range communication devices. Furthermore, by analyzing the frequency shift of the voice signal in the vehicle control command, it can be determined whether the user is approaching, moving away from, or stationary near the vehicle.

[0032] The embodiments of the present invention extract the dynamic environmental features of the vehicle's environment, improve the dimensionality of vehicle control command matching, and improve the accuracy of vehicle voice control.

[0033] In some possible embodiments of the present invention, the matching degree between vehicle control commands and vehicles is determined based on voiceprint similarity, sound field similarity, relative position, and relative motion intention, including: Based on preset weights, the similarity of voiceprint, similarity of sound field, relative position, and relative motion intention are weighted and calculated to obtain the matching degree between the vehicle control command and the vehicle. Among them, the weights of sound field similarity and relative position are greater than the weights of voiceprint similarity and relative motion intention.

[0034] In this embodiment of the invention, when determining the matching degree between the vehicle control command and the vehicle, the matching degree between the voiceprint similarity, sound field similarity, relative position, and relative motion intention can be calculated based on preset weights. The weights of sound field similarity and relative position are greater than those of voiceprint similarity and relative motion intention. Specifically, the formula for calculating the matching degree between the vehicle control command and the vehicle is as follows: Matching score = W1 × voiceprint similarity + W2 × sound field similarity + W3 × (1 / distance attenuation coefficient) + W4 × relative motion intention.

[0035] W1, W2, W3, and W4 are preset weights, with W2 and W3 having higher weights to emphasize vehicle uniqueness. The distance attenuation system is determined based on the relative distance between the vehicle and the user terminal. Specifically, because sound field similarity combines the user's voice and the characteristics of sound propagation within the vehicle, rather than solely considering sound characteristics, it provides more accurate recognition of control commands associated with the vehicle. Distance reflects the distance between the voice controller and the vehicle; generally, users only use voice control when the distance is close. Therefore, sound field similarity and distance can more accurately determine the vehicle targeted by the control command, hence their higher weights.

[0036] This invention improves the accuracy of vehicle voice control by performing weighted calculations on features from multiple dimensions to determine the matching degree between the vehicle and the vehicle control command.

[0037] In some possible embodiments of the present invention, when the matching degree is greater than or equal to a preset matching degree threshold, the vehicle voice control method includes: Control the vehicle to emit sound and / or light alerts.

[0038] In this embodiment of the invention, in densely parked scenarios, multiple vehicles of the same type may simultaneously calculate a high matching degree. At this time, simply using the matching degree to determine the vehicle to which the vehicle control command is targeted is not accurate enough. Therefore, a secondary active confirmation is added. When the matching degree between the vehicle and the vehicle control command is greater than or equal to a preset matching degree threshold, the vehicle will emit an audible and / or visual alert, such as honking the horn or flashing the lights, to indicate the user's vehicle location.

[0039] Furthermore, controlling the vehicle in response to a vehicle control command includes: After the vehicle issues an audible and / or visual alert, if a preset user action command is collected by the vehicle-mounted image acquisition device within a preset time period, the vehicle will be controlled in response to the vehicle control command.

[0040] In this embodiment of the invention, when the vehicle provides an audio / or visual alert to the user, if the user makes a pre-defined action command within a preset time period, it indicates that the user is near the vehicle and needs to control the vehicle via voice. Therefore, the vehicle can be controlled in response to the vehicle control command. Specifically, this can be achieved by capturing user actions such as waving their hand or waving their foot through an image acquisition device.

[0041] This invention, through a secondary active confirmation mechanism, ensures the accuracy of matching vehicle control commands with vehicles, fundamentally eliminating the problem of multiple vehicles of the same model simultaneously responding incorrectly to voice control commands.

[0042] In some possible embodiments of the present invention, the vehicle voice control method further includes: The preset matching threshold value is adjusted based on the risk level of the vehicle control password. The higher the risk level of the vehicle control password, the larger the preset matching threshold value.

[0043] In this embodiment of the invention, different vehicle control commands may have different risk levels. For example, opening the trunk and opening the door have different risk levels. For security, different matching thresholds can be set for vehicle control commands with different risk levels. For example, the matching threshold for the vehicle control command "open the trunk" is 0.75, the matching threshold for the vehicle control command "open the door" is 0.85, and the matching threshold for the vehicle control command "start the engine" is 0.9, etc.

[0044] This invention improves the security of vehicle voice control by assessing the risk level of vehicle control commands and setting corresponding matching thresholds.

[0045] In some possible embodiments of the present invention, such as Figure 3 As shown, when a vehicle control command is received, the voiceprint characteristics, sound field characteristics, and dynamic environmental characteristics of the vehicle's surroundings are collected, including: S301, Parse vehicle control password. When the vehicle control password contains the vehicle's dynamic password, collect the voiceprint characteristics, sound field characteristics, and dynamic environmental characteristics of the vehicle's environment. S302, when the vehicle control password does not contain the vehicle's dynamic password, ignore the vehicle control password.

[0046] In this embodiment of the invention, in order to further improve the accuracy of vehicle voice control, a dynamic password can be generated daily. The subsequent matching degree judgment is only performed when the vehicle control password contains the daily dynamic password. For example, if the dynamic password for a certain day is "star", then the next feature extraction operation will only be performed if the vehicle control password contains "star". If the vehicle control password does not contain "star", then the vehicle control password will be ignored directly.

[0047] The embodiments of the present invention further improve the accuracy of vehicle control by adding dynamic passwords.

[0048] Furthermore, to better illustrate the vehicle voice control method provided by this invention, in conjunction with... Figure 4 The system provides a timing diagram of the vehicle voice control method. After the user issues a vehicle control command, multiple vehicles will receive the vehicle control command and calculate their matching degree with the command. Vehicles with a matching degree higher than a preset matching degree threshold will be identified as candidate vehicles. The candidate vehicles will then provide an audible / or visual alert and check whether the user's specified action has been collected within a preset time. Upon receiving the user's braking action, the vehicle will execute the relevant actions of the vehicle control command.

[0049] This invention utilizes distributed parallel processing to independently extract composite features and calculate confidence levels for each vehicle, overcoming the bottleneck of centralized processing. It boasts high speed and robustness. Through unique proactive prompts, only the highest-scoring primary candidate vehicle activates personalized audio / visual cues, clearly identifying the target vehicle in physical space and intuitively informing the user of the decision, guiding correct interaction. The user must prompt the vehicle to perform a predefined action, verified by onboard sensors, forming a closed loop of composite biological commands—"voice + action"—fundamentally eliminating erroneous execution and elevating security verification from a purely signal-based layer to a user intent confirmation layer.

[0050] To better implement the vehicle voice control method in this embodiment of the invention, based on the vehicle voice control method, correspondingly, as follows: Figure 5 As shown, this embodiment of the invention also provides a vehicle voice control device, the vehicle voice control device 500 including: The feature acquisition module 501 is used to acquire the voiceprint features, sound field features, and dynamic environmental features of the vehicle control command when a vehicle control command is received. The feature calculation module 502 is used to calculate the voiceprint similarity between the voiceprint feature and the vehicle user's voiceprint feature, calculate the sound field similarity between the sound field feature and the vehicle's sound field feature, and determine the relative position of the vehicle user and the vehicle, as well as the relative motion intention of the vehicle control command and the vehicle based on the dynamic environment features. The command execution module 503 is used to determine the matching degree between the vehicle control command and the vehicle based on voiceprint similarity, sound field similarity, relative position and relative motion intention. When the matching degree is greater than or equal to the preset matching degree threshold, the vehicle is controlled in response to the vehicle control command.

[0051] The vehicle voice control device 500 provided in the above embodiments can realize the technical solutions described in the above vehicle voice control method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above vehicle voice control method embodiments, and will not be repeated here.

[0052] like Figure 6 As shown, the present invention also provides a vehicle 600. The vehicle 600 includes a processor 601, a memory 602, and an actuator 603. Figure 6 Only some components of vehicle 600 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0053] In some embodiments, processor 601 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in memory 602 or process data, such as the vehicle voice control method of the present invention.

[0054] In some embodiments, memory 602 may be an internal storage unit of vehicle 600, such as a hard disk or memory of vehicle 600. In other embodiments, memory 602 may also be an external storage device of vehicle 600, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on vehicle 600.

[0055] Furthermore, the memory 602 may include both internal storage units of the vehicle 600 and external storage devices. The memory 602 is used to store application software and various types of data installed on the vehicle 600.

[0056] In some embodiments, the actuator 603 can be various vehicle actuators, such as doors, trunk, hood, and various voice-controlled switches.

[0057] In some embodiments, when the processor 601 executes the vehicle voice control program in the memory 602, the following steps may be performed: When a vehicle control command is received, the voiceprint characteristics, sound field characteristics, and dynamic environmental characteristics of the vehicle's environment are collected. Calculate the voiceprint similarity between voiceprint features and vehicle user voiceprint features, calculate the sound field similarity between sound field features and vehicle sound field features, and determine the relative position of vehicle user and vehicle, as well as the relative movement intention of vehicle control commands and vehicle based on dynamic environmental features. The matching degree between the vehicle control command and the vehicle is determined based on voiceprint similarity, sound field similarity, relative position, and relative motion intention. When the matching degree is greater than or equal to the preset matching degree threshold, and when the preset action command is collected within the preset time period, the vehicle is controlled in response to the vehicle control command.

[0058] It should be understood that when the processor 601 executes the vehicle voice control program in the memory 602, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0059] Furthermore, the embodiments of the present invention do not specifically limit the type of vehicle 600 mentioned, and vehicle 600 can be a commercial vehicle, passenger vehicle, special vehicle, etc.

[0060] Accordingly, this application also provides a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, it can implement the steps or functions of the vehicle voice control method provided in the above-described method embodiments.

[0061] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0062] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A vehicle voice control method, characterized in that, include: When a vehicle control command is received, the voiceprint characteristics, sound field characteristics, and dynamic environmental characteristics of the vehicle's environment are collected. Calculate the voiceprint similarity between the voiceprint feature and the vehicle user's voiceprint feature, calculate the sound field similarity between the sound field feature and the vehicle's sound field feature, and determine the relative position of the vehicle user and the vehicle, as well as the relative movement intention of the vehicle control command and the vehicle based on the dynamic environment features. The matching degree between the vehicle control command and the vehicle is determined based on the voiceprint similarity, the sound field similarity, the relative position, and the relative motion intention. When the matching degree is greater than or equal to a preset matching degree threshold, the vehicle is controlled in response to the vehicle control command.

2. The vehicle voice control method according to claim 1, characterized in that, The collection of dynamic environmental characteristics of the vehicle's environment includes: Determine the relative position of the user terminal pre-bound to the vehicle and the vehicle; Analyze the frequency shift characteristics of the vehicle control command, and determine the relative motion intention of the vehicle control command and the vehicle based on the frequency shift characteristics.

3. The vehicle voice control method according to claim 2, characterized in that, The step of determining the matching degree between the vehicle control command and the vehicle based on the voiceprint similarity, the sound field similarity, the relative position, and the relative motion intention includes: The similarity of the voiceprint, the similarity of the sound field, the relative position, and the relative motion intention are weighted and calculated based on preset weights to obtain the matching degree between the vehicle control command and the vehicle. The weights of the sound field similarity and the relative position are greater than the weights of the voiceprint similarity and the relative motion intention.

4. The vehicle voice control method according to claim 3, characterized in that, When the matching degree is greater than or equal to a preset matching degree threshold, the vehicle voice control method includes: Control the vehicle to emit sound and / or light alerts.

5. The vehicle voice control method according to claim 4, characterized in that, The control of the vehicle in response to the vehicle control command includes: After the vehicle issues an audible and / or visual alert, if a preset user action command is collected by the vehicle-mounted image acquisition device within a preset time period, the vehicle will be controlled in response to the vehicle control command.

6. The vehicle voice control method according to claim 1, characterized in that, The vehicle voice control method also includes: The preset matching threshold is adjusted based on the risk level of the vehicle control password. The higher the risk level of the vehicle control password, the larger the preset matching threshold.

7. The vehicle voice control method according to claim 1, characterized in that, When a vehicle control command is received, the voiceprint characteristics, sound field characteristics, and dynamic environmental characteristics of the vehicle's environment are collected, including: The vehicle control password is parsed. When the vehicle control password contains the vehicle's dynamic password, the voiceprint features, sound field features, and dynamic environmental features of the vehicle's environment are collected. If the vehicle control password does not contain the vehicle's dynamic password, the vehicle control password is ignored.

8. A vehicle voice control device, characterized in that, include: The feature acquisition module is used to acquire the voiceprint features, sound field features, and dynamic environmental features of the vehicle's environment when a vehicle control command is received. The feature calculation module is used to calculate the voiceprint similarity between the voiceprint feature and the vehicle user's voiceprint feature, calculate the sound field similarity between the sound field feature and the vehicle's sound field feature, and determine the relative position of the vehicle user and the vehicle, as well as the relative movement intention of the vehicle control command and the vehicle based on the dynamic environment features. The command execution module is used to determine the matching degree between the vehicle control command and the vehicle based on the voiceprint similarity, the sound field similarity, the relative position, and the relative motion intention. When the matching degree is greater than or equal to a preset matching degree threshold, the vehicle is controlled in response to the vehicle control command.

9. A vehicle, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the vehicle voice control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the vehicle voice control method according to any one of claims 1 to 7.

Images