Voice control method for deflection screen in vehicle, vehicle and storage medium

Abstract

The embodiment of the invention provides a voice control method for an in-vehicle deflection screen, a vehicle and a storage medium, and the method comprises the steps: generating a voice control signal based on a user voice instruction which is used for carrying out the voice control of the posture adjustment of the in-vehicle deflection screen; performing voice analysis processing on the voice control signal to obtain a voice analysis result; performing refined parameter analysis processing on the voice analysis result to obtain a screen posture adjustment instruction; and adjusting the posture of the in-vehicle deflection screen according to the screen posture adjusting instruction. According to the invention, the technical problems of low control precision and poor voice recognition effect during the control of the in-vehicle deflection screen in the prior art are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more specifically, to a voice control method for an in-vehicle deflection screen, a vehicle, and a storage medium. Background Technology

[0002] With the development of intelligent vehicle technology, in-vehicle entertainment and information display systems are increasingly becoming key components for enhancing the driving experience. As one such component, tilting screen technology aims to dynamically adjust the screen angle according to the personalized needs of drivers and passengers to optimize the viewing experience. In recent years, the rise of voice interaction has further driven the upgrade of in-vehicle intelligent control systems, aiming to reduce manual operation and improve driving safety and convenience. However, related technologies face many challenges in implementing voice-controlled tilting screens, especially in terms of recognition accuracy and control precision in complex noisy environments.

[0003] There is currently no good solution to the above problems. Summary of the Invention

[0004] This application provides a voice control method for an in-vehicle deflection screen, a vehicle, and a storage medium, to at least solve the technical problems of low control accuracy and poor voice recognition effect in the related art when controlling an in-vehicle deflection screen.

[0005] According to one aspect of the embodiments of this application, a voice control method for an in-vehicle tilting screen is provided, comprising: generating a voice control signal based on a user voice command, wherein the user voice command is used to control the posture adjustment of the in-vehicle tilting screen; performing voice parsing processing on the voice control signal to obtain a voice parsing result; performing fine parameter parsing processing on the voice parsing result to obtain a screen posture adjustment command; and adjusting the posture of the in-vehicle tilting screen according to the screen posture adjustment command.

[0006] Optionally, the user voice command includes a wake-up word and command content. Generating a voice control signal based on the user voice command includes: detecting the wake-up word of the user voice command and obtaining a detection result; identifying the wake-up word based on the detection result, performing voice localization on the user voice command and obtaining a localization result; and performing noise reduction processing on the command content based on the localization result to generate a voice control signal.

[0007] Optionally, the speech control signal is subjected to speech parsing processing to obtain the speech parsing result, including: performing speech recognition on the speech control signal to obtain the instruction text; and performing semantic understanding on the instruction text to obtain the speech parsing result.

[0008] Optionally, the voice control signal is subjected to voice parsing processing to obtain the voice parsing result, which includes: performing intent recognition on the voice control signal to obtain the recognition result; responding to determine the intention to adjust the posture of the in-vehicle tilting screen based on the recognition result, and extracting adjustment object information, adjustment direction information and adjustment amplitude information from the voice control signal; and performing structured encapsulation of the adjustment object information, adjustment direction information and adjustment amplitude information to obtain the voice parsing result.

[0009] Optionally, the screen posture adjustment command is obtained by performing fine-grained parameter parsing on the speech parsing results: performing fine-grained parameter parsing on the speech parsing results, determining the specified adjustment object corresponding to the adjustment object information, the specified adjustment direction corresponding to the adjustment direction information, and the specified adjustment angle corresponding to the adjustment amplitude information, thereby obtaining the screen posture adjustment command.

[0010] Optionally, the speech parsing results are subjected to refined parameter parsing processing to determine the specified adjustment angle corresponding to the adjustment amplitude information, including: parsing the ambiguous terms corresponding to the adjustment amplitude information from the speech parsing results; querying the specified adjustment angle corresponding to the ambiguous terms from the user history records by calling the user preference service, wherein the user history records are used to count the adjustment angle values ​​for multiple uses of the ambiguous terms.

[0011] Optionally, adjusting the posture of the in-vehicle deflection screen according to the screen posture adjustment command includes: converting the screen posture adjustment command into a motor control command; sending the motor control command to the screen controller so that the screen controller controls the motor to adjust the posture of the in-vehicle deflection screen and obtain the adjustment result, wherein the adjustment result is used to indicate whether the in-vehicle deflection screen has successfully completed the posture adjustment operation.

[0012] Optionally, the voice control method for the in-vehicle deflection screen further includes: performing voice synthesis processing on the adjustment result to obtain a synthesized result; and broadcasting a prompt voice based on the synthesized result, wherein the prompt voice is used to indicate whether the in-vehicle deflection screen has successfully completed the posture adjustment operation.

[0013] According to another aspect of the embodiments of this application, a voice control device for an in-vehicle tilting screen is also provided, comprising: a generation module, configured to generate a voice control signal based on a user voice command, wherein the user voice command is used to control the posture adjustment of the in-vehicle tilting screen; a first parsing module, configured to perform voice parsing processing on the voice control signal to obtain a voice parsing result; a second parsing module, configured to perform fine parameter parsing processing on the voice parsing result to obtain a screen posture adjustment command; and an adjustment module, configured to adjust the posture of the in-vehicle tilting screen according to the screen posture adjustment command.

[0014] Optionally, the generation module is also used to: detect wake words for user voice commands and obtain detection results; respond to identify wake words based on detection results, perform voice localization on user voice commands and obtain localization results; and perform noise reduction processing on command content based on localization results to generate voice control signals.

[0015] Optionally, the first parsing module is further configured to: perform speech recognition on the voice control signal to obtain the instruction text; and perform semantic understanding on the instruction text to obtain the speech parsing result.

[0016] Optionally, the first parsing module is further configured to: perform intent recognition on the voice control signal to obtain a recognition result; respond to the determination of the posture adjustment intent of the in-vehicle tilt screen based on the recognition result, extract adjustment object information, adjustment direction information and adjustment amplitude information from the voice control signal; and perform structured encapsulation of the adjustment object information, adjustment direction information and adjustment amplitude information to obtain the voice parsing result.

[0017] Optionally, the second parsing module is also used to: perform refined parameter parsing processing on the speech parsing results, determine the specified adjustment object corresponding to the adjustment object information, the specified adjustment direction corresponding to the adjustment direction information, and the specified adjustment angle corresponding to the adjustment amplitude information, and obtain the screen posture adjustment command.

[0018] Optionally, the second parsing module is also used to: parse the ambiguous terms corresponding to the adjustment range information from the speech parsing results; and query the specified adjustment angle corresponding to the ambiguous terms from the user history records by calling the user preference service, wherein the user history records are used to count the adjustment angle values ​​for multiple uses of the ambiguous terms.

[0019] Optionally, the determining module is further configured to: convert the screen posture adjustment command into a motor control command; send the motor control command to the screen controller so that the screen controller controls the motor to adjust the posture of the in-vehicle deflection screen and obtain the adjustment result, wherein the adjustment result is used to indicate whether the in-vehicle deflection screen has successfully completed the posture adjustment operation.

[0020] Optionally, the voice control device for the in-vehicle deflection screen further includes: a synthesis module for processing the adjustment result into a synthesized result; and a broadcasting module for broadcasting a prompt voice based on the synthesized result, wherein the prompt voice is used to indicate whether the in-vehicle deflection screen has successfully completed the posture adjustment operation.

[0021] According to another aspect of the embodiments of this application, a vehicle is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0022] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0023] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0024] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods in various embodiments of this application.

[0025] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this application.

[0026] In this embodiment, a voice control signal is generated based on the user's voice command, and then the voice control signal is processed by voice parsing to obtain the voice parsing result. Subsequently, the voice parsing result undergoes refined parameter parsing to obtain the screen posture adjustment command. Finally, the posture of the in-vehicle tilting screen is adjusted according to the screen posture adjustment command. This not only improves the convenience of user interaction with the in-vehicle tilting screen but also allows for rapid adaptation to changes in user needs and the diversity of in-vehicle environments, greatly enhancing the user experience and the applicability of the in-vehicle tilting screen. By capturing and converting user voice commands into clear voice control signals, the accuracy and timeliness of user voice commands are ensured. The subsequent refined processing of the voice parsing result accurately understands subtle differences in user intent, further enhancing the intelligence of controlling the in-vehicle tilting screen. Finally, based on the parsed screen posture adjustment command, the posture of the in-vehicle tilting screen can be precisely adjusted, improving control accuracy and voice recognition performance, and ensuring the smoothness and continuity of operation. This solves the technical problems of low control accuracy and poor voice recognition performance in related technologies when controlling in-vehicle tilting screens. Attached Figure Description

[0027] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0028] Figure 1 This is a flowchart of a voice control method for an in-vehicle tilting screen according to an embodiment of this application;

[0029] Figure 2 This is a schematic diagram of a voice control method for an in-vehicle tilting screen according to an embodiment of this application;

[0030] Figure 3 This is a structural block diagram of a voice control device for an in-vehicle deflection screen according to an embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] According to an embodiment of this application, a method embodiment for voice control of an in-vehicle tilting screen is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] This method embodiment can be executed in an electronic device or similar computing device that includes memory and a processor. Taking operation on a computer terminal as an example, the computer terminal may include one or more processors (processors may include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), digital signal processing (DSP) chips, microcontroller units (MCUs), field-programmable gate arrays (FPGAs), neural network processors (NPUs), tensor processors (TPUs), artificial intelligence (AI) type processors, etc.) and memory for storing data. Optionally, the computer terminal may also include transmission devices, input / output devices, and display devices for communication functions. Those skilled in the art will understand that the above structural description is merely illustrative and does not limit the structure of the computer terminal. For example, the computer terminal may include more or fewer components than described above, or have a different configuration than described above.

[0035] The memory can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the voice control method for the in-vehicle tilting screen in this embodiment. The processor executes various functional applications and data processing by running the computer program stored in the memory, thereby realizing the aforementioned voice control method for the in-vehicle tilting screen. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0036] The transmission device is used to receive or send data via a network. Specific examples of the network mentioned above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0037] Display devices can be, for example, touchscreen liquid crystal displays (LCDs) and touch displays (also referred to as "touchscreens" or "touch displays"). The LCD allows users to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), which allows users to interact with the GUI through finger contact and / or gestures on a touch-sensitive surface. Optional human-computer interaction functions include: creating web pages, drawing, word processing, creating electronic documents, playing games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital video, playing digital music, and / or web browsing, etc. Executable instructions for performing the above human-computer interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0038] This embodiment provides a voice control method for an in-vehicle tilting screen. Figure 1 This is a flowchart of a voice control method for an in-vehicle tilting screen according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps:

[0039] Step S11: Generate a voice control signal based on the user's voice command, wherein the user's voice command is used to control the posture adjustment of the in-vehicle tilting screen.

[0040] Step S12: Perform speech parsing processing on the speech control signal to obtain the speech parsing result;

[0041] Step S13: Perform fine-grained parameter parsing processing on the voice parsing results to obtain screen posture adjustment instructions;

[0042] Step S14: Adjust the posture of the in-vehicle tilting screen according to the screen posture adjustment command.

[0043] The aforementioned user voice commands can be control commands issued by the user in natural language, intended to operate the adjustment of the in-vehicle tilting screen, such as "tilt the screen to the left a little" or "return the screen to its initial position." User voice commands can be collected through a microphone array installed in the vehicle.

[0044] The aforementioned voice control signal can be generated by the voice recognition module, which converts the user's voice commands into a format or encoding that the system can understand. The voice control signal contains the semantic information of the voice command and is the basis for subsequent voice parsing and processing.

[0045] In-vehicle screen tilt adjustment refers to the process of changing the orientation or tilt angle of the screen by controlling its mechanical structure to meet the viewing needs of passengers in different scenarios, such as adjusting the screen to face the driver more during driving.

[0046] After obtaining the voice control signal, the voice control signal is processed by voice parsing to obtain the voice parsing result. Voice parsing is the process of converting the semantic information in the voice control signal into specific operation instructions. It involves Natural Language Understanding (NLU) technology, which is used to identify user intent and extract key parameters, such as the direction and magnitude of screen adjustment.

[0047] The aforementioned speech parsing results are the output of structured data or commands after the voice control signals have been analyzed using natural language processing and natural language understanding technologies. Speech parsing results include a semantic interpretation of the user's voice commands, transforming ambiguous, free-form natural language expressions into explicit instructions or parameters that the system can understand and execute. For example, if a user says, "Turn the screen slightly towards me," the speech parsing result can be a data structure containing the recognition of keywords such as "screen," "slightly," and "turn," along with the actions and parameters they indicate in the context.

[0048] Building upon speech parsing and processing, the abstract user intent is further transformed into precise screen posture adjustment commands. The Jiangxi dialect parameter parsing process typically includes parameter quantization, user preference matching, and environmental context understanding, aiming to improve the accuracy and personalization of control. After refined parameter parsing, the generated commands, directly controlling the screen's mechanical structure for posture adjustment, include details such as the specific angle and speed of screen adjustment.

[0049] The screen orientation adjustment command described above is a specific operational guide that includes all the necessary parameters for the adjustment action the screen should perform, typically including but not limited to: target angle, adjustment direction, adjustment magnitude, and control speed. Specifically, the target angle is the desired tilt angle or rotation position on the screen. The adjustment direction determines which direction the screen should tilt, such as left, right, up, or down. The adjustment magnitude indicates the specific amount of screen tilt, such as 5 degrees or 10 degrees for "slightly." The control speed determines the speed of screen tilt to ensure a smooth and comfortable adjustment process.

[0050] For example, during the fine-grained parameter parsing process, the semantic labels output by the NLU service can be further parsed. For instance, the description "slightly" in natural language can be converted into a predefined angle increment, such as 5 degrees. By querying user preference history, the user's habitual screen posture adjustment range and direction can be determined. For example, if a user frequently uses "slightly" to represent a 10-degree deflection, this user habit will be incorporated into the calculation to ensure that the adjustment command meets the user's expectations. Furthermore, by calling the environmental context service to obtain current vehicle status information, such as vehicle speed and seat occupancy, the safety and suitability of the screen posture adjustment can be determined, thereby generating more reasonable and personalized commands. Based on the above processing, the screen deflection control service can generate screen posture adjustment commands containing specific angle, speed, and direction parameters. These screen posture adjustment commands can be encapsulated into a standardized format for easy understanding and execution by the screen driver service.

[0051] By performing refined parameter parsing on the voice analysis results, this embodiment of the application can convert user commands in natural language into precise screen posture adjustment commands. This process not only enhances the system's intelligence and personalized service capabilities but also significantly improves the accuracy of screen posture adjustment and user experience. By considering user preferences and environmental context, the system can flexibly adapt to different scenarios and individual needs, thus achieving a more user-friendly and responsive voice control experience for the in-vehicle tilt screen.

[0052] After receiving the screen posture adjustment command, the in-vehicle deflection screen is adjusted according to the command. Specifically, after receiving the screen posture adjustment command generated by the screen deflection control service, the screen driver service communicates with the screen controller or directly with the actuator (such as a motor) to achieve precise control of the in-vehicle deflection screen based on the specific parameters in the command, such as the target angle, adjustment direction, and amplitude.

[0053] For example, when the screen driver service receives a screen posture adjustment command, it first parses the parameters in the command, including but not limited to the target angle, adjustment direction, and amplitude. Then, it communicates with the screen's physical controller via the vehicle network. The controller is responsible for converting the software-layer command into drive signals for the actuators. Upon receiving the command, the controller sends drive signals to the actuators, such as controlling the motor's speed and direction, to achieve the physical deflection of the screen. The actuators perform corresponding actions based on the signals, ensuring the screen moves accurately according to the command parameters. After the screen deflection is complete, the controller or actuator feeds back the screen's final state (such as the actual deflection angle) to the screen driver service via the same vehicle network.

[0054] Based on steps S11 to S14 above, a voice control signal is generated based on the user's voice command. This signal is then processed through voice parsing to obtain a voice parsing result. Subsequently, the voice parsing result undergoes refined parameter parsing to obtain a screen posture adjustment command. Finally, the posture of the in-vehicle tilting screen is adjusted according to this command. This not only improves the convenience of user interaction with the in-vehicle tilting screen but also allows for rapid adaptation to changing user needs and diverse in-vehicle environments, greatly enhancing the user experience and the applicability of the in-vehicle tilting screen. By capturing and converting user voice commands into clear voice control signals, the accuracy and timeliness of user voice commands are ensured. The subsequent refined processing of the voice parsing result accurately understands subtle differences in user intent, further enhancing the intelligence of controlling the in-vehicle tilting screen. Finally, based on the parsed screen posture adjustment command, the posture of the in-vehicle tilting screen can be precisely adjusted, improving control accuracy and voice recognition performance while ensuring smooth and continuous operation. This solves the technical problems of low control accuracy and poor voice recognition performance in related technologies when controlling in-vehicle tilting screens.

[0055] The voice control method for the in-vehicle deflection screen in this embodiment will be further described below.

[0056] In one optional embodiment, the user voice command includes a wake-up word and command content. Generating a voice control signal based on the user voice command includes: detecting the wake-up word of the user voice command and obtaining a detection result; identifying the wake-up word based on the detection result and performing voice localization on the user voice command to obtain a localization result; and performing noise reduction processing on the command content based on the localization result to generate a voice control signal.

[0057] Wake word detection for user voice commands is a crucial step in a speech recognition system. It's used to quickly detect and confirm specific wake words, such as "Hello, Xiao X," within a continuous speech stream. In this embodiment, the wake word detection module runs under a speech preprocessing service. It continuously monitors the audio captured by the microphone and, through a combination of acoustic and language models, identifies specific wake phrases to determine whether the user is attempting to interact with the in-vehicle system. This detection process filters out non-wake word speech data, reducing unnecessary computational resource waste and improving the efficiency and accuracy of subsequent speech recognition.

[0058] Once the wake-up word is identified based on the detection results, the user's voice command is localized to obtain the localization result. In this embodiment, voice localization can utilize the phase difference of the sound source signals captured by a multi-microphone array to determine the direction in which the user's voice command is issued. Through high-precision voice localization, sound source separation can be achieved, focusing on the voice of the main speaker, thereby improving the clarity and recognition rate of voice commands in noisy in-vehicle environments.

[0059] After identifying the wake word and determining the direction of the voice command's origin, noise reduction processing can be performed on the command content to eliminate background noise, echoes, and interference signals. Noise reduction typically involves using noise suppression algorithms and echo cancellation techniques to ensure that the audio signal transmitted to the Automatic Speech Recognition (ASR) module is clear and pure, thereby improving the accuracy of user voice command transcription and the efficiency of natural language understanding.

[0060] In the in-vehicle environment, when a user utters a wake-up word, the multi-channel microphone array first captures the audio signal containing the wake-up word. Subsequently, the wake-up word detection module quickly identifies the wake-up word, triggering the system's response mechanism and causing this embodiment to switch from passive listening to active command reception. Next, the source of the user's voice command is located to ensure that subsequent processing focuses on valid voice signals. Finally, based on the location results, the voice preprocessing service precisely suppresses noise in the user's voice commands, generating a clean voice control signal to provide high-quality input to the ASR module, thereby improving the recognition accuracy and execution efficiency of the entire voice control system.

[0061] Based on the above optional embodiments, wake-up word detection is performed on user voice commands to obtain detection results. Then, the wake-up word is identified based on the detection results, and the user's voice command is located using voice localization to obtain localization results. Finally, noise reduction processing is applied to the command content based on the localization results to generate a voice control signal. This not only improves the clarity and recognition rate of voice commands but also optimizes the system's response time, ensuring that even in high-noise environments, users can interact smoothly and efficiently with the system using natural language. The application of noise reduction and voice localization technologies significantly enhances the robustness and user-friendliness of the voice control system, laying a solid foundation for the subsequent generation and execution of screen posture adjustment commands.

[0062] In one optional embodiment, the speech parsing processing of the speech control signal to obtain the speech parsing result includes: performing speech recognition on the speech control signal to obtain the instruction text; and performing semantic understanding on the instruction text to obtain the speech parsing result.

[0063] Speech recognition of voice control signals converts preprocessed voice control signals into text format. The speech recognition process involves complex signal analysis and pattern matching to identify and transcribe words and phrases in human speech, providing clear and unambiguous input for subsequent natural language understanding.

[0064] Semantic understanding of command text allows for in-depth analysis, identifying intent and key information to obtain semantic parsing results. By applying syntactic analysis, semantic parsing, and machine learning techniques, the true meaning of user commands can be understood, accurately grasping user needs even when commands are not precisely worded or dialectal differences exist.

[0065] In the in-car environment, upon receiving a voice control signal, the system first performs voice recognition. For example, the voice control signal "turn the screen slightly toward the driver's seat" is converted into a corresponding text command, resulting in the command text. This command text is then submitted to a Natural Language Understanding (NLU) service for analysis. The NLU service not only recognizes keywords such as "screen," "slightly," "turn," and "driver's seat," but also understands the meaning of these words in context. For instance, "slightly" implies a minor adjustment rather than a large movement, while "driver's seat" specifies the direction of screen rotation. Through deep learning and contextual reasoning, the NLU service parses the text command "turn the screen slightly toward the driver's seat" into specific operational parameters, such as a 10-degree screen rotation angle and the direction towards the driver's seat. This yields the voice parsing result, which contains the precise information required for the screen rotation control service to execute.

[0066] Based on the above optional embodiments, by performing speech recognition on the voice control signal to obtain the command text, and then performing semantic understanding on the command text to obtain the speech parsing result, the accuracy and response speed of voice control are significantly improved. The combination of speech recognition and semantic understanding not only enhances the system's ability to understand user voice commands, but also adapts to multiple languages ​​and dialects, providing a more personalized and intelligent voice control experience, and creating an intuitive and efficient screen posture adjustment control method for users.

[0067] In one optional embodiment, the voice control signal undergoes voice parsing processing to obtain the voice parsing result, including:

[0068] The intention of the voice control signal is recognized to obtain the recognition result;

[0069] The response determines the intention to adjust the posture of the in-vehicle tilt screen based on the recognition results, and extracts information on the object to be adjusted, the direction of adjustment, and the magnitude of adjustment from the voice control signal.

[0070] The information on the object being adjusted, the direction of adjustment, and the magnitude of adjustment are encapsulated in a structured manner to obtain the speech parsing results.

[0071] Intent recognition is a core function of natural language understanding technology, responsible for analyzing user intent in voice control signals and translating it into specific operational requirements. In the embodiments of this application, intent recognition can accurately determine whether the user intends to adjust the posture of the in-vehicle tilt screen, as well as the specific direction and magnitude of the adjustment.

[0072] When the recognition results indicate an intention to adjust the posture of the in-vehicle tilting screen, information about the object to be adjusted, the direction of adjustment, and the magnitude of adjustment can be extracted from the voice control signal. The object to be adjusted information represents the object to be adjusted as parsed from the voice control signal. In the scenario of this application embodiment, the object to be adjusted specifically refers to the "in-vehicle tilting screen," clearly defining the target of the command. The direction of adjustment information represents the direction information extracted from the voice control signal that the user needs to execute, such as "left," "right," "forward," or "backward," providing directional guidance for the precise movement of the tilting screen. The magnitude of adjustment information represents the magnitude or order of the tilting screen movement mentioned by the user in the command, such as "slightly" or "larger." In this application embodiment, the magnitude of adjustment information needs to be quantified so that the system can execute the specific tilting operation.

[0073] Furthermore, the adjustment object information, adjustment direction information, and adjustment amplitude information are structurally encapsulated to generate voice parsing results. First, the adjustment object information, such as "in-car deflection screen," adjustment direction information, such as "towards the driver," and adjustment amplitude information, such as "slightly," are identified and extracted from the text output of the voice control signal. For ambiguous adjustment amplitude information, the user preference service can be invoked to query the specific angle value corresponding to "slightly" in the user's historical records. For example, by querying, it can be found that the average angle corresponding to "slightly" in multiple operations by this user is 10 degrees, thus quantifying the ambiguous amplitude information into a specific numerical value.

[0074] Next, the extracted information is organized into a data structure, such as a JSON object or an Extensible Markup Language (JavaScript Object Notation, XML) document, ensuring the integrity and formatting of the information. The data structure may include, but is not limited to, the following fields: "object": adjustment object information, such as "in-vehicle deflection screen"; "direction": adjustment direction information, such as "towards the driver's side"; "magnitude": adjustment magnitude information, such as a quantized angle value of 10 degrees. After creating the data structure, the above parameters can be mapped to meet the interface requirements of the screen deflection control service. Simultaneously, parameter validation is performed to ensure that the numerical parameters are within a reasonable range; for example, the angle value should be between 0 and the maximum deflectable angle. If any parameters are outside this range, adjustments will be made or an error message will be displayed. Finally, the complete data structure containing the adjustment object information, direction information, and magnitude information is encapsulated into a voice parsing result. This voice parsing result will be transmitted to the service scheduling manager or directly to the screen deflection control service for executing specific screen deflection operations.

[0075] Based on the above optional embodiments, by performing intent recognition on the voice control signal, the recognition result is obtained, and then the intention to adjust the posture of the in-vehicle tilt screen is determined based on the recognition result. The adjustment object information, adjustment direction information, and adjustment amplitude information are extracted from the voice control signal. Finally, the adjustment object information, adjustment direction information, and adjustment amplitude information are structurally encapsulated to obtain the voice parsing result. This ensures that the control commands of the in-vehicle tilt screen can not only be accurately understood, but also precisely executed, thereby greatly improving the accuracy of voice-controlled screen posture adjustment operations and user satisfaction.

[0076] In one optional embodiment, the speech parsing results are subjected to fine-grained parameter parsing processing to obtain screen posture adjustment instructions, including:

[0077] The speech parsing results are processed with fine parameters to determine the specified adjustment object corresponding to the adjustment object information, the specified adjustment direction corresponding to the adjustment direction information, and the specified adjustment angle corresponding to the adjustment amplitude information, so as to obtain the screen posture adjustment command.

[0078] Specifically, determining the designated adjustment object corresponding to the adjustment object information involves recognizing the adjustment object mentioned in the voice parsing results, i.e., the device the user wishes to control. In this embodiment, adjustment object information such as "in-vehicle screen" is explicitly identified as the designated adjustment object. For example, when the user says "Turn the screen towards me," the voice parsing results will include "screen" as adjustment object information. The screen deflection control service recognizes this information as the specific hardware device "in-vehicle screen" and confirms it as the operation target.

[0079] The specified adjustment direction corresponding to the adjustment direction information is determined. The adjustment direction information refers to the explicit or implicit deflection direction in the user command. In this embodiment, specific adjustment direction information, such as "towards me," is extracted from the voice parsing results and converted into a specified adjustment direction that the system can understand, such as "towards the driver's seat." The above conversion process can rely on sound source localization data and preset information of the vehicle's internal structure to ensure that the screen deflection direction meets the user's actual needs.

[0080] The specified adjustment angle corresponding to the adjustment range information is determined. This adjustment range information describes the degree of screen deflection the user desires. Through in-depth analysis of the adjustment range information, it is converted into a specific angle value, i.e., the specified adjustment angle. For example, the vague description "slightly" might correspond to an angle range of 5 to 15 degrees in the user's preference history. The screen deflection control service will call the user's historical preference service to query the user's specific angle preference for "slightly." Assuming that historical data analysis shows the user prefers an angle change of 10 degrees corresponding to "slightly," then "slightly" is quantified as "10 degrees," serving as the specified adjustment angle for screen deflection.

[0081] Based on the above optional embodiments, by performing refined parameter parsing processing on the voice parsing results, the specified adjustment object corresponding to the adjustment object information, the specified adjustment direction corresponding to the adjustment direction information, and the specified adjustment angle corresponding to the adjustment amplitude information are determined, and screen posture adjustment instructions are obtained. This enables the generation of accurate screen posture adjustment instructions according to the user's personalized needs, thereby ensuring that the execution of screen posture adjustment instructions not only conforms to the user's intentions but also has a high degree of intelligence and personalization.

[0082] In one optional embodiment, the process of performing fine-grained parameter parsing on the speech parsing results to determine the specified adjustment angle corresponding to the adjustment amplitude information includes:

[0083] Extract the ambiguous terms corresponding to the adjustment range information from the speech analysis results;

[0084] By calling the user preference service, the system queries the user history to find the specified adjustment angle corresponding to the vague terms. The user history is used to count the adjustment angle values ​​for multiple uses of vague terms.

[0085] The aforementioned adjustment range information refers to descriptions of the degree of operation mentioned in the user's voice control signals, such as vague terms like "slightly" or "significantly," used to indicate the magnitude of screen posture adjustment. Vague terms are descriptive words with relative meanings that frequently appear in user voice commands, such as "slightly" or "a lot." Because vague terms are highly subjective, they are difficult to directly convert into specific numerical values.

[0086] The user preference service can be a service based on user history and preference data, used to store and analyze users' personalized settings, including but not limited to adjustment angle values ​​for repeatedly used vague terms. The user history, maintained by the user preference service, records a detailed dataset of past user actions, helping to understand and predict user behavior, especially when dealing with vague terms, providing concrete numerical references. By analyzing the user history, vague terms are converted into specific angle values ​​to guide the precise execution of screen posture adjustment operations.

[0087] Upon receiving the voice parsing results, the analysis of ambiguous terms in the adjustment range information can be initiated immediately. Subsequently, the user preference service is invoked to obtain the specified adjustment angle associated with the ambiguous terms. Specifically, ambiguous terms in the user's voice commands are parsed from the voice parsing results, and the user preference service is invoked to query the actual screen deflection angles corresponding to multiple uses of ambiguous terms in the user's history. Based on the analysis of the user's history, ambiguous users are mapped to specific specified adjustment angles. Finally, the specified adjustment angles are applied to the screen posture adjustment commands to ensure that the screen can accurately deflect according to the user's personalized needs and historical operating habits.

[0088] Based on the above optional embodiments, by parsing the ambiguous terms corresponding to the adjustment range information from the voice analysis results, and then querying the user preference service to find the specified adjustment angle corresponding to the ambiguous terms from the user's history, the accuracy and personalization of screen posture adjustment operations are significantly improved. It can more intelligently understand and respond to user needs, especially when handling subjective voice commands. It can effectively overcome the influence of environmental noise and regional accents, ensuring that the screen deflection service always matches the user's true intentions, optimizing the interactive experience in the cockpit, and enhancing the safety and reliability of operation.

[0089] In one optional embodiment, adjusting the posture of the in-vehicle tilting screen according to the screen posture adjustment command includes:

[0090] Convert screen posture adjustment commands into motor control commands;

[0091] The motor control command is sent to the screen controller, so that the screen controller controls the motor to adjust the attitude of the in-vehicle deflection screen and obtains the adjustment result. The adjustment result is used to indicate whether the in-vehicle deflection screen has successfully completed the attitude adjustment operation.

[0092] The aforementioned motor control commands are further derived from the screen posture adjustment commands, and are specific operation commands that directly guide the screen motor or actuator to deflect.

[0093] The aforementioned screen controller is a hardware unit responsible for receiving motor control commands and executing screen deflection actions. It can understand the commands and drive the corresponding motor. For example, the screen controller receives motor control commands through the vehicle's standard communication protocol bus and controls the motor to deflect the screen to the target angle according to the command information.

[0094] The above adjustment result is the status feedback after the screen controller completes the screen deflection operation, used to confirm whether the screen has successfully reached the specified posture as instructed. For example, the adjustment result can be {Status: Adjustment successful, Final position: 10-degree deflection on the passenger side}, or it can return {Status: Adjustment failed, Reason: Motor overload} if the operation fails.

[0095] Based on the above optional embodiments, by converting the screen posture adjustment command into a motor control command, and then sending the motor control command to the screen controller, the screen controller controls the motor to adjust the posture of the in-vehicle deflection screen and obtain the adjustment result. This ensures the high precision and high efficiency of the screen deflection operation, while enhancing the stability and safety of the system, enabling users to control the in-vehicle screen posture in a natural and intuitive way.

[0096] In one optional embodiment, the voice control method for the in-vehicle tilting screen further includes:

[0097] The adjusted results are processed by speech synthesis to obtain the synthesized result.

[0098] The synthesized result is used to broadcast a prompt voice, which is used to indicate whether the in-vehicle tilt screen has successfully completed the attitude adjustment operation.

[0099] Text-to-Speech (TTS) technology converts text information into speech. During the synthesis process, the text information can be the content of the adjustment result, such as "The screen has been successfully adjusted to 10 degrees towards the passenger side." The synthesized result is an audio file obtained after speech synthesis processing, which retains the information of the adjustment result but is presented in a speech form that humans can understand.

[0100] The synthesized result is played back through audio components such as speakers, informing the user of the screen tilting operation status in voice form. The generation and playback of the prompt voice ensures that the user can understand the screen tilting adjustment status in a timely manner.

[0101] For example, a user might say via voice command, "Turn the screen slightly toward the passenger side." After the screen tilt control service parses the specified adjustment direction and angle, the screen controller performs the screen posture adjustment and feeds the result back to the screen tilt control service. The control service then invokes the TTS service to process the adjustment result, "The screen has been successfully adjusted to 10 degrees toward the passenger side," into speech, generating a synthesized result which is then played through the vehicle's speakers.

[0102] Based on the above optional embodiments, the adjustment results are processed by speech synthesis to obtain a synthesized result, and then a prompt voice is broadcast based on the synthesized result, ensuring that the user can understand the final status of the screen deflection operation in a timely and clear manner. Especially in driving scenarios, this avoids the situation where the user needs to be distracted to look at the screen or dashboard, significantly improving driving safety. At the same time, it also increases the humanized interaction of the system and improves the user experience.

[0103] Figure 2 This is a schematic diagram of a voice control method for an in-vehicle tilting screen according to an embodiment of this application, as shown below. Figure 2As shown, a voice control signal is generated based on user voice commands. These commands are used to control the posture adjustment of the in-vehicle tilting screen. The user voice commands undergo wake-up word detection, and the response identifies the wake-up word based on the detection results. Voice localization is then performed on the user voice commands, and the command content is denoised based on the localization results to generate a voice control signal. The voice control signal undergoes speech recognition to obtain the command text, which is then semantically understood to obtain the speech parsing result. The speech parsing result undergoes refined parameter parsing to obtain the screen posture adjustment command. This command is converted into a motor control command and sent to the screen controller, which then controls the motor to adjust the posture of the in-vehicle tilting screen. The adjustment result indicates whether the in-vehicle tilting screen has successfully completed the posture adjustment operation. The adjustment result undergoes speech synthesis to obtain the synthesized result, and a prompt voice is played based on this result to indicate whether the in-vehicle tilting screen has successfully completed the posture adjustment operation.

[0104] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0105] According to an embodiment of this application, a device embodiment for a voice control method of an in-vehicle tilting screen is provided. It should be noted that the device can be used to execute the above-mentioned voice control method of the in-vehicle tilting screen.

[0106] This application embodiment can also provide a voice control device for an in-vehicle deflection screen that executes the above-described voice control method for an in-vehicle deflection screen. Figure 3 This is a structural block diagram of a voice control device for an in-vehicle tilting screen according to an embodiment of this application, such as... Figure 3 As shown, the device also includes:

[0107] The generation module 301 is used to generate voice control signals based on user voice commands, wherein the user voice commands are used to control the attitude adjustment of the in-vehicle tilting screen.

[0108] The first parsing module 302 is used to perform voice parsing processing on the voice control signal to obtain the voice parsing result;

[0109] The second parsing module 303 is used to perform fine parameter parsing processing on the voice parsing results to obtain screen posture adjustment instructions;

[0110] The adjustment module 304 is used to adjust the posture of the in-vehicle tilting screen according to the screen posture adjustment command.

[0111] Optionally, the generation module 301 is further configured to: detect the wake word of the user's voice command and obtain the detection result; identify the wake word based on the detection result, perform voice localization on the user's voice command and obtain the localization result; and perform noise reduction processing on the command content based on the localization result to generate a voice control signal.

[0112] Optionally, the first parsing module 302 is further configured to: perform speech recognition on the voice control signal to obtain the instruction text; and perform semantic understanding on the instruction text to obtain the speech parsing result.

[0113] Optionally, the first parsing module 302 is further configured to: perform intent recognition on the voice control signal to obtain a recognition result; respond to the determination of the posture adjustment intent of the in-vehicle tilt screen based on the recognition result, extract adjustment object information, adjustment direction information and adjustment amplitude information from the voice control signal; and perform structured encapsulation of the adjustment object information, adjustment direction information and adjustment amplitude information to obtain the voice parsing result.

[0114] Optionally, the second parsing module 303 is further configured to: perform refined parameter parsing processing on the speech parsing results, determine the specified adjustment object corresponding to the adjustment object information, the specified adjustment direction corresponding to the adjustment direction information, and the specified adjustment angle corresponding to the adjustment amplitude information, and obtain the screen posture adjustment command.

[0115] Optionally, the second parsing module 303 is further configured to: parse the ambiguous terms corresponding to the adjustment range information from the speech parsing results; and query the specified adjustment angle corresponding to the ambiguous terms from the user history records by calling the user preference service, wherein the user history records are used to count the adjustment angle values ​​for multiple uses of the ambiguous terms.

[0116] Optionally, the determining module 304 is further configured to: convert the screen posture adjustment command into a motor control command; send the motor control command to the screen controller so that the screen controller controls the motor to adjust the posture of the in-vehicle deflection screen and obtain the adjustment result, wherein the adjustment result is used to indicate whether the in-vehicle deflection screen has successfully completed the posture adjustment operation.

[0117] Optionally, the voice control device for the in-vehicle deflection screen further includes: a synthesis module 305, used to perform voice synthesis processing on the adjustment result to obtain the synthesis result; and a broadcast module 306, used to broadcast a prompt voice based on the synthesis result, wherein the prompt voice is used to indicate whether the in-vehicle deflection screen has successfully completed the posture adjustment operation.

[0118] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0119] Embodiments of this application also provide a vehicle, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods described in various embodiments of this application when it runs.

[0120] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0121] S1, Generate voice control signals based on user voice commands, wherein the user voice commands are used to control the posture adjustment of the in-vehicle tilting screen.

[0122] S2, performs speech parsing processing on the speech control signal to obtain the speech parsing result;

[0123] S3 performs fine-grained parameter parsing on the speech parsing results to obtain screen posture adjustment instructions;

[0124] S4 adjusts the posture of the in-vehicle tilting screen according to the screen posture adjustment command.

[0125] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0126] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0127] S1, Generate voice control signals based on user voice commands, wherein the user voice commands are used to control the posture adjustment of the in-vehicle tilting screen.

[0128] S2, performs speech parsing processing on the speech control signal to obtain the speech parsing result;

[0129] S3 performs fine-grained parameter parsing on the speech parsing results to obtain screen posture adjustment instructions;

[0130] S4 adjusts the posture of the in-vehicle tilting screen according to the screen posture adjustment command.

[0131] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0132] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of this application.

[0133] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of this application.

[0134] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0135] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0136] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0137] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0138] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0139] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A voice control method for an in-vehicle tilting screen, characterized in that, include: Voice control signals are generated based on user voice commands, wherein the user voice commands are used to control the posture adjustment of the in-vehicle tilting screen. The voice control signal is subjected to voice parsing processing to obtain the voice parsing result; The speech parsing results are processed with fine-grained parameter parsing to obtain screen posture adjustment instructions; The in-vehicle tilting screen is adjusted according to the screen posture adjustment command.

2. The voice control method for the in-vehicle deflection screen according to claim 1, characterized in that, The user voice command includes: a wake-up word and command content; generating the voice control signal based on the user voice command includes: The user's voice command is subjected to wake word detection to obtain the detection result; The response identifies the wake word based on the detection result, performs voice localization on the user's voice command, and obtains the localization result; The command content is denoised based on the positioning result to generate the voice control signal.

3. The voice control method for the in-vehicle deflection screen according to claim 1, characterized in that, The speech control signal is subjected to speech parsing processing to obtain the speech parsing result, which includes: The voice control signal is subjected to voice recognition to obtain the instruction text; The instruction text is semantically understood to obtain the speech parsing result.

4. The voice control method for the in-vehicle deflection screen according to claim 1, characterized in that, The speech control signal is subjected to speech parsing processing to obtain the speech parsing result, which includes: The voice control signal is subjected to intent recognition to obtain the recognition result; Based on the recognition result, the system determines that there is an intention to adjust the posture of the in-vehicle tilt screen, and extracts information about the adjustment object, adjustment direction, and adjustment magnitude from the voice control signal. The adjustment object information, adjustment direction information, and adjustment amplitude information are structured and encapsulated to obtain the speech parsing result.

5. The voice control method for the in-vehicle deflection screen according to claim 4, characterized in that, The speech parsing results are processed with fine-grained parameters to obtain the screen posture adjustment instructions, including: The speech parsing results are processed with fine-grained parameter parsing to determine the specified adjustment object corresponding to the adjustment object information, the specified adjustment direction corresponding to the adjustment direction information, and the specified adjustment angle corresponding to the adjustment amplitude information, thereby obtaining the screen posture adjustment command.

6. The voice control method for the in-vehicle deflection screen according to claim 5, characterized in that, The speech parsing results are subjected to refined parameter parsing processing to determine the specified adjustment angle corresponding to the adjustment amplitude information, including: The ambiguous terms corresponding to the adjustment range information are parsed from the speech analysis results; By calling the user preference service, the specified adjustment angle corresponding to the vague term is queried from the user history record, wherein the user history record is used to count the adjustment angle values ​​of multiple uses of the vague term.

7. The voice control method for the in-vehicle deflection screen according to claim 1, characterized in that, Adjusting the posture of the in-vehicle tilting screen according to the screen posture adjustment command includes: Convert the screen posture adjustment command into a motor control command; The motor control command is sent to the screen controller, so that the screen controller controls the motor to adjust the attitude of the in-vehicle deflection screen and obtains the adjustment result. The adjustment result is used to indicate whether the in-vehicle deflection screen has successfully completed the attitude adjustment operation.

8. The voice control method for the in-vehicle deflection screen according to claim 7, characterized in that, The voice control method for the in-vehicle deflection screen also includes: The adjustment result is processed by speech synthesis to obtain the synthesized result; Based on the synthesized result, a prompt voice is played, wherein the prompt voice is used to indicate whether the in-vehicle deflection screen has successfully completed the attitude adjustment operation.

9. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program executes the voice control method for the in-vehicle tilting screen according to any one of claims 1 to 8 when it runs.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the voice control method for the in-vehicle tilting screen as described in any one of claims 1 to 8.

Images