Voice interaction control method and system for electric kick scooter

Abstract

The application discloses a voice interaction control method and system for an electric scooter, and relates to the technical field of voice control. The method comprises the following steps: when a preset voice activation instruction is detected, starting a voice recognition channel to collect a current voice signal; performing source positioning according to the collected current voice signal, screening effective voice input information according to the source result and the direction result; obtaining current running state information of the electric scooter; establishing an interactive control relationship between the current running state information and a control intention recognized by the effective voice input information, performing safety determination on the interactive control relationship, converting the interactive control relationship into a control execution instruction based on the safety determination result; and performing control operation on the electric scooter according to the control execution instruction. The technical problem of low voice command recognition accuracy caused by environmental interference in the prior art is solved, and the technical effects of improving voice command recognition accuracy and ensuring the stability of the interaction process are achieved.

Description

Technical Field

[0001] This invention relates to the field of voice control technology, and more specifically to a voice interaction control method and system for electric scooters. Background Technology

[0002] With the increasing popularity of electric scooters in urban transportation and short-distance travel, users have placed higher demands on the convenience and intelligence of their operation. Voice control, as a natural human-computer interaction method, is gradually being applied to the control of intelligent transportation tools. However, existing voice interaction solutions for electric scooters generally suffer from problems such as voice recognition being easily interfered with by environmental noise, low accuracy in recognizing voice input commands, and a lack of operational status awareness. These issues result in insufficient stability and safety for users using voice control during riding, easily leading to operational misjudgments or delays, and affecting the travel experience. Summary of the Invention

[0003] This application provides a voice interaction control method and system for electric scooters, which solves the technical problem in the prior art where voice recognition is affected by environmental interference, resulting in low accuracy of voice command recognition.

[0004] The first aspect of this application provides a voice interaction control method for an electric scooter, the method comprising:

[0005] When a preset voice activation command is detected, the voice recognition channel is activated to collect the current voice signal; the source of the collected voice signal is located, and valid voice input information is filtered based on the source and location results; the current operating status information of the electric scooter is obtained, including speed, operating mode, and battery level; an interactive control relationship is established between the current operating status information and the control intent identified by the valid voice input information; the safety of the interactive control relationship is determined, and the interactive control relationship is converted into a control execution command based on the safety determination result; the electric scooter is controlled according to the control execution command.

[0006] A second aspect of this application provides a voice-interactive control system for an electric scooter, the system comprising:

[0007] Voice signal acquisition module: When a preset voice activation command is detected, the voice recognition channel is activated to acquire the current voice signal; Voice information filtering module: The source of the acquired current voice signal is located, and valid voice input information is filtered based on the source and location results; Operating status acquisition module: The current operating status information of the electric scooter is acquired, including speed, operating mode, and battery level; Control relationship conversion module: An interactive control relationship is established between the current operating status information and the control intent identified by the valid voice input information, the safety of the interactive control relationship is determined, and the interactive control relationship is converted into a control execution command based on the safety determination result; Scooter control module: The electric scooter is controlled according to the control execution command.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] When a preset voice activation command is detected, the voice recognition channel is activated to collect the current voice signal. The source of the collected voice signal is located, and valid voice input information is filtered based on the source and location results. Next, the current operating status information of the electric scooter is acquired, including speed, operating mode, and battery level. Then, an interactive control relationship is established between the current operating status information and the control intent recognized by the valid voice input information. A safety assessment of the interactive control relationship is performed, and based on the safety assessment result, the interactive control relationship is converted into a control execution command. Finally, the electric scooter is controlled according to the control execution command. This solves the technical problem in existing technologies where environmental interference leads to low accuracy in voice command recognition, achieving the technical effect of improving the accuracy of voice command recognition and ensuring the stability of the interaction process. Attached Figure Description

[0010] 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.

[0011] Figure 1 A schematic flowchart of a voice interaction control method for an electric scooter provided in an embodiment of this application;

[0012] Figure 2 This is a schematic diagram of the voice interaction control system for an electric scooter provided in an embodiment of this application.

[0013] Explanation of reference numerals in the attached diagram: 11. Voice signal acquisition module; 12. Voice information filtering module; 13. Operating status acquisition module; 14. Control relationship conversion module; 15. Scooter control module. Detailed Implementation

[0014] This application provides a voice interaction control method and system for electric scooters, which solves the technical problem in the prior art where voice recognition is affected by environmental interference, resulting in low accuracy of voice command recognition.

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0016] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0017] Example 1, as Figure 1 As shown, this application provides a voice interaction control method for an electric scooter, wherein the method includes:

[0018] When a preset voice activation command is detected, the voice recognition channel is activated to collect the current voice signal.

[0019] In this embodiment, when the system detects a preset voice activation command issued by the user (e.g., "Hello scooter" or any wake-up word set by the user), the system enters the voice recognition working mode and automatically starts the voice recognition channel to collect the voice signal issued by the current user. Specifically, the front-end acquisition circuit of the microphone array or headphone microphone is invoked to activate the voice input hardware port, and a real-time voice acquisition path is established according to the preset voice acquisition sensitivity parameters.

[0020] Furthermore, activating the speech recognition channel to collect the current speech signal includes:

[0021] Obtain the spatial position range of the user's mouth and establish a corresponding voice acquisition cone region; based on the voice acquisition cone region, perform voice recognition channel labeling and filtering, and acquire voice signals.

[0022] Preferably, the spatial position range of the user's mouth is obtained by combining the user's pre-activated body posture information with the posture detection results of the vehicle's sensors. Based on this, a voice acquisition cone area is constructed centered on the user's mouth. This voice acquisition cone area covers the main direction of sound wave propagation when the user speaks normally, serving as the effective space for voice acquisition. Subsequently, the input channels of the microphone array are labeled and filtered according to the voice acquisition cone area, allowing only microphone signals located within the voice acquisition cone area to enter the voice recognition channel, while signals from channels outside the area are downweighted or masked, thereby effectively reducing the impact of interference factors such as environmental noise and distant human voices. Finally, under the labeling and filtering effect of the voice acquisition cone area, the system stores the acquired voice signals in real time.

[0023] Furthermore, obtaining the spatial range of the user's mouth includes:

[0024] The system acquires the user's pre-imported height information through a pre-collection module before cycling activation, combines it with the user's posture information detected by the vehicle's sensors, performs user posture analysis, and establishes a user posture model. Based on the user posture model, the system determines the spatial range of the user's mouth position and performs position matching in conjunction with the microphone's set position.

[0025] Before activating the riding mode, the system uses a pre-collection module to access the user's pre-input or stored height information. Combined with vehicle sensors (including accelerometers, gyroscopes, and pressure sensors), it detects the user's posture in real time while standing, acquiring data such as body tilt angle, head height, and neck and shoulder position. Subsequently, based on the height and posture information, the system performs user posture analysis, establishing a user posture model corresponding to the current riding state. This model reflects the approximate spatial distribution of the user's head and mouth in a three-dimensional coordinate system. Next, based on the user posture model, the system further locates the spatial range of the user's mouth and establishes a local spatial envelope region centered on the mouth's position. Finally, this mouth spatial range is spatially matched with the pre-defined microphone positions on the vehicle to obtain the effective spatial position of the mouth relative to the microphone array.

[0026] The source of the collected current speech signal is located, and valid speech input information is filtered based on the source and location results.

[0027] After acquiring the current voice signal, the system performs source localization to determine whether the signal originates from the user's vocal area. Specifically, the system performs source localization processing on the multi-channel voice signals acquired by the microphone array mounted on the electric scooter. By comparing the arrival time difference, energy difference, or phase difference between different microphone signals, the system calculates the spatial coordinates of the sound source to obtain the source result of the voice signal. The system combines the source result with the voice acquisition cone area corresponding to the user's mouth spatial position range to compare whether the propagation direction of the voice signal is consistent with the mouth area, thus obtaining the orientation result of the voice signal. When the voice signal satisfies both the source localization being near the mouth space and the orientation result matching the preset mouth direction, the voice signal is marked as valid voice input information; for voice signals outside the mouth range or with mismatched orientations, they are processed by weight reduction or directly masked to avoid misjudging environmental noise or irrelevant voice as control input.

[0028] Furthermore, the source of the acquired speech signal is located, and based on the source and location results, valid speech input information is filtered, including:

[0029] The microphone position is located based on the speech signal source, and the channel markings corresponding to the speech acquisition cone area are identified. Speech signals falling within the channel marking range are marked as valid inputs, while speech signals outside the range are downweighted or masked. The energy characteristics, spectral characteristics, and zero-crossing rate characteristics of the acquired speech signal are extracted to determine whether the speech signal is near-end speech or far-end speech. When it is determined to be near-end speech, the orientation is determined based on the relative feature comparison of the microphone signal, and the orientation result is matched with a preset mouth spatial position range. Speech signals that simultaneously meet the near-end speech characteristics and orientation matching conditions are taken as the valid speech input information.

[0030] The system determines the location of the microphone based on the location of the voice signal source and identifies whether the microphone is located within the voice acquisition cone area. If the acquisition channel is within the cone area, the voice signal acquired by that channel is marked as valid input. If the acquisition channel is outside the voice acquisition cone area, its signal is downweighted or directly blocked to prevent irrelevant ambient noise from entering subsequent processing stages.

[0031] The system extracts features from the acquired speech signals to obtain multiple acoustic feature parameters, including energy features, spectral features, and zero-crossing rate features. Based on these features, the system determines whether the speech signal is near-end speech or far-end speech, ensuring that subsequent analysis only targets speech signals near the user's mouth. When the determination result is near-end speech, the system calls a relative feature comparison method for microphone signals, such as calculating the time difference of arrival, relative phase difference, or energy difference between signals acquired by different microphones, to deduce the direction of the sound source and generate a directional result. Finally, the directional result is matched with a preset range of mouth spatial positions. Only when the speech signal simultaneously meets the near-end speech feature and mouth directional matching conditions is it recognized as valid speech input information.

[0032] Furthermore, location determination based on relative feature comparison of microphone signals includes:

[0033] The number and installation location of the acquisition microphones are identified, including vehicle-mounted microphones and / or external microphones; when there are two or more acquisition microphones, the arrival time difference, energy difference or phase difference between the signals acquired by different microphones are calculated; based on the difference results, the direction of the sound source is analyzed, and combined with the relative characteristics of the microphone signals, the directional result of the speech signal is determined.

[0034] Specifically, the number of microphones involved in voice acquisition and their installation locations are identified. These microphones can be either onboard microphones mounted on the electric scooter or external microphones connected to the scooter wirelessly or via wired connection.

[0035] When there are two or more microphones, the system preprocesses the signals of the same voice event from different microphones, including bandpass filtering and amplitude normalization, to eliminate environmental noise interference. Next, it calculates the time difference of arrival, energy difference, or phase difference between the different microphones. Specifically, this includes performing cross-correlation on the signals from the two microphones to obtain the delay corresponding to the maximum correlation coefficient, which is taken as the propagation time difference of the voice signal between the two microphones. Simultaneously, it calculates the energy difference and phase difference between the signals from the different microphones. The energy difference is obtained by integrating the short-time energy of each signal, while the phase difference is calculated by extracting the phase of the dominant frequency component using a fast Fourier transform and then calculating the difference.

[0036] The system uses three characteristic parameters—time difference of arrival, energy difference, and phase difference—to call a sound source direction analysis algorithm. When the spatial coordinates of the microphone are known, the system calculates the azimuth of the sound source in the horizontal and vertical planes using trilateration or least squares methods. The obtained azimuth result is then compared with the user's mouth's spatial position range. If the angle between the calculated azimuth and the preset mouth direction is less than a preset threshold, the azimuth result of the speech signal is determined to be a valid source; otherwise, it is marked as an invalid source.

[0037] Furthermore, filtering valid voice input information also includes:

[0038] When the voice recognition channel is an earphone microphone or a headset near-mouth microphone, the microphone voice channel is set to the highest priority, and the voice signal collected by the priority channel is directly used as the valid voice input information.

[0039] When the voice recognition channel is a headset microphone or a near-mouth microphone, the system sets this type of channel as the highest priority channel in the voice channel priority management module. Specifically, headset microphones or near-mouth microphones, because their physical installation position is close to the user's mouth, have a high signal-to-noise ratio and are less affected by environmental noise and interference from distant sound sources. Therefore, when the system detects that the current voice recognition channel belongs to the above type, it directly marks the voice signal collected by this priority channel as valid voice input information, skipping the secondary screening steps based on spatial location range, energy characteristics, and orientation matching, thereby reducing latency and improving interaction response speed.

[0040] Obtain the current operating status information of the electric scooter, including speed, operating mode, and battery level.

[0041] The system collects real-time operating data of the electric scooter through the vehicle controller and built-in sensor modules. The vehicle speed information is calculated by the wheel speed sensor or motor speed detection module and can be converted into the actual driving speed through the wheel radius and speed parameters. The operating mode information is obtained by the mode selection module of the vehicle control unit. This module can recognize different riding modes preset by the user, such as energy-saving mode, standard mode or sport mode. The battery information is detected in real time by the battery management system (BMS). The BMS calculates the remaining battery percentage through battery voltage, current and capacity parameters and generates a battery status report.

[0042] An interactive control relationship is established between the current operating status information and the control intent identified by the valid voice input information. The security of the interactive control relationship is determined, and the interactive control relationship is converted into a control execution command based on the security determination result.

[0043] The system performs semantic parsing on valid voice input information to extract control intentions, such as commands like "accelerate," "decelerate," "switch modes," and "check battery level." It then associates these control intentions with the electric scooter's current operating status. For example, under constraints of current speed, battery level, and operating mode, it retrieves corresponding candidate control actions from a pre-defined strategy library and modifies their parameters and timing to generate an interactive control relationship that matches the current operating status. The system performs a safety assessment on the generated interactive control relationship, including: risk classification of the control intention; scenario threshold judgment based on current speed and operating mode; calculation of a comprehensive judgment score combining voice recognition confidence, user identity matching, and location matching; and comparison with an adaptive threshold to obtain a safety assessment result. Finally, the system converts the interactive control relationship into a control execution command based on the safety assessment result: when execution is allowed, the command is output directly; when execution is delayed, a buffer parameter is set, and the command is issued only after the confirmation condition is met; when execution is refused, an alternative prompt is generated and provided to the user via voice broadcast or interface feedback.

[0044] Furthermore, establishing the interactive control relationship between the current operating status information and the control intent identified by the valid voice input information includes:

[0045] Based on the control intent, the system retrieves the corresponding candidate control actions and their timing templates from the preset strategy library; it then performs constraint parsing on the candidate control actions and their timing templates according to the current running status information, completes feasibility verification, parameter trimming and timing rearrangement, and generates the interactive control relationship.

[0046] The system searches a preset strategy library based on the control intent, calls up candidate control actions that match the intent, and simultaneously retrieves the action sequence template associated with each candidate action. This template describes the execution order and duration of the control action at different time stages. Subsequently, the system performs constraint analysis on the candidate control actions and their sequence templates based on the electric scooter's current operating status. For example, when the speed is above a safety threshold, "acceleration" type candidate control actions are prohibited or have their parameters limited; when the battery level is below a set lower limit, actions such as "switching to sport mode" are constrained. The constraint analysis process includes: verifying the feasibility of candidate control actions to determine if they meet the execution conditions in the current operating state; trimming the control parameters of candidate control actions to ensure that the action amplitude and timing meet safety requirements; and rearranging the action sequence template, adjusting the order and interval of each execution step to ensure that the actions are time-sequentially compatible with the operating state. Finally, after the above analysis and correction, a complete interactive control relationship is generated, serving as the basis for subsequent safety assessment and control execution.

[0047] Furthermore, the security determination of the aforementioned interactive control relationship includes:

[0048] The control intent is risk-classified; based on the current operating status information, a scene threshold judgment is made, and the risk is marked as an interaction control relationship that does not meet the safety conditions; the recognition confidence, speaker identity matching degree, and location matching degree of the effective voice input information are calculated; the confidence, identity matching degree, and location matching degree are fused to calculate a comprehensive judgment score, and compared with an adaptive threshold to determine the safety judgment result.

[0049] The system performs risk classification on control intentions, categorizing them into low-risk, medium-risk, and high-risk levels. For example, "checking battery level" is low-risk, "switching operating modes" is medium-risk, and "emergency acceleration / braking" is high-risk. Based on current operating status information, the system performs scenario threshold judgments. For instance, if the vehicle speed exceeds a safety threshold, the road gradient exceeds a preset range, or the battery level is below the minimum safe level, the corresponding interactive control relationship is flagged as risky and deemed not to meet safety conditions. The system performs quality and source reliability analysis on the collected valid voice input information, calculating the confidence score of speech recognition, the speaker identity matching score, and the directional matching score of the voice source. The recognition confidence score measures the speech-to-text accuracy, the speaker identity matching score determines whether the input voice comes from an authorized user, and the directional matching score determines whether the direction of the voice source falls within the user's mouth space.

[0050] The system weights and fuses the recognition confidence, identity matching and location matching to obtain a comprehensive judgment score, and compares it with an adaptive threshold. When the comprehensive judgment score is higher than the adaptive threshold, the system outputs a security judgment result that allows execution; when the comprehensive judgment score is close to or lower than the threshold, the system outputs a security judgment result that delays execution or refuses execution.

[0051] Furthermore, based on the security determination results, the interactive control relationship is transformed into control execution instructions, including:

[0052] The security determination results are divided into multiple scenario levels: allowed execution, delayed execution, and denied execution. The execution mode of the interactive control relationship is selected according to the scenario level category. When the security determination result is allowed execution, the corresponding control execution command is directly generated according to the interactive control relationship. When the security determination result is delayed execution, buffer parameters are set based on the current running status information, and the control execution command is issued when the confirmation condition is met. When the security determination result is denied execution, an alternative prompt command is generated and fed back to the user through voice broadcast or display interface.

[0053] The system categorizes safety assessment results into three scenario levels: allowed execution, delayed execution, and denied execution. Based on the scenario level, it selects the corresponding execution mode for the interactive control relationship. When the safety assessment result is allowed execution, the system generates the corresponding control execution command directly based on the interactive control relationship without additional delay or correction, and sends it to the electric scooter's vehicle control unit for action execution. When the safety assessment result is delayed execution, the system sets buffer parameters based on the electric scooter's current operating status information, such as buffer time, speed threshold, or battery replenishment conditions. After confirming that the conditions are met, the system converts the interactive control relationship into a control execution command and sends it for execution, ensuring both safety and execution feasibility. When the safety assessment result is denied execution, the system no longer converts the interactive control relationship into an actual control command, but instead generates an alternative prompt command, such as "This operation is not allowed in the current state" or "Please reduce speed and try again," and provides feedback to the user through the in-vehicle voice broadcast module or display interface.

[0054] The electric scooter is controlled according to the control execution command.

[0055] The system sends control execution commands, generated after safety assessment, to the vehicle control unit of the electric scooter. The vehicle control unit then calls the corresponding execution module to complete the specific operation. For example, when the control execution command is "accelerate," the motor drive module adjusts its output power to increase the vehicle speed; when the control execution command is "decelerate" or "brake," the braking module or energy recovery module receives the command and performs deceleration; when the control execution command is "switch operating mode," the operating mode management module switches to energy-saving mode, standard mode, or sport mode according to the command; when the control execution command is "check battery level," the battery management system (BMS) feeds back the current battery level information to the user interface or outputs it via voice broadcast.

[0056] In summary, the embodiments of this application have at least the following technical effects:

[0057] When a preset voice activation command is detected, the voice recognition channel is activated to collect the current voice signal. The source of the collected voice signal is located, and valid voice input information is filtered based on the source and location results. Next, the current operating status information of the electric scooter is acquired, including speed, operating mode, and battery level. Then, an interactive control relationship is established between the current operating status information and the control intent recognized by the valid voice input information. A safety assessment of the interactive control relationship is performed, and based on the safety assessment result, the interactive control relationship is converted into a control execution command. Finally, the electric scooter is controlled according to the control execution command. This solves the technical problem in existing technologies where environmental interference leads to low accuracy in voice command recognition, achieving the technical effect of improving the accuracy of voice command recognition and ensuring the stability of the interaction process.

[0058] Example 2, based on the same inventive concept as the voice interaction control method for electric scooters in the foregoing examples, such as... Figure 2 As shown, this application provides a voice interaction control system for an electric scooter, wherein the system includes:

[0059] Voice signal acquisition module 11: When a preset voice activation command is detected, the voice recognition channel is activated to acquire the current voice signal; Voice information filtering module 12: The source of the acquired current voice signal is located, and valid voice input information is filtered based on the source and location results; Running status acquisition module 13: The current running status information of the electric scooter is acquired, including speed, running mode, and battery level; Control relationship conversion module 14: An interactive control relationship is established between the current running status information and the control intent identified by the valid voice input information, the safety of the interactive control relationship is determined, and the interactive control relationship is converted into a control execution command based on the safety determination result; Scooter control module 15: The electric scooter is controlled according to the control execution command.

[0060] Furthermore, the voice signal acquisition module 11 is used to perform the following method:

[0061] Obtain the spatial position range of the user's mouth and establish a corresponding voice acquisition cone region; based on the voice acquisition cone region, perform voice recognition channel labeling and filtering, and acquire voice signals.

[0062] Furthermore, the voice signal acquisition module 11 is used to perform the following method:

[0063] The system acquires the user's pre-imported height information through a pre-collection module before cycling activation, combines it with the user's posture information detected by the vehicle's sensors, performs user posture analysis, and establishes a user posture model. Based on the user posture model, the system determines the spatial range of the user's mouth position and performs position matching in conjunction with the microphone's set position.

[0064] Furthermore, the voice information filtering module 12 is used to perform the following method:

[0065] The microphone position is located based on the speech signal source, and the channel markings corresponding to the speech acquisition cone area are identified. Speech signals falling within the channel marking range are marked as valid inputs, while speech signals outside the range are downweighted or masked. The energy characteristics, spectral characteristics, and zero-crossing rate characteristics of the acquired speech signal are extracted to determine whether the speech signal is near-end speech or far-end speech. When it is determined to be near-end speech, the orientation is determined based on the relative feature comparison of the microphone signal, and the orientation result is matched with a preset mouth spatial position range. Speech signals that simultaneously meet the near-end speech characteristics and orientation matching conditions are taken as the valid speech input information.

[0066] Furthermore, the voice information filtering module 12 is used to perform the following method:

[0067] The number and installation location of the acquisition microphones are identified, including vehicle-mounted microphones and / or external microphones; when there are two or more acquisition microphones, the arrival time difference, energy difference or phase difference between the signals acquired by different microphones are calculated; based on the difference results, the direction of the sound source is analyzed, and combined with the relative characteristics of the microphone signals, the directional result of the speech signal is determined.

[0068] Furthermore, the voice information filtering module 12 is used to perform the following method:

[0069] When the voice recognition channel is an earphone microphone or a headset near-mouth microphone, the microphone voice channel is set to the highest priority, and the voice signal collected by the priority channel is directly used as the valid voice input information.

[0070] Furthermore, the control relationship conversion module 14 is used to perform the following method:

[0071] Based on the control intent, the system retrieves the corresponding candidate control actions and their timing templates from the preset strategy library; it then performs constraint parsing on the candidate control actions and their timing templates according to the current running status information, completes feasibility verification, parameter trimming and timing rearrangement, and generates the interactive control relationship.

[0072] Furthermore, the control relationship conversion module 14 is used to perform the following method:

[0073] The control intent is risk-classified; based on the current operating status information, a scene threshold judgment is made, and the risk is marked as an interaction control relationship that does not meet the safety conditions; the recognition confidence, speaker identity matching degree, and location matching degree of the effective voice input information are calculated; the confidence, identity matching degree, and location matching degree are fused to calculate a comprehensive judgment score, and compared with an adaptive threshold to determine the safety judgment result.

[0074] Furthermore, the control relationship conversion module 14 is used to perform the following method:

[0075] The security determination results are divided into multiple scenario levels: allowed execution, delayed execution, and denied execution. The execution mode of the interactive control relationship is selected according to the scenario level category. When the security determination result is allowed execution, the corresponding control execution command is directly generated according to the interactive control relationship. When the security determination result is delayed execution, buffer parameters are set based on the current running status information, and the control execution command is issued when the confirmation condition is met. When the security determination result is denied execution, an alternative prompt command is generated and fed back to the user through voice broadcast or display interface.

[0076] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0077] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0078] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A voice interaction control method for electric scooters, characterized in that, The method includes: When a preset voice activation command is detected, the voice recognition channel is activated to collect the current voice signal; The source of the collected current speech signal is located, and valid speech input information is filtered based on the source and location results. Obtain the current operating status information of the electric scooter, including speed, operating mode, and battery level; Establish an interactive control relationship between the current operating status information and the control intent identified by the valid voice input information, perform a security determination on the interactive control relationship, and convert the interactive control relationship into a control execution command based on the security determination result; The electric scooter is controlled according to the control execution command; This process involves locating the source of the acquired current speech signal, and then filtering valid speech input information based on the source and location results. This includes: The microphone position is located based on the voice signal source, and the channel label of the corresponding voice acquisition cone area is identified. Voice signals falling within the channel label range are marked as valid inputs, and voice signals outside the range are downweighted or masked. Extract the energy characteristics, spectral characteristics, and zero-crossing rate characteristics of the acquired speech signal to determine whether the speech signal is near-end speech or far-end speech; When the speech is determined to be near-end speech, the orientation is determined based on the relative feature comparison of the microphone signal, and the orientation result is matched with the preset mouth space position range. The speech signal that simultaneously meets the near-end speech feature and orientation matching conditions is taken as the effective speech input information. Among them, the location determination based on the relative feature comparison of microphone signals includes: The number and installation location of the acquisition microphones are identified, including vehicle-mounted microphones and / or external microphones; When there are two or more microphones, calculate the arrival time difference, energy difference or phase difference between the signals collected by different microphones; Based on the difference results, the direction of the sound source is analyzed, and combined with the comparison of the relative features of the microphone signal, the directional result of the speech signal is determined. The process of filtering valid voice input information also includes: When the voice recognition channel is an earphone microphone or a headset near-mouth microphone, the microphone voice channel is set to the highest priority, and the voice signal collected by the priority channel is directly used as the valid voice input information.

2. The voice interaction control method for electric scooters according to claim 1, characterized in that, Start the speech recognition channel to collect the current speech signal, including: Obtain the spatial range of the user's mouth and establish a corresponding cone-shaped area for voice acquisition; Based on the cone-shaped area for voice acquisition, voice recognition channel labeling and filtering are performed to acquire voice signals.

3. The voice interaction control method for electric scooters according to claim 2, characterized in that, Obtain the spatial range of the user's mouth, including: The system obtains the user's pre-imported height information through the pre-collection module before cycling activation, and combines it with the user's posture information detected by the vehicle's sensors to perform user posture analysis and establish a user posture model. Based on the user's body shape model, the spatial range of the user's mouth is determined, and position matching is performed in conjunction with the microphone's set position.

4. The voice interaction control method for an electric scooter according to claim 1, characterized in that, Establishing an interactive control relationship between the current operating status information and the control intent identified by the valid voice input information includes: Based on the control intent, retrieve the corresponding candidate control actions and their timing templates from the preset strategy library; Based on the current operating status information, the candidate control actions and the action timing templates are constrained and parsed to complete feasibility verification, parameter trimming and timing rearrangement, and generate the interactive control relationship.

5. The voice interaction control method for an electric scooter according to claim 4, characterized in that, The security determination of the interactive control relationship includes: The control intent is risk-classified; Based on the current operating status information, a scenario threshold judgment is made, and the risk is marked as an interaction control relationship that does not meet the safety conditions. Calculate the recognition confidence, speaker identity matching degree, and location matching degree of the effective voice input information; The confidence level, identity matching degree, and location matching degree are combined to calculate a comprehensive judgment score, which is then compared with an adaptive threshold to determine the security judgment result.

6. The voice interaction control method for an electric scooter according to claim 5, characterized in that, Based on the security determination results, the interactive control relationship is transformed into control execution instructions, including: The security determination results are divided into multiple scenario levels: allowed execution, delayed execution, and denied execution. The execution mode of the interaction control relationship is selected according to the scenario level category. When the security determination result indicates that execution is allowed, the corresponding control execution instruction is directly generated according to the interaction control relationship; When the security determination result is delayed execution, buffer parameters are set based on the current running status information, and a control execution command is issued when the confirmation condition is met. When the security determination result is "reject execution", an alternative prompt instruction is generated and fed back to the user through voice broadcast or display interface.

7. A voice interaction control system for electric scooters, characterized in that, The system is used to implement the voice interaction control method for an electric scooter according to any one of claims 1-6, the system comprising: Voice signal acquisition module: When a preset voice activation command is detected, the voice recognition channel is activated to acquire the current voice signal; Voice information filtering module: Based on the current voice signal collected, the source is located, and based on the source and location results, valid voice input information is filtered. Operating status acquisition module: Acquires the current operating status information of the electric scooter, including speed, operating mode, and battery level; Control Relationship Conversion Module: Establishes an interactive control relationship between the current running status information and the control intent identified by the valid voice input information, performs a security determination on the interactive control relationship, and converts the interactive control relationship into a control execution command based on the security determination result; Scooter control module: Controls the electric scooter according to the control execution instructions.

Images