Voice assistant awakening method, intelligent terminal and storage medium

Abstract

The invention discloses a voice assistant wake-up method, an intelligent terminal and a storage medium, the voice assistant wake-up method is applied to the intelligent terminal, and the voice assistant wake-up method comprises the following steps: obtaining a touch feedback signal generated by sensing a user touch operation by a side sliding key; wherein the touch feedback signal comprises a pressure characteristic parameter and a movement characteristic parameter; detecting whether the pressure characteristic parameter is within a first threshold range or not; if the pressure characteristic parameter is within the first threshold range, detecting whether the movement characteristic parameter is within a second threshold range; and if the movement characteristic parameter is within a second threshold range, starting a microphone and loading a voice assistant processing module. Through the above scheme, the voice assistant wake-up method is simpler to trigger and quicker in response, so that the wake-up success rate is effectively ensured, the false wake-up problem is avoided, the trigger accuracy is higher, the application scenarios are richer, and the user experience is greatly improved.

Description

Technical Field

[0001] This application relates to the field of smart terminal technology, and in particular to a voice assistant wake-up method, a smart terminal, and a storage medium. Background Technology

[0002] In recent years, the mainstream solution in the field of intelligent voice assistant wake-up technology mainly relies on voice wake-up word recognition. The device collects ambient sound through a microphone, processes and analyzes the sound signal using a built-in speech recognition algorithm, and matches the extracted speech features with a pre-set acoustic model of the wake-up word. Once a wake-up word with a matching degree reaching a set threshold is detected, the intelligent assistant is triggered to enter working mode.

[0003] However, existing technologies have many drawbacks: On the one hand, due to the complexity and diversity of sounds in the environment, some speech segments that sound similar to the wake word, such as in noisy public places or when playing TV programs at home, can easily lead to misidentification of the device and accidental wake-up, seriously interfering with normal user use and resulting in frequent false wake-up problems; on the other hand, wake-up accuracy is constrained by a variety of factors. Different users have huge differences in accent, speech speed, and intonation. In addition, noise interference in the device's environment and the performance limitations of audio acquisition hardware make it difficult for speech recognition models to accurately capture and match wake words, making it difficult to guarantee the wake-up success rate and greatly affecting the user experience. Summary of the Invention

[0004] The main technical problem addressed by this application is to provide a voice assistant wake-up method, a smart terminal, and a storage medium to solve the problems of frequent false wake-up in existing voice assistant wake-up methods, the fact that wake-up accuracy is subject to various factors, making it difficult to guarantee the wake-up success rate and greatly affecting the user experience.

[0005] To address the aforementioned issues, the first aspect of this application provides a voice assistant wake-up method applied in a smart terminal. The voice assistant wake-up method includes: acquiring a touch feedback signal generated by a user's touch operation via a side sliding button; wherein the touch feedback signal includes pressure characteristic parameters and movement characteristic parameters; detecting whether the pressure characteristic parameters are within a first threshold range; if the pressure characteristic parameters are within the first threshold range, detecting whether the movement characteristic parameters are within a second threshold range; if the movement characteristic parameters are within the second threshold range, activating the microphone and loading the voice assistant processing module.

[0006] The voice assistant wake-up method further includes: deleting the touch feedback signal if the pressure feature parameter is not within the first threshold range; and deleting the touch feedback signal if the movement feature parameter is not within the second threshold range.

[0007] The smart terminal also includes a vibration module and a display screen. If the motion feature parameter is within the second threshold range, the steps of activating the microphone and loading the voice assistant processing module include: if the motion feature parameter is within the second threshold range, triggering the vibration module to vibrate the smart terminal for a first duration, triggering the display screen to pop up a half-screen interactive interface, activating the microphone and loading the voice assistant processing module.

[0008] The motion feature parameters include direction feature values, sliding distance parameters, and motion speed parameters. The step of detecting whether the motion feature parameters are within the second threshold range includes: detecting whether the direction feature value is positive; if the motion feature parameters are within the second threshold range, the step of activating the microphone and loading the voice assistant processing module includes: if the direction feature value is positive, detecting whether the sliding distance parameter is within the third threshold range; if the sliding distance parameter is within the third threshold range, detecting whether the motion speed parameter is within the fourth threshold range; if the motion speed parameter is within the fourth threshold range, activating the microphone and loading the voice assistant processing module.

[0009] The steps include, after activating the microphone and loading the voice assistant processing module, detecting whether the direction feature value is negative; if the direction feature value is negative, detecting whether the sliding distance parameter is within the fifth threshold range; if the sliding distance parameter is within the fifth threshold range, turning off the voice assistant processing module.

[0010] The step of turning off the voice assistant processing module if the sliding distance parameter is within the fifth threshold range further includes: if the sliding distance parameter is within the fifth threshold range, detecting whether the duration of the touch feedback signal is within the sixth threshold range; if the duration of the touch feedback signal is within the sixth threshold range, turning off the voice assistant processing module.

[0011] The smart terminal also includes a vibration module. If the sliding distance parameter is within the fifth threshold range, the step of turning off the voice assistant processing module further includes: if the sliding distance parameter is within the fifth threshold range, triggering the vibration module to vibrate the smart terminal for a second duration, storing the current dialogue feature signal and unfinished voice commands to a preset storage space, and turning off the voice assistant processing module.

[0012] The voice assistant wake-up method further includes: detecting whether the smart terminal is in a preset working state; if the smart terminal is in a preset working state, disabling the voice assistant processing module; or, adjusting the first threshold range and the second threshold range.

[0013] To address the aforementioned issues, a second aspect of this application provides a smart terminal, comprising a signal processing module, a voice assistant processing module, a microphone, and a side sliding button. The signal processing module is coupled to the voice assistant processing module, the microphone, and the side sliding button. The signal processing module controls the voice assistant processing module using any of the above-mentioned voice assistant wake-up methods.

[0014] To address the aforementioned problems, a third aspect of this application provides a computer-readable storage medium having program instructions stored thereon, which, when executed by a processor, implement the voice assistant wake-up method as described in any of the preceding claims.

[0015] The beneficial effects of this application are as follows: Unlike the prior art, the voice assistant wake-up method of this application obtains the touch feedback signal generated by the user's touch operation through the side sliding button. When the pressure feature parameter in the touch feedback signal is within a first threshold range and the movement feature parameter is within a second threshold range, the microphone is activated and the voice assistant processing module is loaded. This enables the voice assistant to be woken up in response to the sliding trigger operation. The triggering method is simpler and the response is faster, thus effectively ensuring the wake-up success rate. Moreover, the sliding trigger also avoids the problem of false wake-up caused by environmental noise interference, resulting in higher trigger accuracy and richer application scenarios. Especially in scenarios such as driving and meetings where the voice assistant needs to be quickly invoked, the user can wake up the assistant by touching the side sliding button with one hand without having to look at the screen, which greatly improves the user experience. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the first embodiment of the voice assistant wake-up method of this application; Figure 2 This is a flowchart illustrating the second embodiment of the voice assistant wake-up method of this application; Figure 3 This is a flowchart illustrating the third embodiment of the voice assistant wake-up method of this application; Figure 4 This is a flowchart illustrating the fourth embodiment of the voice assistant wake-up method of this application; Figure 5 This is a flowchart illustrating the fifth embodiment of the voice assistant wake-up method of this application; Figure 6 This is a schematic diagram of the framework of one embodiment of the smart terminal of this application; Figure 7 This is a schematic diagram of a framework of one embodiment of the computer-readable storage medium of this application. Detailed Implementation

[0017] 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. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] The terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. 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 device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0019] In this document, the term "implementation" means that a specific feature, structure, or characteristic described in connection with an implementation may be included in at least one implementation of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same implementation, nor is it a separate or alternative implementation mutually exclusive with other implementations. It will be explicitly and implicitly understood by those skilled in the art that the implementations described herein can be combined with other implementations.

[0020] The present application will now be described in detail with reference to the accompanying drawings and embodiments.

[0021] Please see Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the voice assistant wake-up method of this application. Specifically, it may include the following steps: S11: Obtain the touch feedback signal generated by the user's touch operation of the side sliding button.

[0022] It is understood that the voice assistant wake-up method provided in this application is specifically applied to any reasonable smart terminal equipped with a voice assistant processing module, such as a smartphone, tablet computer, or smartwatch. By setting a sliding trigger mechanism in the side button area of ​​the smart terminal to wake up the voice assistant processing module, the wake-up success rate and trigger accuracy are effectively guaranteed. Of course, in other embodiments, this voice assistant wake-up method can also be applied to electric toys, intelligent robots, electric vehicles, or other reasonable electronic devices; this embodiment does not impose any limitations on this.

[0023] It is worth noting that this voice assistant is an application that enables human-computer interaction through natural language processing technology, possessing speech recognition, semantic understanding, and task execution capabilities. The voice assistant processing module can specifically correspond to an application program or a separately configured voice processing chip; this application does not limit this.

[0024] In addition, the smart terminal specifically includes a signal processing module, a voice assistant processing module, a microphone, and a side sliding button. The signal processing module is coupled to the voice assistant processing module, the microphone, and the side sliding button. The side sliding button corresponds to a special sensing button located in the side button area of ​​the smart terminal, which is equipped with one or more of any reasonable sensors such as a capacitive sensor, a displacement sensor, a pressure sensor, and a linear capacitor array. The signal processing module can specifically correspond to an application program or an independently configured signal processing chip, and this application does not limit it in this way.

[0025] In this text, "coupled" refers to any direct or indirect connection. Therefore, if the text describes a first circuit coupled to a second circuit, it means that the first circuit can be directly connected to the second circuit via electrical connection or signal connection methods such as wireless transmission or optical transmission, or indirectly connected to the second circuit via other circuits or connection methods via electrical connection or signal connection.

[0026] Specifically, when a user touches and slides the side sliding button, the side sliding button senses the touch and slide operation in real time to generate a corresponding touch feedback signal and sends the touch feedback signal to the signal processing module.

[0027] The touch feedback signal includes pressure characteristic parameters and movement characteristic parameters, or it can be understood as being parsed and extracted as pressure characteristic parameters and movement characteristic parameters.

[0028] Specifically, the signal processing module is used to acquire the touch feedback signal and parse and extract the pressure characteristic parameters corresponding to the user's touch operation, such as one or more of any reasonable pressure-related parameters such as touch pressure intensity, duration, and pressure change rate, as well as movement characteristic parameters, such as one or more of any reasonable sliding-related parameters such as sliding speed, direction, distance, and trajectory smoothness. This application does not limit these parameters.

[0029] S12: Detect whether the pressure characteristic parameter is within the first threshold range.

[0030] The system detects whether the currently acquired pressure feature parameters are within the first threshold range to determine whether the user's touch operation is invalid.

[0031] In some embodiments, the first threshold range may specifically be a touch pressure threshold, such as 30% to 70% screen pressure; and / or a duration threshold, such as 100ms to 1s, and may be specifically determined by fitting one or more of the following factors in the actual application scenario: excluding light touch, accidental touch, electrostatic interference, avoiding user touch operation that is too light or too heavy, and excluding the influence of instantaneous interference. This application does not limit this.

[0032] In other embodiments, the first threshold range and other threshold ranges mentioned below can also be obtained by collecting and training user historical operation data (such as common pressure and sliding speed) using a deep network learning model to fit the setting. That is, by learning user habits, each threshold range can be dynamically adjusted in a personalized manner. This application does not limit this.

[0033] If the pressure characteristic parameter is not within the first threshold range, then S13 is executed; if the pressure characteristic parameter is within the first threshold range, then S14 is executed.

[0034] S13: Remove touch feedback signal.

[0035] If the currently acquired pressure characteristic parameter is determined to be outside the first threshold range, it indicates that the touch feedback signal is invalid. The user's touch operation may be a mistaken touch due to excessively low or high pressure, such as putting the smart terminal in or taking it out of the pocket. The currently acquired touch feedback signal is then deleted.

[0036] S14: Detect whether the moving feature parameter is within the second threshold range.

[0037] When it is determined that the currently acquired pressure feature parameters are within the first threshold range, it is further detected whether the synchronously acquired movement feature parameters are within the second threshold range, so as to comprehensively determine whether the user's touch operation is an invalid operation.

[0038] In some embodiments, the second threshold range can be any reasonable speed threshold such as greater than 3 cm / s or greater than 4 cm / s; and / or any reasonable sliding distance threshold such as greater than 0.8 cm or greater than 1 cm, and is specifically set by fitting one or more factors in the actual application scenario to exclude the influence of slight shaking, trembling, and no movement interference when pressing. This application does not limit this.

[0039] Understandably, by using a two-parameter joint judgment, the false trigger rate can be significantly reduced and the wake-up accuracy improved.

[0040] S15: Activate the microphone and load the voice assistant processing module.

[0041] When the acquired pressure feature parameters are determined to be within the first threshold range, and the synchronously acquired movement feature parameters are also within the second threshold range, the user touch operation is determined to be a valid operation. The system then switches from low-power standby mode to working mode to activate the microphone to start collecting ambient audio and simultaneously load the voice assistant processing module to wait for voice interaction with the user. That is, when the user speaks a command, the voice assistant processes and responds. It can also automatically shut down the module to reduce power consumption when there is no voice input timeout.

[0042] The above solution uses a side-swipe button to wake up the voice assistant via a swipe-triggered operation. This simpler and faster triggering method effectively ensures a high success rate. Furthermore, the swipe-triggered operation avoids false wake-ups caused by environmental noise, resulting in higher accuracy and a wider range of applications. Especially in scenarios requiring quick voice assistant access, such as driving or meetings, users can wake the assistant with a single touch of the side-swipe button, without needing to look at the screen, significantly improving the user experience. The microphone and voice module only activate after confirming the user's intent, avoiding constant monitoring; there is no risk of "always listening," giving users greater peace of mind; dual-parameter judgment significantly reduces false triggers (such as accidental touches from pockets or environmental noise); the "swipe to wake" is intuitive and enhances the user experience; and the threshold can learn user habits and be personalized.

[0043] Furthermore, in some embodiments, the process after S11 and before S12 may specifically include filtering the touch feedback signal.

[0044] Understandably, by filtering the touch feedback signal, such as using one or more reasonable signal filtering methods like Kalman filtering or moving average, high-frequency jitter and environmental interference can be effectively eliminated, thus achieving anti-shake and noise reduction.

[0045] Furthermore, in some embodiments, the smart terminal also includes a vibration module and a display screen. Specifically, S15 may also include: triggering the vibration module to vibrate the smart terminal for a first duration, triggering the display screen to pop up a half-screen interactive interface, activating the microphone, and loading the voice assistant processing module.

[0046] Understandably, upon confirming that the current user touch operation is valid, the vibration module can be triggered to vibrate the smart terminal for a first duration—that is, to emit a brief vibration—as feedback to prompt the user to activate the voice assistant. Furthermore, simultaneously activating the microphone and loading the voice assistant processing module, a half-screen interactive interface can be displayed to facilitate user input of commands, thus providing the user with a sense of immediate response throughout the entire process. Furthermore, in some embodiments, the process after S12 and before S14 may specifically include: in response to continuously detecting that the pressure characteristic parameter is within the first threshold range for more than a set number of times, or detecting that the pressure characteristic parameter is within the first threshold range for more than a set duration, loading the voice assistant processing module, triggering the voice assistant processing module to silently dial an alarm call, and broadcasting preset alarm voice content.

[0047] Understandably, in specific scenarios such as when a user is being held hostage and it is inconvenient for the user to make a phone call to report an emergency, the background alarm function of the voice assistant can still be effectively realized by setting a specific silent wake-up method for the voice assistant processing module.

[0048] In some embodiments, the voice assistant wake-up method can also be used in scenarios where the user wakes up the voice assistant by sliding it from the side of the phone without having to say a wake-up word; or, in response to the user's operation of the crown on a smartwatch, rotating / sliding the crown to start voice input; or, in response to the user's control of the earphone stem, sliding the earphone stem to wake up the voice assistant; or, in response to in-vehicle voice control, sliding the steering wheel button to start voice navigation, etc., in any reasonable application scenario, and this application does not limit it in any way.

[0049] Please see Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the voice assistant wake-up method of this application. The voice assistant wake-up method of this embodiment... Figure 1 A detailed implementation diagram of the voice assistant wake-up method is shown, including the following steps: S21: Obtain the touch feedback signal generated by the user's touch operation of the side sliding button.

[0050] S22: Detect whether the pressure characteristic parameter is within the first threshold range.

[0051] S23: Remove touch feedback signal.

[0052] Among them, S21, S22 and S23 and Figure 1 S11, S12 and S13 are the same. Please refer to the textual descriptions of S11, S12 and S13 and their related information for details. They will not be repeated here.

[0053] S24: Detect whether the directional feature value is positive.

[0054] In some embodiments, the movement feature parameter may specifically include a direction feature value, a sliding distance parameter, and a movement speed parameter; wherein, the direction feature value can be understood as a feature value given in response to the user's touch operation for swiping up and swiping down in opposite directions, and the feature value corresponding to swiping up is positive and the feature value corresponding to swiping down is negative; or, the feature value corresponding to swiping up is negative and the feature value corresponding to swiping down is positive; or, when the direction feature value is a digital signal, the feature value corresponding to swiping up is 1 and the feature value corresponding to swiping down is 0, or the feature value corresponding to swiping up is 0 and the feature value corresponding to swiping down is 1, and this application does not limit this.

[0055] Specifically, the signal processing module detects whether the currently acquired directional feature value is positive in order to determine whether the sliding direction of the user's touch operation is an upward swipe.

[0056] If the direction characteristic value is positive, then S25 is executed; if the direction characteristic value is negative, then S23 is executed.

[0057] S25: Detect whether the sliding distance parameter is within the third threshold range.

[0058] When the currently acquired directional feature value is determined to be positive, it is further detected whether the synchronously acquired sliding distance parameter is within the third threshold range.

[0059] In some embodiments, the third threshold range can be any reasonable sliding distance threshold such as greater than 0.8cm or greater than 1cm, and is specifically set by fitting one or more factors in the actual application scenario, excluding the influence of slight shaking, trembling, and no movement interference when pressing. This application does not limit this.

[0060] If the sliding distance parameter is within the third threshold range, then S26 is executed; if the sliding distance parameter is not within the third threshold range, then S23 is executed.

[0061] S26: Detect whether the movement speed parameter is within the fourth threshold range.

[0062] When it is determined that the currently acquired sliding distance parameter is within the third threshold range, it is further detected whether the synchronously acquired moving speed parameter is within the fourth threshold range.

[0063] In some embodiments, the fourth threshold range can be any reasonable speed threshold such as greater than 3cm / s or greater than 4cm / s, and is specifically set by fitting one or more factors in the actual application scenario, excluding the influence of slight shaking, trembling, and no movement interference when pressing. This application does not limit this.

[0064] If the movement speed parameter is within the fourth threshold range, then S27 is executed; if the movement speed parameter is not within the fourth threshold range, then S23 is executed.

[0065] S27: Start the microphone and load the voice assistant processing module.

[0066] Among them, S27 and Figure 1 The same applies to S15 in the text. Please refer to S15 and its related textual description for details, which will not be repeated here.

[0067] Please see Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the voice assistant wake-up method of this application. The voice assistant wake-up method of this embodiment... Figure 2 A detailed implementation diagram of the voice assistant wake-up method is shown, including the following steps: S31: Obtain the touch feedback signal generated by the user's touch operation of the side sliding button.

[0068] S32: Detect whether the pressure characteristic parameter is within the first threshold range.

[0069] S33: Remove touch feedback signal.

[0070] S34: Detect whether the directional feature value is positive.

[0071] S35: Detect whether the sliding distance parameter is within the third threshold range.

[0072] S36: Detect whether the movement speed parameter is within the fourth threshold range.

[0073] S37: Activate the microphone and load the voice assistant processing module.

[0074] Among them, S31, S32, S33, S34, S35, S36 and S37 and Figure 2 S21, S22, S23, S24, S25, S26 and S27 are the same. For details, please refer to the textual descriptions of S21, S22, S23, S24, S25, S26 and S27 and their related texts. They will not be repeated here.

[0075] S38: Detect whether the directional feature value is negative.

[0076] Understandably, in order to reduce the overall power consumption of smart terminals and improve their overall battery life, it is also necessary to set a corresponding program mechanism to turn off the voice assistant processing module; or, set the duration for which the voice assistant processing module is on, so that the module will automatically turn off when there is no voice input timeout, thereby reducing power consumption.

[0077] Specifically, the signal processing module detects whether the currently acquired directional feature value is negative in order to determine whether the sliding direction of the user's touch operation is downward.

[0078] If the direction characteristic value is negative, then S39 is executed; if the direction characteristic value is positive, then S33 is executed.

[0079] S39: Detect whether the sliding distance parameter is within the fifth threshold range.

[0080] When the currently acquired directional feature value is determined to be negative, it is further detected whether the synchronously acquired sliding distance parameter is within the fifth threshold range.

[0081] In some embodiments, the fifth threshold range can be any reasonable sliding distance threshold such as greater than 0.8cm or greater than 1cm, and is specifically obtained by fitting one or more factors in the actual application scenario, excluding the influence of slight shaking, trembling, and no movement interference when pressing. This application does not limit this.

[0082] S310: Disable the voice assistant processing module.

[0083] If the directional feature value is negative and the sliding distance parameter is within the fifth threshold range, the user's touch operation is determined to be a valid operation, and the voice assistant processing module is turned off to reduce power consumption.

[0084] Furthermore, in some embodiments, the smart terminal also includes a vibration module, and the above-mentioned S310 may further include: if the sliding distance parameter is within the fifth threshold range, triggering the vibration module to vibrate the smart terminal for a second duration, storing the current dialogue feature signal and unfinished voice commands to a preset storage space, and closing the voice assistant processing module.

[0085] The second duration is longer than the first duration.

[0086] Understandably, when the current user touch operation is determined to be a valid operation, the vibration module can be triggered to vibrate the smart terminal for a second duration, i.e., emit a longer vibration, as feedback to indicate to the user that the voice assistant has been turned off. Furthermore, the current dialogue state, including incomplete voice commands and interface layout, is compressed and saved to local memory space, and then the voice assistant's AI (Artificial Intelligence) computing resources are gradually released, retaining only basic voice monitoring functions, in order to reduce system power consumption to standby level. Please see Figure 4 , Figure 4 This is a flowchart illustrating the fourth embodiment of the voice assistant wake-up method of this application. The voice assistant wake-up method of this embodiment... Figure 3 A detailed implementation diagram of the voice assistant wake-up method is shown, including the following steps: S41: Obtain the touch feedback signal generated by the user's touch operation of the side sliding button.

[0087] S42: Detect whether the pressure characteristic parameter is within the first threshold range.

[0088] S43: Remove touch feedback signal.

[0089] S44: Detect whether the directional feature value is positive.

[0090] S45: Detect whether the sliding distance parameter is within the third threshold range.

[0091] S46: Detect whether the movement speed parameter is within the fourth threshold range.

[0092] S47: Activate the microphone and load the voice assistant processing module.

[0093] S48: Detect whether the directional feature value is negative.

[0094] S49: Detect whether the sliding distance parameter is within the fifth threshold range.

[0095] Among them, S41, S42, S43, S44, S45, S46, S47, S48 and S49 and Figure 3 S31, S32, S33, S34, S35, S36, S37, S38, and S39 are the same. For details, please refer to the textual descriptions of S31, S32, S33, S34, S35, S36, S37, S38, and S39. They will not be repeated here.

[0096] S410: Detect whether the duration of the touch feedback signal is within the sixth threshold range.

[0097] Understandably, in order to avoid interference and misjudgment caused by invalid operations with too short a duration of user touch operation, it is also necessary to limit the duration of touch feedback signal.

[0098] Specifically, it detects whether the duration of the currently acquired touch feedback signal is within the sixth threshold range.

[0099] In some embodiments, the sixth threshold range can be specifically 100ms (milliseconds) to 1s (seconds), and is specifically determined by fitting one or more factors in the actual application scenario, such as excluding light touch, accidental touch, electrostatic interference, avoiding user touch operation that is too light or too heavy, and excluding the influence of instantaneous interference. This application does not limit this.

[0100] If the duration of the touch feedback signal is within the sixth threshold range, then S411 is executed; if the duration of the touch feedback signal is not within the sixth threshold range, then S43 is executed.

[0101] S411: Disable the voice assistant processing module.

[0102] Among them, S411 and Figure 3 The same applies to S310. Please refer to S310 and its related textual descriptions for details, which will not be repeated here.

[0103] Please see Figure 5 , Figure 5 This is a flowchart illustrating the fifth embodiment of the voice assistant wake-up method of this application. The voice assistant wake-up method of this embodiment... Figure 1 A detailed implementation diagram of the voice assistant wake-up method is shown, including the following steps: S51: Obtain the touch feedback signal generated by the user's touch operation of the side sliding button.

[0104] S52: Detect whether the pressure characteristic parameter is within the first threshold range.

[0105] S53: Remove touch feedback signal.

[0106] S54: Detect whether the moving feature parameter is within the second threshold range.

[0107] Among them, S51, S52, S53 and S54 and Figure 1 S11, S12, S13 and S14 are the same. Please refer to the textual descriptions of S11, S12, S13 and S1 and their related texts for details. They will not be repeated here.

[0108] S55: Detects whether the smart terminal is in a preset working state.

[0109] Understandably, in certain application scenarios, such as when the smart terminal is placed face down, in free fall, or when receiving a call, the voice assistant processing module needs to be disabled to avoid accidental operation affecting usage.

[0110] Specifically, it detects whether the smart terminal is in a preset working state, such as determining whether the smart terminal is in any reasonable preset working state, such as being placed face down, in free fall, or making an incoming call, through orientation sensors and state detection.

[0111] If the smart terminal is in a preset working state, then S56 is executed; if the smart terminal is not in a preset working state, then S57 is executed.

[0112] S56: Disable the voice assistant processing module.

[0113] When it is determined that the smart terminal is currently in a preset working state, the voice assistant processing module is disabled, that is, the voice assistant processing module is prohibited from being woken up.

[0114] S57: Activate the microphone and load the voice assistant processing module.

[0115] Among them, S57 and Figure 1 The same applies to S15 in the text. Please refer to S15 and its related textual description for details, which will not be repeated here.

[0116] Furthermore, in some embodiments, the above-mentioned S56 can be replaced by: adjusting the first threshold range and the second threshold range.

[0117] Understandably, by adjusting the trigger threshold, the voice assistant processing module can also be disabled to avoid accidental operation affecting usage.

[0118] Please see Figure 6 , Figure 6 This is a schematic diagram of the framework of one embodiment of the smart terminal of this application. In this embodiment, the smart terminal 60 includes a signal processing module 61, a voice assistant processing module 62, a microphone 63, and a side sliding button 64. The signal processing module 61 is coupled to the voice assistant processing module 62, the microphone 63, and the side sliding button 64.

[0119] In some embodiments, the smart terminal 60 may be any electronic device that is reasonably equipped with a voice assistant processing module 62, such as a smartphone, tablet computer, electronic watch, electric toy, smart robot, or electric vehicle. This application does not limit the specific device to this type.

[0120] The smart terminal 60 also includes a vibration module (not shown) and a display screen (not shown), which are coupled to a signal processing module 61.

[0121] It should be noted that the signal processing module 61 described in this embodiment uses the steps of any of the above-described voice assistant wake-up method embodiments to control the voice assistant processing module 62. For details, please refer to [link to relevant documentation]. Figures 1-5 The relevant textual content will not be elaborated upon here.

[0122] Please see Figure 7 , Figure 7 This is a schematic diagram of a computer-readable storage medium according to one embodiment of the present application. The computer-readable storage medium 71 stores program instructions 711 that can be executed by a processor. The program instructions 711 are used to implement the steps of any of the above-described embodiments of the voice assistant wake-up method.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0124] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0125] 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.

[0126] 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.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A voice assistant wake-up method, applied in a smart terminal, characterized in that, The smart terminal includes a voice assistant processing module, a microphone, and a side sliding button. The voice assistant wake-up method includes: The touch feedback signal generated by the user's touch operation of the side sliding button is acquired; wherein, the touch feedback signal includes pressure characteristic parameters and movement characteristic parameters; Detect whether the pressure characteristic parameter is within the first threshold range; If the pressure feature parameter is within the first threshold range, detect whether the movement feature parameter is within the second threshold range; If the motion feature parameter is within the second threshold range, the microphone is activated and the voice assistant processing module is loaded.

2. The voice assistant wake-up method according to claim 1, characterized in that, The voice assistant wake-up method also includes: If the pressure characteristic parameter is not within the first threshold range, delete the touch feedback signal; If the motion feature parameter is not within the second threshold range, the touch feedback signal is deleted.

3. The voice assistant wake-up method according to claim 1, characterized in that, The smart terminal also includes a vibration module and a display screen. The step of activating the microphone and loading the voice assistant processing module if the motion feature parameter is within the second threshold range includes: If the movement feature parameter is within the second threshold range, the vibration module is triggered to vibrate the smart terminal for a first duration, and the display screen is triggered to pop up a half-screen interactive interface, the microphone is activated, and the voice assistant processing module is loaded.

4. The voice assistant wake-up method according to claim 1, characterized in that, The movement feature parameters include direction feature values, sliding distance parameters, and movement speed parameters. The step of detecting whether the movement feature parameters are within the second threshold range includes: Detect whether the directional feature value is positive; The step of activating the microphone and loading the voice assistant processing module if the motion feature parameter is within the second threshold range includes: If the direction feature value is positive, detect whether the sliding distance parameter is within the third threshold range; If the sliding distance parameter is within the third threshold range, detect whether the moving speed parameter is within the fourth threshold range; If the movement speed parameter is within the fourth threshold range, the microphone is activated and the voice assistant processing module is loaded.

5. The voice assistant wake-up method according to claim 4, characterized in that, After the step of activating the microphone and loading the voice assistant processing module, the method further includes: Detect whether the directional feature value is negative; If the directional feature value is negative, detect whether the sliding distance parameter is within the fifth threshold range; If the sliding distance parameter is within the fifth threshold range, the voice assistant processing module is turned off.

6. The voice assistant wake-up method according to claim 5, characterized in that, The step of shutting down the voice assistant processing module if the sliding distance parameter is within the fifth threshold range further includes: If the sliding distance parameter is within the fifth threshold range, detect whether the duration of the touch feedback signal is within the sixth threshold range; If the duration of the touch feedback signal is within the sixth threshold range, the voice assistant processing module will be turned off.

7. The voice assistant wake-up method according to claim 5, characterized in that, The smart terminal further includes a vibration module, and the step of turning off the voice assistant processing module if the sliding distance parameter is within the fifth threshold range further includes: If the sliding distance parameter is within the fifth threshold range, the vibration module is triggered to vibrate the smart terminal for a second duration, the current dialogue feature signal and unfinished voice commands are stored in a preset storage space, and the voice assistant processing module is turned off.

8. The voice assistant wake-up method according to any one of claims 1-7, characterized in that, The voice assistant wake-up method also includes: Detect whether the smart terminal is in a preset working state; If the smart terminal is in the preset working state, disable the voice assistant processing module; or adjust the first threshold range and the second threshold range.

9. A smart terminal, characterized in that, The smart terminal includes a signal processing module, a voice assistant processing module, a microphone, and a side sliding button. The signal processing module is coupled to the voice assistant processing module, the microphone, and the side sliding button. The signal processing module uses the voice assistant wake-up method as described in any one of claims 1-8 to control the voice assistant processing module.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that, When the program instructions are executed by the processor, the voice assistant wake-up method as described in any one of claims 1-8 is implemented.

Images