Methods and apparatus for production testing of voice devices; voice devices; media

Abstract

This application relates to the field of smart home appliance technology, and discloses a method for production testing of voice devices. The voice device includes: a voice module, an ultrasonic transmitting module for generating and transmitting coded ultrasonic signals, and an ultrasonic receiving module for acquiring ultrasonic signals. The method includes: transmitting generated ultrasonic waves upon receiving a coded sound wave trigger command; simultaneously acquiring reflected ultrasonic signals at the moment of transmitting the generated ultrasonic waves; processing the acquired ultrasonic signals to remove noise signals to obtain denoised ultrasonic signals; and determining whether the voice module supports ultrasonic sensing algorithms based on the sound pressure level value in the denoised ultrasonic signals. This method reduces production costs, simplifies operation procedures, improves testing efficiency, and enhances testing accuracy in detecting whether a voice device supports ultrasonic sensing algorithms. This application also discloses an apparatus, a voice device, and a storage medium for production testing of voice devices.

Description

Technical Field

[0001] This application relates to the field of smart home appliance technology, such as a method and apparatus for production testing of voice devices, voice devices, and storage media. Background Technology

[0002] Currently, with the improvement of people's living standards, people are also placing higher and higher demands on their home environment. To maintain a smart home environment, voice-activated devices have become an indispensable part of people's lives, such as voice-activated air conditioners and voice-activated televisions. However, whether ultrasonic sensing algorithms are compatible with different models of voice devices requires further testing during the production process to determine if the device model supports the ultrasonic sensing algorithm.

[0003] The related technology discloses a method for detecting whether a voice device can support an ultrasonic sensing algorithm. This involves conducting independent verification experiments on environmental indicators and device performance in the laboratory, and also assigning dedicated personnel to conduct testing in the specific production process. The method uses a sound pressure measurement instrument to measure the signal strength in order to detect whether the voice device can support the ultrasonic sensing algorithm.

[0004] In the process of implementing the embodiments of this disclosure, at least the following problems were found in the related art:

[0005] It is necessary to set up a special testing station on the production line to measure separately to check whether the voice device supports the ultrasonic sensing algorithm. This results in high production costs, long testing time, cumbersome operation for testing personnel, and the measuring instruments are easily affected by the environment, making it difficult to guarantee the accuracy of the test.

[0006] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0008] This disclosure provides a method and apparatus for production testing of voice devices, as well as a voice device and a storage medium, to reduce production costs, simplify operation procedures, improve testing efficiency, and enhance testing accuracy in the detection of whether a voice device supports ultrasonic sensing algorithms.

[0009] In some embodiments, the voice device includes: a voice module, an ultrasonic transmitting module for generating and transmitting coded ultrasonic signals, and an ultrasonic receiving module for acquiring ultrasonic signals; the method includes: transmitting the generated ultrasonic waves upon hearing a coded sound wave trigger command; simultaneously acquiring the reflected ultrasonic signals at the moment the generated ultrasonic waves are transmitted; processing the acquired ultrasonic signals to remove noise signals to obtain denoised ultrasonic signals; and determining whether the voice module supports an ultrasonic sensing algorithm based on the sound pressure level value in the denoised ultrasonic signals.

[0010] In some embodiments, the voice device includes: a voice module, an ultrasonic transmitting module for generating and transmitting coded ultrasonic signals, and an ultrasonic receiving module for acquiring ultrasonic signals; the apparatus includes: a transmitting module configured to transmit the generated ultrasonic waves upon hearing a coded sound wave trigger command; an acquisition module configured to synchronously acquire the reflected ultrasonic signals at the moment the generated ultrasonic waves are transmitted; a denoising module configured to process the acquired ultrasonic signals to remove noise signals and obtain denoised ultrasonic signals; and a determining module configured to determine whether the voice module supports an ultrasonic sensing algorithm based on the sound pressure level value in the denoised ultrasonic signals.

[0011] In some embodiments, the apparatus includes a processor and a memory storing program instructions, the processor being configured to execute the method for production testing of a voice device when the program instructions are executed.

[0012] In some embodiments, the voice device includes: a voice device body, comprising: a voice module, an ultrasonic transmitting module for generating and transmitting coded ultrasonic signals, and an ultrasonic receiving module for acquiring ultrasonic signals; the apparatus for voice device production testing is installed on the voice device body.

[0013] In some embodiments, the storage medium stores program instructions that, when executed, perform the method for production testing of a voice device.

[0014] The method and apparatus for production testing of voice devices, the voice device itself, and the storage medium provided in this disclosure can achieve the following technical effects:

[0015] The process of determining whether a voice module supports ultrasonic sensing algorithms has been algorithmically and programmatically implemented. Detection of the voice module's support for ultrasonic sensing algorithms is triggered simply by detecting the coded sound wave. This eliminates the need for a dedicated detection station on the production line, reducing production costs. It also eliminates the need for cumbersome manual operations by measurement personnel; the program controls the emission and acquisition of ultrasonic waves, synchronously replacing the original voice interaction steps, simplifying operations, improving efficiency, and making the detection process intelligent. Furthermore, since noise signals in the ultrasonic signals have been removed, and the accuracy of voice module support for ultrasonic sensing algorithms is determined based on the sound pressure level of the denoised ultrasonic signal, the detection accuracy is improved. Furthermore, the embodiments disclosed herein can not only determine whether the ultrasonic sensing algorithm is compatible with different models, but also determine whether the voice interaction function of the voice module itself is normal. Since the working principle of the sensing algorithm in the ultrasonic segment is the same as that in the audible segment, and the requirements for acoustic devices are also the same, once the voice device is detected to meet the sound pressure requirements of the ultrasonic segment, it will necessarily meet the acoustic performance requirements of the device for voice interaction. Therefore, there is no need to conduct additional special tests for the passability of voice interaction, which also improves the testing efficiency of voice function detection in the production process.

[0016] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0017] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein:

[0018] Figure 1 This is a schematic diagram of a system environment for production testing of voice devices provided in an embodiment of this disclosure;

[0019] Figure 2 This is a schematic diagram of a method for production testing of a voice device provided in an embodiment of this disclosure;

[0020] Figure 3 This is a schematic diagram of another method for production testing of voice devices provided in an embodiment of this disclosure;

[0021] Figure 4 This is a schematic diagram of another method for production testing of voice devices provided in an embodiment of this disclosure;

[0022] Figure 5 This is a schematic diagram of an apparatus for production testing of voice devices provided in an embodiment of this disclosure;

[0023] Figure 6 This is a schematic diagram of another apparatus for production testing of voice devices provided in an embodiment of this disclosure;

[0024] Figure 7 This is a schematic diagram of a voice device provided in an embodiment of this disclosure. Detailed Implementation

[0025] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0026] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0027] Unless otherwise stated, the term "multiple" means two or more.

[0028] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0029] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0030] The term "correspondence" can refer to an association or binding relationship. The correspondence between A and B means that there is an association or binding relationship between A and B.

[0031] In this embodiment of the disclosure, smart home appliances refer to home appliances formed by introducing microprocessors, sensor technology and network communication technology into home appliances. They have the characteristics of intelligent control, intelligent sensing and intelligent application. The operation of smart home appliances often relies on the application and processing of modern technologies such as the Internet of Things, the Internet and electronic chips. For example, smart home appliances can be connected to electronic devices to enable users to remotely control and manage smart home appliances.

[0032] In the disclosed embodiments, the terminal device refers to an electronic device with wireless connectivity. The terminal device can communicate with the aforementioned smart home appliances via the internet, or directly via Bluetooth, Wi-Fi, or other methods. In some embodiments, the terminal device may be, for example, a mobile device, a computer, or an in-vehicle device built into a hovercraft, or any combination thereof. Mobile devices may include, for example, mobile phones, smart home devices, wearable devices, smart mobile devices, virtual reality devices, or any combination thereof. Wearable devices may include, for example, smartwatches, smart bracelets, pedometers, etc.

[0033] Combination Figure 1 As shown, the system environment for production testing of voice equipment includes: voice equipment 1, signal baffle 2, mobile terminal 3, acoustic wave triggering fixture module 4, and manufacturing execution system (MES) 5. Voice equipment 1 includes: a voice module, an ultrasonic transmitting module for generating and transmitting coded ultrasonic signals, and an ultrasonic receiving module for acquiring ultrasonic signals. Voice equipment 1 is installed on production line 6. Signal baffle 2 has dimensions of 2m high and 1m wide, and is directly opposite voice equipment 1 at a set distance. Specifically, the set distance can be 1m. The acoustic wave triggering tool APP (application software) of mobile terminal 3 or acoustic wave triggering fixture module 4 can send coded acoustic wave triggering commands to voice equipment 1. Acoustic wave triggering fixture module 4 is connected to manufacturing execution system (MES) 5.

[0034] Optionally, the ultrasonic transmitting module includes a speaker. The ultrasonic receiving module includes a microphone.

[0035] Based on the aforementioned system environment for voice device production testing, combined with Figure 2 As shown, this disclosure provides a method for production testing of voice devices, including:

[0036] S201, upon receiving a coded sound wave trigger command, the voice device emits generated ultrasonic waves.

[0037] S202, at the moment the generated ultrasonic wave is emitted, the voice device simultaneously acquires the reflected ultrasonic wave signal.

[0038] S203, the voice device processes the acquired ultrasonic signal to remove noise and obtain a denoised ultrasonic signal.

[0039] S204, the voice device determines whether the voice module supports the ultrasonic sensing algorithm based on the sound pressure level value in the denoised ultrasonic signal.

[0040] The method for production testing of voice devices provided in this disclosure algorithmizes and programs the process of determining whether a voice module supports the ultrasonic sensing algorithm. Detection of the voice module's support for the ultrasonic sensing algorithm is triggered simply by detecting the coded sound wave trigger command, eliminating the need for a dedicated detection station on the production line and reducing production costs. It also eliminates the need for cumbersome operations by measurement personnel; the program controls the emission and acquisition of ultrasonic waves, synchronously replacing the original voice interaction detection steps, simplifying the operation, improving detection efficiency, and making the detection process intelligent. Furthermore, since noise signals in the ultrasonic signals have been removed, and the accuracy of detection is improved by determining whether the voice module supports the ultrasonic sensing algorithm based on the sound pressure level value of the denoised ultrasonic signal. Furthermore, the embodiments disclosed herein can not only determine whether the ultrasonic sensing algorithm is compatible with different models, but also determine whether the voice interaction function of the voice module itself is normal. Since the working principle of the sensing algorithm in the ultrasonic segment is the same as that in the audible segment, and the requirements for acoustic devices are also the same, once the voice device is detected to meet the sound pressure requirements of the ultrasonic segment, it will necessarily meet the acoustic performance requirements of the device for voice interaction. Therefore, there is no need to conduct additional special tests for the passability of voice interaction, which also improves the testing efficiency of voice function detection in the production process.

[0041] Optionally, the ultrasonic waves emitted by the voice device include: ultrasonic signals in sinusoidal signal format emitted multiple times by the voice device, with each emission lasting the same duration as the first emission. This facilitates multiple determinations of the sound pressure level value in the ultrasonic signal, intelligently replacing multiple checks in manual testing, thereby improving testing efficiency and making the testing process more intelligent.

[0042] Optionally, the first duration can be 250ms. The frequency range of the ultrasonic signal is [19kHz, 22kHz]. The number of times the generated ultrasonic signal is emitted can be 4. Specifically, the frequency of the ultrasonic signal can be 19kHz, 20kHz, 21kHz, or 22kHz. Thus, the ultrasonic sensing algorithm program generally uses a continuous frequency modulated wave of 19-22kHz. To enable the detection program to complete self-testing faster, four integer frequencies of 19kHz, 20kHz, 21kHz, or 22kHz are selected as the self-testing signals, which is beneficial to improving detection efficiency.

[0043] Optionally, the voice device synchronously acquires the reflected ultrasonic signal, including: the voice device synchronously acquires the reflected ultrasonic signal for a second duration and a set sampling frequency. The second duration is longer than the first duration. In this way, since the sampling duration for acquiring the reflected ultrasonic signal is longer than the duration of ultrasonic wave transmission, the reflected ultrasonic signal can be acquired more completely, improving the detection accuracy.

[0044] Optionally, the second duration can be 300ms. The sampling frequency can be set to 48kHz. In this way, since the sampling duration for acquiring the reflected ultrasonic signal is longer than the duration of the emitted ultrasonic signal, the reflected ultrasonic signal can be acquired more completely, improving the accuracy of detection.

[0045] Optionally, the voice device processes the acquired ultrasonic signals to remove noise, obtaining a denoised ultrasonic signal. This includes: the voice device performing filtering preprocessing on the acquired ultrasonic signals to remove random abnormal reflection signals, thus obtaining a denoised ultrasonic signal. The voice device records and stores the abnormal reflection peak signals in the denoised ultrasonic signal for use in the ultrasonic sensing algorithm. In this way, the acquired ultrasonic signals are first filtered to remove random abnormal reflection signals. Because the actual installation of the ultrasonic transmitting module creates gaps between the casing and the module, these gaps will inevitably create abnormal ultrasonic reflection signals, affecting the accuracy of the subsequent ultrasonic sensing algorithm in detecting human activity. Therefore, during detection, these abnormal reflection peak signals are recorded simultaneously, and the original abnormal peak data is used for compensation in the ultrasonic sensing algorithm, improving the accuracy of the algorithm. This better reduces the impact of the environment or the installation of components within the voice device itself on detection, improves detection accuracy, and enhances the testing efficiency of voice function testing in the production process.

[0046] Optionally, the voice device performs filtering preprocessing on the acquired ultrasonic signals to remove random abnormal reflection signals, obtaining a denoised ultrasonic signal. This includes: the voice device performs bandpass filtering on the acquired ultrasonic signals to obtain bandpass-filtered ultrasonic signals. The voice device uses two bandpass-filtered ultrasonic signals and performs consistency filtering on each individual bandpass-filtered ultrasonic signal to remove random abnormal reflection signals from the individual bandpass-filtered ultrasonic signals, obtaining a denoised ultrasonic signal. In this way, first performing bandpass filtering on the acquired ultrasonic signals, and then performing consistency filtering on the individual ultrasonic signals, achieves better noise reduction. This better reduces the impact of the environment on detection and improves the accuracy of detection.

[0047] Optionally, the voice device performs bandpass filtering on the acquired ultrasonic signal to obtain a bandpass-filtered ultrasonic signal, including: the voice device uses a Butterworth filter to perform bandpass filtering on the acquired ultrasonic signal to obtain a bandpass-filtered ultrasonic signal.

[0048] Specifically, the parameters of a Butterworth filter include: bandpass start frequency Wp1, bandpass cutoff frequency Wp2, passband range [Wp1, Wp2], bandstop start frequency Ws1, bandstop cutoff frequency Ws2, stopband range [0, Ws1] and [Ws2, +∞], passband ripple Rp, and stopband attenuation Rs. The passband ripple is the difference between the maximum and minimum amplitudes of the passband signal in the filter's frequency response, and the stopband attenuation is the minimum allowable attenuation level for signals outside the stopband.

[0049] More specifically, Wp1 can be 19kHz, Wp2 can be 22kHz, Ws1 can be 17kHz, Ws2 can be 24kHz, Rp can be 3dB, and Rs can be 40dB.

[0050] Thus, using a Butterworth filter for bandpass filtering does not introduce amplitude distortion or phase delay within the passband. Furthermore, due to its very high suppression ratio in the stopband, it effectively filters out noise and clutter, improving denoising performance. This better reduces the impact of the environment on detection, increasing detection accuracy. Moreover, the Butterworth filter has a fast response speed and high slew rate, which contributes to improved detection efficiency.

[0051] Optionally, the voice device records and stores abnormal reflection peak signals in the denoised ultrasonic signal for use in an ultrasonic sensing algorithm, including: the voice device calculating the average amplitude of the overall signal of the denoised ultrasonic signal; the voice device separately recording and storing abnormal reflection peak signals in the denoised ultrasonic signal that are greater than a predetermined multiple of the average amplitude; and the voice device compensating for the abnormal reflection peak signals in the denoised ultrasonic signal in the ultrasonic sensing algorithm. Specifically, the predetermined multiple can be 1.5 times.

[0052] In this way, abnormal reflection peak signals exceeding a set multiple of the average amplitude are filtered out from the preprocessed ultrasonic signals and recorded and stored. These abnormal reflection peak signals are then compensated for in the ultrasonic sensing algorithm. Therefore, during detection, these abnormal reflection peak signals are recorded synchronously, and the ultrasonic sensing algorithm utilizes this original abnormal peak data for compensation, improving the accuracy of the ultrasonic sensing algorithm. This further reduces the impact of the environment or the installation of components within the voice equipment itself on the detection, improving detection accuracy and increasing the testing efficiency of voice function testing in the production process.

[0053] Optionally, the voice device calculates the average amplitude of the overall signal of the denoised ultrasonic signal, including: the voice device calculates the average amplitude of each sampling point of the denoised ultrasonic signal.

[0054] Optionally, the voice device separately records and stores abnormal reflection peak signals in the denoised ultrasonic signal that are greater than a set multiple of the average amplitude. This includes: the voice device comparing the amplitude of each sampling point with the multiple relationship of the average amplitude, and selecting sampling points with a multiple relationship greater than a set multiple as abnormal reflection peak signals. The voice device separately records and stores the multiple abnormal reflection peak signals. The set multiple can be 1.5 times.

[0055] In this way, the pre-processed ultrasonic signal can more accurately filter out and record abnormal reflection peak signals that are greater than a set multiple of the average amplitude. These abnormal reflection peak signals are recorded simultaneously and used for compensation in the sound pressure level algorithm, improving the algorithm's accuracy. This further reduces the impact of the environment or the installation of components in the voice equipment itself on the detection, improving detection accuracy and increasing the testing efficiency of voice function testing in the production process.

[0056] Optionally, in the ultrasonic sensing algorithm, the voice device compensates for abnormal reflection peak signals in the denoised ultrasonic signal by replacing the peak values ​​of the sampling points that constitute the abnormal reflection peak signals with zero, thereby obtaining the denoised ultrasonic signal. This method of replacing the peak values ​​of the sampling points of the abnormal reflection peak signals with zero and using this portion of the original abnormal peak data for compensation improves the accuracy of the ultrasonic sensing algorithm. This further reduces the impact of the environment or the installation of components within the voice device itself on the detection process, improves detection accuracy, and enhances the testing efficiency of voice function testing in the production process.

[0057] Optionally, the voice device determines whether the voice module supports the ultrasonic sensing algorithm based on the sound pressure level value in the denoised ultrasonic signal, including:

[0058] The voice device calculates the sound pressure level value in the denoised ultrasonic signal.

[0059] If the sound pressure level values ​​of all denoised ultrasonic signals are greater than or equal to the standard level value, the voice device determines that the voice module supports the ultrasonic sensing algorithm. Alternatively,

[0060] If the sound pressure level of all denoised ultrasonic signals is less than the standard level, the voice device determines that the voice module does not support the ultrasonic sensing algorithm.

[0061] Specifically, the standard rating value can be 52 dB.

[0062] This allows for simultaneous self-testing of both the ultrasonic sensing algorithm and the voice interaction service.

[0063] Optionally, the voice device calculates the sound pressure level value in the denoised ultrasonic signal, including: the voice device calculates the actual signal sound pressure P based on air density ρ, the speed of sound c in the denoised ultrasonic signal, sound power N, sphere radius r, and sound intensity I. The voice device calculates the sound pressure level value SPL based on the actual signal sound pressure P and the reference sound pressure Pref. The unit of P is Pa, and the unit of ρ is kg / m³. 3 The unit of c is m / s, the unit of N is W, the unit of r is m, and the unit of I is W / m. 2 .

[0064] Specifically, the voice device calculates the actual signal sound pressure P based on air density ρ, the speed of sound c in the denoised ultrasonic signal, sound power N, spherical radius r, and sound intensity I, including: the voice device using P 2 =ρ*c*N / (4*π*r 2 P is obtained by calculating ρ*c*I.

[0065] Specifically, the voice device calculates the sound pressure level value SPL based on the actual signal sound pressure P and the reference sound pressure Pref, including: the voice device calculates SPL = 10 * log(P / Pref).

[0066] This allows for more accurate calculation of sound pressure level values, thereby enabling a more accurate determination of whether ultrasonic sensing algorithms are supported and whether voice interaction services are qualified.

[0067] Combination Figure 3 As shown in the embodiments of this disclosure, another method for production testing of voice devices is provided, including:

[0068] S301, when the voice device is powered on, the voice device listens for sound wave trigger commands.

[0069] S302, upon receiving a coded sound wave trigger command, the voice device emits generated ultrasonic waves.

[0070] S303: At the moment the generated ultrasonic wave is emitted, the voice device simultaneously acquires the reflected ultrasonic wave signal.

[0071] S304, the voice device processes the acquired ultrasonic signal to remove noise and obtain a denoised ultrasonic signal.

[0072] S305, the voice device determines whether the voice module supports the ultrasonic sensing algorithm based on the sound pressure level value in the denoised ultrasonic signal.

[0073] The method for production testing of voice devices provided in this disclosure algorithmizes and programs the process of determining whether a voice module supports the ultrasonic sensing algorithm. Detection of the voice module's support for the ultrasonic sensing algorithm is triggered simply by detecting the coded sound wave trigger command, eliminating the need for a dedicated detection station on the production line and reducing production costs. It also eliminates the need for cumbersome operations by measurement personnel; the program controls the emission and acquisition of ultrasonic waves, synchronously replacing the original voice interaction detection steps, simplifying the operation, improving detection efficiency, and making the detection process intelligent. Furthermore, since noise signals in the ultrasonic signals have been removed, and the accuracy of detection is improved by determining whether the voice module supports the ultrasonic sensing algorithm based on the sound pressure level value of the denoised ultrasonic signal. Furthermore, the embodiments disclosed herein can not only determine whether the ultrasonic sensing algorithm is compatible with different models, but also determine whether the voice interaction function of the voice module itself is normal. Since the working principle of the sensing algorithm in the ultrasonic segment is the same as that in the audible segment, and the requirements for acoustic devices are also the same, once the voice device is detected to meet the sound pressure requirements of the ultrasonic segment, it will necessarily meet the acoustic performance requirements of the device for voice interaction. Therefore, there is no need to conduct additional special tests for the passability of voice interaction, which also improves the testing efficiency of voice function detection in the production process.

[0074] Optionally, the voice device listens to coded acoustic wave trigger commands, including: listening to acoustic wave trigger commands sent by the coded acoustic wave trigger tool APP on the mobile terminal or listening to coded acoustic wave trigger commands emitted by the acoustic wave triggering fixture module. In this way, the trigger tool APP and the acoustic wave triggering fixture module can send coded acoustic wave trigger commands separately, and the fixture module can interface with the MES system on the production site to complete the process, thereby achieving complete automated testing.

[0075] Optionally, the communication method for encoding the acoustic wave triggering command is acoustic wave frequency modulation encoding, using a first frequency acoustic wave signal as a low-frequency transmission signal and a second frequency acoustic wave signal as a high-frequency transmission signal, with the signal transmission baud rate being a set baud rate, and the broadcast method being global broadcast.

[0076] The encoded acoustic trigger command consists of a start signal, a reserved address code, and a start information code. Specifically, the start signal can be FFFE, the reserved address code can be four bits, and the start information code can be 01.

[0077] Specifically, the first frequency can be 16kHz, and the second frequency can be 17kHz. The baud rate can be set to 96bit / s.

[0078] In this way, the communication of the encoded sound wave trigger command is mainly used to trigger the start of the voice module's self-test program. Choosing a relatively low communication rate will reduce the design of the detector and at the same time significantly reduce the occupation of the module's hardware and software resources.

[0079] Combination Figure 4 As shown in the embodiments of this disclosure, another method for production testing of voice devices is provided, including:

[0080] S401, when the voice device is powered on, the voice device listens for sound wave trigger commands.

[0081] S402, upon receiving an coded acoustic wave trigger command, the voice device repeatedly transmits ultrasonic signals in the format of a sinusoidal signal, with each transmission lasting the first duration.

[0082] S403: At the moment the generated ultrasonic wave is emitted, the voice device simultaneously acquires the reflected ultrasonic wave signal.

[0083] S404, the voice device performs filtering preprocessing on the acquired ultrasonic signal to remove random abnormal reflection signals and obtain a denoised ultrasonic signal.

[0084] S405, the voice device records and stores abnormal reflection peak signals in the denoised ultrasonic signal for use in ultrasonic sensing algorithms.

[0085] S406, the voice device calculates the sound pressure level value in the denoised ultrasonic signal.

[0086] S407, when the sound pressure level values ​​of all denoised ultrasonic signals are greater than or equal to the standard level value, the voice device determines that the voice module supports the ultrasonic sensing algorithm. Or,

[0087] S408, if the sound pressure level of the denoised ultrasonic signal is lower than the standard level, the voice device determines that the voice module does not support the ultrasonic sensing algorithm.

[0088] The method for production testing of voice devices provided in this disclosure algorithmizes and programs the measurement process of whether a voice module supports the ultrasonic sensing algorithm. The detection of whether the voice module supports the ultrasonic sensing algorithm is triggered simply by detecting the coded sound wave trigger command, eliminating the need for a dedicated detection station on the production line, thus reducing production costs. It also eliminates the need for cumbersome operations by measurement personnel; the program controls the emission and acquisition of ultrasonic waves, simultaneously replacing the original voice interaction detection steps, simplifying the operation, improving detection efficiency, and making the detection process intelligent. First, the acquired ultrasonic waves are filtered and pre-processed to remove random abnormal reflection signals. Since the actual installation of the ultrasonic transmitting module creates gaps between the casing and the module, these gaps will inevitably generate abnormal ultrasonic reflection signals, affecting the accuracy of the subsequent ultrasonic sensing algorithm in detecting human activity. Therefore, during detection, these abnormal reflection peak signals are recorded simultaneously, and the original abnormal peak data is used in the ultrasonic sensing algorithm for compensation, improving the accuracy of the ultrasonic sensing algorithm. This reduces the impact of the environment or the installation of components of the voice equipment on the testing, improves the accuracy of the testing, and enhances the testing efficiency of voice function testing in the production process.

[0089] Combination Figure 5 As shown, this disclosure provides an apparatus 200 for production testing of voice devices, including a transmitting module 501, a data acquisition module 502, a noise reduction module 503, and a determining module 504. The transmitting module 501 is configured to transmit generated ultrasonic waves upon receiving a coded sound wave trigger command. The data acquisition module 502 is configured to simultaneously acquire the reflected ultrasonic wave signal at the moment the generated ultrasonic wave is transmitted. The noise reduction module 503 is configured to process the acquired ultrasonic wave signal to remove noise signals, obtaining a noise-reduced ultrasonic wave signal. The determining module 504 is configured to determine whether the voice module supports an ultrasonic sensing algorithm based on the sound pressure level value in the noise-reduced ultrasonic wave signal.

[0090] The apparatus for production testing of voice devices provided in this disclosure algorithmizes and programs the process of determining whether a voice module supports the ultrasonic sensing algorithm. Detection of the voice module's support for the ultrasonic sensing algorithm is triggered simply by detecting the coded sound wave trigger command, eliminating the need for a dedicated detection station on the production line and reducing production costs. It also eliminates the need for cumbersome operations by measurement personnel; the program controls the emission and acquisition of ultrasonic waves, simultaneously replacing the original voice interaction detection steps, simplifying operations, improving detection efficiency, and making the detection process intelligent. Furthermore, since noise signals in the ultrasonic signals have been removed, and the accuracy of detection is improved by determining whether the voice module supports the ultrasonic sensing algorithm based on the sound pressure level value of the denoised ultrasonic signal. Furthermore, the embodiments disclosed herein can not only determine whether the ultrasonic sensing algorithm is compatible with different models, but also determine whether the voice interaction function of the voice module itself is normal. Since the working principle of the sensing algorithm in the ultrasonic band is the same as that in the audible band, and the requirements for acoustic devices are also the same, once the voice device is detected to meet the sound pressure requirements of the ultrasonic band, it will necessarily meet the acoustic performance requirements of the device for voice interaction. Therefore, there is no need to conduct additional special tests for the passability of voice interaction, which also improves the testing efficiency of voice function detection in the production process.

[0091] Combination Figure 6 As shown in the figure, this disclosure provides an apparatus 300 for voice device production testing, including a processor 600 and a memory 601. Optionally, the apparatus may further include a communication interface 602 and a bus 603. The processor 600, communication interface 602, and memory 601 can communicate with each other via the bus 603. The communication interface 602 can be used for information transmission. The processor 600 can call logical instructions in the memory 601 to execute the method for voice device production testing described in the above embodiment.

[0092] Furthermore, the logic instructions in the aforementioned memory 601 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0093] The memory 601, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 600 executes functional applications and data processing by running the program instructions / modules stored in the memory 601, thereby implementing the method for voice device production testing described in the above embodiments.

[0094] The memory 601 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 601 may include high-speed random access memory and may also include non-volatile memory.

[0095] Combination Figure 7 As shown, this disclosure provides a voice device 100, including a voice device body and the aforementioned apparatus 200 (300) for voice device production testing. The apparatus 200 (300) for voice device production testing is installed on the voice device body. The installation relationship described herein is not limited to placement inside the voice device, but also includes installation connections with other components of the voice device, including but not limited to physical connections, electrical connections, or signal transmission connections. Those skilled in the art will understand that the apparatus 200 (300) for voice device production testing can be adapted to feasible voice device bodies to achieve other feasible embodiments.

[0096] This disclosure provides a computer-readable storage medium storing computer-executable instructions configured to perform the above-described method for production testing of voice devices.

[0097] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0098] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, including: a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media capable of storing program code; it can also be a transient storage medium.

[0099] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0100] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0101] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0102] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for production testing of a voice device, characterized by, The voice device comprises a voice module, an ultrasonic wave emitting module for generating and emitting coded ultrasonic wave signals, and an ultrasonic wave receiving module for collecting ultrasonic wave signals; the method comprises: emitting the generated ultrasonic wave in the case of listening to a coded sound wave trigger instruction; synchronously collecting the reflected ultrasonic wave signals at the moment of emitting the generated ultrasonic wave; processing the collected ultrasonic wave signals to remove noise signals and obtaining denoised ultrasonic wave signals; determining whether the voice module supports an ultrasonic wave perception algorithm according to the sound pressure level values in the denoised ultrasonic wave signals; wherein the processing of the collected ultrasonic wave signals to remove noise signals and obtaining denoised ultrasonic wave signals comprises: filtering and preprocessing the collected ultrasonic wave signals to remove random abnormal reflection signals and obtaining denoised ultrasonic wave signals; recording and storing abnormal reflection peak signals in the denoised ultrasonic wave signals to compensate for the abnormal reflection peak signals in the denoised ultrasonic wave signals; the compensation for the abnormal reflection peak signals in the denoised ultrasonic wave signals comprises: replacing the peak values of the sampling points as the abnormal reflection peak signals with zero to obtain denoised ultrasonic wave signals.

2. The method of claim 1, wherein, The emission of the generated ultrasonic wave comprises: emitting the generated ultrasonic wave signals in a sinusoidal signal format multiple times, and the emission time length of each time is a first time length.

3. The method of claim 1, wherein, The filtering and preprocessing of the collected ultrasonic wave signals to remove random abnormal reflection signals and obtaining denoised ultrasonic wave signals comprises: band-pass filtering the collected ultrasonic wave signals to obtain band-pass filtered ultrasonic wave signals; using two band-pass filtered ultrasonic wave signals to perform consistency filtering on each single band-pass filtered ultrasonic wave signal to remove random abnormal reflection signals on the single band-pass filtered ultrasonic wave signal and obtain denoised ultrasonic wave signals.

4. The method of claim 1, wherein, The recording and storing of the abnormal reflection peak signals in the denoised ultrasonic wave signals comprise: calculating the average amplitude of the overall signals of the denoised ultrasonic wave signals; individually recording and storing abnormal reflection peak signals in the denoised ultrasonic wave signals that are greater than a set multiple of the average amplitude.

5. The method according to any one of claims 2 to 4, characterized in that, The determination of whether the voice module supports an ultrasonic wave perception algorithm according to the sound pressure level values in the denoised ultrasonic wave signals comprises: calculating the sound pressure level values in the denoised ultrasonic wave signals; in the case that all the sound pressure level values of the denoised ultrasonic wave signals are greater than or equal to a standard level value, determining that the voice module supports the ultrasonic wave perception algorithm; or in the case that there is a denoised ultrasonic wave signal whose sound pressure level value is less than the standard level value, determining that the voice module does not support the ultrasonic wave perception algorithm.

6. An apparatus for production testing of a voice device, characterized by The voice device comprises a voice module, an ultrasonic wave emitting module for generating and emitting coded ultrasonic wave signals, and an ultrasonic wave receiving module for collecting ultrasonic wave signals; the device comprises: an emitting module configured to emit the generated ultrasonic wave in the case of listening to a coded sound wave trigger instruction; a collecting module configured to synchronously collect the reflected ultrasonic wave signals at the moment of emitting the generated ultrasonic wave; a denoising module configured to process the collected ultrasonic wave signals to remove noise signals and obtain denoised ultrasonic wave signals; The determining module is configured to determine whether the voice module supports the ultrasonic sensing algorithm according to the sound pressure level value in the de-noised ultrasonic signal. The processing of the collected ultrasonic signal to remove the noise signal and obtain the de-noised ultrasonic signal comprises: filtering and preprocessing the collected ultrasonic signal to remove random abnormal reflection signals and obtain the de-noised ultrasonic signal; and recording and storing abnormal reflection peak signals in the de-noised ultrasonic signal to compensate for the abnormal reflection peak signals in the de-noised ultrasonic signal. The compensation of the abnormal reflection peak signals in the de-noised ultrasonic signal comprises: replacing the peak value of the sampling point as the abnormal reflection peak signal with zero to obtain the de-noised ultrasonic signal.

7. An apparatus for voice device production testing, comprising a processor and a memory having stored therein program instructions, the apparatus characterized by: The processor is configured to execute the method for production testing of a voice device as claimed in any one of claims 1 to 5 when the program instructions are run.

8. A voice device, characterized by The method comprises: The voice device body comprises: a voice module, an ultrasonic emission module for generating and emitting coded ultrasonic signals, and an ultrasonic receiving module for collecting ultrasonic signals. The device for production testing of a voice device as claimed in claim 6 or 7 is installed in the voice device body.

9. A storage medium storing program instructions, characterized in that, The program instructions, when executed, perform the method for production testing of a voice device as claimed in any one of claims 1 to 5.

Images