Quality evaluation method and device, computer equipment and readable storage medium

Abstract

The invention relates to a quality evaluation method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring a sound signal acquired by a sound acquisition device based on a preset frequency during operation of a to-be-tested device; the preset frequency is associated with the auditory frequency of the human ear, a preset distance exists between the sound collection device and the to-be-tested device, and the preset distance is associated with the distance between the to-be-tested device and the human ear of the user when the user uses the to-be-tested device; preprocessing the sound signal to obtain a preprocessed sound signal; and determining a quality evaluation result based on the preprocessed sound signal. On the basis of the distance between the to-be-tested device and the ear of the user, the sound signal within the auditory frequency range of the ear is collected, the sound signal heard by the user when the user uses the to-be-tested device can be obtained, the sound signal better conforms to the real acoustic characteristics actually reaching the ear, quality evaluation is carried out on the basis of the sound signal, and the user experience is improved. The equipment with better user experience can be screened out, and the judgment standard of quality evaluation is improved.

Description

Technical Field

[0001] This application relates to the field of quality testing technology, and in particular to a quality assessment method, apparatus, computer equipment, and computer-readable storage medium. Background Technology

[0002] With the development of the manufacturing industry, users' requirements for the quality of home appliances are increasing. Sound signals are an important indicator for evaluating the quality of home appliances. Home appliances are usually evaluated for quality based on the sound signals when running under no-load conditions. Based on these sound signals, defective products with faults and qualified products without faults can be identified. However, these sound signals can only control the product quality to a minimum standard and cannot further distinguish high-quality products that can improve the user experience. Summary of the Invention

[0003] Therefore, it is necessary to provide a quality assessment method, apparatus, computer equipment, computer-readable storage medium, and computer program product to address the aforementioned technical problems.

[0004] In a first aspect, this application provides a quality assessment method, the method comprising:

[0005] The sound acquisition device acquires the sound signal of the device under test during operation based on a preset frequency; the preset frequency is related to the human hearing frequency; there is a preset distance between the sound acquisition device and the device under test; the preset distance is related to the distance between the device under test and the user's ear when the user uses the device under test.

[0006] The sound signal is preprocessed to obtain the preprocessed sound signal;

[0007] The quality assessment result is determined based on the preprocessed sound signal.

[0008] In one embodiment, determining the quality assessment result based on the preprocessed audio signal includes:

[0009] Feature extraction is performed on the preprocessed sound signal to obtain multiple first acoustic features;

[0010] Determine the score for each of the first acoustic features;

[0011] The quality score of the device under test is obtained by weighted summing of the scores corresponding to all the first acoustic features.

[0012] The quality assessment result is determined based on the quality score.

[0013] In one embodiment, the plurality of first acoustic features include essential features and supplementary features;

[0014] The feature extraction of the preprocessed sound signal yields multiple first acoustic features, including:

[0015] Feature extraction is performed on the sound signal to obtain the necessary features and the supplementary features;

[0016] The essential features include the dominant frequency, harmonic amplitude ratio, and spectral centroid, and the supplementary features include at least one of the Mel frequency cepstral coefficient, spectral roll-off point, spectral flux, and zero-crossing rate.

[0017] In one embodiment, determining the score for each of the first acoustic features includes:

[0018] Acquire multiple second acoustic features of qualified equipment, the second acoustic features corresponding to the first acoustic features;

[0019] Calculate the first similarity value between the first acoustic feature and the corresponding second acoustic feature, and use the first similarity value as the score of the first acoustic feature.

[0020] In one embodiment, determining the quality assessment result based on the quality score includes:

[0021] If the quality score is greater than or equal to the first preset score, the quality assessment result is determined to be qualified;

[0022] If the quality score is less than the second preset score, the quality assessment result is determined to be unqualified.

[0023] If the quality score is greater than or equal to the second preset score and less than the first preset score, the sound signal of the device under test is re-acquired and the quality score is obtained. If the quality score is less than the first preset score, the quality assessment result is determined to be unqualified.

[0024] In one embodiment, the device under test includes a shaver, and if the quality assessment result is unsatisfactory, the method further includes:

[0025] Acquire multiple third acoustic features of shavers with multiple fault types; the fault types include motor wear, blade imbalance, and bearing defects; the third acoustic features correspond to the first acoustic features;

[0026] Obtain a second similarity value between each of the first acoustic features of the shaver under test and the third acoustic feature of the faulty shaver;

[0027] The fault type corresponding to the largest of the multiple second similarity values ​​is determined as the fault type of the device under test.

[0028] In one embodiment, when the motor of the device under test includes a brushed DC motor, the step of acquiring the sound signal of the device under test during operation, acquired by the sound acquisition device based on a preset frequency, includes:

[0029] The sound acquisition device acquires the sound signal of the device under test during operation within a preset duration based on a preset frequency; the preset duration is longer than multiple rotation cycles of the brushed DC motor.

[0030] Secondly, this application also provides a quality assessment device, the device comprising:

[0031] The data acquisition module is used to acquire the sound signal of the device under test during operation, which is acquired by the sound acquisition device based on a preset frequency; the preset frequency is related to the human hearing frequency, and there is a preset distance between the sound acquisition device and the device under test, which is related to the distance between the device under test and the user's ear when the user uses the device under test;

[0032] The preprocessing module is used to preprocess the sound signal to obtain the preprocessed sound signal;

[0033] The quality assessment module is used to determine the quality assessment result based on the preprocessed sound signal.

[0034] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0035] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0036] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method.

[0037] The aforementioned quality assessment methods, devices, computer equipment, computer-readable storage media, and computer program products collect sound signals within the human ear's hearing frequency range based on the distance between the device under test and the user's ear. This allows the acquisition of the sound signals heard by the user when using the device under test, which more closely resemble the actual acoustic characteristics reaching the human ear. Quality assessment based on these sound signals can filter out devices that provide a better user experience and improve the criteria for quality assessment. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a diagram illustrating the application environment of a quality assessment method in one embodiment;

[0040] Figure 2 This is a flowchart illustrating a quality assessment method in one embodiment;

[0041] Figure 3 This is a flowchart illustrating the quality assessment method in another embodiment;

[0042] Figure 4 This is a flowchart illustrating the quality assessment method in another embodiment;

[0043] Figure 5 This is a flowchart illustrating the quality assessment method in another embodiment.

[0044] Figure 6 This is a structural block diagram of a quality assessment device in one embodiment;

[0045] Figure 7 This is a structural block diagram of the quality assessment device in another embodiment;

[0046] Figure 8 This is an internal structural diagram of a computer device in one embodiment.

[0047] Figure label:

[0048] 102 - Data acquisition module; 104 - Preprocessing module; 106 - Quality assessment module; 108 - Fault detection module. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0051] In one exemplary embodiment, such as Figure 1 As shown, a quality assessment method is provided, including the following steps S102 to S106, wherein:

[0052] Step S102: Acquire the sound signal of the device under test during operation based on the preset frequency collected by the sound acquisition device. The preset frequency is related to the human hearing frequency. There is a preset distance between the sound acquisition device and the device under test. The preset distance is related to the distance between the device under test and the user's ear when the user uses the device under test.

[0053] The preset frequency is correlated with the human hearing frequency, meaning it can be determined based on the human hearing frequency. The human hearing frequency range is 20 Hz to 20 kHz. According to the Nyquist-Shannon sampling theorem, the preset frequency should be at least twice the highest frequency audible to the human ear. Therefore, the preset frequency could be 40 kHz. To obtain a sound signal that closely approximates human hearing, the preset frequency could be 44.1 kHz. The preset frequency can also be other frequencies with larger values; no restrictions are placed here. By correlating the preset frequency with the human hearing frequency, sound signals covering the human hearing frequency range can be collected.

[0054] It is understandable that sound signals received from different locations differ, therefore the location for collecting sound signals is crucial. To more accurately acquire the sound signals heard by the user when using the device, a preset distance is correlated with the distance between the device and the user's ear when using the device. The preset distance can be determined by the distance between the user's ear and the device when using it. For example, if the device under test is a razor, the preset distance can be determined by the distance between the razor and the user's ear when using the razor, such as a preset distance of 10 centimeters. More specifically, it can be determined by obtaining the average distance between the razor and the user's ear when a large number of users use the device; no limitation is imposed here.

[0055] The preset distance can be the distance between the sound acquisition device and the device under test. The sound acquisition device acquires sound signals based on the preset frequency and preset distance, which can obtain sound signals that are closer to what the user hears when using the device under test.

[0056] Optionally, the sound acquisition device can be a linear array of multiple microphones, including 2 to 4 microphones. Sound signal acquisition can be conducted in an anechoic or semi-anechoic chamber with background noise below 40 decibels to reduce the impact of ambient noise on the acquired sound signal. During sound signal acquisition, the device under test can operate under no-load conditions at its rated voltage, ensuring the motor operates at its nominal operating state and isolating load noise.

[0057] Step S104: Preprocess the sound signal to obtain the preprocessed sound signal.

[0058] Preprocessing can include denoising, filtering, normalization, etc., and is not limited here.

[0059] For example, spectral subtraction can be used to remove ambient noise from the audio signal at the moment of startup. Bandpass filtering can be used to remove power frequency interference and high-frequency noise. The amplitude of the filtered signal can also be normalized to the range of [-1, 1] to eliminate amplitude deviations caused by differences in microphone distance or gain.

[0060] The denoising and filtering methods in the above examples are merely illustrative and not intended to limit this application. The specific methods used can be replaced according to requirements. For example, wavelet denoising can be used when there is a lot of non-stationary noise. Adaptive filtering can be used in scenarios with changing noise characteristics. No specific preprocessing methods are limited here.

[0061] Step S106: Determine the quality assessment result based on the preprocessed sound signal.

[0062] Optionally, the quality assessment result can be either qualified or unqualified. Understandably, traditional quality assessment methods focus on whether the equipment is faulty. More specifically, traditional methods focus on measuring the sound source itself, without considering the actual sound received by the user's ears. Products identified as qualified through this sound signal identification are those without any hard defects. However, these qualified products may negatively impact the user experience due to a rough tone or the presence of annoying high-frequency feedback. In other words, traditional quality assessment methods cannot filter out products with a better user experience.

[0063] The aforementioned quality assessment method, based on the distance between the device under test and the user's ear, collects sound signals within the range of human hearing frequencies. This allows the acquisition of the sound signals heard by the user when using the device under test. These sound signals are more consistent with the actual acoustic characteristics reaching the human ear. Quality assessment based on these sound signals can filter out devices that provide a better user experience and improve the judgment criteria for quality assessment.

[0064] In one embodiment, when the motor of the device under test includes a brushed DC motor, step S102: acquiring the sound signal of the device under test during operation, collected by the sound acquisition device based on a preset frequency, includes:

[0065] The sound acquisition device acquires the sound signal of the device under test during operation within a preset duration based on a preset frequency. The preset duration is longer than multiple rotation cycles of the brushed DC motor.

[0066] It is understandable that the initial position of a brushed DC motor is uncertain, and there is a large difference between the early and later operating data. By limiting the preset time to multiple rotation cycles of the brushed DC motor, it can be ensured that the sound signal after stable operation is collected.

[0067] For example, if the motor rotates at 50 Hz and one rotation cycle takes 20 milliseconds, and multiple rotation cycles can be at least 3, then the preset duration should be greater than 60 milliseconds. Furthermore, to ensure that the sound acquisition device can acquire sound signals from multiple complete rotation cycles, as well as sound signals after the device has been running smoothly, the preset duration can be increased to the order of seconds. The specific duration can be determined based on the time required for the device to run smoothly, and is not limited here.

[0068] In one embodiment, step S106: determine the quality assessment result based on the preprocessed audio signal, see [reference]. Figure 2 The process includes steps S1062 to S1068, wherein:

[0069] Step S1062: Extract features from the preprocessed sound signal to obtain multiple first acoustic features.

[0070] Among them, multiple primary acoustic features can be multi-dimensional acoustic features with different focuses. Multi-dimensional acoustic features can comprehensively depict sound information, providing a foundation for subsequent accurate evaluation of devices with a better user experience.

[0071] Step S1064: Determine the score for each first acoustic feature.

[0072] Understandably, by obtaining a score for each primary acoustic feature, the performance of the device under test in various dimensions can be clearly defined.

[0073] Step S1066: Perform a weighted summation of the scores corresponding to all first acoustic features to obtain the quality score of the device under test.

[0074] The sum of the weights of all first acoustic features is 1. It is understandable that if the scores corresponding to a first acoustic feature are not on the same dimension as the scores corresponding to other first acoustic features, all first acoustic features can be standardized to ensure that all scores are within the same dimension before weighted summation. For example, all scores can be within the range of 0-1, 0-10, or 0-100; no restrictions are imposed here.

[0075] By integrating the scores of multiple acoustic features into a single overall score, the complexity of subsequent quality assessments based on the score can be reduced. Furthermore, by adjusting the weights, the weight of the scores corresponding to the primary acoustic features related to device reliability and user experience can be increased, allowing for flexible adjustments to the emphasis on qualified products.

[0076] Step S1068: Determine the quality assessment result based on the quality score.

[0077] An objective evaluation standard can be established by determining the score of the first acoustic feature, determining the quality score based on the score of the first acoustic feature, and determining the quality assessment result based on the quality score.

[0078] In one embodiment, the plurality of first acoustic features include essential features and supplementary features.

[0079] Step S1062: Extract features from the preprocessed sound signal to obtain multiple first acoustic features, including:

[0080] Feature extraction is performed on the sound signal to obtain necessary and supplementary features.

[0081] Essential features include the dominant frequency, harmonic amplitude ratio, and spectral centroid, while supplementary features include at least one of the following: Mel-Frequency Cepstral Coefficients (MFCC), spectral roll-off point, spectral flux, and zero-crossing rate.

[0082] The essential features mainly include three, while the supplementary features can be one or more.

[0083] For example, multiple first acoustic features may include the dominant frequency, harmonic amplitude ratio, spectral centroid, and Mel frequency cepstral coefficient.

[0084] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, and spectral roll-off point.

[0085] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, and spectral flux.

[0086] For example, the plurality of first acoustic features may further include the dominant frequency, harmonic amplitude ratio, spectral centroid, and zero-crossing rate. For example, the plurality of first acoustic features may further include the dominant frequency, harmonic amplitude ratio, spectral centroid, Mel frequency cepstral coefficient, and spectral roll-off point.

[0087] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, Mel frequency cepstral coefficient, and spectral flux.

[0088] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, Mel frequency cepstral coefficient, and zero-crossing rate.

[0089] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, spectral roll-off point, and spectral flux.

[0090] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, spectral roll-off point, and zero-crossing rate.

[0091] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, spectral flux, and zero-crossing rate.

[0092] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, Mel frequency cepstral coefficient, spectral roll-off point, and spectral flux.

[0093] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, spectral roll-off point, spectral flux, and zero-crossing rate.

[0094] For example, the primary acoustic features may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, Mel frequency cepstral coefficient, spectral roll-off point, spectral flux, and zero-crossing rate.

[0095] No restrictions are imposed on the multiple primary acoustic features here.

[0096] Optionally, in addition to requiring feature extraction from the audio signal, preprocessing may further include frame division of the acquired audio signal. That is, after performing the preprocessing steps described in the foregoing embodiments, the audio signal acquired based on a preset duration is divided into smaller units, and feature extraction can be performed based on these divided units. For example, if the preset duration is 5 seconds and the frame length is 40 milliseconds, the acquired 5-second audio signal is divided into 40-millisecond units, and the frame movement speed can be 20 milliseconds per frame, without limitation.

[0097] Understandably, the essential features are all frequency domain signals. Therefore, a Fast Fourier Transform (FFT) can be performed on the audio signal of each unit to obtain the spectrum of each unit. More specifically, a Hanning window can be used to smoothly attenuate the two ends of the frame to near zero before performing an FFT. The FFT can have 1024 points, and the FFT outputs a linear spectrum, which directly reflects the energy distribution of the signal at different frequency components.

[0098] Optionally, the frequency corresponding to the maximum value of the spectral amplitude can be determined as the main frequency within the fundamental frequency range of the motor of the device under test.

[0099] Optionally, the amplitude value of the second harmonic of the main frequency is extracted, and the amplitude value of the second harmonic is compared with the amplitude value of the fundamental frequency to obtain the harmonic amplitude ratio. The harmonic amplitude ratio may also include the ratio of the amplitude value of the third harmonic of the main frequency to the amplitude value of the fundamental frequency, which is not limited here.

[0100] Alternatively, the spectral centroid can be obtained by calculating the weighted average of the spectral frequencies, which will not be elaborated here.

[0101] Understandably, abnormal main frequency usually points to fundamental problems such as unstable motor drive or sudden load changes. An increase in harmonic amplitude ratio usually indicates problems such as bearing wear or gear defects. An upward shift of the spectral centroid usually indicates problems such as accelerated component wear or poor lubrication. In other words, the essential features mainly detect hardware faults corresponding to traditional pass / fail standards. Based on these essential features, faulty equipment can be screened out.

[0102] Optionally, the core of Mel frequency cepstral coefficients is to simulate the nonlinear perception of sound frequencies by the human ear, mapping linear sound wave frequencies to a Mel frequency scale that conforms to human hearing, and then extracting parameters that characterize the essential features of the sound. For example, the power spectrum reflecting the energy magnitude of each frequency component can be obtained based on the output of the FFT, and then mapped to the Mel frequency scale using a Mel filter bank. Taking the logarithm of the output energy of each Mel filter simulates the logarithmic loudness perception characteristic of the human ear. Performing a Discrete Cosine Transform (DTC) on the logarithmic energy transforms the signal from the Mel frequency domain to the cepstral domain, and the resulting coefficients are the Mel frequency cepstral coefficients. The first 12 or 13 coefficients can be selected as the primary features.

[0103] Optionally, the spectral roll-off point represents the frequency at which the accumulated spectral energy reaches a preset proportion of the total energy. The spectral roll-off point can be determined by calculating the cumulative spectral energy curve and finding the frequency corresponding to the preset proportion.

[0104] Optionally, the spectral flux can be obtained by calculating the norm of the difference in spectral amplitude between two adjacent frames, which will not be elaborated here.

[0105] Optionally, the zero-crossing rate represents how frequently a signal crosses zero, and can be obtained by directly counting the time-domain waveform.

[0106] The aforementioned features can also be obtained through Short-Time Fourier Transform (STFT) and Wavelet Transform (WT), which will not be elaborated here.

[0107] Understandably, the Mel frequency cepstral coefficients mimic human hearing, and this characteristic is highly correlated with users' evaluation of product quality and comfort. Taking a shaver as an example, the roll-off point can be used to measure the proportion of high-frequency energy. A roll-off point that is too low may make users feel that the shaver is not powerful enough, while a roll-off point that is too high may cause users auditory discomfort. Spectral flux can quantify the stability of sound; if the spectral flux is too high, it may cause users to experience unpleasant sensations such as pulling or shaving. Zero-crossing rate can reflect the high-frequency components in the sound signal; a zero-crossing rate that is too high may produce noise that affects auditory comfort. Therefore, supplementary features are mainly used to evaluate the user's experience.

[0108] In one embodiment, step S1064: determine the score for each first acoustic feature, see [reference]. Figure 3 This includes steps S10642 and S10644, wherein:

[0109] Step S10642: Obtain multiple second acoustic features of the qualified equipment, the second acoustic features corresponding to the first acoustic features.

[0110] Among these, qualified equipment can be screened for fault-free products through traditional quality assessment methods, and then further selected based on user experience. The second acoustic feature corresponds to the first acoustic feature, meaning it includes the same features as the first. For example, the first acoustic feature includes the dominant frequency, harmonic amplitude ratio, spectral centroid, and Mel-frequency cepstral coefficients; the second acoustic feature also includes the dominant frequency, harmonic amplitude ratio, spectral centroid, and Mel-frequency cepstral coefficients. The difference is that the first acoustic feature is extracted by collecting the sound signal from the device under test, while the second acoustic feature is extracted by collecting the sound signal from qualified equipment. To ensure consistency, the feature extraction method for the second acoustic feature is the same as that for the corresponding first acoustic feature.

[0111] Step S10644: Calculate the first similarity value between the first acoustic feature and the corresponding second acoustic feature, and use the first similarity value as the score of the first acoustic feature.

[0112] Understandably, feature extraction is performed based on the units after frame division, and a first acoustic feature can be extracted within each unit. The first acoustic features extracted from all units are combined into a first feature vector, and the second acoustic features are combined into a second feature vector using the same method. The cosine similarity between the first and second feature vectors can be calculated, and the cosine similarity value is used as the score for the first acoustic feature.

[0113] For example, the dominant frequencies of all units in a sound signal of a preset duration collected by the device under test can be obtained and used to form a first dominant frequency vector. Based on the dominant frequencies of all units in the sound signal of a qualified device, a second dominant frequency vector is formed, and the cosine similarity value between the first and second dominant frequency vectors is used as the score for the dominant frequency. Other first acoustic features can be derived similarly and will not be elaborated here.

[0114] By calculating the first similarity value, the distance between the product under test and the qualified product can be quantified. Furthermore, the similarity value itself is a normalized quantitative indicator, eliminating the need for additional normalization operations and reducing computational costs.

[0115] In another embodiment, step S106: determining the quality assessment result based on the preprocessed audio signal may further include:

[0116] Feature extraction is performed on the preprocessed sound signal to obtain multiple first acoustic features, which include necessary features and supplementary features.

[0117] Essential features include the dominant frequency, harmonic amplitude ratio, and spectral centroid, while supplementary features include at least one of the following: Mel frequency cepstral coefficient, spectral roll-off point, spectral flux, and zero-crossing rate.

[0118] Acquire multiple second acoustic features of qualified equipment, which correspond to the first acoustic features.

[0119] The third feature vector is composed of multiple first acoustic features, and the fourth feature vector is composed of multiple second acoustic features.

[0120] For example, multiple first acoustic features include the dominant frequency, harmonic amplitude ratio, spectral centroid, and spectral roll-off point. The corresponding third feature vector may include the dominant frequency, harmonic amplitude ratio, spectral centroid, and spectral roll-off point. The fourth feature vector follows the same pattern. As described in the above embodiments, before extracting the first acoustic features, frame division is performed. Taking the dominant frequency as an example, a dominant frequency can be extracted in each unit or in each frame. The dominant frequency in the third feature vector can be the average of all extracted dominant frequencies. The harmonic amplitude ratio, spectral centroid, and spectral roll-off point, and so on, will not be elaborated further.

[0121] The cosine similarity between the third and fourth feature vectors is used as the quality score. The higher the similarity value, the closer the device under test is to a qualified device, and the greater the probability that the device under test is a qualified device.

[0122] In one embodiment, determining the quality assessment result based on the quality score includes:

[0123] If the quality score is greater than or equal to the first preset score, the quality assessment result is determined to be qualified.

[0124] If the quality score is lower than the second preset score, the quality assessment result is determined to be unqualified.

[0125] If the quality score is greater than or equal to the second preset score but less than the first preset score, the sound signal of the device under test is re-acquired and the quality score is obtained. If the quality score is less than the first preset score, the quality assessment result is determined to be unqualified.

[0126] That is, if the quality score is greater than or equal to the second preset score and less than the first preset score, repeat steps S102 to S106. In step S106, if the quality score obtained the second time is still less than the first preset score, the quality assessment result of the device under test is determined to be unqualified.

[0127] The first preset score is greater than the second preset score. The first and second preset scores can be determined based on needs, experience, etc., and are not restricted here.

[0128] By applying the above restrictions, an objective quality assessment standard can be established, and the devices under test that fall within the ambiguous range between the first and second preset scores can be reassessed. This avoids inaccurate judgment of device quality due to measurement errors in sound signals and improves the accuracy of qualified device testing.

[0129] In another embodiment, step S106: determining the quality assessment result based on the preprocessed audio signal may further include:

[0130] The preprocessed audio signal is input into the trained quality assessment model, and the quality assessment result is output.

[0131] The quality assessment model can be a traditional classification model, such as a support vector machine, or a deep learning model, such as a neural network. No specific model is restricted here.

[0132] For example, when the quality assessment model is a support vector machine, the preprocessed sound signal of the qualified equipment can be input into the quality assessment model for training. After the training reaches the preset target, the trained quality assessment model is obtained. The preprocessed sound signal of the device under test is input into the trained quality assessment model. If the preprocessed sound signal of the device under test is outside the boundary of the preprocessed sound signal of the qualified equipment, the quality assessment result of the device under test is determined to be unqualified.

[0133] The quality assessment model learns from a large number of samples and can obtain complex, non-linear relationships between features. Based on these relationships, quality assessment can be performed more accurately.

[0134] In one embodiment, the device under test includes a razor, and in the event that the quality assessment result is unsatisfactory, see [reference needed]. Figure 4 The method further includes step S108, wherein:

[0135] Step S108: If the quality assessment result is unqualified, determine the fault type of the device under test based on the first acoustic feature.

[0136] See Figure 5 Step S108 includes steps S1082 to S1086, wherein:

[0137] Step S1082: Obtain multiple third acoustic features of malfunctioning shavers with multiple fault types, including motor wear, blade imbalance, and bearing defects; the third acoustic features correspond to the first acoustic features.

[0138] That is, the third acoustic feature includes the same feature types as the first acoustic feature. Referring to the relationship between the second and first acoustic features, in this embodiment, the third acoustic feature is extracted from the sound signal of the faulty shaver, while the first acoustic feature is extracted from the sound signal of the shaver under test. Multiple third acoustic features are acquired for shavers with multiple fault types, namely, multiple third acoustic features for shavers with motor wear, multiple third acoustic features for shavers with blade imbalance, and multiple third acoustic features for shavers with bearing defects.

[0139] Step S1084: Obtain the second similarity value of each first acoustic feature of the shaver under test and the third acoustic feature of the faulty shaver.

[0140] The fifth feature vector is formed based on the first acoustic features of the shaver under test, and the sixth feature vector is formed based on the third acoustic features of the faulty shaver. It can be understood that since the faulty shaver has multiple faults, different sixth feature vectors can be obtained based on different faults.

[0141] For example, the fifth feature vector may include the dominant frequency, harmonic amplitude ratio, spectral centroid, and spectral roll-off point, and the corresponding sixth feature vector may also include the dominant frequency, harmonic amplitude ratio, spectral centroid, and spectral roll-off point.

[0142] The process of calculating the second similarity value between the fifth and sixth eigenvectors will not be elaborated here.

[0143] Step S1086: Determine the fault type corresponding to the largest of the multiple second similarity values ​​as the fault type of the device under test.

[0144] It is understandable that the above-mentioned faults may exist when the quality inspection of the shaver under test fails. By determining the similarity, the most likely fault type can be identified, which will help staff quickly locate the fault in the shaver under test.

[0145] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0146] Based on the same inventive concept, this application also provides a quality assessment apparatus for implementing the quality assessment method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more quality assessment apparatus embodiments provided below can be found in the limitations of the quality assessment method described above, and will not be repeated here.

[0147] In one exemplary embodiment, such as Figure 6 As shown, this application also provides a quality assessment device, including a data acquisition module 102, a preprocessing module 104, and a quality assessment module 106, wherein:

[0148] The data acquisition module 102 is used to acquire the sound signal of the device under test during operation based on the sound acquisition device at a preset frequency. The preset frequency is related to the human hearing frequency. There is a preset distance between the sound acquisition device and the device under test. The preset distance is related to the distance between the device under test and the user's ear when the user uses the device under test.

[0149] The preprocessing module 104 is used to preprocess the sound signal to obtain the preprocessed sound signal.

[0150] The quality assessment module 106 is used to determine the quality assessment result based on the preprocessed sound signal.

[0151] The aforementioned quality assessment device collects sound signals within the human ear's hearing frequency range based on the distance between the device under test and the user's ear. This allows the user to obtain the sound signals heard when using the device under test, which are more consistent with the actual acoustic characteristics reaching the human ear. Quality assessment based on these sound signals can filter out devices that provide a better user experience and improve the judgment criteria for quality assessment.

[0152] In one embodiment, such as Figure 7 As shown, the quality assessment device also includes a fault detection module 108. When the device under test is a shaver, the fault detection module 108 is used to determine the fault type of the device under test based on the first acoustic feature when the quality assessment result is unqualified.

[0153] The solution to the problem provided by the quality assessment device in the above embodiments is similar to the solution described in the quality assessment method above. The specific limitations in the embodiments of the quality assessment device can be found in the limitations of the quality assessment method above, and will not be repeated here.

[0154] Each module in the aforementioned quality assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0155] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a quality assessment method.

[0156] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0157] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the various method embodiments.

[0158] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the various method embodiments.

[0159] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the various method embodiments.

[0160] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0163] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A quality assessment method, characterized in that, The method includes: The sound acquisition device acquires the sound signal of the device under test during operation based on a preset frequency; the preset frequency is related to the human hearing frequency; there is a preset distance between the sound acquisition device and the device under test; the preset distance is related to the distance between the device under test and the user's ear when the user uses the device under test. The sound signal is preprocessed to obtain the preprocessed sound signal; The quality assessment result is determined based on the preprocessed sound signal.

2. The method according to claim 1, characterized in that, The determination of the quality assessment result based on the preprocessed sound signal includes: Feature extraction is performed on the preprocessed sound signal to obtain multiple first acoustic features; Determine the score for each of the first acoustic features; The quality score of the device under test is obtained by weighted summing of the scores corresponding to all the first acoustic features. The quality assessment result is determined based on the quality score.

3. The method according to claim 2, characterized in that, The multiple first acoustic features include essential features and supplementary features; The feature extraction of the preprocessed sound signal yields multiple first acoustic features, including: Feature extraction is performed on the sound signal to obtain the necessary features and the supplementary features; The essential features include the dominant frequency, harmonic amplitude ratio, and spectral centroid, and the supplementary features include at least one of the Mel frequency cepstral coefficient, spectral roll-off point, spectral flux, and zero-crossing rate.

4. The method according to claim 2 or 3, characterized in that, The step of determining the score for each of the first acoustic features includes: Acquire multiple second acoustic features of qualified equipment, the second acoustic features corresponding to the first acoustic features; Calculate the first similarity value between the first acoustic feature and the corresponding second acoustic feature, and use the first similarity value as the score of the first acoustic feature.

5. The method according to claim 2 or 3, characterized in that, The process of determining the quality assessment result based on the quality score includes: If the quality score is greater than or equal to the first preset score, the quality assessment result is determined to be qualified; If the quality score is less than the second preset score, the quality assessment result is determined to be unqualified. If the quality score is greater than or equal to the second preset score and less than the first preset score, the sound signal of the device under test is re-acquired and the quality score is obtained. If the quality score is less than the first preset score, the quality assessment result is determined to be unqualified.

6. The method according to claim 5, characterized in that, The device under test includes a shaver, and if the quality assessment result is unsatisfactory, the method further includes: Acquire multiple third acoustic features of shavers with multiple fault types; the fault types include motor wear, blade imbalance, and bearing defects; the third acoustic features correspond to the first acoustic features; Obtain a second similarity value between each of the first acoustic features of the shaver under test and the third acoustic feature of the faulty shaver; The fault type corresponding to the largest of the multiple second similarity values ​​is determined as the fault type of the device under test.

7. The method according to claim 1, characterized in that, When the motor of the device under test includes a brushed DC motor, the acquisition of the sound signal of the device under test during operation, acquired by the sound acquisition device based on a preset frequency, includes: The sound acquisition device acquires the sound signal of the device under test during operation within a preset duration based on a preset frequency; the preset duration is longer than multiple rotation cycles of the brushed DC motor.

8. A quality assessment device, characterized in that, The device includes: The data acquisition module is used to acquire the sound signal of the device under test during operation, which is acquired by the sound acquisition device based on a preset frequency; the preset frequency is related to the human hearing frequency, and there is a preset distance between the sound acquisition device and the device under test, which is related to the distance between the device under test and the user's ear when the user uses the device under test; The preprocessing module is used to preprocess the sound signal to obtain the preprocessed sound signal; The quality assessment module is used to determine the quality assessment result based on the preprocessed sound signal.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images