Smart watch and unlocking method thereof
Through the smartwatch unlocking method of voice signal processing and coordinate verification, the problem of smartwatch lacking locking function and inconvenient password input is solved, and data security and user experience are improved.
Patent Information
- Application Number
- CN202211088308.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-09-07
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2042-09-07
AI Technical Summary
The lack of locking function of existing smart watches makes it difficult to guarantee data security. Due to the small display screen, it is inconvenient to enter passwords, resulting in poor user experience and experience.
By obtaining the user's voice signal, noise filtering and processing are performed, voiceprint recognition is used for unlocking, and the user's coordinates are predicted based on the signal strength range. If the coordinates are within the preset set, the unlocking is successful, ensuring data security and improving users Experience.
Voice unlocking is realized, avoiding the inconvenience of manually entering passwords, improving the user experience, and ensuring data security through coordinate verification, enhancing the security performance of smart watches.
Smart Images

Figure CN115909548B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart watches, and in particular, to a smart watch and an unlocking method thereof. Background Art
[0002] In recent years, with the development of the Internet of Things and edge computing, the construction of "smart outlets" with the core of promoting the intelligence of bank outlets is in full swing. In the banking industry, account managers generally use tablets for communication and sending and receiving messages. Since tablets are not portable, the existing technology has proposed a solution to consider using smart watches for communication and message sending and receiving. However, since commercially available smart watches do not have a locking function, the data security of smart watches cannot be guaranteed after being stolen. Some existing smart watches support password unlocking, but because the display screen of smart watches is small, it is very inconvenient to enter passwords. Therefore, the inconvenience of unlocking smart watches has led to poor user experience and experience, which has become a problem that needs to be solved urgently. Summary of the invention
[0003] The purpose of the embodiments of this article is to provide a smart watch and an unlocking method thereof, so as to enhance the user's sense of use and experience while ensuring data security.
[0004] To achieve the above objectives, on the one hand, an embodiment of the present invention provides a method for unlocking a smart watch, which is applied to the smart watch and includes:
[0005] Acquiring a user's voice signal;
[0006] Filtering out noise in the speech signal to obtain a denoised speech signal;
[0007] Inputting the de-noised speech signal into a matched filter and outputting a processed speech signal;
[0008] Performing a convolution operation on the denoised speech signal and the processed speech signal to obtain a result sequence;
[0009] Determine whether the result data at a specified position in the result sequence is greater than a set threshold;
[0010] If not, stop executing the subsequent steps and the unlocking fails;
[0011] If yes, predicting the coordinates of the user according to the signal strength range at the current location of the user;
[0012] Determining whether the coordinates of the user are within a preset coordinate set;
[0013] If yes, the unlocking is successful;
[0014] If not, the unlocking fails.
[0015] Preferably, filtering out the noise in the speech signal to obtain the denoised speech signal further comprises:
[0016] Inputting the speech signal into a non-recursive finite-length unit impulse response filter to obtain a filtered speech signal;
[0017] Downsampling and upsampling the filtered speech signal in sequence to obtain a sampled speech signal;
[0018] Pre-emphasize the sampled speech signals in sequence to obtain pre-emphasized speech signals;
[0019] Performing a frame operation on the speech signal after the pre-emphasis processing;
[0020] Perform short-time Fourier transform on each frame of speech signal after framing to obtain a spectrum sequence;
[0021] Calculate the logarithmic energy of the spectrum sequence, and perform discrete cosine transform on the logarithmic energy to obtain the Mel frequency cepstrum;
[0022] The Mel-frequency cepstral coefficients are filtered using a digital low-pass filter to obtain the denoised speech signal.
[0023] Preferably, the step of calculating the logarithmic energy of the spectrum sequence further comprises:
[0024] The logarithmic energy of the spectrum sequence is calculated by the following formula:
[0025] S(n)=ln(MELapr(f s,new *n / N)*(|X(n)| 2 ));
[0026] MELapr(f s,new *n / N)=(-2.51*10 -21 )*(f s,new *n / N) 5 +(1.1*10 -16 )*(f s,new *n / N) 4 -(1.81*10 -12 )*(f s,new *n / N) 3 +(1.4*10 -8 )*(f s,new *n / N) 2 -(5.47*10 -5 )*(f s,new *n / N)+0.107;
[0027] Among them, S(n) is the logarithmic energy corresponding to the nth sampling point in the spectrum sequence, X(n) is the frequency corresponding to the nth sampling point in the spectrum sequence, N is the number of sampling points in the spectrum sequence, and f s,new The target sampling rate when downsampling.
[0028] Preferably, the method for determining the set threshold includes:
[0029] Obtaining a speech training signal;
[0030] Filtering out the noise in the training signal by a preset denoising method to obtain a denoised training signal;
[0031] Inputting the denoised training signal into a matched filter and outputting a processed training signal;
[0032] Performing a convolution operation on the denoised training signal and the processed training signal to obtain a training result sequence;
[0033] Get the training result data at the specified position in the training result sequence;
[0034] A set threshold is calculated based on the training result data.
[0035] Preferably, the step of calculating the set threshold value according to the training result data further comprises:
[0036] The set threshold is calculated by the following formula:
[0037]
[0038] Among them, γ is the set threshold, γ α is the preset accuracy value, which is any number greater than 0 and less than or equal to 1. MEa(l) is the denoised training signal, h(l) is the processed training signal, is the convolution operation, is the training result sequence, l=1,…,2L-1, L is the specified position.
[0039] Preferably, the method for determining the signal strength range at the user's current location includes:
[0040] Setting a plurality of signal points, wherein the signal points are used to transmit signals to the smart watch;
[0041] According to the signal strength range of the smart watch corresponding to each signal point, the signal strength range of each signal point corresponding to the user's current location is determined.
[0042] Preferably, predicting the coordinates of the user according to the signal strength range at the current location of the user further comprises:
[0043] Determine the coordinate range of the user according to the signal strength range corresponding to each signal point at the current position of the user and the coordinates of each signal point;
[0044] The coordinates of the user are predicted according to the coordinate range of the user.
[0045] Preferably, determining the coordinate range of the user according to the signal strength range corresponding to each signal point at the current position of the user and the coordinates of each signal point further comprises:
[0046] Determine the distance range between the user's current position and each signal point according to the signal strength range corresponding to each signal point at the user's current position;
[0047] The coordinate range of the user is determined according to the distance range between the current position of the user and each signal point, and the coordinates of each signal point.
[0048] On the other hand, an embodiment of the present invention provides a smart watch, including:
[0049] An acquisition module, used to acquire a user's voice signal;
[0050] A noise removal module, used to filter out noise in the speech signal to obtain a noise-removed speech signal;
[0051] A processing module, used for inputting the de-noised speech signal into a matched filter and outputting a processed speech signal;
[0052] An operation module, used for performing a convolution operation on the denoised speech signal and the processed speech signal to obtain a result sequence;
[0053] A first judgment module, used to judge whether the result data at a specified position in the result sequence is greater than a set threshold;
[0054] If not, stop executing the subsequent steps and the unlocking fails;
[0055] If yes, predicting the coordinates of the user according to the signal strength range at the current location of the user;
[0056] A second determination module, used to determine whether the coordinates of the user are within a preset coordinate set;
[0057] If yes, the unlocking is successful;
[0058] If not, the unlocking fails.
[0059] On the other hand, the embodiments of the present invention further provide a computer device, including a memory, a processor, and a computer program stored in the memory, wherein when the computer program is executed by the processor, the instructions of any one of the above methods are executed.
[0060] On the other hand, the embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor of a computer device, the computer program executes instructions of any one of the above-described methods.
[0061] It can be seen from the technical solutions provided in the above embodiments of this invention that, through the method of the embodiments of this invention, when a bank account manager uses a smart watch, the smart watch can be unlocked by voice, and unlocked by voiceprint recognition, which can eliminate the inconvenience of manually entering a password and improve the experience. At the same time, in order to ensure data security, the coordinates of the user can be determined by the smart watch, and the unlocking can be successful only if the coordinates are within the preset coordinate set.
[0062] In order to make the above and other purposes, features and advantages of this article more obvious and easy to understand, the following specifically cites preferred embodiments and describes them in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] In order to more clearly illustrate the technical solutions in the embodiments of this article or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of this article. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0064] Figure 1 A schematic diagram showing a flow chart of a method for unlocking a smart watch provided in an embodiment of this invention;
[0065] Figure 2 A schematic diagram of a process for filtering noise from a speech signal to obtain a de-noised speech signal is shown in an embodiment of the present invention;
[0066] Figure 3 A schematic diagram of a process for determining a threshold value provided in an embodiment of the present invention is shown;
[0067] Figure 4 A schematic flow chart of a method for determining a signal strength range at a user's current location provided in an embodiment of this document is shown;
[0068] Figure 5 A schematic diagram of a process for predicting the coordinates of a user according to a signal strength range at the user's current location provided by an embodiment of the present invention is shown;
[0069] Figure 6 A schematic diagram of a flow chart for determining a coordinate range of a user according to a signal strength range corresponding to each signal point at a current position of the user and the coordinates of each signal point provided in an embodiment of the present invention is shown;
[0070] Figure 7 A schematic diagram of the module structure of a smart watch provided in an embodiment of this invention is shown;
[0071] Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of this invention is shown.
[0072] Description of the accompanying symbols:
[0073] 100. Get module;
[0074] 200, noise removal module;
[0075] 300, processing module;
[0076] 400, operation module;
[0077] 500, first judgment module;
[0078] 600, second judgment module;
[0079] 702. Computer equipment;
[0080] 704, processor;
[0081] 706. Memory;
[0082] 708, driving mechanism;
[0083] 710, input / output module;
[0084] 712. Input devices;
[0085] 714. Output devices;
[0086] 716. Presentation equipment;
[0087] 718. Graphical user interface;
[0088] 720, network interface;
[0089] 722. Communication link;
[0090] 724. Communication bus. DETAILED DESCRIPTION
[0091] The following will be combined with the drawings in the embodiments of this article to clearly and completely describe the technical solutions in the embodiments of this article. Obviously, the described embodiments are only part of the embodiments of this article, not all of the embodiments. Based on the embodiments of this article, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this article.
[0092] In recent years, with the development of the Internet of Things and edge computing, the construction of "smart outlets" with the core of promoting the intelligence of bank outlets is in full swing. In the banking industry, account managers generally use tablets for communication and sending and receiving messages. Since tablets are not portable, the existing technology has proposed a solution to consider using smart watches for communication and message sending and receiving. However, since commercially available smart watches do not have a locking function, the data security of smart watches cannot be guaranteed after being stolen. Some existing smart watches support password unlocking, but because the display screen of smart watches is small, it is very inconvenient to enter passwords. Therefore, the inconvenience of unlocking smart watches has led to poor user experience and experience, which has become a problem that needs to be solved urgently.
[0093] In order to solve the above problems, the embodiments of this document provide a smart watch and an unlocking method thereof, which can improve the user's sense of use and experience while ensuring data security. Figure 1 This is a flowchart of a method for unlocking a smart watch provided in an embodiment of this invention. This specification provides method operation steps as described in the embodiment or flowchart, but more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the order of many steps and does not represent the only execution order. When the actual system or device product is executed, it can be executed in the order of the method shown in the embodiment or the accompanying drawings or in parallel.
[0094] It should be noted that the terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.
[0095] Reference Figure 1 , this article shows a method for unlocking a smart watch, which is applied to the smart watch and includes:
[0096] S101: Acquire a user's voice signal;
[0097] S102: Filter out the noise in the speech signal to obtain a denoised speech signal;
[0098] S103: inputting the de-noised speech signal into a matched filter, and outputting a processed speech signal;
[0099] S104: performing a convolution operation on the denoised speech signal and the processed speech signal to obtain a result sequence;
[0100] S105: Determine whether the result data at a specified position in the result sequence is greater than a set threshold;
[0101] S106: If not, stop executing the subsequent steps and the unlocking fails;
[0102] S107: If yes, predicting the coordinates of the user according to the signal strength range at the current position of the user;
[0103] S108: Determine whether the coordinates of the user are within a preset coordinate set;
[0104] S109: If yes, unlocking is successful;
[0105] S110: If not, the unlocking fails.
[0106] When the user unlocks the smartwatch, he usually says voice commands such as "power on" or "unlock". At this time, the smartwatch can obtain the user's voice signal. Specifically, a microphone can be set in the smartwatch to obtain the user's voice signal. After obtaining the user's voice signal, the noise in the voice signal is filtered out, and then the denoised voice signal is input into the matched filter. In theory, the ratio of the instantaneous power of the signal at the output of the matched filter to the average power of the noise is large, and the signal-to-noise ratio of the processed voice signal output is high.
[0107] For a person's voiceprint, it can uniquely identify a specific person just like a fingerprint. After the de-noised voice signal and the processed voice signal are convolved, a result sequence can be obtained. According to whether the result data at the specified position in the result sequence is greater than the set threshold, it can be determined whether the voiceprint of the currently acquired user is the set voiceprint, and then determine whether the unlocking is successful. The set voiceprint can be the voiceprint of the smart watch that the owner of the smart watch has entered in advance. Only when the result data at the specified position in the result sequence is greater than the set threshold, it indicates that the current user is the owner of the smart watch. Otherwise, the unlocking fails.
[0108] In addition to voiceprint verification, especially in scenarios where the security of smart watches is high, such as banks, it is necessary to ensure that users can use smart watches within a certain range. The smart watch determines the signal strength range of the user's current location, and then determines the user's coordinates, and determines whether the user's coordinates are within the preset coordinate set. If so, the smart watch can be unlocked successfully.
[0109] Through the method of the embodiment of this article, when a bank account manager uses a smart watch, he can unlock the smart watch by voice, and unlock it through voiceprint recognition, which can eliminate the inconvenience of manually entering the password and improve the experience. At the same time, in order to ensure data security, the user's coordinates can be determined by the smart watch, and the unlocking can be successful only if the coordinates are within the preset coordinate set.
[0110] In the examples herein, reference Figure 2 , the filtering out the noise in the speech signal to obtain the denoised speech signal further comprises:
[0111] S201: inputting the speech signal into a non-recursive finite-length unit impulse response filter to obtain a filtered speech signal;
[0112] S202: Downsampling and upsampling the filtered speech signal in sequence to obtain a sampled speech signal;
[0113] S203: pre-emphasize the sampled speech signals in sequence to obtain pre-emphasized speech signals;
[0114] S204: performing a frame operation on the pre-emphasized speech signal;
[0115] S205: performing short-time Fourier transform on each frame of the speech signal after framing to obtain a spectrum sequence;
[0116] S206: Calculate the logarithmic energy of the spectrum sequence, and perform discrete cosine transform on the logarithmic energy to obtain the Mel-frequency cepstrum;
[0117] S207: Filter the Mel-frequency cepstral coefficients using a digital low-pass filter to obtain a de-noised speech signal.
[0118] Among them, the non-recursive finite-length unit impulse response filter can increase the accuracy infinitely under the premise of sufficient computing power. On the one hand, when filtering through the non-recursive finite-length unit impulse response filter, the mechanical noise and various environmental secondary noises in the actual working scene can be filtered out, and the filtering accuracy is relatively high. On the other hand, the non-recursive finite-length unit impulse response filter is conducive to low-performance terminal processing (the hardware often has an acceleration module dedicated to this type of filter), and this type of filter is stable and will not produce oscillations.
[0119] In the embodiment of this article, the main purpose of downsampling and variable sampling is to reduce the complexity of subsequent data processing and improve the spectral accuracy of subsequent Fourier transform. First, the filtered speech signal passes through the first filter, and the bandwidth B of the first filter is required to be <f s,new , in order to avoid spectrum aliasing after downsampling, where f s,new is the target sampling rate after downsampling. And at f s,new The gain at the point is less than the set bandwidth. Generally speaking, the set bandwidth is -40dB. If the set bandwidth is too small, the filter algorithm complexity is high and it is not conducive to the operation of small intelligent devices. If the set bandwidth is too large, the noise elimination is not enough. Generally speaking, the bandwidth B is 2kHz to 5kHz, which is determined by the processor performance. If the performance is good, a higher sampling rate can be used to improve the recognition accuracy. Then, the downsampled signal is efficiently sampled through a multiphase filter to obtain the sampled speech signal.
[0120] When downsampling and variable sampling are performed, the speech signal is discretized in time and sampled at a certain time interval to obtain multiple sampling points. -1 The sampled speech signal is pre-emphasized to increase the high-frequency resolution of the human voice. Where a is the pre-emphasis coefficient, 0.9<a<1, z -1 Represents unit delay. The speech signal after pre-emphasis processing is y(n)=x(n)-ax(n-1), n is the nth sampling point, x(n) is the input signal of the nth sampling point, and y(n) is the output signal of the nth sampling point.
[0121] The pre-emphasized speech signal is divided into frames, the frame length is W (W can be an integer between 10 and 30 ms), and the frame shift is i*W (i can be any number between 0 and 0.5) to reduce the amount of data processing.
[0122] Perform short-time Fourier transform on each frame of speech signal after framing to obtain the spectrum sequence X(n), where n=0,…,N-1, and N is the number of sampling points. The amount of subsequent calculations can be reduced by removing the extremely low-frequency components in the speech signal. For example, the signal in the frequency band below 200Hz can be removed, and the corresponding Points, To round up.
[0123] Furthermore, the step of calculating the logarithmic energy of the spectrum sequence further includes:
[0124] The logarithmic energy of the spectrum sequence is calculated by the following formula:
[0125] S(n)=ln(MELapr(f s,new *n / N)*(|X(n)|2 ));
[0126] MELapr(f s,new *n / N)=(-2.51*10 -21 )*(f s,new *n / N) 5 +(1.1*10 -16 )*(f s,new *n / N) 4 -(1.81*10 -12 )*(f s,new *n / N) 3 +(1.4*10 -8 )*(f s,new *n / N) 2 -(5.47*10 -5 )*(f s,new *n / N)+0.107;
[0127] Among them, S(n) is the logarithmic energy corresponding to the nth sampling point in the spectrum sequence, X(n) is the frequency corresponding to the nth sampling point in the spectrum sequence, N is the number of sampling points in the spectrum sequence, and f s,new The target sampling rate when downsampling.
[0128] The Mel frequency cepstrum is obtained by performing discrete cosine transform on the logarithmic energy. Its coefficients are the Mel frequency cepstrum coefficients, which reflect the characteristics of the speech data. The Mel filter bank containing multiple filters is approximated as a single formula, which reduces the computational complexity, improves the processing speed and reduces power consumption while having little impact on the accuracy.
[0129] Where MFCC(l) is the Mel frequency cepstral coefficient, L is the Mel frequency cepstral coefficient order, which can be any integer from 16 to 32, M is the number of filters in the Mel filter bank, and t is the initial sampling point. For example,
[0130] Use a digital low-pass filter to filter the Mel frequency cepstral coefficients, and smooth the process to retain only the envelope of the Mel frequency cepstral coefficients to remove accidental noise. The normalized cutoff frequency parameter of the digital low-pass filter is between 0.3 and 0.8, which can be adjusted according to the environment. If the noise is relatively large and the environment is noisy, the cutoff frequency should be lower.
[0131] In the examples herein, reference Figure 3 , the method for determining the set threshold includes:
[0132] S301: Acquire a speech training signal;
[0133] S302: Filter out the noise in the training signal by a preset denoising method to obtain a denoised training signal;
[0134] S303: inputting the denoised training signal into a matched filter, and outputting a processed training signal;
[0135] S304: performing a convolution operation on the denoised training signal and the processed training signal to obtain a training result sequence;
[0136] S305: Obtain training result data at a specified position in the training result sequence;
[0137] S306: Calculate and obtain a set threshold value according to the training result data.
[0138] The speech training signal may be a training signal recorded in advance by the user. By recording the user's speech training signal in advance, the user's voiceprint can be identified to facilitate subsequent judgment.
[0139] The preset denoising method can refer to the above steps S201 to S207 for denoising, and then the denoised training signal is input into the matched filter to output the processed training signal. Whether S104 or S304 performs convolution operation, the convolution operation can be performed by the following formula (only S304 step is used as an example):
[0140]
[0141] Among them, h(l′) is the processed training signal, MEt(l′) is the denoised training signal, y(l′) is the training result sequence, L is the length of the processed training signal and the denoised training signal, and the length of the training result sequence obtained after the convolution operation is the sum of the lengths of the processed training signal and the denoised training signal minus one.
[0142] For S105 and S305, the designated position is the position when l′=L. Taking step S305 as an example, the result data at the designated position is the value of y(L).
[0143] In the embodiment of this article, the set threshold is calculated by the following formula:
[0144]
[0145] Among them, γ is the set threshold, γ α is the preset accuracy value, which is any number greater than 0 and less than or equal to 1. MEa(l) is the denoised training signal, h(l) is the processed training signal, is the convolution operation, is the training result sequence, l=1,…,2L-1, L is the specified position.
[0146] Of course, in most cases, the user can record the speech training signal in advance multiple times, and the above S301 to S305 can be executed for each recorded training signal to obtain multiple training result data, and the multiple training result data are averaged and then the set threshold is calculated by the average value of the training result data. In S105, when the result data at the specified position in the result sequence is greater than the set threshold, the subsequent steps can be executed.
[0147] In the examples herein, reference Figure 4 , the method for determining the signal strength range at the user's current location includes:
[0148] S401: Setting a plurality of signal points, where the signal points are used to transmit signals to a smart watch;
[0149] S402: Determine the signal strength range of each signal point corresponding to the user's current location according to the signal strength range of each signal point corresponding to the smart watch.
[0150] The plurality of signal points are generally three or more, which can more accurately determine the user's location. A wireless signal module can be set in the smart watch, and the wireless signal module can receive the signal after the signal point transmits a signal to the smart watch.
[0151] Further, see Figure 5 , predicting the coordinates of the user according to the signal strength range at the current position of the user further includes:
[0152] S501: Determine a coordinate range of the user according to a signal strength range corresponding to each signal point at the current position of the user and the coordinates of each signal point;
[0153] S502: Predicting the coordinates of the user according to the coordinate range of the user.
[0154] Further, refer to Figure 6 , the determining the coordinate range of the user according to the signal strength range corresponding to each signal point at the current position of the user and the coordinates of each signal point further comprises:
[0155] S601: Determine a distance range between the user's current position and each signal point according to a signal strength range corresponding to each signal point at the user's current position;
[0156] S602: Determine the coordinate range of the user according to the distance range between the current position of the user and each signal point, and the coordinates of each signal point.
[0157] The coordinates of multiple signal points are known, and the signal strength range of each signal point at the user's current location can be expressed by the following formula:
[0158] RSSI=-(10mlog 10 d+R);
[0159] RSSI is the signal strength of each signal point at the user's current location, d is the distance between the user's current location and each signal point, R is the RSSI value measured when the distance between the user's current location and each signal point is 1 meter, and m is the signal attenuation factor, which can be any number between 2 and 4.
[0160] The signal strength of each signal point at the user's current location can be obtained through the wireless signal module in the smart watch, and then the distance between the user's current location and each signal point can be obtained through the above formula. Since the signal strength of each signal point at the current location obtained by the wireless signal module may be inaccurate, for each signal point, multiple RSSI values can be obtained through the wireless signal module for multiple times to calculate multiple d values, and then the distance range between the user's current location and each signal point can be obtained.
[0161] Since the coordinates of each signal point are known, and the distance range between the user's current position and each signal point is obtained, the coordinate range of the user can be calculated by the following formula:
[0162]
[0163] Where (x, y) is the coordinate of each signal point, d A is the distance between the user's current position and each signal point. The distance can be the minimum value, maximum value or any value in the distance range. The coordinates of the user's current position corresponding to the distance can be calculated (x A ,y A ).
[0164] Through the above formula, multiple coordinates of the user's current position, that is, the coordinate range, can be calculated. According to the coordinate range, the user's coordinates can be predicted by the following formula:
[0165]
[0166] Where s is the number of coordinates in the coordinate range, (x s ,y s ) is any coordinate in the coordinate range.
[0167] Thus, it is determined whether the user's coordinates are within the preset coordinate set, which is the range within which the user is allowed to unlock the smart watch. If so, the unlocking is successful, and if not, the unlocking fails. This ensures that the user uses the smart watch within the permitted range, thereby improving the safety performance of the smart watch when in use.
[0168] 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, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. And the acquisition, storage, use, and processing of data in the technical solutions described in the embodiments of this application are in compliance with the relevant provisions of national laws and regulations.
[0169] Based on the unlocking method of a smart watch described above, an embodiment of this invention also provides a smart watch. The device may include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiment of this invention and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiment of this invention is as described in the following embodiments. Since the implementation scheme and method of the device to solve the problem are similar, the implementation of the specific device in the embodiment of this invention can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.
[0170] Specifically, Figure 7 This is a schematic diagram of the module structure of an embodiment of a smart watch provided in the embodiments of this article, referring to Figure 7 As shown, a smart watch provided in an embodiment of the present invention includes: an acquisition module 100, a noise removal module 200, a processing module 300, a calculation module 400, a first judgment module 500, and a second judgment module 600.
[0171] An acquisition module 100 is used to acquire a user's voice signal;
[0172] A noise removal module 200, used to filter out noise in the speech signal to obtain a noise-removed speech signal;
[0173] The processing module 300 is used to input the de-noised speech signal into a matched filter and output a processed speech signal;
[0174] An operation module 400 is used to perform a convolution operation on the denoised speech signal and the processed speech signal to obtain a result sequence;
[0175] The first judgment module 500 is used to judge whether the result data at the specified position in the result sequence is greater than a set threshold; if not, stop executing the subsequent steps and the unlocking fails; if so, predict the coordinates of the user according to the signal strength range at the current position of the user;
[0176] The second determination module 600 is used to determine whether the coordinates of the user are within the preset coordinate set; if so, the unlocking is successful; if not, the unlocking fails.
[0177] Reference Figure 8 As shown, based on the unlocking method of a smart watch described above, a computer device 702 is also provided in one embodiment of this invention, wherein the above method is run on the computer device 702. The computer device 702 may include one or more processors 704, such as one or more central processing units (CPUs) or graphics processing units (GPUs), and each processing unit may implement one or more hardware threads. The computer device 702 may also include any memory 706, which is used to store any kind of information such as code, settings, data, etc. In a specific embodiment, the computer program on the memory 706 and which can be run on the processor 704, when the computer program is run by the processor 704, can execute instructions according to the above method. Non-limitingly, for example, the memory 706 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component of the computer device 702. In one embodiment, when the processor 704 executes the associated instructions stored in any memory or combination of memories, the computer device 702 can perform any operation of the associated instructions. The computer device 702 also includes one or more drive mechanisms 708 for interacting with any memory, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.
[0178] The computer device 702 may also include an input / output module 710 (I / O) for receiving various inputs (via input devices 712) and for providing various outputs (via output devices 714). A specific output mechanism may include a presentation device 716 and an associated graphical user interface 718 (GUI). In other embodiments, the input / output module 710 (I / O), input device 712, and output device 714 may not be included, and the computer device 702 may be used as a computer device in a network. The computer device 702 may also include one or more network interfaces 720 for exchanging data with other devices via one or more communication links 722. One or more communication buses 724 couple the components described above together.
[0179] The communication link 722 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 722 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.
[0180] Corresponds to Figure 1-Figure 6 The method in this article also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are executed.
[0181] The embodiment of the present invention also provides a computer readable instruction, wherein when the processor executes the instruction, the program therein causes the processor to execute the following Figures 1 to 6 The method shown.
[0182] It should be understood that in the various embodiments of this document, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.
[0183] It should also be understood that in the embodiments of this article, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.
[0184] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this article.
[0185] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0186] In the several embodiments provided herein, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.
[0187] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this article.
[0188] In addition, each functional unit in each embodiment of this invention 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. The above integrated unit may be implemented in the form of hardware or in the form of software functional unit.
[0189] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this article is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of this article. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0190] Specific embodiments are used in this article to illustrate the principles and implementation methods of this article. The description of the above embodiments is only used to help understand the methods and core ideas of this article. At the same time, for general technicians in this field, according to the ideas of this article, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on this article.
Claims
1. A method for unlocking a smart watch, It is characterized in that Applied to the smart watch, including: Acquiring a user's voice signal; Inputting the speech signal into a non-recursive finite-length unit impulse response filter to obtain a filtered speech signal; Downsampling and upsampling the filtered speech signal in sequence to obtain a sampled speech signal; Pre-emphasize the sampled speech signals in sequence to obtain pre-emphasized speech signals; Performing a frame operation on the speech signal after the pre-emphasis processing; Perform short-time Fourier transform on each frame of speech signal after framing to obtain a spectrum sequence; Calculate the logarithmic energy of the spectrum sequence, and perform discrete cosine transform on the logarithmic energy to obtain the Mel frequency cepstrum; The Mel frequency cepstral coefficients are filtered using a digital low-pass filter to obtain a de-noised speech signal; Inputting the de-noised speech signal into a matched filter and outputting a processed speech signal; Performing a convolution operation on the denoised speech signal and the processed speech signal to obtain a result sequence; Determine whether the result data at a specified position in the result sequence is greater than a set threshold; If not, stop executing the subsequent steps and the unlocking fails; If yes, predicting the coordinates of the user according to the signal strength range at the current location of the user; Determining whether the coordinates of the user are within a preset coordinate set; If yes, the unlocking is successful; If not, the unlocking fails; The logarithmic energy of the spectrum sequence is specifically calculated by the following formula: ; ; in, is the logarithmic energy corresponding to the nth sampling point in the spectrum sequence, is the frequency corresponding to the nth sampling point in the spectrum sequence, N is the number of sampling points in the spectrum sequence, The target sampling rate when downsampling.
2. The unlocking method of the smart watch according to claim 1, It is characterized in that The method for determining the set threshold includes: Obtaining a speech training signal; Filtering out the noise in the training signal by a preset denoising method to obtain a denoised training signal; Inputting the denoised training signal into a matched filter and outputting a processed training signal; Performing a convolution operation on the denoised training signal and the processed training signal to obtain a training result sequence; Get the training result data at the specified position in the training result sequence; A set threshold is calculated based on the training result data.
3. The unlocking method of the smart watch according to claim 2, It is characterized in that The step of calculating the set threshold value according to the training result data further comprises: The set threshold is calculated by the following formula: ; in, To set the threshold, is the preset accuracy value, which can be any number greater than 0 and less than or equal to 1. is the denoised training signal, is the processed training signal, Convolution operation, is the training result sequence, , L is the specified position.
4. The unlocking method of a smart watch according to claim 1, It is characterized in that The method for determining the signal strength range at the user's current location includes: Setting a plurality of signal points, wherein the signal points are used to transmit signals to the smart watch; According to the signal strength range of the smart watch corresponding to each signal point, the signal strength range of each signal point corresponding to the user's current location is determined.
5. The unlocking method of the smart watch according to claim 4, It is characterized in that The predicting the coordinates of the user according to the signal strength range at the current position of the user further comprises: Determine the coordinate range of the user according to the signal strength range corresponding to each signal point at the current position of the user and the coordinates of each signal point; The coordinates of the user are predicted according to the coordinate range of the user.
6. The unlocking method of the smart watch according to claim 5, It is characterized in that Determining the coordinate range of the user according to the signal strength range corresponding to each signal point at the current position of the user and the coordinates of each signal point further includes: Determine the distance range between the user's current position and each signal point according to the signal strength range corresponding to each signal point at the user's current position; The coordinate range of the user is determined according to the distance range between the current position of the user and each signal point, and the coordinates of each signal point.
7. A smart watch, It is characterized in that include: An acquisition module, used to acquire a user's voice signal; A denoising module is used to input the speech signal into a non-recursive finite-length unit impulse response filter to obtain a filtered speech signal; sequentially downsample and upsample the filtered speech signal to obtain a sampled speech signal; sequentially pre-emphasize the sampled speech signal to obtain a pre-emphasized speech signal; perform a framing operation on the pre-emphasized speech signal; perform a short-time Fourier transform on each frame of the speech signal after framing to obtain a spectrum sequence; calculate the logarithmic energy of the spectrum sequence, and perform a discrete cosine transform on the logarithmic energy to obtain a Mel-frequency cepstrum; The Mel frequency cepstral coefficients are filtered using a digital low-pass filter to obtain a de-noised speech signal; A processing module, used for inputting the de-noised speech signal into a matched filter and outputting a processed speech signal; An operation module, used for performing a convolution operation on the denoised speech signal and the processed speech signal to obtain a result sequence; A first judgment module, used to judge whether the result data at a specified position in the result sequence is greater than a set threshold; If not, stop executing the subsequent steps and the unlocking fails; If yes, predicting the coordinates of the user according to the signal strength range at the current location of the user; The second judgment module is used to judge whether the coordinates of the user are within the preset coordinate set; if so, the unlocking is successful; if not, the unlocking fails; The logarithmic energy of the spectrum sequence is specifically calculated by the following formula: ; ; in, is the logarithmic energy corresponding to the nth sampling point in the spectrum sequence, is the frequency corresponding to the nth sampling point in the spectrum sequence, N is the number of sampling points in the spectrum sequence, The target sampling rate when downsampling.
8. A computer device comprising a memory, a processor, and a computer program stored on the memory, It is characterized in that When the computer program is executed by the processor, the method according to any one of claims 1 to 6 is performed.
9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor of a computer device, the method according to any one of claims 1 to 6 is executed.
Citation Information
Patent Citations
Method and apparatus for voiceprint verification, computer device and storage medium
CN109378002A
Virtual resource transfer processing method and device, storage medium and computer equipment
CN112863547A
