A method and device for filtering abnormal signals

Abstract

The present application provides a method and device for filtering abnormal signals. The method includes: the electronic device detects the acquired sound signal according to a pre-trained detection model. If the electronic device detects the presence of an abnormal high-frequency signal in the sound signal, it can issue a warning to the user, or filter out the abnormal high-frequency signal in the sound signal. The advantage of this method is that it can prevent the user's privacy from being leaked without the user's knowledge. Through this method, potential hidden communication threats can be identified and intercepted, reducing the risk of privacy information leakage.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method and device for filtering abnormal signals. Background Art

[0002] With the rapid development of the Internet and informatization, information release and online trade through the Internet are being widely used by people. At the same time, various confidential information, including national security information, private information (such as personal accounts), etc. need to be transmitted through the Internet. In order to protect the security of various confidential information, hidden communication technology can effectively prevent confidential information from being intercepted and obtained by third parties.

[0003] Hidden communication technology based on sound waves has been widely used. Its main working process is: the synthesis device modulates the information to be sent into a carrier signal of a specific frequency, and synthesizes the carrier signal into a normal sound signal; the transmitter sends the normal sound signal, and the receiver receives and demodulates the information to be sent in the normal sound signal, completing the hidden communication based on sound waves.

[0004] Hidden communications based on sound waves also bring users the risk of personal information leakage. The attacker modulates special information into a high-frequency carrier signal through a synthesis device, and synthesizes the high-frequency carrier signal into a normal sound signal, which is imperceptible to the user. The playback device (such as a speaker) plays the synthesized sound signal. When the user approaches the playback device, the user's electronic device (such as a mobile phone) can receive the synthesized sound signal. If the user's electronic device (such as a mobile phone) is installed with an application developed by the attacker, and the application can detect the high-frequency carrier signal modulated by the attacker, the application can collect the user's or device information, such as the identification of the electronic device (such as a mobile phone) or the current location of the electronic device (such as a mobile phone), and send it to the attacker. At this time, the attacker obtains the user's information without the user's knowledge. Summary of the invention

[0005] The present application provides a method for filtering abnormal signals. The electronic device detects the collected sound signals. When the abnormal signal detection module finds abnormal high-frequency signals, that is, when the high-frequency energy value of the sound signal is higher than the threshold, the abnormal situation is notified to the user. The user can choose to filter out the abnormal high-frequency signals to intercept potential hidden communication threats, and at the same time, the sound signal after filtering out the abnormal high-frequency signals is returned to the first application. In this way, hidden communications can be identified and intercepted, improving the security of user privacy.

[0006] In the first aspect, the present application provides a method for detecting and filtering abnormal high-frequency signals. The method includes: an electronic device receives a request for obtaining a sound signal; in response to the request for obtaining a sound signal, the electronic device obtains a sound signal; and the electronic device determines the high-frequency energy value of the sound signal based on the sound signal. If the high-frequency energy value of the sound signal is greater than the ambient sound energy threshold, the electronic device sends a prompt message to the user, and the prompt message is used to prompt the user that there is an abnormal high-frequency signal in the sound signal.

[0007] The electronic device detects the acquired sound signal according to the pre-trained detection model. If the electronic device detects abnormal high-frequency signals in the sound signal, it can warn the user or filter out the abnormal high-frequency signals in the sound signal. The advantage of this method is that it can prevent the user's privacy from being leaked without the user's knowledge. Through this method, potential hidden communication threats can be identified and intercepted, reducing the risk of privacy information leakage.

[0008] In combination with the first aspect, in a possible implementation of the first aspect, after the electronic device sends a prompt message to the user, the electronic device also receives a filtering operation from the user; in response to the filtering operation, the electronic device filters out abnormal high-frequency signals in the sound signal. In this way, the user can perceive that there are abnormal high-frequency signals in the sound signal obtained by the electronic device, and when the user passes through this area next time, he will be on guard against abnormal high-frequency signals in the area; or the user reports the existence of abnormal high-frequency signals in the area to the server, and the server will summarize the information reported by the user and take measures to prevent abnormal high-frequency signals from causing the user's privacy information to be leaked. In some embodiments, when the electronic device determines that the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold, the electronic device does not need to send a prompt message to the user, and the electronic device directly removes the abnormal high-frequency signal in the sound signal. In this way, when the user is calling a friend through the electronic device or the electronic device is displaying a navigation route, the electronic device does not send a prompt message to the user, and will not affect the user's current operation.

[0009] In combination with the first aspect, in a possible implementation of the first aspect, the electronic device further sends the sound signal from which the abnormal high-frequency signal is filtered out to the receiving device. When the user is calling a friend through the electronic device or playing a game with a friend in a team, the electronic device sends the sound signal from which the abnormal high-frequency signal is filtered out to the receiving device through the communication module. The receiving device is the device currently being used by the user's friend, so that the user's current operation will not be affected.

[0010] In combination with the first aspect, in a possible implementation of the first aspect, the electronic device obtains first environmental information, the first environmental information includes location information and / or environmental sound; the electronic device determines the environmental sound energy threshold according to the first environmental information. Here, the first environmental information is used to determine the current environment (for example, a shopping mall), and the electronic device determines the environmental sound energy threshold corresponding to the current environment according to the current environment, and the environmental sound energy threshold is used to compare with the high-frequency energy value of the sound signal. If the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold corresponding to the current environment, the electronic device determines that there is an abnormal high-frequency signal in the sound signal.

[0011] In combination with the first aspect, in a possible implementation of the first aspect, the electronic device determines the high-frequency energy value of the sound signal based on the sound signal, specifically including the following steps: first, the electronic device obtains the ambient sound before obtaining the sound signal; second, the electronic device determines the ambient noise energy value based on the ambient sound; finally, the electronic device determines the high-frequency energy value of the sound signal based on the actual high-frequency energy value of the sound signal and the ambient noise energy value. Here, the electronic device determines the high-frequency energy value of the sound signal based on the actual high-frequency energy value of the sound signal and the ambient noise energy value in order to eliminate the influence of the ambient noise, and removes the ambient noise energy value from the actual high-frequency energy value of the sound signal. In this way, the accuracy of confirming the high-frequency energy value of the sound signal can be improved.

[0012] In combination with the first aspect, in a possible implementation of the first aspect, the electronic device determines the high-frequency energy value of the sound signal according to the actual high-frequency energy value of the sound signal and the energy value of the ambient noise, specifically including the following steps: the electronic device obtains the high-frequency signal in the sound signal; the electronic device divides the high-frequency signal into high-frequency signal segments of n time windows, where n is a positive integer; the electronic device calculates the actual high-frequency energy value of the high-frequency signal segments in the n time windows; the electronic device calculates the full-decibel high-frequency energy value of the high-frequency signal segments in the n time windows according to the actual high-frequency energy value of the high-frequency signal segments in the n time windows; the electronic device determines the high-frequency energy value of the sound signal according to the full-decibel high-frequency energy value of the high-frequency signal segments in the n time windows and the energy value of the ambient noise. Here, since the frequency band range of the abnormal high-frequency signal is in the high-frequency band, only the high-frequency band signal of the sound signal needs to be obtained, and the high-frequency energy value of the sound signal needs to be calculated according to the high-frequency band signal of the sound signal. In this way, the operation of the electronic device can be reduced and consumption can be saved.

[0013] In combination with the first aspect, in a possible implementation of the first aspect, the electronic device may determine the full decibel high-frequency energy value of the high-frequency signal segment in the n time windows according to the actual high-frequency energy value of the high-frequency signal segment in the n time windows by the following formula:

[0014]

[0015] Among them, Pb i is the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window, Sb i is the actual high-frequency energy value of the medium- and high-frequency signal segment in the i-th time window, Sj is the number of bits required for the electronic device to store the medium- and high-frequency signal segment in the j-th time window, j is a positive integer greater than or equal to 1 and less than or equal to n, and i is a positive integer less than or equal to n.

[0016] In combination with the first aspect, in a possible implementation of the first aspect, the electronic device can determine the high-frequency energy value of the sound signal according to the full decibel high-frequency energy value of the high-frequency signal segment in the n time windows and the ambient noise energy value by the following formula:

[0017]

[0018] Among them, Pb i is the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window, Pci is the difference between the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window and the ambient noise energy value, Pm represents the ambient noise energy value, i is a positive integer less than or equal to n; P0 represents the high-frequency energy value of the sound signal.

[0019] In combination with the first aspect, in a possible implementation manner of the first aspect, the frequency band of the abnormal high-frequency signal includes 18 KHz-20 KHz.

[0020] In the second aspect, the present application provides an electronic device, including a sound collection module and an abnormal signal detection framework; wherein the sound collection module is used to obtain sound signals; the abnormal signal detection framework is used to determine the high-frequency energy value of the sound signal; the abnormal signal detection framework is also used to determine if the high-frequency energy value of the sound signal is greater than the ambient sound energy threshold, and send a prompt message to the user, wherein the prompt message is used to prompt that the sound signal contains an abnormal high-frequency signal.

[0021] The electronic device detects the acquired sound signal according to the abnormal signal detection framework. If the abnormal signal detection framework detects the presence of abnormal high-frequency signals in the sound signal, it can warn the user or filter out the abnormal high-frequency signals in the sound signal. The advantage of this method is that it can prevent the user's privacy from being leaked without the user's knowledge. In this way, potential hidden communication threats can be identified and intercepted, reducing the risk of privacy information leakage.

[0022] In combination with the second aspect, in a possible implementation of the second aspect, the abnormal signal detection framework is also used to receive the user's filtering operation; in response to the user's filtering operation, the abnormal high-frequency signal present in the sound signal is filtered out. In this way, the user can perceive the presence of abnormal high-frequency signals in the sound signal obtained by the electronic device, and when the user passes through this area next time, the abnormal high-frequency signal present in the area will be guarded against; or the user reports the presence of abnormal high-frequency signals in the area to the server, and the server will summarize the information reported by the user and take measures to prevent the abnormal high-frequency signal from causing the user's privacy information to be leaked. In some embodiments, when the electronic device determines that the high-frequency energy value of the sound signal is greater than the ambient sound energy threshold, the electronic device does not need to send a prompt message to the user, and the electronic device directly removes the abnormal high-frequency signal in the sound signal. In this way, when the user is calling a friend through the electronic device or the electronic device is displaying the navigation route, the electronic device does not send a prompt message to the user, and will not affect the user's current operation.

[0023] In combination with the second aspect, in a possible implementation of the second aspect, the sound collection module is also used to send the sound signal that filters out abnormal high-frequency signals to a receiving device. When a user is calling a friend through an electronic device or is playing a game with a friend in a team, the abnormal signal detection framework calls the sound collection module, and the sound collection module sends the sound signal that filters out abnormal high-frequency signals to the receiving device through the communication module. The receiving device is the device that the user's friend is using, so that it will not affect the user's current operation. In some embodiments, the abnormal signal detection framework does not need to call the sound collection module, and directly sends the sound signal that filters out abnormal high-frequency signals to the receiving device through the communication module.

[0024] In conjunction with the second aspect, in a possible implementation of the second aspect, the abnormal signal detection framework is also used to obtain first environmental information, the first environmental information including location information and / or environmental sound; and determine the environmental sound energy threshold according to the first environmental information. Here, the first environmental information is used to determine the current environment (e.g., a shopping mall), and the abnormal signal detection framework determines the environmental sound energy threshold corresponding to the current environment based on the current environment. The environmental sound energy threshold is used to compare with the high-frequency energy value of the sound signal. If the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold corresponding to the current environment, the abnormal signal detection framework determines that there is an abnormal high-frequency signal in the sound signal.

[0025] In combination with the second aspect, in a possible implementation of the second aspect, the sound collection module is further used to obtain environmental sounds before obtaining sound signals; the abnormal signal detection framework is further used to determine the environmental noise energy value based on the environmental sounds; and the high-frequency energy value of the sound signal is determined based on the actual high-frequency energy value of the sound signal and the environmental noise energy value. Here, the electronic device determines the high-frequency energy value of the sound signal based on the actual high-frequency energy value of the sound signal and the environmental noise energy value in order to eliminate the influence of environmental noise, and removes the environmental noise energy value from the actual high-frequency energy value of the sound signal, so that the accuracy of confirming the high-frequency energy value of the sound signal can be improved.

[0026] In combination with the second aspect, in a possible implementation of the second aspect, the abnormal signal detection framework is also used to obtain the high-frequency signal in the sound signal; divide the high-frequency signal into high-frequency signal segments of n time windows, where n is a positive integer; calculate the actual high-frequency energy value of the high-frequency signal segment in the n time windows; based on the actual high-frequency energy value of the high-frequency signal segment in the n time windows; calculate the full-decibel high-frequency energy value of the high-frequency signal segment in the n time windows; determine the high-frequency energy value of the sound signal based on the full-decibel high-frequency energy value of the high-frequency signal segment in the n time windows and the environmental noise energy value. Here, since the frequency band range of the abnormal high-frequency signal is in the high-frequency band, the abnormal signal detection framework only needs to obtain the high-frequency band signal of the sound signal, and calculate the high-frequency energy value of the sound signal based on the high-frequency band signal of the sound signal. In this way, calculations can be reduced and consumption can be saved.

[0027] In combination with the second aspect, in a possible implementation of the second aspect, the abnormal signal detection framework is further used to determine the full decibel high-frequency energy value of the high-frequency signal segment in the n time windows according to the actual high-frequency energy value of the high-frequency signal segment in the n time windows by the following formula:

[0028]

[0029] Among them, Pb i is the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window, Sb i is the actual high-frequency energy value of the medium- and high-frequency signal segment in the i-th time window, Sj is the number of bits required for the electronic device to store the medium- and high-frequency signal segment in the j-th time window, j is a positive integer greater than or equal to 1 and less than or equal to n, and i is a positive integer less than or equal to n.

[0030] In combination with the second aspect, in a possible implementation of the second aspect, the abnormal signal detection framework is specifically used to determine the high-frequency energy value of the sound signal according to the full decibel high-frequency energy value and the ambient noise energy value of the high-frequency signal segment in the n time windows by the following formula:

[0031] Pc i =Pbi –Pm;

[0032]

[0033] Among them, Pb i is the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window, Pci is the difference between the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window and the ambient noise energy value, Pm represents the ambient noise energy value, i is a positive integer less than or equal to n; P0 represents the high-frequency energy value of the sound signal.

[0034] In combination with the second aspect, in a possible implementation manner of the second aspect, a frequency band range of the high-frequency signal includes 18 KHz-20 KHz.

[0035] In a third aspect, the present application provides a device for filtering abnormal signals, comprising one or more processors, one or more memories, and a sound collector; the one or more memories and the sound collector are coupled to the one or more processors, the one or more memories are used to store computer program codes, the computer program codes include computer instructions, and one or more processors call the computer instructions to enable the device to execute a method for filtering abnormal signals in any possible implementation of the first aspect above.

[0036] In a fourth aspect, an embodiment of the present application provides a computer storage medium, including computer instructions. When the computer instructions are executed on an electronic device, the communication device executes a method for filtering abnormal signals in any possible implementation of the first aspect mentioned above.

[0037] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a computer, it enables the computer to execute a method for filtering abnormal signals in any possible implementation of the first aspect.

[0038] The present application provides a method and device for filtering abnormal signals. The electronic device detects the acquired sound signal according to a pre-trained detection model. If the electronic device detects the presence of an abnormal high-frequency signal in the sound signal, it can issue a warning to the user, or filter out the abnormal high-frequency signal in the sound signal. The advantage of this method is that it can prevent the user's privacy from being leaked without the user's knowledge. Through this method, potential hidden communication threats can be identified and intercepted, reducing the risk of privacy information leakage. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flow chart of a method for obtaining user privacy information through hidden communication technology provided in an embodiment of the present application;

[0040] Figure 2 A schematic diagram of the architecture of an electronic device 100 provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of the architecture of a system 10 provided in an embodiment of the present application;

[0042] Figure 4 A functional schematic diagram of each module provided in an embodiment of the present application;

[0043] Figure 5 A flowchart of a method for filtering abnormal signals provided in an embodiment of the present application;

[0044] Figure 6 A schematic diagram of a flow chart of another abnormal signal filtering method provided in an embodiment of the present application;

[0045] Figure 7A-7F A set of UI diagrams provided for embodiments of the present application;

[0046] Figure 8A-8D A flowchart of an abnormal high-frequency signal detection and filtering method provided in an embodiment of the present application;

[0047] Fig. 9 A schematic diagram of a device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the accompanying drawings to clearly and thoroughly describe the technical solutions in the embodiments of the present application. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in the text is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0049] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0050] At present, the hidden communication technology based on sound waves is mainly implemented through high-frequency signals and applications that can identify high-frequency signals. That is, when the application recognizes a specific high-frequency signal, it can perform the operation set in advance by the application developer, such as obtaining the user's privacy information. The frequency of high-frequency signals is generally greater than 18KHz, and due to the limitations of the human auditory system (HAS), most users can only hear sounds with frequencies below 16KHz, so most users cannot perceive whether there are high-frequency signals in the surrounding environment. At the same time, the hardware configuration of most existing electronic devices can support the reception and demodulation of signals above 18KHz, but lacks control measures for high-frequency signals. In other words, it is difficult for most users to know whether there is a high-frequency signal at present, and whether there is hidden communication at present. If the application obtains the user's privacy information (such as the electronic device identification and the location of the electronic device) after recognizing a specific high-frequency signal and sends it to a specific server or electronic device, the user's privacy information, such as user identity information, location information or operation habits, can be obtained without the user's awareness.

[0051] Figure 1 A flowchart of a method for obtaining user privacy information by using hidden communication technology provided by an embodiment of the present application is shown. Figure 1 As shown, at this time, the speakers placed at the door of the store are playing promotional advertisements, and the promotional advertisements contain abnormal high-frequency signals synthesized by a third party. When the user passes by the store while running, the electronic device carried by the user may obtain the sound of the promotional advertisement. When there is an application in the user's electronic device that can identify the high-frequency signal contained in the promotional advertisement, the application may obtain the identification of the user's electronic device and the location of the electronic device after identifying the abnormal high-frequency signal, and send it to a third party. The application can be an application with normal functions. For example, the electronic device receives the user's operation to open the voice assistant, and the voice assistant collects the sound signal; for another example, the user teams up with friends to play games through a game application. In order to facilitate communication, the user opens the microphone control of the game interface, and the sound collection module of the user's electronic device collects the sound signal; for another example, the user makes a video call with a friend through a social application in a shopping mall, and the sound collection module of the user's electronic device collects the sound. If there is hidden communication information at the user's location (for example, there is a high-frequency signal in the music played in the shopping mall), the user's electronic device collects the sound signal and sends it to the application. The application in the user's electronic device (for example, a voice assistant, a game application, a social application) can identify the high-frequency signal in the sound signal, and the high-frequency signal triggers the application to obtain the identification of the user's electronic device and the location of the electronic device, and send it to a third party.

[0052] It should be noted that the above application scenarios are only used to explain the present application and may include more or fewer application scenarios and should not constitute a limitation.

[0053] It can be seen from this that when an electronic device with a voice input function obtains external sound signals, the first application (such as a navigation application) installed in the electronic device is at risk of obtaining user privacy information through hidden communication and causing personal privacy leakage.

[0054] In order to identify high frequency signals, there are two ways to detect sound signals.

[0055] Method 1: Abnormal sound detection and abnormal sound classification technology, which is mainly used to detect abnormal sounds in environmental sounds, such as screams, gunshots, breaking sounds, and other sounds that represent abnormal events. Abnormal sound detection technology extracts features such as zero-crossing rate, amplitude difference, power spectrum density, spectral entropy, and mel-frequency cepstral coefficients (MFCC) from the sample sound set, models each type of abnormal sound signal, and trains a classifier for each type of abnormal sound signal. Multiple features such as zero-crossing rate, amplitude difference, power spectrum density, spectral entropy, and mel-frequency cepstral coefficients are extracted from the sound to be detected for abnormal detection, so that the sound to be detected is classified into a specific sound category. If the signal to be detected is not classified into a specific sound category, the sound to be detected is determined to be an unknown sound category. Method 1 is mainly used to detect abnormal sounds that can be perceived by humans in environmental sounds. It has a large amount of calculation and poor real-time performance, which is not conducive to implementation in electronic devices.

[0056] Method 2: Ultrasonic voice hidden attack detection method, this method performs spectrum analysis on the ultrasonic signal collected by the electronic device to obtain the center frequency of the ultrasonic signal, and determines whether the center frequency is within the set attack frequency range. If it is within the attack frequency range, the ultrasonic signal is bandpass filtered to filter out the frequency components of the upper and lower limits of the voice frequency to obtain the baseband signal, and detect whether the baseband signal contains voice. Method 2 can only detect attacks that carry voice signals in ultrasonic signals, and cannot identify hidden attacks that use ultrasonic signals to transmit non-voice signals.

[0057] The present application provides a method for detecting and filtering abnormal high-frequency signals. The electronic device detects the acquired sound signal according to a pre-trained detection model. If the electronic device detects the presence of an abnormal high-frequency signal in the sound signal, it can issue a warning to the user, or filter out the abnormal high-frequency signal in the sound signal. The advantage of this method is that it can prevent the user's privacy from being leaked without the user's knowledge. Through this method, potential hidden communication threats can be identified and intercepted, reducing the risk of privacy information leakage while ensuring user experience.

[0058] For example, when a user passes by a shopping mall, the speakers installed in the mall are playing promotional advertisements or music. The promotional advertisements or music contain abnormal high-frequency signals, and the user's electronic device (such as a mobile phone) can detect the abnormal high-frequency signals and send an alarm to the user to prevent a third party from obtaining the user's privacy and pushing advertisements to the user.

[0059] For another example, when a user is watching a TV program at home, an abnormal high-frequency signal is synthesized in the audio played in the TV program (the special information carried by the abnormal high-frequency signal can be used to mark the currently playing video content, such as computer promotions, clothing advertisements, etc.). The user's electronic device (such as a mobile phone) can detect the abnormal high-frequency signal and send an alarm to the user to prevent a third party from understanding the user's viewing habits and pushing recommended programs to the user.

[0060] For another example, a user accesses an anonymous network through an electronic device (such as a desktop computer), and a third-party server publishes audio and video content synthesized with abnormal high-frequency signals in the anonymous network, which can attract anonymous users to watch. The user's electronic device (such as a mobile phone) can detect the abnormal high-frequency signal and send an alarm to the user to prevent a third party from obtaining the real information of the user accessing the anonymous network.

[0061] It should be noted that hidden communication based on sound waves has been widely used to protect the security of secret information. For example, the information that needs to be transmitted confidentially at the sender is modulated into a high-frequency carrier, and then the high-frequency carrier is hidden in ordinary information. The secret information is released through ordinary information, and it is difficult for attackers to detect the existence of secret information from ordinary information, thereby making the secret information more concealed and secure. The receiving end receives ordinary information and demodulates the secret information in the ordinary information. At this time, the receiving end will display the corresponding prompt information. The prompt information can be a prompt information containing the sender device identification. For example, the prompt information can be "receiving secret information sent from HUAWEI P30". The user at the receiving end determines that this information is useful information rather than junk information based on the prompt information. The user can choose not to filter out the signal, thereby receiving the secret information sent by the sender. This method can ensure that useful information is not mistaken for junk information and filtered out.

[0062] The above embodiments are only used to explain the present application and should not be construed as limiting.

[0063] Figure 2 A schematic structural diagram of an electronic device 100 is shown.

[0064] The following is a specific description of the embodiment using the electronic device 100 as an example. The device types of the electronic device 100 may include mobile phones, televisions, tablet computers, speakers, watches, desktop computers, laptop computers, handheld computers, notebook computers, ultra-mobile personal computers (ultra-mobile personal computers, UMPC), netbooks, and personal digital assistants (personal digital assistants, PDAs), augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) devices, etc. The embodiment of the present application does not impose any special restrictions on the device type of the electronic device 100.

[0065] It should be understood that Figure 2 The electronic device 100 shown is only an example, and the electronic device 100 may have more Figure 2 The more or less components shown in the figure can be combined with two or more components, or can have different component configurations. The various components shown in the figure can be implemented in hardware, software, or a combination of hardware and software including one or more signal processing and / or application specific integrated circuits.

[0066] The electronic device 100 may include: a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0067] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or separate some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0068] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0069] The controller may be the nerve center and command center of the electronic device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0070] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0071] In some embodiments, the processor 110 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0072] The I2C interface is a bidirectional synchronous serial bus, including a serial data line (SDA) and a serial clock line (SCL). In some embodiments, the processor 110 may include multiple groups of I2C buses. The processor 110 may be coupled to the touch sensor 180K, the charger, the flash, the camera 193, etc. through different I2C bus interfaces. For example: the processor 110 may be coupled to the touch sensor 180K through the I2C interface, so that the processor 110 communicates with the touch sensor 180K through the I2C bus interface, thereby realizing the touch function of the electronic device 100.

[0073] The I2S interface can be used for audio communication. In some embodiments, the processor 110 can include multiple I2S buses. The processor 110 can be coupled to the audio module 170 via the I2S bus to achieve communication between the processor 110 and the audio module 170. In some embodiments, the audio module 170 can transmit an audio signal to the wireless communication module 160 via the I2S interface to achieve the function of answering a call through a Bluetooth headset.

[0074] The PCM interface can also be used for audio communication, sampling, quantizing and encoding analog signals. In some embodiments, the audio module 170 and the wireless communication module 160 can be coupled via a PCM bus interface. In some embodiments, the audio module 170 can also transmit audio signals to the wireless communication module 160 via the PCM interface to realize the function of answering calls via a Bluetooth headset. Both the I2S interface and the PCM interface can be used for audio communication.

[0075] The UART interface is a universal serial data bus for asynchronous communication. The bus can be a bidirectional communication bus. It converts the data to be transmitted between serial communication and parallel communication. In some embodiments, the UART interface is generally used to connect the processor 110 and the wireless communication module 160. For example, the processor 110 communicates with the Bluetooth module in the wireless communication module 160 through the UART interface to implement the Bluetooth function. In some embodiments, the audio module 170 can transmit an audio signal to the wireless communication module 160 through the UART interface to implement the function of playing music through a Bluetooth headset.

[0076] The MIPI interface can be used to connect the processor 110 with peripheral devices such as the display screen 194 and the camera 193. The MIPI interface includes a camera serial interface (CSI), a display serial interface (DSI), etc. In some embodiments, the processor 110 and the camera 193 communicate via the CSI interface to implement the shooting function of the electronic device 100. The processor 110 and the display screen 194 communicate via the DSI interface to implement the display function of the electronic device 100.

[0077] The GPIO interface can be configured by software. The GPIO interface can be configured as a control signal or as a data signal. In some embodiments, the GPIO interface can be used to connect the processor 110 with the camera 193, the display 194, the wireless communication module 160, the audio module 170, the sensor module 180, etc. The GPIO interface can also be configured as an I2C interface, an I2S interface, a UART interface, a MIPI interface, etc.

[0078] The USB interface 130 is an interface that complies with the USB standard specification, and specifically can be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface 130 can be used to connect a charger to charge the electronic device 100, and can also be used to transfer data between the electronic device 100 and a peripheral device. It can also be used to connect headphones to play audio through the headphones. The interface can also be used to connect other electronic devices, such as AR devices, etc.

[0079] It is understandable that the interface connection relationship between the modules illustrated in the embodiment of the present invention is only a schematic illustration and does not constitute a structural limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0080] The charging management module 140 is used to receive charging input from a charger. The charger may be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 may receive charging input from a wired charger through the USB interface 130. In some wireless charging embodiments, the charging management module 140 may receive wireless charging input through a wireless charging coil of the electronic device 100. While the charging management module 140 is charging the battery 142, it may also power the electronic device through the power management module 141.

[0081] The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, and supplies power to the processor 110, the internal memory 121, the external memory, the display screen 194, the camera 193, and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle number, battery health status (leakage, impedance), etc. In some other embodiments, the power management module 141 can also be set in the processor 110. In other embodiments, the power management module 141 and the charging management module 140 can also be set in the same device.

[0082] The wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0083] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0084] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the electronic device 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, and filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the same device as at least some of the modules of the processor 110.

[0085] The modem processor may include a modulator and a demodulator. Among them, the modulator is used to modulate the low-frequency baseband signal to be sent into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to a speaker 170A, a receiver 170B, etc.), or displays an image or video through a display screen 194. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and be set in the same device as the mobile communication module 150 or other functional modules.

[0086] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the electronic device 100. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the frequency of the electromagnetic wave signal and performs filtering, and sends the processed signal to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, modulate the frequency of it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0087] In some embodiments, the antenna 1 of the electronic device 100 is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou navigation satellite system (BDS), a quasi-zenith satellite system (QZSS) and / or a satellite based augmentation system (SBAS).

[0088] The electronic device 100 implements the display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

[0089] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.

[0090] The electronic device 100 can realize the shooting function through ISP, camera 193, video codec, GPU, display screen 194 and application processor.

[0091] ISP is used to process the data fed back by camera 193. For example, when taking a photo, the shutter is opened, and the light is transmitted to the camera photosensitive element through the lens. The light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to ISP for processing and converts it into an image visible to the naked eye. ISP can also perform algorithm optimization on the noise, brightness, and skin color of the image. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some embodiments, ISP can be set in camera 193.

[0092] The camera 193 is used to capture still images or videos. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then passes the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV or other format. In some embodiments, the electronic device 100 may include 1 or N cameras 193, where N is a positive integer greater than 1.

[0093] The digital signal processor is used to process digital signals, and can process not only digital image signals but also other digital signals. For example, when the electronic device 100 is selecting a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.

[0094] Video codecs are used to compress or decompress digital videos. The electronic device 100 may support one or more video codecs. Thus, the electronic device 100 may play or record videos in a variety of coding formats, such as Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

[0095] NPU is a neural network (NN) computing processor. By drawing on the structure of biological neural networks, such as the transmission mode between neurons in the human brain, it can quickly process input information and can also continuously self-learn. Through NPU, applications such as intelligent cognition of electronic device 100 can be realized, such as image recognition, face recognition, voice recognition, text understanding, etc.

[0096] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function, such as storing music, video and other files in the external memory card.

[0097] The internal memory 121 can be used to store computer executable program codes, which include instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the electronic device 100 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0098] The electronic device 100 can implement audio functions such as music playing and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone jack 170D, and the application processor.

[0099] The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. The audio module 170 can also be used to encode and decode audio signals. In some embodiments, the audio module 170 can be arranged in the processor 110, or some functional modules of the audio module 170 can be arranged in the processor 110.

[0100] The speaker 170A, also called a "speaker", is used to convert an audio electrical signal into a sound signal. The electronic device 100 can listen to music or listen to a hands-free call through the speaker 170A.

[0101] The receiver 170B, also called a "earpiece", is used to convert audio electrical signals into sound signals. When the electronic device 100 receives a call or voice message, the voice can be received by placing the receiver 170B close to the human ear.

[0102] Microphone 170C, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can speak by putting their mouth close to microphone 170C to input the sound signal into microphone 170C. The electronic device 100 can be provided with at least one microphone 170C. In other embodiments, the electronic device 100 can be provided with two microphones 170C, which can not only collect sound signals but also realize noise reduction function. In other embodiments, the electronic device 100 can also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify the sound source, realize directional recording function, etc.

[0103] The earphone interface 170D is used to connect a wired earphone and can be a USB interface 130 or a 3.5 mm open mobile terminal platform (OMTP) standard interface or a cellular telecommunications industry association of the USA (CTIA) standard interface.

[0104] The pressure sensor 180A is used to sense the pressure signal and can convert the pressure signal into an electrical signal. In some embodiments, the pressure sensor 180A can be set on the display screen 194. There are many types of pressure sensors 180A, such as resistive pressure sensors, inductive pressure sensors, capacitive pressure sensors, etc. The capacitive pressure sensor can be a parallel plate including at least two conductive materials. When a force acts on the pressure sensor 180A, the capacitance between the electrodes changes. The electronic device 100 determines the intensity of the pressure according to the change in capacitance. When a touch operation acts on the display screen 194, the electronic device 100 detects the touch operation intensity according to the pressure sensor 180A. The electronic device 100 can also calculate the touch position according to the detection signal of the pressure sensor 180A. In some embodiments, touch operations acting on the same touch position but with different touch operation intensities can correspond to different operation instructions. For example: when a touch operation with a touch operation intensity less than the first pressure threshold acts on the short message application icon, an instruction to view the short message is executed. When a touch operation with a touch operation intensity greater than or equal to the first pressure threshold acts on the short message application icon, an instruction to create a new short message is executed.

[0105] The gyro sensor 180B can be used to determine the motion posture of the electronic device 100. In some embodiments, the angular velocity of the electronic device 100 around three axes (i.e., x, y, and z axes) can be determined by the gyro sensor 180B. The gyro sensor 180B can be used for anti-shake shooting. For example, when the shutter is pressed, the gyro sensor 180B detects the angle of the electronic device 100 shaking, calculates the distance that the lens module needs to compensate based on the angle, and allows the lens to offset the shaking of the electronic device 100 through reverse movement to achieve anti-shake. The gyro sensor 180B can also be used for navigation and somatosensory game scenes.

[0106] The air pressure sensor 180C is used to measure air pressure. In some embodiments, the electronic device 100 calculates the altitude through the air pressure value measured by the air pressure sensor 180C to assist positioning and navigation.

[0107] The magnetic sensor 180D includes a Hall sensor. The electronic device 100 can use the magnetic sensor 180D to detect the opening and closing of the flip leather case. In some embodiments, when the electronic device 100 is a flip phone, the electronic device 100 can detect the opening and closing of the flip cover according to the magnetic sensor 180D. Then, according to the detected opening and closing state of the leather case or the opening and closing state of the flip cover, the flip cover can be automatically unlocked.

[0108] The acceleration sensor 180E can detect the magnitude of the acceleration of the electronic device 100 in all directions (generally three axes). When the electronic device 100 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of the electronic device and is applied to applications such as horizontal and vertical screen switching and pedometers.

[0109] The distance sensor 180F is used to measure the distance. The electronic device 100 can measure the distance by infrared or laser. In some embodiments, when shooting a scene, the electronic device 100 can use the distance sensor 180F to measure the distance to achieve fast focusing.

[0110] The proximity light sensor 180G may include, for example, a light emitting diode (LED) and a light detector, such as a photodiode. The light emitting diode may be an infrared light emitting diode. The electronic device 100 emits infrared light outward through the light emitting diode. The electronic device 100 uses a photodiode to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that there is an object near the electronic device 100. When insufficient reflected light is detected, the electronic device 100 can determine that there is no object near the electronic device 100. The electronic device 100 can use the proximity light sensor 180G to detect that the user holds the electronic device 100 close to the ear to talk, so as to automatically turn off the screen to save power. The proximity light sensor 180G can also be used in leather case mode and pocket mode to automatically unlock and lock the screen.

[0111] The ambient light sensor 180L is used to sense the ambient light brightness. The electronic device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived ambient light brightness. The ambient light sensor 180L can also be used to automatically adjust the white balance when taking pictures. The ambient light sensor 180L can also cooperate with the proximity light sensor 180G to detect whether the electronic device 100 is in a pocket to prevent accidental touches.

[0112] The fingerprint sensor 180H is used to collect fingerprints. The electronic device 100 can use the collected fingerprint characteristics to implement fingerprint unlocking, access application locks, fingerprint photography, fingerprint call answering, etc.

[0113] The temperature sensor 180J is used to detect temperature. In some embodiments, the electronic device 100 uses the temperature detected by the temperature sensor 180J to execute a temperature processing strategy. For example, when the temperature reported by the temperature sensor 180J exceeds a threshold, the electronic device 100 reduces the performance of a processor located near the temperature sensor 180J to reduce power consumption and implement thermal protection. In other embodiments, when the temperature is lower than another threshold, the electronic device 100 heats the battery 142 to avoid abnormal shutdown of the electronic device 100 due to low temperature. In other embodiments, when the temperature is lower than another threshold, the electronic device 100 performs a boost on the output voltage of the battery 142 to avoid abnormal shutdown caused by low temperature.

[0114] The touch sensor 180K is also called a "touch panel". The touch sensor 180K can be set on the display screen 194, and the touch sensor 180K and the display screen 194 form a touch screen, also called a "touch screen". The touch sensor 180K is used to detect touch operations acting on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to the touch operation can be provided through the display screen 194. In other embodiments, the touch sensor 180K can also be set on the surface of the electronic device 100, which is different from the position of the display screen 194.

[0115] The bone conduction sensor 180M can obtain a vibration signal. In some embodiments, the bone conduction sensor 180M can obtain a vibration signal of a vibrating bone block of the vocal part of the human body. The bone conduction sensor 180M can also contact the human pulse to receive a blood pressure beat signal. In some embodiments, the bone conduction sensor 180M can also be set in an earphone and combined into a bone conduction earphone. The audio module 170 can parse out a voice signal based on the vibration signal of the vibrating bone block of the vocal part obtained by the bone conduction sensor 180M to realize a voice function. The application processor can parse the heart rate information based on the blood pressure beat signal obtained by the bone conduction sensor 180M to realize a heart rate detection function.

[0116] The key 190 includes a power key, a volume key, etc. The key 190 may be a mechanical key or a touch key. The electronic device 100 may receive key input and generate key signal input related to user settings and function control of the electronic device 100.

[0117] Motor 191 can generate vibration prompts. Motor 191 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, audio playback, etc.) can correspond to different vibration feedback effects. For touch operations acting on different areas of the display screen 194, motor 191 can also correspond to different vibration feedback effects. Different application scenarios (for example: time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

[0118] Indicator 192 may be an indicator light, which may be used to indicate charging status, power changes, messages, missed calls, notifications, etc.

[0119] The SIM card interface 195 is used to connect a SIM card. The SIM card can be connected to and separated from the electronic device 100 by inserting it into the SIM card interface 195 or pulling it out from the SIM card interface 195. The electronic device 100 can support 1 or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface 195 can support Nano SIM cards, Micro SIM cards, SIM cards, and the like. Multiple cards can be inserted into the same SIM card interface 195 at the same time. The types of the multiple cards can be the same or different. The SIM card interface 195 can also be compatible with different types of SIM cards. The SIM card interface 195 can also be compatible with external memory cards. The electronic device 100 interacts with the network through the SIM card to implement functions such as calls and data communications. In some embodiments, the electronic device 100 uses an eSIM, i.e., an embedded SIM card. The eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100.

[0120] In order to facilitate understanding of the embodiments of the present application, the system architecture of the embodiments of the present application is first described below.

[0121] Figure 3 The schematic diagram of the architecture of a system 10 provided in an embodiment of the present application is shown as an example. Figure 3 As shown, the system 10 includes an electronic device 100 and a server 200 .

[0122] The electronic device 100 includes a sound collection module 101, an abnormal signal detection framework 102 and an application 103. The sound collection module 101 can be used to collect sound and transmit the sound signal to the application 103. The abnormal signal detection framework 102 can be used to detect the sound signal received by the application 103 and determine whether there is an abnormal high-frequency signal in the sound signal. If it is determined that there is an abnormal high-frequency signal in the sound signal, the abnormal signal detection framework 102 can send an alarm prompt to the user and filter out the abnormal high-frequency signal in the sound signal. The application 103 can be used to send an acquisition request to the sound collection module 101, and the acquisition request is used to request the sound collection module 101 to collect the sound signal. The application 103 is also used to receive the sound signal sent by the sound collection module 101.

[0123] The server 200 includes a detection module 104. The detection module 104 can be used to obtain various environmental sound energy thresholds by using a detection model trained according to a sample sound data set.

[0124] The detection model may include various environmental identifiers and the environmental sound energy thresholds corresponding to the various environmental identifiers; or, the detection model comprehensively considers the environmental sound energy thresholds corresponding to the various environmental identifiers to obtain an average environmental sound energy threshold.

[0125] In some embodiments, after the server 200 has trained the detection model, it sends the detection model to the electronic device 100. The electronic device 100 receives the detection model sent by the server 200.

[0126] Alternatively, the server 200 periodically updates the detection model according to the sample sound data set, and the server 200 periodically sends the detection model to the electronic device 100. The electronic device 100 receives the detection model sent by the server 200, and periodically updates the detection model.

[0127] In other embodiments, the manufacturer of the electronic device 100 pre-sets a detection model in the electronic device 100. That is, when the user purchases the electronic device 100, turns it on and starts using it, the detection model already exists in the electronic device 100, and the electronic device 100 does not need to obtain the detection model from the server 200.

[0128] In other embodiments, the application developer of the first application pre-sets the detection model in the first application, and when the electronic device 100 receives a user operation to download the first application from the application store, the detection model will be downloaded to the electronic device 100 at the same time as the first application. In this way, the electronic device 100 does not need to obtain the detection model from the server 200.

[0129] In other embodiments, the electronic device 100 may train the detection model by collecting sound samples or obtaining sound samples from the Internet.

[0130] In the above-mentioned embodiment where the electronic device 100 does not need to obtain the detection model from the server 200, the detection model in the electronic device 100 is already trained, that is, the detection model includes each environmental identifier and the environmental sound energy threshold corresponding to each environmental identifier; or, the detection model comprehensively considers the environmental sound energy threshold corresponding to each environmental identifier and only includes the average environmental sound energy threshold. It can be understood that in the embodiment of the present application,

[0131] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0132] The detection model is used to detect whether there is an abnormal high-frequency signal in the sound signal. After acquiring the detection model, the electronic device 100 can determine whether there is an abnormal high-frequency signal in the acquired sound signal according to the detection model.

[0133] In some embodiments, the detection model comprehensively considers the environmental sound energy thresholds corresponding to each environmental identifier to obtain an average environmental sound energy threshold. When the electronic device 100 needs to detect the collected sound signal, the electronic device 100 first confirms the high-frequency energy value of the sound signal, and the electronic device 100 inputs the high-frequency energy value of the sound signal into the detection model. The detection model determines that if the high-frequency energy value of the sound signal is greater than the average environmental sound energy threshold, the detection model outputs a detection result, and the detection result is that there is an abnormal high-frequency signal in the sound signal.

[0134] In other embodiments, the detection model may include various environmental identifiers and the environmental sound energy thresholds corresponding to the various environmental identifiers. When the electronic device 100 needs to detect the collected sound signal, the electronic device 100 confirms the high-frequency energy value of the sound signal, and then confirms the current environmental identifier (such as a shopping mall) based on the sound signal. The electronic device 100 inputs the high-frequency energy value of the sound signal into the detection model, and confirms the environmental sound energy threshold corresponding to the current environmental identifier from the detection model based on the current environmental identifier. If the detection model determines that the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold corresponding to the current environmental identifier, the detection model outputs a detection result, and the detection result is that an abnormal high-frequency signal exists in the sound signal.

[0135] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0136] The abnormal signal detection framework 102 includes an abnormal signal detection module 1021 , a model management module 1022 , an alarm module 1023 , an alarm application 1024 , and a filtering module 1025 .

[0137] Among them, the abnormal signal detection module 1021 can be used to detect whether there is an abnormal high-frequency signal in the sound signal collected by the sound collection module 101. Among them, the abnormal signal detection module 1021 receives the detection model sent by the model management module 1022. The abnormal signal detection module 1021 can first calculate the high-frequency energy value of the sound signal, and then input the high-frequency energy value into the detection model. If the detection model determines that the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold (the environmental sound energy threshold can be the average environmental sound energy threshold, or the environmental sound energy threshold corresponding to the current environmental identifier), the detection model determines that there is an abnormal high-frequency signal in the sound signal.

[0138] The model management module 1022 is responsible for downloading and updating the detection model and sending the detection model to the abnormal signal detection module 1021 .

[0139] The alarm module 1023 may be used to send an alarm instruction to the alarm application 1024, where the alarm instruction is used to instruct the alarm application 1024 to display alarm information to the user.

[0140] The alarm application 1024 can be used to display alarm prompts to users, provide user operation interfaces, and obtain user operations (such as choosing to ignore alarms or choosing to confirm alarms).

[0141] The filtering module 1025 may be used to filter out abnormal high-frequency signals in the sound signal after receiving a user confirmation operation.

[0142] In one possible implementation, after the electronic device 100 receives the user's cancellation of the filtering operation, that is, the user chooses not to filter out the abnormal high-frequency signal in the sound signal, the alarm application 1024 sends a first prompt message to the alarm module 1023, and the first prompt message is used to prompt the alarm module 1023 to call the sound collection module 101, and the sound collection module 101 returns the sound signal without filtering out the abnormal high-frequency signal to the application 103.

[0143] In another possible implementation, after the electronic device 100 receives user confirmation of the filtering operation, that is, the user chooses to filter out the abnormal high-frequency signal in the sound signal, the alarm application 1024 sends a second prompt message to the alarm module 1023, and the second prompt message is used to prompt the alarm module 1023 to send a filtering instruction to the filtering module 1025, and the filtering module 1025 filters out the abnormal high-frequency signal in the sound signal. At the same time, the filtering module 1025 calls the sound collection module 101, and the sound collection module 101 returns the sound signal with the abnormal high-frequency signal filtered out to the application 103.

[0144] It should be noted that the above embodiments are only used to explain the present application and should not constitute a limitation. In some embodiments, the detection model is located in the server 200. That is, after the detection module 104 has trained the detection model, the server 200 does not need to send the detection model to the electronic device 100. At this time, after the electronic device obtains the sound signal, it can send the sound signal to the server. After receiving the sound signal, the server can determine whether the sound signal has an abnormal high-frequency signal according to the detection model, and return the determination result to the electronic device.

[0145] Exemplarily, after the electronic device 100 acquires the sound signal, it sends the collected sound signal to the server 200. The abnormal signal detection framework 102 in the server 200 confirms the high-frequency energy value of the sound signal, and the server 200 confirms the current environment identifier based on the sound signal, and matches the environmental sound energy threshold corresponding to the current environment identifier from the detection model. If the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold, the detection model outputs a detection result, and the detection result is that there is an abnormal high-frequency signal in the sound signal. The server 200 sends a warning instruction to the electronic device 100, the electronic device 100 receives and responds to the warning instruction, and the electronic device 100 issues a warning prompt to the user. The electronic device 100 generates a filtering instruction according to the user confirmation operation, and the electronic device 100 sends the filtering instruction to the server 200, and the abnormal signal detection framework 102 in the server 200 filters out the abnormal high-frequency signal in the sound signal. The server 200 returns the sound signal that filters out the abnormal high-frequency signal to the electronic device 100, and the electronic device 100 receives the sound signal that filters out the abnormal high-frequency signal and sends it to the application.

[0146] Understandably, Figure 3The detection model and abnormal signal detection framework 102 shown can be located in the server 200. At this time, the abnormal signal detection module 1021, the model management module 1022, and the filtering module 1025 in the abnormal signal detection framework 102 are located in the server 200; the alarm application 1024 and the alarm module 1023 in the abnormal signal detection framework 102 are located in the electronic device 100. There is no limitation on whether each module is located in the server 200 or in the electronic device 100. Another possible implementation is that the abnormal signal detection framework 102 can be located in the electronic device 100, and the detection model is located in the server 200. After the electronic device 100 collects the sound signal, the electronic device 100 confirms the high-frequency energy value of the sound signal, and the electronic device 100 confirms the current environment identifier according to the sound signal, and the electronic device 100 sends the current environment identifier to the server 200. The server 200 matches the environmental sound energy threshold corresponding to the current environment identifier from the detection model according to the current environment identifier. The server 200 sends the environmental sound energy threshold to the electronic device 100. If the electronic device 100 determines that the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold, then there is an abnormal high-frequency signal in the sound signal, and the server 200 sends a warning prompt to the electronic device 100, and the electronic device 100 displays an alarm message to the user. The electronic device 100 generates a filtering instruction according to the user confirmation operation, and the electronic device 100 sends the filtering instruction to the server 200. The abnormal signal detection framework 102 in the server 200 filters out the abnormal high-frequency signal in the sound signal, and the server 200 returns the sound signal with the abnormal high-frequency signal filtered out to the electronic device 100. The electronic device 100 receives the sound signal after the abnormal high-frequency signal is removed, and sends it to the application 103.

[0147] In other embodiments, the detection model is located in the electronic device 100. That is, after the detection module 104 trains the detection model, the server 200 sends the detection model to the electronic device 100 or the detection model already exists in the electronic device 100, and the electronic device 100 does not need to obtain the detection model from the server 200.

[0148] One possible implementation is that the detection model and the abnormal signal detection framework 102 can both be located in the electronic device 100. After the electronic device 100 obtains the sound signal, the abnormal signal detection framework 102 in the electronic device 100 can confirm the high-frequency energy value of the sound signal, and the electronic device 100 confirms the current environment identifier based on the sound signal, and matches the environmental sound energy threshold corresponding to the current environment identifier from the detection model. If the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold, the detection model outputs a detection result, and the detection result is that there is an abnormal high-frequency signal in the sound signal, and the electronic device 100 issues a warning prompt to the user. The electronic device 100 generates a filtering instruction based on the user's confirmation operation, and the abnormal signal detection framework 102 in the electronic device 100 filters out the abnormal high-frequency signal in the sound signal, and sends the sound signal with the abnormal high-frequency signal filtered out to the application.

[0149] Another possible implementation manner is that the detection model is located in the electronic device 100 , and the abnormal signal detection framework 102 may be located in the server 200 .

[0150] At this time, the abnormal signal detection module 1021, the model management module 1022, and the filtering module 1025 in the abnormal signal detection framework 102 are located in the server 200; the alarm application 1024 and the alarm module 1023 in the abnormal signal detection framework 102 are located in the electronic device 100. There is no limitation on whether each module is located in the server 200 or in the electronic device 100.

[0151] After collecting the sound signal, the electronic device 100 can send the sound signal to the server 200, and the abnormal signal detection framework 102 in the server 200 confirms the high-frequency energy value of the sound signal, and the electronic device 100 confirms the current environment identifier according to the sound signal, and matches the environmental sound energy threshold corresponding to the current environment identifier. The electronic device 100 sends the environmental sound energy threshold to the server 200, and the server 200 determines that the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold, and then determines that there is an abnormal high-frequency signal in the sound signal. The server 200 sends a warning prompt to the electronic device 100, and the electronic device 100 displays the warning information to the user. The electronic device 100 generates a filtering instruction according to the user confirmation operation, and the electronic device 100 sends the filtering instruction to the server 200. The abnormal signal detection framework 102 in the server 200 filters out the abnormal high-frequency signal in the sound signal, and the server 200 returns the sound signal after filtering out the abnormal high-frequency signal to the electronic device 100, and the electronic device 100 receives the sound signal after removing the abnormal high-frequency signal and sends it to the application.

[0152] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0153] like Figure 4 As shown, the functions of the modules included in the sound collection module 101, the detection module 104 and the abnormal signal detection framework 102 are introduced.

[0154] The sound collection module 101 may be composed of a microphone and a processor, etc. The microphone is used to collect sound signals, and the processor is used to convert the collected sound signals into analog signals.

[0155] For example, the electronic device 100 does not need to collect sound signals through the sound collection module 101. The sound signals obtained by the electronic device 100 can be obtained through a smart wearable device (such as a Bluetooth watch, a Bluetooth headset, etc.). The smart wearable device (such as a Bluetooth watch, a Bluetooth headset, etc.) establishes a communication connection with the electronic device 100. The smart wearable device (such as a Bluetooth watch, a Bluetooth headset, etc.) obtains the sound signal and sends the sound signal to the electronic device 100, and the electronic device 100 obtains the sound signal.

[0156] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0157] The model management module 1022 receives the detection model and sends it to the abnormal signal detection module 1021. In some embodiments, the detection model can be Figure 3 The detection module 104 is shown. In other embodiments, the detection model can also be trained by the electronic device itself.

[0158] The sound collection module 101 collects sound, and the sound collection module 101 sends the sound signal to the abnormal signal detection module 1021 .

[0159] The abnormal signal detection module 1021 detects whether there is an abnormal high-frequency signal in the sound signal. When an abnormal high-frequency signal is detected in the sound signal, the abnormal signal detection module 1021 sends an abnormal instruction, which is used to prompt the alarm module 1013 that the sound signal has an abnormal high-frequency signal.

[0160] At the same time, the abnormal signal detection module 1021 sends the sound signal to the filtering module 1025 .

[0161] Specifically, the abnormal signal detection module 1021 detects whether there is an abnormal high-frequency signal on the sound signal, including the abnormal signal detection module 1021 performing spectrum analysis on the sound signal to obtain the high-frequency energy value of the sound signal, and inputting the high-frequency energy value of the sound signal into the detection model. The detection model determines that if the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold, the detection model outputs a detection result, and the detection result is that there is an abnormal high-frequency signal in the sound signal. Then the abnormal signal detection module 1021 determines that there is an abnormal high-frequency signal in the sound signal.

[0162] The abnormal high-frequency signal refers to a high-frequency signal in a specified frequency band (eg, 18KHz-20KHz) in a sound signal when the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold.

[0163] The alarm module 1023 receives and responds to the abnormal instruction sent by the abnormal signal detection module 1021. In response to the abnormal instruction, the alarm module 1023 is used to send an alarm instruction to the alarm application 1024, and the alarm instruction is used to instruct the alarm application 1024 to send an alarm message to the user. There are many ways to express the alarm information, and the specific forms will be described in detail below.

[0164] The electronic device 100 receives the user operation and generates a filtering instruction according to the user operation, and the electronic device 100 sends the filtering instruction to the filtering module 1025 .

[0165] The filtering module 1025 receives and responds to the filtering instruction to filter out abnormal high-frequency signals in the sound signal.

[0166] The filtering module 1025 calls the sound collecting module 101 , and the sound collecting module 101 sends the sound signal with abnormal high-frequency signals filtered out to the application 1013 .

[0167] In some embodiments, the filtering module 1025 does not need to call the sound collection module 101 , and the filtering module 1025 directly sends the sound signal with the abnormal high-frequency signal filtered out to the application 1013 .

[0168] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0169] See also Figure 5 , Figure 5 is a flow chart of a method for filtering abnormal signals provided in an embodiment of the present application, which can be applied to Figure 3 In the system 10 described in the above, the system 10 may include an electronic device 100 and a server 200. The electronic device 100 may include a sound collection module 101, an abnormal signal detection framework 102 and an application 103. For a detailed introduction to the system 10, please refer to the aforementioned Figure 3 The embodiment shown is not described in detail here. The method may include:

[0170] S501. The server 200 uses the sound signal data sets in different environments to train and obtain the sound energy thresholds in different environments, obtain the average environmental sound energy threshold, and update the detection model.

[0171] Specifically, 1. The server 200 calculates the high-frequency energy value P of the ambient noise according to the ambient noise signal.z .

[0172] The server 200 obtains an ambient noise signal and reads the ambient noise signal of n time windows according to the ambient noise signal. The server 200 calculates the high-frequency energy value of the ambient noise signal of each time window under the full decibel scale (decibels full scale, DBFS) according to the actual high-frequency energy value of the ambient noise signal of each time window and stores it in queue 1, wherein DBFS refers to the decibel value based on the full scale in digital audio, and the high-frequency energy value calculation formula under the full decibel scale of each time window can be:

[0173]

[0174] As shown in formula (1), Pi represents the full decibel high-frequency energy value of the high-frequency environmental noise signal segment in the i-th time window, S i represents the actual high-frequency (e.g., 18KHz-20KHz) energy value of the high-frequency environmental noise signal segment in the i-th time window. The actual high-frequency energy value of the environmental noise signal can be obtained by short-time Fourier transform and other methods. Sj represents the maximum value that can be expressed by the number of bits required to store the high-frequency environmental noise signal segment in the j-th time window, that is, S j =2 j -1, j is a positive integer greater than or equal to 1 and less than or equal to n, and i is a positive integer less than or equal to n.

[0175] For example, setting S i =7841, and a 16-bit signed number is used to store each sound signal value, then S j The maximum value that can be expressed is 2 15 -1, according to formula (1), the full decibel high-frequency energy value of the ambient noise signal in the current time window can be obtained as -12.4.

[0176] The server 200 can calculate the full-decibel high-frequency energy values ​​of the high-frequency environmental noise signal segments in n time windows respectively through formula (1).

[0177] It is understood that formula (1) is only used to explain the present application and should not be construed as limiting.

[0178] The server 200 obtains the high-frequency energy value of the first group of environmental noise signals according to the average high-frequency energy of the full-decibel high-frequency energy values ​​of the high-frequency environmental noise signal segments of the n time windows, and stores the average energy in the queue 2. The calculation formula of the average high-frequency energy can be:

[0179]

[0180] As shown in formula (2), RMS represents the average high-frequency energy of the ambient noise signal, Pi It represents the full decibel high-frequency energy value of the high-frequency ambient noise signal segment in the i-th time window, where n is a positive integer and i is a positive integer less than or equal to n.

[0181] It is to be understood that formula (2) is only used to explain the present application and should not be construed as limiting.

[0182] Server 200 continues to acquire new noise signals from the environment, and reads sound signals of n time windows according to the new noise signals, discards the existing sound signals in the n time windows, calculates the average high-frequency energy of the new noise signals according to formula (1) and formula (2), and adds them to queue 2.

[0183] By analogy, the average high-frequency energy of m groups of environmental noise signals is obtained in the above manner and exists in queue 2.

[0184] The server 200 calculates the arithmetic mean of the average high-frequency energy of the m groups of environmental noise signals in queue 2 as the current environmental noise high-frequency energy value P z .

[0185] 2. The server 200 calculates the ambient sound energy threshold Pt based on the ambient sound signal sample data set.

[0186] The server 200 first extracts the first group of sound signals from the current environmental sound signal sample data set, and reads the sound signals of n time windows based on the first group of sound signals, and calculates the full decibel high-frequency energy values ​​of the n time windows according to the above formula (1).

[0187] In order to eliminate the high-frequency signal interference of the ambient noise signal caused by the frequency shift phenomenon, the present application subtracts the high-frequency energy value Pz of the current ambient noise signal from the full-decibel high-frequency energy value of the first group of sound signals calculated according to formula (1). The calculation formula can be:

[0188]

[0189] As shown in formula (3), Pwi represents the difference between the full-decibel high-frequency energy value of the high-frequency sound signal segment in the i-th time window and the high-frequency energy value Pz of the current ambient noise signal, and Pz is the high-frequency energy value of the current ambient noise.

[0190] Secondly, the server 200 can calculate the average high-frequency energy value of the first group of sound signals according to formula (2).

[0191] Then, the server 200 continues to extract m groups of sound signals from the current environmental sound signal data set, and calculates the average high-frequency energy values ​​of the m groups of sound signals through the method described in step 2.

[0192] Finally, the server 200 calculates the arithmetic mean of the average high frequency energy of the m groups of sound signals to obtain the ambient sound energy threshold Pt, and the calculation formula can be:

[0193] Pt=(Pw1+Pw2…Pwm) / mFormula (4)

[0194] As shown in formula (4), Pwm is the average high-frequency energy value of the mth group of sound signals, and m means that there are a total of m groups of sound signals in different environments.

[0195] It is to be understood that formula (4) is only used to explain the present application and should not be construed as limiting.

[0196] It can be known that the server 200 comprehensively considers the high-frequency energy values ​​of the sound signals in various environments, and the environmental sound energy threshold Pt represents the average environmental sound energy threshold.

[0197] In some embodiments, the server 200 can obtain each environment identifier and the environmental sound energy threshold corresponding to each environment identifier. At this time, each environment identifier and the environmental sound energy threshold corresponding to each environment identifier can be obtained by using the above formula (1), formula (2), and formula (3). For details, please refer to the above embodiment, and this application will not repeat them here.

[0198] In some embodiments, the detection model comprehensively considers the environmental sound energy thresholds corresponding to various environmental identifiers to obtain an average environmental sound energy threshold. The server 200 updates the detection model, and the detection model includes the average environmental sound energy threshold.

[0199] In other embodiments, the server 200 updates the detection model, which includes each environmental identifier and the environmental sound energy threshold corresponding to each environmental identifier.

[0200] The above embodiments are only used to explain the present application and should not be construed as limiting.

[0201] In some embodiments, after the server 200 updates the detection model, the server 200 sends the detection model to the electronic device 100, and the electronic device 100 receives the detection model.

[0202] Here, the electronic device 100 can refer to the detection model to determine whether there is an abnormal high-frequency signal in the sound signal. Figure 3 The embodiments described above will not be described in detail in this application.

[0203] In other embodiments, after the server 200 updates the detection model, the server 200 does not need to send the detection model to the electronic device 100 .

[0204] The detection model may include various environmental identifiers and the environmental sound energy thresholds corresponding to the various environmental identifiers. The electronic device 100 confirms the high-frequency energy value of the sound signal, and then confirms the current environmental identifier (e.g., a shopping mall) based on the sound signal, or the electronic device 100 obtains the first environmental information (e.g., location information and / or environmental sound), and confirms the current environmental identifier (e.g., a shopping mall) based on the first environmental information. The electronic device 100 sends the current environmental identifier to the server 200, and the detection model confirms the environmental sound energy threshold corresponding to the current environmental identifier based on the current environmental identifier, and the server 200 sends the environmental sound energy threshold corresponding to the current environmental identifier to the electronic device 100. The electronic device 100 determines whether the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold corresponding to the current environment. If the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold corresponding to the current environment, then there is an abnormal high-frequency signal in the sound signal.

[0205] Or the detection model comprehensively considers the environmental sound energy thresholds corresponding to each environmental identifier to obtain an average environmental sound energy threshold. When the electronic device 100 needs to detect the collected sound signal, the electronic device 100 sends the sound signal to the server 200. The server 200 confirms the high-frequency energy value of the sound signal and inputs the high-frequency energy value of the sound signal into the detection model. The detection model outputs the detection result. The detection result may be that there is an abnormal high-frequency signal in the sound signal or that there is no abnormal high-frequency signal in the sound signal. If the detection result is that there is an abnormal high-frequency signal in the sound signal, the server 200 sends the abnormal high-frequency signal in the sound signal to the electronic device 100.

[0206] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0207] S502 : The application 103 sends a request to the sound collection module 101 to obtain a sound signal.

[0208] In some embodiments, application 103 may respond to user operations, and application 103 sends a request to obtain a sound signal to the sound collection module 101. Exemplarily, application 103 may be a voice assistant, and the user operation may be a voice command. For example, the voice command may be the wake-up word "Xiao E Xiao E", and the voice assistant receives and responds to the wake-up word "Xiao E Xiao E", and the wake-up word "Xiao E Xiao E" triggers the voice assistant to turn on. In response to the voice assistant turning on, the voice assistant sends a request to obtain a sound signal to the sound collection module 101. Application 103 may also be a game application. The user interface displayed by application 103 includes a microphone control, which receives and responds to a single-click operation by the user. A game application sends a request to obtain a sound signal to the sound collection module 101, and the sound collection module 101 collects the sound signal and sends it to the receiving device through the communication module, so that the user can exchange game experience with the game friends of the receiving device. The application 103 may also be a social application. The user interface displayed by the application 103 includes a video call or audio call control. The video call or audio call control receives and responds to the user's single-click operation. The social application sends a request to obtain a sound signal to the sound collection module 101. The sound collection module 101 collects the sound signal and sends it to the receiving device through the communication module. In this way, the user can make a voice call or a video call with a friend through the social application.

[0209] In other embodiments, the application 103 may also send a request for obtaining a sound signal to the sound collection module 101 without user consent. The embodiment of the present application does not limit the triggering condition for sending the request for obtaining a sound signal.

[0210] S503 : In response to the request for obtaining a sound signal, the sound collection module 101 collects sound.

[0211] In some embodiments, after the sound collection module receives the request to obtain the sound signal, it will start to collect the sound. For example, in the video call application scenario, it is assumed that application 103 is a video call application. When the user sends a request to establish a video connection to a friend through application 103, and the friend receives the request to establish a video connection, at this time, application 103 sends a request to obtain a sound signal to the sound collection module 101, and the request is used to obtain an external sound signal. When the sound collection module receives the request to obtain the sound signal, it will start to collect the sound signal.

[0212] In some other embodiments, the application 103 does not need to send a request to obtain a sound signal to the sound collection module 101. The electronic device 100 may obtain the sound signal through a smart wearable device (such as a Bluetooth watch, a Bluetooth headset, etc.), the smart wearable device (such as a Bluetooth watch, a Bluetooth headset, etc.) establishes a communication connection with the electronic device 100, the smart wearable device (such as a Bluetooth watch, a Bluetooth headset, etc.) obtains the sound signal and sends the sound signal to the electronic device 100, and the electronic device 100 obtains the sound signal.

[0213] S504 , the sound collection module 101 sends the collected sound signal to the abnormal signal detection framework 102 .

[0214] After acquiring the sound signal, the sound collection module 101 sends the sound signal to the abnormal signal detection framework 102. For example, in the above-mentioned video call application scenario, the sound collection module 101 sends the collected sound signal to the abnormal signal detection framework 102 before sending it to the application 103. The abnormal signal detection framework 102 detects the sound signal to determine whether there is an abnormal high-frequency signal in the sound signal, thereby avoiding the leakage of user privacy.

[0215] S505 . The abnormal signal detection framework 102 sends an acquisition request to the server 200 .

[0216] The acquisition request is used to request the server 200 to acquire a detection model, where the detection model includes an average environmental sound energy threshold, or the detection model includes each environmental identifier and an environmental sound energy threshold corresponding to each environmental identifier.

[0217] The electronic device may perform this step before step S502 or after step S504. The embodiment of the present application does not limit the execution order of the steps.

[0218] It is understandable that this step is an optional step. In some embodiments, the detection model is generated by an electronic device. At this time, when the abnormal signal detection framework obtains the sound signal, it can determine whether the sound signal has an abnormal high-frequency signal based on the detection model obtained in advance or the detection model generated by the electronic device 100.

[0219] S506: The server 200 sends the detection model to the abnormal signal detection framework 102, where the detection model includes an average ambient sound energy threshold.

[0220] The abnormal signal detection framework 102 receives the detection model.

[0221] In some embodiments, the detection model includes various environmental identifiers and the environmental sound energy thresholds corresponding to each environmental identifier. The electronic device 100 can determine the current environmental identifier (for example, a shopping mall) based on the collected sound signals, and determine the environmental sound energy threshold from the detection model based on the current environmental identifier.

[0222] In some embodiments, the electronic device 100 may also acquire first environmental information, which may be location information and / or environmental sound.

[0223] The electronic device 100 sends the first environment information to the server 200. Based on the current position positioning technology, the server 200 can accurately identify the user's current environment identifier according to the user's current position information. The current environment identifier can be a shopping mall, a coffee shop, or a library.

[0224] It should be noted that the first environmental information including location information and / or environmental sound is only used to explain the present application and should not constitute a limitation. In a specific implementation, the first environmental information may include other content.

[0225] In other embodiments, the electronic device 100 may determine the detection model or the corresponding ambient sound energy threshold that needs to be obtained based on the first environmental information, and then request the server 200 to obtain the determined detection model or ambient sound energy threshold through an acquisition request.

[0226] S507 . The abnormal signal detection framework 102 performs spectrum analysis on the sound signal to obtain a high-frequency energy value P0 of the sound signal.

[0227] 1. The abnormal signal detection framework 102 calculates the environmental noise energy value Pm according to the environmental noise.

[0228] Some time before the application 103 responds to the request to obtain the sound, the sound collection module 101 collects a section of sound signal as the environmental noise.

[0229] For example, in the first two seconds before the application 103 responds to the request to obtain sound, the sound collection module 101 uses the collected sound signal as the environmental noise, and the abnormal signal detection framework 102 calculates the high-frequency energy value Pm of the environmental noise according to the environmental sound.

[0230] For example, in a video call application scenario, when a user sends a video connection request to a friend through application 103, before the friend receives the video connection request, application 103 has not started to collect sound signals. At this time, the sound collection module 101 will collect 2 seconds of environmental sound and calculate the environmental noise energy value through the 2 seconds of environmental sound. After the friend receives the video connection request, application 103 sends the collected sound signal to the friend.

[0231] Specific:

[0232] 1. The abnormal signal detection framework 102 obtains the high-frequency band (e.g., 18KH to 20KHz) signal of the ambient sound, reads the high-frequency ambient sound signal of n time windows, and calculates the full-decibel high-frequency energy value of the high-frequency ambient sound signal of n time windows respectively and exists in queue 1. The calculation formula can be:

[0233]

[0234] As shown in formula (5), Pa i is the full decibel high-frequency energy value of the high-frequency ambient sound signal segment in the i-th time window, Sa i represents the actual high-frequency energy value of the high-frequency ambient sound signal segment in the i-th time window. The high actual frequency (e.g., 18KHz-20KHz) energy value of the ambient sound signal can be obtained by short-time Fourier transform and other methods. Sj represents the maximum value that can be expressed by the number of bits required to store the high-frequency ambient noise signal segment in the j-th time window, that is, S j =2 j -1, j is a positive integer greater than or equal to 1 and less than or equal to n, and i is a positive integer less than or equal to n.

[0235] The abnormal signal detection framework 102 can calculate the full-decibel high-frequency energy values ​​of the high-frequency ambient sound signal segments of n time windows respectively through formula (5).

[0236] It is understood that formula (1) is only used to explain the present application and should not be construed as limiting.

[0237] 2. The abnormal signal detection framework 102 obtains the high-frequency energy value of the first group of environmental sound signals according to the average high-frequency energy of the full-decibel high-frequency energy value of the high-frequency environmental sound signal segments of the above n time windows, and stores the average energy in queue 2. The calculation formula of the average high-frequency energy can be:

[0238]

[0239] As shown in formula (6), Pu represents the average high-frequency energy of the ambient sound signal, P ai Represents the full decibel high-frequency energy value of the high-frequency ambient sound signal segment in the i-th time window, where i is a positive integer less than or equal to n.

[0240] It is understood that formula (6) is only used to explain the present application and should not be construed as limiting.

[0241] The abnormal signal detection framework 102 continues to obtain new environmental noise from the environment, and reads the sound signals of n time windows according to the new environmental noise, discards the existing sound signals in the n time windows, calculates the average high-frequency energy of the new environmental sound according to formula (5) and formula (6) and adds it to queue 2.

[0242] By analogy, the average high-frequency energy of w groups of environmental sounds is obtained in the above manner and exists in queue 2.

[0243] The abnormal signal detection framework 102 calculates the arithmetic mean of the average high-frequency energy of the w groups of environmental sounds in queue 2 as the environmental noise energy value Pm.

[0244] 3. The abnormal signal detection framework 102 calculates the high-frequency energy value P0 of the sound signal at the full decibel scale according to the actual high-frequency energy value of the sound signal.

[0245] After the application 103 responds to the sound acquisition request, the sound acquisition module 101 collects the sound, and the sound acquisition module 101 sends the sound signal to the abnormal signal detection framework 102. The abnormal signal detection framework 102 calculates the high-frequency energy value P0 of the sound signal under the full decibel scale according to the sound signal. Specifically:

[0246] First, the sound signals of n time windows are read, and the high-frequency energy value of the sound signal of each time window at the full decibel scale is calculated according to the actual high-frequency energy value of the sound signal of each time window and stored in queue 1. The calculation formula is:

[0247]

[0248] As shown in formula (7), Pb i is the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window, Sb i is the actual high-frequency energy value of the high-frequency signal segment in the i-th time window. The high-frequency energy value can be obtained by short-time Fourier transform and other methods to obtain the actual energy value of the high-frequency segment of the sound signal. Sj is the number of bits required by the electronic device to store the high-frequency signal segment in the i-th time window, that is, S j =2 j -1, for S j The explanation of can refer to the aforementioned embodiment, which will not be repeated here.

[0249] Secondly, in order to eliminate the high-frequency signal interference caused by the frequency shift phenomenon of the ambient noise signal, the present application subtracts the ambient noise energy value Pm from the full decibel high-frequency energy value of the sound signal calculated according to formula (7). The calculation formula can be:

[0250] Pc i =Pb i–Pm formula (8)

[0251] As shown in formula (8), Pb i is the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window, Pci is the difference between the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window and the ambient noise energy value, and Pm is the ambient noise energy value.

[0252] Finally, the average energy value of the difference between the full decibel high-frequency energy value of the sound signal in n time windows and the high-frequency energy value Pm of the ambient noise signal is taken as the high-frequency energy value P0 of the sound signal. The calculation formula can be:

[0253]

[0254] As shown in formula (9), Pci is the difference between the full-decibel high-frequency energy value of the high-frequency signal segment in the i-th time window and the ambient noise energy value, i is a positive integer less than or equal to n; P0 represents the high-frequency energy value of the sound signal.

[0255] S508 : The abnormal signal detection framework 102 determines whether the high-frequency energy value P0 of the sound signal is greater than the average ambient sound energy threshold value Pt.

[0256] The abnormal signal detection framework 102 compares the high-frequency energy value P0 of the sound signal with the average environmental sound energy threshold. If the high-frequency energy value P0 of the sound signal is less than the average environmental sound energy threshold, the electronic device 100 continues to obtain new sound signals from the current environment and calculates the high-frequency energy value P0 of the new sound signal until the high-frequency energy value P0 of the new sound signal is greater than the average environmental sound energy threshold.

[0257] If the abnormal signal detection framework 102 does not detect that the high-frequency energy value P0 of the new sound signal is greater than the average environmental sound energy threshold, it means that there is no abnormal high-frequency signal in the user's current environment.

[0258] S509: When the high-frequency energy value P0 of the sound signal is greater than the average ambient sound energy threshold, the abnormal signal detection framework 102 sends an alarm prompt to the user.

[0259] The abnormal signal detection framework 102 determines that the high-frequency energy value P0 of the sound signal is greater than the average environmental sound energy threshold, and then an abnormal high-frequency signal exists in the current environment. The abnormal signal detection framework 102 outputs an alarm prompt to the user.

[0260] The warning prompt may be a prompt box displayed on the user interface of the electronic device 100, and the prompt box is used to prompt the user that an abnormal high-frequency signal exists in the current environment.

[0261] The warning prompt can also be a prompt bar displayed on the edge of the display screen of the electronic device 100. The prompt box can be static or flashing, which is used to prompt the user that there is an abnormal high-frequency signal in the current environment. The prompt bar can receive a user click operation. In response to the user's click operation, the user interface of the electronic device 100 displays the above prompt box. The purpose of displaying the prompt bar is that it does not affect the user's current operation. For example, if the user is making a video call, the prompt bar will not affect the user's call quality (such as freezes).

[0262] The warning prompt may also be a voice prompt, for example, the electronic device 100 plays an alarm sound through a speaker.

[0263] The warning prompt may also be vibration of the electronic device 100.

[0264] The warning prompt may also be a prompt message displayed in the status bar of the electronic device 100.

[0265] The warning prompt may also be the flashlight of the electronic device 100 flashing.

[0266] It is understandable that the alarm prompt may be a combination of two or more of the above alarm prompt notification methods, and this application does not limit this.

[0267] In some possible embodiments, when the abnormal signal detection framework 102 detects an abnormal high-frequency signal, the electronic device 100 outputs an alarm prompt to the user only once. When the abnormal signal detection framework 102 detects an abnormal high-frequency signal again, the abnormal signal detection framework 102 directly filters out the abnormal high-frequency signal in the sound signal, and the electronic device 100 no longer outputs an alarm prompt to the user, which does not affect the user's current operation.

[0268] S510 , the abnormal signal detection framework 102 receives a filtering instruction.

[0269] S511 . In response to the filtering instruction, the abnormal signal detection framework 102 filters out abnormal high-frequency signals in the sound signal.

[0270] The abnormal high-frequency signal refers to a high-frequency signal in a specified frequency band (eg, 18KHz-20KHz) in the sound signal when the high-frequency energy value of the sound signal is greater than the ambient sound energy threshold.

[0271] After the user chooses to filter out abnormal high-frequency signals in the sound signal, the electronic device 100 generates a filtering instruction based on the user's operation, and the electronic device 100 sends the filtering instruction to the abnormal signal detection framework 102. The abnormal signal detection framework 102 receives and responds to the filtering instruction, and the abnormal signal detection framework 102 filters out abnormal high-frequency signals in the sound signal.

[0272] Specifically, after the user chooses to perform a filtering operation, the filtering module 1025 in the abnormal signal detection framework 102 may use a low-pass filter or a band-stop filter to process the sound signal, that is, filter out abnormal high-frequency signals in the sound signal.

[0273] Here we take the band-stop filter as an example, the form of the filter is:

[0274] y IRR (m)=b(0)x(m)+b(1)x(m-1)+…+b(p)x(mp)-a(1)y IRR (m-1)-a(2)y IRR (m-2)-…--a(q)y IRR (mq)Formula (10)

[0275] As shown in formula (10), x(m) represents the sound signal collected at time m, m represents a certain moment of the sound signal, p and q represent a certain moment between time 0 and time m, a(q) refers to the correlation coefficient of the filter at time q, and b(p) refers to the correlation coefficient of the filter at time p.

[0276] S512 , the abnormal signal detection framework 102 calls the sound collection module 101 .

[0277] S513 , the sound collection module 101 sends the sound signal with abnormal high-frequency signals filtered out to the application 103 .

[0278] The abnormal signal detection framework 102 calls the sound collection module 101, and the sound collection module 101 sends the sound signal with the abnormal high-frequency signal filtered out to the application 103, so as not to affect the user's operation.

[0279] In the above video call application scenario, the sound collection module 101 sends the sound signal with abnormal high-frequency signals filtered out to the communication module in the electronic device 100, and the communication module is used to send the sound signal with abnormal high-frequency signals filtered out to the receiving device.

[0280] In some embodiments, the abnormal signal detection framework 102 does not need to call the sound collection module 101 , and the abnormal signal detection framework 102 directly sends the sound signal after filtering out the abnormal high-frequency signal to the application 103 .

[0281] For example, in the above-mentioned video call application scenario, the abnormal signal detection framework 102 does not need to call the sound collection module 101. The abnormal signal detection framework 102 directly sends the sound signal that filters out the abnormal high-frequency signal to the communication module in the electronic device 100. The communication module is used to send the sound signal that filters out the abnormal high-frequency signal to the receiving device.

[0282] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0283] like Figure 6 As shown, Figure 6 A flowchart of another abnormal signal filtering method provided in an embodiment of the present application.

[0284] S601: The electronic device 100 obtains a detection model.

[0285] In some embodiments, the electronic device 100 may obtain the detection model from the server 200 .

[0286] In other embodiments, the detection model may also be preset in the electronic device 100. Please do not elaborate on it here.

[0287] The electronic device 100 may obtain the detection model before the abnormal high-frequency signal detection function is turned on, or may obtain the detection model after the abnormal high-frequency signal detection function is turned on, which is not limited in the present application.

[0288] In some embodiments, the alarm application 1024 exists in the electronic device 100 in the form of a system application.

[0289] The above embodiments are only used to explain the present application and should not be construed as limiting.

[0290] The abnormal high-frequency signal detection function in the electronic device 100 may be enabled by the electronic device 100 receiving a user operation to enable the abnormal high-frequency signal detection function, or it may be enabled automatically by the electronic device 100, which is not limited in the present application.

[0291] like Figure 7A-7C As shown, Figure 7A-7C This is a UI diagram showing the alarm application 1024 receiving a user operation to enable the abnormal high-frequency signal detection function.

[0292] Fig. 7A The figure is a UI diagram of a setting user interface of the alarm application 1024 in the electronic device 100 .

[0293] like Fig. 7A As shown, Fig. 7A A setting user interface 700 of the electronic device 100 is included.

[0294] The setting user interface 700 includes one or more function switch controls, for example, an airplane mode control 7001 , a wireless LAN control 7002 , a Bluetooth control 7003 , an alarm application control 7004 , and a notification control 7005 .

[0295] Among them, the flight mode control 7001 displays "off", the wireless LAN control 7002 displays "on", the Bluetooth control 7003 displays "on", the alarm application control 7004 displays "off", and the notification control 7005 displays "on".

[0296] It should be noted that the setting user interface 700 may include more or fewer setting controls, and this application does not limit this.

[0297] The alarm application control 7004 can receive a user operation (such as a single click), and in response to the user operation (such as a single click), the electronic device 100 displays the following Figure 7B Alarm application user interface 710 is shown.

[0298] Figure 7B A UI diagram for setting a user interface for an alarm application in the electronic device 100.

[0299] The alarm application setting user interface can receive a user operation to turn on or off the abnormal high-frequency signal detection function, and can also receive a user operation to set the time for the abnormal high-frequency signal detection function.

[0300] The alarm application user interface 710 includes an alarm application control 7004, which displays "off". When the alarm application control 7004 displays "off", the abnormal high-frequency signal detection function is turned off; a detection time control 7006, which displays "07:00-22:00", that is, the electronic device 100 detects whether the sound signal includes abnormal high-frequency signals during the time period of "07:00-22:00". During the remaining time periods, the user is resting at home, the abnormal high-frequency signal detection function is turned off, and the electronic device 100 does not perform detection, which can save consumption.

[0301] Figure 7C This is a UI diagram showing the alarm application in the electronic device 100 receiving a user operation to enable the abnormal high-frequency signal detection function.

[0302] When the alarm application control 7004 displays "off", the alarm application control 7004 can receive a user operation (such as a single click) to turn on the abnormal high-frequency signal detection function.

[0303] When the alarm application control 7004 displays "on", the alarm application control 7004 can receive a user operation (such as a single click) to turn off the abnormal high-frequency signal detection function.

[0304] Figure 7D-7F A UI diagram showing the electronic device 100 receiving a user operation to set the activation time of the abnormal high-frequency signal detection function.

[0305] like Fig.7DAs shown, the detection time control 7006 can receive a user operation (eg, a single click) to set the start time of the abnormal high-frequency signal detection function.

[0306] In response to the user clicking the detection time control 7006, the electronic device 100 displays the following Fig. 7E The user interface 720 for setting the detection time shown includes a time selection control 7007 and a save control 7008 .

[0307] Among them, the time selection control 7007 can receive a single-finger swipe up or down operation by the user to select the time the user wants to set. For example, if the user sets the detection time to "06:00-21:00", the abnormal high-frequency signal detection function is turned on during the time period "06:00-21:00", that is, the electronic device 100 detects whether the sound signal includes an abnormal high-frequency signal during the time period "06:30-21:30".

[0308] like Figure 7F As shown, the time selection control 7007 in the user interface 720 is displayed as "06:30-21:30". The save control 7008 can receive a user operation (e.g., a single click), and in response to the user (e.g., a single click), the electronic device 100 sets the activation time period of the abnormal high-frequency signal detection function to "06:30-21:30".

[0309] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0310] The electronic device 100 may also automatically enable an abnormal signal detection function.

[0311] When the abnormal signal detection function in the electronic device 100 is turned on, the electronic device 100 detects the collected sound signal to detect whether there is an abnormal high-frequency signal in the sound signal.

[0312] In some embodiments, when the electronic device 100 is in the power-on state, the electronic device 100 turns on the abnormal signal detection function.

[0313] In some embodiments, when the electronic device 100 turns off the screen, the electronic device 100 turns off the abnormal signal detection function.

[0314] In some embodiments, the electronic device 100 is in a fixed location (such as a library) for a long time. When the electronic device 100 carried by the user first arrives at the location, the electronic device 100 turns on the abnormal signal detection function for a period of time, and the electronic device 100 does not detect abnormal high-frequency signals in the collected sound signals. Since the electronic device 100 is in the location (such as a library) for a long time, the surrounding environment of the location is single, so the abnormal signal detection function can be turned off after being turned on for a period of time to save consumption.

[0315] In some embodiments, the electronic device 100 may selectively enable an abnormal signal detection function based on historical location information of the electronic device 100 .

[0316] For example, during the time period "8:00-22:00", the electronic device 100 turns on the abnormal signal detection function because the user is resting at home during the time period "22:00-8:00". The electronic device 100 detects that the historical location information of the electronic device 100 (such as the location of the user's home) during the time period "22:00-8:00" is basically the same, so the abnormal signal detection function can be turned off to reduce consumption.

[0317] For another example, during the time period "9:00-17:00" from Monday to Friday, the electronic device 100 detects that the historical location information (such as the company location) of the electronic device 100 during the time period "9:00-17:00" is basically the same, and the company's environment is relatively simple, then the electronic device 100 can turn off the abnormal signal detection function.

[0318] For another example, between the time periods "7:00-9:00" and "17:00-19:00" from Monday to Friday, the electronic device 100 turns on the abnormal signal detection function. Based on the historical location information, the electronic device 100 determines that the location information of the electronic device 100 during the time period "7:00-9:00" is from the first location to the second location, and the location information of the electronic device 100 during the time period "17:00-19:00" is from the second location to the first location. It can be determined that the user is on the way to work and get off work between the above two time periods. Because the surrounding environment on the way to work and get off work is relatively complex, there may be a risk of obtaining user privacy due to hidden communication technology. The electronic device 100 turns on the abnormal signal detection function to prevent the leakage of user privacy information.

[0319] In some embodiments, the electronic device 100 may selectively enable an abnormal signal detection function based on user behavior habits collected by the electronic device 100.

[0320] For example, the electronic device 100 detects that the website that the user frequently logs in may be a high-risk website based on the user's online habits. The high-risk website can obtain the user's terminal information and user personal information. When the user accesses such a website through the electronic device 100, the electronic device 100 turns on the abnormal signal detection function to prevent such a website from obtaining the user's private information.

[0321] In some embodiments, the server may send an abnormal signal detection function activation notification to the electronic device 100 , and in response to the activation notification, the electronic device 100 activates the abnormal signal detection function.

[0322] The server can collect information reported by multiple electronic devices. When one or more of the multiple electronic devices detect special information in a specific area (such as a shopping mall or supermarket), the one or more electronic devices report the presence of special signals in the specific area to the server, and the server summarizes the information reported by the one or more electronic devices.

[0323] Before the user arrives at this specific area, the server can send a notification to the electronic device 100 carried by the user to turn on the abnormal signal detection function. This notification can be used to notify the electronic device 100 to turn on the abnormal signal detection function when it is a certain distance (for example, 100 meters) from this specific area.

[0324] Alternatively, when the user arrives at the specific area, the server sends a notification to the electronic device 100 carried by the user to activate the abnormal signal detection function. In response to the notification, the electronic device 100 carried by the user activates the abnormal signal detection function.

[0325] In some other embodiments, the server may send an advertisement of an advertising service provider in a specific area (such as a shopping mall or supermarket). When the server 200 detects the presence of special information in the advertisement, the server 200 sends a notification to the user's electronic device to enable the abnormal signal detection function. This notification can be used to notify the electronic device to enable the abnormal signal detection function when it is a certain distance (such as 100 meters) from the specific area or when the user arrives at the specific area.

[0326] In this way, third parties can be prevented from obtaining users' private information without the users' knowledge and authorization.

[0327] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0328] S602: The electronic device 100 obtains a sound signal.

[0329] The electronic device 100 can receive user operations and obtain sound signals through the sound collection module.

[0330] The user operation may be a voice command. For example, the voice command may be a wake-up word "Xiao E Xiao E". The electronic device 100 receives and responds to the wake-up word "Xiao E Xiao E". The wake-up word "Xiao E Xiao E" triggers the voice assistant to start. In response to the voice assistant starting, the electronic device 100 starts to collect sound signals.

[0331] The user operation may also be an operation in which the user triggers a social application to talk to a friend. In response to the user operation, the electronic device 100 acquires a sound signal through a sound collection module and sends the sound signal to the electronic device on the friend's side.

[0332] In some embodiments, the electronic device 100 may also obtain sound signals through a smart wearable device (such as a Bluetooth watch, a Bluetooth headset, etc.). The smart wearable device (such as a Bluetooth watch, a Bluetooth headset, etc.) establishes a communication connection with the electronic device 100. The smart wearable device (such as a Bluetooth watch, a Bluetooth headset, etc.) obtains the sound signal and sends the sound signal to the electronic device 100, and the electronic device 100 obtains the sound signal.

[0333] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0334] S603: The electronic device 100 determines whether there is an abnormal high-frequency signal in the sound signal according to the detection model.

[0335] After the electronic device 100 confirms the high-frequency energy value P0 of the sound signal based on the acquired sound signal, the electronic device 100 inputs the high-frequency energy value of the sound signal into the detection model. If the electronic device 100 determines that the high-frequency energy value P0 of the sound signal is greater than the average ambient sound energy threshold, then there is an abnormal high-frequency signal in the sound signal.

[0336] Alternatively, after the electronic device 100 confirms the high-frequency energy value P0 of the sound signal based on the acquired sound signal, the electronic device 100 inputs the high-frequency energy value of the sound signal into the detection model, and the electronic device 100 confirms the ambient sound energy threshold corresponding to the current environment identifier from the detection model based on the sound signal. If the electronic device 100 determines that the high-frequency energy value P0 of the sound signal is greater than the ambient sound energy threshold corresponding to the current environment identifier, then there is an abnormal high-frequency signal in the sound signal.

[0337] Here, the electronic device 100 can determine the high-frequency energy value P0 of the sound signal according to the acquired sound signal. Figure 5 The embodiment described in S507 will not be repeated in this application.

[0338] The electronic device 100 can refer to the detection model to determine whether there is an abnormal high-frequency signal in the sound signal. Figure 5 The embodiment described in S501 will not be repeated in this application.

[0339] If the electronic device 100 determines that there is an abnormal high-frequency signal in the sound signal, the electronic device 100 may send an alarm prompt to the user.

[0340] Here, the warning tips can refer to Figure 5 The embodiment described in S509 of the embodiment will not be described in detail here.

[0341] For example, a user is in a shopping mall, music is playing in the mall, and the user is making a video call with a friend. The electronic device 100 collects sound signals through the sound collection module. If there is hidden communication information (such as abnormal high-frequency signals) in the music played in the mall, the hidden communication information (such as abnormal high-frequency signals) can steal the user's privacy information in the electronic device 100. The electronic device 100 can detect and filter out the hidden communication information (such as abnormal high-frequency signals) in the sound signal.

[0342] Figure 8A-8C A UI diagram showing an alarm prompt on the electronic device 100.

[0343] Fig. 8A A UI diagram including a user interface 801 for a user to have a video call with a friend.

[0344] The electronic device 100 collects the user's image and sound signals and sends them to the user's friend terminal device. At the same time, the electronic device 100 receives and displays the user's friend image and sound signals collected by the user's friend terminal device.

[0345] The user interface 801 includes a first screen 8001 , a second screen 8002 , a control 8003 for switching the front and back shooting directions, a control 8004 for ending a call, and a control 8005 for mute.

[0346] Among them, the first screen 8001 is a user image captured by the electronic device 100.

[0347] The second screen 8002 is an image of the user's friend received and displayed by the electronic device 100.

[0348] The flip shooting direction control 8003 can receive user operations (such as single clicks). If the current shooting direction of the electronic device 100 is forward (such as a selfie direction), the electronic device 100 will convert the shooting direction to backward; if the current shooting direction of the electronic device 100 is backward, the electronic device 100 will convert the shooting direction to forward (such as a selfie direction).

[0349] The end call control 8004 can receive a user operation (eg, a single click), and the electronic device 100 ends the current video call.

[0350] The mute control 8005 can receive a user operation (eg, a single click), and the electronic device 100 will no longer send the sound signal collected by the electronic device 100 to the user's friends.

[0351] In a possible implementation, when the electronic device 100 detects that there is hidden communication information (such as an abnormal high-frequency signal) in the current environment, such as Figure 8BAs shown, the user interface 801 of the electronic device 100 displays a prompt box 8006, which is used to prompt the user that there is hidden communication information (such as abnormal high-frequency signals) in the current environment. The prompt box 8006 includes the prompt information "Abnormal high-frequency signals are detected, do you want to filter them out?", a "Yes" control 8007, and a "No" control 8008.

[0352] Among them, the "yes" control 8007 can receive user operations (such as single clicks), and in response to the user operations (such as single clicks), the abnormal signal detection framework 102 will filter out hidden communication information (such as abnormal high-frequency signals) in the sound signal.

[0353] The "No" control 8008 may receive a user operation (eg, a single click), and in response to the user operation (eg, a single click), the abnormal signal detection framework 102 does not filter out hidden communication information (eg, abnormal high-frequency signals) in the sound signal.

[0354] In another possible implementation, Figure 8C As shown, the user interface 801 displays a prompt bar 8009, and the prompt bar 8009 is used to prompt the user that there is hidden communication information (such as abnormal high-frequency signals) in the current environment. This does not affect the user's current operation.

[0355] The prompt bar 8009 can receive a user operation (such as a click), and in response to the user click operation, the user interface 801 displays the following Figure 8B Prompt box 8006 is shown.

[0356] S604: The electronic device 100 filters out abnormal high-frequency signals in the sound signal according to the filtering operation confirmed by the user.

[0357] In some embodiments, after the electronic device 100 detects the presence of an abnormal high-frequency signal in a sound signal, the user interface of the electronic device 100 will display an alarm prompt, which can receive user operations (such as a single click). In response to the user operation, the electronic device 100 filters out the abnormal high-frequency signal in the sound signal.

[0358] In some embodiments, when the electronic device 100 detects an abnormal high-frequency signal, the electronic device 100 directly filters out the abnormal high-frequency signal in the sound signal, and the electronic device 100 does not output an alarm prompt to the user.

[0359] For example, Fig.8D A UI diagram showing the electronic device 100 displaying the prompt message “abnormal high-frequency signal has been filtered out”.

[0360] In response to a user click Figure 8B The "yes" control 8007 shown, such as Fig.8DAs shown, the user interface 801 of the electronic device 100 displays a prompt box 8010, which is used to prompt the user that the electronic device 100 has filtered out the abnormal high-frequency signal in the sound signal. The prompt box 8010 includes the prompt information "abnormal high-frequency signal has been filtered out".

[0361] It should be noted that the above embodiments are only used to explain the present application and should not be construed as limiting.

[0362] In other possible embodiments, the user is driving, the user interface of the electronic device 100 is displaying a navigation route, and the Bluetooth headset has established a communication connection with the electronic device 100. When the electronic device 100 detects the presence of an abnormal high-frequency signal nearby, the user interface of the electronic device 100 does not display an alarm prompt, which does not affect the user's navigation route. Instead, a voice prompt message is played through the Bluetooth headset to remind the user that an abnormal high-frequency signal is nearby, and the user can use voice input to inform the electronic device 100 to filter out the abnormal high-frequency signal.

[0363] In other possible embodiments, the Bluetooth watch has established a communication connection with the electronic device 100. When the electronic device 100 detects that there is an abnormal high-frequency signal nearby, the electronic device 100 does not display a warning message, but prompts the abnormal high-frequency signal through the Bluetooth watch. The prompt method can be a watch vibration, voice prompt, etc. The user informs the electronic device 100 to filter out the abnormal high frequency through voice input. In other possible embodiments, after the user filters out the abnormal high-frequency signal detected by the electronic device 100, the user can report the abnormal high-frequency signal to the server 200, and the server receives the abnormal high-frequency signal information uploaded by the electronic device 100. The server 200 counts the abnormal high-frequency signal information uploaded by each user in each region, and counts the probability of abnormal high-frequency signal information in each region. The server informs the map manufacturer of the region with a high probability of abnormal high-frequency signal information. When the user uses the map to plan a route, the navigation route displayed on the map can avoid the user passing through the region with a high probability of abnormal high-frequency signal information, or the map prompts the user through voice when the user approaches the region with a high probability of abnormal high-frequency signal information "There is an abnormal high-frequency signal nearby, which is easy to cause personal information leakage, please detour", so as to avoid the user's personal privacy information from being leaked.

[0364] It should be noted that the above embodiments can be used with Figures 3 to 5 The embodiments shown are combined.

[0365] See also Fig. 9 , Fig. 9 A schematic diagram of a device provided in an embodiment of the present application. Device 910 includes a sound collector 9001 and a processor 9002. Among them:

[0366] The sound collector 9001 can be used to collect sound signals and transmit the sound signals to applications of the electronic device 100 .

[0367] Processor 9002 may be used to process the sound signal, specifically including:

[0368] 1. The processor 9002 determines the environmental sound energy threshold according to the sound signal.

[0369] 2. The processor 9002 determines the high-frequency energy value of the sound signal based on the sound signal.

[0370] 3. The processor 9002 determines the high-frequency energy value of the sound signal and the ambient sound energy threshold. If the high-frequency energy value of the sound signal is greater than the current ambient sound energy threshold, it is determined that an abnormal high-frequency signal exists in the sound signal.

[0371] 4. Processor 9002 sends an alarm message to the user.

[0372] 5. The processor 9002 filters out abnormal high-frequency signals in the sound signal according to the user's filtering operation.

[0373] 6. The processor 9002 calls the sound collector 9001 , and the sound collector 9001 sends the sound signal with abnormal high-frequency signals filtered out to the application of the electronic device 100 .

[0374] The sound collector 9001 can execute the various steps executed by the aforementioned sound collection module. For details, please refer to the aforementioned embodiment, which will not be repeated here.

[0375] The processor 9002 may execute each step executed by the aforementioned abnormal signal detection framework. For details, reference may be made to the aforementioned embodiment, which will not be described in detail here.

[0376] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for filtering abnormal signals, characterized in that: include: The electronic device receives a request for obtaining a sound signal; In response to the sound signal acquisition request, the electronic device acquires a sound signal; The electronic device acquires environmental sound; The electronic device determines the environmental noise energy value according to the environmental sound; The electronic device determines the high-frequency energy value of the sound signal according to the actual high-frequency energy value of the sound signal and the energy value of the ambient noise; If the high-frequency energy value of the sound signal is greater than the environmental sound energy threshold, the electronic device sends a prompt message to the user, where the prompt message is used to prompt that an abnormal high-frequency signal exists in the sound signal.

2. The method according to claim 1, characterized in that After the electronic device sends a prompt message to the user, the method further includes: The electronic device receives a filtering operation by a user; In response to the filtering operation, the electronic device filters out the abnormal high-frequency signal.

3. The method according to claim 2, characterized in that The method further comprises: The electronic device sends the sound signal after filtering out the abnormal high-frequency signal to a receiving device.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: The electronic device acquires first environmental information, where the first environmental information includes location information and / or environmental sound; The electronic device determines the environmental sound energy threshold according to the first environmental information.

5. The method according to claim 1, characterized in that The electronic device determines the high-frequency energy value of the sound signal according to the actual high-frequency energy value of the sound signal and the environmental noise energy value, specifically including: The electronic device acquires a high-frequency signal in the sound signal; The electronic device divides the high-frequency signal into high-frequency signal segments of n time windows, where n is a positive integer; The electronic device calculates actual high-frequency energy values ​​of the high-frequency signal segments in the n time windows; The electronic device calculates the full decibel high-frequency energy value of the high-frequency signal segment in the n time windows according to the actual high-frequency energy value of the high-frequency signal segment in the n time windows; The electronic device determines the high-frequency energy value of the sound signal according to the full-decibel high-frequency energy value of the high-frequency signal segment in the n time windows and the environmental noise energy value.

6. The method according to claim 5, characterized in that The electronic device calculates the full decibel high-frequency energy value of the high-frequency signal segment in the n time windows according to the actual high-frequency energy value of the high-frequency signal segment in the n time windows, specifically including: The electronic device determines the full decibel high-frequency energy value of the high-frequency signal segment in the n time windows by the following formula: Among them, Pb i is the full decibel high-frequency energy value of the high-frequency signal segment in the i-th time window, Sb i is the actual high-frequency energy value of the high-frequency signal segment in the i-th time window, Sj is the number of bits required for the electronic device to store the high-frequency signal segment in the j-th time window, j is a positive integer greater than or equal to 1 and less than or equal to n, and i is a positive integer less than or equal to n.

7. The method according to claim 5, characterized in that The electronic device determines the high-frequency energy value of the sound signal according to the full-decibel high-frequency energy value of the high-frequency signal segment in the n time windows and the environmental noise energy value, specifically including: The electronic device determines the high-frequency energy value of the sound signal by the following formula: Pc i =Pb i –Pm; Among them, Pb i is the full-decibel high-frequency energy value of the high-frequency signal segment in the i-th time window, Pci is the difference between the full-decibel high-frequency energy value of the high-frequency signal segment in the i-th time window and the ambient noise energy value, Pm represents the ambient noise energy value, i is a positive integer less than or equal to n; P0 represents the high-frequency energy value of the sound signal.

8. The method according to any one of claims 1 to 3, characterized in that: The frequency band of the abnormal high-frequency signal includes 18KHz-20KHz.

9. A device for filtering abnormal signals, characterized in that: One or more processors, one or more memories, and a sound collector; the one or more memories and the sound collector are coupled to the one or more processors, the one or more memories are used to store computer program codes, the computer program codes include computer instructions, and one or more processors call the computer instructions to enable the device to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 8.

Images