Processing method, device, equipment and medium

Abstract

The invention provides a processing method and device, equipment and a medium. The processing method comprises the following steps: acquiring a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval; if the first time-frequency feature and the second time-frequency feature have a first similarity, determining that the nearby state of the target equipment is a first state; if the first time-frequency feature and the second time-frequency feature have a second similarity, determining that the nearby state of the target equipment is a second state; wherein the second time-frequency feature is a time-frequency feature corresponding to the sound wave signal received by the target object which does not exist near the target equipment.

Description

Technical Field

[0001] The present disclosure relates to the technical field of ultrasonic detection and signal processing, and in particular to a processing method, device, equipment and medium. Background Art

[0002] Ultrasonic detection technology can detect objects or obstacles in the surrounding environment by sending and receiving ultrasonic signals, and determine their distance, position and size, so as to achieve real-time perception and detection of objects in the surrounding environment. However, traditional detection methods have low detection accuracy, misjudgment, and low detection sensitivity for different scenarios, which makes it difficult to meet actual detection needs. Summary of the invention

[0003] One aspect of the present disclosure provides a processing method, including: obtaining a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval; if there is a first similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a first state; if there is a second similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a second state; wherein the second time-frequency feature is a time-frequency feature corresponding to a sound wave signal received when there is no target object near the target device.

[0004] According to an embodiment of the present disclosure, the first state represents that a target object exists near the target device, and the second state represents that a target object does not exist near the target device.

[0005] According to an embodiment of the present disclosure, the processing method also includes: if there is a third similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a third state, the third state characterizing that there is a target object approaching and / or moving away near the target device.

[0006] According to an embodiment of the present disclosure, the processing method further includes: if there is a second similarity between the first time-frequency feature and the second time-frequency feature, using the first time-frequency feature as the second time-frequency feature.

[0007] According to an embodiment of the present disclosure, the target detection interval includes a first detection interval and a second detection interval, and the processing method also includes: receiving a first sound wave signal, and obtaining time-frequency characteristics corresponding to the first sound wave signal, the time-frequency characteristics including time domain characteristics and frequency domain characteristics; if the frequency domain characteristics corresponding to the first sound wave signal meet the time-frequency characteristic conditions, intercepting the sound wave signal in the first sound wave signal with the first detection interval to obtain the target sound wave signal; if the frequency domain characteristics corresponding to the first sound wave signal do not meet the time-frequency characteristic conditions, intercepting the sound wave signal in the first sound wave signal with the second detection interval to obtain the target sound wave signal; wherein, the frequency domain characteristics corresponding to the first sound wave signal meet the time-frequency characteristic conditions to characterize that the first sound wave signal is a stable sound wave signal; the first detection interval is larger than the second detection interval.

[0008] According to an embodiment of the present disclosure, the processing method further includes: updating a function enabling state of the target function based on a proximity state of the target device.

[0009] According to an embodiment of the present disclosure, the frequency domain characteristic condition includes a condition threshold, and the processing method further includes: updating the condition threshold based on the environmental noise information, and the condition threshold is greater than the fluctuation characteristic value generated by the environmental noise information.

[0010] Another aspect of the present disclosure provides a processing device, including: a first time-frequency feature acquisition module, used to acquire a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval; a first state determination module, used to determine that a nearby state of a target device is a first state if there is a first similarity between the first time-frequency feature and the second time-frequency feature; a second state determination module, used to determine that a nearby state of the target device is a second state if there is a second similarity between the first time-frequency feature and the second time-frequency feature; wherein the second time-frequency feature is a time-frequency feature corresponding to a sound wave signal received when there is no target object near the target device.

[0011] Another aspect of the present disclosure provides an electronic device, including: a sound wave receiving device for receiving a sound wave signal; a processor, the processor being configured to: obtain a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval; if there is a first similarity between the first time-frequency feature and the second time-frequency feature, determine that the proximity state of the target device is a first state; if there is a second similarity between the first time-frequency feature and the second time-frequency feature, determine that the proximity state of the target device is a second state; wherein the second time-frequency feature is a time-frequency feature corresponding to a sound wave signal received when there is no target object near the target device.

[0012] Another aspect of the present disclosure provides a non-volatile storage medium storing computer executable instructions, which are used to implement any of the above methods when executed.

[0013] Another aspect of the present disclosure provides a computer program, which includes computer executable instructions, and the instructions are used to implement any of the above methods when executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] For a more complete understanding of the present disclosure and its advantages, reference will now be made to the following description taken in conjunction with the accompanying drawings, in which:

[0015] Figure 1 A schematic diagram of an electronic device according to an embodiment of the present disclosure is shown;

[0016] Figure 2 A flowchart schematically shows a processing method according to an embodiment of the present disclosure;

[0017] Figure 3 A schematic diagram showing an example of a process of determining a nearby state of a target device according to a time-frequency feature comparison according to an embodiment of the present disclosure;

[0018] Figure 4 An example diagram schematically shows a process of updating and comparing stable state detection intervals according to an embodiment of the present disclosure;

[0019] Figure 5 A block diagram of a processing device according to an embodiment of the present disclosure is shown;

[0020] Figure 6 A schematic block diagram of an example electronic device that can be used to implement the method of the embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0021] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0022] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0023] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0024] Some block diagrams and / or flow charts are shown in the accompanying drawings. It should be understood that some blocks or combinations thereof in the block diagrams and / or flow charts may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that these instructions, when executed by the processor, may create a device for implementing the functions / operations described in these block diagrams and / or flow charts.

[0025] Therefore, the technology of the present disclosure can be implemented in the form of hardware and / or software (including firmware, microcode, etc.). In addition, the technology of the present disclosure can take the form of a computer program product on a computer-readable medium storing instructions, which can be used by an instruction execution system or in combination with an instruction execution system. In the context of the present disclosure, a computer-readable medium can be any medium that can contain, store, transmit, propagate, or transmit instructions. For example, a computer-readable medium can include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, device, or propagation medium. Specific examples of computer-readable media include: magnetic storage devices, such as magnetic tape or hard disk (HDD); optical storage devices, such as compact disk (CD-ROM); memory, such as random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0026] Figure 1 A schematic diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0027] It should be noted that Figure 1 The examples shown are merely scenarios in which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0028] like Figure 1 As shown, the electronic device 100 is a terminal device, which may include a sound wave generator 101, a sound wave receiver 102, and a processor 103. The sound wave generator 101 is configured to output a sound signal, including but not limited to at least one of a speaker and an ultrasonic transmitter, and the sound wave receiver 102 is configured to input a sound signal, which may include a signal receiver and a signal converter.

[0029] The processor 103 may include one or more components to execute instructions to complete all or part of the steps of the above-mentioned processing method. For example, the processor 103 processes the time-frequency features corresponding to the sound wave signal to obtain the similarity between different time-frequency features. After analyzing and processing the received data to be processed (such as the sound wave signal), the data processor can control the activation state of other functional devices (such as controlling the display screen to turn off) based on the processing result (such as the similarity).

[0030] The electronic device 100 may be any device having the functions of generating, receiving and processing sound wave signals, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, etc. It should be noted that the processing method provided in the embodiment of the present disclosure can generally be performed by the electronic device 100. Accordingly, the processing device provided in the embodiment of the present disclosure can generally be arranged in the electronic device 100. The processing method provided in the embodiment of the present disclosure can also be performed by a server or a server cluster that is different from the electronic device 100 and can communicate with the electronic device 100. Accordingly, the processing device provided in the embodiment of the present disclosure can also be arranged in a server or a server cluster that is different from the electronic device 100 and can communicate with the electronic device 100.

[0031] It should be understood that Figure 1 The number of the acoustic wave receivers, acoustic wave generators, processors and electronic devices in the embodiment is only for illustration. According to the implementation requirements, any number of acoustic wave receivers, acoustic wave generators, processors and electronic devices may be provided.

[0032] In some examples, Doppler is used to detect whether an object is approaching or moving away. After an ultrasonic signal is transmitted, if the object moves toward the sensor (or wave source), the frequency of the received signal will increase (called "approaching"), and if the object moves away from the sensor, the frequency of the received signal will decrease (called "moving away").

[0033] However, if we only rely on Doppler shift, we may not fully consider the impact of other obstacles (such as walls) as obstacles. In the scenario where a mobile phone is used as a sound wave receiving device to detect the distance or approach of an obstacle, during a mobile phone call, 1 is close to the face → 2 is close to the wall → 3 is far away from the wall → far away from the face. Since the Doppler effect is based on the relative speed between the object and the sensor, the system is not always able to distinguish the movement of different objects. Therefore, in the state of being far away from the wall in step 3, there is a false judgment that there is no obstruction.

[0034] In other examples, in steady-state detection, the microphone receives the sound played by the speaker directly reaching the microphone, which is superimposed on the sound played in the environment and reflected by obstacles to reach the microphone, which can be understood as "reception = direct + reflection". If the direct sound is a stable and unchanging time domain waveform under ideal circumstances, it can be directly derived from "reception-direct (fixed) = reflection".

[0035] However, in actual application scenarios, the direct signal does not have a fixed amplitude and phase. Under the influence of various factors (such as changes in the signal propagation path, dynamic changes in the environmental medium, multipath effects, changes in the characteristics of the receiver, and internal noise of the device), the steady state (direct) will change over time, affecting the accuracy of the detection results.

[0036] In other examples, after transmitting an ultrasonic signal and receiving a reflected wave, a fixed time window is used to detect the time-frequency characteristics of the echo signal, thereby determining whether the object is obscured by comparing the change in the echo signal intensity within the fixed time window.

[0037] However, if the detection window is too short, when there is continuous occlusion, a stable feature may be detected and identified as non-occlusion; and if the detection window is too long, the triggering time is too long during movement, resulting in low flexibility of the detection effect and difficulty in meeting actual needs.

[0038] Based on the above problems, the present disclosure provides a processing method, including: obtaining a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval; if there is a first similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a first state; if there is a second similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a second state; wherein the second time-frequency feature is a time-frequency feature corresponding to a sound wave signal received when there is no target object near the target device.

[0039] According to the embodiments of the present disclosure, the proximity state of the target device is determined by the different similarities between the first time-frequency feature and the second time-frequency feature corresponding to the target sound wave signal. Since the time-frequency feature includes the dual characteristics of frequency domain characteristics and time domain characteristics, the robustness of occlusion detection is improved, and the misjudgment of only using Doppler detection in traditional technology is avoided. Based on the different similarities between different time-frequency features, the proximity state of the target device can be flexibly and accurately determined, which improves the accuracy and sensitivity of occlusion detection and further meets the occlusion detection needs in complex scenarios.

[0040] Figure 2 The flowchart of the processing method according to the embodiment of the present disclosure is schematically shown.

[0041] Specifically, Figure 2 As shown, the processing method includes operations S201 to S203.

[0042] In operation S201, a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval is acquired.

[0043] In an embodiment of the present disclosure, the target detection interval may represent a detection time interval for detecting the time domain characteristics of a sound wave signal. The target sound wave signal may be a sound wave signal corresponding to the target detection interval acquired by a sound wave receiving device (sensor). The sound wave receiving device may be a functional device that is built into or configured by the target device. For example, the target detection interval is 100ms, and a sound wave signal of 100ms is intercepted every time as the target sound wave signal. It can be understood that the target device may be various electronic devices with a sound wave signal receiving function. The time-frequency feature may be obtained by converting the target sound wave signal through a preset conversion algorithm. The first time-frequency feature may include a first time domain feature and a first frequency domain feature corresponding to the target sound wave signal. The time-frequency feature may be specifically described in the relevant technology, and the present disclosure will not be described in detail here.

[0044] For example, after receiving the target sound wave signal using Doppler detection technology, the first time domain feature can be obtained according to the corresponding detection time interval and the target sound wave signal. The first time domain feature can include the amplitude change, waveform change and time domain change rate of the signal; thereby analyzing the spectrum characteristics of the target sound wave signal to obtain the first frequency domain feature (including Doppler frequency shift). It can be understood that when the object is close to the sensor, the frequency of the echo signal will increase (positive frequency shift); when the object is far away from the sensor, the frequency of the echo signal will decrease (negative frequency shift), and then by analyzing the frequency change in the frequency domain, the object's movement speed and direction can be obtained. If there is occlusion, the frequency domain feature can be manifested as the disappearance of the frequency change.

[0045] In operation S202, if there is a first similarity between the first time-frequency feature and the second time-frequency feature, it is determined that the proximity state of the target device is a first state.

[0046] In operation S203, if there is a second similarity between the first time-frequency feature and the second time-frequency feature, it is determined that the proximity state of the target device is a second state.

[0047] The second time-frequency feature is a time-frequency feature corresponding to a sound wave signal received when there is no target object near the target device.

[0048] In an embodiment of the present disclosure, the second time-frequency feature can characterize the time-frequency feature corresponding to the sound wave signal when the target object is not detected near the target device, including the second frequency domain feature and the second time domain feature. The second time-frequency feature can be used as a reference time-frequency feature to determine the similarity with the first time-frequency feature, so as to compare the similarity with the similarity threshold, and determine different nearby states of the target device based on the difference in similarity. The higher the similarity, the higher the similarity between the nearby state of the target device in the target detection interval and the nearby state corresponding to the second time-frequency feature; the lower the similarity, the lower the similarity between the nearby state of the target device in the target detection interval and the nearby state corresponding to the second time-frequency feature. The second time-frequency feature is the time-frequency feature corresponding to the sound wave signal received when there is no target object near the target device. Therefore, by comparing the first time-frequency feature with the second time-frequency feature, the similarity between the nearby state of the target device when collecting the target sound wave signal and the nearby state corresponding to the second time-frequency feature can be obtained, and then the nearby state of the target device can be obtained.

[0049] Furthermore, different proximity states of the target device are distinguished according to the similarity between the first time-frequency feature and the second time-frequency feature.

[0050] For example, the first time-frequency feature is compared with the second time-frequency feature for similarity to obtain a first similarity, and the first similarity indicates that the similarity between the two time-frequency features is low, and thus it can be determined that the nearby state of the target device obtaining the first time-frequency feature is not similar to the nearby state of the target device obtaining the second time-frequency feature.

[0051] For example, the first time-frequency feature is compared with the second time-frequency feature for similarity to obtain a second similarity, and the second similarity indicates that the similarity between the two time-frequency features is high, and thus it can be determined that the nearby state of the target device obtaining the first time-frequency feature is relatively similar to the attachment state of the target device obtaining the second time-frequency feature.

[0052] For example, when the feature similarity between the first time-frequency feature and the second time-frequency feature is determined to be the first similarity, it can be represented that an object, a person, or other obstacle is detected near the target device. When the feature similarity between the first time-frequency feature and the second time-frequency feature is determined to be the second similarity, it can be represented that no object, a person, or other obstacle is detected near the target device.

[0053] It should be noted that the first time-frequency feature and the second time-frequency feature, the first similarity and the second similarity, the first state and the second state in the present disclosure are only used to distinguish different features, similarities and states, and are not used for limitation. For example, the second time-frequency feature may be the time-frequency feature corresponding to the sound wave signal received when there is a target object near the target device, and the first time-frequency feature may be the time-frequency feature corresponding to the sound wave signal received when there is no target object near the target device. Application scenarios applicable to determining the state between the target device and the target object according to different time-frequency features include, but are not limited to, autonomous driving and robot obstacle avoidance systems, electronic equipment ultrasonic sensors, and automatic parking systems.

[0054] According to the embodiments of the present disclosure, the proximity state of the target device is determined by the different similarities between the first time-frequency feature and the second time-frequency feature corresponding to the target sound wave signal. Since the time-frequency feature includes the dual characteristics of frequency domain characteristics and time domain characteristics, the robustness of occlusion detection is improved, and the misjudgment of only using Doppler detection in traditional technology is avoided. Based on the different similarities between different time-frequency features, the proximity state of the target device can be flexibly and accurately determined, which improves the accuracy and sensitivity of occlusion detection and further meets the occlusion detection needs in complex scenarios.

[0055] It can be understood that the above describes the determination of the proximity state of the target device, and the following describes the first state and the second state.

[0056] According to an embodiment of the present disclosure, the first state represents that a target object exists near the target device, and the second state represents that a target object does not exist near the target device.

[0057] In an embodiment of the present disclosure, the first state may represent the presence of an object, a person or other obstacle near the target device, and the target object blocks the target device; conversely, the second state may represent that no object, a person or other obstacle is identified or detected near the target device, and there is no obstruction near the target device.

[0058] For example, in the scenario where the target device is a mobile phone and a call is made using the mobile phone, the first state may represent that the mobile phone is close to the face, close to an object, or placed in a bag. For example, in the scenario of an autonomous driving or robot obstacle avoidance system, the first state may represent that an obstacle or occlusion is detected nearby in real time, affecting the autonomous driving or robot's forward path.

[0059] It can be understood that the first state and the second state are described above, and how to determine the third state will be described below.

[0060] According to an embodiment of the present disclosure, the processing method also includes: if there is a third similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a third state, the third state characterizing that there is a target object approaching and / or moving away near the target device.

[0061] For the sake of convenience of description, the presence of a stable object, person or other obstacle near the target device is called a stable occlusion state; the absence of an object, person or other obstacle near the target device is called a stable non-occlusion state, such as the second state mentioned above; the presence of an unstable object, person or other obstacle near the target device is called an unstable state, such as the third state mentioned above.

[0062] In the embodiment of the present disclosure, the second time-frequency feature is obtained in a stable non-occluded state, and the sound wave signals collected by the target device in the stable occluded and stable non-occluded states are both stable, the difference between the two is small, and the similarity is high. Therefore, if the similarity between the obtained first time-frequency feature and the second time-frequency feature is the first similarity, the current state is a stable occluded state; if the similarity between the obtained first time-frequency feature and the second time-frequency feature is the second similarity, the current state is a stable non-occluded state; if the similarity between the first time-frequency feature and the second time-frequency feature is the third similarity, the current state is an unstable state. It can be understood that the three similarities can be in the order of the size of the similarities: the second similarity, the first similarity, and the third similarity. The proximity state of the target device can be determined by setting a similarity threshold corresponding to the similarity.

[0063] For example, when the second similarity S2 is detected between the first time-frequency feature and the second time-frequency feature, and S2 is greater than or equal to 95%, it can be determined that the current state is a stable non-occluded state (second state); when the first similarity S1 is detected between the first time-frequency feature and the second time-frequency feature, and 90%<S1≤95%, it can be determined that the current state is a stable occluded state (first state); when the third similarity S3 is detected between the first time-frequency feature and the second time-frequency feature, and S3<90%, it can be determined that the current state is an unstable state (approaching and / or moving away).

[0064] It can be understood that the third similarity can represent the feature similarity based on the frequency domain features, and the feature similarity between the target device and the target object is determined to be close or far away according to the direction of the Doppler effect. The Doppler effect can not only be used to measure the speed of an object, but also to determine the direction of movement of the target object according to the change direction (increase or decrease) of the frequency domain features. The third state can represent the state in the process of converting any state of the first state and the second state to another state. It can be understood that the state in the process of converting from the first state (approaching) to the second state (far away) can be determined as the third state, and at the same time, the state in the process of converting from the second state (far away) to the first state (approaching) can also be determined as the third state.

[0065] For example, when a target object (such as an obstacle) approaches a target device, the frequency of the reflected waves received by the sensor in the target device will increase, and the received frequency will be higher than the transmitted frequency. At this time, it can be determined that the obstacle is gradually approaching the target device.

[0066] For example, when a target object (such as a pedestrian) moves away from a target device, the frequency of the reflected waves received by the sensor in the target device will decrease, and the received frequency will be lower than the transmitted frequency. At this time, it can be determined that the pedestrian is gradually moving away from the target device.

[0067] Reference below Figure 3 , a method for determining the nearby state of the current target device by comparing the stable state is described in conjunction with a specific embodiment.

[0068] Figure 3 The diagram schematically shows an example of a process of determining the vicinity state of a target device based on time-frequency feature comparison according to an embodiment of the present disclosure.

[0069] When the time domain feature indicates that the nearby state of the current target device is unobstructed, the comparison stable state stage is entered to detect whether the target device is obstructed by the target object. Figure 3As shown, the sound wave signal corresponds to multiple transmission frequencies. Since the superposition of periodic sin signals still has periodicity, and according to the difference in amplitude group and phase group, the time domain envelope shape feature 300 is formed, wherein the frequency with the strongest change feature is characterized by the highest point 301 and the lowest point 302 of the time domain envelope in the entire cycle, and multiple relative high points 303 and multiple relative low points 304 in the envelope fluctuation. Taking a mobile phone as an example, since the speaker frequency response and microphone frequency response of different transmission frequencies are different, different transmission frequencies with the same amplitude receive different amplitudes, resulting in different performances of the same features at different frequencies. The frequency with the strongest change feature can be used, or energy verification can be performed based on the frequency response and then statistical judgment can be performed on multiple frequencies. When updating the steady state, the similarity threshold can be set according to the degree of influence of noise on the calculated result; the similarity is calculated with the unobstructed state, and if it is lower than the similarity threshold, it is considered to be blocked.

[0070] Further, when it is determined that the nearby state of the target device is not far away, not close, and not blocked, it can be determined that the current target device is in an unblocked state, and then the stable state threshold is updated based on the current time-frequency feature. It can be understood that in other states except unblocked, the stable state is stopped from being updated, and the stable state comparison is continued to determine whether there is blockage.

[0071] It can be understood that the above describes an example of how to determine the third state, and the following will describe how to use the first time-frequency feature as the second time-frequency feature.

[0072] According to an embodiment of the present disclosure, the processing method further includes: if there is a second similarity between the first time-frequency feature and the second time-frequency feature, using the first time-frequency feature as the second time-frequency feature.

[0073] In the embodiments of the present disclosure, taking into account the changes in the surrounding environment of the target device, the sound wave signal in the stable non-obstructed state is also in dynamic change accordingly. Therefore, when it is determined that the current state is a stable non-obstructed state, the current first time-frequency feature can be updated in real time as the second time-frequency feature. When the feature similarity between the first time-frequency feature and the second time-frequency feature is greater than or equal to the similarity threshold, the first time-frequency feature and the reference time-frequency feature are characterized as being the same or close time-frequency features, so that the current first time-frequency feature can be used as the second time-frequency feature (reference time-frequency feature) as a reference time-frequency feature for subsequent comparison of stable states (for example, feature comparison from unobstructed to obstructed).

[0074] For example, in a target tracking system, when the similarity between the first time-frequency feature and the second time-frequency feature is greater than a preset similarity threshold, the system can choose to replace the current second time-frequency feature with the first time-frequency feature as the updated second time-frequency feature, thereby realizing real-time updating or matching of features, especially in dynamic and complex environments, and maintaining the real-time nature of unobstructed steady-state time domain features, thereby improving the system's adaptability, response speed, and accuracy of detection results.

[0075] It can be understood that the above describes how to use the first time-frequency feature as an example of the second time-frequency feature, and the following describes how to determine the target sound wave signal and the target time-frequency feature.

[0076] According to an embodiment of the present disclosure, the target detection interval includes a first detection interval and a second detection interval, and the processing method also includes: receiving a first sound wave signal, and obtaining time-frequency characteristics corresponding to the first sound wave signal, the time-frequency characteristics including time domain characteristics and frequency domain characteristics; if the frequency domain characteristics corresponding to the first sound wave signal meet the time-frequency characteristic conditions, selecting the first detection interval to intercept the sound wave signal in the first sound wave signal to obtain the target sound wave signal; if the frequency domain characteristics corresponding to the first sound wave signal do not meet the time-frequency characteristic conditions, selecting the second detection interval to intercept the sound wave signal in the first sound wave signal to obtain the target sound wave signal; wherein, the frequency domain characteristics corresponding to the first sound wave signal meet the time-frequency characteristic conditions to characterize that the first sound wave signal is a stable sound wave signal; the first detection interval is larger than the second detection interval.

[0077] In traditional technology, when multiple fixed-duration detection intervals are used to implement ultrasonic occlusion detection, if the detection interval time length is too short and the occlusion is continuous, stable features may be detected, and continuous occlusion may be mistakenly identified as non-occlusion; and if the detection interval time length is too long, it may take too long to trigger during movement, resulting in low detection sensitivity and accuracy. To solve this technical problem, the present disclosure dynamically updates and adjusts the detection time length of the detection interval to adapt to the detection needs under different time domain feature states.

[0078] Considering that the stable occlusion state and the stable non-occlusion state are both stable sound wave signals, a larger detection interval can be selected to detect the stable occlusion state or the stable non-occlusion state; considering that the difference between the stable state and the unstable state is relatively large and easy to distinguish, a smaller detection interval can be selected to distinguish and detect the stable state and the unstable state.

[0079] In an embodiment of the present disclosure, the target detection interval may include a first detection interval and a second detection interval based on different detection time lengths, and the detection time length corresponding to the first detection interval is greater than the detection time length corresponding to the second detection interval. The first sound wave signal may be an overall sound wave signal to be detected corresponding to actual detection requirements, and different detection intervals may be used to intercept sound wave signals of different time lengths from the first sound wave signal to obtain multiple target sound wave signals.

[0080] It should be noted that when detecting the target sound wave signal, the detection interval corresponding to the second time-frequency feature includes both the first detection interval and the second detection interval of different time lengths, and the time domain characteristics of the signal are detected in real time, and different detection intervals are selected to detect the time domain characteristics according to the difference in frequency domain characteristics to determine the nearby state of the target device. For example, based on the difference in frequency domain characteristics, the second time-frequency feature can be divided into a first sub-time-frequency feature and a second sub-time-frequency feature. When the first sub-time-frequency feature corresponds to a stable frequency domain feature and the second sub-time-frequency feature corresponds to an unstable frequency domain feature, it can be determined that the first sub-time-frequency feature in the second time-frequency feature corresponds to the first detection interval, and the second sub-time-frequency feature in the second time-frequency feature corresponds to the second detection interval.

[0081] In the embodiments of the present disclosure, the frequency domain features can characterize the spectral features of the target sound wave signal, and can be used to capture the motion information of the target object relative to the target device (such as Doppler frequency shift) and the frequency changes corresponding to different states. The time domain features can characterize the change characteristics of the target sound wave signal over time, and can be used to analyze the amplitude, waveform and change law of the signal. By performing dual analysis on the time domain features and the frequency domain features, the time domain features can be used to provide intuitive time evolution information of the sound wave signal, and the frequency domain features can be used to analyze and extract the movement speed, direction and whether it is blocked by the target object.

[0082] In the embodiments of the present disclosure, the time domain characteristic condition can be used to determine whether the sound wave signal corresponding to the frequency domain characteristic is stable and whether frequency shift (frequency change) occurs. If the frequency domain characteristic satisfies the time domain characteristic condition, it can be characterized that the sound wave signal corresponding to the current frequency domain characteristic is a stable sound wave signal and the frequency change disappears. If the frequency domain characteristic does not satisfy the time-frequency characteristic condition, it can be characterized that the sound wave signal corresponding to the current frequency domain characteristic is an unstable sound wave signal and the frequency change is large (including increase and decrease); thus, different detection intervals are selected according to the state of the sound wave signal to obtain the target sound wave signal.

[0083] Reference below Figure 4 , a method for dynamically adjusting the detection interval for ultrasonic detection is described in conjunction with a specific embodiment.

[0084] Figure 4 An example diagram schematically shows a process of updating and comparing stable state detection intervals according to an embodiment of the present disclosure.

[0085] like Figure 4As shown, when the stable state 410 (unobstructed state) is updated, the time-frequency features can be detected using the longer detection interval 420 and the shorter detection window 430 at the same time. When the first frequency domain feature 401 corresponding to the first sound wave signal is a stable sound wave signal and the frequency change disappears, it can be determined that there is currently an obstruction or obstacle, so that the sound wave signal corresponding to the longer detection interval 420 (first detection interval) is selected as the target sound wave signal, so as to analyze the time domain features. When the target device is obstructed, the detection interval size of the stable state is increased to prevent the feature from being close to the stable state in a short period of time when it is obstructed, resulting in a misjudgment of no obstruction.

[0086] In the stage of comparing the stable state 440, it is detected whether the target device is blocked by the target object. When the second frequency domain feature 402 corresponding to the first sound wave signal is an unstable sound wave signal and the frequency increases, it can be determined that a target object (such as an obstacle) is approaching, so the sound wave signal corresponding to the detection interval 430 (the second detection interval) with a shorter duration is selected as the target sound wave signal, so as to analyze the time domain features.

[0087] When the third frequency domain feature 403 corresponding to the first sound wave signal is an unstable sound wave signal and the frequency is decreasing, it can be determined that a target object (such as a pedestrian) is currently moving away, and the sound wave signal corresponding to the detection interval 430 (second detection interval) with a shorter duration is selected as the target sound wave signal, thereby performing time domain feature analysis.

[0088] It can be understood that when the Doppler is detected to be approaching or moving away, the detection interval size of the comparison stable state is shortened to ensure the sensitive state switching effect. When the moving speed is fast, it is violently unstable in a short period of time, and when the moving speed is slow, it is slightly unstable for a long time. The moving speed affects the Doppler frequency deviation, thereby dynamically modulating the window length. Since the moving away, approaching, stable occlusion and stable non-occlusion states all need to be detected, by setting the detection interval of different time lengths, it can ensure the recognition accuracy between the stable occlusion and stable non-occlusion states, and also ensure the recognition efficiency between the stable state (stable occlusion state and stable non-occlusion state) and the unstable state (moving away and approaching).

[0089] According to an embodiment of the present disclosure, by adjusting the detection interval of the comparison stable state, the system can more quickly identify changes in the signal. When the motion state of the target object changes (for example, switching from approaching to moving away, or vice versa), the system can quickly perceive this change and make corresponding adjustments. Adjusting the detection interval indicates that the judgment of the target state will be based on more accurate real-time data. Compared with the detection method of fixed time detection interval, dynamically adjusting the monitoring interval can reduce the impact of the transition period and avoid erroneous state judgments due to long-term accumulated errors, thereby improving the accuracy of the detection results. Especially in the case of relatively small Doppler frequency shifts, shortening the interval can increase sensitivity to smaller changes.

[0090] It can be understood that the above describes an example of how to obtain the target time-frequency feature, and the following will describe how to update the function activation state of the target function.

[0091] According to an embodiment of the present disclosure, the processing method further includes: updating a function enabling state of the target function based on a proximity state of the target device.

[0092] In an embodiment of the present disclosure, after the proximity state of the target device is determined, the enabling states of different target functions in the target device may be updated according to the current proximity state.

[0093] For example, in autonomous driving, ultrasonic occlusion detection can be used to detect obstacles, pedestrians, other vehicles, etc. around the vehicle. When the ultrasonic sensor (sound wave receiving device) detects that an obstacle is approaching rapidly, the system can activate the braking module or the automatic obstacle avoidance module to avoid collision by reducing the vehicle speed or adjusting the path. When the obstacle gradually moves away, the system can switch to the path planning module, re-evaluate the driving path, or even cancel the obstacle avoidance measures and return to normal driving. When the ultrasonic signal is blocked (for example, when encountering a large object or irregular surface), the system can enable supplementary sensors such as lidar or camera sensors to obtain additional information and continue to detect the surrounding environment.

[0094] For example, the mobile phone screen can automatically sense the user's behavior and the surrounding environment in multiple scenarios by using ultrasonic detection technology, and then switch to different states. When the user picks up the phone to answer a call, the phone's ultrasonic sensor can detect that the user's ear is close to the screen, and the screen can automatically turn off to prevent the user's face or ear from accidentally touching the screen and avoid misoperation (such as hanging up the phone, switching applications). When the phone is taken out of the user's pocket or bag, the ultrasonic sensor can detect the distance between the screen and the object. When it detects that the phone is away from the user (for example, after putting it back in the pocket), it can automatically detect this change and perform the corresponding operation.

[0095] For example, in robot motion control and grasping scenarios, when ultrasound detects an object approaching, the robot can switch to grasping mode, adjust the motion trajectory and start grasping or carrying operations; when the object moves away, the robot can enter scanning mode or adjust its position to prepare for the next task; when an obstruction (such as a wall or other object) is detected in front of the path, the robot can automatically switch to obstacle avoidance mode to avoid collision or interference by adjusting the route or pausing the current action.

[0096] According to the embodiments of the present disclosure, the activation state of the target function can be flexibly switched based on the proximity state of the target device. By intelligently sensing the distance between the user and the device or whether they are blocked, far away, or close, the user's misoperation or inconvenient operation process can be effectively avoided, thereby improving the user's overall experience. Ultrasonic detection can intelligently switch the function state according to the usage state of the target device, which can optimize resource (such as battery) usage and reduce unnecessary resource consumption.

[0097] It can be understood that the above describes an example of how to update the function enablement of the target function, and the following will describe how to adjust the condition threshold.

[0098] According to an embodiment of the present disclosure, the frequency domain characteristic condition includes a condition threshold, and the processing method further includes: updating the condition threshold based on the environmental noise information, and the condition threshold is greater than the fluctuation characteristic value generated by the environmental noise information.

[0099] In an embodiment of the present disclosure, the conditional threshold can represent the threshold for distinguishing between the noise characteristics and the Doppler characteristics corresponding to the environmental noise in ultrasonic detection. Considering that the characteristics of the environmental noise (background noise) may vary with changes in the environment or conditions during the actual detection process. To solve this technical problem, the present disclosure dynamically updates the conditional threshold. When the system detects that the signal is pure noise, the conditional threshold can be updated according to the statistical characteristics of the noise (such as the mean and variance of the noise energy), so that the system can adapt to different noise environments and better distinguish between noise and Doppler signals.

[0100] For example, when the frequency domain energy of a signal exceeds the updated conditional threshold, it is more likely to be judged as a signal containing the Doppler effect rather than noise. By dynamically updating the conditional threshold, the system can more accurately determine whether a signal contains Doppler features.

[0101] According to the embodiments of the present disclosure, the updated conditional threshold can help filter out more noise, reduce the possibility of misjudgment, and further effectively improve the robustness and accuracy of signal recognition.

[0102] In a feasible embodiment, in the Doppler-assisted ultrasonic detection method, sensors such as a gyroscope, an accelerometer, and a capacitive touch screen may also be used to assist in determining whether the target object blocks the target device.

[0103] In a feasible embodiment, the Doppler-assisted ultrasonic detection process may include: using frequency domain detection to obtain frequency domain characteristics corresponding to the ultrasonic signal, so as to detect whether there is a target object approaching the target device according to the direction of the Doppler effect; at the same time, it can be judged whether it is Doppler or pure noise (no Doppler) according to different mathematical statistical characteristics of the frequency domain characteristics. When it is pure noise, the noise threshold can be updated to achieve more accurate judgment of the existence of Doppler characteristics.

[0104] It can be understood that the closer the target object is to the target device, the greater the reflected Doppler energy. Therefore, a threshold can be set according to the distance of approach and distance, so that when moving close enough, the occlusion can be detected. A single transmission frequency has one set of Dopplers, and multiple transmission frequencies have multiple sets of Dopplers. Therefore, the Doppler characteristics of multiple transmission frequencies can be used for comparison and verification to enhance the robustness of the Doppler results.

[0105] When it is detected that there is no obstruction (direct access), the steady-state threshold can be updated based on the current time domain features. In the stage of comparing the steady state, the time-frequency features can be compared to detect whether there is obstruction. Based on multiple transmission frequencies, since the superposition of periodic signals still has periodicity, the time domain features (envelope shape features) can be formed according to the differences in amplitude groups and phase groups, including the highest and lowest points of the time domain envelope in the entire cycle, and multiple relative high points and multiple relative low points in the envelope fluctuations.

[0106] Since the speaker frequency response and microphone frequency response of different transmitting frequencies are different, different transmitting frequencies with the same amplitude will receive different amplitudes, resulting in different performances of the same features at different frequencies. The frequency with the strongest variable feature can be used, or energy verification can be performed based on the frequency response and then statistical judgment can be made at multiple frequencies.

[0107] When updating the stable state threshold, the similarity threshold can be set according to the degree of influence of noise on the calculated result, and multiple detection intervals can be saved at the same time, including the long first detection interval stable state and the short second detection interval stable state; then the feature similarity is calculated with the time-frequency features corresponding to the unobstructed state. When the feature similarity is less than the similarity threshold, it is considered to be an occlusion state, and if it is greater than or equal to the similarity, it is judged to be unobstructed. When the frequency domain feature is identified as occlusion, the detection interval size of the comparison stable state can be increased (that is, the first detection interval stable state is selected) to prevent the feature from being close to the stable state in a short period of time during occlusion, resulting in a misjudgment of no occlusion; when the Doppler is detected to be close and far away, the detection interval size of the comparison stable state can be shortened (that is, the second detection interval stable state is selected) to ensure sensitive state switching effect.

[0108] It can be understood that when the target object moves fast, it is extremely unstable for a short period of time; and when it moves slowly, it is slightly unstable for a long time. The moving speed of the target object affects the Doppler frequency deviation, thereby dynamically modulating the window length.

[0109] In a feasible embodiment, the Doppler-assisted ultrasonic detection processing method may include operations S41 to S46.

[0110] In operation S41, a first sound wave signal is received and time domain features and frequency domain features corresponding to the first sound wave signal are acquired.

[0111] In operation S42, when the frequency domain characteristics corresponding to the first sound wave signal meet the time-frequency characteristic conditions, the first detection interval can be selected to intercept the sound wave signal in the first sound wave signal to obtain the target sound wave signal; if the frequency domain characteristics corresponding to the first sound wave signal do not meet the time-frequency characteristic conditions, the second detection interval can be selected to intercept the sound wave signal in the first sound wave signal to obtain the target sound wave signal.

[0112] In operation S43, a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval is acquired.

[0113] In operation S44, when there is a first similarity between the first time-frequency feature and the second time-frequency feature, the proximity state of the target device can be determined to be the first state; when there is a second similarity between the first time-frequency feature and the second time-frequency feature, the proximity state of the target device can be determined to be the second state, and the second time-frequency feature is a time-frequency feature corresponding to the sound wave signal received when there is no target object near the target device.

[0114] In operation S45 , when there is a third similarity between the first time-frequency feature and the second time-frequency feature, it can be determined that the proximity state of the target device is a third state, and the third state indicates that there is a target object approaching and / or moving away near the target device.

[0115] In operation S46 , based on the proximity state of the target device, the function enablement state of the target function may be updated.

[0116] Based on the above processing method, the present disclosure also provides a processing device. Figure 5 The device is described in detail.

[0117] Figure 5 A block diagram of a processing device according to an embodiment of the present disclosure is shown.

[0118] like Figure 5 As shown, the processing device 500 includes a first time-frequency feature acquisition module 501 , a first state determination module 502 and a second state determination module 503 .

[0119] According to some embodiments of the present disclosure, the processing device 500 may be used to implement the processing method of the embodiments of the present disclosure.

[0120] The first time-frequency feature acquisition module 501 may perform, for example, operation S201 to acquire a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval.

[0121] The first state determination module 502 may perform, for example, operation S202 for determining that the proximity state of the target device is the first state if there is a first similarity between the first time-frequency feature and the second time-frequency feature.

[0122] The second state determination module 503 can execute, for example, operation S203, which is used to determine that the proximity state of the target device is the second state if there is a second similarity between the first time-frequency feature and the second time-frequency feature; wherein the second time-frequency feature is a time-frequency feature corresponding to the sound wave signal received when there is no target object near the target device.

[0123] According to the embodiments of the present disclosure, based on the first time-frequency feature acquisition module 501, the first state determination module 502 and the second state determination module 503 in the processing device 500, the nearby state of the target device is determined by the different similarities between the first time-frequency feature and the second time-frequency feature corresponding to the target sound wave signal. Since the time-frequency feature includes the dual characteristics of frequency domain characteristics and time domain characteristics, the robustness of occlusion detection is improved, and the misjudgment of only using Doppler detection in traditional technology is avoided. Based on the different similarities between different time-frequency features, the nearby state of the target device can be flexibly and accurately determined, thereby improving the accuracy and sensitivity of occlusion detection and further meeting the occlusion detection needs in complex scenarios.

[0124] It can be understood that the first time-frequency feature acquisition module 501, the first state determination module 502, and the second state determination module 503 can be combined in one module, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first time-frequency feature acquisition module 501, the first state determination module 502, and the second state determination module 503 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented in hardware or firmware in any other reasonable way of integrating or packaging the circuit, or in a proper combination of software, hardware, and firmware. Alternatively, at least one of the first time-frequency feature acquisition module 501, the first state determination module 502, and the second state determination module 503 can be at least partially implemented as a computer program module, and when the program is run by a computer, the function of the corresponding module can be executed.

[0125] According to an embodiment of the present disclosure, the first state represents that a target object exists near the target device, and the second state represents that a target object does not exist near the target device.

[0126] According to an embodiment of the present disclosure, the processing device also includes: a third state determination module, which is used to determine that the proximity state of the target device is a third state if there is a third similarity between the first time-frequency feature and the second time-frequency feature, and the third state represents the presence of a target object that is approaching and / or moving away near the target device.

[0127] According to an embodiment of the present disclosure, the processing device further includes: a first time-frequency feature as a module, configured to use the first time-frequency feature as the second time-frequency feature if there is a second similarity between the first time-frequency feature and the second time-frequency feature.

[0128] According to an embodiment of the present disclosure, the target detection interval includes a first detection interval and a second detection interval, and the processing device also includes: a signal receiving module, a first interception module, and a second interception module. The signal receiving module is used to receive the first sound wave signal and obtain the time-frequency characteristics corresponding to the first sound wave signal, and the time-frequency characteristics include time domain characteristics and frequency domain characteristics; the first interception module is used to select the first detection interval to intercept the sound wave signal in the first sound wave signal to obtain the target sound wave signal if the frequency domain characteristics corresponding to the first sound wave signal meet the time-frequency characteristic conditions; the second interception module is used to select the second detection interval to intercept the sound wave signal in the first sound wave signal to obtain the target sound wave signal if the frequency domain characteristics corresponding to the first sound wave signal do not meet the time-frequency characteristic conditions; wherein, the frequency domain characteristics corresponding to the first sound wave signal meet the time-frequency characteristic conditions to indicate that the first sound wave signal is a stable sound wave signal; the first detection interval is larger than the second detection interval.

[0129] A signal receiving module is used to receive a first sound wave signal, and use a first detection interval and a second detection interval to obtain time domain features and frequency domain features corresponding to the first sound wave signal; a first feature selection module is used to select the time domain features corresponding to the first detection interval as the target time domain features if the frequency domain features meet the frequency domain feature conditions, and obtain the target time-frequency features; a second feature selection module is used to select the time domain features corresponding to the second detection interval as the target time domain features if the frequency domain features do not meet the frequency domain feature conditions, and obtain the target time-frequency features; wherein, the frequency domain features meeting the frequency domain feature conditions indicate that the first sound wave signal is a stable sound wave signal, and the time length corresponding to the first detection interval is greater than the time length corresponding to the second detection interval.

[0130] According to an embodiment of the present disclosure, the processing device further includes: a state updating module, configured to update a function enabling state of a target function based on a proximity state of the target device.

[0131] According to an embodiment of the present disclosure, the frequency domain characteristic condition includes a condition threshold, and the processing device further includes: a threshold updating module for updating the condition threshold based on the environmental noise information, and the condition threshold is greater than the fluctuation characteristic value generated by the environmental noise information.

[0132] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, including: a sound wave receiving device for receiving a sound wave signal; a processor, the processor being configured to: obtain a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval; if there is a first similarity between the first time-frequency feature and the second time-frequency feature, determine that the proximity state of the target device is a first state; if there is a second similarity between the first time-frequency feature and the second time-frequency feature, determine that the proximity state of the target device is a second state; wherein the second time-frequency feature is a time-frequency feature corresponding to the sound wave signal received when there is no target object near the target device.

[0133] In an embodiment of the present disclosure, the sound wave receiving device may be a device disposed in a target device, or may be a device independent of the target device and communicating with the target device. For example, a mobile phone, a robot, or an automatic driving system provided with a sound wave receiving device, the specific form of which is not limited herein. The processor may include a general-purpose microprocessor, an instruction set processor, and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), and the like. The processor may also include an onboard memory for caching purposes. The processor may be a single processing unit or multiple processing units for executing different actions of the method flow of an embodiment of the present disclosure.

[0134] Figure 6 A schematic block diagram of an example electronic device that can be used to implement the method of the embodiment of the present disclosure is shown.

[0135] Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0136] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0137] Multiple components in the electronic device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0138] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the virtual image driving method. For example, in some embodiments, the virtual image driving method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the virtual image driving method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the virtual image driving method in any other appropriate manner (e.g., by means of firmware).

[0139] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0140] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0141] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0142] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0143] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0144] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. Among them, the server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0145] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0146] Although the present disclosure has been shown and described with reference to specific exemplary embodiments of the present disclosure, it should be understood by those skilled in the art that various changes in form and details may be made to the present disclosure without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents. Therefore, the scope of the present disclosure should not be limited to the above-mentioned embodiments, but should be determined not only by the appended claims, but also by the equivalents of the appended claims.

Claims

1. A processing method comprising: Acquire a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval; If there is a first similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a first state; If there is a second similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a second state; The second time-frequency feature is a time-frequency feature corresponding to a sound wave signal received when there is no target object near the target device. 2 . The method according to claim 1 , wherein the first state represents that the target object exists near the target device, and the second state represents that the target object does not exist near the target device.

3. The method according to claim 2, further comprising: If there is a third similarity between the first time-frequency feature and the second time-frequency feature, it is determined that the proximity state of the target device is a third state, and the third state indicates that there is the target object approaching and / or moving away near the target device.

4. The method according to claim 2, further comprising: If the first time-frequency feature and the second time-frequency feature have the second similarity, the first time-frequency feature is used as the second time-frequency feature.

5. The method according to claim 3, wherein the target detection interval includes a first detection interval and a second detection interval, and the processing method further includes: Receive a first sound wave signal, and obtain time-frequency features corresponding to the first sound wave signal, wherein the time-frequency features include time domain features and frequency domain features; If the frequency domain feature corresponding to the first sound wave signal satisfies the time-frequency feature condition, selecting the first detection interval to intercept a sound wave signal in the first sound wave signal to obtain the target sound wave signal; If the frequency domain feature corresponding to the first sound wave signal does not meet the time-frequency feature condition, selecting the second detection interval to intercept a sound wave signal in the first sound wave signal to obtain the target sound wave signal; The frequency domain feature corresponding to the first sound wave signal satisfies the time-frequency feature condition, indicating that the first sound wave signal is a stable sound wave signal; the first detection interval is greater than the second detection interval; Among them, the frequency domain feature satisfies the frequency domain feature condition to indicate that the first sound wave signal is a stable sound wave signal, and the time length corresponding to the first detection interval is greater than the time length corresponding to the second detection interval.

6. The method according to claim 1, further comprising: Based on the proximity status of the target device, a function enabling status of a target function is updated.

7. The method according to claim 6, wherein the frequency domain characteristic condition comprises a conditional threshold, and the processing method further comprises: The condition threshold is updated based on the environmental noise information, and the condition threshold is greater than the fluctuation characteristic value generated by the environmental noise information.

8. A processing device comprising: A first time-frequency feature acquisition module, used to acquire a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval; A first state determination module, configured to determine that the proximity state of the target device is a first state if there is a first similarity between the first time-frequency feature and the second time-frequency feature; A second state determination module, configured to determine that the proximity state of the target device is a second state if there is a second similarity between the first time-frequency feature and the second time-frequency feature; The second time-frequency feature is a time-frequency feature corresponding to a sound wave signal received when there is no target object near the target device.

9. An electronic device, comprising: A sound wave receiving device, used for receiving a sound wave signal; processor, The processor is configured as follows: Acquire a first time-frequency feature corresponding to a target sound wave signal located in a target detection interval; If there is a first similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a first state; If there is a second similarity between the first time-frequency feature and the second time-frequency feature, determining that the proximity state of the target device is a second state; The second time-frequency feature is a time-frequency feature corresponding to a sound wave signal received when there is no target object near the target device.

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

Images