Processing method and device based on voice wake-up system, equipment and medium

Abstract

The embodiment of the invention provides a processing method and device based on a voice wake-up system, equipment and a medium. The method comprises the following steps: acquiring a collected sound signal; performing sound source localization on the sound signal, and determining the sound source position of the sound signal; determining a target area where the sound source position is located and area attribute information of the target area; and adjusting a wake-up threshold value of the voice wake-up system according to the region attribute information. According to the embodiment of the invention, the wake-up threshold value of the voice wake-up system is adjusted according to the area where the sound source position is located, so that the wake-up sensitivity of the voice wake-up system is adjusted, the wake-up recognition strategy of the voice wake-up system is optimized, and the false wake-up probability of the voice wake-up system is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of voice data processing, and in particular to a processing method, device, equipment and medium based on a voice wake-up system. Background Art

[0002] Currently, in smart home environments, voice wake-up technology is widely used in various devices so that users can control the devices through voice commands.

[0003] However, in the prior art, if the background noise in a smart home environment, such as a TV or stereo, is too loud, it may be mistakenly recognized by the device as a wake-up command, thereby triggering a false wake-up. Summary of the invention

[0004] In view of the above problems, a processing method, device, equipment and medium based on a voice wake-up system are proposed to overcome the above problems or at least partially solve the above problems, including:

[0005] A processing method based on a voice wake-up system, the method comprising:

[0006] Acquiring collected sound signals;

[0007] Performing sound source localization on the sound signal to determine the sound source position of the sound signal;

[0008] Determine the target area where the sound source is located and area attribute information of the target area;

[0009] According to the area attribute information, a wake-up threshold of the voice wake-up system is adjusted.

[0010] Optionally, adjusting a wake-up threshold of the voice wake-up system according to the area attribute information includes:

[0011] Detecting whether there is a human object in the target area;

[0012] The wake-up threshold of the voice wake-up system is adjusted according to the detection result of the human object and the area attribute information.

[0013] Optionally, adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the area attribute information includes:

[0014] When the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to increase the wake-up sensitivity of the voice wake-up system;

[0015] When the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

[0016] Optionally, adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the area attribute information includes:

[0017] When the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity;

[0018] When the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

[0019] Optionally, adjusting a wake-up threshold of the voice wake-up system according to the area attribute information includes:

[0020] Determining a sound type of the sound signal;

[0021] Adjust the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information.

[0022] Optionally, adjusting a wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes:

[0023] When the sound type indicates that the sound signal is a human voice, and the area attribute information indicates that the target area is a designated area, adjusting a wake-up threshold of the voice wake-up system to increase a wake-up sensitivity of the voice wake-up system;

[0024] When the sound type indicates that the sound signal is a human voice and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

[0025] Optionally, adjusting a wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes:

[0026] When the sound type indicates that the sound signal is noise, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity;

[0027] When the sound type indicates that the sound signal is noise and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

[0028] Optionally, the designated area is a permanent area or an activity area, and the non-designated area is a temporary activity area or an inactive area.

[0029] Optionally, before acquiring the collected sound signal, the method includes:

[0030] Historical personnel activity information is obtained, and based on the historical personnel activity information, multiple areas are determined in the current environment, and area attribute information of each area is set.

[0031] Optionally, the voice wake-up system is deployed in a smart home device with a millimeter-wave radar.

[0032] A processing device based on a voice wake-up system, the device comprising:

[0033] A sound signal acquisition module, used to acquire the collected sound signal;

[0034] A sound source location determination module, used to perform sound source location on the sound signal to determine the sound source location of the sound signal;

[0035] A region attribute information determination module, used to determine the target region where the sound source is located and the region attribute information of the target region;

[0036] The wake-up threshold adjustment module is used to adjust the wake-up threshold of the voice wake-up system according to the area attribute information.

[0037] An electronic device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method described above when executed by the processor.

[0038] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0039] The embodiments of the present invention have the following advantages:

[0040] In an embodiment of the present invention, by acquiring a collected sound signal; locating the sound source of the sound signal to determine the sound source position of the sound signal; determining the target area where the sound source position is located and the regional attribute information of the target area; and adjusting the wake-up threshold of the voice wake-up system according to the regional attribute information, the wake-up threshold of the voice wake-up system is adjusted according to the area where the sound source position is located, thereby adjusting the wake-up sensitivity of the voice wake-up system, optimizing the wake-up recognition strategy of the voice wake-up system, and reducing the probability of false wake-up of the voice wake-up system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0042] Figure 1 is a flowchart of a processing method based on a voice wake-up system provided by an embodiment of the present invention;

[0043] Figure 2 is an example diagram of a processing method based on a voice wake-up system provided by an embodiment of the present invention;

[0044] Figure 3 is a flowchart of another processing method based on a voice wake-up system provided by an embodiment of the present invention;

[0045] Figure 4 It is a structural block diagram of a processing device based on a voice wake-up system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In related technologies, sound source localization technology mainly relies on microphone arrays to determine the location of sound sources through signal processing algorithms. However, in the presence of a large amount of background noise or multiple sound sources, the accuracy is limited, especially in complex indoor environments, where it may be difficult to accurately distinguish and locate specific sound sources. Taking the home environment as an example, there are various interfering sound sources, such as the voice of a person on the TV, the voice of a person outside the window, or other interfering sounds. The current speech recognition technology cannot identify whether the voice of such an interfering sound source is a real person or a recording, so the interfering sound source hitting the wake-up word or command word will trigger voice wake-up and recognition.

[0048] Based on this, the embodiment of the present invention is able to dynamically adjust the threshold to adapt to environmental changes, thereby improving the accuracy and response speed of the voice wake-up system. Specifically, the present invention proposes to divide the area by detecting the activity area of ​​the personnel through millimeter waves. When the voice is detected to wake up, it is determined in which area the wake-up sound source is. For those in the resident activity area, it is assumed that there is a high probability that it is a real person's voice. The normal threshold or lowered voice threshold can be used to improve the wake-up response. If the wake-up sound source falls in a non-resident activity area or is accompanied by a noise source, it may be an interference sound, so the threshold is increased. At this time, the wake-up sensitivity will be reduced to avoid false wake-ups.

[0049] The present invention will be further described below in conjunction with the accompanying drawings:

[0050] Reference Figure 1 , shows a step flow chart of a processing method based on a voice wake-up system provided by an embodiment of the present invention, where the voice wake-up system is deployed in a smart home device with a millimeter-wave radar.

[0051] In some examples, millimeter-wave radar can obtain activity information of people in the current environment by emitting millimeter-wave signals and receiving reflected signals. The radar signals are processed at high frequency and converted into data describing the position and motion status of the people.

[0052] As some examples, smart home devices may be smart air conditioners, smart central control screens, etc.

[0053] Specifically, the following steps may be included:

[0054] Step 101, obtaining a collected sound signal.

[0055] In practical applications, the sound signal may be the sound made by a person in the current environment, or the background sound made by other devices, such as the background sound made by a TV when a user is watching TV.

[0056] As some examples, one or more microphone arrays can be deployed in smart home devices to collect sound signals in the current environment in real time through the microphones; the voice wake-up system can obtain the sound signals collected by the microphone array for processing, such as sound classification, sound source localization, etc.

[0057] In some embodiments of the present invention, before acquiring the collected sound signal, the process includes:

[0058] Historical personnel activity information is obtained, and based on the historical personnel activity information, multiple areas are determined in the current environment, and area attribute information of each area is set.

[0059] In some examples, historical personnel activity information is personnel activity information within a period obtained by collecting information based on millimeter-wave radar after the smart home device is installed. For example, after the device is installed, personnel activities are continuously detected for 10 days, and the personnel activity trajectory is obtained to determine multiple areas and set the area attribute information for each area.

[0060] For example, if a person stays in an area for more than 2 hours every day for 10 days, or if a person moves around in an area every day, such as the sofa in the living room, the corridor, or the corridor between the TV and the sofa in the living room, the area attribute information of the area can be set as the designated area. If a person stays in an area occasionally, or if a person stays in an area once a day or for 10 consecutive days, or if there is no human activity in an area, the area attribute information of the area can be defined as the non-designated area.

[0061] In actual applications, the voice wake-up system can obtain historical personnel activity information collected by millimeter-wave radar, determine multiple areas in the current environment based on the historical personnel activity information, and set corresponding area attribute information for each area, such as designated area and non-designated area.

[0062] In some embodiments of the present invention, the designated area is a permanent area or an active area, and the non-designated area is a temporary active area or an inactive area.

[0063] As some examples, permanent areas are areas where users often stay, such as the sofa in the living room. Usually, these areas have less background noise, and the user's voice commands have a higher priority; activity areas are areas where users may frequently enter and exit, such as corridors, room activity areas, etc., and the user's voice commands in these areas need to be responded to quickly; temporary activity areas are areas that appear occasionally, such as TV areas or temporarily set up activity areas. These areas may be affected by occasional noise, and the threshold needs to be increased to reduce false wake-ups; inactive areas are places that users do not often go to, such as storage cabinets, etc.

[0064] Step 102: localize the sound source of the sound signal to determine the sound source position of the sound signal.

[0065] As some examples, a sound source localization algorithm can be used to locate the sound signal and determine the sound source position of the sound signal; for example, the sound source localization algorithm can use direction of arrival (DOA) estimation and positioning triangulation technology; multiple microphones (microphone arrays) are used to measure the sound source at different measurement points, and since the time for the sound signal to reach different microphones has different degrees of delay (also known as time delay), the measured sound signal is processed by an algorithm to obtain the arrival direction (including azimuth, pitch angle) and distance of the sound source point relative to the microphone as the sound source position.

[0066] In practical applications, the voice wake-up system can locate the sound source of the acquired sound signal through a microphone array and a sound source localization algorithm to determine the sound source position of the sound signal.

[0067] Step 103: determine the target area where the sound source is located and the area attribute information of the target area.

[0068] As some examples, after determining the location of the sound source, the area where the sound signal is emitted can be determined as the target area based on the location of the sound source; since multiple areas have been determined in the current environment based on historical personnel activity information before obtaining the sound signal, and each area corresponds to an area attribute information, it is possible to determine which area in the current environment the target area belongs to, and use the area attribute information of the area as the area attribute information of the target area.

[0069] Step 104: adjusting a wake-up threshold of the voice wake-up system according to the area attribute information.

[0070] After determining the regional attribute information of the target area, the wake-up threshold of the voice wake-up system can be adjusted according to the area type indicated by the regional attribute information to adjust the wake-up sensitivity of the voice wake-up system; wherein the area type includes a designated area and a non-designated area; the designated area is a permanent area or an active area, and the non-designated area is a temporary active area or an inactive area.

[0071] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the area attribute information includes: detecting whether there is a human object in the target area; and adjusting the wake-up threshold of the voice wake-up system according to the detection result of the human object and the area attribute information.

[0072] After determining the regional attribute information of the target area, the voice wake-up system can also call the millimeter-wave radar to detect whether there is a human object in the target area, and adjust the wake-up threshold of the voice wake-up system according to the detection result of the human object and the area type indicated by the regional attribute information; wherein the detection result of the human object includes the presence of a human object in the target area and the absence of a human object in the target area.

[0073] If it is determined that the target area is a permanent area in the designated area, the voice wake-up system calls the millimeter-wave radar to detect whether there is anyone in the target area. If there is someone, the wake-up threshold of the voice wake-up system is reduced to increase the wake-up sensitivity of the voice wake-up system.

[0074] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the area attribute information includes:

[0075] Sub-step 11, when the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a designated area, adjust the wake-up threshold of the voice wake-up system to increase the wake-up sensitivity of the voice wake-up system.

[0076] As some examples, when the area attribute information of the target area is a permanent area or an active area in a specified area, when the voice wake-up system calls the millimeter-wave radar to detect that there is someone in the target area, the wake-up threshold of the voice wake-up system can be reduced to increase the wake-up sensitivity of the voice wake-up system, thereby improving the response speed of the voice wake-up system.

[0077] Sub-step 12, when the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a non-designated area, adjust the wake-up threshold of the voice wake-up system to reduce the wake-up sensitivity of the voice wake-up system.

[0078] As some examples, when the area attribute information of the target area is a temporary active area or an inactive area in a non-specified area, when the voice wake-up system calls the millimeter-wave radar to detect that there is someone in the target area, the wake-up threshold of the voice wake-up system can be increased to reduce the wake-up sensitivity of the voice wake-up system, thereby reducing the response speed of the voice wake-up system.

[0079] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the area attribute information includes:

[0080] Sub-step 13, when the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a designated area, adjust the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity.

[0081] As some examples, when the area attribute information of the target area is a permanent area or an active area in a specified area, when the voice wake-up system calls the millimeter-wave radar to detect that there is no one in the target area, the wake-up threshold of the voice wake-up system can be adjusted to the default threshold to adjust the wake-up sensitivity of the voice wake-up system to the default sensitivity.

[0082] In some examples, the default threshold may be a threshold set when the smart home device is produced, such as a factory default threshold of 85%; wherein the default threshold may have different default thresholds according to different voice wake-up systems and smart home devices, and subsequent adjustments to the wake-up threshold are made based on the default threshold.

[0083] Sub-step 14, when the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a non-designated area, adjust the wake-up threshold of the voice wake-up system to reduce the wake-up sensitivity of the voice wake-up system.

[0084] As some examples, when the area attribute information of the target area is a temporary active area or an inactive area in a non-specified area, when the voice wake-up system calls the millimeter-wave radar to detect that there is no one in the target area, the wake-up threshold of the voice wake-up system can be increased to reduce the wake-up sensitivity of the voice wake-up system, thereby avoiding the voice wake-up system from being woken up by mistake.

[0085] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the area attribute information includes:

[0086] Determine the sound type of the sound signal; and adjust the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information.

[0087] As some examples, the voice wake-up system can use neural networks, sound signal processing algorithms (such as time domain and frequency domain analysis, beamforming technology) to classify sound signals to identify and distinguish human voices from background noise sources.

[0088] In some examples, the sound type of the sound signal can be determined, such as whether the sound type is human voice or noise; the voice wake-up system adjusts its own wake-up threshold and then adjusts the wake-up sensitivity according to the sound type and regional attribute information of the target area.

[0089] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes:

[0090] Sub-step 21, when the sound type indicates that the sound signal is a human voice, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to increase the wake-up sensitivity of the voice wake-up system.

[0091] As some examples, when the area attribute information of the target area is a permanent area or an active area in a specified area, if the voice wake-up system determines that the sound signal is a human voice, the wake-up threshold of the voice wake-up system can be reduced to increase the wake-up sensitivity of the voice wake-up system, thereby improving the response speed of the voice wake-up system.

[0092] Sub-step 22, when the sound type indicates that the sound signal is a human voice, and the area attribute information indicates that the target area is a non-designated area, adjust the wake-up threshold of the voice wake-up system to reduce the wake-up sensitivity of the voice wake-up system.

[0093] As some examples, when the area attribute information of the target area is a temporary active area or an inactive area in a non-specified area, when the voice wake-up system determines that the sound signal is a human voice, the wake-up threshold of the voice wake-up system can be increased to reduce the wake-up sensitivity of the voice wake-up system, thereby avoiding the voice wake-up system from being mistakenly awakened.

[0094] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes:

[0095] Sub-step 23, when the sound type indicates that the sound signal is noise, and the area attribute information indicates that the target area is a designated area, adjust the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity.

[0096] As some examples, when the area attribute information of the target area is a permanent area or an active area in a specified area, if the voice wake-up system determines that the sound signal is noise, the wake-up threshold of the voice wake-up system can be adjusted to the default threshold to adjust the wake-up sensitivity of the voice wake-up system to the default sensitivity.

[0097] In some examples, the default threshold may be a threshold set when the smart home device leaves the factory. For example, the factory default threshold is 85%, and wake-up is triggered when the probability of the wake-up word in the sound signal reaches 85%. Among them, the default threshold may have different default thresholds according to different voice wake-up systems and smart home devices, and subsequent adjustments to the wake-up threshold are made based on the default threshold.

[0098] In sub-step 24, when the sound type indicates that the sound signal is noise and the area attribute information indicates that the target area is a non-specified area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system, thereby preventing the voice wake-up system from being mistakenly awakened.

[0099] As some examples, when the area attribute information of the target area is a temporary active area or an inactive area in a non-specified area, when the voice wake-up system determines that the sound signal is noise, the wake-up threshold of the voice wake-up system can be increased to reduce the wake-up sensitivity of the voice wake-up system, thereby avoiding the voice wake-up system from being mistakenly awakened.

[0100] As some examples, the default threshold of the wake-up threshold of the voice wake-up system is 85%, where the adjustment of the wake-up threshold is based on the default threshold. If the default threshold is 85%, and it needs to be reduced to 80% of the default threshold, the wake-up threshold needs to be adjusted to 68% (default threshold 85% multiplied by 80%=68%).

[0101] In some examples, the wake-up threshold of the voice wake-up system can also be adjusted according to the sound type, the detection result of the human object and the regional attribute information; Figure 2 As shown, the following situations may be included:

[0102] Resident area: When the sound source of the sound signal is located in a resident area (such as the sofa in the living room) and there is no particularly large background noise source at the sound source, when the radar detects that there is someone in the area, the system will lower the voice wake-up recognition threshold, for example, to 80% of the default threshold. If the radar detects that there is no one, the normal threshold (default threshold) will be restored.

[0103] Activity area: When the sound source of the sound signal is located in an activity area (such as an aisle or room activity area) and there is no particularly large background noise source at the sound source, when the radar detects that there is someone in the area, the system will lower the voice wake-up recognition threshold, for example, to 85% of the default threshold. If the radar detects that there is no one, the normal threshold (default threshold) will be restored.

[0104] Temporary activity area: When the sound source of the sound signal is located in a temporary activity area (such as a TV area) and there is no particularly large background noise source at the sound source location, when the radar detects that there is someone in the area, the system will increase the threshold, for example, to 120% of the default threshold. If the radar detects that there is no one, the threshold is further increased, for example, to 130% of the default threshold; if there is human voice and noise in the sound signal and the sound source locations overlap, the threshold needs to be further increased.

[0105] Inactive area: When the sound source of the sound signal is located in an inactive area (such as a storage cabinet area) and there is no particularly large background noise source at the sound source location, when the radar detects that there is someone in the area, the system will increase the threshold, for example, to 125% of the default threshold. If the radar detects that there is no one, the threshold is further increased, for example, to 135% of the default threshold. If there is human voice and noise in the sound signal and the sound source locations overlap, the threshold needs to be further increased.

[0106] In some examples of the present invention, by combining millimeter-wave radar and sound detection technology, the threshold of voice wake-up recognition is intelligently adjusted according to the area to which the sound source belongs and the indoor activities, thereby reducing false wake-ups and improving the response speed; by dividing multiple areas, distinguishing between permanent areas, active areas, temporary active areas, and inactive areas, and then optimizing the voice wake-up recognition strategy, the accuracy and response speed of the voice wake-up recognition system are improved, especially the anti-interference ability in complex environments.

[0107] For example, if the user is on the sofa in the living room (the permanent area), when the user issues a wake-up command, the system will respond quickly. If the user leaves the sofa in the living room, the system will return to the normal threshold to avoid false wake-ups.

[0108] For example, if a user is in the TV area (temporary activity area), when the TV is turned on and someone is in the area, the system will increase the threshold to avoid being mistakenly recognized as a wake-up command by the TV sound. If the TV is turned off and no one is in the area, the system will further increase the threshold to ensure that it will only respond when the user explicitly issues a wake-up command.

[0109] In an embodiment of the present invention, by acquiring a collected sound signal; locating the sound source of the sound signal to determine the sound source position of the sound signal; determining the target area where the sound source position is located and the regional attribute information of the target area; and adjusting the wake-up threshold of the voice wake-up system according to the regional attribute information, the wake-up threshold of the voice wake-up system is adjusted according to the area where the sound source position is located, thereby adjusting the wake-up sensitivity of the voice wake-up system, optimizing the wake-up recognition strategy of the voice wake-up system, and reducing the probability of false wake-up of the voice wake-up system.

[0110] Reference Figure 3, shows a step flow chart of a processing method based on a voice wake-up system provided by an embodiment of the present invention, where the voice wake-up system is deployed in a smart home device with a millimeter-wave radar.

[0111] In some examples, millimeter-wave radar can obtain activity information of people in the current environment by emitting millimeter-wave signals and receiving reflected signals. The radar signals are processed at high frequency and converted into data describing the position and motion status of the people.

[0112] As some examples, smart home devices may be smart air conditioners, smart central control screens, etc.

[0113] Specifically, the following steps may be included:

[0114] Step 301 : Obtain historical personnel activity information, and determine multiple areas in the current environment based on the historical personnel activity information, and set area attribute information for each area.

[0115] In some examples, historical personnel activity information is personnel activity information within a period obtained by collecting information based on millimeter-wave radar after the smart home device is installed. For example, after the device is installed, personnel activities are continuously detected for 10 days, and the personnel activity trajectory is obtained to determine multiple areas and set the area attribute information for each area.

[0116] For example, if a person stays in an area for more than 2 hours every day for 10 days, or if a person moves around in an area every day, such as the sofa in the living room, the corridor, or the corridor between the TV and the sofa in the living room, the area attribute information of the area can be set as the designated area. If a person stays in an area occasionally, or if a person stays in an area once a day or for 10 consecutive days, or if there is no human activity in an area, the area attribute information of the area can be defined as the non-designated area.

[0117] In actual applications, the voice wake-up system can obtain historical personnel activity information collected by millimeter-wave radar, determine multiple areas in the current environment based on the historical personnel activity information, and set corresponding area attribute information for each area, such as designated area and non-designated area.

[0118] In some embodiments of the present invention, the designated area is a permanent area or an active area, and the non-designated area is a temporary active area or an inactive area.

[0119] As some examples, permanent areas are areas where users often stay, such as the sofa in the living room. Usually, these areas have less background noise, and the user's voice commands have a higher priority; activity areas are areas where users may frequently enter and exit, such as corridors, room activity areas, etc., and the user's voice commands in these areas need to be responded to quickly; temporary activity areas are areas that appear occasionally, such as TV areas or temporarily set up activity areas. These areas may be affected by occasional noise, and the threshold needs to be increased to reduce false wake-ups; inactive areas are places that users do not often go to, such as storage cabinets, etc.

[0120] Step 302: Acquire the collected sound signal.

[0121] In practical applications, the sound signal may be the sound made by a person in the current environment, or the background sound made by other devices, such as the background sound made by a TV when a user is watching TV.

[0122] As some examples, one or more microphone arrays can be deployed in smart home devices to collect sound signals in the current environment in real time through the microphones; the voice wake-up system can obtain the sound signals collected by the microphone array for processing, such as sound classification, sound source localization, etc.

[0123] Step 303: localize the sound source of the sound signal to determine the sound source position of the sound signal.

[0124] As some examples, a sound source localization algorithm can be used to locate the sound signal and determine the sound source position of the sound signal; for example, the sound source localization algorithm can use direction of arrival (DOA) estimation and positioning triangulation technology; multiple microphones (microphone arrays) are used to measure the sound source at different measurement points, and since the time for the sound signal to reach different microphones has different degrees of delay (also known as time delay), the measured sound signal is processed by an algorithm to obtain the arrival direction (including azimuth, pitch angle) and distance of the sound source point relative to the microphone as the sound source position.

[0125] In practical applications, the voice wake-up system can locate the sound source of the acquired sound signal through a microphone array and a sound source localization algorithm to determine the sound source position of the sound signal.

[0126] Step 304: determine the target area where the sound source is located and the area attribute information of the target area.

[0127] As some examples, after determining the location of the sound source, the area where the sound signal is emitted can be determined as the target area based on the location of the sound source; since multiple areas have been determined in the current environment based on historical personnel activity information before obtaining the sound signal, and each area corresponds to an area attribute information, it is possible to determine which area in the current environment the target area belongs to, and use the area attribute information of the area as the area attribute information of the target area.

[0128] Step 305: adjusting a wake-up threshold of the voice wake-up system according to the area attribute information.

[0129] After determining the regional attribute information of the target area, the wake-up threshold of the voice wake-up system can be adjusted according to the area type indicated by the regional attribute information to adjust the wake-up sensitivity of the voice wake-up system; wherein the area type includes a designated area and a non-designated area; the designated area is a permanent area or an active area, and the non-designated area is a temporary active area or an inactive area.

[0130] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the area attribute information includes: detecting whether there is a human object in the target area; and adjusting the wake-up threshold of the voice wake-up system according to the detection result of the human object and the area attribute information.

[0131] After determining the regional attribute information of the target area, the voice wake-up system can also call the millimeter-wave radar to detect whether there is a human object in the target area, and adjust the wake-up threshold of the voice wake-up system according to the detection result of the human object and the area type indicated by the regional attribute information; wherein the detection result of the human object includes the presence of a human object in the target area and the absence of a human object in the target area.

[0132] If it is determined that the target area is a permanent area in the designated area, the voice wake-up system calls the millimeter-wave radar to detect whether there is anyone in the target area. If there is someone, the wake-up threshold of the voice wake-up system is reduced to increase the wake-up sensitivity of the voice wake-up system.

[0133] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the area attribute information includes:

[0134] Sub-step 11, when the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a designated area, adjust the wake-up threshold of the voice wake-up system to increase the wake-up sensitivity of the voice wake-up system.

[0135] As some examples, when the area attribute information of the target area is a permanent area or an active area in a specified area, when the voice wake-up system calls the millimeter-wave radar to detect that there is someone in the target area, the wake-up threshold of the voice wake-up system can be reduced to increase the wake-up sensitivity of the voice wake-up system, thereby improving the response speed of the voice wake-up system.

[0136] Sub-step 12, when the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a non-designated area, adjust the wake-up threshold of the voice wake-up system to reduce the wake-up sensitivity of the voice wake-up system.

[0137] As some examples, when the area attribute information of the target area is a temporary active area or an inactive area in a non-specified area, when the voice wake-up system calls the millimeter-wave radar to detect that there is someone in the target area, the wake-up threshold of the voice wake-up system can be increased to reduce the wake-up sensitivity of the voice wake-up system, thereby reducing the response speed of the voice wake-up system.

[0138] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the area attribute information includes:

[0139] Sub-step 13, when the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a designated area, adjust the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity.

[0140] As some examples, when the area attribute information of the target area is a permanent area or an active area in a specified area, when the voice wake-up system calls the millimeter-wave radar to detect that there is no one in the target area, the wake-up threshold of the voice wake-up system can be adjusted to the default threshold to adjust the wake-up sensitivity of the voice wake-up system to the default sensitivity.

[0141] In some examples, the default threshold may be a threshold set when the smart home device is produced, such as a factory default threshold of 85%; wherein the default threshold may have different default thresholds according to different voice wake-up systems and smart home devices, and subsequent adjustments to the wake-up threshold are made based on the default threshold.

[0142] Sub-step 14, when the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a non-designated area, adjust the wake-up threshold of the voice wake-up system to reduce the wake-up sensitivity of the voice wake-up system.

[0143] As some examples, when the area attribute information of the target area is a temporary active area or an inactive area in a non-specified area, when the voice wake-up system calls the millimeter-wave radar to detect that there is no one in the target area, the wake-up threshold of the voice wake-up system can be increased to reduce the wake-up sensitivity of the voice wake-up system, thereby avoiding the voice wake-up system from being woken up by mistake.

[0144] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the area attribute information includes:

[0145] Determine the sound type of the sound signal; and adjust the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information.

[0146] As some examples, the voice wake-up system can use neural networks, sound signal processing algorithms (such as time domain and frequency domain analysis, beamforming technology) to classify sound signals to identify and distinguish human voices from background noise sources.

[0147] In some examples, the sound type of the sound signal can be determined, such as whether the sound type is human voice or noise; the voice wake-up system adjusts its own wake-up threshold and then adjusts the wake-up sensitivity according to the sound type and regional attribute information of the target area.

[0148] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes:

[0149] Sub-step 21, when the sound type indicates that the sound signal is a human voice, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to increase the wake-up sensitivity of the voice wake-up system.

[0150] As some examples, when the area attribute information of the target area is a permanent area or an active area in a specified area, if the voice wake-up system determines that the sound signal is a human voice, the wake-up threshold of the voice wake-up system can be reduced to increase the wake-up sensitivity of the voice wake-up system, thereby improving the response speed of the voice wake-up system.

[0151] Sub-step 22, when the sound type indicates that the sound signal is a human voice, and the area attribute information indicates that the target area is a non-designated area, adjust the wake-up threshold of the voice wake-up system to reduce the wake-up sensitivity of the voice wake-up system.

[0152] As some examples, when the area attribute information of the target area is a temporary active area or an inactive area in a non-specified area, when the voice wake-up system determines that the sound signal is a human voice, the wake-up threshold of the voice wake-up system can be increased to reduce the wake-up sensitivity of the voice wake-up system, thereby avoiding the voice wake-up system from being mistakenly awakened.

[0153] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes:

[0154] Sub-step 23, when the sound type indicates that the sound signal is noise, and the area attribute information indicates that the target area is a designated area, adjust the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity.

[0155] As some examples, when the area attribute information of the target area is a permanent area or an active area in a specified area, if the voice wake-up system determines that the sound signal is noise, the wake-up threshold of the voice wake-up system can be adjusted to the default threshold to adjust the wake-up sensitivity of the voice wake-up system to the default sensitivity.

[0156] In some examples, the default threshold may be a threshold set when the smart home device leaves the factory. For example, the factory default threshold is 85%, and wake-up is triggered when the probability of the wake-up word in the sound signal reaches 85%. Among them, the default threshold may have different default thresholds according to different voice wake-up systems and smart home devices, and subsequent adjustments to the wake-up threshold are made based on the default threshold.

[0157] In sub-step 24, when the sound type indicates that the sound signal is noise and the area attribute information indicates that the target area is a non-specified area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system, thereby preventing the voice wake-up system from being mistakenly awakened.

[0158] As some examples, when the area attribute information of the target area is a temporary active area or an inactive area in a non-specified area, when the voice wake-up system determines that the sound signal is noise, the wake-up threshold of the voice wake-up system can be increased to reduce the wake-up sensitivity of the voice wake-up system, thereby avoiding the voice wake-up system from being mistakenly awakened.

[0159] As some examples, the default threshold of the wake-up threshold of the voice wake-up system is 85%, where the adjustment of the wake-up threshold is based on the default threshold. If the default threshold is 85%, and it needs to be reduced to 80% of the default threshold, the wake-up threshold needs to be adjusted to 68% (default threshold 85% multiplied by 80%=68%).

[0160] In some examples, the wake-up threshold of the voice wake-up system can also be adjusted according to the sound type, the detection result of the human object and the regional attribute information; Figure 2 As shown, the following situations may be included:

[0161] Resident area: When the sound source of the sound signal is located in a resident area (such as the sofa in the living room) and there is no particularly large background noise source at the sound source, when the radar detects that there is someone in the area, the system will lower the voice wake-up recognition threshold, for example, to 80% of the default threshold. If the radar detects that there is no one, the normal threshold (default threshold) will be restored.

[0162] Activity area: When the sound source of the sound signal is located in an activity area (such as an aisle or room activity area) and there is no particularly large background noise source at the sound source, when the radar detects that there is someone in the area, the system will lower the voice wake-up recognition threshold, for example, to 85% of the default threshold. If the radar detects that there is no one, the normal threshold (default threshold) will be restored.

[0163] Temporary activity area: When the sound source of the sound signal is located in a temporary activity area (such as a TV area) and there is no particularly large background noise source at the sound source location, when the radar detects that there is someone in the area, the system will increase the threshold, for example, to 120% of the default threshold. If the radar detects that there is no one, the threshold is further increased, for example, to 130% of the default threshold; if there is human voice and noise in the sound signal and the sound source locations overlap, the threshold needs to be further increased.

[0164] Inactive area: When the sound source of the sound signal is located in an inactive area (such as a storage cabinet area) and there is no particularly large background noise source at the sound source location, when the radar detects that there is someone in the area, the system will increase the threshold, for example, to 125% of the default threshold. If the radar detects that there is no one, the threshold is further increased, for example, to 135% of the default threshold. If there is human voice and noise in the sound signal and the sound source locations overlap, the threshold needs to be further increased.

[0165] In some examples of the present invention, by combining millimeter-wave radar and sound detection technology, the threshold of voice wake-up recognition is intelligently adjusted according to the area to which the sound source belongs and the indoor activities, thereby reducing false wake-ups and improving the response speed; by dividing multiple areas, distinguishing between permanent areas, active areas, temporary active areas, and inactive areas, and then optimizing the voice wake-up recognition strategy, the accuracy and response speed of the voice wake-up recognition system are improved, especially the anti-interference ability in complex environments.

[0166] For example, if the user is on the sofa in the living room (the permanent area), when the user issues a wake-up command, the system will respond quickly. If the user leaves the sofa in the living room, the system will return to the normal threshold to avoid false wake-ups.

[0167] For example, if a user is in the TV area (temporary activity area), when the TV is turned on and someone is in the area, the system will increase the threshold to avoid being mistakenly recognized as a wake-up command by the TV sound. If the TV is turned off and no one is in the area, the system will further increase the threshold to ensure that it will only respond when the user explicitly issues a wake-up command.

[0168] In an embodiment of the present invention, historical personnel activity information is obtained, and based on the historical personnel activity information, multiple areas are determined in the current environment, and regional attribute information of each area is set; then the collected sound signal is obtained; the sound source of the sound signal is located to determine the sound source position of the sound signal; the target area where the sound source position is located and the regional attribute information of the target area are determined; according to the regional attribute information, the wake-up threshold of the voice wake-up system is adjusted, and the wake-up threshold of the voice wake-up system is adjusted according to the area where the sound source position is located, thereby adjusting the wake-up sensitivity of the voice wake-up system, optimizing the wake-up recognition strategy of the voice wake-up system, and reducing the probability of false wake-up of the voice wake-up system.

[0169] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0170] Reference Figure 4 , shows a schematic diagram of the structure of a processing device based on a voice wake-up system provided by an embodiment of the present invention, which may specifically include the following modules:

[0171] The sound signal acquisition module 401 is used to acquire the collected sound signal;

[0172] A sound source location determination module 402, configured to perform sound source location on the sound signal to determine the sound source location of the sound signal;

[0173] The area attribute information determination module 403 is used to determine the target area where the sound source position is located and the area attribute information of the target area;

[0174] The wake-up threshold adjustment module 404 is used to adjust the wake-up threshold of the voice wake-up system according to the area attribute information.

[0175] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the area attribute information includes:

[0176] Detecting whether there is a human object in the target area;

[0177] The wake-up threshold of the voice wake-up system is adjusted according to the detection result of the human object and the area attribute information.

[0178] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the area attribute information includes:

[0179] When the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to increase the wake-up sensitivity of the voice wake-up system;

[0180] When the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

[0181] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the area attribute information includes:

[0182] When the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity;

[0183] When the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

[0184] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the area attribute information includes:

[0185] Determining a sound type of the sound signal;

[0186] Adjust the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information.

[0187] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes:

[0188] When the sound type indicates that the sound signal is a human voice, and the area attribute information indicates that the target area is a designated area, adjusting a wake-up threshold of the voice wake-up system to increase a wake-up sensitivity of the voice wake-up system;

[0189] When the sound type indicates that the sound signal is a human voice and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

[0190] In some embodiments of the present invention, adjusting the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes:

[0191] When the sound type indicates that the sound signal is noise, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity;

[0192] When the sound type indicates that the sound signal is noise and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

[0193] In some embodiments of the present invention, the designated area is a permanent area or an active area, and the non-designated area is a temporary active area or an inactive area.

[0194] In some embodiments of the present invention, the device further comprises:

[0195] The area determination module is used to obtain historical personnel activity information, and determine multiple areas in the current environment based on the historical personnel activity information, and set area attribute information for each area.

[0196] In some embodiments of the present invention, the voice wake-up system is deployed in a smart home device with a millimeter-wave radar.

[0197] An embodiment of the present invention further provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and the computer program implements the above-mentioned method when executed by the processor.

[0198] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0199] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0200] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0201] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0202] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0203] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0204] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0205] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0206] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the above elements.

[0207] The above is a detailed introduction to a processing method, device, equipment and medium based on a voice wake-up system. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A processing method based on a voice wake-up system, characterized in that: The method comprises: Acquiring collected sound signals; Performing sound source localization on the sound signal to determine the sound source position of the sound signal; Determine the target area where the sound source is located and area attribute information of the target area; According to the area attribute information, a wake-up threshold of the voice wake-up system is adjusted.

2. The method according to claim 1, characterized in that: The adjusting the wake-up threshold of the voice wake-up system according to the area attribute information includes: Detecting whether there is a human object in the target area; The wake-up threshold of the voice wake-up system is adjusted according to the detection result of the human object and the area attribute information.

3. The method according to claim 2, characterized in that The step of adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the region attribute information includes: When the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to increase the wake-up sensitivity of the voice wake-up system; When the detection result of the human object indicates that there is a human object in the target area, and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

4. The method according to claim 2, characterized in that: The step of adjusting the wake-up threshold of the voice wake-up system according to the detection result of the person object and the region attribute information includes: When the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity; When the detection result of the human object indicates that there is no human object in the target area, and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

5. The method according to claim 1, characterized in that The adjusting the wake-up threshold of the voice wake-up system according to the area attribute information includes: Determining a sound type of the sound signal; Adjust the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information.

6. The method according to claim 5, characterized in that The adjusting the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes: When the sound type indicates that the sound signal is a human voice, and the area attribute information indicates that the target area is a designated area, adjusting a wake-up threshold of the voice wake-up system to increase a wake-up sensitivity of the voice wake-up system; When the sound type indicates that the sound signal is a human voice and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

7. The method according to claim 5, characterized in that The adjusting the wake-up threshold of the voice wake-up system according to the sound type and the area attribute information includes: When the sound type indicates that the sound signal is noise, and the area attribute information indicates that the target area is a designated area, adjusting the wake-up threshold of the voice wake-up system to adjust the wake-up sensitivity of the voice wake-up system to a default sensitivity; When the sound type indicates that the sound signal is noise and the area attribute information indicates that the target area is a non-designated area, the wake-up threshold of the voice wake-up system is adjusted to reduce the wake-up sensitivity of the voice wake-up system.

8. The method according to claim 3 or 4 or 6 or 7, characterized in that: The designated area is a permanent area or an activity area, and the non-designated area is a temporary activity area or an inactive area.

9. The method according to any one of claims 1 to 7, characterized in that: Before obtaining the collected sound signal, the method includes: Historical personnel activity information is obtained, and based on the historical personnel activity information, multiple areas are determined in the current environment, and area attribute information of each area is set.

10. The method according to any one of claims 1 to 7, characterized in that: The voice wake-up system is deployed in a smart home device with a millimeter-wave radar.

11. A processing device based on a voice wake-up system, characterized in that: The device comprises: A sound signal acquisition module, used to acquire the collected sound signal; A sound source location determination module, used to perform sound source location on the sound signal to determine the sound source location of the sound signal; A region attribute information determination module, used to determine the target region where the sound source is located and the region attribute information of the target region; The wake-up threshold adjustment module is used to adjust the wake-up threshold of the voice wake-up system according to the area attribute information.

12. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method according to any one of claims 1 to 10 when executed by the processor.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images