Voice equipment control method and device, equipment and medium

Abstract

The invention discloses a voice equipment control method and device, equipment and a medium. The voice equipment control method comprises the steps that the target user number and target noise parameters of the space where voice equipment is located are collected; determining a target wake-up threshold value of the voice device according to the target user number and the target noise parameter; and controlling the voice device to operate according to the target wake-up threshold. According to the invention, the voice equipment can be controlled to dynamically adjust the wake-up threshold according to the number of users in the space and the noise parameter, so that the wake-up error rate and the wake-up rate are ensured to be in a relatively balanced state, the wake-up error rate is not reduced by sacrificing the wake-up rate, the wake-up error rate is ensured to be in a relatively low level, and the wake-up rate is ensured to be in a relatively high level. Therefore, the voice equipment is usually in a state with relatively high wake-up performance in the space, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a voice device control method, device, equipment and medium. Background Art

[0002] With the continuous development of intelligent recognition technology, the application of artificial intelligence wake-up is becoming more and more extensive. Common artificial intelligence wake-up methods include voice wake-up. Among them, the wake-up rate and false wake-up rate are the main indicators to characterize the voice wake-up function.

[0003] Currently, the false awakening rate is reduced by manually adjusting the wake-up threshold of the voice device, but this reduces the awakening rate to a certain extent. Therefore, how to balance the false awakening rate and the awakening rate so that the voice device has a higher awakening rate and a lower false awakening rate is an urgent problem to be solved. Summary of the invention

[0004] In view of the above-mentioned technical problems in the related art, the embodiments of the present invention provide a method, apparatus, device and medium for controlling a voice device.

[0005] In a first aspect, an embodiment of the present invention provides a method for controlling a voice device, the method comprising:

[0006] Collect the target number of users and target noise parameters in the space where the voice equipment is located;

[0007] Determining a target wake-up threshold of the voice device according to the target number of users and the target noise parameter;

[0008] The voice device is controlled to operate according to the target wake-up threshold.

[0009] In some implementations, determining a target wake-up threshold of the voice device according to the target number of users and the target noise parameter includes:

[0010] Determining a target wake-up gear corresponding to the target number of users and the target noise parameter according to a correspondence between the number of users, the noise parameter, and the wake-up gear;

[0011] According to the corresponding relationship between the wake-up gear and the wake-up threshold, the wake-up threshold corresponding to the target wake-up gear is determined as the target wake-up threshold.

[0012] In some implementations, the correspondence between the wake-up gear and the wake-up threshold is obtained by the following steps:

[0013] Obtain a preset wake-up rate range of the voice device;

[0014] Divide the preset wake-up rate range into N groups of reference wake-up rate ranges, where N is a positive integer;

[0015] Based on the N groups of reference wake-up rate ranges, N wake-up gears are determined, and based on the reference wake-up rate range corresponding to each wake-up gear, a wake-up threshold corresponding to each wake-up gear is determined.

[0016] In some implementations, the target number of users is positively correlated with the target wake-up threshold, and the target noise parameter is positively correlated with the target wake-up threshold.

[0017] In some implementations, the collecting the target number of users in the space where the voice device is located includes:

[0018] Collecting morphological data of spatial objects in the space where the voice device is located;

[0019] According to the morphological data of the spatial object, the users in the space where the voice device is located are identified to determine the number of target users.

[0020] In some implementations, controlling the voice device to operate according to the target wake-up threshold includes:

[0021] Under the target wake-up threshold, original audio information received by the voice device is recognized to obtain target audio information;

[0022] The target audio information is matched with the reference wake-up audio information. If the match is successful, the voice device is controlled to respond to the target audio information, and the reference wake-up audio information is the audio information corresponding to the wake-up word.

[0023] In some embodiments, after determining the target wake-up threshold of the voice device, the method further includes:

[0024] If an adjustment operation of the user for the target wake-up threshold is received, determining an adjusted wake-up threshold corresponding to the adjustment operation;

[0025] The voice device is controlled to operate according to the adjusted wake-up threshold.

[0026] In a second aspect, an embodiment of the present invention provides a voice device control device, the device comprising:

[0027] A collection module, used to collect the target number of users and target noise parameters in the space where the voice equipment is located;

[0028] A threshold determination module, used to determine a target wake-up threshold of the voice device according to the target number of users and the target noise parameter;

[0029] A control module is used to control the voice device to operate according to the target wake-up threshold.

[0030] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the first aspect when executing the program.

[0031] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method steps provided in the first aspect.

[0032] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0033] An embodiment of the present invention provides a method for controlling a voice device, which collects the target number of users and the target noise parameters of the space where the voice device is located; then, according to the target number of users and the target noise parameters, determines the target wake-up threshold of the voice device; finally, controls the voice device to operate according to the target wake-up threshold. It can be seen that the embodiment of this specification can control the voice device to dynamically adjust the wake-up threshold according to the number of users and noise parameters in the space, ensuring that the false wake-up rate and the wake-up rate are in a relatively balanced state, rather than reducing the false wake-up rate by sacrificing the wake-up rate, thus ensuring that the false wake-up rate is at a low level and the wake-up rate is at a high level, so that the voice device is usually in a state of high wake-up performance in the space where it is located, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 A flowchart of a voice device control method provided in this application;

[0036] Figure 2 A schematic diagram of the corresponding relationship between the number of users, noise parameters and wake-up gears provided in this application;

[0037] Figure 3 A schematic diagram of the structure of a voice device control device provided in this application;

[0038] Figure 4 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0039] The embodiment of this specification provides a method for controlling a voice device, the method comprising: collecting the target number of users and target noise parameters of a space where the voice device is located; determining a target wake-up threshold of the voice device based on the target number of users and the target noise parameters; and controlling the voice device to operate according to the target wake-up threshold.

[0040] By collecting the target number of users and target noise parameters of the space where the voice device is located; then, according to the target number of users and the target noise parameters, determining the target wake-up threshold of the voice device; finally, controlling the voice device to operate according to the target wake-up threshold. It can be seen that the embodiments of this specification can control the voice device to dynamically adjust the wake-up threshold according to the number of users and noise parameters in the space, ensuring that the false wake-up rate and the wake-up rate are in a relatively balanced state, rather than reducing the false wake-up rate by sacrificing the wake-up rate, thus ensuring that the false wake-up rate is at a low level and the wake-up rate is at a high level, so that the voice device is usually in a state of high wake-up performance in the space where it is located, thereby improving the user experience.

[0041] The solution in the embodiments of this specification realizes the positioning and type determination of smart devices through mobile robots without human intervention, which greatly improves the accuracy of smart device positioning and improves user experience.

[0042] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiment 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.

[0043] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0044] Voice devices refer to a type of intelligent hardware device that can interact through voice. They can complete various operations through voice control, such as music playback, smart home control, voice search, etc. Voice devices usually have technologies such as voice recognition, speech synthesis, and natural language processing, and can achieve voice interaction with users. Voice devices can be awakened by a wake-up word, which can be a specific word agreed upon in advance, such as Xiaomei Xiaomei.

[0045] The wake-up rate of a voice device refers to the ratio of the voice device being successfully awakened when the wake-up word is issued to the voice device.

[0046] The false wake-up rate of a voice device refers to the number of false triggers and false wake-ups of the voice module within a period of time in the user's actual living noise environment. False wake-up refers to the false triggering of the voice device due to noise (environment, human voice, etc.).

[0047] The wake-up threshold refers to the probability that the voice device can be successfully awakened, which can be expressed as 0-100%. When the wake-up threshold is higher, it means that the probability of the voice device being successfully awakened is greater, and relatively, the probability of the voice device being woken up by mistake is also greater. When the wake-up threshold is lower, it means that the probability of the voice device being successfully awakened is lower, and relatively, the probability of the voice device being woken up by mistake is also lower.

[0048] like Figure 1 FIG. 1 is a flowchart of a method for controlling a voice device provided in an embodiment of the present specification, and the method specifically includes the following steps:

[0049] Step S101, collecting the target number of users and target noise parameters in the space where the voice device is located;

[0050] Step S102, determining a target wake-up threshold of the voice device according to the target number of users and the target noise parameter;

[0051] Step S103: Control the voice device to operate according to the target wake-up threshold.

[0052] The solution provided in the embodiments of this specification can be applied to voice devices or other terminal devices that can be controlled by voice, wherein the voice device can be a mobile phone, a smart speaker, a home appliance with a voice control function, etc. This solution can also be applied to a server, where the server communicates with the voice device, and the voice device sends the detected number of users and noise parameters to the server, so that the server processes the received number of users and noise parameters to obtain the target wake-up threshold, and controls the voice device to operate according to the target wake-up threshold. This solution can also be applied to a system consisting of a voice device and a server, which is not limited in the embodiments of this specification.

[0053] Regarding step S101, the space where the voice device is located can be a relatively independent area where the voice device is located, for example, it can be an area divided according to the function of the house, including bedroom, kitchen, living room, dining room, office, etc. The space where the voice device is located can be determined according to the actual placement of the voice device. When the voice device is placed in bedroom No. 1, the space where the voice device is located is bedroom No. 1; when the voice device is placed in kitchen No. 2, the space where the voice device is located is kitchen No. 2; and so on, the embodiments of this specification will not be repeated here.

[0054] The target user refers to a person who can use the wake-up word to wake up the voice device in the space where the voice device is currently located. The number of target users in the space where the voice device is located can be collected in the following ways: collecting the morphological data of the spatial objects in the space where the voice device is located; identifying the users in the space where the voice device is located based on the morphological data of the spatial objects to determine the number of target users.

[0055] Specifically, the spatial objects in the space where the voice device is located include non-living objects such as furniture and machines, as well as living objects such as users and pets. The morphological data of the spatial objects can be any data or a combination of various data that can distinguish users and other spatial objects, such as infrared thermal imaging data, contour data, moving speed feature data, etc.

[0056] The frequency of collecting the morphological data of the spatial objects in the space where the voice device is located can be determined according to actual needs. For example, based on the historical records of the space where the voice device is located, determine whether the changes of the spatial objects in the space where the voice device is located are frequent. If the changes are frequent, a higher collection frequency can be set to update the morphological data in time, and then the number of target users can be updated at a higher frequency, and finally the wake-up threshold of the voice device is updated more frequently, which can improve the closeness between the voice device and the environmental changes, balance the false awakening rate and the awakening rate of the voice device in time according to the environmental changes, and improve the awakening performance of the voice device. If the changes of the spatial objects in the space where the voice device is located are not frequent, a lower collection frequency can be set to update the morphological data. On the one hand, it can ensure that the false awakening rate and the awakening rate of the voice device are in a relatively balanced state, and ensure that the wake-up performance of the voice device is good. On the other hand, it can also reduce the data processing frequency and reduce the data processing amount, which also reduces the operating power consumption of the voice device and saves resources.

[0057] According to different morphological data, collecting the morphological data of the spatial objects in the space where the voice device is located can be implemented in different ways, for example, it can include the following three implementation methods or any combination of the following three methods. It should be noted that after any combination of the following three methods, more diversified data support can be provided for determining the number of target users, thereby making the final number of target users more accurate.

[0058] Method 1: Use an infrared imager to collect infrared thermal imaging data of spatial objects in the space where the voice device is located.

[0059] Method 2: Use image acquisition equipment to collect contour data of spatial objects in the space where the voice device is located.

[0060] Method 3: Use millimeter-wave radar to collect the moving speed of spatial objects in the space where the voice device is located.

[0061] After obtaining the morphological data of the spatial object, it is possible to determine whether the spatial object is the target user based on the morphological data of the spatial object. For example, when the morphological data is infrared thermal imaging data, the infrared thermal imaging data can be matched with the human body temperature reference data. If the two match, it can be determined that the current spatial object is the target user. When the morphological data is contour data, the contour data can be matched with the human contour reference data. If the two match, it can be determined that the current spatial object is the target user. Alternatively, when the morphological data is moving speed, the moving features can be extracted based on the moving speed, and the moving features can be matched with the moving reference features of the human. If the two match, it can be determined that the current spatial object is the target user.

[0062] In the same time period, the number of space objects identified as target users in the space where the voice device is located is counted, and the number of target users can be finally obtained.

[0063] In the embodiments of this specification, the target noise parameter refers to the sound intensity of the audio that the voice device can detect in the same time period, which can usually be expressed in decibels. Regarding the target noise parameters of the space where the voice device is located, the microphone of the voice device can be used for collection, so there is no need to install an additional audio signal collection device for the voice device, which can avoid the redundant structure of the voice device on the one hand, and reduce the equipment investment cost of the voice device on the other hand.

[0064] Regarding step S102, according to the target number of users and the target noise parameter, determining the target wake-up threshold of the voice device can be implemented in a variety of ways, two of which are described below. It should be noted that, regardless of the implementation in the following method 1 or method 2, it is necessary to satisfy the relationship that the target number of users is positively correlated with the target wake-up threshold, and the target noise parameter is positively correlated with the target wake-up threshold.

[0065] Mode 1: According to the corresponding relationship between the number of users, the noise parameter and the wake-up threshold, determine the target wake-up threshold corresponding to the target number of users and the target noise parameter.

[0066] Method 2: According to the correspondence between the number of users, noise parameters and wake-up gears, determine the target wake-up gear corresponding to the target number of users and the target noise parameter; according to the correspondence between the wake-up gear and the wake-up threshold, determine the wake-up threshold corresponding to the target wake-up gear as the target wake-up threshold.

[0067] Regarding mode 1, the corresponding relationship between the number of users, the noise parameter and the wake-up threshold includes: the number of users is positively correlated with the wake-up threshold, and the noise parameter is positively correlated with the wake-up threshold. In other words, the larger the number of users, the larger the corresponding wake-up threshold, and the larger the noise parameter, the larger the corresponding wake-up threshold. The corresponding relationship between the number of users, the noise parameter and the wake-up threshold can be embodied in at least one form of a table, a curve, or point data, which can be selected according to actual conditions.

[0068] For example, as shown in Table 1, the corresponding relationship between the number of users, the noise parameter and the wake-up threshold is shown in a table. According to Table 1, when the number of users is 1 and the noise parameter is 46 dB, the corresponding wake-up threshold is 50%. It should be noted that the values ​​and their corresponding relationships involved in Table 1 are only for illustrative purposes and do not limit the solutions provided in the embodiments of this specification.

[0069] According to the target number of users and the target noise parameter determined in step S101, the corresponding relationship between the number of users, the noise parameter and the wake-up threshold is queried, and the target wake-up threshold corresponding to the target number of users and the target noise parameter can be determined. For example, when the number of target users is 3 and the target noise parameter is less than or equal to 45dB, it can be known from the above Table 1 that the corresponding target wake-up threshold is 60%.

[0070] Table 1

[0071]

[0072] Regarding mode 2, the corresponding relationship between the number of users, the noise parameter, and the wake-up gear includes: the number of users is positively correlated with the wake-up gear, and the noise parameter is positively correlated with the wake-up gear. The corresponding relationship between the number of users, the noise parameter, and the wake-up gear can be embodied in at least one form of a table, a curve, or point data, which can be selected according to actual conditions.

[0073] For example, Figure 2 As shown, a curve (specifically, a contour line) is used to reflect the corresponding relationship between the number of users, the noise parameter, and the wake-up threshold, wherein the horizontal axis represents the number of users, and the vertical axis represents the noise parameter. Figure 2Each curve in the figure corresponds to the same wake-up gear. Along the line connecting the three points ABC, the wake-up gear corresponding to each curve gradually increases. Point A in the figure indicates that when 1 person is detected and the noise is between 45db-47db, the wake-up threshold gear is 1 gear. Point B in the figure indicates that when 4 people are detected and the noise is between 51db-53db, the wake-up threshold gear is 5 gears. Point C in the figure indicates that when 7 people are detected and the noise is between 59db and 61db, there are many people and the noise is loud, which is very easy to cause false wake-ups. Therefore, the wake-up threshold gear is the maximum gear 9 gears, which ensures that wake-ups can be made while minimizing false wake-ups.

[0074] from Figure 2 As can be seen from the figure, as the number of users increases and the noise parameter increases, the corresponding wake-up gear also gradually increases. It should be noted that Figure 2 The numerical values ​​and their corresponding relationships involved are only exemplary and do not limit the solutions provided in the embodiments of this specification.

[0075] In addition, the corresponding relationship between the wake-up gear and the wake-up threshold is that the higher the wake-up gear, the larger the corresponding wake-up threshold, which can be embodied in at least one form of a table, a curve, or point data, which can be selected according to actual conditions. The corresponding relationship between the wake-up gear and the wake-up threshold can be that each wake-up gear corresponds to a fixed wake-up threshold, for example, as shown in Table 2, different gears correspond to different fixed wake-up thresholds.

[0076] Table 2

[0077] Wake-up gear 1st gear 2nd gear 3rd gear 4th gear 5th gear 6th gear 7th gear Wake-up threshold 35％ 45％ 55％ 65％ 75％ 85％ 95％

[0078] In addition, the correspondence between the wake-up gear and the wake-up threshold may be that each wake-up gear corresponds to a fixed wake-up threshold range, for example, as shown in Table 3, different gears correspond to different wake-up threshold ranges.

[0079] Table 3

[0080] Wake-up gear 1st gear 2nd gear 3rd gear 4th gear 5th gear 6th gear Threshold Range 25％-35％ 35％-45％ 45％-55％ 55％-65％ 65％-75％ 75％-85％

[0081] According to the target number of users and the target noise parameter determined in step S101, the corresponding relationship between the number of users, the noise parameter and the wake-up gear can be queried to determine the target wake-up gear corresponding to the target number of users and the target noise parameter. Figure 2 It can be seen that when the number of target users is 3 and the target noise parameter is 48dB, the corresponding target wake-up gear is 3.

[0082] When the correspondence between the wake-up gear and the wake-up threshold is that each wake-up gear corresponds to a fixed wake-up threshold, the target wake-up threshold corresponding to the target wake-up gear can be directly determined according to the correspondence between the wake-up gear and the wake-up threshold. For example, when the target wake-up gear is gear 3, then according to Table 2, the corresponding target wake-up threshold is 55%.

[0083] When the correspondence between the wake-up gear and the wake-up threshold is that each wake-up gear corresponds to a fixed wake-up threshold range, the target wake-up threshold range corresponding to the target wake-up gear can be determined according to the correspondence between the wake-up gear and the wake-up threshold range. For example, when the target wake-up gear is gear 3, then according to Table 3, the corresponding target wake-up threshold is 45%-55%. At this time, you can arbitrarily specify a wake-up threshold from 45%-55% as the target wake-up threshold, or you can select a wake-up threshold from 45%-55% as the target wake-up threshold based on the historical detection data of the voice device. This specification embodiment does not limit this.

[0084] Furthermore, the corresponding relationship between the wake-up gear and the wake-up threshold is obtained by the following steps:

[0085] Obtain a preset wake-up rate range of the voice device;

[0086] Divide the preset wake-up rate range into N groups of reference wake-up rate ranges, where N is a positive integer;

[0087] Based on the N groups of reference wake-up rate ranges, N wake-up gears are determined, and based on the reference wake-up rate range corresponding to each wake-up gear, a wake-up threshold corresponding to each wake-up gear is determined.

[0088] The preset wake-up rate range can be selected from the range of 0-100%. In some embodiments, the preset wake-up rate range can be a part of 0-100%, for example, 30%-100%, or 29%-98%, etc., which can be set according to the actual scenario.

[0089] The value of N can be set according to the adjustment accuracy of the wake-up threshold in the actual scenario. The larger the value of N, the finer the division of the wake-up rate, and the higher the adjustment accuracy of the wake-up threshold; when the value of N is smaller, the coarser the division of the wake-up rate, and the lower the adjustment accuracy of the wake-up threshold.

[0090] The preset wake-up rate range is divided into N groups. The preset wake-up rate range can be evenly divided into the N groups, or the preset wake-up rate range can be unequally divided into the N groups. The specific selection can be made according to actual conditions, and the embodiments of this specification do not limit this.

[0091] For example, when the preset wake-up rate range is 30%-100%, N is 7, and an average division method is adopted, a corresponding relationship as shown in Table 4 can be obtained.

[0092] Table 4

[0093]

[0094] For another example, when the preset wake-up rate range is 30%-100%, N is 7, and an uneven division method is adopted, the corresponding relationship shown in Table 5 can be obtained.

[0095] Table 5

[0096]

[0097] Furthermore, after determining the target wake-up threshold of the voice device, it is also possible to monitor whether the user generates an adjustment operation for the target wake-up threshold. If an adjustment operation of the user for the target wake-up threshold is received, the adjusted wake-up threshold corresponding to the adjustment operation is determined; and the voice device is controlled to operate according to the adjusted wake-up threshold.

[0098] After determining the target wake-up threshold, step S103 can be directly executed, and it can also be monitored whether the user generates an adjustment operation for the target wake-up threshold. The user can generate an adjustment operation for the target wake-up threshold through a client or other device. When an adjustment operation is received, it means that the current target wake-up threshold does not meet the user's needs. The adjusted wake-up threshold is obtained from the relevant information of the adjustment operation, and the voice device is controlled to operate according to the adjusted wake-up threshold. In this way, the degree of adaptation between the wake-up performance of the voice device and the user's needs can be improved, and the user experience can be improved. Among them, the method of controlling the voice device to operate according to the adjusted wake-up threshold is similar to that of step S103. For details, please refer to the relevant description of step S103, which will not be repeated here.

[0099] Regarding step S103, the voice device is controlled to operate according to the target wake-up threshold. When a wake-up word is detected, the wake-up word is responded to at the target wake-up threshold. Specifically, it can be implemented according to the following steps: at the target wake-up threshold, the original audio information received by the voice device is identified to obtain the target audio information; the target audio information is matched with the reference wake-up audio information. If the match is successful, the voice device is controlled to respond to the target audio information, and the reference wake-up audio information is the audio information corresponding to the wake-up word.

[0100] The target frequency feature is a frequency feature that matches the frequency of the sound waves emitted by the user. Under the target wake-up threshold, the microphone of the voice device is used to collect the original audio information of the space where the voice device is located, and the original audio information is separated, and the audio information with the target frequency feature is screened out as the target audio information, that is, the audio information emitted by the user is screened out as the target audio information. By screening out the target audio information, the matching accuracy between the target audio information and the reference wake-up audio information can be improved by removing the ambient noise in the space where the voice device is located, thereby improving the response performance of the voice device.

[0101] The target audio information is matched with the reference wake-up audio information, and whether the target audio information is the audio information containing the wake-up word is determined according to the degree of match between the two. When the degree of match between the target audio information and the reference wake-up audio information is less than or equal to the preset match, it is considered that the target audio information does not belong to the audio information containing the wake-up word, and the voice device is controlled not to respond to the target audio information.

[0102] When the degree of match between the target audio information and the reference wake-up audio information is greater than a preset degree of match, the target audio information is considered to be audio information containing a wake-up word, and the voice device can be controlled to respond to the target audio information.

[0103] In summary, the embodiments of this specification collect the target number of users and target noise parameters of the space where the voice device is located; then, according to the target number of users and the target noise parameters, determine the target wake-up threshold of the voice device; finally, control the voice device to operate according to the target wake-up threshold. It can be seen that the embodiments of this specification can control the voice device to dynamically adjust the wake-up threshold according to the number of users and noise parameters in the space, ensuring that the false wake-up rate and the wake-up rate are in a relatively balanced state, rather than reducing the false wake-up rate by sacrificing the wake-up rate, thus ensuring that the false wake-up rate is at a low level and the wake-up rate is at a high level, so that the voice device is usually in a state of high wake-up performance in the space where it is located, thereby improving the user experience.

[0104] If the number of people in the current space of the voice device is smaller and the noise parameter is lower, that is, the space where the voice device is located is in a quiet environment, a relatively low wake-up threshold is set to make the voice device easier to wake up. And because the noise is smaller, the probability of the voice device being woken up by mistake is also reduced, thereby greatly improving the wake-up effect.

[0105] If there are more people in the current space and the noise parameter is higher, that is, the space where the voice device is located is in a relatively noisy environment, a relatively high wake-up threshold is set so that the voice device is relatively difficult to wake up. Although the noise is large, since the voice device is relatively difficult to wake up, the probability of false wake-up is reduced, thereby greatly improving the wake-up effect.

[0106] If the number of people in the current space is moderate and the noise parameters are moderate, that is, the space where the voice device is located is in a relatively moderate environment, a relatively moderate wake-up threshold is set. This can ensure that the voice device can be awakened, but at the same time ensure that the probability of the voice device being awakened by mistake is moderate, thereby greatly improving the wake-up effect.

[0107] Based on the same inventive concept, the embodiments of this specification provide Figure 3 A voice device control device is shown, the device comprising:

[0108] The collection module 301 is used to collect the number of target users and target noise parameters in the space where the voice device is located;

[0109] A threshold determination module 302, configured to determine a target wake-up threshold of the voice device according to the target number of users and the target noise parameter;

[0110] The control module 303 is used to control the voice device to operate according to the target wake-up threshold.

[0111] In some implementations, the threshold determination module 302 includes:

[0112] A gear determination submodule, used to determine a target wake-up gear corresponding to the target number of users and the target noise parameter according to the corresponding relationship between the number of users, the noise parameter and the wake-up gear;

[0113] The threshold determination submodule is used to determine the wake-up threshold corresponding to the target wake-up gear as the target wake-up threshold according to the corresponding relationship between the wake-up gear and the wake-up threshold.

[0114] In some embodiments, the apparatus further includes a corresponding relationship determination module, configured to:

[0115] Obtain a preset wake-up rate range of the voice device;

[0116] Divide the preset wake-up rate range into N groups of reference wake-up rate ranges, where N is a positive integer;

[0117] Based on the N groups of reference wake-up rate ranges, N wake-up gears are determined, and based on the reference wake-up rate range corresponding to each wake-up gear, a wake-up threshold corresponding to each wake-up gear is determined.

[0118] In some implementations, the target number of users is positively correlated with the target wake-up threshold, and the target noise parameter is positively correlated with the target wake-up threshold.

[0119] In some embodiments, the acquisition module 301 includes:

[0120] A morphological data collection submodule, used to collect morphological data of spatial objects in the space where the voice device is located;

[0121] The quantity determination submodule is used to identify the users in the space where the voice device is located according to the morphological data of the spatial object to determine the number of target users.

[0122] In some implementations, the control module 303 includes:

[0123] A screening submodule, configured to identify the original audio information received by the voice device under the target wake-up threshold to obtain target audio information;

[0124] The running submodule is used to match the target audio information with the reference wake-up audio information. If the match is successful, the voice device is controlled to respond to the target audio information, and the reference wake-up audio information is the audio information corresponding to the wake-up word.

[0125] In some embodiments, the apparatus further comprises a regulating module, configured to:

[0126] After determining the target wake-up threshold of the voice device, if an adjustment operation of the user for the target wake-up threshold is received, determining an adjusted wake-up threshold corresponding to the adjustment operation;

[0127] The voice device is controlled to operate according to the adjusted wake-up threshold.

[0128] Regarding the above-mentioned device, the specific functions of each module therein have been described in detail in an embodiment of a voice device control method provided in an embodiment of this specification, and will not be elaborated here.

[0129] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, referring to Figure 4 As shown, it includes: a memory 404, a processor 402, and a computer program stored in the memory 404 and executable on the processor 402. When the processor 402 executes the program, any implementation method in an embodiment of a voice device control method is implemented.

[0130] Among them, Figure 4In the embodiment of the present invention, a bus architecture (represented by bus 400) is shown, which may include any number of interconnected buses and bridges, and bus 400 links various circuits including one or more processors represented by processor 402 and memory represented by memory 404. Bus 400 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 405 provides an interface between bus 400 and receiver 401 and transmitter 403. Receiver 401 and transmitter 403 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 402 is responsible for managing bus 400 and general processing, while memory 404 may be used to store data used by processor 402 when performing operations.

[0131] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on a computer-readable medium or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these. In addition, each functional unit may be integrated into a processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed in multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0134] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0135] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. A voice device control method, characterized in that: The method comprises: Collect the target number of users and target noise parameters in the space where the voice equipment is located; Determining a target wake-up threshold of the voice device according to the target number of users and the target noise parameter; The voice device is controlled to operate according to the target wake-up threshold.

2. The method according to claim 1, characterized in that The step of determining a target wake-up threshold of the voice device according to the target number of users and the target noise parameter includes: Determining a target wake-up gear corresponding to the target number of users and the target noise parameter according to a correspondence between the number of users, the noise parameter, and the wake-up gear; According to the corresponding relationship between the wake-up gear and the wake-up threshold, the wake-up threshold corresponding to the target wake-up gear is determined as the target wake-up threshold.

3. The method according to claim 2, characterized in that The corresponding relationship between the wake-up gear and the wake-up threshold is obtained by the following steps: Obtain a preset wake-up rate range of the voice device; Divide the preset wake-up rate range into N groups of reference wake-up rate ranges, where N is a positive integer; Based on the N groups of reference wake-up rate ranges, N wake-up gears are determined, and based on the reference wake-up rate range corresponding to each wake-up gear, a wake-up threshold corresponding to each wake-up gear is determined.

4. The method according to claim 1, characterized in that The target number of users is positively correlated with the target awakening threshold, and the target noise parameter is positively correlated with the target awakening threshold.

5. The method according to claim 1, characterized in that The target number of users in the space where the voice collection device is located includes: Collecting morphological data of spatial objects in the space where the voice device is located; According to the morphological data of the spatial object, the users in the space where the voice device is located are identified to determine the number of target users.

6. The method according to claim 1, characterized in that The controlling the voice device to operate according to the target wake-up threshold comprises: Under the target wake-up threshold, original audio information received by the voice device is recognized to obtain target audio information; The target audio information is matched with the reference wake-up audio information. If the match is successful, the voice device is controlled to respond to the target audio information, and the reference wake-up audio information is the audio information corresponding to the wake-up word.

7. The method according to claim 1, characterized in that After determining the target wake-up threshold of the voice device, the method further includes: If an adjustment operation of the user for the target wake-up threshold is received, determining an adjusted wake-up threshold corresponding to the adjustment operation; The voice device is controlled to operate according to the adjusted wake-up threshold.

8. A voice device control device, characterized in that: The device comprises: A collection module, used to collect the target number of users and target noise parameters in the space where the voice equipment is located; A threshold determination module, used to determine a target wake-up threshold of the voice device according to the target number of users and the target noise parameter; A control module is used to control the voice device to operate according to the target wake-up threshold.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.

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

Images