Voice wake-up method, device, electronic device, and storage medium for device

Abstract

The embodiments of the present invention relate to a voice wake-up method, apparatus, electronic device, and storage medium for a device. The voice wake-up method for the device includes, after acquiring the user's voice signal, determining the user's target age type and determining the similarity between the voice signal and the target wake-up word; determining the target wake-up sensitivity of the device corresponding to the target age type based on the target age type; and determining the device's wake-up strategy based on the similarity and the target wake-up sensitivity to control the device to perform operations corresponding to the wake-up strategy. Therefore, when performing voice wake-up, the embodiments of the present invention analyze the user's age and adopt different sensitivities according to different age groups to make corresponding wake-up decisions, thereby improving the accuracy of the user's voice wake-up device and improving the user experience.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of smart home technology, and in particular to a method and apparatus for waking up a device by voice, an electronic device, and a storage medium. Background Art

[0002] With the advancement of technology and the development of science and technology, most smart homes in the home are equipped with voice wake-up functions, and users can use preset wake-up words to wake up smart devices.

[0003] In related technologies, most smart homes are pre-set with wake-up sensitivity. When the user's voice signal is collected, the similarity between the user's voice signal and the wake-up word is determined, and whether to wake up the smart home is controlled based on the similarity and the size of the wake-up sensitivity.

[0004] However, since the wake-up sensitivity is a certain value and different users have different voice characteristics, the voice wake-up of the user's smart device is inaccurate, resulting in a poor user experience. Summary of the Invention

[0005] In view of this, in order to solve the technical problems of inaccuracy and poor user experience in the prior art of user voice wake-up of smart homes, embodiments of the present invention provide a device voice wake-up method, apparatus, electronic device and storage medium.

[0006] In a first aspect, an embodiment of the present invention provides a voice wake-up method for a device, comprising:

[0007] After acquiring the user's voice signal, determining the target age type of the user and determining the similarity between the voice signal and the target wake-up word;

[0008] determining, according to the target age type, a target wake-up sensitivity of a device corresponding to the target age type;

[0009] A wake-up strategy for the device is determined according to the similarity and the target wake-up sensitivity, so as to control the device to perform an operation corresponding to the wake-up strategy.

[0010] In an optional implementation, determining, based on the target age type, a target wake-up sensitivity of a device corresponding to the target age type includes:

[0011] inputting the target age type into a first model so that the first model outputs a target wake-up sensitivity of the device corresponding to the target age type; or

[0012] The target age type is input into a second model so that the second model outputs a target adjustment value corresponding to the target age type, and the preset wake-up sensitivity is adjusted according to the target adjustment value to obtain the target wake-up sensitivity of the device corresponding to the target age type.

[0013] In an optional embodiment, the method further comprises:

[0014] Performing speech recognition on the speech signal to obtain a recognition result of the speech signal;

[0015] determining, based on the similarity, the target wake-up sensitivity, and the recognition result, a number of false wake-ups or unsuccessful wake-ups of the device corresponding to the target age type;

[0016] The first model or the second model is updated according to the number of false awakenings or the number of unsuccessful awakenings.

[0017] In an optional embodiment, updating the first model or the second model according to the number of false awakenings or the number of unsuccessful awakenings includes:

[0018] When the number of false awakenings satisfies a first preset relationship, updating the first model or the second model according to the number of false awakenings; or,

[0019] When the number of unsuccessful awakenings satisfies a second preset relationship, the first model or the second model is updated according to the number of unsuccessful awakenings.

[0020] In an optional embodiment, determining the number of false awakenings or unsuccessful awakenings of the device corresponding to the target age type based on the similarity, the target awakening sensitivity, and the recognition result includes:

[0021] When the similarity is greater than the target wake-up sensitivity, and the recognition result is that the voice signal does not include the target wake-up word, updating the number of false wake-ups of the device corresponding to the target age type;

[0022] When the similarity is less than or equal to the target wake-up sensitivity, and the recognition result is that the voice signal includes the target wake-up word, the number of unsuccessful wake-up times of the device corresponding to the target age type is updated.

[0023] In an optional embodiment, after acquiring the user's voice signal, determining the target age type corresponding to the user and determining the similarity between the voice signal and the target wake-up word includes:

[0024] After simultaneously acquiring voice signals of multiple users, determining a target age type for each of the users, and determining a similarity between each of the voice signals and a target wake-up word, to obtain a plurality of similarities;

[0025] The determining, according to the target age type, a target wake-up sensitivity of a device corresponding to the target age type includes:

[0026] Selecting a highest similarity from the plurality of similarities, and determining a target age type corresponding to the highest similarity;

[0027] According to the target age type corresponding to the highest similarity, a target wake-up sensitivity of a device corresponding to the target age type is determined.

[0028] In an optional implementation, determining, based on the target age type, a target wake-up sensitivity of a device corresponding to the target age type includes:

[0029] When an operation signal is received, an adjustment interface for wake-up sensitivity is displayed; wherein the operation signal is used to trigger the display of the adjustment interface for wake-up sensitivity, the adjustment interface including at least one target age type and a sliding adjustment bar corresponding to the at least one target age type;

[0030] When an adjustment signal corresponding to any of the sliding adjustment bars is acquired, the target wake-up sensitivity of the device corresponding to the target age type is determined according to the adjustment position of the sliding adjustment bar.

[0031] In an optional embodiment, determining the wake-up strategy of the device according to the similarity and the target wake-up sensitivity to control the device to perform an operation corresponding to the wake-up strategy includes:

[0032] When the similarity is greater than the target wake-up sensitivity, determining the wake-up strategy of the device to be wake-up, so as to control the device to wake up;

[0033] When the similarity is less than or equal to the target wake-up sensitivity, the wake-up strategy of the device is determined to be sleep, so as to control the device to sleep.

[0034] In a second aspect, an embodiment of the present invention provides a voice wake-up device for a device, including:

[0035] A first determination module is configured to, after acquiring a user's voice signal, determine a target age type of the user and determine a similarity between the voice signal and a target wake-up word;

[0036] a second determining module, configured to determine, according to the target age type, a target wake-up sensitivity of a device corresponding to the target age type;

[0037] The wake-up control module is configured to determine a wake-up strategy for the device according to the similarity and the target wake-up sensitivity, so as to control the device to perform an operation corresponding to the wake-up strategy.

[0038] In a third aspect, an embodiment of the present invention provides an electronic device, including: a processor and a memory, wherein the processor is configured to execute a voice wake-up program of the device stored in the memory to implement the voice wake-up method of the device as described above.

[0039] In a fourth aspect, an embodiment of the present invention provides a storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the voice wake-up method of the device as described above.

[0040] An embodiment of the present invention provides a method for voice wake-up of a device. After acquiring a user's voice signal, the method determines the user's target age type and the similarity between the voice signal and the target wake-up word. Based on the target age type, the method determines the target wake-up sensitivity of the device corresponding to the target age type. Based on the similarity and the target wake-up sensitivity, the method determines the device's wake-up strategy to control the device to perform operations corresponding to the wake-up strategy. When performing voice wake-up, the present invention analyzes the user's age and adopts different sensitivities based on different age groups to make corresponding wake-up decisions, thereby improving the accuracy of the user's voice wake-up device and enhancing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic diagram of a flow chart of a voice wake-up method for a device provided in an embodiment of the present invention;

[0042] Figure 2 A flowchart of a voice wake-up method for another device provided by an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the structure of a voice wake-up device of a device provided by an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0045] In the above attached figures:

[0046] 31. First determination module; 32. Second determination module; 33. Wake-up control module;

[0047] 400. Electronic device; 401. Processor; 402. Memory; 4021. Operating system; 4022. Application; 403. User interface; 404. Network interface; 405. Bus system. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0049] To facilitate understanding of the embodiments of the present invention, specific embodiments will be further explained below with reference to the accompanying drawings. The embodiments do not limit the embodiments of the present invention.

[0050] refer to Figure 1 , Figure 1 A flow chart of a method for waking up a device by voice provided by an embodiment of the present invention. A method for waking up a device by voice provided by an embodiment of the present invention includes:

[0051] S11: After acquiring the user's voice signal, determine the target age type of the user and determine the similarity between the voice signal and the target wake-up word.

[0052] Among them, the device can be a smart refrigerator, a smart washing machine, a smart air conditioner, etc. In this embodiment, the form of the device is not specifically limited, and it can be selected according to actual needs. Among them, the device can be voice-awakened through the terminal (the terminal can be a mobile phone, etc.), or the device can be directly voice-awakened by itself. When voice wake-up is performed through the terminal, the terminal is configured with a voice wake-up function; when voice wake-up is performed through the device, the device is configured with a voice wake-up function. The voice signal can be collected and obtained by the device or by the terminal. When the user's voice signal is collected through the device, a voice collection module and a voice assistant are provided in the device, and the user's voice signal is collected through the voice assistant and the voice collection module; when the user's voice signal is collected through the terminal, the device voice collection module and the voice assistant in the terminal are used to collect the user's voice signal.

[0053] After acquiring the user's voice signal, the user's voiceprint features are extracted and input into the voiceprint recognition model to output the user's age category corresponding to the user's voiceprint features. Age categories include childhood, youth, middle-aged, and elderly. Different age categories correspond to different age groups, and the correspondence between age categories and age groups can be set according to actual needs.

[0054] In this embodiment, the similarity between the voice signal and the target wake-up word is used to indicate whether the voice signal matches the target wake-up word, wherein the user's voice signal can be converted into corresponding text, and the similarity between the voice signal and the target wake-up word can be determined based on the minimum edit distance algorithm and the cosine algorithm based on the space vector. The specific method for determining the similarity is not specifically limited in this embodiment and can be selected according to actual needs. In this embodiment, the target wake-up word is a word used to wake up the device. The target wake-up word can be set according to actual needs. The target wake-up word for waking up the device can be one or more, and the number of target wake-up words can be set according to actual needs. Different devices in the home have different target wake-up words to ensure the accuracy of waking up the device.

[0055] The above method is for determining the target age type and similarity of a user after acquiring only one user's voice signal. Of course, when the user wakes up the device, they may be in a noisy environment, so the collected voice signals may be multiple. When there are multiple voice signals, step S11 specifically includes:

[0056] After simultaneously acquiring voice signals of multiple users, the target age type of each user is determined, and the similarity between each voice signal and the target wake-up word is determined to obtain multiple similarities.

[0057] Among them, the method for determining the target age type of each user and the similarity between each voice signal and the target wake-up word is consistent with the above, and will not be repeated here in this embodiment.

[0058] S12: Determine, according to the target age type, a target wake-up sensitivity of a device corresponding to the target age type.

[0059] In this embodiment, each target age type corresponds to a target awakening sensitivity, that is, childhood, youth, middle-aged, and elderly age groups each correspond to a awakening sensitivity. In one example, the target awakening sensitivity can be determined as follows:

[0060] inputting the target age type into a first model so that the first model outputs a target wake-up sensitivity of the device corresponding to the target age type; or

[0061] The target age type is input into a second model so that the second model outputs a target adjustment value corresponding to the target age type, and the preset wake-up sensitivity is adjusted according to the target adjustment value to obtain the target wake-up sensitivity of the device corresponding to the target age type.

[0062] In this embodiment, the first model is a model based on age type and wake-up sensitivity. This model can be trained using historical wake-up data corresponding to age type to continuously adjust the wake-up sensitivity corresponding to age type, thereby further improving the accuracy of user device wake-up and enhancing the user experience. The first model can be a deep learning network model, etc., and the specific model can be selected based on actual needs.

[0063] The second model is a model that combines age categories and wake-up sensitivity adjustment values. This model can be trained using historical wake-up data corresponding to age categories to continuously modify the adjustment values ​​corresponding to age categories. The preset wake-up sensitivity is then adjusted based on the adjustment values, further improving the accuracy of user device wake-up and enhancing the user experience. The second model can be a deep learning network model, for example, and the specific model can be selected based on actual needs. In this embodiment, the preset sensitivity can be set based on actual needs and is not specifically limited in this embodiment.

[0064] In another example, the target wake-up sensitivity may also be determined as follows:

[0065] When an operation signal is received, an adjustment interface for wake-up sensitivity is displayed; wherein the operation signal is used to trigger the display of the adjustment interface for wake-up sensitivity, the adjustment interface including at least one target age type and a sliding adjustment bar corresponding to the at least one target age type;

[0066] When an adjustment signal corresponding to any of the sliding adjustment bars is acquired, the target wake-up sensitivity of the device corresponding to the target age type is determined according to the adjustment position of the sliding adjustment bar.

[0067] Among them, the wake-up sensitivity can be adjusted through the adjustment interface. For example, when voice wake-up is performed directly through the device, a display module for displaying the interface can be provided on the device, and a plurality of controls are provided in the display interface, and each control corresponds to a corresponding operation function. When the user needs to adjust the wake-up sensitivity, by touching the corresponding control in the display interface (for example: sensitivity adjustment control), the adjustment interface for displaying the wake-up sensitivity is triggered. The adjustment interface may include childhood, youth, middle-aged and elderly age types, and each age type corresponds to an adjustment bar. At the same time, each age type position corresponds to an age range, that is, an age range belonging to childhood, an age range belonging to youth, an age range belonging to middle-aged and an age range belonging to the elderly, so that the user can select the age type according to the age range, and adjust the wake-up sensitivity by sliding the adjustment bar corresponding to the age type. Similarly, when the device is voice-wake-up performed through the terminal, the wake-up sensitivity can also be adjusted by the same method as above.

[0068] In the above, the target wake-up sensitivity of the device is determined based on the voice signal of one user. When multiple voice signals are obtained, the target wake-up sensitivity of the device can be determined by the following method, as follows:

[0069] Selecting a highest similarity from the plurality of similarities, and determining a target age type corresponding to the highest similarity;

[0070] According to the target age type corresponding to the highest similarity, a target wake-up sensitivity of a device corresponding to the target age type is determined.

[0071] The multiple similarities are determined after simultaneously acquiring voice signals of multiple users. The specific method for determining the target wakefulness of the device corresponding to the target age type is the same as described above and will not be described in detail in this embodiment.

[0072] S13: Determine a wake-up strategy for the device according to the similarity and the target wake-up sensitivity, so as to control the device to perform an operation corresponding to the wake-up strategy.

[0073] In this embodiment, the device can be awakened or put to sleep by comparing the similarity and the target awakening degree. In this embodiment, step S13 specifically includes:

[0074] When the similarity is greater than the target wake-up sensitivity, determining the wake-up strategy of the device to be wake-up, so as to control the device to wake up;

[0075] When the similarity is less than or equal to the target wake-up sensitivity, the wake-up strategy of the device is determined to be sleep, so as to control the device to sleep.

[0076] Among them, if the similarity is greater than the target wake-up sensitivity, it indicates that the user's voice signal matches the target wake-up word successfully and can successfully wake up the device; if the similarity is less than or equal to the target wake-up sensitivity, it indicates that the user's voice signal fails to match the target wake-up word and fails to wake up the device, so as to control the device to continue to sleep.

[0077] In this embodiment, it should be noted that after successfully waking up the device, if no user voice signal is received within a preset time, the device is controlled to sleep to reduce power consumption. The preset time can be set according to actual needs, and this embodiment does not specifically limit the specific value of the preset time.

[0078] This embodiment provides a device voice wake-up method. After acquiring a user's voice signal, the method determines the user's target age type and the similarity between the voice signal and the target wake-up word. Based on the target age type, the method determines the target wake-up sensitivity of the device corresponding to the target age type. Based on the similarity and the target wake-up sensitivity, the method determines the device's wake-up strategy to control the device to perform operations corresponding to the wake-up strategy. When performing voice wake-up, the present invention analyzes the user's age and adopts different sensitivities based on different age groups to make corresponding wake-up decisions, thereby improving the accuracy of the user's voice wake-up device and enhancing the user experience.

[0079] refer to Figure 2 , Figure 2 This is a flow chart of another method for waking up a device by voice provided by an embodiment of the present invention. The method for waking up a device by voice provided by this embodiment includes:

[0080] S21: After acquiring the user's voice signal, determine the target age type of the user and determine the similarity between the voice signal and the target wake-up word.

[0081] In this embodiment, step S21 is similar to the above-mentioned step S11 and will not be described in detail in this embodiment.

[0082] S22: Determine, according to the target age type, a target wake-up sensitivity of a device corresponding to the target age type.

[0083] In this embodiment, step S22 is similar to the above-mentioned step S12, and will not be described in detail in this embodiment.

[0084] S23: Determine a wake-up strategy for the device according to the similarity and the target wake-up sensitivity, so as to control the device to perform an operation corresponding to the wake-up strategy.

[0085] In this embodiment, step S23 is similar to the above-mentioned step S13 and will not be described in detail in this embodiment.

[0086] S24: Perform speech recognition on the speech signal to obtain a recognition result of the speech signal.

[0087] Among them, step S24 can be executed between step S21 and step S22, between step S22 and step S23, or after step S23. Of course, it can also be executed after obtaining the user's voice signal in step S21. That is, after obtaining the recognition result of the voice signal, the user's target age type and the similarity between the voice signal and the target wake-up word can be determined. After determining the user's target age type and the similarity between the voice signal and the target wake-up word, the recognition result of the voice signal can be obtained. The specific execution order can be set according to actual needs. In this embodiment, there is no specific limitation on the specific execution order.

[0088] The speech recognition result may be a result of the speech signal including or excluding the target wake-up word. The speech signal recognition algorithm may employ a hidden Markov model algorithm or a vector quantization algorithm, etc. The algorithm may be selected based on actual needs and is not specifically limited in this embodiment.

[0089] S25: Determine the number of false awakenings or unsuccessful awakenings of the device corresponding to the target age type according to the similarity, the target awakening sensitivity and the recognition result.

[0090] In this embodiment, a false awakening occurs when the user intended to awaken the device but the device successfully awakens. This occurs when the wakeup strategy is set to wake, but the recognition result indicates that the target wakeup word is not included in the speech signal. An unsuccessful awakening occurs when the user intended to awaken the device but the device failed to awaken. This occurs when the wakeup strategy is set to sleep, but the recognition result indicates that the speech signal includes the target wakeup word. A false awakening indicates that the device's wakeup sensitivity may be low and should be increased accordingly. An unsuccessful awakening indicates that the device's wakeup sensitivity may be high and should be decreased accordingly.

[0091] In this embodiment, step S25 specifically includes:

[0092] When the similarity is greater than the target wake-up sensitivity, and the recognition result is that the voice signal does not include the target wake-up word, updating the number of false wake-ups of the device corresponding to the target age type;

[0093] When the similarity is less than or equal to the target wake-up sensitivity, and the recognition result is that the voice signal includes the target wake-up word, the number of unsuccessful wake-up times of the device corresponding to the target age type is updated.

[0094] In this embodiment, if the similarity is greater than the target wake-up sensitivity, it indicates that the wake-up strategy is wake-up; if the similarity is less than or equal to the target wake-up sensitivity, it indicates that the wake-up strategy is sleep.

[0095] S26: Update the first model or the second model according to the number of false awakenings or the number of unsuccessful awakenings.

[0096] In this embodiment, updating the first model refers to updating the wakeup sensitivity corresponding to the age type, and updating the second model refers to updating the adjustment value corresponding to the age type. The increase or decrease in wakeup sensitivity needs to be set based on the number of false wakeups and unsuccessful wakeups to prevent inaccurate wakeup sensitivity adjustment, which reduces the user experience.

[0097] In this embodiment, step S26 specifically includes:

[0098] When the number of false awakenings satisfies a first preset relationship, updating the first model or the second model according to the number of false awakenings; or,

[0099] When the number of unsuccessful awakenings satisfies a second preset relationship, the first model or the second model is updated according to the number of unsuccessful awakenings.

[0100] In this embodiment, the first preset relationship is that the number of false awakenings is greater than or equal to the first preset threshold, and the second preset relationship is that the number of unsuccessful awakenings is greater than or equal to the second preset threshold. The first preset threshold and the second preset threshold can be set according to actual needs, and this embodiment does not make specific limitations here.

[0101] In this embodiment, after the first model or the second model is updated, the next time the user's voice signal is acquired, the target wake-up sensitivity of the device corresponding to the target age type is determined based on the updated first model or the second model, thereby controlling the wake-up of the device.

[0102] This embodiment provides a device voice wake-up method. After acquiring a user's voice signal, the method determines the user's target age type and the similarity between the voice signal and the target wake-up word. Based on the target age type, the method determines the target wake-up sensitivity of the device corresponding to the target age type. Based on the similarity and the target wake-up sensitivity, the method determines the device's wake-up strategy to control the device to perform operations corresponding to the wake-up strategy. When performing voice wake-up, the present invention analyzes the user's age and adopts different sensitivities based on different age groups to make corresponding wake-up decisions, thereby improving the accuracy of the user's voice wake-up device and enhancing the user experience.

[0103] refer to Figure 3 , Figure 3A schematic structural diagram of a voice wake-up device of a device provided in an embodiment of the present invention. The voice wake-up device of a device provided in this embodiment includes a first determination module 31, a second determination module 32 and a wake-up control module 33, wherein the first determination module 31 is used to determine the target age type of the user and the similarity between the voice signal and the target wake-up word after acquiring the user's voice signal. The second determination module 32 is used to determine the target wake-up sensitivity of the device corresponding to the target age type based on the target age type. The wake-up control module 33 is used to determine the wake-up strategy of the device based on the similarity and the target wake-up sensitivity, so as to control the device to perform operations corresponding to the wake-up strategy.

[0104] In this embodiment, the second determining module 32 is further configured to input the target age type into the first model, so that the first model outputs a target wake-up sensitivity of the device corresponding to the target age type; or

[0105] The target age type is input into a second model so that the second model outputs a target adjustment value corresponding to the target age type, and the preset wake-up sensitivity is adjusted according to the target adjustment value to obtain the target wake-up sensitivity of the device corresponding to the target age type.

[0106] The voice wake-up device of a device provided in this embodiment further includes an update module; wherein the update module is configured to:

[0107] Performing speech recognition on the speech signal to obtain a recognition result of the speech signal;

[0108] determining, based on the similarity, the target wake-up sensitivity, and the recognition result, a number of false wake-ups or unsuccessful wake-ups of the device corresponding to the target age type;

[0109] The first model or the second model is updated according to the number of false awakenings or the number of unsuccessful awakenings.

[0110] In this embodiment, the update module is further used to:

[0111] When the number of false awakenings satisfies a first preset relationship, updating the first model or the second model according to the number of false awakenings; or,

[0112] When the number of unsuccessful awakenings satisfies a second preset relationship, the first model or the second model is updated according to the number of unsuccessful awakenings.

[0113] In this embodiment, the update module is further used to:

[0114] When the similarity is greater than the target wake-up sensitivity, and the recognition result is that the voice signal does not include the target wake-up word, updating the number of false wake-ups of the device corresponding to the target age type;

[0115] When the similarity is less than or equal to the target wake-up sensitivity, and the recognition result is that the voice signal includes the target wake-up word, the number of unsuccessful wake-up times of the device corresponding to the target age type is updated.

[0116] In this embodiment, the first determination module 31 is further used to determine the target age type of each user after simultaneously acquiring the voice signals of multiple users, and determine the similarity between each voice signal and the target wake-up word to obtain multiple similarities.

[0117] In this embodiment, the second determining module 32 is further configured to select the highest similarity from the plurality of similarities and determine the target age type corresponding to the highest similarity;

[0118] According to the target age type corresponding to the highest similarity, a target wake-up sensitivity of a device corresponding to the target age type is determined.

[0119] In this embodiment, the second determining module 32 is further configured to display an adjustment interface for wake-up sensitivity when an operation signal is received; wherein the operation signal is configured to trigger the display of the adjustment interface for wake-up sensitivity, and the adjustment interface includes at least one target age type and a sliding adjustment bar corresponding to the at least one target age type;

[0120] When an adjustment signal corresponding to any of the sliding adjustment bars is acquired, the target wake-up sensitivity of the device corresponding to the target age type is determined according to the adjustment position of the sliding adjustment bar.

[0121] In this embodiment, the wake-up control module 33 is further configured to determine that the wake-up strategy of the device is wake-up when the similarity is greater than the target wake-up sensitivity, so as to control the device to wake up;

[0122] When the similarity is less than or equal to the target wake-up sensitivity, the wake-up strategy of the device is determined to be sleep, so as to control the device to sleep.

[0123] The present embodiment provides a voice wake-up device for a device, comprising a first determination module 31, a second determination module 32 and a wake-up control module 33, wherein the first determination module 31 is used to determine the target age type of the user and the similarity between the voice signal and the target wake-up word after acquiring the user's voice signal. The second determination module 32 is used to determine the target wake-up sensitivity of the device corresponding to the target age type based on the target age type. The wake-up control module 33 is used to determine the wake-up strategy of the device based on the similarity and the target wake-up sensitivity, so as to control the device to perform operations corresponding to the wake-up strategy. When performing voice wake-up, the present invention analyzes the age of the user and adopts different sensitivities according to different age groups to make corresponding wake-up decisions, thereby improving the accuracy of the user's voice wake-up device and improving the user experience.

[0124] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 The electronic device 400 shown can be a terminal or a smart home. The electronic device 400 includes: at least one processor 401, a memory 402, at least one network interface 404 and other user interfaces 403. The various components in the electronic device 400 are coupled together through a bus system 405. It can be understood that the bus system 405 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 405 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 4 Various buses are labeled as bus system 405 .

[0125] The user interface 403 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touchpad, or a touch screen).

[0126] It is understood that the memory 402 in the embodiment of the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 402 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0127] In some embodiments, the memory 402 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 4021 and application programs 4022 .

[0128] The operating system 4021 includes various system programs, such as a framework layer, a core library layer, and a driver layer, for implementing various basic services and handling hardware-based tasks. Application programs 4022 include various application programs, such as a media player and a browser, for implementing various application services. Programs implementing the methods of the embodiments of the present invention may be included in application programs 4022.

[0129] In an embodiment of the present invention, by calling the program or instructions stored in the memory 402, specifically, the program or instructions stored in the application 4022, the processor 401 is used to execute the method steps provided by each method embodiment, for example, including: after obtaining the user's voice signal, determining the target age type of the user and determining the similarity between the voice signal and the target wake-up word; determining the target wake-up sensitivity of the device corresponding to the target age type according to the target age type; determining the wake-up strategy of the device according to the similarity and the target wake-up sensitivity, so as to control the device to perform operations corresponding to the wake-up strategy.

[0130] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 401. Processor 401 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in processor 401 or by software instructions. The above processor 401 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software units in the decoding processor. The software units can be located in storage media well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 402 , and the processor 401 reads the information in the memory 402 and completes the steps of the above method in combination with its hardware.

[0131] It is understood that the embodiments described herein may be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or a combination thereof.

[0132] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0133] The electronic device provided in this embodiment may be Figure 4 The electronic device shown in FIG. 1 can perform the following operations: Figure 1-2 All steps of the voice wake-up method of the device in the Figure 1-2 For technical effects of the voice wake-up method of the device shown, please refer to Figure 1-2 For the sake of brevity, the relevant description will not be repeated here.

[0134] An embodiment of the present invention further provides a storage medium (computer-readable storage medium). The storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; and the memory may also include a combination of the aforementioned types of memory.

[0135] When one or more programs in the storage medium can be executed by one or more processors, the voice wake-up method of the device is implemented on the voice wake-up device side of the device.

[0136] The processor is used to execute the voice wake-up method program of the device stored in the memory to implement the following steps of the voice wake-up method of the device executed on the voice wake-up device side of the device: after obtaining the user's voice signal, determining the target age type of the user and determining the similarity between the voice signal and the target wake-up word; determining the target wake-up sensitivity of the device corresponding to the target age type based on the target age type; determining the wake-up strategy of the device based on the similarity and the target wake-up sensitivity to control the device to perform an operation corresponding to the wake-up strategy.

[0137] Professionals should also be further aware that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0138] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0139] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A voice wake-up method for a device, characterized in that: include: After acquiring the user's voice signal, determining the target age type of the user and determining the similarity between the voice signal and the target wake-up word; determining, according to the target age type, a target wakeup sensitivity of a device corresponding to the target age type, wherein the target age type and the target wakeup sensitivity have a one-to-one correspondence; A wake-up strategy for the device is determined according to the similarity and the target wake-up sensitivity, so as to control the device to perform an operation corresponding to the wake-up strategy.

2. The method according to claim 1, characterized in that The determining, according to the target age type, a target wake-up sensitivity of a device corresponding to the target age type includes: inputting the target age type into a first model so that the first model outputs a target wake-up sensitivity of the device corresponding to the target age type; or The target age type is input into a second model so that the second model outputs a target adjustment value corresponding to the target age type, and the preset wake-up sensitivity is adjusted according to the target adjustment value to obtain the target wake-up sensitivity of the device corresponding to the target age type.

3. The method according to claim 2, characterized in that The method further comprises: Performing speech recognition on the speech signal to obtain a recognition result of the speech signal; determining, based on the similarity, the target wake-up sensitivity, and the recognition result, a number of false wake-ups or unsuccessful wake-ups of the device corresponding to the target age type; The first model or the second model is updated according to the number of false awakenings or the number of unsuccessful awakenings.

4. The method according to claim 3, characterized in that The updating of the first model or the second model according to the number of false awakenings or the number of unsuccessful awakenings includes: When the number of false awakenings satisfies a first preset relationship, updating the first model or the second model according to the number of false awakenings; or, When the number of unsuccessful awakenings satisfies a second preset relationship, the first model or the second model is updated according to the number of unsuccessful awakenings.

5. The method according to claim 3 or 4, characterized in that The determining, based on the similarity, the target wake-up sensitivity, and the recognition result, the number of false wake-ups or unsuccessful wake-ups of the device corresponding to the target age type includes: When the similarity is greater than the target wake-up sensitivity, and the recognition result is that the voice signal does not include the target wake-up word, updating the number of false wake-ups of the device corresponding to the target age type; When the similarity is less than or equal to the target wake-up sensitivity, and the recognition result is that the voice signal includes the target wake-up word, the number of unsuccessful wake-up times of the device corresponding to the target age type is updated.

6. The method according to claim 1, characterized in that After acquiring the user's voice signal, determining the target age type corresponding to the user and determining the similarity between the voice signal and the target wake-up word includes: After simultaneously acquiring voice signals of multiple users, determining a target age type for each of the users, and determining a similarity between each of the voice signals and a target wake-up word, to obtain a plurality of similarities; The determining, according to the target age type, a target wake-up sensitivity of a device corresponding to the target age type includes: Selecting a highest similarity from the plurality of similarities, and determining a target age type corresponding to the highest similarity; According to the target age type corresponding to the highest similarity, a target wake-up sensitivity of a device corresponding to the target age type is determined.

7. The method according to claim 1 or 6, characterized in that The determining, according to the target age type, a target wake-up sensitivity of a device corresponding to the target age type includes: When an operation signal is received, an adjustment interface for wake-up sensitivity is displayed; wherein the operation signal is used to trigger the display of the adjustment interface for wake-up sensitivity, the adjustment interface including at least one target age type and a sliding adjustment bar corresponding to the at least one target age type; When an adjustment signal corresponding to any of the sliding adjustment bars is acquired, the target wake-up sensitivity of the device corresponding to the target age type is determined according to the adjustment position of the sliding adjustment bar.

8. The method according to claim 1, characterized in that The determining the wake-up strategy of the device according to the similarity and the target wake-up sensitivity to control the device to perform an operation corresponding to the wake-up strategy includes: When the similarity is greater than the target wake-up sensitivity, determining the wake-up strategy of the device to be wake-up, so as to control the device to wake up; When the similarity is less than or equal to the target wake-up sensitivity, the wake-up strategy of the device is determined to be sleep, so as to control the device to sleep.

9. A voice wake-up device for a device, characterized in that: include: A first determination module is configured to, after acquiring a user's voice signal, determine a target age type of the user and determine a similarity between the voice signal and a target wake-up word; a second determining module, configured to determine, based on the target age type, a target wake-up sensitivity of a device corresponding to the target age type, wherein the target age type and the target wake-up sensitivity have a one-to-one correspondence; The wake-up control module is configured to determine a wake-up strategy for the device according to the similarity and the target wake-up sensitivity, so as to control the device to perform an operation corresponding to the wake-up strategy.

10. An electronic device, characterized in that: include: A processor and a memory, wherein the processor is configured to execute a voice wake-up program of a device stored in the memory to implement the voice wake-up method of the device according to any one of claims 1 to 8.

11. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the voice wake-up method of the device according to any one of claims 1 to 8.

Images