Server, terminal device, voice wake-up method and medium

Abstract

The present disclosure relates to a server, a terminal device, a voice wake-up method and a medium. The server stores a preset instruction weight library, which includes a plurality of preset instructions and a weight corresponding to each preset instruction. The server includes a first controller configured to receive a request instruction sent by a terminal device, determine a target instruction corresponding to the request instruction from the plurality of preset instructions, and if the weight corresponding to the target instruction is greater than or equal to a preset threshold, determine that the target instruction is an instruction for waking up a voice assistant of the terminal device, and send a wake-up instruction to the terminal device, wherein the wake-up instruction is used to instruct the voice assistant of the terminal device to wake up. In the above technical solution, the problem that the voice interaction between the user and the terminal device is not convenient and fast in the prior art is solved, and the user experience is improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of speech processing, and in particular to a server, a terminal device, a speech wake-up method and a medium. BACKGROUND

[0002] With the development of artificial intelligence, it has been very common for users to use terminal devices for speech interaction functions. In the prior art, speech interaction functions between users and terminal devices are usually realized through voice assistants. Specifically, in the speech interaction process between users and terminal devices, the voice assistant of the terminal device needs to be woken up by a wake-up keyword first, i.e., the terminal device is woken up. After determining that the terminal device is woken up, the request instruction input by the user is received and executed, so as to realize the speech interaction function between the user and the terminal device.

[0003] However, in the prior art, the terminal device needs to be woken up by the user through a wake-up keyword before receiving each request instruction input by the user, which causes the speech interaction function between the user and the terminal device to be inconvenient and slow, and affects the user experience. SUMMARY

[0004] To solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a server, a terminal device, a speech wake-up method and a medium. The first controller of the server determines a target instruction corresponding to a request instruction sent by a terminal device in a preset instruction weight library stored on the server. When it is determined that the weight corresponding to the target instruction is greater than or equal to a preset threshold, the target instruction is determined to be an instruction for waking up the voice assistant of the terminal device. The wake-up instruction for waking up the voice assistant of the terminal device is sent to the terminal device, so as to wake up the voice assistant of the terminal device. Thus, when the user inputs the next request instruction through the user voice, the user does not need to wake up the voice assistant of the terminal device according to the wake-up keyword carried by the wake-up request. This solves the problem that the speech interaction between the user and the terminal device is not convenient and fast in the prior art, and improves the user experience.

[0005] In a first aspect, the present disclosure provides a server, which stores a preset instruction weight library. The preset instruction weight library includes a plurality of preset instructions and a weight corresponding to each preset instruction. The server includes:

[0006] A first controller configured to:

[0007] receive a request instruction sent by a terminal device, and determine a target instruction corresponding to the request instruction from the plurality of preset instructions;

[0008] If the weight value corresponding to the target instruction is greater than or equal to a preset threshold, the target instruction is determined as an instruction for waking up a voice assistant of the terminal device, and a wake-up instruction is sent to the terminal device, where the wake-up instruction is used to instruct to wake up the voice assistant of the terminal device.

[0009] As an optional implementation of the embodiment of the present disclosure, the first controller is further configured to:

[0010] obtain a plurality of historical request instructions input by a user respectively corresponding to preset instructions;

[0011] determine a plurality of preset instruction sets as a plurality of first preset instruction sets based on a preset time interval;

[0012] delete a target non-voice preset instruction in each of the first preset instruction sets to obtain a plurality of second preset instruction sets, where a first preset instruction in each of the second preset instruction sets is obtained according to user voice, and the target non-voice preset instruction is arranged before the first preset instruction in each of the first preset instruction sets;

[0013] delete a non-voice preset instruction from each of the second preset instruction sets and perform splitting processing to obtain a plurality of third preset instruction sets;

[0014] determine a target preset instruction set in combination with the third preset instruction sets, where the target preset instruction set includes a plurality of preset instructions obtained according to user voice;

[0015] determine a weight value of a preset instruction corresponding to each request operation based on an occurrence frequency of the preset instruction and a weight factor of the preset instruction in the target preset instruction set to obtain a weight value of each preset instruction;

[0016] determine the preset instruction weight library according to the plurality of preset instructions and the weight value of each preset instruction.

[0017] As an optional implementation of the embodiment of the present disclosure, the first controller is specifically configured to:

[0018] for a preset instruction corresponding to each request operation in the target preset instruction set, obtain a first total number of times that the preset instruction exists in the target preset instruction set, a second total number of times that the preset instruction exists in preset instructions respectively corresponding to a plurality of historical request instructions, and calculate a quotient value of the first total number and the second total number to obtain the occurrence frequency of the preset instruction;

[0019] acquire a first timestamp corresponding to each of the preset instructions, a second timestamp corresponding to a next preset instruction adjacent to the preset instruction, and determine a weight factor of the preset instruction according to the first timestamp, the second timestamp, a preset mapping table, and a first total number;

[0020] multiply the occurrence frequency and the weight factor to obtain a weight corresponding to the preset instruction.

[0021] As an optional implementation of an embodiment of the present disclosure, the first controller is specifically further configured to:

[0022] acquire a plurality of historical request instructions input by a user according to a preset condition;

[0023] determine a preset instruction corresponding to each of the historical request instructions;

[0024] The preset condition includes at least one of a preset time period and a preset scene.

[0025] As an optional implementation of an embodiment of the present disclosure, the first controller is specifically configured to:

[0026] determine a first instruction corresponding to a request instruction sent by a terminal device;

[0027] match a target instruction corresponding to the request instruction from a plurality of preset instructions according to the first instruction and user identification information corresponding to the first instruction, and determine a weight corresponding to the target instruction; or

[0028] match a target instruction corresponding to the request instruction from a plurality of preset instructions according to the first instruction, user identification information corresponding to the first instruction, and preset information corresponding to the first instruction, and determine a weight corresponding to the target instruction, wherein the preset information includes at least one of a preset time period and a preset scene.

[0029] As an optional implementation of an embodiment of the present disclosure, the first controller is further configured to:

[0030] if the weight corresponding to the target instruction is less than a preset threshold, determine that the target instruction is not an instruction of a wake-up-free voice assistant, and send a shutdown instruction to the terminal device, wherein the shutdown instruction is used to instruct to shut down a preset program of the terminal device.

[0031] In a second aspect, the present disclosure provides a terminal device, comprising:

[0032] a second controller configured to:

[0033] wake up the voice assistant of the terminal device in response to a wake-up request input by a user, wherein the wake-up request carries a wake-up keyword used to wake up the voice assistant of the terminal device;

[0034] after determining that the voice assistant of the terminal device is woken up, send a request instruction input by a user to a server in response to the request instruction;

[0035] wake up the voice assistant of the terminal device in response to a wake-up instruction sent by the server.

[0036] wake up the voice assistant of the terminal device in response to a wake-up instruction sent by the server.

[0037] In a third aspect, the present disclosure provides a voice wake-up method applied to a server, wherein the server stores a preset instruction weight library, and the preset instruction weight library includes: a plurality of preset instructions, and a weight corresponding to each preset instruction; and the method includes:

[0038] receive a request instruction sent by a terminal device, and determine a target instruction corresponding to the request instruction from the plurality of preset instructions;

[0039] if the weight corresponding to the target instruction is greater than or equal to a preset threshold, determine that the target instruction is an instruction for waking up a voice assistant of the terminal device, and send a wake-up instruction to the terminal device, wherein the wake-up instruction is used to instruct to wake up the voice assistant of the terminal device.

[0040] In a fourth aspect, the present disclosure provides a voice wake-up method applied to a terminal device, and the method includes:

[0041] wake up the voice assistant of the terminal device in response to a wake-up request input by a user, wherein the wake-up request carries a wake-up keyword used to wake up the voice assistant of the terminal device;

[0042] after determining that the voice assistant of the terminal device is woken up, send a request instruction input by a user to a server in response to the request instruction;

[0043] wake up the voice assistant of the terminal device in response to a wake-up instruction sent by the server.

[0044] In a fifth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the voice wake-up method according to the third aspect and the fourth aspect.

[0045] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0046] In the technical solution provided by this disclosure embodiment, a preset instruction weight library is stored on the server. The preset instruction weight library includes: multiple preset instructions and the weight corresponding to each preset instruction. The first controller of the server receives a request instruction sent by the terminal device, determines the target instruction corresponding to the request instruction from the multiple preset instructions, and if the weight corresponding to the target instruction is greater than or equal to a preset threshold, it determines that the target instruction is the instruction of the voice assistant of the wake-up-free terminal device, and sends a wake-up instruction to the terminal device. The wake-up instruction is used to instruct the voice assistant of the terminal device to be woken up. In the above technical solution, the server's first controller, in response to the request command sent by the terminal device, determines the target command corresponding to the request command in a preset command weight library stored on the server. Further, if the weight corresponding to the target command is greater than or equal to a preset threshold, the target command is determined to be a command for the voice assistant of the terminal device that does not require wake-up. A wake-up command is then sent to the terminal device to wake up the voice assistant, thereby waking it up. This allows the user to input the next request command via voice without needing to wake up the voice assistant based on the wake-up keyword carried in the wake-up request. This solves the problem of inconvenience and slowness in existing technologies when users interact with terminal devices via voice, improving the user experience. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0048] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A schematic diagram of the scenario architecture for the voice wake-up method provided in the embodiments of this disclosure;

[0050] Figure 2 This is a hardware configuration block diagram of a terminal device 200 according to one or more embodiments of the present disclosure;

[0051] Figure 3 This is a schematic diagram of the software configuration in a terminal device 200 according to one or more embodiments of the present disclosure;

[0052] Figure 4 This is a system framework diagram for voice wake-up according to one or more embodiments of the present disclosure;

[0053] Figure 5A flowchart of a voice wake-up method provided by an embodiment of the present disclosure is shown in FIG. 1.

[0054] Figure 6 An interaction diagram of a voice wake-up method provided by an embodiment of the present disclosure is shown in FIG. 2.

[0055] Figure 7 A flowchart of another voice wake-up method provided by an embodiment of the present disclosure is shown in FIG. 3.

[0056] Figure 8 A flowchart of still another voice wake-up method provided by an embodiment of the present disclosure is shown in FIG. 4.

[0057] Figure 9 A flowchart of yet another voice wake-up method provided by an embodiment of the present disclosure is shown in FIG. 5.

[0058] Figure 10 An interaction diagram of another voice wake-up method provided by an embodiment of the present disclosure is shown in FIG. 6.

[0059] Figure 11 A flowchart of yet another voice wake-up method provided by an embodiment of the present disclosure is shown in FIG. 7.

[0060] Figure 12 An interaction diagram of still another voice wake-up method provided by an embodiment of the present disclosure is shown in FIG. 8. DETAILED DESCRIPTION

[0061] In order to more clearly understand the above-mentioned purposes, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0062] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the description are only some of the embodiments of the present disclosure, not all the embodiments.

[0063] The terms "first" and "second" and the like in the present disclosure are used to distinguish different objects, not to describe a specific order of the objects. For example, the first processing result and the second processing result are used to distinguish different processing results, not to describe a specific order of the processing results.

[0064] At present, a user realizes a voice interaction function with a terminal device such as a mobile phone or a smart television through a voice assistant. Specifically, when the user and the terminal device perform a voice interaction process, the voice assistant of the terminal device needs to be woken up according to a wake-up keyword first, so as to wake up the terminal device. After the terminal device is woken up, the terminal device receives and executes a request instruction input by the user, thereby realizing the voice interaction function between the user and the terminal device.

[0065] Exemplary, Figure 1 The scene architecture schematic diagram of the voice wake-up method provided by the embodiments of the present disclosure, the scene architecture provided by the embodiments of the present disclosure includes: a server 100 and a terminal device 200. The terminal device 200 can have various implementation forms, for example, can be a smart speaker, a television, a mobile phone, a personal computer, a smart television, a display, an electronic whiteboard, an electronic desktop, etc. A user wakes up the terminal device 200 according to a wake-up keyword such as “XX genie”. When the voice assistant of the terminal device 200 receives the wake-up keyword “XX genie”, the voice assistant replies to the user “I'm here, master”, so as to determine that the voice assistant of the terminal device 200 is woken up at this time, and the terminal device 200 is also in a wake-up state at this time. The terminal device 200 receives and executes the request instruction input by the user voice, such as “I want to listen to music”, and plays music for the user. When the user needs to increase the volume of the music during the process of listening to the music, the user still needs to wake up the voice assistant of the terminal device 200 through the wake-up keyword “XX genie”, and the user inputs the request instruction “help me increase the volume” through the voice.

[0066] However, since the terminal device needs the user to wake up the terminal device through the wake-up keyword before receiving each request instruction input by the user, when the user and the terminal device perform voice interaction, there is a problem of inconvenience and slowness, which affects the user experience.

[0067] In order to solve the above problems, the embodiments of the present disclosure provide a voice wake-up method, applied to a server, the server stores a preset instruction weight value library, the preset instruction weight value library includes: a plurality of preset instructions, and a weight value corresponding to each preset instruction; a first controller of the server receives a request instruction sent by a terminal device, and determines a target instruction corresponding to the request instruction from the plurality of preset instructions; if the weight value corresponding to the target instruction is greater than or equal to a preset threshold value, it is determined that the target instruction is an instruction for waking up a voice assistant of the terminal device without the terminal device, and an wake-up instruction is sent to the terminal device, wherein the wake-up instruction is used to instruct to wake up the voice assistant of the terminal device. In the above technical solution, the first controller of the server determines the target instruction corresponding to the request instruction sent by the terminal device in the preset instruction weight value library stored on the server, and further determines that the target instruction is an instruction for waking up the voice assistant of the terminal device without the terminal device when the weight value corresponding to the target instruction is greater than or equal to the preset threshold value. The wake-up instruction for waking up the voice assistant of the terminal device is sent to the terminal device, so as to wake up the voice assistant of the terminal device, so that the user does not need to wake up the voice assistant of the terminal device according to the wake-up keyword carried by the wake-up request when inputting the next request instruction through the user voice, thereby solving the problem of inconvenience and slowness when the user and the terminal device perform voice interaction in the prior art, and improving the user experience.

[0068] In some embodiments, the terminal device 200 can communicate data with the server 100 when receiving the voice instruction of the user. The terminal device 200 can be allowed to be connected to the server 100 through a local area network (LAN) or a wireless local area network (WLAN).

[0069] The server 100 can be a server providing various services, such as a server providing support for audio data collected by the terminal device 200. The server can analyze and process received data such as audio, and feed back the processing result (such as endpoint information) to the terminal device. The server 100 can be one server cluster or multiple server clusters, and can include one or more types of servers.

[0070] The voice wake-up method provided by the embodiments of the present disclosure can be executed by the server 100, or by the terminal device 200, or by the server 100 and the terminal device 200 together, and the present disclosure does not limit this.

[0071] In some embodiments, the terminal device 200 can also be controlled by a control device. The control device can be a remote controller, and the communication between the remote controller and the terminal device 200 can include infrared protocol communication, Bluetooth protocol communication, wireless or other wired methods, etc., and the terminal device 200 can be controlled through the above communication methods. The user can input user instructions through the keys on the remote controller, voice input, control panel input, etc., to control the terminal device 200. For example, the user can input corresponding control instructions through the volume up and down keys, menu keys, power on and off keys, etc. on the remote controller, to realize the function of controlling the terminal device 200.

[0072] Figure 2 A hardware configuration block diagram of the terminal device 200 according to one or more embodiments of the present disclosure is shown in FIG. 2. As shown in FIG. 2, the terminal device 200 can include a processor 201, a memory 202, a communication interface 203, and a power supply 204. Figure 2The terminal device 200 includes at least one of a tuner and demodulator 210, a communicator 220, a detector 230, an external device interface 240, a second controller 250, a display 260, an audio output interface 270, a storage, a power supply, and a user interface (i.e., a user input interface) 280. The second controller 250 includes a central processing unit, a video processor, an audio processor, a graphic processor, a RAM, a ROM, and a first interface to an n-th interface for input / output. The display 260 can be at least one of a liquid crystal display, an OLED display, a touch display, and a projection display, and can also be a projection device and a projection screen. The tuner and demodulator 210 receives a broadcast television signal through a wired or wireless reception method, and demodulates audio and video signals and EPG data signals from a plurality of wireless or wired broadcast television signals. The communicator 220 is a component for communicating with an external device or a server according to various communication protocol types. For example, the communicator can include at least one of a Wifi module, a Bluetooth module, a wired Ethernet module, and other network communication protocol chips or near field communication protocol chips, and an infrared receiver. The terminal device 200 can establish transmission and reception of control signals and data signals with the external control device or the server 100 through the communicator 220. The detector 230 is used to collect signals of an external environment or interaction with the outside. The second controller 250 and the tuner and demodulator 210 can be located in different split devices, i.e., the tuner and demodulator 210 can also be in an external device of the main body device where the second controller 250 is located, such as an external set-top box. The user interface 280 can be used to receive control signals of a control device (e.g., an infrared remote controller).

[0073] In some embodiments, the second controller 250 controls the operation of the terminal device and responds to the user's operation through various software control programs stored in the storage. The second controller 250 controls the overall operation of the terminal device 200. The user can input a user command in a graphical user interface (GUI) displayed on the display 260, and the user input interface receives the user input command through the graphical user interface (GUI). Alternatively, the user can input a user command by inputting a specific sound or gesture, and the user input interface receives the user input command by recognizing the sound or gesture through a sensor.

[0074] In some embodiments, the "user interface" is a medium interface for interaction and information exchange between an application program or an operating system and a user, which realizes the conversion between the internal form of information and the form that the user can accept. The commonly used form of the user interface is a graphic user interface (GUI), which refers to a user interface related to computer operation displayed in a graphical manner. It can be an icon, a window, and a control interface element displayed on the display screen of an electronic device, wherein the control can include at least one of the visible interface elements such as an icon, a button, a menu, a tab, a text box, a dialog box, a status bar, a navigation bar, and a widget.

[0075] Figure 3 A schematic diagram of software configuration in a terminal device 200 according to one or more embodiments of the present disclosure is shown in FIG. 1, in which the system is divided into four layers from top to bottom, namely, an applications layer (referred to as "application layer" for short), an application framework layer (referred to as "framework layer" for short), an Android runtime and system library layer (referred to as "system runtime library layer" for short), and a kernel layer. Figure 3

[0076] In some embodiments, at least one application program is running in the application layer, which can be a window (Window) program, a system setting program, or a clock program provided by the operating system, or an application program developed by a third-party developer. In a specific implementation, the application program in the application layer includes but is not limited to the above examples.

[0077] In some embodiments, the system runtime library layer provides support for the upper layer, i.e., the framework layer. When the framework layer is used, the Android operating system runs the C / C++ library contained in the system runtime library layer to realize the functions of the framework layer.

[0078] In some embodiments, the kernel layer is a layer between hardware and software, which at least contains at least one of the following drivers: an audio driver, a display driver, a Bluetooth driver, a camera driver, a WIFI driver, a USB driver, an HDMI driver, a sensor driver (such as a fingerprint sensor, a temperature sensor, a pressure sensor, etc.), and a power supply driver, etc.

[0079] In some embodiments, the server 100 stores a preset instruction weight value library, which includes a plurality of preset instructions and a weight value corresponding to each preset instruction; and the server 100 includes:

[0080] The first controller is configured to:

[0081] ​receive a request instruction sent by a terminal device, and determine a target instruction corresponding to the request instruction from the plurality of preset instructions;

[0082] If the weight value corresponding to the target instruction is greater than or equal to a preset threshold value, it is determined that the target instruction is an instruction for waking up a voice assistant of the terminal device, and a wake-up instruction is sent to the terminal device, wherein the wake-up instruction is used to instruct to wake up the voice assistant of the terminal device.

[0083] In some embodiments, the first controller is further configured to:

[0084] Obtain a plurality of historical request instructions input by a user respectively corresponding to preset instructions;

[0085] Determine a plurality of preset instruction sets as a plurality of first preset instruction sets based on a preset time interval;

[0086] Delete a target non-voice preset instruction in each of the first preset instruction sets to obtain a plurality of second preset instruction sets, wherein a first preset instruction in each of the second preset instruction sets is obtained according to user voice, and the target non-voice preset instruction is arranged before the first preset instruction in each of the first preset instruction sets;

[0087] Delete a non-voice preset instruction from each of the second preset instruction sets of the plurality of second preset instruction sets and perform splitting processing to obtain a plurality of third preset instruction sets;

[0088] Determine a target preset instruction set in combination with the plurality of third preset instruction sets, wherein the plurality of preset instructions included in the target preset instruction set are obtained according to user voice;

[0089] Determine a weight value of a preset instruction corresponding to each request operation based on an occurrence frequency of the preset instruction corresponding to each request operation in the target preset instruction set and a weight factor to obtain a weight value of each preset instruction;

[0090] Determine the preset instruction weight library according to the plurality of preset instructions and the weight value of each preset instruction.

[0091] In some embodiments, the first controller is specifically configured to:

[0092] For the preset instruction corresponding to each request operation in the target preset instruction set, obtain a first total number of times that the preset instruction exists in the target preset instruction set, a second total number of times that the preset instruction exists in the preset instructions respectively corresponding to a plurality of historical request instructions, and calculate a quotient value of the first total number and the second total number to obtain the occurrence frequency of the preset instruction;

[0093] acquire a first timestamp corresponding to each of the preset instructions, a second timestamp corresponding to a next preset instruction adjacent to the preset instruction, and determine a weight factor of the preset instruction according to the first timestamp, the second timestamp, a preset mapping table, and a first total number;

[0094] multiply the occurrence frequency and the weight factor to obtain a weight corresponding to the preset instruction.

[0095] In some embodiments, the first controller is specifically further configured to:

[0096] acquire a plurality of historical request instructions input by a user according to a preset condition;

[0097] determine a preset instruction corresponding to each of the historical request instructions;

[0098] The preset condition includes at least one of a preset scene and a preset time period.

[0099] In some embodiments, the first controller is specifically configured to:

[0100] determine a first instruction corresponding to a request instruction sent by a terminal device;

[0101] match a target instruction corresponding to the request instruction from a plurality of preset instructions according to the first instruction and user identification information corresponding to the first instruction, and determine a weight corresponding to the target instruction; or

[0102] match a target instruction corresponding to the request instruction from a plurality of preset instructions according to the first instruction, user identification information corresponding to the first instruction, and preset information corresponding to the first instruction, and determine a weight corresponding to the target instruction, wherein the preset information includes at least one of a preset time period and a preset scene.

[0103] In some embodiments, the first controller is further configured to:

[0104] if the weight corresponding to the target instruction is less than the preset threshold, determine that the target instruction is not an instruction of a wake-up-free voice assistant, and send a shutdown instruction to the terminal device, wherein the shutdown instruction is used to instruct to shut down a preset program of the terminal device.

[0105] In summary, the present disclosure executes the above-mentioned voice wake-up method on the server, the server stores a preset instruction weight value library, the preset instruction weight value library includes a plurality of preset instructions and a weight value corresponding to each preset instruction, a first controller of the server receives a request instruction sent by a terminal device, determines a target instruction corresponding to the request instruction from the plurality of preset instructions, if the weight value corresponding to the target instruction is greater than or equal to a preset threshold, it is determined that the target instruction is an instruction for waking up a voice assistant of the terminal device, and a wake-up instruction is sent to the terminal device, wherein the wake-up instruction is used to instruct to wake up the voice assistant of the terminal device. In the above technical solution, the first controller of the server determines the target instruction corresponding to the request instruction sent by the terminal device in the preset instruction weight value library stored on the server, and further determines that the target instruction is an instruction for waking up the voice assistant of the terminal device when it is determined that the weight value corresponding to the target instruction is greater than or equal to the preset threshold, and sends the wake-up instruction for waking up the voice assistant of the terminal device to the terminal device, so as to wake up the voice assistant of the terminal device, so that the user does not need to wake up the voice assistant of the terminal device according to the wake-up keyword carried by the wake-up request when inputting the next request instruction in the form of user voice, solving the problem that the voice interaction between the user and the terminal device is not convenient and fast in the prior art, and improving the user experience.

[0106] Figure 4 For the system framework diagram for voice wake-up according to one or more embodiments of the present disclosure, as shown in Figure 4 The target instruction determination module 401 is used to receive a request instruction sent by a terminal device, and determine a target instruction corresponding to the request instruction from a plurality of preset instructions. Further, the wake-up module 402 is used to determine that the target instruction is an instruction for waking up a voice assistant of the terminal device if the weight value corresponding to the target instruction is greater than or equal to a preset threshold, and send a wake-up instruction to the terminal device, wherein the wake-up instruction is used to instruct to wake up the voice assistant of the terminal device. In the above technical solution, the first controller of the server determines the target instruction corresponding to the request instruction sent by the terminal device in the preset instruction weight value library stored on the server, and further determines that the target instruction is an instruction for waking up the voice assistant of the terminal device when it is determined that the weight value corresponding to the target instruction is greater than or equal to the preset threshold, and sends the wake-up instruction for waking up the voice assistant of the terminal device to the terminal device, so as to wake up the voice assistant of the terminal device, so that the user does not need to wake up the voice assistant of the terminal device according to the wake-up keyword carried by the wake-up request when inputting the next request instruction in the form of user voice, solving the problem that the voice interaction between the user and the terminal device is not convenient and fast in the prior art, and improving the user experience.

[0107] To further illustrate the present solution, the following will be in an exemplary manner combined with Figure 5 It can be understood that, Figure 5 The steps involved in the above embodiments can include more steps or fewer steps, and the order between the steps can be different, as long as the voice wake-up method provided in the embodiments of the present disclosure can be implemented, and the embodiments of the present disclosure are not limited.

[0108] Figure 5 A flowchart of a voice wake-up method provided by the embodiments of the present disclosure. Figure 6 An interaction diagram of a voice wake-up method provided by the embodiments of the present disclosure, the present embodiment is applied to the server side, and the server stores a preset instruction weight library, which includes a plurality of preset instructions and a weight corresponding to each preset instruction. As shown in the figure, Figure 5 The voice wake-up method specifically includes the following steps:

[0109] S51, receiving a request instruction sent by a terminal device, and determining a target instruction corresponding to the request instruction from a plurality of preset instructions.

[0110] The request instruction is a request instruction input by a user through a user voice when the user uses a terminal device, and the terminal device sends the request instruction to the server after receiving the request instruction. For example, the request instruction can be "I want to listen to music", "turn up the volume", etc., but is not limited thereto, and the present disclosure is not specifically limited.

[0111] The plurality of preset instructions are instructions stored in the preset instruction weight library, and each preset instruction in the preset instruction weight library corresponds to a weight, which is determined according to the way the user inputs the request instruction when the user uses the terminal device. Further, the preset instruction weight library further includes user identification information such as user voiceprint identification, preset scenes such as video search scenes and song playing scenes, preset time periods such as the time period from 7:00 to 10:00 when the user often uses the terminal device, and location information such as XX province and XX district, but is not limited thereto, and the present disclosure is not specifically limited, and those skilled in the art can set it according to the actual situation.

[0112] Specifically, after the terminal device receives the request instruction input by the user, the terminal device sends the request instruction to the server, and the first controller of the server determines the target instruction corresponding to the request instruction from the plurality of preset instructions included in the preset instruction weight library pre-stored on the server after receiving the request instruction sent by the terminal device.

[0113] Figure 7 A flowchart of another voice wake-up method provided by the embodiments of the present disclosure, Figure 7 is Figure 5Further, based on the embodiments shown above, a possible implementation of S51 can be: Figure 7

[0114] S71, determining the first instruction corresponding to the request instruction sent by the terminal device.

[0115] Specifically, after receiving the request instruction sent by the terminal device, the first controller of the server identifies the request instruction and determines the first instruction corresponding to the request instruction.

[0116] S72a, according to the first instruction and the user identification information corresponding to the first instruction, matching the target instruction corresponding to the request instruction in the plurality of preset instructions, and determining the weight value corresponding to the target instruction.

[0117] The user identification information is unique identification information for identifying a user, for example, it can be a user voiceprint identification 1, and the way to obtain the user identification information can be that the terminal device carries the user identification information when sending the request instruction to the server, so as to obtain the user identification information, but not limited to this, the present disclosure does not specifically limit it, and those skilled in the art can set it according to the actual situation.

[0118] Specifically, according to the first instruction corresponding to the request instruction and the user identification information corresponding to the first instruction, the first controller of the server matches in the plurality of preset instructions, determines the preset instruction consistent with the first instruction and the user identification information corresponding to the first instruction as the target instruction corresponding to the request instruction, and obtains the weight value corresponding to the target instruction.

[0119] For example, based on the above embodiments, for the request instruction "I want to listen to music" of the user, the user identification information is user voiceprint identification 1, according to the identification module, the first instruction corresponding to the request instruction "I want to listen to music" is "music search", after determining that the first instruction is "music search", according to the first instruction "music search" and the user voiceprint identification 1, matching in the plurality of preset instructions, determining the preset instruction consistent with the first instruction and the user voiceprint identification 1 as the target instruction, and obtaining the weight value corresponding to the target instruction such as 0.6, but not limited to this, the present disclosure does not specifically limit it, and those skilled in the art can set it according to the actual situation.

[0120] Optionally, based on the above embodiments, in some embodiments of the present disclosure, because the user interacts with the terminal device, the behavior habits of the user interacting with the terminal device are different for different preset scenes and different preset time periods, and because the preset instruction weight value library is obtained based on the behavior data of the user interacting with the terminal device, based on this, in order to more accurately judge whether the request instruction of the user is the instruction of the voice assistant of the terminal device, further referring to Figure 7 ​Another way of determining the target instruction corresponding to the request instruction from the plurality of preset instructions can also be:

[0121] S72b, according to the first instruction, the user identification information corresponding to the first instruction, and the preset information corresponding to the first instruction, matching the target instruction corresponding to the request instruction in the plurality of preset instructions, and determining the weight value corresponding to the target instruction.

[0122] The preset information includes at least one of a preset time period and a preset scene.

[0123] Specifically, the first controller of the server matches in the plurality of preset instructions according to the first instruction corresponding to the request instruction, the user identification information corresponding to the first instruction, and the preset information corresponding to the first instruction such as the preset time period or the preset scene, determines the target instruction corresponding to the request instruction, and obtains the weight value corresponding to the target instruction.

[0124] In the technical scheme provided by the embodiments of the present disclosure, in the above process, the target instruction is determined from the plurality of preset instructions according to the first instruction, the user identification information corresponding to the first instruction, or the first instruction, the user identification information corresponding to the first instruction and the preset information, which improves the accuracy of obtaining the target instruction, avoids the user repeatedly waking up the voice assistant of the terminal device according to the wake-up keyword, and improves the user experience.

[0125] S52, if the weight value corresponding to the target instruction is greater than or equal to a preset threshold, determining the target instruction as the instruction for waking up the voice assistant of the terminal device, and sending a wake-up instruction to the terminal device.

[0126] The wake-up instruction is used to instruct to wake up the voice assistant of the terminal device. The preset threshold is a parameter set to determine whether the request instruction sent by the terminal device received by the server is the instruction for waking up the voice assistant of the terminal device. The preset threshold may be 0.5, but is not limited thereto. The present disclosure does not specifically limit it, and those skilled in the art can set it according to the actual situation.

[0127] The above instruction for waking up the voice assistant of the terminal device specifically refers to the case that if there is still a user who needs to wake up the voice assistant of the terminal device after the user inputs the request instruction on the terminal device, the user inputs the next request instruction by voice. In this case, it is determined that the request instruction input by the current user is the instruction for waking up the voice assistant of the terminal device. Therefore, in order to avoid the user from inputting the next request instruction after waking up the voice assistant of the terminal device by the wake-up keyword, the server sends a wake-up instruction to the terminal device to wake up the voice assistant of the terminal device.

[0128] For example, based on the above embodiment, after the user awakens the voice assistant of the terminal device according to the wake-up keyword "XX fairy", the user inputs the request instruction "I want to listen to music" in the form of user voice, and then the user needs to continue to awaken the voice assistant of the terminal device and input the next request instruction "turn up the sound" in the form of user voice. At this time, it is determined that the request instruction "I want to listen to music" is a command for which the voice assistant of the terminal device is not awakened, but the present disclosure is not limited thereto, and the person skilled in the art can set it according to the actual situation.

[0129] Specifically, the first controller of the server determines whether the weight value corresponding to the target instruction is greater than or equal to the preset threshold value. When it is determined that the weight value corresponding to the target instruction is greater than or equal to the preset threshold value, it is determined that the target instruction is a command for which the voice assistant of the terminal device is not awakened. The first controller of the server sends a wake-up instruction for awakening the voice assistant of the terminal device to the terminal device to awaken the voice assistant of the terminal device.

[0130] In the technical solution provided by the embodiments of the present disclosure, the preset instruction weight value library is stored on the server, the preset instruction weight value library includes a plurality of preset instructions and a weight value corresponding to each preset instruction, the first controller of the server receives a request instruction sent by a terminal device, determines a target instruction corresponding to the request instruction from the plurality of preset instructions, and if the weight value corresponding to the target instruction is greater than or equal to a preset threshold value, it is determined that the target instruction is a command for which the voice assistant of the terminal device is not awakened, and a wake-up instruction is sent to the terminal device, wherein the wake-up instruction is used to instruct to awaken the voice assistant of the terminal device. In the above technical solution, the first controller of the server determines the target instruction corresponding to the request instruction sent by the terminal device in the preset instruction weight value library stored on the server, and further determines that the target instruction is a command for which the voice assistant of the terminal device is not awakened when it is determined that the weight value corresponding to the target instruction is greater than or equal to the preset threshold value. The wake-up instruction for awakening the voice assistant of the terminal device is sent to the terminal device to awaken the voice assistant of the terminal device. Therefore, when the user inputs the next request instruction in the form of user voice, the user does not need to awaken the voice assistant of the terminal device according to the wake-up keyword carried in the wake-up request, thereby solving the problem that the user and the terminal device do not interact conveniently and quickly in the prior art, and improving the user experience.

[0131] Figure 8 For another voice wake-up method provided by the embodiments of the present disclosure, Figure 8 is Figure 7 based on the embodiments shown in the above, further, as Figure 8 shown, before performing S51, it further includes:

[0132] S81, obtaining a plurality of historical request instructions input by a user respectively corresponding to a preset instruction.

[0133] The plurality of historical request instructions can be input by user voice, can be input by a button on a control device such as a remote controller, or can be input by a virtual button on a touch display screen, but are not limited thereto. The present disclosure is not specifically limited, and a person skilled in the art can set according to actual conditions.

[0134] The preset instruction corresponds to the historical request instruction input by the user. For example, in the above embodiment, the historical request instruction is "I want to listen to music", and the corresponding preset instruction is "music search". Alternatively, the historical request instruction is "increase the volume of the currently played music", and the corresponding preset instruction is "increase the volume", but is not limited thereto. The present disclosure is not specifically limited, and a person skilled in the art can set according to actual conditions.

[0135] Specifically, the first controller of the server obtains the preset instruction corresponding to each historical request instruction in the plurality of historical request instructions input by the user, to obtain a plurality of preset instructions.

[0136] Optionally, based on the above embodiment, in some embodiments of the present disclosure, because the user has different habits of inputting request instructions in different preset scenes such as a video search scene and a music playing scene and in different preset time periods, in order to improve the accuracy of obtaining the preset instruction weight library according to the request instruction input by the user, one implementation of S81 can be:

[0137] S811, obtaining a plurality of historical request instructions input by the user according to a preset condition.

[0138] The preset condition includes at least one of a preset scene and a preset time period.

[0139] S812, determining the preset instruction corresponding to each historical request instruction.

[0140] Specifically, the first controller of the server obtains the preset instruction corresponding to each historical request instruction in the plurality of historical request instructions input by the user according to the preset condition such as the preset scene or the preset time period or the preset scene and the preset time period, and identifies each historical request instruction to determine the preset instruction corresponding to each historical request instruction.

[0141] The above identification of each historical request instruction to determine the corresponding preset instruction can be identification by a trained identification model. The specific identification process is referred to the prior art, and the present disclosure will not be described in detail.

[0142] In the technical scheme provided by the embodiments of the present disclosure, in the above process, the historical request instructions are acquired according to the preset conditions such as a preset scene and / or a preset time period, and the preset instructions corresponding to the historical request instructions are determined, so that the operation habits of the user in inputting the request instructions in different preset scenes and / or different preset time periods can be considered, and the accuracy of subsequently acquiring the weights corresponding to the plurality of preset instructions in the preset weight library is improved.

[0143] S82, determine the plurality of preset instructions as a plurality of first preset instruction sets based on a preset time interval.

[0144] The preset time interval refers to a parameter set for grouping the plurality of preset instructions, and the plurality of preset instructions are grouped according to the preset time interval to obtain a plurality of first preset instruction sets, wherein the preset instructions included in each first preset instruction set are continuous instructions. The preset time interval may be 60 seconds or 120 seconds, but is not limited thereto. The present disclosure does not specifically limit this, and a person skilled in the art can set it according to the actual situation.

[0145] For example, the preset time interval is 60 seconds, and the plurality of preset instructions are grouped to obtain a plurality of first preset instruction sets such as first preset instruction set 1, first preset instruction set 2, first preset instruction set 3, first preset instruction set 4, and first preset instruction set n. The plurality of preset instructions included in the first preset instruction set 1 are, for example, preset instruction 1, preset instruction 2, and preset instruction 3. It is considered that the preset instruction 1, the preset instruction 2, and the preset instruction 3 are continuous instructions, that is, the user will input the preset instruction 2 in a short time after inputting the preset instruction 1, and then input the preset instruction 3 after inputting the preset instruction 2. However, this is not limited thereto. The present disclosure does not specifically limit this, and a person skilled in the art can set it according to the actual situation.

[0146] It should be noted that each first preset instruction set also includes user identification information corresponding to each preset instruction and a timestamp when the user inputs the request instruction. For example, the preset command may be {user identification information: user voiceprint identification 1, preset command: music search, acquisition method: user voice, timestamp: 1664767295189}, but is not limited thereto. The present disclosure does not specifically limit this, and a person skilled in the art can set it according to the actual situation.

[0147] S83, delete a target non-voice preset instruction in each first preset instruction set to obtain a plurality of second preset instruction sets.

[0148] The first preset instruction in each second preset instruction set is acquired according to the user voice, and the target non-voice preset instruction in each first preset instruction set is arranged before the first preset instruction.

[0149] Specifically, the first controller of the server groups the preset instructions according to preset time intervals to obtain a plurality of first preset instruction sets, and then deletes target non-voice preset instructions before a first preset instruction obtained by user voice in each first preset instruction set, so as to obtain a plurality of second preset instruction sets. At this time, the first preset instruction in each second preset instruction set is obtained according to user voice.

[0150] S84, deleting non-voice preset instructions from each second preset instruction set of the plurality of second preset instruction sets to obtain a plurality of third preset instruction sets.

[0151] S85, determining a target preset instruction set in combination with the plurality of third preset instruction sets.

[0152] The plurality of preset instructions included in the target preset instruction set are obtained according to user voice.

[0153] Specifically, since the voice assistant of the wake-up terminal device is woken up by user voice according to a wake-up keyword, the first controller of the server deletes non-voice preset instructions in each second preset instruction set to obtain a plurality of third preset instruction sets, and combines the plurality of third preset instruction sets to obtain a target preset instruction set. The plurality of preset instructions included in the target preset instruction set are obtained by user voice.

[0154] S86, determining a weight value of a preset instruction corresponding to each request operation based on an occurrence frequency of the preset instruction and a weight factor, to obtain a plurality of weight values respectively corresponding to the plurality of preset instructions.

[0155] Optionally, based on the above-mentioned embodiments, in some embodiments of the present disclosure, one implementation of S86 can be:

[0156] S861, for each preset instruction corresponding to each request operation in the target preset instruction set, obtaining a first total number of preset instructions existing in the target preset instruction set, a second total number of preset instructions existing in a plurality of historical request instructions respectively corresponding to the preset instructions, and calculating a quotient value of the first total number and the second total number to obtain an occurrence frequency of the preset instruction.

[0157] The request operation refers to an operation performed according to a preset instruction. For example, the preset instruction is "music search", and the request operation is the operation of music search. For multiple preset instructions included in the target preset instruction set, there can be multiple preset instructions for each request operation. For example, the multiple preset instructions included in the target preset instruction set are: preset instruction 1, preset instruction 2, preset instruction 1, preset instruction 2, preset instruction 3, preset instruction 1, preset instruction 4, preset instruction 2, preset instruction 5, preset instruction 6,..., and preset instruction n. There are multiple preset instructions 1 for the request operation 1, but the present disclosure is not limited thereto, and the person skilled in the art can set it according to the actual situation.

[0158] Specifically, the first controller of the server counts the first total number of the preset instruction in the target preset instruction set and the second total number of the preset instruction corresponding to each request operation in the target preset instruction set, and calculates the quotient of the first total number and the second total number to determine the frequency of occurrence of the preset instruction corresponding to each request operation.

[0159] For example, based on the above embodiment, the first total number of the preset instruction 1 in the target preset instruction set is N1, and the second total number of the preset instruction corresponding to each request operation in the multiple historical request instructions is N2. The frequency of occurrence of the preset instruction 1 is T1=N1 / N2, but the present disclosure is not limited thereto, and the person skilled in the art can set it according to the actual situation.

[0160] S862, obtaining the first timestamp corresponding to each preset instruction, the second timestamp corresponding to the next preset instruction adjacent to the preset instruction, and determining the weight factor of the preset instruction according to the first timestamp, the second timestamp, the preset mapping table, and the first total number.

[0161] The preset mapping table is used to determine the initial weight of each preset instruction. The preset mapping table includes multiple preset time difference ranges, and each preset time difference range corresponds to a preset weight. For example, as shown in Table 1 below:

[0162] Table 1

[0163] Pre-set time difference range (seconds) Pre-set weight [0,3] 1 (3,5] 0.9 (5,10] 0.6 (10,15] 0.15 (15,20] 0.1 (20,] 0.01

[0164] Specifically, the first controller of the server obtains the first timestamp corresponding to each preset instruction, and obtains the second timestamp corresponding to the next preset instruction adjacent to each preset instruction. After obtaining the first timestamp and the second timestamp, the weight factor of the preset instruction is determined according to the first timestamp, the second timestamp, the preset mapping table, and the first total number of the preset instruction in the target preset instruction set.

[0165] Optionally, based on the above embodiments, in some embodiments of the present disclosure, according to the first timestamp, the second timestamp, the preset mapping table and the first total number, one implementation of determining the weight factor of the preset instruction can be: first, calculate the time difference value of the second timestamp and the first timestamp, after obtaining the time difference value, determine the preset time difference range to which the time difference value belongs in the preset mapping table, to determine the initial weight value corresponding to the preset instruction, then calculate the quotient value of the initial weight value and the first total number, and finally sum the initial weight values corresponding to each of the plurality of preset instructions existing for each request operation to obtain the weight factor of the preset instruction corresponding to each request operation.

[0166] S863, the frequency of occurrence is multiplied by the weight factor to obtain the weight value corresponding to the preset instruction.

[0167] Specifically, the first controller of the server performs product operation on the frequency of occurrence corresponding to the preset instruction and the weight factor, to obtain the weight value corresponding to the preset instruction.

[0168] S87, according to the plurality of preset instructions and the weight of each preset instruction, determine the preset instruction weight library.

[0169] Specifically, the first controller of the server saves the plurality of preset instructions and the weight corresponding to each of the plurality of preset instructions in the preset instruction weight library, to obtain the preset instruction weight library.

[0170] In the technical scheme provided by the embodiments of the present disclosure, in the above process, since the preset weight library is obtained by calculating and obtaining according to the user historical request instruction, the operation habit of inputting the request instruction of the user can be considered, thereby improving the accuracy of subsequently obtaining the weight corresponding to each of the plurality of preset instructions in the preset weight library, and further, based on the weight, the request instruction received by the server can be more accurately determined as the instruction of the voice assistant of the terminal device which does not need to wake up the terminal device, to determine whether the wake-up instruction of the voice assistant of the terminal device which wakes up the terminal device needs to be sent to the terminal device, and the voice assistant of the terminal device is woken up, thereby solving the problem that the user and the terminal device do not interact with each other conveniently and quickly in the prior art, and improving the user experience.

[0171] Figure 9 For another flowchart of the voice wake-up method provided by the embodiments of the present disclosure, Figure 10 For another flowchart of the voice wake-up method provided by the embodiments of the present disclosure, Figure 9 is Figure 5 based on the embodiments shown in the figure, further, Figure 10 as shown, further comprising:

[0172] S91, if the weight value corresponding to the target instruction is less than the preset threshold, it is determined that the target instruction is not an instruction for which the voice assistant is exempt from being woken up, and a shutdown instruction is sent to the terminal device.

[0173] The shutdown instruction is used to instruct the shutdown of the preset program of the terminal device. For example, the shutdown instruction is used to instruct the shutdown of the preset program of the terminal device, such as a built-in microphone for receiving user voice, or can also be a screen, but is not limited thereto. The present disclosure does not make specific arrangements, and a person skilled in the art can make arrangements according to actual conditions.

[0174] Specifically, when the first controller of the server determines that the weight value corresponding to the target instruction is less than the preset threshold, it is determined that the target instruction is not an instruction for which the voice assistant is exempt from being woken up. After determining that the target instruction is not an instruction for which the voice assistant is exempt from being woken up, a shutdown instruction is sent to the terminal device to shut down the preset program of the terminal device.

[0175] In the technical solution provided by the embodiments of the present disclosure, in the above process, after it is determined that the target instruction is not an instruction for which the voice assistant is exempt from being woken up according to the weight value corresponding to the target instruction, a shutdown instruction is sent to the terminal device to shut down the terminal device, so that the resources of the terminal device can be saved in a timely manner.

[0176] Figure 11 A flowchart of another voice wake-up method provided by the embodiments of the present disclosure. Figure 12 An interaction diagram of another voice wake-up method provided by the embodiments of the present disclosure, which is applied to the terminal device side. As shown in the figure, Figure 11 The method specifically includes the following steps:

[0177] S111, in response to a wake-up request input by a user, waking up the voice assistant of the terminal device.

[0178] The wake-up request carries a wake-up keyword, and the wake-up keyword is used to wake up the voice assistant of the terminal device. For example, the wake-up keyword can be "XX genie", but is not limited thereto. The present disclosure does not make specific limitations, and a person skilled in the art can make arrangements according to actual conditions.

[0179] S112, after determining that the voice assistant of the terminal device is woken up, in response to a request instruction input by a user, sending the request instruction to a server.

[0180] S113, in response to a wake-up instruction sent by the server, waking up the voice assistant of the terminal device.

[0181] Specifically, the second controller of the terminal device responds to a wake-up request input by a user, wherein the wake-up request carries a wake-up keyword, and the voice assistant of the terminal device is woken up according to the wake-up keyword. After it is determined that the voice assistant of the terminal device is woken up, a request instruction input by the user is received, and the request instruction is sent to a server, so that the server determines whether the request instruction is an instruction for which the voice assistant of the terminal device is exempted from being woken up. When the server determines that the request instruction is an instruction for which the voice assistant of the terminal device is exempted from being woken up, a wake-up instruction is sent to the terminal device, and the terminal device responds to the wake-up instruction sent by the server and wakes up the voice assistant of the terminal device.

[0182] In the technical solution provided by the embodiments of the present disclosure, the second controller of the terminal device responds to a wake-up request input by a user to wake up the voice assistant of the terminal device, wherein the wake-up request carries a wake-up keyword, and the wake-up keyword is used to wake up the voice assistant of the terminal device. After it is determined that the voice assistant of the terminal device is woken up, a request instruction input by the user is received, and the request instruction is sent to a server. The voice assistant of the terminal device is woken up in response to a wake-up instruction sent by the server. In the technical solution, after the second controller of the terminal device wakes up the voice assistant of the terminal device according to the wake-up keyword carried in the wake-up request, the second controller receives a request instruction input by the user and sends the request instruction to the server. The server determines a target instruction corresponding to the request instruction in a preset instruction weight library, and determines that the target instruction is an instruction for which the voice assistant of the terminal device is exempted from being woken up when a weight corresponding to the target instruction is greater than or equal to a preset threshold. The server sends a wake-up instruction for waking up the voice assistant of the terminal device to the terminal device. In this way, the voice assistant of the terminal device is woken up, so that the user does not need to wake up the voice assistant of the terminal device according to the wake-up keyword carried in the wake-up request when inputting a next request instruction by voice. The problem that the user and the terminal device do not interact by voice conveniently and quickly in the prior art is solved, and the user experience is improved.

[0183] The computer readable storage medium stores a computer program, which is executed by a processor to implement each process of the voice wake-up method and achieve the same technical effects. To avoid repetition, details are not described herein.

[0184] The computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0185] The present disclosure provides a computer program product comprising computer executable instructions that, when executed by a computer, cause the computer to implement the voice wake-up method described above.

[0186] The above description has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the embodiments to the precise forms disclosed. Modifications and variations are possible in light of the above teachings or can be acquired from practice of the embodiments. The described embodiments were chosen on the basis of results that are considered to achieve the objectives and principles of the application. Other embodiments will occur to readers to practice the application and are encompassed within the scope of the disclosure.

Claims

1. A server, characterized by The server stores a preset instruction weight value library, the preset instruction weight value library is obtained based on the behavior habits of the user interacting with the terminal device, the preset instruction weight value library includes: a plurality of preset instructions, and a weight value corresponding to each preset instruction; comprising: The first controller is configured to: receive a request instruction sent by the terminal device, determine a target instruction corresponding to the request instruction from the plurality of preset instructions; if the weight value corresponding to the target instruction is greater than or equal to a preset threshold, determine that the target instruction is an instruction for waking up the voice assistant of the terminal device, and send a wake-up instruction to the terminal device, wherein the wake-up instruction is used to instruct to wake up the voice assistant of the terminal device.

2. The server of claim 1, wherein, The first controller is further configured to: obtain a plurality of historical request instructions input by the user respectively corresponding to a preset instruction; determine a plurality of preset instructions as a plurality of first preset instruction sets based on a preset time interval; delete a target non-voice preset instruction in each first preset instruction set to obtain a plurality of second preset instruction sets, wherein the first preset instruction in each second preset instruction set is obtained according to user voice, and the target non-voice preset instruction in each first preset instruction set is arranged before the first preset instruction; delete non-voice preset instructions from each second preset instruction set of the plurality of second preset instruction sets and perform splitting processing to obtain a plurality of third preset instruction sets; determine a target preset instruction set in combination with the plurality of third preset instruction sets, wherein the plurality of preset instructions included in the target preset instruction set are obtained according to user voice; determine the weight value of the preset instruction corresponding to each request operation based on the occurrence frequency of the preset instruction corresponding to each request operation in the target preset instruction set and a weight factor, to obtain the weight value of the plurality of preset instructions respectively corresponding to the weight value; determine the preset instruction weight value library according to the plurality of preset instructions and the weight value of each preset instruction.

3. The server of claim 2, wherein, The first controller is specifically configured to: for the preset instruction corresponding to each request operation in the target preset instruction set, obtain a first total number of the preset instruction existing in the target preset instruction set, a second total number of the preset instruction existing in the preset instruction corresponding to a plurality of historical request instructions respectively, and calculate the quotient of the first total number and the second total number to obtain the occurrence frequency of the preset instruction; obtain a first timestamp corresponding to each preset instruction, a second timestamp corresponding to a next preset instruction adjacent to the preset instruction, and determine a weight factor of the preset instruction according to the first timestamp, the second timestamp, a preset mapping table, and the first total number; multiply the occurrence frequency and the weight factor to obtain the weight value corresponding to the preset instruction.

4. The server of claim 2, wherein, The first controller is specifically further configured to: obtain a plurality of historical request instructions input by the user according to a preset condition; for each historical request instruction, determine the preset instruction corresponding to the historical request instruction; wherein the preset condition includes at least one of a preset scene and a preset time period.

5. The server of claim 1, wherein, The first controller is specifically configured to: determine a first instruction corresponding to the request instruction sent by the terminal device; match a target instruction corresponding to the request instruction from the plurality of preset instructions according to the first instruction and user identification information corresponding to the first instruction, and determine a weight value corresponding to the target instruction; or match a target instruction corresponding to the request instruction from the plurality of preset instructions according to the first instruction, user identification information corresponding to the first instruction, and preset information corresponding to the first instruction, and determine a weight value corresponding to the target instruction, wherein the preset information includes at least one of a preset time period and a preset scene.

6. The server of claim 1, wherein, The first controller is further configured to: if the weight value corresponding to the target instruction is less than the preset threshold value, determine that the target instruction is not an instruction for the voice assistant of the terminal device, and send a shutdown instruction to the terminal device, wherein the shutdown instruction is used to instruct to shut down a preset program of the terminal device.

7. A voice wake-up method, characterized by, The application is applied to a server, the server stores a preset instruction weight value library, the preset instruction weight value library is acquired based on the behavior habits of a user interacting with a terminal device, and the preset instruction weight value library includes a plurality of preset instructions and a weight value corresponding to each preset instruction. receive a request instruction sent by a terminal device, and determine a target instruction corresponding to the request instruction from the plurality of preset instructions; if the weight value corresponding to the target instruction is greater than or equal to a preset threshold value, determine that the target instruction is an instruction for the voice assistant of the terminal device, and send a wake-up instruction to the terminal device, wherein the wake-up instruction is used to instruct to wake up the voice assistant of the terminal device.

8. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the method of claim 7.

Images