Display device and voice instruction recognition method

Abstract

The embodiment of the invention provides a display device and a voice instruction recognition method, and the method comprises the steps: converting a voice instruction into semantic information containing a target instruction character string and a text corresponding to the voice instruction according to a preset format under the condition that the voice instruction is received; performing validity judgment on the target instruction character string according to an instruction character string set of the target application program, and determining a target voice instruction in a voice instruction library of the target application program according to a text corresponding to the voice instruction under the condition that a judgment result is an invalid result; therefore, the target application program is controlled to execute an application function corresponding to the target voice instruction. By setting the semantic information conversion mechanism, the validity judgment mechanism based on the target application program instruction character string set and the mode of starting voice instruction library matching when the result is invalid, the judgment range of the voice instruction can be expanded, and therefore the accuracy of voice instruction recognition is improved.

Description

Technical Field

[0001] The present application relates to the technical field of display devices, and in particular to a display device and a voice command recognition method. Background Art

[0002] A display device is a terminal device used to display images, and the applications installed on the display device can output different display images. Users can directly view the output display images or interact with the display device by inputting operating instructions guided by the output display images. To meet the diverse and personalized needs of users, display devices can be installed with a variety of applications with different functions.

[0003] Users can use voice commands to control applications to execute corresponding application functions. Taking applications with video playback functions as an example, voice commands can be play commands, fast-forward commands, or pause commands, etc. The application with video playback functions can execute the corresponding playback functions according to the voice commands.

[0004] However, if the voice command input by the user is not standardized, even if the application can execute the corresponding application function, the voice command cannot be matched with the text content corresponding to the voice command preset by the application, resulting in the voice command not being recognized or being recognized incorrectly, and the application function corresponding to the voice command is not executed. Summary of the Invention

[0005] The present application provides a display device and a voice command recognition method to solve the problem that the user inputs non-standard voice commands, resulting in the application program being unable to execute the application function corresponding to the voice command.

[0006] In a first aspect, some embodiments of the present application provide a display device, including:

[0007] a display configured to display a user interface;

[0008] a sound collector configured to receive voice commands;

[0009] The controller is configured as:

[0010] When a voice command is received, converting the voice command into semantic information according to a preset format, wherein the semantic information includes a target command string and a text corresponding to the voice command;

[0011] Searching for the target instruction string in an instruction string set of a target application, where the target application is an application registered with a speech recognition function in the display device;

[0012] If the target instruction string is not found in the instruction string set, generating the invalid result based on the target instruction string;

[0013] Determining a target voice instruction in a voice instruction library of the target application according to the invalid result and the text corresponding to the voice instruction, wherein the voice instruction library stores a preset number of voice template instructions executable by the target application;

[0014] In response to a target voice instruction, the target application is controlled to execute an application function corresponding to the target voice instruction.

[0015] The above technical solution has the following beneficial effects or advantages: when the display device receives a voice instruction, it converts the voice instruction into semantic information, and determines the validity of the target instruction string through the instruction string set of the target application. When it is determined to be invalid, it automatically switches to the semantic matching mode of the text corresponding to the voice instruction, so as to determine the target voice instruction according to the text corresponding to the voice instruction in the voice instruction library, and control the application to execute the application function corresponding to the target voice instruction. This application solves the problem of recognition failure caused by the non-standard format of the user's voice instruction in the background technology by setting a semantic information conversion mechanism, a validity judgment mechanism based on the target application instruction string set, and enabling voice instruction library matching when the result is invalid. It ensures that even if the user's expression has grammatical deviations or non-standard terminology, it can still accurately trigger the application function of the target application, thereby improving the success rate of voice interaction.

[0016] In some embodiments, when the target instruction string is found in the instruction string set, the controller is further configured to:

[0017] Generate a valid result based on the target instruction string;

[0018] If the determination result is a valid result, the voice instruction is marked as a target voice instruction.

[0019] The above technical solution has the following beneficial effects or advantages: This embodiment provides processing logic for valid determinations. When the target command string exists in the command string set, a valid result is generated and the voice command is marked as the target voice command. If the target command string is not found in the command string set, a semantic matching process is executed. This hierarchical processing mechanism can optimize the allocation of system resources for display devices and improve the recognition coverage of unconventional voice commands.

[0020] In some embodiments, before executing the step of searching the target application's instruction string set for the target instruction string, the controller is further configured to:

[0021] Based on the registered speech recognition function, the instruction character string set sent by the target application corresponding to the speech recognition function is received.

[0022] The above technical solution has the following beneficial effects or advantages: after the display device registers the voice recognition function for the target application, it can receive the command string set sent by the target application, so as to query the target command string according to the command string set, thereby obtaining the result of the voice command validity judgment.

[0023] In some embodiments, the voice instruction library includes a preset number of voice template instructions, and the controller determines the target voice instruction in the voice instruction library of the target application according to the text corresponding to the voice instruction, and is specifically configured as follows:

[0024] Calculating the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction;

[0025] The voice template instruction whose semantic matching degree is greater than or equal to the matching degree threshold and whose semantic matching degree is the highest is marked as the target voice instruction.

[0026] The above technical solution has the following beneficial effects or advantages: This application calculates the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction, and marks the voice instruction with the highest semantic matching degree as the target voice instruction when the semantic matching degree is greater than or equal to the matching degree threshold. By limiting the semantic matching degree calculation and threshold screening mechanism of the voice instruction library matching, the text corresponding to the voice instruction and the preset template instruction are quantitatively compared for similarity, and the matching degree threshold is set as the validity filtering condition. It can be ensured that the execution is triggered only when there are valid instructions with highly similar semantics, reducing the problem of false rejection caused by differences in the expression form of the instructions. Setting a threshold mechanism can filter out invalid matches with too low similarity, and through the highest matching degree screening, it is ensured that the display device can determine the target instruction among multiple candidate instructions, thereby improving the recognition accuracy of non-standard instructions.

[0027] In some embodiments, the controller is further configured to:

[0028] When the semantic matching degrees between all the voice template instructions in the voice instruction library and the text corresponding to the voice instruction are less than the matching degree threshold, generating prompt information indicating that the voice instruction cannot be recognized;

[0029] A prompt window is created in the user interface, and the prompt information is displayed in the prompt window.

[0030] The above technical solution has the following beneficial effects or advantages: When the semantic matching degree between all voice template instructions in the voice instruction library and the text corresponding to the voice instruction is less than the matching degree threshold, the present application generates a prompt message through an exception handling mechanism, creates a visual prompt window in the user interface, and displays a prompt message in the prompt window to prompt the user of the voice recognition failure, thereby avoiding the situation where the user cannot know whether the input voice instruction is valid when the voice instruction fails silently, causing the user to repeatedly input invalid voice instructions. This embodiment can guide the user to adjust the expression method or use other interaction methods through prompt information, thereby improving the convenience of voice interaction.

[0031] In some embodiments, the system further includes a memory configured to store a semantic understanding model, and the controller calculates the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction, specifically configured to:

[0032] Performing semantic understanding on the text corresponding to the voice instruction using the semantic understanding model to obtain first semantic information;

[0033] Performing semantic understanding on the instruction text corresponding to the voice template instruction by the semantic understanding model to obtain second semantic information;

[0034] Calculate the semantic matching degree between the first semantic information and the second semantic information.

[0035] The above technical solution has the following beneficial effects or advantages: In this embodiment, the memory stores a semantic understanding model, and the semantic understanding model can be used to perform semantic understanding on the text corresponding to the voice instruction, thereby obtaining first semantic information. The semantic understanding model is then used to perform semantic understanding on the instruction text corresponding to the voice template instruction in the voice instruction library to obtain second semantic information, thereby calculating the semantic matching degree between the first voice information and the second semantic information. Through a dual-path processing mechanism based on a semantic understanding model preset in the memory, the problem of amplified deviations between the first voice information and the second semantic information caused by heterogeneous algorithms is avoided.

[0036] In some embodiments, the controller controls the target application to execute an application function corresponding to the target voice instruction in response to the target voice instruction, and is specifically configured to:

[0037] Detecting configuration parameters in the semantic information, where the configuration parameters are used to represent parameters for executing application functions of the target application;

[0038] If the semantic information includes the configuration parameters, then in response to the target voice instruction, the application function corresponding to the target voice instruction is executed according to the configuration parameters.

[0039] The above technical solution has the following beneficial effects or advantages: This embodiment adds detection and execution logic for configuration parameters in semantic information. When a voice command contains parameter configuration, the display device can automatically extract the parameter configuration and configure it into the execution item of the application function, so that the application function executes the application function according to the configuration parameters. By structured parsing of the "command + parameter" compound voice command, a single voice interaction can be executed according to the configuration parameters within the threshold, thereby improving the accuracy of executing the voice command.

[0040] In some embodiments, the controller is further configured to:

[0041] In response to a startup instruction input by a user based on the application, starting the application;

[0042] After detecting a startup event of the application, registering a speech recognition function of the application in the display device;

[0043] After registering the speech recognition function of the application, marking the application as the target application;

[0044] Based on the voice recognition function, the voice collector collects voice instructions for instructing the target application to perform a specified interactive action.

[0045] The above technical solution has the following beneficial effects or advantages: This embodiment establishes a dynamic registration mechanism for application voice functions, triggering the registration process for application voice recognition capabilities through startup commands. This dynamic registration mechanism for voice functions can mark an application as a target application when the application is started, ensuring that voice commands are targeted to the target application, preventing voice commands from being applied to applications that do not have registered voice recognition capabilities, ensuring the targeted execution capability of voice commands, and improving the accuracy of voice command responses.

[0046] In some embodiments, the controller is further configured to:

[0047] closing the target application in response to a closing instruction input by a user based on the target application;

[0048] After detecting a closing event of the target application, deregistering a speech recognition function of the application in the display device;

[0049] After deregistering the speech recognition function of the application, the target application is marked as the application.

[0050] The above technical solution has the following beneficial effects or advantages: In this embodiment, the display device responds to the user input of a close command, and after closing the target application, the voice recognition function of the application is deregistered in the display device, which can prevent the closed application from continuously occupying the system resources of the display device through the voice recognition function, thereby freeing up system resources to allow newly launched applications or already launched applications to use system resources to execute the voice recognition function, thereby improving the utilization of system resources and ensuring the real-time voice response in multi-application switching scenarios.

[0051] In a second aspect, some embodiments of the present application provide a voice command recognition method, applied to the display device described in the first aspect, the method comprising:

[0052] When a voice command is received, converting the voice command into semantic information according to a preset format, wherein the semantic information includes a target command string and a text corresponding to the voice command;

[0053] Searching for the target instruction string in an instruction string set of a target application, where the target application is an application registered with a speech recognition function in the display device;

[0054] If the target instruction string is not found in the instruction string set, generating the invalid result based on the target instruction string;

[0055] Determining a target voice instruction in a voice instruction library of the target application according to the invalid result and the text corresponding to the voice instruction, wherein the voice instruction library stores a preset number of voice template instructions executable by the target application;

[0056] In response to a target voice instruction, the target application is controlled to execute an application function corresponding to the target voice instruction.

[0057] It can be seen from the above technical solutions that some embodiments of the present application provide a display device and a voice instruction recognition method, which converts the voice instruction into semantic information containing a target instruction string and a text corresponding to the voice instruction according to a preset format when a voice instruction is received. Then, a validity judgment is performed on the target instruction string based on the instruction string set of the target application, and when the judgment result is an invalid result, the target voice instruction is determined in the voice instruction library of the target application based on the text corresponding to the voice instruction, thereby controlling the target application to execute the application function corresponding to the target voice instruction. The present application can expand the judgment scope of voice instructions by setting a semantic information conversion mechanism, a validity judgment mechanism based on the instruction string set of the target application, and enabling voice instruction library matching when the result is invalid, thereby improving the accuracy of voice instruction recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0059] Figure 1 A schematic diagram of an operation scenario between a display device and a control device provided in some embodiments of the present application;

[0060] Figure 2 A schematic diagram of the hardware configuration of a display device provided in some embodiments of the present application;

[0061] Figure 3 A schematic diagram of software configuration of a display device provided in some embodiments of the present application;

[0062] Figure 4 A flowchart of a display device refusing to recognize non-standard voice commands provided in some embodiments of the present application;

[0063] Figure 5 A flowchart of a method for performing voice command recognition on a display device provided in some embodiments of the present application;

[0064] Figure 6 A timing diagram of a method for recognizing a voice command executed by a display device according to some embodiments of the present application;

[0065] Figure 7 A flowchart of converting voice commands into a display device provided in some embodiments of the present application;

[0066] Figure 8 A flowchart of a display device receiving a set of instruction strings provided in some embodiments of the present application;

[0067] Figure 9 A flowchart of a display device determining a target voice command based on a valid result provided in some embodiments of the present application;

[0068] Figure 10 A schematic diagram of generating effective results for a display device provided in some embodiments of the present application;

[0069] Figure 11 A flow chart of a display device determining a target voice command based on semantic matching provided in some embodiments of the present application;

[0070] Figure 12 A schematic diagram of an interface for displaying prompt information on a display device provided in some embodiments of the present application;

[0071] Figure 13 A flowchart of calculating semantic matching degree for a display device provided in some embodiments of the present application;

[0072] Figure 14 A flowchart of a display device executing application functions provided in some embodiments of the present application. DETAILED DESCRIPTION

[0073] The following embodiments are described in detail, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numbers in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following embodiments are not intended to represent all possible implementations consistent with the present application. They are merely examples of systems and methods consistent with certain aspects of the present application, as detailed in the claims.

[0074] It should be noted that the brief descriptions of terms in this application are only for the purpose of facilitating the understanding of the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and usual meanings.

[0075] In the specification and claims of this application and the accompanying drawings, the terms "first," "second," "third," etc. are used to distinguish similar or similar objects or entities, and are not necessarily intended to limit a particular order or sequence, unless otherwise noted. It should be understood that the terms used in this manner are interchangeable under appropriate circumstances.

[0076] The terms "comprise," "include," and "have," and any variations thereof, are intended to cover but not exclude inclusion; for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0077] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functionality associated with that element.

[0078] In the embodiments of the present application, the display device 200 generally refers to a device capable of displaying images and processing data. For example, the display device 200 includes but is not limited to a smart TV, a mobile terminal, a computer, a monitor, an advertising screen, a wearable device, a virtual reality device, an augmented reality device, etc.

[0079] Figure 1 This is a schematic diagram of an operation scenario between a display device and a control device provided in some embodiments of the present application. Figure 1As shown in FIG, a user can operate the display device 200 through touch operation, the mobile terminal 300, and the control device 100. The control device 100 is used to receive operation instructions input by the user and convert the operation instructions into control instructions that the display device 200 can recognize and respond to. For example, the control device 100 can be a remote control, a stylus pen, a handle, etc.

[0080] The mobile terminal 300 can function as a control device for performing human-computer interaction between a user and the display device 200. The mobile terminal 300 can also function as a communication device for establishing a communication connection with the display device 200 and exchanging data. In some embodiments, the mobile terminal 300 can install software applications with the display device 200, enabling connection and communication via a network communication protocol, enabling one-to-one control operations and data communication. Audio and video content displayed on the mobile terminal 300 can also be transmitted to the display device 200 for synchronized display.

[0081] In some embodiments, the mobile terminal 300 or other electronic devices can also simulate the functions of the control device 100 by running an application program for controlling the display device 200 .

[0082] like Figure 1 As shown in FIG, the display device 200 also communicates data with the server 400 through various communication methods. The display device 200 may be allowed to communicate via a local area network (LAN), a wireless local area network (WLAN), and other networks.

[0083] The display device 200 may provide a broadcast receiving television function, and may also additionally provide an intelligent network television function with a computer support function, including but not limited to network television, smart TV, Internet Protocol television (IPTV), etc.

[0084] Figure 2 Some embodiments of this application provide Figure 1 2 is a block diagram of the hardware configuration of the display device 200.

[0085] In some embodiments, the display device 200 may include at least one of a tuner 210, a communication device 220, a detector 230, a device interface 240, a controller 250, a display 260, an audio output device 270, a memory, a power supply, and a user input interface.

[0086] In some embodiments, detector 230 is used to collect signals from the external environment or external interactions. For example, detector 230 may include a light receiver, such as a sensor for collecting ambient light intensity; or an image collector, such as a camera, for collecting external environmental scenes, user attributes, or user interaction gestures; or a sound collector, such as a microphone, for receiving external sounds.

[0087] In some embodiments, the display 260 includes a display component for presenting images and a driver component for driving image display. The display 260 is configured to receive image signals output from the controller 250 for display. For example, the display 260 can be used to display video content, image content, menu control interface components, and user control UI interfaces.

[0088] In some embodiments, the communication device 220 is a component used to communicate with an external device or server 400 according to various communication protocol types. The display device 200 can be provided with multiple communication devices 220 depending on the supported communication methods. For example, if the display device 200 supports wireless network communication, the display device 200 can be provided with a communication device 220 including WiFi functionality. If the display device 200 supports Bluetooth connection communication, the display device 200 needs to be provided with a communication device 220 including Bluetooth functionality.

[0089] The communication device 220 can establish a communication connection between the display device 200 and an external device or server 400 via a wireless or wired connection. A wired connection can connect the display device 200 to an external device via a data cable, an interface, or other components. A wireless connection can connect the display device 200 to an external device via a wireless signal or wireless network. The display device 200 can establish a connection with an external device directly or indirectly through a gateway, router, or connection device.

[0090] In some embodiments, the controller 250 may include at least one of a central processing unit (CPU), a video processor, an audio processor, a graphics processor, and a power processor, and first to nth interfaces for input / output. The controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in a memory. The controller 250 controls the overall operation of the display device 200.

[0091] In some embodiments, the controller 250 and the tuner 210 may be located in different separate devices, that is, the tuner 210 may also be located in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0092] In some embodiments, the user may input a user command through 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).

[0093] In some embodiments, the audio output device 270 may be a local speaker of the display device 200, or an external audio output device connected to the display device 200. For the external audio output device connected to the display device 200, the display device 200 may further be provided with an external audio output terminal, through which the audio output device may be connected to the display device 200 to output the sound of the display device 200.

[0094] In some embodiments, the user input interface 280 may be configured to receive instructions from a user.

[0095] To facilitate user interaction, in some embodiments, the display device 200 may run an operating system. The operating system is a computer program used to manage and control the hardware and software resources of the display device 200. The operating system can control the display device 200 to provide a user interface. For example, the operating system can directly control the display device to provide a user interface, or it can provide a user interface by running an application program. The operating system also allows the user to interact with the display device 200.

[0096] It should be noted that the operating system may be a native operating system based on a specific operating platform, or a third-party operating system deeply customized based on a specific operating platform, or an independent operating system specially developed for the display device.

[0097] The operating system can be divided into different modules or layers according to the functions implemented, e.g. Figure 3 As shown, in some embodiments, the system is divided into four layers, from top to bottom, namely, the application layer (referred to as "application layer"), the application framework layer (referred to as "framework layer"), the system library layer and the kernel layer.

[0098] In some embodiments, the application layer provides services and interfaces for applications, enabling the display device 200 to run applications and interact with the user based on the applications. The application layer can host at least one application, which can include built-in window programs, system settings programs, clock programs, and the like, or applications developed by third-party developers. In specific implementations, the application packages in the application layer are not limited to the examples above.

[0099] The framework layer provides applications with an application programming interface (API) and programming framework. The application framework layer includes predefined functions. The application framework layer acts as a processing center, determining the actions taken by applications in the application layer. Through the API, applications can access system resources and services during execution.

[0100] like Figure 3 As shown, Figure 3 This is a software configuration diagram of a display device provided in some embodiments of the present application. In some embodiments, the system of the display device 200 can be divided into three layers, namely, an application layer, a middleware layer, and a hardware layer from top to bottom.

[0101] The application layer mainly includes applications on the TV and the application framework. Among them, applications are mainly browser-based applications, such as HTML5 apps and native apps.

[0102] The Application Framework is a complete program model that has all the basic functions required by standard application software, such as file access, data exchange, etc., as well as the user interfaces of these functions (toolbars, status bars, menus, dialog boxes).

[0103] Native apps can support online or offline, message push or local resource access.

[0104] The middleware layer includes various TV protocols, multimedia protocols, and system components. Middleware uses the basic services (functions) provided by system software to connect various parts of the application system or different applications on the network, enabling resource and function sharing.

[0105] The hardware layer mainly includes the HAL interface, hardware, and drivers. The HAL interface is a unified interface for all TV chips, and the specific logic is implemented by each chip. Drivers mainly include: audio driver, display driver, Bluetooth driver, camera driver, WiFi driver, USB driver, HDMI driver, sensor driver (such as fingerprint sensor, temperature sensor, pressure sensor, etc.), and power driver.

[0106] It should be noted that the above example is only a simple division of the operating system functions and does not constitute a limitation on the specific operating system form of the display device 200 in the embodiment of the present application. Depending on factors such as the function of the display device and the type of operating system, the number of levels and specific level types contained in the operating system may be expressed in other forms.

[0107] In some embodiments, the display device 200 may also have a voice interaction function. When the display device 200 receives a voice command sent by a user to the display device 200, the display device 200 may perform voice recognition on the voice command, thereby executing an interactive action corresponding to the voice command.

[0108] To facilitate user use of the voice interaction function of the display device 200, the display device 200 may also integrate a voice application that can quickly recognize voice commands sent by the user to improve interaction efficiency. The display device 200 may integrate a voice application on the display device 200 through a software development kit (SDK). A voice application is an application that implements voice interaction functions through voice recognition and natural language processing technologies. When a user sends a voice command to the display device 200, the voice application can recognize the voice command and control the display device 200 to perform the corresponding functional operation, such as searching for programs, playing music, and querying information.

[0109] In some embodiments, the voice application can be integrated into the application or into the system of the display device 200. When the voice application is integrated into the application, the application has a voice recognition function, and the display device 200 can control the application to recognize voice commands through the voice recognition function, so that during the operation of the application, the application can execute the interactive action corresponding to the voice command.

[0110] Different types of applications have different voice commands that can be responded to. For example, for a video playback application, users can say voice commands such as "Pause video" or "Start video" to control video playback. Users can also say voice commands such as "Increase volume" or "Decrease volume" to adjust the volume.

[0111] It should be noted that the above examples are only used for video playback applications and do not limit the types of applications. It should be understood that the above examples can also be applied to other applications, such as audio playback programs, text display programs, game applications, or browser applications. The voice commands can be adjusted according to the executable functions of the corresponding application. For example, for an audio playback program, the corresponding voice commands can be voice commands such as "play audio", "cut song", "adjust playback sound effects", etc. For other types of applications, you can refer to the above examples and will not repeat them here.

[0112] Next, this embodiment uses a video playback program as an example. For the HBBTV (Hybrid Broadcast-Broadband TV) application, it can be run in a display device 200 that has a hybrid connection between broadcasting and the Internet. The user can control the video playback program to perform corresponding interactive actions by inputting voice commands. For example, when the display device 200 plays video media data through the HBBTV application, the user can say voice commands such as "pause", "fast forward", and "stop fast forward" to interact with the HBBTV application.

[0113] When an application recognizes a voice command, it will recognize it based on the text content corresponding to the preset voice command. If the voice command input by the user is not standardized, even if the application can execute the corresponding application function, the voice command will not be recognized or will be recognized incorrectly because the voice command cannot match the text content corresponding to the preset voice command of the application. Figure 4 As shown, for example, the text content corresponding to the voice instruction for the fast-forward playback function of the HBBTV application is "fast play", and the voice instruction input by the user is the colloquial expression "play quickly". This results in the HBBTV application being able to execute the fast-forward playback function, but because the voice instruction input by the user cannot be accurately matched with the text content corresponding to the voice instruction, the voice instruction input by the user is rejected, resulting in the failure to successfully execute the application function corresponding to the voice instruction.

[0114] To address the above technical issues, some embodiments of the present application provide a display device comprising a display 260 configured to display a user interface, a sound collector configured to receive voice data, wherein the voice data may include voice commands, and a controller 250 configured to execute a voice command recognition method.

[0115] Figure 5 A flowchart of a method for performing voice command recognition on a display device provided in some embodiments of the present application. Figure 6 A timing diagram of a display device executing a voice command recognition method provided in some embodiments of the present application.

[0116] See also Figure 5 and Figure 6 , the method includes the following contents:

[0117] S100: When a voice instruction is received, convert the voice instruction into semantic information according to a preset format.

[0118] When a user inputs a voice command into the display device 200, the display device 200 can obtain the voice command through the sound collector. After receiving the voice command, the display device 200 can perform preprocessing on the audio data corresponding to the voice command. The preprocessing can include noise reduction and cleaning. The noise reduction process can reduce noise interference in the voice command, and the cleaning process can eliminate content in the voice command that is irrelevant to the text corresponding to the voice command, such as interjections such as "ah", "oh", and "ya", thereby improving the accuracy of subsequent voice recognition.

[0119] After pre-processing the voice command, the controller 250 may convert the voice command into semantic information according to a preset format, such as Figure 7 As shown, the preset format can be JSON format, and the semantic information in JSON format can include a command field and a queryText field, wherein the command field is the target instruction string of the voice instruction, which is used to determine whether the application can execute the voice instruction, and the queryText field is the text corresponding to the voice instruction obtained according to the voice instruction recognition. Exemplarily, the command field is connector.device.command.Media fast_forward, indicating that the voice instruction is a fast-forward operation instruction. Exemplarily, the queryText field is Skip ahead 7minutes, which means fast forward 7 minutes. It should be noted that the above is only an exemplary description in English. In actual application, the language of the queryText field can be switched according to actual needs.

[0120] In some embodiments, the controller 250 can parse the voice instructions through a speech recognition model. For example, the controller 250 can call the automatic speech recognition (ASR) model at the system layer to convert the voice instructions into text corresponding to the voice instructions, for example, converting "fast forward play" in voice format into "fast forward play" in text format.

[0121] S200: Searching for the target instruction string in the instruction string set of the target application.

[0122] The target application is an application that has registered a voice recognition function in the display device 200. When the target application is started and supports voice recognition, it can send a voice recognition registration request to the display device 200 to register the voice recognition function in the display device 200, thereby performing voice recognition on the voice commands acquired by the display device 200 through the sound collector.

[0123] like Figure 8 As shown, in order to determine whether the target application can execute the application function corresponding to the voice command, the target application can send a set of target application command strings to the controller 250 after registering the voice recognition function. The set of command strings is used to represent the command strings corresponding to the application functions that the target application can execute. The display device 200 can receive the set of command strings based on the registered voice recognition function, so that the display device 200 can perform a validity determination on the voice command by searching the set of command strings for the target command string, thereby generating a determination result.

[0124] For example, when the target application is the HBBTV app, the command string set may include standard operation strings such as {"play", "pause", "fast_forward", "start_reverse", and "skip_ad"}. "play" is the command string corresponding to the video play function, "pause" is the command string corresponding to the video pause function, "fast_forward" is the command string corresponding to the video fast forward function, and "skip_ad" is the command string corresponding to the ad skip function. The set of these strings is the command string set for the target application.

[0125] After determining the instruction string set, the display device 200 may perform validity determination on the target instruction string according to the instruction string set, that is, search for the target instruction string in the instruction string set.

[0126] S300: When the target instruction string is not found in the instruction string set, generate an invalid result based on the target instruction string.

[0127] If the target instruction string is not found in the instruction string set, it means that the target application cannot recognize the voice instruction and thus cannot execute the application function corresponding to the voice instruction. Therefore, the display device 200 can generate an invalid result based on the target instruction string. For example, for the fast rewind instruction, the corresponding string in the instruction string set is "start_reverse". When the voice instruction input by the user is "start rewinding", the target instruction string is "start_rewinding". Although the voice instruction also means fast rewind, the target instruction string is "start_rewinding" in the instruction string set and does not match "start_reverse". Therefore, based on the target application, the display device 200 cannot recognize the voice instruction "start rewinding" as a fast rewind instruction. Therefore, the display device 200 can generate an invalid result based on the target instruction string "start_rewinding".

[0128] In some embodiments, when the display device 200 performs validity determination on the target instruction string according to the instruction string set, if the target instruction string is identified as an empty string, it means that the voice instruction cannot be recognized and an invalid result can still be generated.

[0129] S400: When the determination result is an invalid result, determine a target voice instruction in a voice instruction library of the target application according to the invalid result and the text corresponding to the voice instruction.

[0130] If the result is invalid, it means that the voice command input by the user cannot accurately match the text content corresponding to the voice command preset by the application. Therefore, the display device 200 can perform secondary semantic recognition on the voice command through semantic recognition to improve the accuracy of the voice command.

[0131] To this end, the display device 200 can parse the semantic content of the text corresponding to the voice command based on the semantic understanding model of the BERT architecture, and then search the voice command library for the target voice command with the highest semantic content match. The voice command library is a database of voice template commands that the target application can respond to. Through the recognition method of semantic understanding, the accuracy of the display device 200 in recognizing voice commands through the target application can be improved.

[0132] For example, the voice command input by the user is "turn up the volume". By performing semantic understanding on the voice command, the display device 200 can determine that the voice command is a voice template command corresponding to the volume adjustment function. Therefore, the display device 200 can query the voice template command corresponding to the volume adjustment function in the voice command library. For example, the voice template instructions corresponding to the volume adjustment function may include "increase the volume" and "lower the volume", thereby further determining that the voice template instruction "increase the volume" that matches the voice command of "turn up the volume" is the target voice command.

[0133] S500: In response to a target voice instruction, controlling the target application to execute an application function corresponding to the target voice instruction.

[0134] Since the target application cannot execute the corresponding application function according to the pre-set voice instruction, after the display device 200 determines the target voice instruction from the voice instruction library, it can respond to the target voice instruction and control the target application to execute the application function corresponding to the target voice instruction.

[0135] Continuing with the example of step S400, the display device 200 can use the voice matching module to identify the voice template command "Increase volume" as the target voice command. The display device 200 can then send the target voice command to the HBBTV module of the application layer through the voice matching module. The HBBTV module can then send the target voice command to the HBBTV application for execution, thereby increasing the volume of the media data being played, thereby making the target voice command effective.

[0136] Based on the above technical solution, when the display device receives a voice command, it converts the voice command into semantic information, and determines the validity of the target command string through the command string set of the target application. When it is determined to be invalid, it automatically switches to the semantic matching mode of the text corresponding to the voice command, so as to determine the target voice command according to the text corresponding to the voice command in the voice command library, and control the application to execute the application function corresponding to the target voice command. This application solves the problem of recognition failure caused by the non-standard format of the user's voice command in the background technology by setting a semantic information conversion mechanism, a validity judgment mechanism based on the target application command string set, and enabling voice command library matching when the result is invalid. It ensures that even if the user's expression has grammatical deviations or non-standard terminology, it can still accurately trigger the application function of the target application, thereby improving the success rate of voice interaction.

[0137] In some embodiments, when a target instruction string is found in an instruction string set, Figure 9 As shown, the method may further include steps S600-S700.

[0138] S600: Generate a valid result based on the target instruction string.

[0139] When the display device 200 finds the target instruction string in the instruction string set, it indicates that the target application can directly execute the application function corresponding to the voice instruction. Therefore, the display device 200 can generate a valid result according to the target instruction string.

[0140] For example, Figure 10 As shown, when the command field is connector.device.command.Mediafast_forward, the command field can be queried in the command string set. Based on the above example, the command string set can include standard operation strings such as {"play", "pause", "fast_forward", "start_reverse", "skip_ad"}. Among them, "fast_forward" is the same as the command field, that is, the target command string can be queried in the command string set, so the display device 200 can generate a valid result.

[0141] S700: When the determination result is a valid result, mark the voice instruction as a target voice instruction.

[0142] When the judgment result is a valid result, the display device 200 does not need to search for the target voice instruction through the text corresponding to the voice instruction in the voice instruction library. It only needs to mark the voice instruction input by the user as the target voice instruction, and send the target voice instruction to the target application for execution response through the voice service module corresponding to the voice recognition function.

[0143] In some embodiments, as Figure 11 As shown, step S400 may further include steps S410-S420.

[0144] S410: Calculating the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction;

[0145] For example, taking the text corresponding to the voice command "I want to watch the movie XX" as an example, the display device 200 can perform word segmentation on the text corresponding to the voice command, breaking it into words such as "I," "want," "watch," "XX," and "movie." After the segmentation is completed, the display device 200 can extract key information of each voice template command from the voice command library to calculate the semantic matching degree between the text corresponding to the voice command and the voice template command.

[0146] In order to calculate the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction, the display device 200 can adopt a semantic matching algorithm based on word vectors. The semantic matching algorithm can map each word obtained by performing word segmentation on the text corresponding to the voice instruction into a high-dimensional vector space, so that the positions of words with similar semantics in the vector space are closer. For example, "watch" and "play" are semantically similar, and the vectors of the two words "watch" and "play" in the vector space will also have a certain degree of similarity.

[0147] Based on the semantic matching algorithm, the display device 200 can calculate the similarity between the vector of each word in the text corresponding to the voice instruction and the corresponding word vector in the voice template instruction, and then assign different weights to the words according to the importance of the words in the text corresponding to the voice instruction, so as to comprehensively calculate the overall semantic matching degree between the text corresponding to the voice instruction and the voice template instruction.

[0148] In some embodiments, the display device 200 can also adjust the semantic matching degree based on contextual information. For example, if the user has mentioned keywords or topics related to "movies" in previous voice commands, then when calculating the matching degree between the voice command "I want to watch the movie "××"" and the voice template command, the display device 200 can increase the weight of the word "movies" to more accurately reflect the user's intentions.

[0149] S420: Mark the voice instruction with the semantic matching degree greater than or equal to the matching degree threshold and the highest semantic matching degree as the target voice instruction.

[0150] After completing the calculation of the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction, the display device 200 needs to filter out the target voice instruction in the voice instruction library according to a preset matching degree threshold.

[0151] In the HBBTV video playback scenario, the display device 200 can set a reasonable matching threshold based on actual needs and experience, for example, a matching threshold of 0.7. After the display device 200 calculates the semantic matching between the text corresponding to the voice command and each voice template command, it will filter and compare these semantic matchings using the matching threshold.

[0152] The user issues the voice command "I want to watch the movie "××"". The system calculates that the semantic matching degree of this voice command with the voice template command "Play the movie "××"" is 0.9, the semantic matching degree with the voice template command "Pause the current video" is 0.1, the semantic matching degree with the voice template command "Fast forward 5 minutes" is 0.2, and the semantic matching degree with the voice template command "Search for comedy variety shows" is 0.05.

[0153] Display device 200 compares all semantic matching degrees with a preset matching threshold of 0.7, filtering out commands with matching degrees greater than or equal to 0.7. In the above example, only the semantic matching degree of 0.9 for "Play movie "XX"" exceeds the matching threshold of 0.7. Then, among these voice template commands that meet the threshold condition, the command with the highest semantic matching degree, namely "Play movie "XX"," is selected as the target voice command.

[0154] In some embodiments, if there are multiple voice template commands whose semantic matching degrees are greater than or equal to a threshold, the display device 200 will further compare the semantic matching degrees of the voice template commands and select the command with the highest matching degree as the target voice command. For example, if the user's voice command has a semantic matching degree of 0.9 with "Play the movie XX" and a semantic matching degree of 0.92 with "Play the Blu-ray version of XX", both of which are greater than the threshold of 0.7, the display device 200 will mark "Play the Blu-ray version of XX" as the target voice command.

[0155] Based on the above technical solution, this embodiment calculates the semantic match between the text corresponding to the voice command and the voice template command, and marks the voice command with the highest semantic match greater than or equal to the matching threshold as the target voice command. By setting a threshold mechanism, invalid matches with low similarity can be filtered out. The highest matching degree screening ensures that the display device can identify the target voice command from multiple candidate voice template commands, thereby improving the recognition accuracy of voice commands.

[0156] In some embodiments, see Figure 11 , step S300 may further include steps S330-S340.

[0157] S430: When the semantic matching degrees between all the voice template instructions in the voice instruction library and the text corresponding to the voice instruction are less than the matching degree threshold, generate prompt information for indicating that the voice instruction cannot be recognized.

[0158] The display device 200 can traverse the semantic matching degrees of all voice template instructions in the voice instruction library and the text corresponding to the voice instructions. If the semantic matching degrees are all less than the matching threshold, it means that there is no voice template instruction in the voice instruction library that matches the text corresponding to the voice instruction. Therefore, the display device 200 will generate a prompt message to indicate that the voice instruction cannot be recognized.

[0159] S440: Creating a prompt window in the user interface, and displaying the prompt information in the prompt window.

[0160] In some embodiments, the prompt information may be in text form, such as Figure 12As shown, the content of the prompt message may be "Sorry, your voice command cannot be recognized. Please re-enter." To facilitate displaying the prompt message to the user, the display device 200 may create a prompt window in the user interface. The display device 200 may display the prompt message in the prompt window to remind the user that the display device 200 cannot recognize the voice command.

[0161] In some embodiments, the prompt window can include various display effects, such as floating display, that is, canceling the display after a period of time, to prevent the prompt window from blocking the user interface for a long time. To reduce the obstruction of the user interface, the display device 200 can set the transparency of the prompt window so that the user can see the content of the user interface through the prompt window while viewing the prompt information.

[0162] In some embodiments, in addition to the prompt information, the display device 200 may also display guiding content in the prompt window, for example, "Please re-enter the voice command using a more standardized language" to guide the user to enter the voice command in a voice input method that the display device 200 can recognize.

[0163] In some embodiments, the prompt information may also be in audio form. After generating the prompt information, the display device 200 may play the prompt information through the audio output device 270 to prompt the user that the display device cannot recognize the voice command.

[0164] Based on the above technical solution, this embodiment generates a prompt message through an exception handling mechanism when the semantic matching degree between all voice template commands in the voice command library and the text corresponding to the voice command is less than the matching degree threshold. A visual prompt window is created in the user interface, and a prompt message is displayed in the prompt window to inform the user of the voice recognition failure. This avoids the situation where the user cannot know whether the input voice command is valid when the voice command fails silently, causing the user to repeatedly input invalid voice commands. This embodiment can guide the user to adjust the expression method or use other interaction methods through prompt information, thereby improving the convenience of voice interaction.

[0165] In some embodiments, in the process of calculating the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction as a whole, Figure 13 As shown, step S430 may include steps S431-S433.

[0166] S431: Perform semantic understanding on the text corresponding to the voice instruction through the semantic understanding model to obtain first semantic information.

[0167] During the process of calculating the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction, the controller 250 may call a semantic understanding model from the memory to perform semantic understanding on the text corresponding to the voice instruction using the semantic understanding model. The semantic understanding model may be a pre-trained semantic understanding model, and the display device 200 may perform in-depth analysis and processing on the text corresponding to the voice instruction using the semantic understanding model to extract first semantic information of the text corresponding to the voice instruction.

[0168] For example, if the text corresponding to the voice command is "jump to one minute to play the video", after inputting the text corresponding to the voice command into the semantic understanding model, the first semantic information obtained is "command=seek-content, anchor=start, offset=60)".

[0169] S432: Perform semantic understanding on the instruction text corresponding to the voice template instruction through the semantic understanding model to obtain second semantic information.

[0170] After obtaining the first semantic information, the controller 250 may continue to perform semantic understanding on the instruction text corresponding to the voice template instruction using the semantic understanding model. To this end, the controller 250 may input the instruction text corresponding to the voice template instruction into the semantic understanding model, so as to perform in-depth analysis and processing on the instruction text corresponding to the voice template instruction using the semantic understanding model to extract the second semantic information of the instruction text.

[0171] S433: Calculate the semantic matching degree between the first semantic information and the second semantic information.

[0172] After the first semantic information and the second semantic information are obtained, the semantic matching degree of the first semantic information and the second semantic information can be determined by calculating the similarity between the first semantic information and the second semantic information.

[0173] Based on the above technical solution, in this embodiment, the memory stores a semantic understanding model, which can be used to perform semantic understanding on the text corresponding to the voice instruction, thereby obtaining first semantic information. The semantic understanding model is then used to perform semantic understanding on the instruction text corresponding to the voice template instruction in the voice instruction library, obtaining second semantic information, thereby calculating the semantic matching degree between the first voice information and the second semantic information. Through a dual-path processing mechanism based on a pre-set semantic understanding model in the memory, the problem of amplified deviations between the first voice information and the second semantic information caused by heterogeneous algorithms is avoided.

[0174] In some embodiments, as Figure 14 As shown, step S500 may include steps S510-S520.

[0175] S510: Detect configuration parameters in the semantic information.

[0176] Configuration parameters are parameters used to represent the functions required to execute an application in a voice command. For adjusting playback progress, the configuration parameter can be the duration of the adjustment or the time point at which the progress needs to be adjusted. For a duration adjustment, the voice command might be "Play the video content after one minute," where the configuration parameter is one minute.

[0177] When the configuration parameter is a scenario where the time point of the set schedule needs to be adjusted, the voice command may be "play the video content from the third minute onwards", and the configuration parameter is the time point corresponding to the third minute.

[0178] In order to determine whether the display device 200 needs to execute the application function according to the configuration parameters in response to the voice command, after the display device 200 converts the voice command into semantic information, the configuration parameters in the semantic information can be detected.

[0179] S520: If the semantic information includes the configuration parameter, in response to the target voice instruction, execute the application function corresponding to the target voice instruction according to the configuration parameter.

[0180] Configuration parameters are related to the text content of the voice command. For example, when the voice command is "increase the volume," the semantic information corresponding to the voice command does not include a value for increasing the volume, or configuration parameters such as increasing the volume to a specific value. Therefore, the display device 200 cannot detect the configuration parameters in the voice command "increase the volume."

[0181] For another example, when the voice command is "increase volume by 10," the display device 200 can detect that the configuration parameter is "10" in the semantic information. If the semantic information includes the configuration parameter, the display device 200 can execute the application function corresponding to the target voice command according to the configuration parameter. For example, if the current volume is 5, the display device 200 responds to the target voice command "increase volume" and increases the volume corresponding to the target application to 15 according to the configuration parameter "10."

[0182] Based on the above technical solution, this embodiment adds detection and execution logic for configuration parameters in semantic information. When a voice command contains parameter configuration, the display device can automatically extract the parameter configuration and configure it into the execution item of the application function, so that the application function executes the application function according to the configuration parameters. This allows a single voice interaction to be executed according to the configuration parameters, thereby improving the accuracy of executing the voice command.

[0183] In some embodiments, after the display device 200 starts the application, it is necessary to register the voice recognition function for the application to facilitate subsequent voice recognition of the voice command. To this end, the display device 200 can start the application in response to the start-up instruction input by the user based on the application. After the display device 200 starts the application, a start-up event of the application is generated to indicate that the application has completed the startup. After the display device 200 detects the start-up event of the application, the display device 200 can register the voice recognition function of the application in the display device 200. After completing the registration of the voice recognition function of the application, the display device 200 can mark the application as a target application to indicate that the display device 200 can execute the application function corresponding to the voice instruction through the target application.

[0184] Based on the voice recognition function, the display device 200 can collect voice instructions for instructing the target application to perform a specified interactive action through a sound collector. The display device 200 can convert the voice instructions subsequently input by the user into semantic information through the voice recognition function, and then execute S200-S500 based on the semantic information to determine the target voice instruction, and send the target voice instruction to the target application to control the target application to perform the interactive action corresponding to the target voice instruction.

[0185] Based on the above technical solution, this embodiment establishes a dynamic registration mechanism for application voice functions, triggering the registration process for application voice recognition capabilities through startup commands. This dynamic registration mechanism for voice functions can mark an application as a target application when the application is started, ensuring that voice commands are targeted to the target application, preventing voice commands from being applied to applications that do not have registered voice recognition functions, ensuring the targeted execution capability of voice commands, and improving the accuracy of voice command responses.

[0186] In some embodiments, the display device 200 can also close the target application in response to a close instruction input by the user based on the target application. After the target application is closed, the display device 200 can deregister the voice recognition function of the target application in the display device 200 to release the system resources occupied by the voice recognition function. To this end, the display device 200 can detect a close event of the target application after responding to the close instruction, and the close event is used to characterize that the target application is in a closed state. After detecting the close event of the target application, the display device 200 can deregister the voice recognition function of the application and mark the target application as an application. This embodiment can prevent closed applications from continuously occupying the system resources of the display device through the voice recognition function, thereby freeing up system resources to use system resources for newly launched applications or already launched applications to perform voice recognition functions, improve the utilization of system resources, and ensure the real-time performance of voice response in multi-application switching scenarios.

[0187] Some embodiments of the present application also provide a method for voice command recognition, which is applied to a display device 200. To facilitate the execution of the method, the display device 200 includes at least a display 260, a sound collector, and a controller 250. The method includes:

[0188] S100: When a voice instruction is received, convert the voice instruction into semantic information according to a preset format.

[0189] The semantic information includes the target instruction character string and the text corresponding to the voice instruction;

[0190] S200: Searching for the target instruction string in the instruction string set of the target application.

[0191] Wherein, the target application is an application registered with a voice recognition function in the display device;

[0192] S300: When the target instruction string is not found in the instruction string set, generate an invalid result based on the target instruction string.

[0193] S400: Determine a target voice instruction in a voice instruction library of the target application according to the invalid result and the text corresponding to the voice instruction;

[0194] S500: In response to a target voice instruction, controlling the target application to execute an application function corresponding to the target voice instruction.

[0195] It can be seen from the above technical solution that the embodiment of the present application provides a display device and a voice instruction recognition method, which converts the voice instruction into semantic information containing a target instruction string and a text corresponding to the voice instruction according to a preset format when a voice instruction is received. Then, a validity judgment is performed on the target instruction string based on the instruction string set of the target application, and when the judgment result is an invalid result, the target voice instruction is determined in the voice instruction library of the target application based on the text corresponding to the voice instruction, thereby controlling the target application to execute the application function corresponding to the target voice instruction. The present application can expand the judgment scope of voice instructions by setting a semantic information conversion mechanism, a validity judgment mechanism based on the target application instruction string set, and enabling voice instruction library matching when an invalid result is obtained, thereby improving the accuracy of voice instruction recognition.

[0196] The same and similar parts between the various embodiments in this specification can be referenced to each other and will not be repeated here.

[0197] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus a necessary general-purpose hardware platform. Based on this understanding, the technical solutions in the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention or certain portions of the embodiments.

[0198] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

[0199] For ease of explanation, the above description has been made with reference to specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Based on the above teachings, various modifications and variations are possible. The above embodiments are selected and described to better explain the principles and practical applications, so that those skilled in the art can better utilize the embodiments and various different variations of the embodiments suitable for specific use considerations.

Claims

1. A display device, characterized in that: include: a display configured to display a user interface; a sound collector configured to receive voice commands; The controller is configured as: When a voice command is received, converting the voice command into semantic information according to a preset format, the semantic information including a target command string and a text corresponding to the voice command; Searching for the target instruction string in an instruction string set of a target application, where the target application is an application registered with a speech recognition function in the display device; If the target instruction string is not found in the instruction string set, generating an invalid result based on the target instruction string; Determining a target voice instruction in a voice instruction library of the target application according to the invalid result and the text corresponding to the voice instruction, wherein the voice instruction library stores a preset number of voice template instructions executable by the target application; In response to a target voice instruction, the target application is controlled to execute an application function corresponding to the target voice instruction.

2. The display device according to claim 1, wherein In a case where the target instruction string is found in the instruction string set, the controller is further configured to: Generate a valid result based on the target instruction string; If the determination result is a valid result, the voice instruction is marked as a target voice instruction.

3. The display device according to claim 1, wherein Before executing the step of searching the target instruction string in the instruction string set of the target application, the controller is further configured to: Based on the registered speech recognition function, the instruction character string set sent by the target application corresponding to the speech recognition function is received.

4. The display device according to claim 1, wherein The voice instruction library includes a preset number of voice template instructions, and the controller determines a target voice instruction in the voice instruction library of the target application according to the invalid result and the text corresponding to the voice instruction, and is specifically configured as follows: Calculating the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction; The voice template instruction whose semantic matching degree is greater than or equal to the matching degree threshold and whose semantic matching degree is the highest is marked as the target voice instruction.

5. The display device according to claim 4, wherein: The controller is further configured to: When the semantic matching degree between all the voice template instructions in the voice instruction library and the voice text is less than the matching degree threshold, generating prompt information for indicating that the voice instruction cannot be recognized; A prompt window is created in the user interface, and the prompt information is displayed in the prompt window.

6. The display device according to claim 4, wherein: The system further includes a memory configured to store a semantic understanding model, and the controller calculates the semantic matching degree between the text corresponding to the voice instruction and the voice template instruction, specifically configured to: Performing semantic understanding on the text corresponding to the voice instruction using the semantic understanding model to obtain first semantic information; Performing semantic understanding on the instruction text corresponding to the voice template instruction by the semantic understanding model to obtain second semantic information; Calculate the semantic matching degree between the first semantic information and the second semantic information.

7. The display device according to claim 1, wherein The controller controls the target application to execute an application function corresponding to the target voice instruction in response to the target voice instruction, and is specifically configured to: Detecting configuration parameters in the semantic information, where the configuration parameters are used to represent parameters for executing application functions of the target application; If the semantic information includes the configuration parameters, then in response to the target voice instruction, the application function corresponding to the target voice instruction is executed according to the configuration parameters.

8. The display device according to claim 1, wherein The controller is further configured to: In response to a startup instruction input by a user based on the application, starting the application; After detecting a startup event of the application, registering a speech recognition function of the application in the display device; After registering the speech recognition function of the application, marking the application as the target application; Based on the voice recognition function, the voice collector collects voice instructions for instructing the target application to perform a specified interactive action.

9. The display device according to claim 8, wherein The controller is further configured to: closing the target application in response to a closing instruction input by a user based on the target application; After detecting a closing event of the target application, deregistering a speech recognition function of the application in the display device; After deregistering the speech recognition function of the application, the target application is marked as the application.

10. A method for voice command recognition, characterized in that: Applied to a display device, the display device includes a display configured to display a user interface; a sound collector configured to receive voice commands; Controller; the method comprising: When a voice command is received, converting the voice command into semantic information according to a preset format, wherein the semantic information includes a target command string and a text corresponding to the voice command; Searching for the target instruction string in an instruction string set of a target application, where the target application is an application registered with a speech recognition function in the display device; If the target instruction string is not found in the instruction string set, generating the invalid result based on the target instruction string; Determining a target voice instruction in a voice instruction library of the target application according to the invalid result and the text corresponding to the voice instruction, wherein the voice instruction library stores a preset number of voice template instructions executable by the target application; In response to a target voice instruction, the target application is controlled to execute an application function corresponding to the target voice instruction.

Images