Display device, text error correction method and server

Abstract

The embodiment of the present application provides a display device, a text correction method and a server, wherein the display device includes a display and a controller, wherein the controller is configured to: in response to receiving a voice command input by a user, perform voice conversion on the voice command to obtain a text to be corrected; control the display to display the text to be corrected; correct the text to be corrected based on a similar sound-shape confusion set and a graph attention mechanism to obtain an initial correction text, perform candidate recall on the text to be corrected and the initial correction text, and obtain a final correction text based on the sorting results of the recalled texts; and control the display to refresh the text to be corrected to the final correction text. The embodiment of the present application generates a pronunciation-similar knowledge graph and a shape-similar knowledge graph based on the confusion set corresponding to the text to be corrected, integrates the pinyin and glyph-related knowledge of Chinese characters into a graph neural network, extracts deep semantic information between similar characters, and can effectively utilize the knowledge of similar sound and shape to improve the accuracy and recall rate of error detection and correction.

Description

Technical Field

[0001] The present application relates to the technical field of display devices, and in particular to a display device, a text error correction method, and a server. Background Art

[0002] With the development of computers, big data, and machine learning, spelling correction technology has been widely applied in a wide range of fields, including Chinese and English input methods, document editing tools, search tools, optical character recognition (OCR), and speech recognition. Spelling correction technology was first proposed for English, the most widely used language globally. After decades of development, rule-based, statistical, and feature-based techniques have emerged, achieving impressive accuracy. In comparison, Chinese spelling correction, due to its later development, the greater complexity of Chinese compared to English, and the relatively low investment in research, currently offers lower performance and accuracy, and fewer mature and usable tools.

[0003] The accuracy of Chinese input data is a fundamental prerequisite for common natural language processing tasks and is crucial for improving the performance of upper-layer applications. Among related technologies, LSTM+CRF-based error detection techniques are limited by their reliance on large numbers of labeled samples, making them difficult to implement widely. N-gram-based error detection techniques also suffer from poor algorithmic performance due to their rigid discrimination rules, resulting in low error detection efficiency. Summary of the Invention

[0004] To solve the above technical problems, the present application provides a display device, a text error correction method and a server.

[0005] In a first aspect, the present application provides a display device, comprising:

[0006] monitor;

[0007] A controller is connected to the display, and the controller is configured to:

[0008] In response to receiving a voice command input by a user, performing voice conversion on the voice command to obtain a text to be corrected;

[0009] Controlling the display to display the text to be corrected;

[0010] Correcting the text to be corrected based on a confusion set of similar sound and form and a graph attention mechanism to obtain an initial corrected text;

[0011] Perform candidate recall on the text to be corrected and the initial correction text, and obtain the final correction text according to the sorting result of the recalled texts;

[0012] The display is controlled to refresh the text to be corrected into the final text to be corrected.

[0013] In some embodiments, the correcting the text to be corrected based on the sound-shape confusion set and graph attention mechanism includes:

[0014] Perform feature extraction on the text to be corrected to obtain the initial representation matrix;

[0015] Creating an adjacency matrix for each character in the text to be corrected based on a confusion set of similar sound and form;

[0016] Inputting the initial representation matrix and the adjacency matrix into a multi-layer graph convolutional neural network to obtain a next-layer representation matrix;

[0017] Obtaining the last layer representation matrix of the multi-layer graph convolutional neural network according to the graph attention mechanism;

[0018] Generate characters through a fully connected layer and a probability normalization function.

[0019] In some embodiments, the step of creating an adjacency matrix for each character in the text to be corrected based on the sound-shape confusion set includes:

[0020] Obtaining, for each character in the text to be corrected, characters with similar pronunciations and characters with similar shapes in a similar pronunciation-shape confusion set;

[0021] Using the characters in the text to be corrected, the characters with similar pronunciations, and the characters in the character library as nodes and the relationships between the characters as edges to establish a pronunciation similarity adjacency matrix;

[0022] The characters in the text to be corrected, the characters with similar shapes and the characters in the character library are used as nodes, and the relationships between the characters are used as edges to establish a shape-similar adjacency matrix.

[0023] In some embodiments, inputting the initial representation matrix and the adjacency matrix into a multi-layer graph convolutional neural network to obtain a next-layer representation matrix includes:

[0024] Adding the adjacency matrix to the identity matrix to obtain an adjacency estimate matrix;

[0025] Calculating a diagonal matrix corresponding to the adjacency estimation matrix to obtain a diagonal estimation matrix;

[0026] A next-layer representation matrix is ​​obtained according to the adjacency estimation matrix, the diagonal estimation matrix and the initial representation matrix.

[0027] In some embodiments, obtaining the last layer representation matrix of the multi-layer graph convolutional neural network according to the graph attention mechanism includes:

[0028] Use the attention mechanism to calculate the attention representation matrix of knowledge fusion;

[0029] The final layer representation matrix is ​​obtained according to the sum of the attention representation matrix and each layer representation matrix.

[0030] In a second aspect, an embodiment of the present application provides a text error correction method for a display device, the method comprising:

[0031] Based on the similar sound-form confusion set and graph attention mechanism, the correction text is corrected to obtain the initial correction text.

[0032] Performing candidate recall on the text to be corrected and the initial correction text to obtain a recalled text;

[0033] The recalled texts are sorted, and a final correction text corresponding to the text to be corrected is obtained according to the sorting result.

[0034] In a third aspect, an embodiment of the present application provides a server, which is configured to:

[0035] receiving a text to be corrected from a display device;

[0036] Correct the text to be corrected based on the similar sound-form confusion set and graph attention mechanism to obtain the initial corrected text.

[0037] Perform candidate recall on the text to be corrected and the initial correction text, and obtain the final correction text according to the sorting result of the recalled texts;

[0038] The final error-corrected text is sent to the display device.

[0039] The display device, text error correction method, and server provided by this application have the following beneficial effects:

[0040] The embodiment of the present application generates a pronunciation-similar knowledge graph and a shape-similar knowledge graph based on the confusion set corresponding to the text to be corrected, integrates the pinyin and glyph-related knowledge of Chinese characters into the graph neural network, extracts the deep semantic information between similar characters, and can effectively utilize the knowledge of similar pronunciation and shape to improve the accuracy and recall rate of error detection and correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 Schematic diagram showing an operation scenario between a display device and a control apparatus according to some embodiments;

[0043] Figure 2exemplarily shows a hardware configuration block diagram of a display device 200 according to some embodiments;

[0044] Figure 3 exemplarily shows a hardware configuration block diagram of the control device 100 according to some embodiments;

[0045] Figure 4 exemplarily shows a schematic diagram of software configuration in the display device 200 according to some embodiments;

[0046] Figure 5 exemplarily shows a schematic diagram of an icon control interface display of an application in a display device 200 according to some embodiments;

[0047] Figure 6 hereinafter is a schematic diagram showing an overall process of text error correction according to some embodiments;

[0048] Figure 7 hereinafter is a flowchart of a text error correction method according to some embodiments;

[0049] Figure 8 hereinafter is a schematic diagram showing a structure of an end-to-end error detection and correction model according to some embodiments;

[0050] Figure 9 hereinafter is a flow chart showing a method for parsing a text to be corrected according to some embodiments;

[0051] Figure 10 hereinafter is a flow chart showing a method for creating an adjacency matrix according to some embodiments;

[0052] Figure 11 Schematic diagram of a voice interaction interface according to some embodiments is exemplarily shown in FIG;

[0053] Figure 12 Schematic diagram of a voice interaction interface according to some embodiments is exemplarily shown in FIG;

[0054] Figure 13 Schematic diagram of a voice interaction interface according to some embodiments is exemplarily shown in FIG. DETAILED DESCRIPTION

[0055] In order to make the purpose, implementation mode and advantages of the present application clearer, the exemplary implementation mode of the present application will be clearly and completely described below in conjunction with the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0056] All other embodiments derived by persons of ordinary skill in the art based on the exemplary embodiments described herein without inventive effort are within the scope of protection of the claims appended hereto. Furthermore, although the disclosure herein is presented based on one or more exemplary embodiments, it should be understood that each aspect of the disclosure may constitute a complete embodiment on its own.

[0057] 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.

[0058] In the specification and claims of this application and the 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 precedence, unless otherwise indicated. It should be understood that the terms used in this manner are interchangeable under appropriate circumstances, for example, the embodiments of this application can be implemented in an order other than those shown or described in the drawings.

[0059] In addition, the terms "comprises" and "comprising" 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 those components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0060] The term "module" as used in this application 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 functions associated with that element.

[0061] The term "remote control" as used in this application refers to a component of an electronic device (such as the display device disclosed in this application) that can wirelessly control the electronic device, typically over a short distance. It typically connects to the electronic device using infrared and / or radio frequency (RF) signals and / or Bluetooth, and may also include functional modules such as WiFi, wireless USB, Bluetooth, and motion sensors. For example, a handheld touch remote control replaces most of the physical built-in hard keys in a typical remote control device with a user interface on a touch screen.

[0062] The term "gesture" used in this application refers to a user's behavior of expressing an intended idea, action, purpose, or result through a change in hand shape or hand movement.

[0063] Figure 1FIG2 is a schematic diagram showing an operation scenario between a display device and a control device according to an embodiment. Figure 1 As shown in FIG, a user can operate the display device 200 through the mobile terminal 300 and the control apparatus 100 .

[0064] In some embodiments, the control device 100 may be a remote control. Communication between the remote control and the display device may include infrared protocol communication, Bluetooth protocol communication, or other short-range communication methods, thereby controlling the display device 200 wirelessly or through wired methods. A user may control the display device 200 by inputting user commands through buttons on the remote control, voice input, control panel input, and the like. For example, a user may control the display device 200 by inputting corresponding control commands through the volume up / down keys, channel control keys, up / down / left / right movement keys, voice input keys, menu keys, power on / off keys, and the like on the remote control.

[0065] In some embodiments, a mobile terminal, tablet computer, computer, laptop computer, or other smart device can also be used to control the display device 200. For example, an application running on the smart device can be used to control the display device 200. The application can be configured to provide the user with various controls in an intuitive user interface (UI) on a screen associated with the smart device.

[0066] In some embodiments, the mobile terminal 300 can install software applications on the display device 200 and establish communication via a network communication protocol, enabling one-to-one control operations and data communication. For example, a control command protocol can be established between the mobile terminal 300 and the display device 200, synchronizing a remote control keyboard to the mobile terminal 300, and controlling the user interface on the mobile terminal 300 to control the display device 200. Alternatively, audio and video content displayed on the mobile terminal 300 can be transmitted to the display device 200 for synchronized display.

[0067] like Figure 1 It is also shown that 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. The server 400 may provide various content and interactions to the display device 200. For example, the display device 200 receives software program updates or accesses a remotely stored digital media library by sending and receiving information and interacting with an electronic program guide (EPG). The server 400 may be a cluster or multiple clusters, and may include one or more types of servers. Other network service content such as video on demand and advertising services is provided through the server 400.

[0068] The display device 200 can be a liquid crystal display, an OLED display, or a projection display device. The specific display device type, size, and resolution are not limited. Those skilled in the art will appreciate that the display device 200 can be modified in terms of performance and configuration as needed.

[0069] In addition to providing broadcast reception television functions, the display device 200 may also provide intelligent network television functions with computer support functions, including but not limited to network television, smart TV, Internet Protocol television (IPTV), etc.

[0070] Figure 2 exemplarily shows a hardware configuration block diagram of the display device 200 according to an exemplary embodiment.

[0071] In some embodiments, the display device 200 includes at least one of a controller 250, a tuner and demodulator 210, a communicator 220, a detector 230, an input / output interface 255, a display 275, an audio output interface 285, a memory 260, a power supply 290, a user interface 265, and an external device interface 240.

[0072] In some embodiments, the display 275 is a component for receiving the image signal output from the first processor and displaying video content and images as well as a menu control interface.

[0073] In some embodiments, the display 275 includes a display screen component for presenting images and a driving component for driving image display.

[0074] In some embodiments, the displayed video content may be from broadcast television content, or various broadcast signals received via wired or wireless communication protocols, or various image content received from a network server via a network communication protocol.

[0075] In some embodiments, the display 275 is used to present a user manipulation UI interface generated in the display device 200 and used to control the display device 200 .

[0076] In some embodiments, depending on the type of display 275 , a driving component for driving the display is also included.

[0077] In some embodiments, the display 275 is a projection display and may further include a projection device and a projection screen.

[0078] In some embodiments, the communicator 220 is a component for communicating with external devices or external servers according to various communication protocols. For example, the communicator may include at least one of a Wi-Fi chip, a Bluetooth communication protocol chip, a wired Ethernet communication protocol chip, or other network communication protocol chip or a near-field communication protocol chip, as well as an infrared receiver.

[0079] In some embodiments, the display device 200 may establish transmission and reception of control signals and data signals with the external control apparatus 100 or the content providing apparatus through the communicator 220 .

[0080] In some embodiments, the user interface 265 may be configured to receive infrared control signals from the control device 100 (eg, an infrared remote controller, etc.).

[0081] In some embodiments, the detector 230 is a signal used by the display device 200 to collect external environment or interact with the outside.

[0082] In some embodiments, the detector 230 includes a light receiver, a sensor for collecting ambient light intensity, and can adaptively display parameter changes by collecting ambient light.

[0083] In some embodiments, the detector 230 may also include an image collector, such as a camera, a camera, etc., which can be used to collect external environment scenes, as well as to collect user attributes or gestures for interacting with the user. It can adaptively change display parameters and recognize user gestures to realize the function of interacting with the user.

[0084] In some embodiments, the detector 230 may further include a temperature sensor, such as by sensing the ambient temperature.

[0085] In some embodiments, the display device 200 can adaptively adjust the color temperature of the image displayed. For example, when the temperature is high, the display device 200 can be adjusted to display a cooler color temperature image, or when the temperature is low, the display device 200 can be adjusted to display a warmer color temperature image.

[0086] In some embodiments, the detector 230 may also be a sound collector, such as a microphone, for receiving the user's voice, illustratively including a voice signal of a user's control command for controlling the display device 200, or collecting ambient sound for identifying the type of ambient scene, so that the display device 200 can adaptively adapt to the ambient noise.

[0087] In some embodiments, as Figure 2 As shown, the input / output interface 255 is configured to perform data transmission between the controller 250 and other external devices or other controllers 250, such as receiving video signal data and audio signal data, or command instruction data from external devices.

[0088] In some embodiments, the external device interface 240 may include, but is not limited to, any one or more interfaces such as a high-definition multimedia interface (HDMI), an analog or digital high-definition component input interface, a composite video input interface, a USB input interface, an RGB port, etc. Alternatively, multiple interfaces may be combined to form a composite input / output interface.

[0089] In some embodiments, as Figure 2 As shown, the tuner-demodulator 210 is configured to receive broadcast television signals through wired or wireless reception, and can perform modulation and demodulation processing such as amplification, mixing and resonance, and demodulate audio and video signals from multiple wireless or wired broadcast television signals. The audio and video signals may include television audio and video signals carried in the television channel frequency selected by the user, as well as EPG data signals.

[0090] In some embodiments, the frequency demodulated by the tuner-demodulator 210 is controlled by the controller 250, which can send a control signal based on the user's selection to enable the modem to respond to the TV signal frequency selected by the user and modulate and demodulate the TV signal carried by the frequency.

[0091] In some embodiments, broadcast television signals can be classified as terrestrial broadcast signals, cable broadcast signals, satellite broadcast signals, or Internet broadcast signals based on the broadcast format of the television signal. Alternatively, they can be classified as digital modulation signals, analog modulation signals, etc. based on the modulation type. Alternatively, they can be classified as digital signals, analog signals, etc. based on the type of signal.

[0092] In some embodiments, the controller 250 and the tuner / demodulator 210 may be located in different separate devices, that is, the tuner / demodulator 210 may be located in an external device of the main device where the controller 250 is located, such as an external set-top box. In this way, the set-top box modulates and demodulates the received broadcast television signal into television audio and video signals and outputs them to the main device, which then receives the audio and video signals via the first input / output interface.

[0093] In some embodiments, controller 250 controls the operation of the display device and responds to user operations via various software control programs stored in memory. Controller 250 can control the overall operation of display device 200. For example, in response to receiving a user command to select a UI object for display on display 275, controller 250 can perform operations related to the object selected by the user command.

[0094] In some embodiments, the object can be any one of selectable objects, such as a hyperlink or an icon. Operations related to the selected object, for example, displaying a page, document, image connected to the hyperlink, or executing a program corresponding to the icon. User commands for selecting UI objects can be commands input through various input devices connected to the display device 200 (e.g., a mouse, keyboard, touchpad, etc.) or voice commands corresponding to voice spoken by the user.

[0095] like Figure 2 As shown, the controller 250 includes at least one of a random access memory 251 (RAM), a read-only memory 252 (ROM), a video processor 270, an audio processor 280, other processors 253 (e.g., a graphics processing unit (GPU), a central processing unit (CPU) 254), a communication interface (Communication Interface), and a communication bus 256 (Bus). The communication bus connects the various components.

[0096] In some embodiments, RAM 251 is used to store temporary data for the operating system or other running programs.

[0097] In some embodiments, ROM 252 is used to store various system startup instructions.

[0098] In some embodiments, ROM 252 is used to store a basic input / output system, called a Basic Input / Output System (BIOS), which is used to perform a power-on self-test of the system, initialize various functional modules in the system, provide basic input / output drivers for the system, and boot the operating system.

[0099] In some embodiments, upon receiving a power-on signal, the display device 200 starts up, and the CPU executes system startup instructions in the ROM 252, copying temporary operating system data stored in the memory to the RAM 251 to facilitate booting or running the operating system. After the operating system boot is complete, the CPU copies temporary data for various application programs in the memory to the RAM 251 to facilitate booting or running the various application programs.

[0100] In some embodiments, the CPU processor 254 is configured to execute operating system and application instructions stored in the memory, and to execute various applications, data, and content based on various interactive instructions received from external input, so as to ultimately display and play various audio and video content.

[0101] In some exemplary embodiments, the CPU processor 254 may include multiple processors. The multiple processors may include a main processor and one or more sub-processors. The main processor is used to perform certain operations of the display device 200 in pre-power mode and / or display images in normal mode. The one or more sub-processors are used to perform certain operations in states such as standby mode.

[0102] In some embodiments, the graphics processor 253 is used to generate various graphical objects, such as icons, operation menus, and graphics displayed in response to user input commands. It includes an operator that performs operations based on various user interaction commands and displays various objects according to display attributes. It also includes a renderer that renders the various objects generated by the operator. These rendered objects are then displayed on the display.

[0103] In some embodiments, the video processor 270 is configured to receive an external video signal and perform video processing such as decompression, decoding, scaling, noise reduction, frame rate conversion, resolution conversion, image synthesis, etc. according to the standard codec protocol of the input signal, and obtain a signal that can be directly displayed or played on the display device 200.

[0104] In some embodiments, the video processor 270 includes a demultiplexing module, a video decoding module, an image synthesis module, a frame conversion module, a display formatting module, and the like.

[0105] Among them, the demultiplexing module is used to demultiplex the input audio and video data stream. For example, if MPEG-2 is input, the demultiplexing module demultiplexes it into video signals and audio signals.

[0106] The video decoding module is used to process the demultiplexed video signal, including decoding and scaling.

[0107] The image synthesis module, such as an image synthesizer, is used to superimpose and mix the GUI signal generated by the graphics generator according to user input or itself with the scaled video image to generate an image signal for display.

[0108] The frame conversion module is used to convert the input video frame rate, such as converting the 60Hz frame rate to the 120Hz frame rate or the 240Hz frame rate. The usual format is implemented by using a frame insertion method.

[0109] The display formatting module is used to convert the received frame number into a video output signal and change the signal to conform to the display format, such as outputting an RGB data signal.

[0110] In some embodiments, the graphics processor 253 can be integrated with the video processor or can be separately configured. When integrated, it can perform processing of the graphics signals output to the display. When separately configured, it can perform different functions separately, such as a GPU+FRC (Frame Rate Conversion) architecture.

[0111] In some embodiments, the audio processor 280 is used to receive an external audio signal, and perform decompression and decoding, as well as noise reduction, digital-to-analog conversion, and amplification processing according to the standard codec protocol of the input signal to obtain a sound signal that can be played in a speaker.

[0112] In some embodiments, the video processor 270 may include one or more chips. The audio processor may also include one or more chips.

[0113] In some embodiments, the video processor 270 and the audio processor 280 may be separate chips, or may be integrated with the controller into one or more chips.

[0114] In some embodiments, the audio output receives the sound signal output by the audio processor 280 under the control of the controller 250, such as: the speaker 286, and in addition to the speaker carried by the display device 200 itself, can be output to the external audio output terminal of the sound-emitting device of the external device, such as: an external audio interface or a headphone interface, etc., and can also include a short-range communication module in the communication interface, for example: a Bluetooth module for Bluetooth speaker sound output.

[0115] The power supply 290, under the control of the controller 250, uses the power input from the external power source to provide power supply support for the display device 200. The power supply 290 can include a built-in power supply circuit installed inside the display device 200, or it can be installed externally to the display device 200 and provide a power interface for the display device 200 to connect to an external power source.

[0116] The user interface 265 is used to receive user input signals and then send the received user input signals to the controller 250. The user input signals may be remote control signals received by an infrared receiver or various user control signals received by a network communication module.

[0117] In some embodiments, the user inputs a user command through the control device 100 or the mobile terminal 300 , the user input interface is based on the user input, and the display device 200 responds to the user input through the controller 250 .

[0118] In some embodiments, the user may input a user command through a graphical user interface (GUI) displayed on the display 275, and the user input interface receives the user input command through the graphical user interface (GUI). Alternatively, the user may input a user command through a specific sound or gesture, and the user input interface may recognize the sound or gesture through a sensor to receive the user input command.

[0119] In some embodiments, a "user interface" is a medium interface for interaction and information exchange between an application or operating system and a user, which realizes the conversion between the internal form of information and the form acceptable to the user. A common form of user interface is a graphical user interface (GUI), which refers to a user interface related to computer operations that is displayed in a graphical manner. It can be an interface element such as an icon, window, or control displayed on the display screen of an electronic device, where a control can include visual interface elements such as icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, and widgets.

[0120] The memory 260 stores various software modules for driving the display device 200. For example, the various software modules stored in the first memory include at least one of a basic module, a detection module, a communication module, a display control module, a browser module, and various service modules.

[0121] The basic module is a low-level software module used to communicate signals between various hardware components in the display device 200 and send processing and control signals to upper-level modules. The detection module is a management module used to collect various information from various sensors or user input interfaces, perform digital-to-analog conversion, and perform analysis and management.

[0122] For example, the speech recognition module includes a speech parsing module and a speech command database module. The display control module is used to control the display to display image content and can be used to play multimedia image content and UI interface information. The communication module is used to control and communicate data with external devices. The browser module is used to perform data communication between browsing servers. The service module is used to provide various services and various applications. Memory 260 is also used to store received external data and user data, images of various items in the user interface, and visual effects of focus objects.

[0123] Figure 3Schematically shows a block diagram of the configuration of the control device 100 according to an exemplary embodiment. Figure 3 As shown, the control device 100 includes a controller 110, a communication interface 130, a user input / output interface, a memory, and a power supply.

[0124] The control device 100 is configured to control the display device 200 and receive user input commands. It converts these commands into commands that the display device 200 can recognize and respond to, acting as an intermediary for interaction between the user and the display device 200. For example, a user operates the channel up / down keys on the control device 100, and the display device 200 responds to these channel up / down operations.

[0125] In some embodiments, the control device 100 may be a smart device. For example, the control device 100 may be installed with various applications for controlling the display device 200 according to user needs.

[0126] In some embodiments, as Figure 1 As shown, after installing the application for controlling the display device 200, the mobile terminal 300 or other intelligent electronic device can perform similar functions to the control device 100. For example, the user can install the application and use various function keys or virtual buttons of the graphical user interface provided on the mobile terminal 300 or other intelligent electronic device to realize the functions of the physical buttons of the control device 100.

[0127] The controller 110 includes a processor 112, RAM 113, ROM 114, a communication interface 130, and a communication bus. The controller is used to control the operation and performance of the control device 100, as well as the communication and coordination between internal components and external and internal data processing functions.

[0128] Under the control of the controller 110, the communication interface 130 communicates control signals and data signals with the display device 200. For example, it transmits received user input signals to the display device 200. The communication interface 130 may include at least one of a WiFi chip 131, a Bluetooth module 132, an NFC module 133, or other near-field communication modules.

[0129] The user input / output interface 140 includes at least one of a microphone 141, a touchpad 142, a sensor 143, a keypad 144, and other input interfaces. For example, a user can input user commands through voice, touch, gestures, pressing, and other actions. The input interface converts received analog signals into digital signals, and then converts the digital signals into corresponding command signals, which are then sent to the display device 200.

[0130] The output interface includes an interface for transmitting received user commands to the display device 200. In some embodiments, this can be either an infrared interface or a radio frequency interface. For example, in an infrared signal interface, user input commands need to be converted into infrared control signals according to an infrared control protocol and then transmitted to the display device 200 via an infrared transmission module. Alternatively, in a radio frequency signal interface, user input commands need to be converted into digital signals, modulated according to a radio frequency control signal modulation protocol, and then transmitted to the display device 200 via a radio frequency transmission terminal.

[0131] In some embodiments, the control device 100 includes at least one of a communication interface 130 and an input / output interface 140. The control device 100 is configured with the communication interface 130, such as a WiFi, Bluetooth, or NFC module, to encode user input commands via the WiFi protocol, Bluetooth protocol, or NFC protocol and transmit them to the display device 200.

[0132] The memory 190 is used to store various operating programs, data and applications for driving and controlling the control device 200 under the control of the controller. The memory 190 can store various control signal instructions input by the user.

[0133] The power supply 180 is used to provide operating power support for various components of the control device 100 under the control of the controller. It can be a battery and related control circuits.

[0134] In some embodiments, the system may include a kernel, a command parser (shell), a file system, and applications. The kernel, shell, and file system together form the basic operating system structure, allowing users to manage files, run programs, and use the system. After power is applied, the kernel boots up, activates kernel space, abstracts hardware, initializes hardware parameters, and runs and maintains virtual memory, a scheduler, signals, and inter-process communication (IPC). After the kernel boots up, the shell and user applications are loaded. After booting up, the application is compiled into machine code, forming a process.

[0135] See also Figure 4 In some embodiments, the system is divided into four layers, from top to bottom: the application layer (referred to as the "application layer"), the application framework layer (referred to as the "framework layer"), the Android runtime and system library layer (referred to as the "system runtime library layer"), and the kernel layer.

[0136] In some embodiments, at least one application runs in the application layer. These applications may be window programs, system settings programs, clock programs, camera applications, etc. that come with the operating system; or they may be applications developed by third-party developers, such as hi-view programs, karaoke programs, and magic mirror programs. In specific implementations, the application packages in the application layer are not limited to the above examples and may actually include other application packages, which are not limited in this embodiment of the present application.

[0137] The framework layer provides application programming interfaces (APIs) and a programming framework for applications in the application layer. 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.

[0138] like Figure 4 As shown, in the embodiment of the present application, the application framework layer includes managers, content providers, etc., wherein the manager includes at least one of the following modules: an activity manager (ActivityManager) is used to interact with all activities running in the system; a location manager (Location Manager) is used to provide system services or applications with access to system location services; a package manager (Package Manager) is used to retrieve various information related to the application packages currently installed on the device; a notification manager (NotificationManager) is used to control the display and clearing of notification messages; a window manager (Window Manager) is used to manage icons, windows, toolbars, wallpapers, and desktop widgets on the user interface.

[0139] In some embodiments, the activity manager is used to: manage the life cycle of each application and the usual navigation back function, such as controlling the exit of the application (including switching the user interface currently displayed in the display window to the system desktop), opening, backing (including switching the user interface currently displayed in the display window to the upper-level user interface of the currently displayed user interface), etc.

[0140] In some embodiments, the window manager is used to manage all window programs, such as obtaining the display screen size, determining whether there is a status bar, locking the screen, capturing the screen, controlling display window changes (for example, shrinking the display window, shaking the display, distorting the display, etc.), etc.

[0141] In some embodiments, the system runtime layer provides support for the upper layer, namely the framework layer. When the framework layer is used, the Android operating system will run the C / C++ library contained in the system runtime layer to implement the functions to be implemented by the framework layer.

[0142] In some embodiments, the kernel layer is a layer between hardware and software. Figure 4 As shown, the kernel layer includes at least one of the following drivers: audio driver, display driver, Bluetooth driver, camera driver, WIFI driver, USB driver, HDMI driver, sensor driver (such as fingerprint sensor, temperature sensor, touch sensor, pressure sensor, etc.), etc.

[0143] In some embodiments, the core layer further includes a power driver module for performing power management.

[0144] In some embodiments, Figure 4 The software programs and / or modules corresponding to the software architecture in Figure 2 or Figure 3 In the first memory or the second memory shown.

[0145] In some embodiments, for a display device with a touch function, taking a split-screen operation as an example, the display device receives an input operation (such as a split-screen operation) performed by a user on the display screen, and the kernel layer can generate a corresponding input event based on the input operation and report the event to the application framework layer. The activity manager of the application framework layer sets the window mode (such as a multi-window mode) and the window position and size corresponding to the input operation. The window management of the application framework layer draws the window according to the settings of the activity manager, and then sends the drawn window data to the display driver of the kernel layer, which displays the corresponding application interface in different display areas of the display screen.

[0146] In some embodiments, as Figure 5 As shown in , the application layer includes at least one application that can display corresponding icon controls on the display, such as: live TV application icon controls, video on demand application icon controls, media center application icon controls, application center icon controls, game application icon controls, etc.

[0147] In some embodiments, the live TV application can provide live TV from various signal sources. For example, the live TV application can provide a TV signal using an input from a cable TV service, over-the-air broadcast, satellite service, or other type of live TV service. Furthermore, the live TV application can display video from the live TV signal on the display device 200.

[0148] In some embodiments, a video-on-demand application can provide videos from various storage sources. Unlike a live TV application, a video-on-demand application provides video display from a storage source. For example, the video-on-demand application can be served from a cloud storage server or from a local hard drive containing stored video programs.

[0149] In some embodiments, a media center application may be an application that provides various multimedia content playback applications. For example, a media center may be a service that is different from live TV or video on demand, and a user may access various images or audio services through the media center application.

[0150] In some embodiments, an application center can provide storage for various applications. These applications can be games, apps, or other applications related to computer systems or other devices that can be run on a smart TV. The application center can obtain these applications from various sources, store them in local storage, and then run them on the display device 200.

[0151] The hardware or software architecture in some embodiments may be based on the introduction in the above embodiments, and in some embodiments may be based on other similar hardware or software architectures, as long as the technical solutions of the present application can be implemented.

[0152] In some embodiments, the application center may be equipped with a voice assistant application to implement intelligent voice services, such as searching for media resources and adjusting volume. The user can wake up the voice assistant application by issuing a voice command to the display device. The voice command can be a preset wake-up word. After the voice assistant application wakes up, the user can interact with the voice assistant application to control the display device by voice. After receiving the user's voice command, the intelligent voice assistant needs to perform voice recognition on the voice command to obtain recognized text. Because many characters are easily confused, there is a certain probability of error in the recognized text.

[0153] To solve the above technical problems, the present application embodiment shows an overall flow chart of text error correction, see Figure 6First, the natural language text is input into the end-to-end error detection and correction model for correction to obtain the first correction result, wherein the end-to-end error detection and correction model performs Bert vector representation, character sound-shape confusion graph representation, multi-layer graph neural network, latent vector classification and character generation on the natural language text, i.e., the text to be corrected; then, the Elasticsearch search engine performs candidate recall on the first correction result according to the correction word library to obtain the recall result, wherein the candidate recall includes Elasticsearch search, correction word library inverted index and other processing; finally, the recall result is sorted to obtain the sorting result, and the final correction result corresponding to the natural language text is generated according to the sorting result, wherein the candidate sorting includes editing distance, threshold filtering and other processing.

[0154] For Figure 6 The text error correction method in the present application is further introduced. The embodiment of the present application also provides a flow chart of a text error correction method, see Figure 7 , the method can be used for a display device, comprising the following steps:

[0155] Step S10: Correct the text to be corrected based on the similar sound-form confusion set and graph attention mechanism to obtain the initial corrected text.

[0156] In some embodiments, after being awakened, a voice assistant application on a display device can receive a user's voice command. A controller on the display device obtains the voice command received by the voice assistant application, performs voice conversion on the voice command, and obtains a text to be corrected. This text to be corrected may have some errors compared to the actual text corresponding to the voice command, and correction is required to obtain the actual text, which can be referred to as the final corrected text.

[0157] In some embodiments, it may take a certain amount of time, such as 1 second, for the display device to correct errors. If the final error correction text is displayed after the error correction, the user may experience a slow response of the display device. To avoid the user waiting for a long time for the display device to respond, after obtaining the text to be corrected, the display can be controlled to display the text to be corrected first, and error correction can be performed in the background.

[0158] In some embodiments, the display device can build an end-to-end error detection and correction model to perform preliminary error correction on the text to be corrected. Figure 8 , is a schematic diagram of the structure of an end-to-end error detection and correction model according to some embodiments, such as Figure 8 As shown in the figure, the text to be corrected, such as "Meet the inverse", is input into the Bert Extractor, which outputs the initial representation matrix H, which includes H0, H1, ...H t+1, where Trm represents the encoding output of the Transformer layer, EMB represents the word embedding of characters, Trm takes EMB as input, and t represents the character length requested by the user.

[0159] The initial representation matrix is ​​input into the GCN Network (Graph Convolutional Nueral Network), and the pronunciation similarity confusion set knowledge graph and shape similarity confusion set knowledge graph of the text to be corrected are respectively input into the GCN Network to update the initial representation matrix. The GCN Network has three layers: layer_1, layer_2, and layer_3.

[0160] The GCN Network inputs the output result to the classifier, which outputs the correction result of the end-to-end error detection and correction model, such as "encountering adversity". The correction result can be used as the initial correction text. The classifier can be a latent vector classifier that can perform latent vector classification. The dotted boxes in the classifier represent the probability distribution of each character prediction, such as 80%, 70%, 85%...

[0161] The analytical method of the above end-to-end error detection and correction model can be found in Figure 9 , is a flowchart of a method for parsing a text to be corrected according to some embodiments of the present application, such as Figure 9 As shown, the parsing method may include steps S101-S105.

[0162] Step S101: extract features from the text to be corrected to obtain an initial representation matrix.

[0163] In some embodiments, feature extraction can be performed on the text to be corrected using a Bert model.

[0164] The BERT model uses a bidirectional Transformer as the encoder, employing two methods: a Masked Language Model (MaskedLM) and Next Sentence Prediction (Next Sentence Prediction) to capture word-level and sentence-level representations, respectively. After inputting the text to be corrected into the BERT model, it outputs the initial representation matrix H.

[0165] Step S102: creating an adjacency matrix for each character in the text to be corrected based on the confusion set of similar sound and form.

[0166] The set of phonetically and visually similar confusing characters includes a preset set of phonetically similar confusing characters and a set of visually similar confusing characters. Among them, the set of phonetically similar confusing characters is a preset set of characters that are likely to be confused due to similar pronunciation; the set of visually similar confusing characters is a preset set of characters that are likely to be confused due to similar shape. In some embodiments, the set of phonetically and visually similar confusing characters can be obtained through data analysis of user data, where the user data can include the input data of the user on the display device.

[0167] In some embodiments, for the character "竟" in the text to be corrected "遇到逆竟", its set of phonetically similar confusing characters is {金, 静, 境, 井, 寄, 竟}, and its set of visually similar confusing characters is {京, 镜, 竟, 竞, 景, 境}.

[0168] In some embodiments, the confusing set of the character "竟" may not only include the above Chinese characters. For example: 竟: 经静景晋径镜鹿璜尽竟金井今禁慌近墙竞进敬紧睛垣精墒京晶憬净瞌渍清, and the confusing set of 竟 is the characters after the colon.

[0169] The method for creating the adjacency matrix can be referred to Figure 10 , including steps S1021 - S1023.

[0170] Step S1021: Obtain the phonetically similar characters and visually similar characters of each character in the text to be corrected in the set of phonetically and visually similar confusing characters.

[0171] Extract the phonetically similar characters and visually similar characters of each character in the text to be corrected in the set of phonetically and visually similar confusing characters from the set of phonetically similar confusing characters and the set of visually similar confusing characters respectively.

[0172] Step S1022: Use the characters in the text to be corrected, the phonetically similar characters, and the characters in the character library as nodes, and use the relationships between the characters as edges to establish a phonetically similar adjacency matrix.

[0173] In some embodiments, a character library can be selected from commonly used Chinese characters in life to provide alternative characters for the text to be corrected.

[0174] Use the characters in the text to be corrected as the central nodes, use the phonetically similar characters of the character and the characters in the character library other than the characters in the text to be corrected and their phonetically similar characters as edge nodes, and use the relationships between the characters as edges to establish a knowledge graph of the set of phonetically similar confusing characters. Among them, each edge represents 0 or 1, 1 means the two nodes of this edge are similar, and 0 means the two nodes of this edge are not similar. For example, the edge connecting the character in the text to be corrected and the character in the set of phonetically similar confusing characters can be represented as 1, and the edge connecting the character in the text to be corrected and the character in the character library that does not belong to its set of phonetically similar confusing characters can be represented as 0.

[0175] The knowledge graph of the pronunciation-similar confusion set can be represented as an N*N adjacency matrix, where N represents the number of commonly used Chinese characters, that is, the number of characters in the character library, such as 5000.

[0176] Step S1023: Using the characters in the text to be corrected, the characters with similar shapes, and the characters in the character library as nodes, and the relationships between the characters as edges, a shape-similar adjacency matrix is ​​established.

[0177] The characters in the text to be corrected are taken as the central nodes, the characters with similar shapes to the characters and the characters in the character library are taken as nodes and edge nodes, and the relationships between the characters are taken as edges to establish a knowledge graph of shape-similar confusion sets, where each edge represents 0 or 1, 1 means that the two nodes of the edge are close, and 0 means that the two nodes of the edge are not close. For example, the edge connecting the characters in the text to be corrected and the characters in the shape-similar confusion set can be represented as 1, and the edge connecting the characters in the text to be corrected and the characters in the character library that do not belong to their shape-similar confusion set can be represented as 0. The knowledge graph of shape-similar confusion sets can also be represented as an N*N adjacency matrix.

[0178] Step S103: Input the initial representation matrix and the adjacency matrix into a multi-layer graph convolutional neural network to obtain a next-layer representation matrix.

[0179] Construct a 3-layer graph neural network, such as Figure 8 In the layer1-layer3 model, the input of layer1 is the encoded output of BertExtractor, and the input of layers 2 and 3 is the output of the previous layer. H and the adjacency matrix A are used as the input of the multi-layer graph convolutional neural network to extract deeper semantic information. The adjacency matrix A includes the adjacency matrix corresponding to the knowledge graph of the pronunciation-similar confusion set and the adjacency matrix corresponding to the knowledge graph of the shape-similar confusion set.

[0180] Take H and the adjacency matrix A as the input of the multi-layer graph convolutional neural network to obtain the representation matrix of the second layer; take the representation matrix of the second layer and the adjacency matrix A as the input of the multi-layer graph convolutional neural network to obtain the representation matrix of the third layer... and so on, to obtain the representation matrix H of each layer of the multi-layer graph convolutional neural network l , the calculation formula is as follows:

[0181]

[0182] (1) In the formula, l represents the lth layer, I represents the unit matrix corresponding to A, The matrix after introducing the node self-connection feature can be called the adjacency estimation matrix. The diagonal matrix corresponding to A is called the diagonal estimation matrix, and the values ​​on its diagonal position are the degrees of the corresponding nodes. Both i and j are between 0 and N. l-1 That is H l The representation matrix of the previous layer, W l Represents the training parameters of the lth layer.

[0183] Step S104: Obtain the last layer representation matrix of the multi-layer graph convolutional neural network according to the graph attention mechanism.

[0184] In some embodiments, a graph attention mechanism can be introduced to combine the knowledge of similar pronunciation and similar shape to obtain the final layer representation matrix H l+1 .

[0185] Use the attention mechanism to calculate the attention representation matrix C of knowledge fusion l , the calculation formula is as follows:

[0186]

[0187] (2) In the formula, C l It is an N*D dimensional matrix, where D represents the vector dimension after Bert encoding, and f k (A k , H l ) i is the i-th row of the graph convolution output for graph k, where graph K is the adjacency matrix of the k-th word, which can also be expressed as A k , s represents similar shape, and p represents similar pronunciation. Represents the scalar weight of the i-th character for the graph k, and l represents the number of neural network layers W a yes The training parameters of β are hyperparameters, and β can be a constant, such as 3.

[0188] The representation matrix H of the last layer is calculated according to the following formula l+1 :

[0189]

[0190] Step S105: Generate characters through the fully connected layer and the probability normalization function.

[0191] In some embodiments, characters may be generated according to a probabilistic normalization function:

[0192]

[0193] (4) In the formula, X represents the entire user request, such as "encountering an inverse competition", The word that represents the correct first position is yp, which represents probability. Denote the probability that the input is X and the i-th character position is y, and W represents the training weight parameters of the fully connected layer.

[0194] According to formula (4), the probability that each character position is a certain character can be obtained. If there are multiple alternative characters at a character position, such as "境" and "竟", select the character corresponding to the maximum probability as the character at that character position. Among them, the alternative characters for each character position can be obtained according to the representation matrix H of the last layer. l+1 After inputting the text to be corrected, "遇到逆竟", into the end-to-end error detection and correction model, the character "遇到逆境" can be generated and output, and this "遇到逆境" can be referred to as the initial corrected text. <>

[0195] Step S20: Perform candidate recall on the text to be corrected and the initial corrected text to obtain the recalled text.

[0196] In some embodiments, the initial corrected text can be queried in Elasticsearch to obtain the first recalled text.

[0197] ES (Elasticsearch, a distributed full-text search engine) is a full-text search server and can also be used as a NoSQL database to store documents and data in any format. The full-text search engine of ES is an open-source search engine built on Lucene (a full-text search framework) and can be used for full-text search and geographical information search.

[0198] Use the initial corrected text as a query for Elasticsearch query. There are multiple query methods, including match search, prefix search, suffix search, fuzzy search, and multiple methods can be combined to search the query to obtain the first recalled text. For example, the match search can be an exact search, requiring the characters to be exactly the same. Search for "小猪佩", and the search result can be "小猪佩奇".

[0199] In some embodiments, an inverted index data structure can be constructed based on the error correction dictionary, and the initial corrected text and the text to be corrected are used as queries respectively to obtain the second recalled text.

[0200] An inverted index, also often called a reverse index, an inverted file, or an inverted file, is an indexing method used to store a mapping of the storage location of a word in a document or a group of documents under full-text search. It is the most commonly used data structure in document retrieval systems. Through the inverted index, you can quickly get a list of documents containing a word based on the word. The inverted index mainly consists of two parts: the "word dictionary" and the "inverted file." Based on the error correction vocabulary, a mapping of Chinese characters to words is created to construct an inverted index. The error correction results and the original text are used as queries respectively. Combined with rule conditions such as the number of similar characters or the number of similar pinyins, similar words in the vocabulary are searched.

[0201] In some embodiments, the recall text may include a first recall text and a second recall text.

[0202] Step S30: performing candidate sorting on the recalled texts, and obtaining a final correction text corresponding to the text to be corrected according to the sorting result.

[0203] The Levenshtein edit distance (string similarity) measures the degree of difference between two strings. It represents the minimum number of character edits (such as modifications, insertions, and deletions) required to modify one string into another. A larger Levenshtein edit distance indicates a weaker correlation between the two strings.

[0204] In some embodiments, the edit distance between each recalled text and the initial correction text can be calculated separately, and the edit distance can be divided by the length of the longest text between the recalled text and the initial correction text to obtain the difference between the recalled text, where the longest text refers to the text with the most words.

[0205] Furthermore, a difference threshold can be set to sort the recalled texts according to the difference, and the recalled texts with a difference higher than the difference threshold can be filtered out. The difference threshold can be set to a constant, such as 0.75.

[0206] The recalled text with the smallest difference is used as the final correction text of the text to be corrected.

[0207] The embodiment of the present application also provides a server, which can be configured to execute Figure 7 The text error correction method shown is used to correct Chinese text.

[0208] In some embodiments, the server may be in communication with the display device, and the display device may send the text to be corrected to the server, and the server may Figure 7 After the text error correction method shown obtains the final error-corrected text, the final error-corrected text is sent to a display device so that the display device displays the final error-corrected text.

[0209] See also Figure 11-13 , is a schematic diagram of a voice interaction interface according to some embodiments, such as Figure 11 As shown, the wake-up word of the voice assistant application can be "Hisense Xiaoju". After waking up, the voice assistant application can display a recording prompt word, such as "Listening...", prompting the user to issue a voice command; Figure 12 As shown, after the user issues a voice command, the display device can convert the voice command into speech and display it in real time. The text after the speech conversion can be the text to be corrected, such as "Meet the reverse competition". After the display device displays the text to be corrected, it can be displayed in the background process of the display device according to the Figure 7 The method shown in the figure is used to correct the text and obtain the final corrected text. Alternatively, the display device uploads the text to be corrected to the server, which corrects the text and then returns the final corrected text to the display device. Figure 13 As shown, after obtaining the final error-corrected text, the display device can refresh the text to be corrected to the final error-corrected text. Furthermore, the display device can also respond according to the final error-corrected text, such as controlling the display device or playing corresponding audio and video media.

[0210] It can be seen from the above embodiments that the embodiments of the present application generate a pronunciation-similar knowledge graph and a shape-similar knowledge graph based on the confusion set corresponding to the text to be corrected, integrate the pinyin and glyph-related knowledge of Chinese characters into the graph neural network, extract the deep semantic information between similar characters, and effectively utilize the knowledge of similar pronunciation and shape to improve the accuracy and recall rate of error detection and correction.

[0211] Since the above embodiments are all described by reference in combination with other embodiments, different embodiments have the same parts, and the same and similar parts between the various embodiments in this specification can be referred to each other. No further detailed explanation is given here.

[0212] It should be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such circuit structure, article or device. In the absence of further restrictions, the presence of an element defined by the phrase "includes a..." does not exclude the presence of other identical elements in the circuit structure, article or device comprising the element.

[0213] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the disclosure of the invention herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein. The description and examples are to be considered merely exemplary, and the true scope and spirit of this application are indicated by the contents of the claims. The above embodiments of this application do not constitute a limitation on the scope of protection of this application.

Claims

1. A display device, characterized in that: include: monitor; A controller is connected to the display, and the controller is configured to: In response to receiving a voice command input by a user, performing voice conversion on the voice command to obtain a text to be corrected; Controlling the display to display the text to be corrected; Correcting the text to be corrected based on a confusion set of similar sound and form and a graph attention mechanism to obtain an initial corrected text; Recalling the characters in the initial error-correcting text and the text to be corrected respectively by using an inverted index vocabulary and preset rule conditions to obtain a recalled text, wherein the inverted index vocabulary is created based on the error-correcting vocabulary and is used to perform an inverted index on the mapping of Chinese characters to words; the preset rule conditions include the number of similar characters or the number of similar pinyins to the initial error-correcting text or the text to be corrected; Calculating the edit distance between the recalled text and the initial correction text respectively; dividing the edit distance by the length of the longest text between the recalled text and the initial correction text to obtain the difference between the recalled text and the initial correction text; sorting the recalled texts according to the difference, and selecting the recalled text with the smallest difference as the final correction text of the text to be corrected; The display is controlled to refresh the text to be corrected into the final text to be corrected.

2. The display device according to claim 1, wherein The correcting the text to be corrected based on the phonetic-phonological confusion set and the graph attention mechanism includes: Perform feature extraction on the text to be corrected to obtain the initial representation matrix; Creating an adjacency matrix for each character in the text to be corrected based on a confusion set of similar sound and form; Inputting the initial representation matrix and the adjacency matrix into a multi-layer graph convolutional neural network to obtain a next-layer representation matrix; Obtaining the last layer representation matrix of the multi-layer graph convolutional neural network according to the graph attention mechanism; Generate characters through a fully connected layer and a probability normalization function.

3. The display device according to claim 2, wherein The step of creating an adjacency matrix for each character in the text to be corrected based on the similar sound-shape confusion set includes: Obtaining, for each character in the text to be corrected, characters with similar pronunciations and characters with similar shapes in a similar pronunciation-shape confusion set; Using the characters in the text to be corrected, the characters with similar pronunciations, and the characters in the character library as nodes and the relationships between the characters as edges to establish a pronunciation similarity adjacency matrix; The characters in the text to be corrected, the characters with similar shapes and the characters in the character library are used as nodes, and the relationships between the characters are used as edges to establish a shape-similar adjacency matrix.

4. The display device according to claim 2, wherein: The initial representation matrix and the adjacency matrix are input into a multi-layer graph convolutional neural network to obtain a next layer of representation matrix, including: Adding the adjacency matrix to the identity matrix to obtain an adjacency estimate matrix; Calculating a diagonal matrix corresponding to the adjacency estimation matrix to obtain a diagonal estimation matrix; A next-layer representation matrix is ​​obtained according to the adjacency estimation matrix, the diagonal estimation matrix and the initial representation matrix.

5. The display device according to claim 2, wherein: The last layer representation matrix of the multi-layer graph convolutional neural network is obtained according to the graph attention mechanism, including: Use the attention mechanism to calculate the attention representation matrix of knowledge fusion; The final layer representation matrix is ​​obtained according to the sum of the attention representation matrix and each layer representation matrix.

6. The display device according to claim 1, wherein The controller is further configured to: Filter the recalled texts whose difference is higher than the difference threshold.

7. A text error correction method for a display device, characterized in that: include: Based on the similar sound-form confusion set and graph attention mechanism, the correction text is corrected to obtain the initial correction text. Recalling the characters in the initial correction text and the text to be corrected respectively by using an inverted index vocabulary and preset rule conditions to obtain a recalled text, wherein the inverted index vocabulary is created based on the correction vocabulary and is used to map Chinese characters to words; the preset rule conditions include the number of similar characters or the number of similar pinyins to the initial correction text or the text to be corrected; Calculate the edit distance between the recalled text and the initial correction text respectively; divide the edit distance by the length of the longest text between the recalled text and the initial correction text to obtain the difference of the recalled text; sort the recalled texts according to the difference, and use the recalled text with the smallest difference as the final correction text of the text to be corrected.

8. A server, characterized in that: The server is configured to: receiving a text to be corrected from a display device; Correcting the text to be corrected based on a confusion set of similar sound and form and a graph attention mechanism to obtain an initial corrected text; Recalling the characters in the initial correction text and the text to be corrected respectively by using an inverted index vocabulary and preset rule conditions to obtain a recalled text, wherein the inverted index vocabulary is created based on the correction vocabulary and is used to map Chinese characters to words; the preset rule conditions include the number of similar characters or the number of similar pinyins to the initial correction text or the text to be corrected; Calculate the edit distance between the recalled text and the initial correction text respectively; divide the edit distance by the length of the longest text between the recalled text and the initial correction text to obtain the difference of the recalled text; sort the recalled texts according to the difference, and use the recalled text with the smallest difference as the final correction text of the text to be corrected.

Images