CN114187905A

CN114187905A - Training method of user intention recognition model, server and display equipment

Info

Publication number: CN114187905A
Application number: CN202010880811.0A
Authority: CN
Inventors: 王利杰; 王聪; 沈承恩; 杨善松
Original assignee: Hisense Visual Technology Co Ltd
Current assignee: Hisense Visual Technology Co Ltd
Priority date: 2020-08-27
Filing date: 2020-08-27
Publication date: 2022-03-15

Abstract

The embodiment of the application provides a training method, a server and display equipment for a user intention recognition model, wherein the training method comprises the following steps: dividing samples in a training sample set into a plurality of training groups, wherein each training group comprises a support set and a query set; inputting the training group into a user intention recognition model, and respectively extracting sample characteristics of a support set and sample characteristics of a query set; calculating the similarity between the sample characteristics of the support set and the sample characteristics of the query set through a cosine function; calculating a loss function of the user intention recognition model according to the similarity; optimizing the loss function through a plurality of the training sets until the user intent recognition model converges. According to the method and the device, the user intention recognition model is trained based on a small sample classification mode, sample data can be fully utilized, and the generalization and recognition accuracy of the user intention recognition model are improved.

Description

Training method of user intention recognition model, server and display equipment

Technical Field

The application relates to the technical field of display equipment, in particular to a training method of a user intention recognition model, a server and display equipment.

Background

With the rapid development of artificial intelligence, the deep learning method has been widely applied in text classification. Meanwhile, as the demand of the voice assistant service on the intelligent device, such as the display device, rapidly increases, the domain location module set on the controller of the display device or the server of the display device needs to be continuously updated iteratively to meet the service demand. Currently, a domain location module can classify texts of user requests received by a voice assistant based on a deep learning model, and locate a service module to process the user requests according to a classification result, so as to identify and respond to user intentions.

In the related art, the domain positioning module establishes a deep learning model based on network structures such as textCNN, textRNN and the like, the deep learning model needs a large amount of data to train the deep learning model so as to improve the classification accuracy of the deep learning model, however, when a service module is newly added, a large amount of data of newly added services are often difficult to obtain immediately, so that the deep learning model is easily trapped in an over-fitting state, the generalization is reduced, and the model accuracy is reduced.

Disclosure of Invention

In order to solve the technical problem, the application provides a training method, a server and a display device for a user intention recognition model.

In a first aspect, the present application provides a training method for a user intention recognition model, the method including:

dividing samples in a training sample set into a plurality of training groups, wherein each training group comprises a support set and a query set;

inputting the training group into a user intention recognition model, and respectively extracting sample characteristics of a support set and sample characteristics of a query set;

calculating the similarity between the sample characteristics of the support set and the sample characteristics of the query set through a cosine function;

calculating a loss function of the user intention recognition model according to the similarity;

optimizing the loss function through a plurality of the training sets until the user intent recognition model converges.

In some embodiments, the number of samples for all categories in the support set and query set is the same. For example, the support set includes samples of C categories, the number of samples of each category is K, the query set may also include samples of C categories, and the number of samples of each category is K, so that sampling in a C way-K shot training mode is realized, and sample data can be fully utilized.

In some embodiments, the extracting sample features of the support set comprises:

processing the sample in the supporting set through an embedding layer to obtain a first vector;

extracting context information of the first vector through a long and short memory neural network layer to obtain a first correction vector corresponding to the first vector;

extracting key sentence features of the first correction vector through an attention layer.

In some embodiments, said extracting sample features of the set of queries comprises:

processing the samples in the query set through an embedding layer to obtain a second vector;

extracting context information of the second vector through a long and short memory neural network layer to obtain a second correction vector corresponding to the second vector;

extracting key sentence features of the second correction vector through an attention layer.

In a second aspect, embodiments of the present application provide a server, which may be configured to perform the training method of the user intention recognition model according to the first aspect.

In a third aspect, an embodiment of the present application provides a server, where the server may be configured to:

processing a user request from a display device through a user intention identification model to obtain a category label of the user request;

processing the user request according to the service module corresponding to the category label to obtain a response result;

sending the response result to a display device;

wherein the user intention recognition model is trained based on the method of the first aspect.

In a fourth aspect, an embodiment of the present application provides a display device, including:

a display;

a controller connected with the display, the controller configured to:

responding to a received voice command input by a user, and performing text recognition on the voice command to obtain a user request;

processing a user request through a user intention identification model to obtain a category label of the user request;

controlling a display to display the response result;

The training method of the user intention recognition model and the display device have the advantages that:

the user intention recognition model is trained based on a small sample classification mode, sample data can be fully utilized, the similarity is calculated by adopting cosine, and a relu activation function is combined; under the condition of high-dimensional characteristics, the cosine is utilized to calculate the similarity, and the higher the similarity is, the closer the value is to 1, the orthogonal value is 0, and the opposite value is-1; combining with relu activation function, ensuring that the value of the feature vector is 0 when the feature vector is orthogonal and opposite, and the higher the similarity is, the closer the value is to 1; the method has a good effect on calculating the feature similarity of a high-dimensional space to a certain extent, and can be trained by using a small amount of data based on a small sample classification mode, has small interference on the original intention categories, has certain generalization on the newly added intention categories, and has high accuracy and recall ratio of the newly added categories.

Drawings

In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic diagram illustrating an operational scenario between a display device and a control apparatus according to some embodiments;

a block diagram of a hardware configuration of a display device 200 according to some embodiments is illustrated in fig. 2;

a block diagram of the hardware configuration of the control device 100 according to some embodiments is illustrated in fig. 3;

a schematic diagram of a software configuration in a display device 200 according to some embodiments is illustrated in fig. 4;

FIG. 5 illustrates an icon control interface display diagram of an application in the display device 200, according to some embodiments;

FIG. 6 illustrates a training overall flow diagram of a user intent recognition model, according to some embodiments;

FIG. 7 illustrates a structural diagram of a user intent recognition model, according to some embodiments;

FIG. 8 illustrates a flow diagram of a method of training a user intent recognition model, according to some embodiments;

FIG. 9 illustrates a flow diagram of a method of feature extraction for a support set, according to some embodiments;

a flow diagram of a method of feature extraction for a set of queries, according to some embodiments, is illustrated in fig. 10.

Detailed Description

To make the objects, embodiments and advantages of the present application clearer, the following description of exemplary embodiments of the present application will clearly and completely describe the exemplary embodiments of the present application with reference to the accompanying drawings in the exemplary embodiments of the present application, and it is to be understood that the described exemplary embodiments are only a part of the embodiments of the present application, and not all of the embodiments.

All other embodiments, which can be derived by a person skilled in the art from the exemplary embodiments described herein without inventive step, are intended to be within the scope of the claims appended hereto. In addition, while the disclosure herein has been presented in terms of one or more exemplary examples, it should be appreciated that aspects of the disclosure may be implemented solely as a complete embodiment.

It should be noted that the brief descriptions of the terms in the present application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of the present application. These terms should be understood in their ordinary and customary meaning unless otherwise indicated.

The terms "first," "second," "third," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between similar or analogous objects or entities and are not necessarily intended to limit the order or sequence of any particular one, Unless otherwise indicated. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein.

Furthermore, the terms "comprises" and "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a product or device that comprises a list of elements is not necessarily limited to those elements explicitly listed, but may include other elements not expressly listed or inherent to such product or device.

The term "module," as used herein, 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.

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 is typically wirelessly controllable over a relatively short range of distances. Typically using infrared and/or Radio Frequency (RF) signals and/or bluetooth to connect with the electronic device, and may also include WiFi, wireless USB, bluetooth, motion sensor, etc. For example: the hand-held touch remote controller replaces most of the physical built-in hard keys in the common remote control device with the user interface in the touch screen.

The term "gesture" as used in this application refers to a user's behavior through a change in hand shape or an action such as hand motion to convey a desired idea, action, purpose, or result.

Fig. 1 is a schematic diagram illustrating an operation scenario between a display device and a control apparatus according to an embodiment. As shown in fig. 1, a user may operate the display device 200 through the mobile terminal 300 and the control apparatus 100.

In some embodiments, the control apparatus 100 may be a remote controller, and the communication between the remote controller and the display device includes an infrared protocol communication or a bluetooth protocol communication, and other short-distance communication methods, etc., and the display device 200 is controlled by wireless or other wired methods. The user may input a user command through a key on a remote controller, voice input, control panel input, etc. to control the display apparatus 200. Such as: the user can input a corresponding control command through a volume up/down key, a channel control key, up/down/left/right moving keys, a voice input key, a menu key, a power on/off key, etc. on the remote controller, to implement the function of controlling the display device 200.

In some embodiments, mobile terminals, tablets, computers, laptops, and other smart devices may also be used to control the display device 200. For example, the display device 200 is controlled using an application program running on the smart device. The application, through configuration, may provide the user with various controls in an intuitive User Interface (UI) on a screen associated with the smart device.

In some embodiments, the mobile terminal 300 may install a software application with the display device 200 to implement connection communication through a network communication protocol for the purpose of one-to-one control operation and data communication. Such as: the mobile terminal 300 and the display device 200 can establish a control instruction protocol, synchronize a remote control keyboard to the mobile terminal 300, and control the display device 200 by controlling a user interface on the mobile terminal 300. The audio and video content displayed on the mobile terminal 300 can also be transmitted to the display device 200, so as to realize the synchronous display function.

As also shown in fig. 1, the display apparatus 200 also performs data communication with the server 400 through various communication means. The display device 200 may be allowed to be communicatively connected through a Local Area Network (LAN), a Wireless Local Area Network (WLAN), and other networks. The server 400 may provide various contents and interactions to the display apparatus 200. Illustratively, the display device 200 receives software program updates, or accesses a remotely stored digital media library, by sending and receiving information, as well as Electronic Program Guide (EPG) interactions. The server 400 may be a cluster or a plurality of clusters, and may include one or more types of servers. Other web service contents such as video on demand and advertisement services are provided through the server 400.

The display device 200 may be a liquid crystal display, an OLED display, a projection display device. The particular display device type, size, resolution, etc. are not limiting, and those skilled in the art will appreciate that the display device 200 may be modified in performance and configuration as desired.

The display apparatus 200 may additionally provide an intelligent network tv function of a computer support function including, but not limited to, a network tv, an intelligent tv, an Internet Protocol Tv (IPTV), and the like, in addition to the broadcast receiving tv function.

A hardware configuration block diagram of a display device 200 according to an exemplary embodiment is exemplarily shown in fig. 2.

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

In some embodiments, a display 275 receives image signals originating from the first processor output and displays video content and images and components of the menu manipulation interface.

In some embodiments, the display 275, includes a display screen assembly for presenting a picture, and a driving assembly that drives the display of an image.

In some embodiments, the video content is displayed from broadcast television content, or alternatively, from various broadcast signals that may be received via wired or wireless communication protocols. Alternatively, various image contents received from the network communication protocol and sent from the network server side can be displayed.

In some embodiments, the display 275 is used to present a user-manipulated UI interface generated in the display apparatus 200 and used to control the display apparatus 200.

In some embodiments, a driver assembly for driving the display is also included, depending on the type of display 275.

In some embodiments, display 275 is a projection display and may also include a projection device and a projection screen.

In some embodiments, communicator 220 is a component for communicating with external devices or external servers according to various communication protocol types. For example: the communicator may include at least one of a Wifi chip, a bluetooth communication protocol chip, a wired ethernet communication protocol chip, and other network communication protocol chips or near field communication protocol chips, and an infrared receiver.

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

In some embodiments, the user interface 265 may be configured to receive infrared control signals from a control device 100 (e.g., an infrared remote control, etc.).

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

In some embodiments, the detector 230 includes a light receiver, a sensor for collecting the intensity of ambient light, and parameters changes can be adaptively displayed by collecting the ambient light, and the like.

In some embodiments, the detector 230 may further include an image collector, such as a camera, etc., which may be configured to collect external environment scenes, collect attributes of the user or gestures interacted with the user, adaptively change display parameters, and recognize user gestures, so as to implement a function of interaction with the user.

In some embodiments, the detector 230 may also include a temperature sensor or the like, such as by sensing ambient temperature.

In some embodiments, the display apparatus 200 may adaptively adjust a display color temperature of an image. For example, the display apparatus 200 may be adjusted to display a cool tone when the temperature is in a high environment, or the display apparatus 200 may be adjusted to display a warm tone when the temperature is in a low environment.

In some embodiments, the detector 230 may also be a sound collector or the like, such as a microphone, which may be used to receive the user's voice. Illustratively, a voice signal including a control instruction of the user to control the display device 200, or to collect an ambient sound for recognizing an ambient scene type, so that the display device 200 can adaptively adapt to an ambient noise.

In some embodiments, as shown in fig. 2, the input/output interface 255 is configured to allow data transfer between the controller 250 and external other devices or other controllers 250. Such as receiving video signal data and audio signal data of an external device, or command instruction data, etc.

In some embodiments, the external device interface 240 may include, but is not limited to, the following: the interface can be any one or more of a high-definition multimedia interface (HDMI), an analog or data high-definition component input interface, a composite video input interface, a USB input interface, an RGB port and the like. The plurality of interfaces may form a composite input/output interface.

In some embodiments, as shown in fig. 2, the tuning demodulator 210 is configured to receive a broadcast television signal through a wired or wireless receiving manner, perform modulation and demodulation processing such as amplification, mixing, resonance, and the like, and demodulate an audio and video signal from a plurality of wireless or wired broadcast television signals, where the audio and video signal may include a television audio and video signal carried in a television channel frequency selected by a user and an EPG data signal.

In some embodiments, the frequency points demodulated by the tuner demodulator 210 are controlled by the controller 250, and the controller 250 can send out control signals according to user selection, so that the modem responds to the television signal frequency selected by the user and modulates and demodulates the television signal carried by the frequency.

In some embodiments, the broadcast television signal may be classified into a terrestrial broadcast signal, a cable broadcast signal, a satellite broadcast signal, an internet broadcast signal, or the like according to the broadcasting system of the television signal. Or may be classified into a digital modulation signal, an analog modulation signal, and the like according to a modulation type. Or the signals are classified into digital signals, analog signals and the like according to the types of the signals.

In some embodiments, the controller 250 and the modem 210 may be located in different separate devices, that is, the modem 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. Therefore, the set top box outputs the television audio and video signals modulated and demodulated by the received broadcast television signals to the main body equipment, and the main body equipment receives the audio and video signals through the first input/output interface.

In some embodiments, the controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in memory. The controller 250 may control the overall operation of the display apparatus 200. For example: in response to receiving a user command for selecting a UI object to be displayed on the display 275, the controller 250 may perform an operation related to the object selected by the user command.

In some embodiments, the object may be any one of selectable objects, such as a hyperlink or an icon. Operations related to the selected object, such as: displaying an operation connected to a hyperlink page, document, image, or the like, or performing an operation of a program corresponding to the icon. The user command for selecting the UI object may be a command input through various input means (e.g., a mouse, a keyboard, a touch pad, etc.) connected to the display apparatus 200 or a voice command corresponding to a voice spoken by the user.

As shown in fig. 2, 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 254 (CPU), a Communication Interface (Communication Interface), and a Communication Bus 256(Bus), which connects the respective components.

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

In some embodiments, ROM 252 is used to store instructions for various system boots.

In some embodiments, the ROM 252 is used to store a Basic Input Output System (BIOS). The system is used for completing power-on self-test of the system, initialization of each functional module in the system, a driver of basic input/output of the system and booting an operating system.

In some embodiments, when the power-on signal is received, the display device 200 starts to power up, the CPU executes the system boot instruction in the ROM 252, and copies the temporary data of the operating system stored in the memory to the RAM 251 so as to start or run the operating system. After the start of the operating system is completed, the CPU copies the temporary data of the various application programs in the memory to the RAM 251, and then, the various application programs are started or run.

In some embodiments, CPU processor 254 is used to execute operating system and application program instructions stored in memory. And executing various application programs, data and contents according to various interactive instructions received from the outside so as to finally display and play various audio and video contents.

In some example embodiments, the CPU processor 254 may comprise a plurality of processors. The plurality of processors may include a main processor and one or more sub-processors. A main processor for performing some operations of the display apparatus 200 in a pre-power-up mode and/or operations of displaying a screen in a normal mode. One or more sub-processors for one operation in a standby mode or the like.

In some embodiments, the graphics processor 253 is used to generate various graphics objects, such as: icons, operation menus, user input instruction display graphics, and the like. The display device comprises an arithmetic unit which carries out operation by receiving various interactive instructions input by a user and displays various objects according to display attributes. And the system comprises a renderer for rendering various objects obtained based on the arithmetic unit, wherein the rendered objects are used for being displayed on a display.

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

In some embodiments, video processor 270 includes a demultiplexing module, a video decoding module, an image composition module, a frame number conversion module, a display formatting module, and the like.

The demultiplexing module is used for demultiplexing the input audio and video data stream, and if the input MPEG-2 is input, the demultiplexing module demultiplexes the input audio and video data stream into a video signal and an audio signal.

And the video decoding module is used for processing the video signal after demultiplexing, including decoding, scaling and the like.

And the image synthesis module is used for carrying out superposition mixing processing on the GUI signal input by the user or generated by the user and the video image after the zooming processing by the graphic generator so as to generate an image signal for display.

The frame conversion module is used for converting the input video frame number, such as converting the 60Hz frame number into the 120Hz frame number or the 240Hz frame number, and the common format is realized by adopting a frame interpolation mode.

The display format module is used for converting the received frame number into a video output signal and changing the signal to conform to the display format, such as outputting an RGB data signal.

In some embodiments, the graphics processor 253 and the video processor may be integrated or separately configured, and when the graphics processor and the video processor are integrated, the graphics processor and the video processor may perform processing of graphics signals output to the display, and when the graphics processor and the video processor are separately configured, the graphics processor and the video processor may perform different functions, respectively, for example, a GPU + frc (frame Rate conversion) architecture.

In some embodiments, the audio processor 280 is configured to receive an external audio signal, decompress and decode the received audio signal according to a standard codec protocol of the input signal, and perform noise reduction, digital-to-analog conversion, and amplification processes to obtain an audio signal that can be played in a speaker.

In some embodiments, video processor 270 may comprise one or more chips. The audio processor may also comprise one or more chips.

In some embodiments, the video processor 270 and the audio processor 280 may be separate chips or may be integrated together with the controller in one or more chips.

In some embodiments, the audio output, under the control of controller 250, receives sound signals output by audio processor 280, such as: the speaker 286, and an external sound output terminal of the sound generating device that can output to the external device, in addition to the speaker carried by the display device 200 itself, such as: external sound interface or earphone interface, etc., and may also include a near field communication module in the communication interface, for example: and the Bluetooth module is used for outputting sound of the Bluetooth loudspeaker.

The power supply 290 supplies power to the display device 200 from the power input from the external power source under the control of the controller 250. The power supply 290 may include a built-in power supply circuit installed inside the display apparatus 200, or may be a power supply interface installed outside the display apparatus 200 to provide an external power supply in the display apparatus 200.

A user interface 265 for receiving an input signal of a user and then transmitting the received user input signal to the controller 250. The user input signal may be a remote controller signal received through an infrared receiver, and various user control signals may be received through the network communication module.

In some embodiments, the user inputs a user command through the control apparatus 100 or the mobile terminal 300, the user input interface responds to the user input through the controller 250 according to the user input, and the display device 200 responds to the user input through the controller 250.

In some embodiments, a user may enter user commands on a Graphical User Interface (GUI) displayed on the display 275, and the user input interface receives the user input commands through the Graphical User Interface (GUI). Alternatively, the user may input the user command by inputting a specific sound or gesture, and the user input interface receives the user input command by recognizing the sound or gesture through the sensor.

In some embodiments, a "user interface" is a media interface for interaction and information exchange between an application or operating system and a user that enables conversion between an internal form of information and a form that is acceptable to the user. A commonly used presentation form of the User Interface is a Graphical User Interface (GUI), which refers to a User Interface related to computer operations and displayed in a graphical manner. It may be an interface element such as an icon, a window, a control, etc. displayed in the display screen of the electronic device, where the control may include a visual interface element such as an icon, a button, a menu, a tab, a text box, a dialog box, a status bar, a navigation bar, a Widget, etc.

The memory 260 includes a memory storing various software modules for driving the display device 200. Such as: various software modules stored in the first memory, including: at least one of a basic module, a detection module, a communication module, a display control module, a browser module, and various service modules.

The base module is a bottom layer software module for signal communication between various hardware in the display device 200 and for sending processing and control signals to the upper layer module. The detection module is used for collecting various information from various sensors or user input interfaces, and the management module is used for performing digital-to-analog conversion and analysis management.

For example, the voice recognition module comprises a voice analysis module and a voice instruction database module. The display control module is used for controlling the display to display the image content, and can be used for playing the multimedia image content, UI interface and other information. And the communication module is used for carrying out control and data communication with external equipment. And the browser module is used for executing a module for data communication between browsing servers. And the service module is used for providing various services and modules including various application programs. Meanwhile, the memory 260 may store a visual effect map for receiving external data and user data, images of various items in various user interfaces, and a focus object, etc.

Fig. 3 exemplarily shows a block diagram of a configuration of the control apparatus 100 according to an exemplary embodiment. As shown in fig. 3, the control device 100 includes a controller 110, a communication interface 130, a user input/output interface, a memory, and a power supply.

The control apparatus 100 is configured to control the display device 200 and may receive an input operation instruction of a user and convert the operation instruction into an instruction recognizable and responsive by the display device 200, serving as an interaction intermediary between the user and the display device 200. Such as: the user operates the channel up/down key on the control device 100, and the display device 200 responds to the channel up/down operation.

In some embodiments, the control device 100 may be a smart device. Such as: the control apparatus 100 may install various applications that control the display device 200 according to user demands.

In some embodiments, as shown in fig. 1, a mobile terminal 300 or other intelligent electronic device may function similar to the control apparatus 100 after an application for manipulating the display device 200 is installed. Such as: the user may implement the function of controlling the physical keys of the apparatus 100 by installing an application, various function keys or virtual buttons of a graphical user interface available on the mobile terminal 300 or other intelligent electronic device.

The controller 110 includes a processor 112 and RAM 113 and ROM 114, a communication interface 130, and a communication bus. The controller is used for controlling the operation of the control device 100, as well as the communication cooperation among the internal components and the external and internal data processing functions.

The communication interface 130 enables communication of control signals and data signals with the display apparatus 200 under the control of the controller 110. Such as: the received user input signal is transmitted to the display apparatus 200. The communication interface 130 may include at least one of a WiFi chip 131, a bluetooth module 132, an NFC module 133, and other near field communication modules.

A user input/output interface 140, wherein the input interface includes at least one of a microphone 141, a touch pad 142, a sensor 143, keys 144, and other input interfaces. Such as: the user can realize a user instruction input function through actions such as voice, touch, gesture, pressing, and the like, and the input interface converts the received analog signal into a digital signal and converts the digital signal into a corresponding instruction signal, and sends the instruction signal to the display device 200.

The output interface includes an interface that transmits the received user instruction to the display apparatus 200. In some embodiments, the interface may be an infrared interface or a radio frequency interface. Such as: when the infrared signal interface is used, the user input instruction needs to be converted into an infrared control signal according to an infrared control protocol, and the infrared control signal is sent to the display device 200 through the infrared sending module. The following steps are repeated: when the rf signal interface is used, a user input command needs to be converted into a digital signal, and then the digital signal is modulated according to the rf control signal modulation protocol and then transmitted to the display device 200 through the rf transmitting terminal.

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 a communication interface 130, such as: the WiFi, bluetooth, NFC, etc. modules may transmit the user input command to the display device 200 through the WiFi protocol, or the bluetooth protocol, or the NFC protocol code.

A memory 190 for storing various operation programs, data and applications for driving and controlling the control apparatus 200 under the control of the controller. The memory 190 may store various control signal commands input by a user.

And a power supply 180 for providing operation power support for each element of the control device 100 under the control of the controller. A battery and associated control circuitry.

In some embodiments, the system may include a Kernel (Kernel), a command parser (shell), a file system, and an application program. The kernel, shell, and file system together make up the basic operating system structure that allows users to manage files, run programs, and use the system. After power-on, the kernel is started, kernel space is activated, hardware is abstracted, hardware parameters are initialized, and virtual memory, a scheduler, signals and interprocess communication (IPC) are operated and maintained. And after the kernel is started, loading the Shell and the user application program. The application program is compiled into machine code after being started, and a process is formed.

Referring to fig. 4, in some embodiments, the system is divided into four layers, which are an Application (Applications) layer (abbreviated as "Application layer"), an Application Framework (Application Framework) layer (abbreviated as "Framework layer"), an Android runtime (Android runtime) and system library layer (abbreviated as "system runtime library layer"), and a kernel layer from top to bottom.

In some embodiments, at least one application program runs in the application program layer, and the application programs can be Window (Window) programs carried by an operating system, system setting programs, clock programs, camera applications and the like; or may be an application developed by a third party developer such as a hi program, a karaoke program, a magic mirror program, or the like. In specific implementation, the application packages in the application layer are not limited to the above examples, and may actually include other application packages, which is not limited in this embodiment of the present application.

The framework layer provides an Application Programming Interface (API) and a programming framework for the application program of the application layer. The application framework layer includes a number of predefined functions. The application framework layer acts as a processing center that decides to let the applications in the application layer act. The application program can access the resources in the system and obtain the services of the system in execution through the API interface.

As shown in fig. 4, in the embodiment of the present application, the application framework layer includes a manager (Managers), a Content Provider (Content Provider), and the like, where the manager includes at least one of the following modules: an Activity Manager (Activity Manager) is used for interacting with all activities running in the system; the Location Manager (Location Manager) is used for providing the system service or application with the access of the system Location service; a Package Manager (Package Manager) for retrieving various information related to an application Package currently installed on the device; a Notification Manager (Notification Manager) for controlling display and clearing of Notification messages; a Window Manager (Window Manager) is used to manage the icons, windows, toolbars, wallpapers, and desktop components on a user interface.

In some embodiments, the activity manager is to: managing the life cycle of each application program and the general navigation backspacing function, such as controlling the exit of the application program (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 previous user interface of the user interface currently displayed), and the like.

In some embodiments, the window manager is configured to manage all window processes, such as obtaining a display size, determining whether a status bar is available, locking a screen, intercepting a screen, controlling a display change (e.g., zooming out, dithering, distorting, etc.) and the like.

In some embodiments, the system runtime layer provides support for the upper layer, i.e., the framework layer, and when the framework layer is used, the android operating system runs the C/C + + library included in the system runtime layer to implement the functions to be implemented by the framework layer.

In some embodiments, the kernel layer is a layer between hardware and software. As shown in fig. 4, the core layer includes at least one of the following drivers: audio drive, display drive, bluetooth drive, camera drive, WIFI drive, USB drive, HDMI drive, sensor drive (such as fingerprint sensor, temperature sensor, touch sensor, pressure sensor, etc.), and so on.

In some embodiments, the kernel layer further comprises a power driver module for power management.

In some embodiments, software programs and/or modules corresponding to the software architecture of fig. 4 are stored in the first memory or the second memory shown in fig. 2 or 3.

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) that a user acts on a display screen, and the kernel layer may generate a corresponding input event according to the input operation and report the event to the application framework layer. The window mode (such as multi-window mode) corresponding to the input operation, the position and size of the window and the like are set by an activity manager of the application framework layer. And the window management of the application program framework layer draws a window according to the setting of the activity manager, then sends the drawn window data to the display driver of the kernel layer, and the display driver displays the corresponding application interface in different display areas of the display screen.

In some embodiments, as shown in fig. 5, the application layer containing at least one application may display a corresponding icon control in the display, such as: the system comprises a live television application icon control, a video on demand application icon control, a media center application icon control, an application center icon control, a game application icon control and the like.

In some embodiments, the live television application may provide live television via different signal sources. For example, a live television application may provide television signals using input from cable television, radio broadcasts, satellite services, or other types of live television services. And, the live television application may display video of the live television signal on the display device 200.

In some embodiments, a video-on-demand application may provide video from different storage sources. Unlike live television applications, video on demand provides a video display from some storage source. For example, the video on demand may come from a server side of the cloud storage, from a local hard disk storage containing stored video programs.

In some embodiments, the media center application may provide various applications for multimedia content playback. For example, a media center, which may be other than live television or video on demand, may provide services that a user may access to various images or audio through a media center application.

In some embodiments, an application center may provide storage for various applications. The application may be a game, an application, or some other application associated with a computer system or other device that may be run on the smart television. The application center may obtain these applications from different sources, store them in local storage, and then be operable on the display device 200.

The hardware or software architecture in some embodiments may be based on the description in the above embodiments, and in some embodiments may be based on other hardware or software architectures that are similar to the above embodiments, and it is sufficient to implement the technical solution of the present application.

In some embodiments, a voice assistant application may be disposed in the application center, and the voice assistant application may receive a user voice, recognize a user request according to the voice, further analyze the user request to obtain a user intention, perform a corresponding action according to the user intention, for example, control a display device, or play a response result corresponding to the user intention, such as a corresponding audio or video.

In some embodiments, the voice assistant application may also be provided on other devices, such as a speaker device.

In some embodiments, the controller of the display device may pre-train a user intention recognition model from which to recognize the user intention from the user request.

In some embodiments, training a user intention recognition model requires inputting a large amount of tag data into the model, extracting sample features of the same tag according to tag learning text classification, namely, deep learning, classifying the sample according to the sample feature learning, inputting a user request into the model after training is finished, recognizing the tag after the user request is classified through the model, and selecting a corresponding service module according to the tag to process the user request.

However, in many scenarios, it is very expensive, difficult, or even impossible to collect a large amount of tag data, and the increasing updating of the functions of the display device may generate many new business modules, which may lead to the user's intention that the recognition model needs to be trained by adding new tag data, and if the tag data is too small, the generalization of the recognition result may not reach the intended goal.

In order to solve the technical problem, in the embodiment of the application, a user intention recognition model based on small sample learning is trained in advance, and the model can achieve a better classification effect by using a small number of samples, so that the accuracy of user intention recognition is improved.

Referring to fig. 6, model training and prediction can be performed through the label data, wherein the label data can be sampled during training, a C way k shot mode can be selected for sampling, a model file can be obtained after model training is performed according to the sampled data, and further, the classification effect of the model can be verified according to the model training result, so that the model is corrected; when prediction is carried out, the label data can be sampled in a C way k shot mode, the sampled data and the user request are input into a trained model, and the type prediction of the user request can be realized.

In some embodiments, a user intent recognition model may be pre-constructed and then trained using label data.

Referring to fig. 7, the user intention recognition model constructed in the embodiment of the present application may include an Input Layer, an Embedding Layer, a bidirectional LSTM (Long Short Term), an Attention Layer, a Similarity Layer, and an Output Layer, where the Embedding Layer, the bidirectional LSTM Layer, and the Attention Layer may form an encoding Layer for extracting features, and after inputting tag data into the Input Layer of the user intention recognition model, the encoding Layer, the relationship Layer, and the encoding Layer are sequentially processed, and a tag in the tag data may be Output at the Output Layer, so as to complete one training.

Specific training method of the user intention recognition model referring to fig. 8, which is a flow chart of a training method of the user intention recognition model according to some embodiments, the method may include the following steps:

step S110: samples in a training sample set are divided into a plurality of training groups, and each training group comprises a support set and a query set.

In some embodiments, the training sample set may be derived from the label data shown in fig. 6, each piece of label data may be used as a sample of the training sample set, and the label may be a classification identifier added manually for determining the business module. The business module can be a functional module capable of responding to a sample or a user request in a certain field, such as an encyclopedia module, a movie module, a music module and the like.

In some embodiments, based on the tags, c classes may be randomly drawn from the training sample set, k samples may be randomly drawn from each of the c classes to form a support set, which may also be referred to as a SupportSet, and some classes may be randomly drawn from the remaining samples in the training sample set, k samples may be randomly drawn from each of the classes to form a query set, which may also be referred to as a query set. The support set and the query set constitute a training set.

And continuously extracting samples from the rest samples in the training sample set to form a next training group, and repeating the steps until the training sample set is divided into a plurality of training groups, wherein each training group comprises a support set and a query set, and the number of samples in all classes in one training group is the same.

In some embodiments, the support set has c-3 and k-5, and the query set may have 3 categories, and k-5 categories. An example of a support set and a query set is as follows:

support:{

searching for inter-vocals, looking up inter-folk classic fun inter-vocals

Searching for inter-folk photo and sound film collection

Searching for inter-national phase sound

Searching for the great voice of the great news of the plum-tiger

Search for inter-phase sound, find the complete set of inter-phase sound of Zhude just and fun

Searching films and televisions, and playing a film to a person who wants to see Sichuan at home

Searching movies, and playing movies that are ill at home and want to watch Ningxia to me

Searching movies and televisions, and playing a TV show that a person is ill and wants to watch Tianjin at home

Searching films and televisions, and playing a film which is sick at home and wants to see Tianjin

Searching films and televisions, and playing a film which is sick at home and wants to watch Taiwan to me

Music of song search, Zhao Lei unable to grow up

Song search, Zhao Lin singing a song

Song search, Zhao Peng song sadness

Song search, Zhao Peng go to ask for a white balloon

Song search, Zhao Wei Song emotion deep rain Mongolian

}

query:{

Searching the vocals, and showing the vocals of Mashuchun to me

Search for phase sounds, the most intense phase sounds of Martensing's performance being those

Search for phase phonetics, marming's phase phonetics

Searching the phase sound, and broadcasting the phase sound with the highest score in the equine season by one

Phase sound search, where a good yellow iron is found

Film obtained through Cannes international movie festival in movie and television search and high-speed key performance

TV play series for obtaining the golden panda prize of Sichuan TV festival

Searching film and television, finding out the film which has acquired the most popular actor prize of golden eagle

Video search, finding out one super-clear play for the films played in super-close two years in Deng

Film searching, and finding one of the best new people's prizes from the film beyond the desire to see the aspects of youth and spring

Song search, Gong Yue Meng in Water

Classical music appreciation of China in Song search, Ma Chengdong

Song search, magic castle music video

Song search to return to a seventeen year old song

Song search, drunk Chibi Linjunjie's song

}

Wherein, the vocal search and the song search are labels for determining the service module for responding.

Step S120: and inputting the training group into a user intention recognition model, and respectively extracting sample features of the support set and sample features of the query set.

When training is started for the user intention recognition model once, the support set and the query set in a training set can be respectively input into the input layer of the user intention recognition model.

In some embodiments, the encoding layer of the user intent recognition model may process the support set and the query set in parallel, respectively.

In some embodiments, the X1, X2, … X of the input layer_TCan be represented as a sample of a support set, the input layer will support the set { x1, x 2.. x_TAnd outputting the data to an encoding layer for processing.

In some embodiments, the encoding layer includes an embedding layer, a bi-directional LSTM layer, and an attention layer, and referring to fig. 9, the processing of the support set by the encoding layer may include steps S1201-S1203.

Step S1201: and processing the sample in the support set through an embedding layer to obtain a first vector.

In some embodiments, the embedding layer may represent each sample of the support set as a first vector, respectively, resulting in a set { e1, e 2.. e_TThe embedding layer outputs the set to the bi-directional LSTM layer.

Step S1202: and extracting context information of the first vector through a long and short memory neural network layer to obtain a first correction vector corresponding to the first vector.

In some embodiments, the bi-directional LSTM layer may extract context information for each sample, where the context information may be represented as

Or

For example, the context information of e1 can be expressed as

The context information of e2 can be expressed as

The bidirectional LSTM layer is equivalent to two layers of neural networks, one layer is used as input from the beginning of a sentence, and the other layer is used as input from the last word of the sentence; and finally, splicing the two layers to obtain context information, wherein the sentence can refer to a sample.

For example, will

After splicing, obtaining context information: a first correction vector h1, will

After the splicing, a first correction vector h2 is obtained.

The set of first modified vectors corresponding to the query set may be denoted as H, e.g., H ═ H1, H2 … hT ], and the bi-directional LSTM layer outputs the set H to the attention layer.

Step S1203: extracting key sentence features of the first correction vector through an attention layer.

In some embodiments, the Attention layer may extract key features of the sentence using the Attention mechanism, and the calculation formula is as follows:

M＝Tanh(H)

α＝SOftmax(w^TM)

r＝Hα² (1)

(1) wherein M represents a hidden layer state representation; α represents the probability after the Softmax normalization as the weight of the attention mechanism; r represents a first correction vector.

d^wRepresenting the pre-trained word vector dimension, w^TIs the transpose of a parameter for training learning, and the key sentence features used to characterize SupportSet are:

h'＝tanh(r) (2)

in some embodiments, the key sentence features may be represented as sample features, i.e., features of a sentence, wherein a sentence may refer to a sample.

In some embodiments, the X1, X2, … X of the input layer_TThe query set can be represented as a sample of the query set, and after the query set is output to the coding layer through the input layer, the key sentence characteristics of the QuerySet can be obtained.

Referring to FIG. 10, the processing of the query set by the encoding layer may include steps S1211-S1213.

Step S1211: and processing the samples in the query set through an embedding layer to obtain a second vector.

Step S1212: and extracting context information of the second vector through a long and short memory neural network layer to obtain a second correction vector corresponding to the second vector.

Step S1213: extracting key sentence features of the second correction vector through an attention layer.

In some embodiments, the specific processes of steps S1211-S1213 are different from the steps S1201-S1203 in that the processing objects are different, that is, the processing objects of steps S1201-S1203 are samples of the support set, the processing objects of steps S1211-S1213 are samples of the query set, and the specific algorithms of steps S1211-S1213 may refer to steps S1201-S1203, which is not described herein again.

Step S130: and calculating the similarity between the sample characteristics of the support set and the sample characteristics of the query set through a cosine function.

In some embodiments, the distance between the support set and the query set may be calculated by a cosine function, as follows:

(3) wherein i is 1, 2_iSamples in SupportSet, e.g. x_jAs samples in QuerySet, d_θThe presentation relationship measurement network module is,

a representation feature extraction network module;

representing a feature representation representing a support set;

representing a feature representation representing a set of queries; c represents a linkage; wherein the feature representations of the support set and the query set are obtained by the results of equation (2).

Further, the distance may be mapped to a preset range by a ReLu (linear rectification) function, so as to obtain the similarity between the support set and the query set. In some embodiments, the predetermined range may include 0-1.

Step S140: and calculating a loss function of the user intention recognition model according to the similarity.

In some embodiments, the model loss function may be calculated by a MSE (mean square error) function, which is calculated as follows:

(4) in the formula, y_iRepresenting a support set label; y is_jThe representation represents a query set tag.

In some examples, after the Softmax normalization is used, the prediction result with the highest probability is obtained as the output y ^ and finally the prediction label corresponding to the input sample is obtained.

Step S150: optimizing the loss function through a plurality of the training sets until the user intent recognition model converges.

In some embodiments, data of a plurality of training groups are sequentially input to the user intention recognition model for iterative training, back propagation is performed by using gradients, training parameters of the user intention recognition model are updated until the iteration number reaches a set threshold, the loss of the verification set does not decrease any more, and the accuracy does not increase any more, the user intention recognition model is judged to be converged, training is stopped for the user intention recognition model, and the user intention recognition model is stored.

In some embodiments, during training, the overfitting may be reduced using L2 regularization and Dropout methods.

In some embodiments, after a user intention recognition model is trained, the user intention recognition model may be stored in a controller of a display device, the display device may perform text recognition on a voice command after receiving the voice command of a user through a voice assistant application to obtain a user request, input the user request as a query into the user intention recognition model, perform text classification on the user request through the user intention recognition model, output a category tag of the user request, process the user request according to a service module corresponding to the category tag to obtain a response result, and control a display to display the response result.

In some embodiments, after a user intention recognition model is trained, the user intention recognition model may be stored in a server, a display device is in communication connection with the server, the display device may perform text recognition on a voice command after receiving the voice command of a user through a voice assistant application to obtain a user request, send the user request to the server, the server inputs the user request as a query into the user intention recognition model, performs text classification on the user request through the user intention recognition model, outputs a category tag of the user request, processes the user request according to a service module corresponding to the category tag to obtain a response result, and the server sends the response result to the display device to cause the display device to display the response result.

According to the embodiment, the user intention recognition model is trained based on a small sample classification mode, and compared with the traditional deep learning mode, the C way-K shot training mode is adopted in the training process, and sample data can be fully utilized. Calculating similarity by cosine adopted by the relation weighing layer, and combining with a relu activation function; under the condition of high-dimensional characteristics, the cosine is utilized to calculate the similarity, and the higher the similarity is, the closer the value is to 1, the orthogonal value is 0, and the opposite value is-1; combining with relu activation function, ensuring that the value of the feature vector is 0 when the feature vector is orthogonal and opposite, and the higher the similarity is, the closer the value is to 1; the method has a good effect on calculating the feature similarity of a high-dimensional space to a certain extent, and can be trained by using a small amount of data based on a small sample classification mode, has small interference on the original intention categories, has certain generalization on the newly added intention categories, and has high accuracy and recall ratio of the newly added categories.

Since the above embodiments are all described by referring to and combining with other embodiments, the same portions are provided between different embodiments, and the same and similar portions between the various embodiments in this specification may be referred to each other. And will not be described in detail herein.

It is noted that, in this specification, relational terms such as "first" and "second," and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a circuit structure, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such circuit structure, article, or apparatus. Without further limitation, the presence of an element identified by the phrase "comprising an … …" does not exclude the presence of other like elements in a circuit structure, article, or device comprising the element.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims. The above embodiments of the present application do not limit the scope of the present application.

Claims

1. A training method of a user intention recognition model is characterized by comprising the following steps:

2. The method of claim 1, wherein the number of samples in all categories in the support set and the query set are the same.

3. The training method of a user intention recognition model according to claim 1, wherein each of the samples is provided with a label.

4. The method for training a user intention recognition model according to claim 1, wherein the extracting sample features of the support set comprises:

5. The method for training a user intention recognition model according to claim 1, wherein the extracting sample features of the query set comprises:

6. The training method of the user intention recognition model according to claim 1, wherein the calculating the similarity between the support set and the query set by a cosine function comprises:

calculating the distance between the support set and the query set through a cosine function;

and mapping the distance to a preset range through a linear rectification function to obtain the similarity between the support set and the query set.

7. A training method for a user intention recognition model according to claim 1, wherein the model loss function comprises a mean square error function.

8. A server, characterized in that the server is configured to perform the method of any of claims 1-7.

9. A server, wherein the server is configured to:

sending the response result to a display device;

wherein the user intent recognition model is trained based on the method of any of claims 1-7.

10. A display device, comprising:

a display;

a controller connected with the display, the controller configured to:

controlling a display to display the response result;