Display apparatus and reply language generation method

Abstract

The invention relates to a display device and a reply language generation method. The method belongs to the technical field of display equipment, and comprises the following steps: determining a target attribute score of current text interaction content in each field according to the current text interaction content and a historical interaction record; and obtaining a target reply language corresponding to the current text interaction content from a corpus according to the current text interaction content and the target attribute score of the current text interaction content in each field. And controlling the display device to display the target reply language. When the display device generates the target reply language, not only is the current text interaction content considered, but also the historical interaction record is considered. According to the embodiment of the invention, the target attribute score of the current text interaction content in each field is determined based on the current text interaction content and the historical interaction record, and the target reply language corresponding to the current text interaction content is determined based on the target attribute score, so that the finally obtained reply language is more accurate and can better meet the requirements of a user, and the user experience is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of display devices, and in particular to a display device and a method for generating a reply message. Background Art

[0002] With the rapid development of artificial intelligence, voice interaction has become a key function of display devices (such as smart TVs). The voice interaction function not only enriches the functions of display devices, but also increases the frequency of users using display devices.

[0003] However, the voice interaction function of existing display devices is limited to using specified rules to match scene replies. The reply sentences are relatively simple and users cannot get the answers they want, resulting in a poor user experience. Summary of the invention

[0004] Based on this, it is necessary to provide a display device and a reply generation method that can improve the accuracy of reply generation in response to the above technical problems.

[0005] In a first aspect, the present application provides a display device. The display device includes:

[0006] a display configured to display content from a broadcast system or network and / or a user interface;

[0007] A user input interface configured to receive current text interaction content initiated by a user;

[0008] and at least one controller connected to the display and configured to:

[0009] Determine the target attribute scores of the current text interaction content in various fields based on the current text interaction content and historical interaction records;

[0010] According to the current text interaction content and the target attribute scores of the current text interaction content in various fields, the target reply words corresponding to the current text interaction content are obtained from the corpus;

[0011] Control the display device to display the target reply language.

[0012] In this embodiment, the user input interface of the display device is configured to receive the current text interaction content initiated by the user; and at least one controller is connected to the display and is configured to: determine the target attribute scores of the current text interaction content in various fields according to the current text interaction content and the historical interaction records. And according to the current text interaction content and the target attribute scores of the current text interaction content in various fields, obtain the target reply language corresponding to the current text interaction content from the corpus. Control the display device to display the target reply language. When generating the target reply language, the display device of the present application not only considers the current text interaction content, but also considers the historical interaction records. Based on the current text interaction content and the historical interaction records, the target attribute scores of the current text interaction content in various fields are determined, and based on the target attribute scores, the target reply language corresponding to the current text interaction content is determined, so that the final reply language is more accurate, can better meet the needs of users, and effectively improve the user experience.

[0013] In one embodiment, when the controller determines the target attribute scores of the current text interaction content in various fields according to the current text interaction content and the historical interaction records, the controller is configured to:

[0014] Perform vertical domain analysis on the current text interaction content to obtain the first attribute score of the current text interaction content in each field;

[0015] Perform vertical domain analysis on historical interaction records to obtain the second attribute scores of historical interaction records in various fields;

[0016] According to the first attribute scores of the current text interaction content in each field and the second attribute scores of the historical interaction records in each field, the target attribute scores of the current text interaction content in each field are determined.

[0017] In this embodiment, the first attribute score of the current text interaction content in each field is obtained by performing a vertical domain analysis on the current text interaction content. And the second attribute score of the historical interaction record in each field is obtained by performing a vertical domain analysis on the historical interaction record. Finally, according to the first attribute score of the current text interaction content in each field and the second attribute score of the historical interaction record in each field, the target attribute score of the current text interaction content in each field is determined. In this embodiment, when determining the target attribute score of the current text interaction content in each field, the first attribute score of the current text interaction content in each field and the second attribute score of the historical interaction record in each field are determined, and the first attribute score and the second attribute score are comprehensively determined, thereby improving the rationality and accuracy of the determination of the target attribute score.

[0018] In one embodiment, when the controller determines the target attribute score of the current text interaction content in each field according to the first attribute score of the current text interaction content in each field and the second attribute score of the historical interaction record in each field, the controller is configured as follows:

[0019] For each domain, the sum of the first attribute score of the current text interaction content in the domain and the second attribute score of the historical interaction record in the domain is used as the domain attribute score;

[0020] The ratio of the first attribute score of the current text interaction content in the domain to the domain attribute score is used as the target attribute score of the current text interaction content in the domain.

[0021] In this embodiment, for each field, the sum of the first attribute score of the current text interaction content in the field and the second attribute score of the historical interaction record in the field is used as the field attribute score. The ratio of the first attribute score of the current text interaction content in the field to the field attribute score is used as the target attribute score of the current text interaction content in the field. Based on this embodiment, a strong association is achieved between the first attribute score and the second attribute score, further increasing the accuracy of the target attribute score.

[0022] In one embodiment, when the controller executes acquiring the target reply words corresponding to the current text interaction content from the corpus according to the current text interaction content and the target attribute scores of the current text interaction content in various fields, the controller is configured to:

[0023] Determine the category label of the current text interaction content according to the field corresponding to the maximum target attribute score;

[0024] According to the current text interaction content and category label, the target reply language corresponding to the current text interaction content is obtained from the corpus.

[0025] In this embodiment, the category label of the current text interaction content can be determined according to the domain corresponding to the maximum target attribute score. Then, according to the current text interaction content and the category label, the target reply language corresponding to the current text interaction content is obtained from the corpus, so that the domain category corresponding to the obtained target reply language is more consistent with the domain category preferred by the user, thereby improving the accuracy of the target reply language in the domain.

[0026] In one embodiment, when the user input interface receives the current text interaction content initiated by the user, it is configured to:

[0027] Receiving voice interaction content input by a user through a voice receiving device in an external control device or a display device;

[0028] Perform semantic analysis on the voice interaction content to obtain the user's current text interaction content.

[0029] In this embodiment, the voice interaction content input by the user through the voice receiving device in the external control device or display device is received. The voice interaction content is semantically analyzed to obtain the current text interaction content of the user. In this embodiment, the current text interaction content can be obtained based on the voice interaction content input by the voice receiving device in the external control device or display device, thereby increasing the flexibility of obtaining the current text interaction content.

[0030] In one embodiment, when the controller executes obtaining a target reply word corresponding to the current text interaction content from a corpus according to the current text interaction content and the category label, the controller is configured to:

[0031] Determine the user's target identity based on the voice interaction content;

[0032] According to the target identity, obtain the user's attribute information;

[0033] According to the attribute information, the current text interaction content and the category label, the target reply language corresponding to the current text interaction content is obtained from the corpus.

[0034] In this embodiment, the target identity of the user can be determined according to the voice interaction content. According to the target identity, the attribute information of the user is obtained. Finally, the attribute information, the current text interaction content and the category label are integrated to obtain the target reply language that meets the requirements of the three from the corpus. Since the attribute information of the user (for example, age, preference, gender, etc.) is taken into consideration, the obtained target reply language can better meet the needs of the user.

[0035] In one embodiment, the controller is further configured to:

[0036] Determine the user's target identity based on the voice interaction content;

[0037] Get the historical interaction records corresponding to the target identity.

[0038] In this embodiment, the historical interaction records corresponding to the target identity are obtained by obtaining the target identity of the user. That is, the historical interaction records in this application are historical interaction records that match the target identity, so that the historical interaction records match the user identity, increasing the accuracy of the target reply.

[0039] In one embodiment, the historical interaction record includes historical text interaction content and historical reply words corresponding to the historical interaction content.

[0040] In this embodiment, the historical interaction record includes historical text interaction content and historical reply language corresponding to the historical interaction content, that is, the text interaction content of historical rounds and the reply language of historical rounds, making the historical interaction record more meaningful for reference.

[0041] In one embodiment, while the display device displays the target reply language, the controller is further configured to:

[0042] Control the multimedia playback device in the display device to play the target reply language.

[0043] In this embodiment, the controller can control the multimedia playback device in the display device to play the target reply language, which not only realizes the voice dialogue between the user and the real device, but also improves the flexibility of the user in obtaining the target reply language.

[0044] In a second aspect, the present application also provides a method for generating a reply. The method comprises:

[0045] Determine the target attribute scores of the current text interaction content in various fields based on the current text interaction content and historical interaction records;

[0046] According to the current text interaction content and the target attribute scores of the current text interaction content in various fields, the target reply words corresponding to the current text interaction content are obtained from the corpus;

[0047] Control the display device to display the target reply language.

[0048] The reply language generation method of the present embodiment determines the target attribute scores of the current text interaction content in various fields according to the current text interaction content and the historical interaction records. And according to the current text interaction content and the target attribute scores of the current text interaction content in various fields, the target reply language corresponding to the current text interaction content is obtained from the corpus. The display device is controlled to display the target reply language. When generating the target reply language, the display device of the present application not only considers the current text interaction content, but also considers the historical interaction records. Based on the current text interaction content and the historical interaction records, the target attribute scores of the current text interaction content in various fields are determined, and based on the target attribute scores, the target reply language corresponding to the current text interaction content is determined, so that the final reply language is more accurate, can better meet the needs of users, and effectively improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] FIG1 is a schematic diagram of an operation scenario between a display device and a control device provided in some embodiments of the present application;

[0050] FIG2 is a schematic diagram of a hardware configuration of a display device provided in some embodiments of the present application;

[0051] FIG3 is a schematic diagram of a hardware configuration of a control device provided in some embodiments of the present application;

[0052] FIG4 is a schematic diagram of software configuration of a display device provided in some embodiments of the present application;

[0053] FIG5 is a flow chart of a first reply generation method provided in some embodiments of the present application;

[0054] Figure 6 A schematic diagram of a process for determining target attribute scores of current text interaction content in various fields provided in some embodiments of the present application;

[0055] Figure 7 A schematic diagram of a first process of obtaining a target reply language corresponding to the current text interaction content from a corpus provided in some embodiments of the present application;

[0056] Figure 8 A schematic diagram of a second process of obtaining a target reply language corresponding to the current text interaction content from a corpus provided in some embodiments of the present application;

[0057] Fig. 9 A timing diagram of a display device generating a target reply statement according to some embodiments of the present application. DETAILED DESCRIPTION

[0058] The following embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following embodiments do not represent all implementations consistent with the present application. They are only examples of systems and methods consistent with some aspects of the present application as detailed in the claims.

[0059] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings.

[0060] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0061] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0062] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0063] In the embodiment of the present application, the display device 200 generally refers to a device with image display and data processing capabilities. For example, the display device 200 includes but is not limited to a smart TV, a mobile terminal, a computer, a monitor, an advertising screen, a wearable device, a virtual reality device, an augmented reality device, etc.

[0064] Figure 1 is a schematic diagram of an operation scenario between a display device and a control device provided in some embodiments of the present application. As shown in Figure 1, a user can operate a display device 200 through touch operation, a mobile terminal 300, and a control device 100. For example, the control device 100 can be a remote controller, a stylus, a handle, etc.

[0065] The mobile terminal 300 can be used as a control device for performing human-computer interaction between the user and the display device 200. The mobile terminal 300 can also be used as a communication device for establishing a communication connection with the display device 200 and performing data interaction. In some embodiments, the mobile terminal 300 can install software applications with the display device 200, and achieve connection and communication through a network communication protocol to achieve the purpose of one-to-one control operation and data communication. The audio and video content displayed on the mobile terminal 300 can also be transmitted to the display device 200 to achieve a synchronous display function.

[0066] 1 , the display device 200 also communicates data with the server 400 through various communication methods. The display device 200 may be allowed to communicate and connect through a local area network (LAN), a wireless local area network (WLAN) and other networks.

[0067] The display device 200 may provide a broadcast receiving television function, and may also additionally provide an intelligent network television function of a computer support function, including but not limited to network television, smart television, Internet Protocol television (IPTV), etc.

[0068] FIG. 2 is a hardware configuration block diagram of the display device 200 in FIG. 1 provided in some embodiments of the present application.

[0069] In some embodiments, the display device 200 may include at least one of a tuner 210, a communication device 220, a detector 230, a device interface 240, a controller 250, a display 260, an audio output device 270, a memory, a power supply, and a user input interface.

[0070] In some embodiments, the detector 230 is used to collect signals of the external environment or external interaction. For example, the detector 230 includes a light receiver, a sensor for collecting the intensity of ambient light; or, the detector 230 includes an image collector, such as a camera, which can be used to collect external environment scenes, user attributes or user interaction gestures; or, the detector 230 includes a sound collector, such as a microphone, etc., for receiving external sounds.

[0071] In some embodiments, the display 260 includes a display function component for presenting a picture, and a driving component for driving an image display. The display 260 is used to receive an image signal output from the controller 250 for display. For example, the display 260 can be used to display video content, image content, and components of a menu control interface and a user control UI interface.

[0072] In some embodiments, the communication device 220 is a component for communicating with an external device or server 400 according to various communication protocol types. The display device 200 may be provided with a plurality of communication devices 220 according to different supported communication modes. For example, when the display device 200 supports wireless network communication, the display device 200 may be provided with a communication device 220 including a WiFi function. When the display device 200 supports Bluetooth connection communication, the display device 200 needs to be provided with a communication device 220 including a Bluetooth function.

[0073] The communication device 220 can enable the display device 200 to communicate with the external device or server 400 by wireless or wired connection. Among them, the wired connection can connect the display device 200 with the external device through components such as data cables and interfaces. The wireless connection can connect the display device 200 with the external device through wireless signals or wireless networks. The display device 200 can establish a connection relationship with the external device directly, or indirectly establish a connection relationship through a gateway, a router, a connection device, etc.

[0074] In some embodiments, the controller 250 may include at least one of a central processing unit, a video processor, an audio processor, a graphics processor, and a power processor, and a first interface to an nth interface for input / output. The controller 250 controls the operation of the display device and responds to the user's operation through various software control programs stored in the memory. The controller 250 controls the overall operation of the display device 200.

[0075] 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 also be located in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0076] In some embodiments, the user may input a user command through a graphical user interface (GUI) displayed on the display 260 , and the user input interface receives the user input command through the graphical user interface (GUI).

[0077] In some embodiments, the audio output device 270 may be a local speaker of the display device 200, or may be an external audio output device of the display device 200. In particular, for the external audio output device of the display device 200, the display device 200 may also be provided with an external audio output terminal, and the audio output device may be connected to the display device 200 through the external audio output terminal to output the sound of the display device 200.

[0078] In some embodiments, the user input interface 280 may be used to receive instructions from a user.

[0079] Fig. 3 is a hardware configuration block diagram of the control device in Fig. 1 provided in some embodiments of the present application. As shown in Fig. 3, the control device 100 may include: a controller 110, a communication interface 130, a user input / output interface, a memory, and a power supply.

[0080] The control device 100 is configured to control the display device 200 , and can receive user input operation instructions, and convert the operation instructions into instructions that the display device 200 can recognize and respond to, playing the role of an interactive intermediary between the user and the display device 200 .

[0081] 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.

[0082] In some embodiments, as shown in FIG. 1 , the mobile terminal 300 or other intelligent electronic device can perform similar functions to the control device 100 after installing an application for operating the display device 200 .

[0083] The controller 110 includes a processor 112, a RAM 113, a ROM 114, a communication interface 130, and a communication bus. The controller 110 is used to control the operation and operation of the control device 100, as well as the communication and cooperation between the internal components and the external and internal data processing functions.

[0084] The communication interface 130 implements communication of control signals and data signals with the display device 200 under the control of the controller 110. The communication interface 130 may include at least one of other near field communication modules such as a WiFi chip 131, a Bluetooth module 132, and an NFC module 133.

[0085] The user input / output interface 140 , wherein the input interface includes at least one of other input interfaces such as a microphone 141 , a touch panel 142 , a sensor 143 , and a button 144 .

[0086] 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 a WiFi, Bluetooth, NFC or other module, and can encode the user input command through the WiFi protocol, Bluetooth protocol, or NFC protocol and send it to the display device 200.

[0087] The memory 190 is used to store various operating programs, data and applications for driving and controlling the control device 100 under the control of the controller. The memory 190 can store various control signal instructions input by the user.

[0088] The power supply 180 is used to provide operating power support for each component of the control device 100 under the control of the controller.

[0089] In order to perform user interaction, in some embodiments, the display device 200 may run an operating system. The operating system is a computer program for managing and controlling hardware resources and software resources in the display device 200. The operating system may (control the display device) provide a user interface, allow the user to interact with the display device 200, and support the running of various application programs.

[0090] It should be noted that the operating system can be a native operating system based on a specific operating platform, a third-party operating system deeply customized based on a specific operating platform, or an independent operating system specially developed for the display device.

[0091] The operating system can be divided into different modules or levels according to the functions implemented, as shown in Figure 4, which is a schematic diagram of the software configuration in the display device in Figure 1 provided in some embodiments of the present application. In some embodiments, the system of the display device 200 can be divided into three layers, namely, the application layer, the middleware layer and the hardware layer from top to bottom.

[0092] The application layer mainly includes commonly used applications on TV and application frameworks. Common applications are mainly applications developed based on browsers, such as HTML5 APPs and native APPs.

[0093] The Application Framework is a complete program model that has all the basic functions required by standard application software, such as file access, data exchange, etc., as well as the user interfaces of these functions (toolbars, status bars, menus, dialog boxes).

[0094] Native apps can support online or offline, message push or local resource access.

[0095] The middleware layer includes various TV protocols, multimedia protocols, system components and other middleware. Middleware can use the basic services (functions) provided by the system software to connect various parts of the application system or different applications on the network, and can achieve the purpose of resource sharing and function sharing.

[0096] The hardware layer mainly includes the hardware abstraction layer (HAL) interface, hardware and drivers. The HAL interface is a unified interface for all TV chips to connect, and the specific logic is implemented by each chip. Drivers mainly include: audio driver, display driver, Bluetooth driver, camera driver, WIFI driver, USB driver, HDMI driver, sensor driver (such as fingerprint sensor, temperature sensor, pressure sensor, etc.), and power driver.

[0097] It should be noted that the above example is only a simple division of the operating system functions and does not constitute a limitation on the specific operating system form of the display device 200 in the embodiment of the present application. Depending on factors such as the function of the display device and the type of operating system, the number of levels and specific level types contained in the operating system may be expressed in other forms.

[0098] The above embodiments illustrate the hardware / software architecture and functional implementation of a display device 200. In some embodiments, the display device 200 is configured with a user interaction application, and the display in the display device 200 can display the interactive interface of the user interaction application; the controller in the display device can receive the control signal of the control device 100, and control the display in the display device to display the user interaction application according to the control signal; the user can control the display device 200 through the control device 100 to perform user interaction operations in the user interaction application; the user's voice can also be received through the sound collector in the detector 230 to interact with the user to complete the user interaction operation in the user interaction application.

[0099] With the rapid development of artificial intelligence, voice interaction has become a key function of display devices (e.g., smart TVs). The voice interaction function not only enriches the functions of display devices, but also increases the frequency of users using display devices. However, the voice interaction function of existing display devices is limited to using specified rules to match scene replies. The reply sentences are relatively simple, and users cannot get the answers they want, resulting in a poor user experience.

[0100] Based on this, in some embodiments, the present application provides a display device, which includes: a display configured to display content from a broadcast system or network and / or a user interface; a user input interface configured to receive current text interaction content initiated by a user; and at least one controller connected to the display and configured to: determine the target attribute scores of the current text interaction content in various fields according to the current text interaction content and the historical interaction records. And according to the current text interaction content and the target attribute scores of the current text interaction content in various fields, obtain the target reply language corresponding to the current text interaction content from the corpus. Control the display device to display the target reply language. When generating the target reply language, the display device of the present application not only considers the current text interaction content, but also considers the historical interaction records. Based on the current text interaction content and the historical interaction records, the target attribute scores of the current text interaction content in various fields are determined, and based on the target attribute scores, the target reply language corresponding to the current text interaction content is determined, so that the final reply language is more accurate, can better meet the needs of users, and effectively improve the user experience.

[0101] Optionally, referring to FIG5 , the method for generating a reply message applied to a controller of a display device comprises the following steps:

[0102] S501, determining the target attribute scores of the current text interaction content in various fields according to the current text interaction content and the historical interaction records.

[0103] Among them, the current text interaction content refers to the text content of the conversation initiated by the user requesting the display device to make a corresponding reply. The historical interaction record refers to the content of the user's interaction with the display device in a preset historical period stored by the display device. The target attribute score refers to the score of the field that the current text interaction content tends to. The higher the score, the more the current text interaction content tends to that field, such as sports, life, medicine, movies, variety shows, and TV series.

[0104] Optionally, the historical interaction content in this embodiment includes but is not limited to the historical text interaction content and the historical reply language corresponding to the historical interaction content. The historical text interaction content refers to the text interaction content initiated by the user to the display device within a preset historical period. The historical interaction record in this embodiment includes the historical text interaction content and the historical reply language corresponding to the historical interaction content. That is, the text interaction content of the historical rounds and the reply language of the historical rounds make the historical interaction record more meaningful for reference.

[0105] In this embodiment, an optional implementation method for obtaining the current text interaction content is to receive the voice interaction content input by the user through the voice receiving device in the external control device or the display device. The voice interaction content is semantically analyzed to obtain the user's current text interaction content. Among them, the external control device can be a user terminal (for example, a mobile phone, a computer, a smart watch, a smart bracelet, etc.), or a remote control of the display device. The voice receiving device refers to a microphone or other voice detector of the display device. In this embodiment. An optional implementation method for performing semantic analysis on the voice interaction content to obtain the user's current text interaction content is to pre-process the voice interaction content and extract voiceprint features and audio segments. Then remove the redundant information of the audio segment to obtain the current text interaction content. Among them, the pre-processing method includes but is not limited to filtering, framing, breakpoint detection and other pre-processing. The method for extracting voiceprint features and audio segments adopts but is not limited to the Mel Frequency Cepstral Coefficients (MFCC) method to extract features.

[0106] Another optional implementation of acquiring the current text interaction content in this embodiment is to receive the current text interaction content input by the user through an external control device or a voice receiving device in a display device, for example, through an input control.

[0107] In this embodiment, an optional implementation method for obtaining historical interaction records is that the controller retrieves historical interaction content within a preset historical period from the memory according to a preset historical period.

[0108] Another optional implementation method for obtaining historical interaction records in this embodiment is that if the current text interaction content is determined based on the voice interaction content, the user's target identity is determined based on the voiceprint features corresponding to the voice interaction content. According to the preset historical period and target identity, the historical interaction content that matches the target identity is obtained. By obtaining the user's target identity, the historical interaction records corresponding to the target identity are obtained. In other words, the historical interaction records in this application are historical interaction records that match the target identity, so that the historical interaction records match the user identity, which increases the accuracy of the target reply.

[0109] As an optional implementation method of the embodiment of the present application, the current text interaction content and historical interaction records are input into a neural network model, and the neural network model outputs the target attribute scores of the current text interaction content in various fields.

[0110] Another optional implementation of the embodiment of the present application is to perform semantic analysis on the current text interaction content and the historical interaction content respectively, and determine the target attribute scores of the current text interaction content in various fields based on the speech analysis results.

[0111] S502, acquiring a target reply language corresponding to the current text interaction content from a corpus according to the current text interaction content and the target attribute scores of the current text interaction content in various fields.

[0112] Among them, corpus refers to a large-scale collection of language samples, which is usually used in various fields such as linguistic research, natural language processing (NLP), machine translation, text analysis, dictionary compilation, language teaching, etc. The target response language refers to the response language corresponding to the current text interaction content.

[0113] As an optional implementation of the embodiment of the present application, the current text interaction content and the target attribute scores of the current text interaction content in various fields are input into the language analysis model, and the language analysis model obtains the target response language corresponding to the current text interaction content from the corpus. The language analysis model can be natural language processing or dialogue system models.

[0114] Another optional implementation method of the present application is to perform word segmentation processing on the current text interaction content to obtain the corresponding content word vector. Obtain candidate noun entities corresponding to each content word vector from the corpus. Then, based on the domain category of each candidate noun entity and the target attribute score of the current text interaction content in each domain, select the candidate noun entity with the closest domain category from each candidate noun entity as the target noun entity corresponding to the content word vector. Generate a target reply based on each target noun entity and language logic rules.

[0115] S503, controlling the display device to display the target reply language.

[0116] As an optional implementation of the embodiment of the present application, if the current text interaction content is determined based on the voice interaction content, the target identity of the user is determined based on the voice interaction content. According to the target identity, attribute information matching the target identity is obtained from the database, including but not limited to age, gender, language information, and preference information. According to the attribute information, the display device is controlled to display the target reply language that meets the attribute characteristics. For example, if the user is young, the target reply language can be displayed in eye protection mode. If the user is older, the target reply language is displayed in a large font based on the user's preference information.

[0117] As another optional implementation of the embodiment of the present application, while the display device displays the target reply, the multimedia playback device in the display device is controlled to play the target reply, for example, the multimedia playback device in the display device is controlled to voice play the target reply. Specifically, if the current text interaction content is determined based on the voice interaction content, the target identity of the user is determined based on the voice interaction content. According to the target identity, attribute information matching the target identity is obtained from the database, including but not limited to age, gender, language information and preference information. According to the attribute information, the multimedia playback device in the display device is controlled to play the target reply. For example, according to the user's preference information, the user's preferred volume is determined. According to the preferred volume, the multimedia playback device in the display device is controlled to play the target reply. For another example, according to the user's preference information, the user's preferred timbre (for example, male, female, uncle, cartoon, etc.) is determined. According to the preferred timbre, the multimedia playback device in the display device is controlled to play the target reply.

[0118] In this embodiment, the user input interface of the display device is configured to receive the current text interaction content initiated by the user; and at least one controller is connected to the display and is configured to: determine the target attribute scores of the current text interaction content in various fields according to the current text interaction content and the historical interaction records. And according to the current text interaction content and the target attribute scores of the current text interaction content in various fields, obtain the target reply language corresponding to the current text interaction content from the corpus. Control the display device to display the target reply language. When generating the target reply language, the display device of the present application not only considers the current text interaction content, but also considers the historical interaction records. Based on the current text interaction content and the historical interaction records, the target attribute scores of the current text interaction content in various fields are determined, and based on the target attribute scores, the target reply language corresponding to the current text interaction content is determined, so that the final reply language is more accurate, can better meet the needs of users, and effectively improve the user experience.

[0119] In one embodiment, in order to more accurately determine the target reply language that meets the user's requirements, such as Figure 6 As shown, the controller performs an optional implementation method of determining the target attribute scores of the current text interaction content in various fields according to the current text interaction content and the historical interaction records, including:

[0120] S601, performing vertical domain analysis on the current text interaction content to obtain the first attribute score of the current text interaction content in each field.

[0121] The first attribute score refers to the attribute scores in different fields obtained by performing field analysis on the current text information.

[0122] Optionally, in this embodiment, a deep learning network is used to perform vertical domain analysis on the current text information to obtain the first attribute score of the current text interaction content in each field. Specifically, the deep learning network maps the words in the current text interaction content to low-dimensional vector representations, so that semantically similar words are closer in low-order space; through the CNN convolution layer, the convolution operation extracts the combined representation of adjacent characters or words to capture the combined features between words, better extract the global features of the sentence, obtain the grammatical and semantic information of the current text interaction content, and then obtain the first attribute score of the current text interaction content in each field.

[0123] S602, performing vertical domain analysis on the historical interaction records to obtain the second attribute scores of the historical interaction records in each domain.

[0124] The second attribute score refers to the attribute scores of historical interaction records in different fields obtained by vertical domain analysis of historical interaction records.

[0125] Optionally, in this embodiment, a deep learning network is used to perform vertical domain analysis on the historical interaction records to obtain the second attribute scores of the historical interaction records in each field.

[0126] It should be noted that the principle of using a deep learning network to determine the second attribute score of historical interaction records in various fields is roughly the same as the principle of determining the first attribute score, and will not be repeated here.

[0127] S603, determining a target attribute score of the current text interaction content in each field according to the first attribute score of the current text interaction content in each field and the second attribute score of the historical interaction record in each field.

[0128] Optionally, in this embodiment, for each field, the sum of the first attribute score of the current text interaction content in the field and the second attribute score of the historical interaction record in the field is used as the field attribute score. The ratio of the first attribute score of the current text interaction content in the field to the field attribute score is used as the target attribute score of the current text interaction content in the field.

[0129] Specifically, the target attribute scores of the current text content in different fields can be determined by the following formula (1):

[0130] (1)

[0131] Among them, S i represents the target attribute score of the i-th domain; e V i represents the first attribute score of the i-th field; C represents the number of fields.

[0132] In this embodiment, for each field, the sum of the first attribute score of the current text interaction content in the field and the second attribute score of the historical interaction record in the field is used as the field attribute score. The ratio of the first attribute score of the current text interaction content in the field to the field attribute score is used as the target attribute score of the current text interaction content in the field. Based on this embodiment, a strong association is achieved between the first attribute score and the second attribute score, further increasing the accuracy of the target attribute score.

[0133] In this embodiment, the first attribute score of the current text interaction content in each field is obtained by performing a vertical domain analysis on the current text interaction content. And the second attribute score of the historical interaction record in each field is obtained by performing a vertical domain analysis on the historical interaction record. Finally, according to the first attribute score of the current text interaction content in each field and the second attribute score of the historical interaction record in each field, the target attribute score of the current text interaction content in each field is determined. In this embodiment, when determining the target attribute score of the current text interaction content in each field, the first attribute score of the current text interaction content in each field and the second attribute score of the historical interaction record in each field are determined, and the first attribute score and the second attribute score are comprehensively determined, thereby improving the rationality and accuracy of the determination of the target attribute score.

[0134] In one embodiment, in order to increase the accuracy of the target response, such as Figure 7 As shown, the controller executes an optional implementation method of acquiring a target reply language corresponding to the current text interaction content from a corpus according to the current text interaction content and the target attribute scores of the current text interaction content in various fields, including:

[0135] S701, determining a category label of the current text interaction content according to the field corresponding to the maximum target attribute score.

[0136] Among them, the category label refers to the field category label corresponding to the current text educational content.

[0137] Optionally, in this embodiment, the target attribute scores are sorted according to the score sizes, and the domain category label of the domain corresponding to the maximum target attribute score is used as the category label of the current text interaction content.

[0138] S702, acquiring a target reply language corresponding to the current text interaction content from a corpus according to the current text interaction content and the category label.

[0139] Optionally, in this embodiment, the current text interaction content is segmented to obtain the corresponding content word vector. Candidate noun entities corresponding to each content word vector are obtained from the corpus. Then, according to the field category of each candidate noun entity and the category label corresponding to the current text interaction content, a candidate noun entity corresponding to the category label is selected from each candidate noun entity as the first noun entity corresponding to the content word vector. If the number of the first noun entity is more than one, the similarity between the first noun entity and the content word vector is further determined. According to the similarity, the first noun entity with the highest similarity is selected as the second noun entity. And further determine whether the similarity of the second noun entity is a high similarity threshold. If it is higher, the second noun entity is used as the target noun entity. Otherwise, it is determined that there is no match. According to each target noun entity and language logic rules, a target reply is generated.

[0140] In this embodiment, the category label of the current text interaction content can be determined according to the field corresponding to the maximum target attribute score. Then, according to the current text interaction content and the category label, the target reply language corresponding to the current text interaction content is obtained from the corpus, so that the field category corresponding to the obtained target reply language is more consistent with the field category preferred by the user, thereby improving the accuracy of the target reply language.

[0141] In one embodiment, in order to further improve the user's satisfaction with the target reply, Figure 8 As shown, the controller executes an optional implementation method of acquiring a target reply language corresponding to the current text interaction content from a corpus according to the current text interaction content and the category label, including:

[0142] S801, determining the target identity of the user according to the voice interaction content.

[0143] Among them, the voice interaction content refers to the audio clips input by the user through the voice receiving device in the external control device or display device when the user has the need for human-computer interaction.

[0144] As an optional implementation of the embodiment of the present application, the voice interaction content is sent to the user input interface of the display device through an external control device. The user input interface sends the voice interaction content to the controller. The external control device can be a user terminal (for example, a mobile phone, a computer, a smart watch, a smart bracelet, etc.), or a remote control of the display device.

[0145] As another optional implementation of the embodiment of the present application, the voice interaction content is input through a voice receiving device in the display device. The voice receiving device may be a user input interface, and the voice receiving device may be a microphone or other sound detector.

[0146] Optionally, in this embodiment, an optional implementation method of determining the target identity of the user according to the voice interaction content is to obtain the user's voiceprint feature according to the voice interaction content. According to the user's voiceprint feature, a user identity matching the user's voiceprint feature is retrieved from a database as the target identity.

[0147] S802, obtaining attribute information of the user according to the target identity.

[0148] The attribute information refers to the user's related attribute information, including but not limited to age, gender, dialect and preference information.

[0149] Optionally, in this embodiment, the attribute information of the user can be determined according to the target identity and the attribute list, wherein the attribute list records each user identity and the attribute information corresponding to each user identity.

[0150] S803, acquiring a target reply language corresponding to the current text interaction content from a corpus according to the attribute information, the current text interaction content and the category label.

[0151] Optionally, in this embodiment, a user portrait of the user is constructed based on the attribute information. The current text interaction content is segmented to obtain the corresponding content word vector. The candidate noun entities corresponding to each content word vector are obtained from the corpus. Then, based on the domain category of each candidate noun entity, as well as the category label corresponding to the user portrait and the current text interaction content, the candidate noun entity corresponding to the category label and the user portrait is selected from each candidate noun entity as the first noun entity corresponding to the content word vector. If the number of the first noun entity is more than one, the similarity between the first noun entity and the content word vector is further determined. Based on the similarity, the first noun entity with the highest similarity is selected as the second noun entity. And further determine whether the similarity of the second noun entity is a high similarity threshold. If it is higher, the second noun entity is used as the target noun entity. Otherwise, it is determined that there is no match. Generate a target reply based on each target noun entity and language logic rules.

[0152] Optionally, a user portrait generation model (e.g., a GAN (Generative Adversarial Network) model) can be used to construct a user portrait based on attribute information. Subsequently, the relevant parameters in the user portrait generation model can be flexibly adjusted according to the user's feedback on the target reply (e.g., inaccurate) to achieve self-training of the user portrait generation model.

[0153] In this embodiment, the target identity of the user can be determined according to the voice interaction content. According to the target identity, the attribute information of the user is obtained. Finally, the attribute information, the current text interaction content and the category label are integrated to obtain the target reply language that meets the requirements of the three from the corpus. Since the attribute information of the user (for example, age, preference, gender, etc.) is taken into consideration, the obtained target reply language can better meet the needs of the user.

[0154] In one embodiment, if Fig. 9 As shown, the controller of the display device executes an optional implementation of the reply speech generating method, including:

[0155] S901, a user input interface receives voice interaction content input by a user through a voice receiving device in an external control device or a display device.

[0156] S902: The controller performs semantic analysis on the voice interaction content to obtain the user's current text interaction content.

[0157] S903: The controller determines the target identity of the user according to the voice interaction content.

[0158] S904, the controller obtains the user's attribute information and the historical interaction record corresponding to the target identity according to the target identity, wherein the historical interaction record includes the historical text interaction content and the historical reply words corresponding to the historical interaction content.

[0159] S905: The controller performs vertical domain analysis on the current text interaction content to obtain a first attribute score of the current text interaction content in each domain.

[0160] S906: The controller performs vertical domain analysis on the historical interaction records to obtain second attribute scores of the historical interaction records in each domain.

[0161] S907, the controller determines the target attribute score of the current text interaction content in each field according to the first attribute score of the current text interaction content in each field and the second attribute score of the historical interaction record in each field.

[0162] S908: For each field, the controller uses the sum of the first attribute score of the current text interaction content in the field and the second attribute score of the historical interaction record in the field as the field attribute score.

[0163] S909: The controller uses the ratio of the first attribute score of the current text interaction content in the domain to the domain attribute score as the target attribute score of the current text interaction content in the domain.

[0164] S910: The controller determines a category label of the current text interaction content according to the field corresponding to the maximum target attribute score.

[0165] S911, the controller obtains the target reply language corresponding to the current text interaction content from the corpus according to the attribute information, the current text interaction content and the category label.

[0166] S912, the controller controls the display to display the target reply language.

[0167] S913, controlling the multimedia playback device in the display device to play the target reply language.

[0168] In this embodiment, the user input interface of the display device is configured to receive the current text interaction content initiated by the user; and at least one controller is connected to the display and is configured to: determine the target attribute scores of the current text interaction content in various fields according to the current text interaction content and the historical interaction records. And according to the current text interaction content and the target attribute scores of the current text interaction content in various fields, obtain the target reply language corresponding to the current text interaction content from the corpus. Control the display device to display the target reply language. When generating the target reply language, the display device of the present application not only considers the current text interaction content, but also considers the historical interaction records. Based on the current text interaction content and the historical interaction records, the target attribute scores of the current text interaction content in various fields are determined, and based on the target attribute scores, the target reply language corresponding to the current text interaction content is determined, so that the final reply language is more accurate, can better meet the needs of users, and effectively improve the user experience.

[0169] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0170] Based on the same inventive concept, the embodiment of the present application also provides a role template generation device for implementing the above-mentioned display device format switching method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method. The specific limitations can be found in the above-mentioned limitations on the display device format switching method, which will not be repeated here.

[0171] In one embodiment, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned reply generation method are implemented.

[0172] In one embodiment, the present application further provides a computer program product, including a computer program, which implements the steps of the above-mentioned reply generation method when executed by a processor.

[0173] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0174] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0175] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A display device, characterized in that: include: a display configured to display content from a broadcast system or network and / or a user interface; A user input interface configured to receive current text interaction content initiated by a user; and at least one controller connected to the display and configured to: Determining target attribute scores of the current text interaction content in various fields according to the current text interaction content and historical interaction records; According to the current text interaction content and the target attribute scores of the current text interaction content in various fields, acquiring a target reply language corresponding to the current text interaction content from a corpus; The display device is controlled to display the target reply word.

2. The display device according to claim 1, characterized in that When the controller determines the target attribute scores of the current text interaction content in each field according to the current text interaction content and the historical interaction records, the controller is configured as follows: Performing vertical domain analysis on the current text interaction content to obtain first attribute scores of the current text interaction content in each field; Performing vertical domain analysis on the historical interaction records to obtain second attribute scores of the historical interaction records in various fields; According to the first attribute score of the current text interaction content in each field and the second attribute score of the historical interaction record in each field, the target attribute score of the current text interaction content in each field is determined.

3. The display device according to claim 2, characterized in that When the controller determines the target attribute score of the current text interaction content in each field according to the first attribute score of the current text interaction content in each field and the second attribute score of the historical interaction record in each field, the controller is configured as follows: For each field, the sum of the first attribute score of the current text interaction content in the field and the second attribute score of the historical interaction record in the field is used as the field attribute score; The ratio of the first attribute score of the current text interaction content in the field to the field attribute score is used as the target attribute score of the current text interaction content in the field.

4. The display device according to claim 1, characterized in that When the controller executes acquiring the target reply words corresponding to the current text interaction content from the corpus according to the current text interaction content and the target attribute scores of the current text interaction content in various fields, the controller is configured as follows: Determining a category label of the current text interaction content according to the field corresponding to the maximum target attribute score; According to the current text interaction content and the category label, a target reply language corresponding to the current text interaction content is acquired from a corpus.

5. The display device according to claim 4, characterized in that When the user input interface receives the current text interaction content initiated by the user, it is configured as follows: Receiving voice interaction content input by the user through an external control device or a voice receiving device in the display device; The voice interaction content is semantically analyzed to obtain the user's current text interaction content.

6. The display device according to claim 5, characterized in that When the controller acquires a target reply word corresponding to the current text interaction content from a corpus according to the current text interaction content and the category label, the controller is configured to: Determining the target identity of the user according to the voice interaction content; According to the target identity, acquiring attribute information of the user; According to the attribute information, the current text interaction content and the category label, a target reply language corresponding to the current text interaction content is acquired from a corpus.

7. The display device according to claim 5, characterized in that The controller is also configured to: Determining the target identity of the user according to the voice interaction content; Obtain historical interaction records corresponding to the target identity.

8. The display device according to any one of claims 1 to 7, characterized in that: The historical interaction record includes historical text interaction content and historical reply words corresponding to the historical interaction content.

9. The display device according to any one of claims 1 to 7, characterized in that: While the display device displays the target reply language, the controller is further configured to: Control the multimedia playback device in the display device to play the target reply language.

10. A method for generating a reply, characterized in that: The method is applied to a controller of a display device, and the method comprises: Determining target attribute scores of the current text interaction content in various fields according to the current text interaction content and historical interaction records; According to the current text interaction content and the target attribute scores of the current text interaction content in various fields, acquiring a target reply language corresponding to the current text interaction content from a corpus; The display device is controlled to display the target reply word.

Images