WO2019218656A1 - 一种智能电视、其截屏应用方法及存储介质 - Google Patents

一种智能电视、其截屏应用方法及存储介质 Download PDF

Info

Publication number
WO2019218656A1
WO2019218656A1 PCT/CN2018/121061 CN2018121061W WO2019218656A1 WO 2019218656 A1 WO2019218656 A1 WO 2019218656A1 CN 2018121061 W CN2018121061 W CN 2018121061W WO 2019218656 A1 WO2019218656 A1 WO 2019218656A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
voice
screen capture
instruction
screen
Prior art date
Application number
PCT/CN2018/121061
Other languages
English (en)
French (fr)
Inventor
于芝涛
高斯太
Original Assignee
聚好看科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 聚好看科技股份有限公司 filed Critical 聚好看科技股份有限公司
Publication of WO2019218656A1 publication Critical patent/WO2019218656A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H04N21/42203—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] sound input device, e.g. microphone
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/44—Receiver circuitry for the reception of television signals according to analogue transmission standards
    • H04N5/4448—Receiver circuitry for the reception of television signals according to analogue transmission standards for frame-grabbing

Definitions

  • the present disclosure relates to the field of multimedia technologies, and in particular, to a smart television, a screen capture application method thereof, and a storage medium.
  • smart TV based on Internet technology has an open platform and is equipped with an operating system. In addition to realizing ordinary TV program playback, it can also realize the installation and use of various application software. Especially after the rapid development of artificial intelligence technology, the smart TV can recognize the user's voice command and perform corresponding operations according to the voice command.
  • a smart TV generally performs a screenshot operation on a video according to a voice instruction after receiving a voice instruction of the user, thereby displaying information related to the screenshot.
  • the process of inputting the voice by the user and recognizing the input voice takes a period of time. Therefore, the image obtained by the smart TV screen capture is often not the image required by the user, and the information related to the image further displayed is not required by the user. The user experience is not good.
  • the present disclosure provides a smart TV, a screen capture application method thereof and a storage medium for quickly responding to screen captures, improving the accuracy of the screen capture application, and adapting to the user's intention of use.
  • Some embodiments of the present disclosure provide a screen capture application method for a smart TV, including:
  • the currently displayed image on the display screen of the smart TV is screened and the screen capture image is stored;
  • a corresponding operation is performed on the stored screen shot image in accordance with the voice instruction.
  • the method further includes:
  • the stored screenshot image is deleted in response to the voice instruction being an operation instruction that is not related to the screen capture.
  • the method before the performing the corresponding operation on the stored screenshot image according to the voice instruction, the method further includes:
  • Performing corresponding operations on the stored screenshot image according to the voice instruction including:
  • a corresponding operation is performed on the screen shot image in accordance with the voice instruction.
  • the method further includes:
  • the video is played back with the current display image as the starting image
  • the voice instruction when the voice instruction is an image recognition instruction, the performing the corresponding operation on the stored screenshot image according to the voice instruction, including:
  • the method further includes:
  • the image element includes one or more of a character, an item, a two-dimensional code, and a logo.
  • An embodiment of the present disclosure further provides a smart television, including: a display screen, a voice input module, a memory, and a processor, where
  • a voice input module for receiving voice input from a user :
  • a memory in communication with the display screen and the voice input module for storing computer instructions, data associated with the display screen, and data associated with the voice input module;
  • a processor in communication with the display screen, the voice input module, and the memory, configured to execute the computer instructions to cause the smart television to perform: on a display screen of the smart television at a time when the user is recognized to initiate voice input
  • the current display image is screened and the screen capture image is stored; at the end of the user's voice input, the input voice is converted into a voice command; the voice command is determined to be an operation command related to the screen capture; and the voice command is An operation instruction related to the screen capture performs a corresponding operation on the stored screen shot image according to the voice instruction.
  • Embodiments of the present disclosure provide a machine readable non-volatile storage medium storing computer-executable instructions that, when executed by a processor, cause the smart television to perform any of the above method.
  • FIG. 1 is a schematic flowchart of a screenshot application method of a smart television according to an embodiment of the present disclosure
  • FIG. 2 is a second schematic flowchart of a screenshot application method of a smart television according to an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of a screen capture application device of a smart television according to an embodiment of the present disclosure
  • FIG. 4 is a schematic structural diagram of a smart television according to an embodiment of the present disclosure.
  • the screen capture application method provided by the present disclosure can be applied to a smart TV, which includes a remote control device, a display screen, a voice input module, a memory, a processor, and an image processing module.
  • the user can control the smart TV through the remote control device, or Voice commands control smart TV.
  • the voice input module is capable of receiving a voice input of the user, and inputting the voice input of the user to the processor, performing voice analysis by the processor, determining a voice command of the user, thereby controlling the smart TV to perform a corresponding operation.
  • the voice input module receives the voice input of the user, the notification signal may be sent to the processor, and the processor controls the display screen to perform a screenshot operation on the currently displayed image, and stores it in the memory to be processed by the subsequent processing.
  • the processor determines that the voice instruction is an operation instruction related to the screen shot when the user voice input is completed, the corresponding operation is performed on the stored screen shot image according to the voice instruction.
  • the user can control the smart TV to realize the corresponding function through the remote control device.
  • the remote control device can include a button for controlling the smart TV to realize the screenshot or image recognition.
  • the smart TV receives the key value of the corresponding button, the smart TV can The image currently displayed by the smart TV performs a screenshot operation, and the image processing module is activated to perform image processing on the intercepted image, analyze image elements included in the image, and search for information related to the image elements to be displayed on the display screen of the smart television. For users to view.
  • FIG. 1 is a schematic flowchart of a screen capture application method of a smart TV according to an embodiment of the present disclosure. As shown in FIG. 1 , the method includes:
  • the method for controlling the screenshot of the voice command often has a problem of lag.
  • the embodiment of the present disclosure provides a screen capture application method for the smart TV. At the moment when the voice input of the user is just started, the current display image is screened first, and at the same time, the screen is still received. The voice input of the user, after the voice input is completed and converted into a voice command, the parsing voice command determines whether the parsed voice command is an operation instruction related to the screen capture, and if the voice command is determined to be an operation instruction related to the screen capture, then the voice command can be directly used. The screen capture image obtained at the beginning of the voice input is correspondingly operated.
  • the display image that the user is viewing when starting the voice input is the image that the user needs, and the voice input by the user is also an instruction for performing related operations on the image. Therefore, the screen capture image obtained by performing the screen capture operation at this time is most suitable for the user's needs.
  • the operation flow of parsing and parsing is adopted to avoid missing the image required by the user due to the time taken by the speech recognition.
  • the screen capture image obtained by such a screen capture method is more in line with the user's intention of use, and is advantageous for improving the accuracy of acquiring the screen capture image and improving the accuracy of the screen capture image. User experience.
  • the smart TV may be integrated with a voice recognition related function module or an application program, and trigger a screen capture instruction to recognize the user's voice input to control the smart TV to perform a screen capture operation.
  • the module or program with voice recognition function is integrated in the remote control device, and the remote control device sends a screen capture control signal to the smart TV at the initial recognition of the voice input, so that the smart TV performs the screen capture operation.
  • the above-mentioned remote control device may be a smart phone, a tablet computer, a remote controller, etc., which establish a communication connection with the smart TV, and is not limited herein. And determining whether the voice instruction is an operation instruction related to the screen capture needs to be determined according to the content of the voice instruction.
  • the voice instruction involves operations such as querying, searching, and image sharing in the image
  • the screen capture is required.
  • operations such as image recognition or image processing on the screen capture image it can be determined that the voice instruction is an operation instruction related to the screen capture, that is, if the operation indicated by the voice instruction must be screen shot, the voice instruction is an operation instruction related to the screen capture.
  • the voice instruction involves an operation such as fast forward, channel change, etc., that is, an operation that the voice instruction does not need to take a screen shot, the voice instruction is an operation instruction that is not related to the screen capture.
  • the parsed voice command is an operation command that is not related to the screen capture after the screen capture operation is performed
  • the screen capture image saved at the beginning of the voice input has no subsequent use.
  • the stored screenshots can be deleted to free up storage space without taking up memory.
  • the above-mentioned screen capture application method provided by the embodiment of the present disclosure can effectively improve the matching degree of the screen capture image with the user's intention, but does not completely eliminate the possibility of screen capture failure. This is because it takes a while for the voice input of the user to be recognized, although the time period is relatively short, but the screen lag caused by the small time period cannot be avoided. Therefore, in the above method provided by the embodiment of the present disclosure, in the foregoing step S104, before performing the corresponding operation on the stored screenshot image according to the voice instruction, the following steps may be further included:
  • the user can select, by using the remote control device, whether the screen capture image is the key value of the required screen capture image; if the user sees that the screen capture image is indeed a previously excited image. You can select the key value that needs the screenshot image to send the smart TV. If the user sees that the screen capture image is not the image that was of interest before, the key value that does not require the screen capture image can be sent to the smart TV.
  • the smart TV receives the key value of the screen capture image, that is, receives an indication that the screen capture image is required, and receives the key value that does not require the screen capture image, that is, receives an indication that the screen capture image is not required.
  • step S104 performing corresponding operations on the stored screenshot image according to the voice instruction, including:
  • a corresponding operation is performed on the screen shot image according to the voice instruction.
  • the user confirms whether the screen capture image saved by the previous screen capture is an image of interest when the user initiates the voice instruction, and only when the user confirms that the screen capture image is required, the corresponding operation is performed on the screen capture image, thereby avoiding Malfunction or useless operation due to failed capture of the screen image.
  • the user confirms that the screen capture image is not the image of the previous interest and selects the key value that does not require the screen capture image to send the smart TV, the following steps may also be included:
  • the video is played back with the current display image as the starting image
  • the "rewind screen” operation in the embodiment of the present disclosure refers to playing the current display image of the video as a starting image, and playing the video in reverse order. For example, if the video frames played back to the current time sequence are a1, a2, a3, a4, a5, a6, then when the playback to the frame image a6 is instructed to enter the fallback screen capture operation, the video frames to be played are a6, a5, A4, a3, a2, a1.
  • the user can trigger the instruction to pause the video playing through the remote control device, and the image is displayed on the display image when the pause is paused, then this
  • the captured screen capture image is the frame display image that the user was interested in before.
  • the display image that the user is interested in is the image frame a4, and when the video is played back to the image frame a4, the user operates the pause button of the remote control device, and the video is fixed in the image frame a4, and the screen capture operation is performed at this time.
  • the screen capture image is a4, thereby successfully acquiring an image of interest to the user.
  • the above-mentioned screen capture application method provided by the embodiment of the present disclosure combines a voice input time screen capture operation and a back screen capture operation to make the screen capture image more in line with the user's intention of use, and also ensures that when the screen capture image fails to be acquired, the method is implemented in other manners.
  • the user's needs do not affect the normal use of the user and enhance the user experience.
  • the screen capture application method of the smart TV may include the following steps:
  • step S203 determining whether the voice instruction is an operation instruction related to the screen capture, in response to the voice instruction being an operation instruction related to the screen capture, performing step S204; in response to the voice instruction being not an operation instruction related to the screen capture, performing step S211;
  • step S204 display a prompt box to determine whether a screen capture image is required, when receiving an indication that a screen capture image is required, step S205 is performed; when receiving an instruction that does not require a screen capture image, step S206 is performed;
  • the above method provided by the embodiment of the present disclosure combines the voice instruction screen capture with the back screen capture, optimizes the screen capture operation of the smart TV, is more suitable for the user's needs, and ensures that the user can find the image of interest to perform corresponding operations.
  • the above voice command may be a screen capture instruction, or may be other instructions for performing related operations on an image based on a screen shot.
  • the voice instruction is a screen capture instruction
  • the screen capture is performed in the manner described above and the screen capture image is stored.
  • the voice instruction is another instruction, it is necessary to further perform a corresponding operation on the screen capture image.
  • step S104 performing a corresponding operation on the stored screen capture image according to the voice instruction, which may specifically include:
  • the voice input by the user usually includes the image element name that is interested in the screen capture image, and then the keyword of the image element can be extracted when parsing the input voice, thereby identifying the keyword in the screen capture image.
  • Corresponding image elements After analyzing the image element, information related to the image element can be searched for display.
  • the smart TV can search the database for information related to the above image elements, or search for relevant information on the Internet, and then display the information on the display screen of the smart TV.
  • the image elements in the voice instruction may be one or more, and the smart TV may also implement image recognition of the entire scene, and simultaneously identify different image elements in the same image. After the related information is searched, the image may be followed. The elements are classified and the information related to each image element is displayed.
  • voice input can be performed, for example, the user inputs the voice “Who is this person”,
  • the screen capture operation saves the screen capture image of the actor, and after the voice recognition is performed, the image element of the user interest is parsed as a character, and the characters in the screen capture image are recognized, for example, the screen capture is possible.
  • the image is image processed, the face image is extracted, and the face image in the database or the cloud is matched, thereby determining who the character is included in the image, further searching for information related to the character, and searching for the character.
  • the information is displayed.
  • a special function key can be set on the remote control device of the smart TV.
  • the remote control device sends an image recognition instruction to the smart TV, specifically, for setting
  • the above-mentioned method provided by the embodiment of the present disclosure may further include:
  • the special function key can be directly operated, and when the smart TV receives the function key value, the screen can be screened for the current display image of the playing video, and the screen is screened. Each image element in the image searches for related information and displays the searched information.
  • the smart TV can set the above function keys and have the function of voice recognition. Both of the above methods can trigger the function of the smart TV to recognize the full scene image of the currently displayed image.
  • the user can perform image recognition on the image of interest to further obtain related information, enrich the interaction between the smart TV and the user, and enhance the user experience.
  • the above image elements may include: a person, an item, a two-dimensional code, a logo, and the like.
  • the image elements included in the screen capture image can be extracted and matched by image processing technology.
  • the image element is recognized as a character, the basic information of the character and the latest information related to the character can be displayed.
  • the identified image element is an item, information such as the name, performance, and purchase route of the item may be displayed;
  • the recognized image element is a two-dimensional code, the two-dimensional code may be further scanned to enter The link corresponding to the two-dimensional code;
  • the recognized image element is a station logo, the list of recent broadcast programs of the TV station corresponding to the station logo may be displayed for the user to directly cut in.
  • other image elements may be included in the screen capture image, and the manners of image screen capture and image recognition implemented by the present disclosure are all within the protection scope of the present disclosure.
  • the embodiment of the present disclosure further provides a screen capture application device for a smart TV.
  • the functions implemented by the components included in the device can be referred to the screen capture application method of the smart TV, and the repeated description is omitted.
  • the screen capture application device of the smart television provided by the embodiment of the present disclosure specifically includes:
  • the screen capture module 31 is configured to screen the current display image on the display screen of the smart television and store the screen capture image when the user starts to recognize the voice input;
  • the conversion module 32 is configured to convert the input voice into a voice instruction when the user's voice input ends;
  • the parsing module 33 is configured to determine whether the voice instruction is an operation instruction related to the screen capture
  • the application module 34 is configured to perform a corresponding operation on the stored screenshot image according to the voice instruction when determining that the voice instruction is an operation instruction related to the screen shot.
  • the above-mentioned screen capture application device adopts a process of first screen-screening and parsing, and performs a screen-cut operation at the beginning of the user's voice input. After the user's voice input ends, if the user's voice command is parsed to involve a screen capture function, the screen capture application may be directly adopted.
  • the stored screen capture image is operated correspondingly to avoid missing the image required by the user due to voice recognition.
  • the screen capture image obtained by such a screen capture method is more suitable for the user's intention of use, and is advantageous for improving the accuracy of acquiring the screen capture image.
  • the application module 34 is further configured to delete the stored screenshot image when the voice instruction is not an operation instruction related to the screen capture.
  • the foregoing apparatus provided by the embodiment of the present disclosure further includes a determining module not shown in the figure;
  • a determining module configured to display a screen capture image and a prompt box for determining whether a screen capture image is required before performing a corresponding operation on the stored screen capture image according to the voice instruction;
  • the application module 34 is specifically configured to perform a corresponding operation on the screen capture image according to the voice instruction when receiving the indication that the screen capture image is required.
  • the determining module is further configured to: when receiving the indication that the screen capture image is not required, display a prompt box for entering the back screen capture operation;
  • the application module 34 is further configured to roll back the play video with the current display image as the starting image when receiving the indication of entering the fallback screen capture operation;
  • the screen capture module 31 is further configured to: when receiving the pause operation instruction, perform a screen capture on the current display image;
  • the application module 34 is further configured to perform a corresponding operation on the current screenshot image according to the voice instruction.
  • the application module 34 is specifically configured to: when the voice instruction is an image recognition instruction, identify an image element included in the voice instruction in the screen capture image; and search for information related to the image element for display.
  • the application module 34 is further configured to: when receiving the key value for image recognition sent by the user through the remote control device, perform a screen capture on the current display image of the play video; the search is related to each image element included in the screen capture image. The information is displayed.
  • the image element includes one or more of a character, an item, a two-dimensional code, and a logo.
  • an embodiment of the present disclosure further provides a smart television.
  • the smart television may include: a display screen not shown in the figure, a voice input module not shown in the figure, a memory 41, and processing. 42.
  • the display screen is used to display an image
  • a voice input module configured to receive a voice input of a user
  • a memory 41 in communication with the display screen and the voice input module, for storing computer instructions, data associated with the display screen, and data associated with the voice input module;
  • the processor 42 is in communication with the display screen, the voice input module, and the memory, and is configured to execute computer instructions to enable the smart television to perform: taking a screen shot of the currently displayed image on the display screen when the voice input module recognizes that the user initiates voice input
  • the screen capture image is stored; when the voice input module recognizes that the user's voice input ends, the input voice is converted into a voice command; whether the voice command is an operation instruction related to the screen capture; and the voice command is determined to be related to the screen capture operation
  • the instruction performs a corresponding operation on the stored screenshot image according to the voice instruction.
  • the processor communicates with the display screen and the voice input module, and the voice input module can detect the voice input of the user, and send a notification to the processor when the voice input of the user is detected, so that the processor controls the display screen.
  • the currently displayed image is displayed to perform a screen capture operation and the screen capture image is stored in the memory.
  • the voice input module detects that the voice input of the user ends, the voice information is sent to the processor, and the processor analyzes the voice command corresponding to the voice input of the user, and determines whether the voice command is an operation instruction related to the screen capture.
  • the voice instruction is an operation instruction related to the screen capture
  • the corresponding operation is performed on the stored screen capture image according to the voice instruction.
  • the display image that the user is viewing when starting the voice input is the image that the user needs, and the voice input by the user is also an instruction for performing the related operation on the image. Therefore, the screen capture image obtained by the screen capture operation at this time is most suitable for the user's needs.
  • the processor 42 is configured to execute the computer instruction to cause the smart television to execute: in response to the voice instruction being not an operation instruction related to the screen capture, storing The screenshot image is deleted. If the processor determines that the voice instruction is not an operation instruction related to the screen capture, then the screen capture image saved at the beginning of the voice input has no subsequent use, and the stored screen capture image can be deleted at this time to release the memory space.
  • the processor 42 may be configured to execute a computer instruction to cause the smart television to execute: display a screen capture image on the display screen and a prompt box for determining whether a screen capture image is required before performing a corresponding operation on the stored screen capture image according to the voice instruction; If it is a required screen capture image, the user can select the screen capture image by pressing a button of the remote control device or the like, and the processor executes a computer instruction to enable the smart television to execute: in response to receiving the instruction that the screen capture image is required, the screen capture image according to the voice instruction Take the appropriate action.
  • the user can select the screen capture image by controlling the button of the device or the like, and the processor executes the computer instruction to enable the smart television to execute: in response to receiving an instruction that does not require the screen capture image, The display shows whether to enter the prompt box for the back screen capture operation.
  • the processor executes computer instructions to cause the smart television to execute: in response to receiving the indication to enter the fallback screen capture operation, the current display image is used as the starting image to roll back the playback video; upon receiving When the operation instruction is suspended, the current display image is screened; the corresponding operation is performed on the current screen image according to the voice instruction.
  • the processor executes computer instructions to cause the smart television to execute: in response to receiving the indication to abandon the fallback screen capture operation, deleting the screen capture image in memory and continuing to play the current video.
  • the processor is configured to execute a computer command to cause the smart television to perform: identifying an image element included in the voice command in the screen capture image; and searching for information related to the image element for display.
  • the remote control device of the smart TV may be provided with a dedicated button for image recognition, by which the user can control the smart TV to take a screen shot of the currently displayed image, and perform an image recognition operation on the screen capture image. And configured to execute the computer instruction to enable the smart television to perform: taking a screen capture of the current display image of the play video when receiving the key value for image recognition sent by the user through the remote control device; searching and capturing each image included in the screen capture image Information related to image elements is displayed.
  • the image element may include one or more of a character, an item, a two-dimensional code, and a logo.
  • an embodiment of the present disclosure further provides a machine readable non-volatile storage medium having computer instructions stored thereon, and when the computer instructions are executed by the processor, implementing any of the above-described screen capture application methods.
  • the smart television provided by the present disclosure, the screen capture application method, the device and the storage medium perform screen capture on the current display image of the play video and store the screen capture image when the user starts the voice input; when the user's voice input ends Converting the input voice into a voice instruction; determining whether the voice instruction is an operation instruction related to the screen capture; and when determining that the voice instruction is an operation instruction related to the screen capture, performing a corresponding operation on the stored screen capture image according to the voice instruction.
  • the above-mentioned screenshot application method provided by the present disclosure adopts a process of first screen-screening and parsing, and performs a screen-cut operation at the beginning of the user's voice input.
  • the method can be directly adopted.
  • the stored screen capture image is operated correspondingly to avoid missing the image required by the user due to voice recognition.
  • the screen capture image obtained by such a screen capture method is more suitable for the user's intention of use, and is advantageous for improving the accuracy of acquiring the screen capture image.
  • embodiments of the present disclosure can be provided as a method, system, or computer program product.
  • embodiments of the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware.
  • the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • Embodiments of the present disclosure are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the present disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG.
  • These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • User Interface Of Digital Computer (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

本发明提供了一种智能电视、其截屏应用方法及存储介质。该方法包括：在识别到用户开始语音输入的时刻，对播放视频当前的显示图像进行截屏，并将截屏图像存储（S101）；在用户的语音输入结束时，将输入的语音转化为语音指令（S102）；确定语音指令是否为与截屏相关的操作指令（S103）；响应于确定语音指令为与截屏相关的操作指令，根据语音指令对存储的截屏图像执行相应操作（S104）。本发明采用先截屏后解析的流程，在用户语音输入之初就进行截屏操作，如果之后解析出用户的语音指令涉及到截屏，则可以直接采用存储的截屏图像进行相应操作，避免由于语音识别错过用户所需要的图像，采用这样的截屏方式得到的截屏图像更符合用户的使用意图，有利于提高获取截屏图像的准确性。

Description

一种智能电视、其截屏应用方法及存储介质
本公开要求在2018年5月17日提交中国专利局、申请号为201810475458.0、申请名称为“一种智能电视、其截屏应用方法、装置及可读性存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及多媒体技术领域，尤其涉及一种智能电视、其截屏应用方法及存储介质。
背景技术
随着互联网(Internet)技术的不断发展，基于Internet技术的智能电视具有开放式平台，搭载操作系统，在实现普通的电视节目播放以外，还可以实现各类应用软件的安装和使用。尤其是在人工智能技术迅速发展之后，智能电视可以识别用户的语音指令，并根据语音指令执行相应的操作。
在一种应用场景中，如果用户在观看到视频中某一图像时对该图像中的物品或人物感兴趣，想进一步了解相关信息，那么可以直接向智能电视发送语音指令控制智能电视进一步显示与该图像中的物品或人物相关的信息。目前，智能电视一般是在接收到用户的语音指令之后，根据语音指令对视频进行截图操作，进而显示与该截图相关的信息。而用户输入语音以及对输入的语音进行识别的过程均需要一段时间，因此智能电视截屏得到的图像往往不是用户所需要的图像，进一步显示的与图像相关的信息也并不是用户需要的，由此造成用户使用体验不佳。
发明内容
本公开提供一种智能电视、其截屏应用方法及存储介质，用以快速响应截屏，提高截屏应用的准确性，适应用户的使用意图。
本公开的一些实施方式，提供一种智能电视的截屏应用方法，包括：
在识别到用户开始语音输入的时刻，对所述智能电视的显示屏上的当前显示图像进行截屏并将截屏图像存储；
在用户的语音输入结束时，将输入的语音转化为语音指令；
确定所述语音指令是否为与截屏相关的操作指令；
响应于所述语音指令为与截屏相关的操作指令，根据所述语音指令对存储的所述截屏 图像执行相应操作。
在一些实施方式中，所述方法还包括：
响应于所述语音指令为不是与截屏不相关的操作指令，将存储的所述截屏图像删除。
在一些实施方式中，在所述根据所述语音指令对存储的所述截屏图像执行相应操作之前，还包括：
显示所述截屏图像以及确定用户是否需要所述截屏图像的提示框；
所述根据所述语音指令对存储的所述截屏图像执行相应操作，包括：
响应于接收到确定用户需要所述截屏图像的指示时，根据所述语音指令对所述截屏图像执行相应操作。
在一些实施方式中，所述方法还包括：
响应于接收到确定用户不需要所述截屏图像的指示，显示是否进入回退截屏操作的提示框；
在接收到进入回退截屏操作的指示时，以当前的显示图像作为起始图像回退播放视频；
在接收到暂停操作指令时，对当前的显示图像进行截屏；
根据所述语音指令对当前的截屏图像执行相应操作。
在一些实施方式中，在所述语音指令为图像识别指令时，所述根据所述语音指令对存储的所述截屏图像执行相应操作，包括：
在所述截屏图像中识别出所述语音指令中包含的图像元素；
搜索所述图像元素相关的信息进行显示。
在一些实施方式中，还包括：
在接收到用户通过遥控设备发送的用于图像识别的键值时，对播放视频当前的显示图像进行截屏；
搜索与截屏图像中包含的各图像元素相关的信息进行显示。
在一些实施方式中，所述图像元素包括人物、物品、二维码以及台标中的一种或多种。
本公开的实施方式，还提供一种智能电视，包括：显示屏、语音输入模块、存储器和处理器，其中，
显示屏，用于显示图像；
语音输入模块，用于接收用户的语音输入：
存储器，与所述显示屏和语音输入模块通信，用于存储计算机指令、与所述显示屏关联的数据以及与所述语音输入模块关联的数据；
处理器，与所述显示屏、语音输入模块和存储器通信，配置为执行所述计算机指令以使所述智能电视执行：在识别到用户开始语音输入的时刻，对所述智能电视的显示屏上的当前显示图像进行截屏并将截屏图像存储；在用户的语音输入结束时，将输入的语音转化为语音指令；确定所述语音指令是否为与截屏相关的操作指令；响应于所述语音指令为与截屏相关的操作指令，根据所述语音指令对存储的所述截屏图像执行相应操作。
本公开的实施方式，提供一种机器可读的非易失性存储介质，所述存储介质存储有计算机可执行指令，所述可执行指令被处理器执行时使所述智能电视执行上述任一方法。
附图说明
为了更清楚地说明本公开实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简要介绍，显而易见地，下面描述中的附图仅仅是本公开的一些实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的智能电视的截屏应用方法的流程示意图之一；
图2为本公开实施例提供的智能电视的截屏应用方法的流程示意图之二；
图3为本公开实施例提供的智能电视的截屏应用装置的结构示意图；
图4为本公开实施例提供的智能电视的结构示意图。
具体实施方式
为了使本公开的目的、技术方案和优点更加清楚，下面将结合附图对本公开作进一步地详细描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本公开保护的范围。
本公开提供的截屏应用方法可应用于智能电视，该智能电视包括遥控设备、显示屏、语音输入模块、存储器、处理器以及图像处理模块等，用户可以通过摇控设备控制智能电视，也可以通过语音指令控制智能电视。其中，语音输入模块，能够接收用户的语音输入，并将用户的语音输入发送处理器，由处理器进行语音解析，确定用户的语音指令，从而控制智能电视执行相应操作。语音输入模块刚接收到用户的语音输入时，可以向处理器发送通知信号，处理器控制显示屏对当前显示图像执行截图操作，存储于存储器中待后续处理应用。如果在用户语音输入完成时，处理器确定语音指令为与截屏相关的操作指令，则根据语音指令对存储的截屏图像执行相应操作。除此之外，用户可以通过摇控设备控制智能 电视实现相应的功能，摇控设备上可以包括控制智能电视实现截图或图像识别的按键，智能电视在接收到相应按键的键值时，可以对智能电视当前显示的图像执行截图操作，并且启动图像处理模块对截得的图像进行图像处理，分析图像中包含的图像元素，搜索与这些图像元素相关的信息显示于智能电视的显示屏上，以供用户查看。
图1示出了本公开实施例提供的智能电视的截屏应用方法的流程示意图，如图1所示，该方法包括：
S101、在识别到用户开始语音输入的时刻，对智能电视的显示屏上的当前显示图像进行截屏并将截屏图像存储；
S102、在用户的语音输入结束时，将输入的语音转化为语音指令；
S103、确定语音指令是否为与截屏相关的操作指令；
S104、响应于确定语音指令为与截屏相关的操作指令，根据语音指令对存储的截屏图像执行相应操作。
针对语音指令控制截屏常常出现滞后的问题，本公开实施例提供一种智能电视的截屏应用方法，在用户语音输入刚刚开始的时刻，就先对当前的显示图像进行截屏操作，与此同时仍然接收用户的语音输入，待语音输入完毕且转换为语音指令之后，解析语音指令确定解析出的语音指令是否为与截屏相关的操作指令，如果确定语音指令为与截屏相关的操作指令，那么可以直接采用之前在语音输入刚开始时截屏得到的截屏图像进行相应的操作。用户在开始语音输入时正在观看的显示图像为用户所需要的图像，用户所输入的语音也是对该图像进行相关操作的指令，因此在这个时刻进行截屏操作得到的截屏图像最符合用户的需求。采用先截屏后解析的操作流程，避免由于语音识别占用的时间错过用户所需要的图像，采用这样的截屏方式得到的截屏图像更符合用户的使用意图，有利于提高获取截屏图像的准确性，提升用户使用体验。
在实际应用中，智能电视可以集成有语音识别相关功能模块或应用程序，在识别到用户的语音输入即触发截屏指令，以控制智能电视执行截屏操作。或者，带有语音识别功能的模块或程序集成于遥控设备中，由遥控设备在识别到语音输入之初始向智能电视发送截屏控制信号，以使智能电视执行截屏操作。上述的遥控设备可为与智能电视建立通信连接的智能手机、平板电脑、摇控器等，在此不做限定。而确定语音指令是否为与截屏相关的操作指令，则需要根据语音指令的内容来确定，例如，如果语音指令中涉及到对图像中的元素查询、搜索、图像分享等操作，则需要先截屏再对截屏图像进行图像识别或图像处理等操作，此时可以确定语音指令为与截屏相关的操作指令，也就是说如果语音指令所指示的操作必须进行截屏，则语音指令为与截屏相关的操作指令；而如果语音指令涉及快进、 换台等操作，即语音指令并不需要截屏就可以执行的操作，则该语音指令则为与截屏不相关的操作指令。
进一步地，在具体实施时，如果在先执行了截屏操作之后，解析出的语音指令为与截屏不相关的操作指令，那么在语音输入之初截屏保存的截屏图像并没有后续的用途，此时可将存储的截屏图像删除，以释放存储空间，不使其占用内存。
本公开实施例提供的上述截屏应用方法，可以有效提升截屏图像与用户意图的匹配程度，但是并不能完全消除截屏失败的可能性。这是因为识别到用户的话音输入仍需要一段时间，虽然该时间段比较短，但无法避免该微小的时间段造成的截屏滞后。因此，在本公开实施例提供的上述方法中，在上述的步骤S104中，在根据语音指令对存储的截屏图像执行相应操作之前，还可以包括以下步骤：
显示截屏图像以及确定是否需要截屏图像的提示框。
在实际应用中，智能电视显示出上述的提示框之后，可由用户通过摇控设备选择指示截屏图像是否为需要的截屏图像的键值；若用户在查看到截屏图像确实为之前感兴的图像时，则可以选择需要截屏图像的键值发送智能电视，如果用户在查看到截屏图像并非之前感兴趣的图像时，则可将选择不需要截屏图像的键值发送智能电视。智能电视在接收到需要截屏图像的键值，即为接收到需要截屏图像的指示，而在接收到不需要截屏图像的键值，即为接收到不需要截屏图像的指示。
相应地，在上述的步骤S104中，根据语音指令对存储的截屏图像执行相应操作，包括：
响应于接收到需要截屏图像的指示，根据语音指令对截屏图像执行相应操作。
通过显示提示框，由用户确认之前截屏保存的截屏图像是否为用户发起语音指令时所感兴趣的图像，且只有在用户确认了需要截屏图像时，才对截屏图像执行相应的操作，由此可以避免由于截屏图像获取失败而造成的误操作或无用操作。
进一步地，如果在上述的步骤中，用户确认截屏图像并非之前感兴趣的图像而选择不需要截屏图像的键值发送智能电视，此时还可以包括如下步骤：
显示是否进入回退截屏操作的提示框；
在接收到进入回退截屏操作的指示时，以当前的显示图像作为起始图像回退播放视频；
在接收到暂停操作指令时，对当前的显示图像进行截屏；
根据语音指令对当前的截屏图像执行相应操作。
具体来说，本公开实施例中的“回退截屏”操作是指播放视频当前的显示图像作为起 始图像，以倒序的方式播放视频。例如截止到当前时序为止所播放的视频帧为a1、a2、a3、a4、a5、a6，那么在播放到帧图像a6时指示进入回退截屏操作，则待播放的视频帧为a6、a5、a4、a3、a2、a1。在回退播放视频的过程中，如果用户发现了之前感兴趣而没有截屏成功的图像，此时用户可以通过遥控设备触发暂停视频播放的指令，显示图像定格在暂停时的显示图像上，那么此时再执行截屏操作，获取到的截屏图像为用户之前所感兴趣的那帧显示图像。例如，用户之前感兴趣的显示图像为图像帧a4，在回退播放视频到图像帧a4时，用户操作了摇控设备的暂停键，视频被定格在图像帧a4，此时执行截屏操作时获取到的截屏图像为a4，由此成功获取到用户感兴趣的图像。
本公开实施例提供的上述截屏应用方法，将语音输入时刻截屏操作与回退截屏操作相结合，使截屏图像更符合用户的使用意图，同时还可以保证在截屏图像获取失败时，以其它方式实现用户的需求，不影响用户的正常使用，提升用户的使用体验。
综上所述，针对应用中可能出现的各种情况，本公开实施例提供的智能电视的截屏应用方法，如图2所示，可以包括如下步骤：
S201、在识别用户开始语音输入的时刻，对智能电视的显示屏上的当前显示图像进行截屏并将截屏图像存储；
S202、在用户的语音输入结束时，将输入的语音转化为语音指令；
S203、确定语音指令是否为与截屏相关的操作指令，响应于语音指令为与截屏相关的操作指令，执行步骤S204；响应于语音指令不是与截屏相关的操作指令，执行步骤S211；
S204、显示确定是否需要截屏图像的提示框，在接收到需要截屏图像的指示时，执行步骤S205；在接收到不需要截屏图像的指示时，执行步骤S206；
S205、根据语音指令对截屏图像执行相应操作；
S206、显示是否进入回退截屏操作的提示框，在接收到进入回退截屏操作的指示时，执行步骤S207-S209；在接收到放弃进入回退截屏操作的指示时，执行步骤S210；
S207、以当前显示图像作为起始图像回退播放视频；
S208、在接收到暂停操作指令时，对当前的显示图像进行截屏；
S209、根据语音指令对当前的截屏图像执行相应操作；
S210、继续播放当前视频；
S211、删除截屏图像。
本公开实施例提供的上述方法，将语音指令截屏结合回退截屏，优化了智能电视的截屏操作，更适用于用户的需要，确保用户能够找到其感兴趣的图像进行相应操作。
在实际应用中，上述的语音指令可为截屏指令，也可以为在截屏基础上对图像进行相 关操作的其它指令。当语音指令为截屏指令时，则以上述的方式进行截屏并将截屏图像存储。而当语音指令为其它指令时，则需要对截屏图像进一步地执行相应操作。
具体地，在语音指令为图像识别指令时，在上述的步骤S104中，根据语音指令对存储的截屏图像执行相应操作，具体可以包括：
在截屏图像中识别出语音指令中包含的图像元素；
搜索图像元素相关的信息进行显示。
在具体实施时，用户所输入的语音中通常包含了对截屏图像所感兴趣的图像元素名称，那么在解析输入的语音时可以提取出图像元素的关键字，从而在截屏图像中识别出与关键字对应的图像元素。通过对该图像元素的分析之后，可以搜索与该图像元素相关的信息进行显示。智能电视可以在数据库中搜索上述图像元素相关的信息，也可以在互联网搜索相关信息，再将信息显示在智能电视的显示屏上。另外，语音指令中的图像元素可为一个也可为多个，同时智能电视也可以实现全场景的图像识别，同时识别同一图像中的不同图像元素，待进行相关的信息搜索之后，可以按照图像元素进行分类，将各图像元素相关的信息进行显示。
举例来说，在用户观看视频时对当前显示图像中的某位演员感兴趣，想要进一步了解该演员的相关信息，此时可进行语音输入，例如用户输入语音“这个人是谁”，在用户刚开始进行语音输入时，即进行截屏操作保存该演员的截屏图像，当进行语音识别之后解析出用户所感兴趣的图像元素为人物，则对截屏图像中的人物进行识别，例如，可对截屏图像进行图像处理，提取出人脸图像，与数据库或云端的人脸图像进行匹配，由此确定出图像中所包含的人物是谁，进一步搜索与该人物相关的信息，并将搜索到的人物信息进行显示。
除此之外，针对快速进行图像识别的功能可在智能电视配套的遥控设备上设置专用的功能键，用户在操作该功能键时，遥控设备向智能电视发送图像识别指令，具体地，针对设置专用键的应用场景，本公开实施例提供的上述方法，还可以包括：
在接收到用户通过遥控设备发送的用于图像识别的键值时，对播放视频当前的显示图像进行截屏；
搜索与截屏图像中包含的各图像元素相关的信息进行显示。
用户在观看视频的过程中如果遇到感兴趣的物品、人物等，可直接操作专用功能键，智能电视在接收到该功能键值时，可对播放视频当前的显示图像进行截屏，并对截屏图像中的各图像元素进行相关信息搜索，并将搜索到的信息进行显示。
在实际应用中，智能电视可以设置上述功能键，同时具备语音识别的功能，以上两种 方式均可以触发智能电视对当前显示图像的全场景图像识别的功能。用户通过操作功能键或者语音输入均可以对感兴趣的图像进行图像识别以进一步获取相关信息，丰富智能电视与用户之间交互，提升用户使用体验。
上述图像元素可以包括：人物、物品、二维码、台标等。其中，截屏图像中包含的各图像元素均可以通过图像处理技术进行提取和匹配，在识别出图像元素为人物时，可以对该人物的基本信息、与该人物相关的最新资讯等信息进行显示；在识别出的图像元素为物品时，可对该物品的名称、性能以及购买途径等信息进行显示；在识别出的图像元素为二维码时，可进一步对该二维码进行扫描，以进入该二维码对应的链接；在识别出的图像元素为台标时，可显示该台标对应的电视台近期的播放节目列表，以供用户选择后直接切入。除此之外，截屏图像中还可以包括其它的图像元素，在此不一一列举，凡是利用本公开构思实现的图像截屏、图像识别的方式均属于本公开的保护范围。
基于同一构思，本公开实施例还提供一种智能电视的截屏应用装置，该装置所包括的各组件所实现的功能可参见上述智能电视的截屏应用方法相，重复之处不再赘述。具体地，如图3所示，本公开实施例提供的智能电视的截屏应用装置，具体包括：
截屏模块31，用于在识别到用户开始语音输入的时刻，对智能电视的显示屏上的当前显示图像进行截屏并将截屏图像存储；
转换模块32，用于在用户的语音输入结束时，将输入的语音转化为语音指令；
解析模块33，用于确定语音指令是否为与截屏相关的操作指令；
应用模块34，用于在确定语音指令为与截屏相关的操作指令时，根据语音指令对存储的截屏图像执行相应操作。
本公开提供的上述截屏应用装置采用先截屏后解析的流程，在用户语音输入之初就进行截屏操作，在用户语音输入结束之后，如果解析出用户的语音指令涉及到截屏作用，则可以直接采用存储的截屏图像进行相应操作，避免由于语音识别错过用户所需要的图像，采用这样的截屏方式得到的截屏图像更适应于用户的使用意图，有利于提高获取截屏图像的准确性。
可选地，应用模块34，还用于在语音指令不是与截屏相关的操作指令时，将存储的截屏图像删除。
可选地，本公开实施例提供的上述装置，还包括图中未示出的判定模块；
判定模块，用于在根据所述语音指令对存储的截屏图像执行相应操作之前，显示截屏图像以及确定是否需要截屏图像的提示框；
应用模块34，具体用于在接收到需要截屏图像的指示时，根据语音指令对截屏图像执 行相应操作。
可选地，判定模块，还用于在接收到不需要截屏图像的指示时，显示是否进入回退截屏操作的提示框；
应用模块34，还用于在接收到进入回退截屏操作的指示时，以当前的显示图像作为起始图像回退播放视频；
截屏模块31，还用于在接收到暂停操作指令时，对当前的显示图像进行截屏；
应用模块34，还用于根据语音指令对当前的截屏图像执行相应操作。
可选地，应用模块34，具体用于在语音指令为图像识别指令时，在截屏图像中识别出语音指令中包含的图像元素；搜索图像元素相关的信息进行显示。
可选地，应用模块34，还用于在接收到用户通过遥控设备发送的用于图像识别的键值时，对播放视频当前的显示图像进行截屏；搜索与截屏图像中包含的各图像元素相关的信息进行显示。
可选地，图像元素包括：人物、物品、二维码以及台标中的一种或多种。
另一方面，本公开实施例还提供一种智能电视，如图4所示，该智能电视可以包括：图中未示出的显示屏、图中未示出的语音输入模块、存储器41和处理器42。
其中，显示屏，用于显示图像；
语音输入模块，用于接收用户的语音输入；
存储器41，与显示屏和语音输入模块通信，用于存储计算机指令、与显示屏关联的数据以及与语音输入模块关联的数据；
处理器42，与显示屏、语音输入模块和存储器通信，配置为执行计算机指令以使智能电视执行：在语音输入模块识别到用户开始语音输入的时刻，对显示屏上的当前显示图像进行截屏并将截屏图像存储；在语音输入模块识别到用户的语音输入结束时，将输入的语音转化为语音指令；确定语音指令是否为与截屏相关的操作指令；响应于确定语音指令为与截屏相关的操作指令，根据语音指令对存储的截屏图像执行相应操作。
智能电视中，处理器与显示屏、语音输入模块之间通信，语音输入模块可以检测用户的语音输入，当检测到用户的语音输入的时刻向处理器发送通知，以使处理器控制显示屏对显当前显示的图像执行截屏操作并将截屏图像存储于存储器中。当语音输入模块检测到用户的语音输入结束时，将识别到的语音信息发送处理器，由处理器解析用户的语音输入对应的语音指令，确定该语音指令是否为与截屏相关的操作指令，如果确定该语音指令是与截屏相关的操作指令时，则根据语音指令对存储的截屏图像执行相应操作。用户在开始语音输入时正在观看的显示图像为用户所需要的图像，用户所输入的语音也是对该图像进 行相关操作的指令，因此在这个时刻进行截屏操作得到的截屏图像最符合用户的需求。
而如果处理器确定语音指令并不是与截屏相关的操作指令时，可选地，处理器42，配置为执行计算机指令以使智能电视执行：响应于语音指令不是与截屏相关的操作指令，将存储的截屏图像删除。如果处理器确定语音指令不是为与截屏相关的操作指令，那么在语音输入之初截屏保存的截屏图像并没有后续的用途，此时可将存储的截屏图像删除，以释放存储器空间。
为了避免对用户不需要的图像进行后续无意义的相应操作，在对截屏图像执行操作之前，可以先确定截屏图像是否为用户需要的图像。此时，处理器42，可以配置为执行计算机指令以使智能电视执行：在根据语音指令对存储的截屏图像执行相应操作之前，在显示屏上显示截屏图像以及确定是否需要截屏图像的提示框；如果为需要的截屏图像，则用户可以通过摇控设备等的按键选择需要该截屏图像，处理器执行计算机指令以使智能电视执行：响应于接收到需要截屏图像的指示，根据语音指令对截屏图像执行相应操作。如果该截屏图像并不是用户需要的图像，则用户可以通过控制设备等的按键选择不需要该截屏图像，处理器执行计算机指令以使智能电视执行：响应于接收到不需要截屏图像的指令，在显示屏上显示是否进入回退截屏操作的提示框。
将语音指令截屏结合回退截屏，优化了智能电视的截屏操作，更适用于用户的需要，确保用户能够找到其感兴趣的图像进行相应操作。用户在查看到是否进入回退截屏操作的提示框后，可以通过摇控设备等进行选择。当用户选择进入回退截屏操作时，处理器执行计算机指令以使智能电视执行：响应于接收到进入回退截屏操作的指示，以当前的显示图像作为起始图像回退播放视频；在接收到暂停操作指令时，对当前的显示图像进行截屏；根据语音指令对当前的截屏图像执行相应操作。当用户选择放弃回退截屏操作时，处理器执行计算机指令以使智能电视执行：响应于接收到放弃回退截屏操作的指示，删除存储器中的截屏图像，继续播放当前视频。
如果用户输入的语音指令为图像识别指令时，处理器配置为执行计算机指令以使智能电视执行：在截屏图像中识别出语音指令中包含的图像元素；搜索图像元素相关的信息进行显示。
除此之外，智能电视的摇控设备可以设有用于进行图像识别的专用按键，用户可以通过该按键控制智能电视对当前显示图像进行截屏，并对截屏图像执行图像识别操作，此时，处理器，可以配置为执行计算机指令以使智能电视执行：在接收到用户通过遥控设备发送的用于图像识别的键值时，对播放视频当前的显示图像进行截屏；搜索与截屏图像中包含的各图像元素相关的信息进行显示。
其中，图像元素可包括人物、物品、二维码以及台标中的一种或多种。
另外，本公开实施例还提供一种机器可读的非易失性存储介质，其上存储有计算机指令，计算机指令被处理器执行时实现上述任一截屏应用方法。
本公开提供的智能电视、其截屏应用方法、装置及存储介质，通过在识别到用户开始语音输入的时刻，对播放视频当前的显示图像进行截屏并将截屏图像存储；在用户的语音输入结束时，将输入的语音转化为语音指令；确定语音指令是否为与截屏相关的操作指令；在确定语音指令为与截屏相关的操作指令时，根据语音指令对存储的截屏图像执行相应操作。本公开提供的上述截屏应用方法采用先截屏后解析的流程，在用户语音输入之初就进行截屏操作，在用户语音输入结束之后，如果解析出用户的语音指令涉及到截屏作用，则可以直接采用存储的截屏图像进行相应操作，避免由于语音识别错过用户所需要的图像，采用这样的截屏方式得到的截屏图像更适应于用户的使用意图，有利于提高获取截屏图像的准确性。
本领域内的技术人员应明白，本公开可提供为方法、系统、或计算机程序产品。因此，本公开实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开实施例是参照根据本公开实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个 方框或多个方框中指定的功能的步骤。

Claims (15)

  1. 一种智能电视的截屏应用方法，所述方法包括：
    在识别到用户开始语音输入的时刻，对所述智能电视的显示屏上的当前显示图像进行截屏并将截屏图像存储；
    在用户的语音输入结束时，将输入的语音转化为语音指令；
    确定所述语音指令是否为与截屏相关的操作指令；
    响应于所述语音指令为与截屏相关的操作指令，根据所述语音指令对存储的所述截屏图像执行相应操作。
  2. 如权利要求1所述的方法，所述方法还包括：
    响应于所述语音指令不是与截屏相关的操作指令，将存储的所述截屏图像删除。
  3. 如权利要求1所述的方法，在所述根据所述语音指令对存储的所述截屏图像执行相应操作之前，还包括：
    显示所述截屏图像以及确定是否需要所述截屏图像的提示框；
    所述根据所述语音指令对存储的所述截屏图像执行相应操作，包括：
    响应于接收到需要所述截屏图像的指示，根据所述语音指令对所述截屏图像执行相应操作。
  4. 如权利要求3所述的方法，所述方法还包括：
    响应于接收到不需要所述截屏图像的指示，显示是否进入回退截屏操作的提示框；
    在接收到进入回退截屏操作的指示时，以当前的显示图像作为起始图像回退播放视频；
    在接收到暂停操作指令时，对当前的显示图像进行截屏；
    根据所述语音指令对当前的截屏图像执行相应操作。
  5. 如权利要求1所述的方法，在所述语音指令为图像识别指令时，所述根据所述语音指令对存储的所述截屏图像执行相应操作，包括：
    在所述截屏图像中识别出所述语音指令中包含的图像元素；
    搜索所述图像元素相关的信息进行显示。
  6. 如权利要求1所述的方法，还包括：
    在接收到用户通过遥控设备发送的用于图像识别的键值时，对播放视频当前的显示图像进行截屏；
    搜索与截屏图像中包含的各图像元素相关的信息进行显示。
  7. 如权利要求5或6所述的方法，所述图像元素包括人物、物品、二维码以及台标 中的一种或多种。
  8. 一种智能电视，包括显示屏、语音输入模块、存储器和处理器，其中，
    显示屏，用于显示图像；
    语音输入模块，用于接收用户的语音输入；
    存储器，与所述显示屏和语音输入模块通信，用于存储计算机指令、与所述显示屏关联的数据以及与所述语音输入模块关联的数据；
    处理器，与所述显示屏、语音输入模块和存储器通信，配置为执行所述计算机指令以使所述智能电视执行：在识别到用户开始语音输入的时刻，对所述智能电视的显示屏上的当前显示图像进行截屏并将截屏图像存储；在用户的语音输入结束时，将输入的语音转化为语音指令；确定所述语音指令是否为与截屏相关的操作指令；响应于所述语音指令为与截屏相关的操作指令，根据所述语音指令对存储的所述截屏图像执行相应操作。
  9. 如权利要求8所述的智能电视，所述处理器，配置为执行所述计算机指令以使所述智能电视执行：响应于所述语音指令不是与截屏相关的操作指令，将存储的所述截屏图像删除。
  10. 如权利要求8所述的智能电视，所述处理器，配置为执行所述计算机指令以使所述智能电视执行：在所述根据所述语音指令对存储的所述截屏图像执行相应操作之前，显示所述截屏图像以及确定是否需要所述截屏图像的提示框；响应于接收到需要所述截屏图像的指示，根据所述语音指令对所述截屏图像执行相应操作。
  11. 如权利要求10所述的智能电视，所述处理器，配置为执行所述计算机指令以使所述智能电视执行：响应于接收到不需要所述截屏图像的指示，显示是否进入回退截屏操作的提示框；在接收到进入回退截屏操作的指示时，以当前的显示图像作为起始图像回退播放视频；在接收到暂停操作指令时，对当前的显示图像进行截屏；根据所述语音指令对当前的截屏图像执行相应操作。
  12. 如权利要求8所述的智能电视，所述处理器，配置为执行所述计算机指令以使所述智能电视执行：在所述语音指令为图像识别指令时，在所述截屏图像中识别出所述语音指令中包含的图像元素；搜索所述图像元素相关的信息进行显示。
  13. 如权利要求8所述的智能电视，所述处理器，配置为执行所述计算机指令以使所述智能电视执行：在接收到用户通过遥控设备发送的用于图像识别的键值时，对播放视频当前的显示图像进行截屏；搜索与截屏图像中包含的各图像元素相关的信息进行显示。
  14. 如权利要求12或13所述的智能电视，所述图像元素包括人物、物品、二维码以及台标中的一种或多种。
  15. 一种机器可读的非易失性存储介质，其上存储有计算机指令，所述计算机指令被处理器执行时实现权利要求1-7任一项所述的方法。
PCT/CN2018/121061 2018-05-17 2018-12-14 一种智能电视、其截屏应用方法及存储介质 WO2019218656A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810475458.0 2018-05-17
CN201810475458.0A CN108712667B (zh) 2018-05-17 2018-05-17 一种智能电视、其截屏应用方法、装置及可读性存储介质

Publications (1)

Publication Number Publication Date
WO2019218656A1 true WO2019218656A1 (zh) 2019-11-21

Family

ID=63869109

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/121061 WO2019218656A1 (zh) 2018-05-17 2018-12-14 一种智能电视、其截屏应用方法及存储介质

Country Status (2)

Country Link
CN (2) CN108712667B (zh)
WO (1) WO2019218656A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113438360A (zh) * 2021-06-18 2021-09-24 当代世界(北京)信息科技研究院 一种安卓客户端基于人工智能与语音识别的截屏方法

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108712667B (zh) * 2018-05-17 2020-04-10 聚好看科技股份有限公司 一种智能电视、其截屏应用方法、装置及可读性存储介质
CN109582825B (zh) * 2018-12-07 2020-01-17 百度在线网络技术（北京）有限公司 用于生成信息的方法和装置
CN111372118A (zh) * 2018-12-25 2020-07-03 深圳Tcl新技术有限公司 一种截屏方法、智能终端及存储介质
CN109979462A (zh) * 2019-03-21 2019-07-05 广东小天才科技有限公司 一种结合上下文语境获取意图的方法和系统
CN111696549A (zh) * 2020-06-02 2020-09-22 深圳创维－Rgb电子有限公司 一种图片搜索方法、装置、电子设备及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103747351A (zh) * 2013-12-02 2014-04-23 乐视致新电子科技（天津）有限公司 智能电视的截屏方法和装置
CN104967889A (zh) * 2015-06-30 2015-10-07 小米科技有限责任公司 控制智能电视进行视频信息处理的方法及装置
CN106412708A (zh) * 2016-10-21 2017-02-15 上海与德信息技术有限公司 一种视频截图方法及装置
CN106604089A (zh) * 2016-10-25 2017-04-26 北京小米移动软件有限公司 智能电视的截屏分享方法及装置
CN107105340A (zh) * 2017-03-21 2017-08-29 百度在线网络技术（北京）有限公司 基于人工智能的视频中显示人物信息方法、装置和系统
CN107480236A (zh) * 2017-08-08 2017-12-15 深圳创维数字技术有限公司 一种信息查询方法、装置、设备和介质
CN108632662A (zh) * 2018-05-17 2018-10-09 聚好看科技股份有限公司 电视截屏方法、装置及包括电视截屏装置的设备
CN108712667A (zh) * 2018-05-17 2018-10-26 聚好看科技股份有限公司 一种智能电视、其截屏应用方法、装置及可读性存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203504698U (zh) * 2013-07-17 2014-03-26 广州珠江数码集团有限公司 一种电视直播截屏系统
CN104837030B (zh) * 2014-02-12 2019-04-16 中国电信股份有限公司 一种http流媒体实现快进快退播放的方法和系统
CN106708823A (zh) * 2015-07-20 2017-05-24 阿里巴巴集团控股有限公司 一种搜索处理方法、装置及系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103747351A (zh) * 2013-12-02 2014-04-23 乐视致新电子科技（天津）有限公司 智能电视的截屏方法和装置
CN104967889A (zh) * 2015-06-30 2015-10-07 小米科技有限责任公司 控制智能电视进行视频信息处理的方法及装置
CN106412708A (zh) * 2016-10-21 2017-02-15 上海与德信息技术有限公司 一种视频截图方法及装置
CN106604089A (zh) * 2016-10-25 2017-04-26 北京小米移动软件有限公司 智能电视的截屏分享方法及装置
CN107105340A (zh) * 2017-03-21 2017-08-29 百度在线网络技术（北京）有限公司 基于人工智能的视频中显示人物信息方法、装置和系统
CN107480236A (zh) * 2017-08-08 2017-12-15 深圳创维数字技术有限公司 一种信息查询方法、装置、设备和介质
CN108632662A (zh) * 2018-05-17 2018-10-09 聚好看科技股份有限公司 电视截屏方法、装置及包括电视截屏装置的设备
CN108712667A (zh) * 2018-05-17 2018-10-26 聚好看科技股份有限公司 一种智能电视、其截屏应用方法、装置及可读性存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113438360A (zh) * 2021-06-18 2021-09-24 当代世界(北京)信息科技研究院 一种安卓客户端基于人工智能与语音识别的截屏方法

Also Published As

Publication number Publication date
CN108712667A (zh) 2018-10-26
CN108712667B (zh) 2020-04-10
CN111010598B (zh) 2022-11-11
CN111010598A (zh) 2020-04-14

Similar Documents

Publication Publication Date Title
WO2019218656A1 (zh) 一种智能电视、其截屏应用方法及存储介质
US10706887B2 (en) Apparatus and method for displaying times at which an object appears in frames of video
WO2018077214A1 (zh) 信息搜索方法和装置
CN113163272B (zh) 视频剪辑方法、计算机设备及存储介质
WO2016029561A1 (zh) 基于显示终端的数据处理方法
CN110691281B (zh) 视频播放处理方法、终端设备、服务器及存储介质
CN107748615B (zh) 屏幕的控制方法、装置、存储介质及电子设备
CN105763897A (zh) 用于识别广播服务器的方法和设备
US11941048B2 (en) Tagging an image with audio-related metadata
CN108090424B (zh) 一种在线教学调研方法及设备
CN105808231B (zh) 录制与播放脚本的系统及方法
CN108881766B (zh) 视频处理方法、装置、终端和存储介质
US20110279224A1 (en) Remote control method and apparatus using smartphone
JP2017021672A (ja) 検索装置
CN111274449A (zh) 视频播放方法、装置、电子设备和存储介质
JP2014229103A (ja) 映像解析装置及び映像解析方法
US20190394361A1 (en) Video monitoring method, server, and video monitoring system
JP2020119181A (ja) 画像形成装置及びイベント検出システム
CN110691256B (zh) 视频关联信息的处理方法、装置，服务器及存储介质
JP2009153077A (ja) 情報処理装置及びプログラム
CN115499610A (zh) 视频生成方法、视频生成装置、电子设备和存储介质
JP2015099568A (ja) 行動記録装置、行動記録方法及びプログラム
CN116708923A (zh) 音视频数据的质量检测方法、装置及设备
KR101701813B1 (ko) 디스플레이 장치 및 이의 보이스 변환 방법
US20150229786A1 (en) Communication device and control method of communication device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18918688

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06.04.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18918688

Country of ref document: EP

Kind code of ref document: A1