WO2016169329A1 - 一种语音控制电子节目的方法、装置及存储介质 - Google Patents

一种语音控制电子节目的方法、装置及存储介质 Download PDF

Info

Publication number
WO2016169329A1
WO2016169329A1 PCT/CN2016/074384 CN2016074384W WO2016169329A1 WO 2016169329 A1 WO2016169329 A1 WO 2016169329A1 CN 2016074384 W CN2016074384 W CN 2016074384W WO 2016169329 A1 WO2016169329 A1 WO 2016169329A1
Authority
WO
WIPO (PCT)
Prior art keywords
program
information
voice
module
text information
Prior art date
Application number
PCT/CN2016/074384
Other languages
English (en)
French (fr)
Inventor
杜建平
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2016169329A1 publication Critical patent/WO2016169329A1/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
    • H04N21/439—Processing of audio elementary streams
    • H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • 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]
    • 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]
    • H04N21/42204—User interfaces specially adapted for controlling a client device through a remote control device; Remote control devices therefor
    • H04N21/42206—User interfaces specially adapted for controlling a client device through a remote control device; Remote control devices therefor characterized by hardware details
    • H04N21/4222—Remote control device emulator integrated into a non-television apparatus, e.g. a PDA, media center or smart toy
    • 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]
    • H04N21/42204—User interfaces specially adapted for controlling a client device through a remote control device; Remote control devices therefor
    • H04N21/42206—User interfaces specially adapted for controlling a client device through a remote control device; Remote control devices therefor characterized by hardware details
    • H04N21/42221—Transmission circuitry, e.g. infrared [IR] or radio frequency [RF]
    • 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
    • H04N21/432—Content retrieval operation from a local storage medium, e.g. hard-disk
    • 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
    • H04N21/439—Processing of audio elementary streams

Definitions

  • the invention relates to a home appliance control technology, and in particular to a method, a device and a storage medium for voice control of an electronic program.
  • the intelligent mobile terminal can utilize the characteristics of the infrared decoding chip itself to integrate the infrared remote control function into the intelligent mobile terminal, thereby realizing the intelligence.
  • the purpose of the mobile terminal to send an infrared signal; and the ability to transmit signals and transmit related data via wifi or Bluetooth.
  • voice interaction will be a very important supplement for human-computer interaction.
  • Voice interaction enables the human-machine interface to have both the ability to "listen” and “speak". When serving the Internet, it will liberate people's hands and lower the threshold of mobile Internet use, making input more convenient and service more efficient.
  • voice interaction as a new type of human-computer interaction is increasingly attracting the attention of the entire IT industry.
  • embodiments of the present invention are directed to a method, an apparatus, and a storage medium for voice control of an electronic program, which are capable of performing various operational controls on an electronic program according to the content input by the user.
  • the embodiment of the invention provides a method for voice control of an electronic program, the method comprising:
  • EPG Electronic Program Guide
  • the method further includes: displaying the searched television program resource information on the display screen of the self, and performing voice broadcast;
  • the program resource information includes, but is not limited to, a program broadcast time, a broadcast station, key person information, and program picture information.
  • the analyzing the text information comprises: performing a retrieval in the memory according to the text information, determining a control command corresponding to the text information according to a frequency of use of the user, and/or a precision matching degree; the control The command includes keyword information corresponding to the voice information input by the user.
  • the method further includes: performing voice training on hot words in the network.
  • the method further includes: updating and storing the EPG program mapping table.
  • controlling the controlled device to perform the program playing according to the search result comprises: sending a physical control signal according to the search result, and controlling the controlled device to perform the program playing;
  • the physical control signals include, but are not limited to, an infrared signal, a wifi, and a Bluetooth signal.
  • An embodiment of the present invention further provides an apparatus for voice control of an electronic program, where the apparatus includes: an external communication module, a voice recognition module, a semantic analysis module, an EPG resource module, and a physical signal sending module, where
  • the external communication module is configured to receive voice information input by the user, and send the voice information to the voice recognition module;
  • the voice recognition module is configured to convert the voice information into text information, and send the text information to a semantic analysis module;
  • the semantic analysis module is configured to analyze the text information, convert the text information into an identifiable control command, query an EPG mapping table according to the control command, and determine program channel information corresponding to the control command; Transmitting the program channel information to an EPG resource module;
  • the EPG resource module is configured to search for a corresponding television program resource according to the program channel information, and send the searched television program resource to a physical signal sending module and a display and broadcast module;
  • the physical signal sending module is configured to control the controlled appliance to play according to the search result.
  • the device further includes a display and broadcast module configured to: display the searched television program resource information on the display screen by the external communication module, and perform voice broadcast;
  • the program resource information includes, but is not limited to, a program broadcast time, a broadcast station, key person information, and program picture information.
  • the semantic analysis module is configured to perform a retrieval in the memory according to the text information, and determine a control command corresponding to the text information according to a frequency of use of the user, and/or an exact matching degree; the control command
  • the keyword information corresponding to the voice information input by the user is included.
  • the voice recognition module is further configured to perform hot words in the network. Voice training.
  • the semantic analysis module is further configured to update and store the EPG program mapping table.
  • the physical signal sending module is configured to send a physical control signal according to the search result, and control the controlled device to perform program broadcasting;
  • the physical control signals include, but are not limited to, an infrared signal, a wifi, and a Bluetooth signal.
  • Embodiments of the present invention also provide a computer storage medium storing a computer program for performing a method of voice control an electronic program according to an embodiment of the present invention.
  • the method, device and storage medium for voice control electronic program provided by the embodiments of the present invention first receive voice information input by a user, convert the voice information into text information, and then analyze the text information, and then the text Converting the information into an identifiable control command; then querying the EPG mapping table according to the control command to determine program channel information corresponding to the control command; and finally searching for the corresponding television program resource according to the program channel information, and controlling according to the search result Control the appliance to play the program.
  • the user only needs to say the TV program that he wants to watch to the mobile terminal, and can complete various operations such as searching, playing, and switching through various contents of the electronic program through the content input by the user voice. Control greatly improves the user experience.
  • FIG. 1 is a schematic flow chart of a voice control electronic program method according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a method for performing voice training on hot words in a network according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of an apparatus for controlling an electronic program by voice according to an embodiment of the present invention.
  • the voice information input by the user is first received, and the voice information is converted into text information; and the text information is analyzed, and the text information is converted into an identifiable control command;
  • the control command queries the EPG mapping table to determine program channel information corresponding to the control command.
  • the corresponding television program resource is searched according to the program channel information, and the controlled device is controlled to play the program according to the search result.
  • the network is connected to the network through an external unified communication interface, and the data is communicated with the external network, so as to receive voice information input by the user, control program play, display and broadcast the TV program resource, and the like.
  • the external unified communication interface includes a user input and output interface and different physical communication interfaces.
  • the user input and output interface accepts the user's voice information through the microphone, and transmits the original, unprocessed voice information to the corresponding internal function module; after searching for the corresponding TV program resource, the user input and output interface passes through the Speakereer The queried television program resources are broadcasted, and the searched television program resources are displayed through the display of the mobile terminal.
  • the physical communication interface provides a unified network interface for external wifi, Bluetooth and other data services, and the mobile terminal can communicate with the Internet through a physical communication interface to realize data transmission and reception.
  • FIG. 1 is a schematic flowchart of a voice control electronic program method according to an embodiment of the present invention. As shown in FIG. 1, the method for voice control an electronic program in this embodiment includes the following steps:
  • Step 101 Receive voice information input by a user, and convert the voice information into text information.
  • the voice information sent by the user through the audio input device such as the mobile terminal microphone is recognized, and the original voice information input by the user is converted into text information in the form of characters or characters; for example, the user inputs through the microphone of the mobile terminal: “I To see rum, in this step, the voice information of "I want to see rumors" is recognized, and the voice information is converted into text information.
  • the recognition is successful, the text information converted into "woyaokanzhenhuanzhuan".
  • the conversion fails that is, according to the voice information input by the user
  • the user cannot be converted into the corresponding text information and then the user is prompted to input again through the external unified communication interface; for example, the external unified communication interface is displayed by voice broadcast or screen display. , prompt the user to enter again.
  • Step 102 Perform analysis on the text information, and convert the text information into an identifiable control command.
  • the analyzing the text information comprises: performing a retrieval in the memory according to the text information, and determining, according to a user's use frequency, and/or a precision matching degree, a corresponding control of the text information.
  • the command includes the keyword information corresponding to the voice information input by the user.
  • the instruction corresponding to the text information is most likely to be determined according to the comprehensive index of the user's usage frequency and the accuracy matching degree, and the determined most likely corresponding instruction is used as the control command corresponding to the text information.
  • a semantic analysis is performed on the received text information “woyaokanzhenhuanzhuan”, and the result of the analysis is that the user wants to watch the program “ ⁇ ”; the text information is converted into a “find rumor” control command, wherein " ⁇ " as a search keyword;
  • Step 103 Query an EPG mapping table according to the control command, and determine program channel information corresponding to the control command.
  • the EPG mapping table is queried according to the keyword information in the control command, where the EPG mapping table is a correspondence table between the program keyword and the corresponding program channel; by querying the EPG mapping table, determining the location a program channel information corresponding to the control command;
  • control command is “Find ⁇ ”
  • search keyword “ ⁇ ” it is determined that the program type is a TV drama, and the EPG mapping table is searched for the TV drama corresponding to “ ⁇ ”.
  • Program channel information such as channel_id;
  • the EPG mapping table may be a locally stored EPG mapping table or a server-side EPG mapping table.
  • the querying the EPG mapping according to the keyword information in the control command The table is: according to the keywords in the control command Information query server EPG mapping table;
  • the method further includes: periodically updating and storing the EPG program mapping table; in an embodiment, periodically The EPG program mapping table in the server is obtained, and the EPG program mapping table is periodically updated and stored locally.
  • the function of periodically updating and storing the EPG program mapping table locally is that when the user converts the voice information into a control command after inputting the voice information, the user can immediately perform the local query. It is not necessary to send a query command query through the network every time; this greatly improves the search efficiency and the user experience is more perfect.
  • the embodiment of the present invention does not limit the query method.
  • the EPG mapping table of the server may be directly queried according to the keyword information in the control command, which requires each network to pass through the query. Search, search is less efficient.
  • Step 104 Search for corresponding TV program resources according to the program channel information, and control the controlled device to perform program playback according to the search result;
  • the corresponding television program resource is searched on the server according to the program channel information, and if the corresponding program resource is searched, the television program resource is stored; wherein the television program resource includes but is not limited to the program broadcast. Time, broadcast station, key person information, program picture information, etc.; if the program resource is not searched, and the searched program does not exist, the feedback search is empty, the program does not exist, and the like;
  • the corresponding program resource may be searched for in the infrared code database data in the set top box information that is configured by the infrared remote control with the infrared signal according to the program channel information.
  • the above manner is taken as an example, but the scope is not limited.
  • the television program resources of the server may also be searched for and received through wifi or 3G, 4G data services.
  • Controlling the program play package according to the search result when the corresponding television program resource is searched The method further comprises: transmitting a physical control signal according to the search result, and controlling the controlled device to perform program play; wherein the physical control signal includes but is not limited to an infrared signal, a wifi, a Bluetooth signal.
  • infrared signals can be used to control various types of infrared TV sets or set-top box devices to control various types of smart wifi TVs or set-top boxes or video box devices through wifi data signals; to control various types of smart Bluetooth TVs or set-top boxes or video box devices through Bluetooth signals;
  • the user can watch the TV program he wants to watch on the controlled appliance such as a television.
  • the method further includes: displaying the searched television program resource information on the display screen of the self-display, and performing the voice broadcast; wherein the program resource information includes but is not limited to: the program broadcast time, broadcast Release, key person information, program picture information.
  • the information display screens such as "search result is empty” and "program does not exist” are displayed on the display screen, and broadcasted by voice.
  • the method when the EPG mapping table is a locally stored EPG mapping table, the method further includes: periodically performing voice training on hot words in the network.
  • the method for periodically performing voice training on hot words in the network in the embodiment of the present invention is as shown in FIG. 2, and includes the following steps:
  • Step 201 Perform statistics on program-related words on the server side to determine a current hot vocabulary
  • the first 20% words with high frequency of occurrence may be used as the current hot words
  • Step 202 Filter and convert the current hot words
  • words that are not related to the title of the program such as words indicating time and place, and hot words that have been identified before are removed, and the unrecognized hot vocabulary information with higher frequency of use is converted into text information;
  • Step 203 Train the received hot vocabulary text information and save the training result.
  • the purpose of performing the voice training on the popular vocabulary in the network is to improve the recognition accuracy of the popular popular vocabulary, and to improve the success rate of the EPG program search.
  • the server-side The voice training of popular vocabulary is generally calculated after a period of accumulation, and the training period can be determined according to the actual situation.
  • FIG. 3 is a schematic structural diagram of a device for controlling an electronic program by voice according to an embodiment of the present invention.
  • the device includes: an external communication module 31, and voice recognition.
  • the external communication module 31 is configured to receive voice information input by the user, and send the voice information to the voice recognition module;
  • the external communication module 31 receives voice information input by a user through an audio input device such as a microphone;
  • the voice recognition module 32 is configured to convert the voice information into text information, and send the text information to the semantic analysis module 33;
  • the voice recognition module 32 converts the received original voice information from the external communication module 31 into text information in the form of characters or characters; for example, the voice recognition module 32 receives voice information from the external communication module 31. After the phrase "I want to see rum", the speech recognition module 32 recognizes the voice information "I want to see rum” and converts the voice information into text information. When the recognition is successful, the converted text information is "woyaokanzhenhuanzhuan", and the converted text information is sent to the semantic analysis module 33.
  • the voice recognition module 32 prompts the user to input again through the external unified communication interface; for example, the external unified communication interface prompts the user to input again through voice announcement or screen display.
  • the semantic analysis module 33 is configured to analyze the text information, convert the text information into an identifiable control command, query the EPG mapping table according to the control command, and determine program channel information corresponding to the control command. Transmitting the program channel information to the EPG resource module 34;
  • the semantic analysis module 33 performs semantic analysis on the text information, and converts the text information into a control command recognizable by the universal interface; in an embodiment, the semantic analysis module 33 is configured to Retrieving in the memory according to the text information, determining a control command corresponding to the text information according to a comprehensive index such as a frequency of use of the user, and/or a precision matching degree; the control command includes a voice information input by the user Corresponding keyword information. For example, the semantic analysis module 33 determines an instruction corresponding to the text information most likely according to a comprehensive index such as a frequency of use of the user and a precision matching degree, and uses the determined most likely corresponding instruction as the corresponding control of the text information. command.
  • the semantic analysis module 33 performs semantic analysis on the received text information “woyaokanzhenhuanzhuan”, and the analyzed result is that the user wants to watch the program “ ⁇ ”; the semantic analysis module 33 converts the text information into "Looking for rumors" is a control command, in which " ⁇ " is a search keyword;
  • the semantic analysis module 33 queries the EPG mapping table according to the control command, and determines the program channel information corresponding to the control command, and queries the EPG mapping table according to the keyword information in the control command, where the EPG mapping table a correspondence table between the program keyword and the corresponding program channel; determining the program channel information corresponding to the control command by querying the EPG mapping table;
  • the semantic analysis module 33 is based on The search keyword " ⁇ " determines that the program type is a TV drama, searches for the program channel information corresponding to the TV series " ⁇ " in the EPG mapping table, such as channel_id; and transmits the program channel information to the EPG resource.
  • Module 34
  • the EPG mapping table may be a locally stored EPG mapping table or a server-side EPG mapping table.
  • the semantic analysis module 33 is configured according to the The keyword information query EPG mapping table in the control command is: querying an EPG mapping table of the server end according to the keyword information in the control command;
  • the semantic analysis module 33 is further configured to: periodically update and store the EPG program mapping table; In an example, the semantic analysis module 33 periodically acquires an EPG program mapping table in the server from the EPG resource module 34, and periodically updates and stores the EPG program mapping table locally.
  • the function of periodically updating and storing the EPG program mapping table locally is that when the user converts the voice information into a control command after inputting the voice information, the user can immediately perform the local query. It is not necessary to send a query command query through the network every time; this greatly improves the search efficiency and the user experience is more perfect.
  • the embodiment of the present invention is not limited to the query method.
  • the EPG mapping table of the server may be directly queried according to the keyword information in the control command, which requires each query. Searched by the web, search efficiency is low
  • the EPG resource module 34 is configured to search for a corresponding television program resource according to the program channel information, and send the searched television program resource to a physical signal sending module and a display and broadcast module;
  • the EPG resource module 34 searches for a corresponding TV program resource on the server side according to the program channel information, and if the corresponding program resource is searched, stores the TV program resource; and searches for the TV program resources are sent to the physical signal sending module and display And the broadcast program module; wherein, the television program resource includes, but is not limited to, a program broadcast time, a broadcast station, key person information, program picture information, and the like; if the program resource is not searched, and the searched program does not exist, Then, the display and the broadcast module feed back error information that the search is empty, the program does not exist, and the like;
  • the EPG resource module 34 may search for corresponding program resources in the infrared code database data in the set top box information that is built by the infrared remote control with the infrared signal according to the program channel information, but Limit this range. In practical applications, you can also search and receive TV program resources on the server side through wifi or 3G, 4G data services.
  • the physical signal sending module 35 is configured to control program play according to the television program resource
  • the physical signal sending module 35 is configured to: send a physical control signal according to the search result, and control the controlled device to perform program play; wherein the physical control signal includes, but is not limited to, an infrared signal, Wifi, Bluetooth signal.
  • infrared signals can be used to control various types of infrared TV sets or set-top box devices to control various types of smart wifi TVs or set-top boxes or video box devices through wifi data signals; to control various types of smart Bluetooth TVs or set-top boxes or video box devices through Bluetooth signals; The user can watch the TV program he wants to watch on the controlled appliance such as a television.
  • the device further includes a display and broadcast module 36 configured to display the searched television program resource information on its own display screen and perform voice broadcast;
  • the display and broadcast module 36 is configured to display the queried program resource on the display screen through an external communication module, and broadcast the message through voice;
  • the program resource information includes but is not limited to: program broadcast Time, broadcast station, key person information, program picture information.
  • the display and broadcast module 36 displays the information display screen such as "search result is empty”, “program does not exist”, and the like, and Broadcast by voice.
  • the voice recognition module 32 is further configured to: periodically perform voice training on hot words in the network;
  • the EPG resource module 34 is further configured to perform statistics on the program-related words on the server side to determine the current hot words.
  • the top 20% words with high frequency of occurrence may be used as the current hot words.
  • the determined current hot words are sent to the semantic analysis module 33;
  • the semantic analysis module 33 is further configured to filter and convert the current hot words
  • the semantic analysis module 33 removes words that are not related to the title of the program, such as words indicating time and place, and hot words that have been identified before, and the current frequency of use is higher. Identifying the popular vocabulary information is converted into text information; and the text information into which the hot vocabulary information is converted is sent to the speech recognition module 32;
  • the voice recognition module 32 is further configured to train the received hot vocabulary text information and save the training result;
  • the voice recognition module 32 continuously performs voice training on the received popular vocabulary text information according to different voices, intonations, and speech rates, and saves the training result;
  • Each module in the voice control electronic program device proposed in the embodiment of the present invention may be implemented by a processor, and may also be implemented by a specific logic circuit; wherein the processor may be a processor on a mobile terminal or a server.
  • the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA).
  • the above method for voice control electronic program is implemented in the form of a software function module and sold or used as a standalone product, it may also be stored in a computer readable storage medium.
  • the technical solution of the embodiments of the present invention may be embodied in the form of a software product in essence or in the form of a software product.
  • the machine software product is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read only memory (ROM), a magnetic disk, or an optical disk.
  • program codes such as a USB flash drive, a mobile hard disk, a read only memory (ROM), a magnetic disk, or an optical disk.
  • an embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores a computer program for performing the above-described voice control electronic program of the embodiment of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Databases & Information Systems (AREA)
  • Telephonic Communication Services (AREA)
  • Selective Calling Equipment (AREA)

Abstract

本发明提供了一种语音控制电子节目的方法，包括：接收用户输入的语音信息，将所述语音信息转换为文本信息；对所述文本信息进行分析，将所述文本信息转换为可识别的控制命令；根据所述控制命令查询电子节目指南EPG映射表，确定所述控制命令对应的节目频道信息；根据所述节目频道信息搜索对应的电视节目资源，根据搜索结果控制被控电器进行节目播放。本发明还提供了一种语音控制电子节目装置及存储介质。

Description

一种语音控制电子节目的方法、装置及存储介质 技术领域
本发明涉及家电控制技术，尤其涉及一种语音控制电子节目的方法、装置及存储介质。
背景技术
随着因特网的高速发展，移动终端已经逐渐成为人们日常工作和生活中必不可少的工具。随着3G业务的全面普及以及智能终端的广泛使用，人们对智能移动终端的诉求已经不限于语音通话，娱乐功能已成为智能移动终端的一大重要功能。并且，目前的智能移动终端在红外遥控功能、wifi、蓝牙传输等方面也有了较为迅速的发展，智能移动终端能够利用红外解码芯片本身的特性，将红外遥控功能集成于智能移动终端，实现了智能移动终端发送红外信号的目的；并能够通过wifi、蓝牙发送信号并传输相关数据。
随着智能移动终端功能的不断完善，语音交互将会是一个非常重要的人机交互补充方式。语音交互使人机界面同时具备了“听”和“说”的能力，在服务互联网化的时，将解放人们的双手，降低移动互联网的使用门槛，让输入更便捷，服务效率更高。随着移动智能终端的普及，语音交互作为一种新型的人机交互方式，正越来越引起整个IT业界的重视。
但是，目前的语音交互仅限于人机的简单沟通，现有技术中并没有涉及太多关于人机语音交互的应用；随着互联网业务的兴起以及各种网络视频的应用，人们通过网络视频装置就可以欣赏各种各样的丰富的网络资源节目。在这种情况下，是否可以通过语音来控制电子节目的检索和播放，现有技术中还没有相关提案，因此，如何通过语音来控制电子节目的检索和播放，实现绝佳体验的智能家电控制功能，是目前亟待解决的问题。
发明内容
有鉴于此，本发明实施例期望提供一种语音控制电子节目的方法、装置及存储介质，能够根据用户语音输入的内容，完成对电子节目的各种操作控制。
为达到上述目的，本发明实施例的技术方案是这样实现的：
本发明实施例提供了一种语音控制电子节目的方法，所述方法包括：
接收用户输入的语音信息，将所述语音信息转换为文本信息；
对所述文本信息进行分析，将所述文本信息转换为可识别的控制命令；
根据所述控制命令查询电子节目指南(EPG，Electronic Program Guide)映射表，确定所述控制命令对应的节目频道信息；
根据所述节目频道信息搜索对应的电视节目资源，根据搜索结果控制被控电器进行节目播放。
上述方案中，所述方法还包括：将搜索到的电视节目资源信息在自身显示屏进行显示，并进行语音播报；
所述节目资源信息包括但不限于：节目播出时间、播出台、关键人物信息、节目图片信息。
上述方案中，所述对文本信息进行分析包括：根据所述文本信息在存储器内进行检索，根据用户的使用频率、和/或精准匹配符合度确定所述文本信息对应的控制命令；所述控制命令中包括用户输入的语音信息所对应的关键词信息。
上述方案中，所述方法还包括：对网络中的热门词汇进行语音训练。
上述方案中，所述方法还包括：更新并存储所述EPG节目映射表。
上述方案中，所述根据搜索结果控制被控电器进行节目播放包括：根据搜索结果发送物理控制信号，控制被控制电器进行节目播放；
其中，所述物理控制信号包括但不限于红外信号、wifi、蓝牙信号。
本发明实施例还提供了一种语音控制电子节目的装置，所述装置包括：外部通讯模块、语音识别模块、语义分析模块、EPG资源模块、物理信号发送模块，其中，
所述外部通讯模块，配置为接收用户输入的语音信息，并将所述语音信息发送到语音识别模块；
所述语音识别模块，配置为将所述语音信息转换为文本信息，并将所述文本信息发送到语义分析模块；
所述语义分析模块，配置为对所述文本信息进行分析，将所述文本信息转换为可识别的控制命令；根据所述控制命令查询EPG映射表，确定所述控制命令对应的节目频道信息；将所述节目频道信息发送到EPG资源模块；
所述EPG资源模块，配置为根据所述节目频道信息搜索对应的电视节目资源，并将搜索到的电视节目资源发送到物理信号发送模块和显示和播报模块；
所述物理信号发送模块，配置为根据搜索结果控制被控电器进行播放。
上述方案中，所述装置还包括显示和播报模块，配置为：通过外部通信模块将搜索到的电视节目资源信息在自身显示屏进行显示，并进行语音播报；
所述节目资源信息包括但不限于：节目播出时间、播出台、关键人物信息、节目图片信息。
上述方案中，所述语义分析模块，配置为根据所述文本信息在存储器内进行检索，根据用户的使用频率、和/或精准匹配符合度确定所述文本信息对应的控制命令；所述控制命令中包括用户输入的语音信息所对应的关键词信息。
上述方案中，所述语音识别模块，还配置为对网络中的热门词汇进行 语音训练。
上述方案中，所述语义分析模块，还配置为更新并存储所述EPG节目映射表。
上述方案中，所述物理信号发送模块，配置为根据搜索结果发送物理控制信号，控制被控制电器进行节目播放；
其中，所述物理控制信号包括但不限于红外信号、wifi、蓝牙信号。
本发明实施例还提供了一种计算机存储介质，所述计算机存储介质存储有计算机程序，该计算机程序用于执行本发明实施例的语音控制电子节目的方法。
本发明实施例所提供的语音控制电子节目的方法、装置及存储介质，先接收用户输入的语音信息，将所述语音信息转换为文本信息；再对所述文本信息进行分析，将所述文本信息转换为可识别的控制命令；之后根据所述控制命令查询EPG映射表，确定所述控制命令对应的节目频道信息；最后根据所述节目频道信息搜索对应的电视节目资源，根据搜索结果控制被控电器进行节目播放。如此，用户只需要通过对移动终端说出自己想要看的电视节目，就可以通过用户语音输入的内容，完成对电子节目的各种操作包括搜索、播放、切换在内的各种操作过程的控制，大大提高了用户体验。
附图说明
图1为本发明实施例一语音控制电子节目方法流程示意图；
图2为本发明实施例对网络中的热门词汇进行语音训练的方法流程示意图；
图3为本发明实施例语音控制电子节目的装置结构示意图。
具体实施方式
本发明实施例中，先接收用户输入的语音信息，将所述语音信息转换为文本信息；再对所述文本信息进行分析，将所述文本信息转换为可识别的控制命令；之后根据所述控制命令查询EPG映射表，确定所述控制命令对应的节目频道信息；最后根据所述节目频道信息搜索对应的电视节目资源，根据搜索结果控制被控电器进行节目播放。
本发明实施例中，在硬件上通过外部统一通讯接口连接网络，与外界网络进行数据通讯，实现接收用户输入的语音信息、控制节目播放、将电视节目资源进行显示和播报等功能。所述外部统一通讯接口，包括用户输入输出接口以及不同的物理通讯接口。例如，用户输入输出接口通过麦克风接受用户的语音信息，将原始的、未经任何处理语音信息的传递到相应的内部功能模块；在搜索到对应的电视节目资源后，用户输入输出接口通过Speakeer将查询到的电视节目资源进行播报，并通过移动终端的显示器将搜索到的电视节目资源进行显示。物理通讯接口为统一提供对外的wifi、蓝牙及其他数据业务的网络接口，移动终端可以通过物理通讯接口与互联网进行通讯，实现数据的收发。
下面结合附图及实施例，对本发明实施例技术方案的实施作进一步的详细描述。图1为本发明实施例一语音控制电子节目方法流程示意图，如图1所示，本实施例语音控制电子节目的方法包括以下步骤：
步骤101：接收用户输入的语音信息，将所述语音信息转换为文本信息；
本步骤中，对用户通过移动终端麦克风等音频输入设备发出的语音信息进行识别，将用户输入的原始语音信息转换为文字或字符形式的文本信息；例如，用户通过移动终端的麦克风输入：“我要看甄嬛传”，本步骤中，对“我要看甄嬛传”这一语音信息进行识别，将语音信息转换成文本信息，当识别成功时，转换成的文本信息为“woyaokanzhenhuanzhuan”。
本步骤中，当转换失败时，即根据用户输入的语音信息无法转换成对应的文本信息时，则通过外部统一通讯接口提示用户再次输入；如：外部统一通讯接口通过语音播报或屏幕显示的方式，提示用户再次输入。
步骤102：对所述文本信息进行分析，将所述文本信息转换为可识别的控制命令；
本步骤中，所述对所述文本信息进行分析包括：根据所述文本信息在存储器内进行检索，根据用户的使用频率、和/或精准匹配符合度等综合指标确定所述文本信息对应的控制命令；所述控制命令中包括用户输入的语音信息所对应的关键词信息。例如，根据用户的使用频次和精准匹配符合度等综合指标确定所述文本信息最可能对应的指令，将所述确定的最可能对应的指令作为所述文本信息对应的控制命令。
例如，对接收到的文本信息“woyaokanzhenhuanzhuan”进行语义分析，分析后的结果为用户要看“甄嬛传”这一节目；将所述文本信息转换成“查找甄嬛传”这一控制命令，其中，“甄嬛传”为搜索关键词；
步骤103：根据所述控制命令查询EPG映射表，确定所述控制命令对应的节目频道信息；
本步骤中，根据所述控制命令中的关键词信息查询EPG映射表，其中，所述EPG映射表为节目关键词与对应的节目频道之间的对应关系表；通过查询EPG映射表，确定所述控制命令对应的节目频道信息；
例如，所述控制命令为“查找甄嬛传”时，本步骤中，根据所述搜索关键词“甄嬛传”，确定节目类型为电视剧，在EPG映射表中查找找到“甄嬛传”这个电视剧所对应的节目频道信息，如channel_id；
EPG映射表可以为本地存储的EPG映射表，也可以是服务器端的EPG映射表；当所述EPG映射表为服务器端的EPG映射表时，所述根据所述控制命令中的关键词信息查询EPG映射表为：根据所述控制命令中的关键词 信息查询服务器端的EPG映射表；
为了提高节目搜索效率，所述EPG映射表可以为本地存储的EPG映射表时，对应的，所述方法还包括：周期性更新并存储所述EPG节目映射表；在一实施例中，周期性获取服务器内的EPG节目映射表，并在本地周期性更新并存储所述EPG节目映射表。
本发明实施例中，在本地周期性更新并存储所述EPG节目映射表的作用是当用户在输入语音信息后，将所述语音信息转换为控制命令后，就可以立即在本地进行查询，而不需要每次都经过网络发送查询命令查询；如此这样大大提高了搜索效率，用户体验更加完美。当然，本发明实施例并不限定这一查询方法，本发明实施例中，也可以根据所述控制命令中的关键词信息直接查询服务器端的EPG映射表，这就需要每次查询都要经过网络搜索，搜索效率较低。
步骤104：根据所述节目频道信息搜索对应的电视节目资源，根据搜索结果控制被控电器进行节目播放；
本步骤中，根据所述节目频道信息在服务器端搜索对应的电视节目资源，如果搜索到对应的节目资源，则存储所述电视节目资源；其中，所述电视节目资源包括但不限于节目播出时间、播出台、关键人物信息、节目图片信息等；如果没有搜索到节目资源、所搜索的节目中不存在时，则反馈搜索为空、节目不存在等错误信息；
本发明实施例中，可以根据所述节目频道信息，通过红外信号在与自身建立红外遥控适配的机顶盒信息中的红外码库数据中搜索对应的节目资源；本发明实施例中，仅仅是以上述方式为例，但并不限定此范围，在实际应用中，还可以通过wifi或3G、4G数据业务搜索并接收服务器端的电视节目资源。
当搜索到对应的电视节目资源时，所述根据搜索结果控制节目播放包 括：根据搜索结果发送物理控制信号，控制被控制电器进行节目播放；其中，所述物理控制信号包括但不限于红外信号、wifi、蓝牙信号。例如，可以通过红外信号控制各类的红外电视机或机顶盒设备通过wifi数据信控制各类智能wifi电视或机顶盒或视频盒子设备；通过蓝牙信号控制各类智能蓝牙电视或机顶盒或视频盒子设备；如此，用户能够在电视机等被控制电器上观看自己想要看的电视节目。
本发明实施例中，所述方法还包括：将搜索到的电视节目资源信息在自身显示屏进行显示，并进行语音播报；其中，所述节目资源信息包括但不限于：节目播出时间、播出台、关键人物信息、节目图片信息。
当没有搜索到节目资源、所搜索的节目中不存在时，将“搜索结果为空”、“节目不存在”等信息显示屏上进行显示，并通过语音进行播报。
如此，用户只需要通过对移动终端说出自己想要看的电视节目，就完成包括节目搜索、播放(切换)在内的整个的操作过程。
本发明实施例中，当所述EPG映射表为本地存储的EPG映射表时，所述方法还包括：周期性对网络中的热门词汇进行语音训练。本发明实施例周期性对网络中的热门词汇进行语音训练的方法如图2所示，包括以下步骤：
步骤201：对服务器端的节目相关词语进行统计，确定当下的热门词汇；
本发明实施例中，可以将出现频度高的前20％词语作为当下的热门词汇；
步骤202：对所述当下的热门词汇进行筛选和转换；
本步骤中，将与节目标题无关的词语，例如表示时间、地点的词语，以及在此之前已经识别出的热门词汇去掉，将当前使用频率较高的、未识别热门词汇信息转换为文本信息；
步骤203：对接收到的热门词汇文本信息进行训练，并保存训练结果。
本步骤中，通过不同的语音、语调、语速，不断对接收到的热门词汇文本信息进行语音训练，并保存训练结果；
本发明实施例中，周期性对网络中的热门词汇进行语音训练的目的是为了提高对当下热门流行词汇的识别准确率，进而提高EPG节目搜索的成功率；本发明实施例中，对服务器端的的热门词汇的语音训练一般是经过一段时间积累后才统计的，训练周期可根据实际情况确定。
本发明实施例还提供了一种语音控制电子节目的装置，图3为本发明实施例语音控制电子节目的装置结构示意图，如图3所示，所述装置包括：外部通讯模块31、语音识别模块32、语义分析模块33、EPG资源模块34、物理信号发送模块35，其中，
所述外部通讯模块31，配置为接收用户输入的语音信息，并将所述语音信息发送到语音识别模块；
在一实施例中，所述外部通讯模块31通过麦克风等音频输入设备接收用户输入的语音信息；
所述语音识别模块32，配置为将所述语音信息转换为文本信息，并将所述文本信息发送到语义分析模块33；
在一实施例中，所述语音识别模块32将接收到的来自外部通讯模块31原始语音信息转换为文字或字符形式的文本信息；例如，语音识别模块32接收到来自外部通讯模块31的语音信息：“我要看甄嬛传”后，所述语音识别模块32对“我要看甄嬛传”这一语音信息进行识别，将语音信息转换成文本信息，当识别成功时，转换成的文本信息为“woyaokanzhenhuanzhuan”，并将转换后的文本信息发送到语义分析模块33。
当转换失败时，即根据用户输入的语音信息无法转换成对应的文本信 息时，则所述语音识别模块32通过外部统一通讯接口提示用户再次输入；如：外部统一通讯接口通过语音播报或屏幕显示的方式，提示用户再次输入。
所述语义分析模块33，配置为对所述文本信息进行分析，将所述文本信息转换为可识别的控制命令；根据所述控制命令查询EPG映射表，确定所述控制命令对应的节目频道信息；将所述节目频道信息发送到EPG资源模块34；
在一实施例中，所述语义分析模块33对所述文本信息进行语义分析，将所述文本信息转换为通用接口可识别的控制命令；在一实施例中，所述语义分析模块33配置为：根据所述文本信息在存储器内进行检索，根据用户的使用频率、和/或精准匹配符合度等综合指标确定所述文本信息对应的控制命令；所述控制命令中包括用户输入的语音信息所对应的关键词信息。例如，所述语义分析模块33根据用户的使用频次和精准匹配符合度等综合指标确定所述文本信息最可能对应的指令，将所述确定的最可能对应的指令作为所述文本信息对应的控制命令。
例如，所述语义分析模块33对接收到的文本信息“woyaokanzhenhuanzhuan”进行语义分析，分析后的结果为用户要看“甄嬛传”这一节目；所述语义分析模块33将所述文本信息转换成“查找甄嬛传”这一控制命令，其中，“甄嬛传”为搜索关键词；
所述语义分析模块33根据所述控制命令查询EPG映射表，确定所述控制命令对应的节目频道信息时，根据所述控制命令中的关键词信息查询EPG映射表，其中，所述EPG映射表为节目关键词与对应的节目频道之间的对应关系表；通过查询EPG映射表，确定所述控制命令对应的节目频道信息；
例如，所述控制命令为“查找甄嬛传”时，所述语义分析模块33根据 所述搜索关键词“甄嬛传”，确定节目类型为电视剧，在EPG映射表中查找找到“甄嬛传”这个电视剧所对应的节目频道信息，如channel_id；并将所述节目频道信息发送到EPG资源模块34；
本发明实施例中，EPG映射表可以为本地存储的EPG映射表，也可以是服务器端的EPG映射表；当所述EPG映射表为服务器端的EPG映射表时，所述所述语义分析模块33根据所述控制命令中的关键词信息查询EPG映射表为：根据所述控制命令中的关键词信息查询服务器端的EPG映射表；
为了提高节目搜索效率，当所述EPG映射表可以为本地存储的EPG映射表时，对应的，所述语义分析模块33还配置为：周期性更新并存储所述EPG节目映射表；在一实施例中，所述语义分析模块33周期性从所述EPG资源模块34获取服务器内的EPG节目映射表，并在本地周期性更新并存储所述EPG节目映射表。
本发明实施例中，在本地周期性更新并存储所述EPG节目映射表的作用是当用户在输入语音信息后，将所述语音信息转换为控制命令后，就可以立即在本地进行查询，而不需要每次都经过网络发送查询命令查询；如此这样大大提高了搜索效率，用户体验更加完美。当然，本发明实施例并不限定于这一种查询方法，本发明实施例中，也可以根据所述控制命令中的关键词信息直接查询服务器端的EPG映射表，这就需要每次查询都要经过网络搜索，搜索效率较低
所述EPG资源模块34，配置为根据所述节目频道信息搜索对应的电视节目资源，并将搜索到的电视节目资源发送到物理信号发送模块和显示和播报模块；
在一实施例中，所述EPG资源模块34，根据所述节目频道信息在服务器端搜索对应的电视节目资源，如果搜索到对应的节目资源，则存储所述电视节目资源；并将搜索到的电视节目资源发送到物理信号发送模块和显 示和播报模块；其中，所述电视节目资源包括但不限于节目播出时间、播出台、关键人物信息、节目图片信息等；如果没有搜索到节目资源、所搜索的节目中不存在时，则向显示和播报模块反馈搜索为空、节目不存在等错误信息；
本发明实施例中，所述EPG资源模块34可根据所述节目频道信息，通过红外信号在与自身建立红外遥控适配的机顶盒信息中的红外码库数据中搜索对应的节目资源，但并不限定此范围，在实际应用中，还可以通过wifi或3G、4G数据业务搜索并接收服务器端的电视节目资源。
所述物理信号发送模块35，配置为根据所述电视节目资源控制节目播放；
当搜索到对应的电视节目资源时，所述物理信号发送模块35配置为：根据搜索结果发送物理控制信号，控制被控制电器进行节目播放；其中，所述物理控制信号包括但不限于红外信号、wifi、蓝牙信号。例如，可以通过红外信号控制各类的红外电视机或机顶盒设备通过wifi数据信控制各类智能wifi电视或机顶盒或视频盒子设备；通过蓝牙信号控制各类智能蓝牙电视或机顶盒或视频盒子设备；如此，用户能够在电视机等被控制电器上观看自己想要看的电视节目。
本发明实施例中，所述装置还包括显示和播报模块36，配置为将搜索到的电视节目资源信息在自身显示屏进行显示，并进行语音播报；
在一实施例中，所述显示和播报模块36配置为：通过外部通讯模块将查询到节目资源在显示屏上进行显示，并通过语音进行播报；所述节目资源信息包括但不限于：节目播出时间、播出台、关键人物信息、节目图片信息。
当没有搜索到节目资源、所搜索的节目中不存在时，所述显示和播报模块36将“搜索结果为空”、“节目不存在”等信息显示屏上进行显示，并 通过语音进行播报。
本发明实施例中，当所述EPG映射表为本地存储的EPG映射表时，所述语音识别模块32还配置为：周期性对网络中的热门词汇进行语音训练；
对应的，所述EPG资源模块34还配置为对服务器端的节目相关词语进行统计，确定当下的热门词汇；本发明实施例中，可以将出现频度高的前20％词语作为当下的热门词汇，并将确定的当下的热门词汇发送到所述语义分析模块33；
语义分析模块33还配置为对所述当下的热门词汇进行筛选和转换；
在一实施例中，所述语义分析模块33，将与节目标题无关的词语，例如表示时间、地点的词语，以及在此之前已经识别出的热门词汇去掉，将当前使用频率较高的、未识别热门词汇信息转换为文本信息；并将所述热门词汇信息转换为的文本信息发送到语音识别模块32；
所述语音识别模块32还配置为对接收到的热门词汇文本信息进行训练，并保存训练结果；
在一实施例中，所述语音识别模块32根据不同的语音、语调、语速，不断对接收到的热门词汇文本信息进行语音训练，并保存训练结果；
本发明实施例中提出的语音控制电子节目装置中的各个模块都可以通过处理器来实现，当然也可通过具体的逻辑电路实现；其中所述处理器可以是移动终端或服务器上的处理器，在实际应用中，处理器可以为中央处理器(CPU)、微处理器(MPU)、数字信号处理器(DSP)或现场可编程门阵列(FPGA)等。
本发明实施例中，如果以软件功能模块的形式实现上述语音控制电子节目的方法，并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算 机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本发明各个实施例所述方法的全部或部分。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read Only Memory，ROM)、磁碟或者光盘等各种可以存储程序代码的介质。这样，本发明实施例不限制于任何特定的硬件和软件结合。
相应地，本发明实施例还提供一种计算机存储介质，该计算机存储介质中存储有计算机程序，该计算机程序用于执行本发明实施例的上述语音控制电子节目的方法。
以上所述仅为本发明的较佳实施例而已，并非用于限定本发明的保护范围。

Claims (13)

  1. 一种语音控制电子节目的方法，所述方法包括：
    接收用户输入的语音信息，将所述语音信息转换为文本信息；
    对所述文本信息进行分析，将所述文本信息转换为可识别的控制命令；
    根据所述控制命令查询电子节目指南EPG映射表，确定所述控制命令对应的节目频道信息；
    根据所述节目频道信息搜索对应的电视节目资源，根据搜索结果控制被控电器进行节目播放。
  2. 根据权利要求1所述方法，其中，所述方法还包括：将搜索到的电视节目资源信息在自身显示屏进行显示，并进行语音播报；
    所述节目资源信息包括但不限于：节目播出时间、播出台、关键人物信息、节目图片信息。
  3. 根据权利要求1所述方法，其中，所述对文本信息进行分析包括：根据所述文本信息在存储器内进行检索，根据用户的使用频率、和/或精准匹配符合度确定所述文本信息对应的控制命令；所述控制命令中包括用户输入的语音信息所对应的关键词信息。
  4. 根据权利要求1所述方法，其中，所述方法还包括：对网络中的热门词汇进行语音训练。
  5. 根据权利要求1所述方法，其中，所述方法还包括：更新并存储所述EPG节目映射表。
  6. 根据权利要求1所述方法，其中，所述根据搜索结果控制被控电器进行节目播放包括：根据搜索结果发送物理控制信号，控制被控制电器进行节目播放；
    其中，所述物理控制信号包括但不限于红外信号、wifi、蓝牙信号。
  7. 一种语音控制电子节目的装置，所述装置包括：外部通讯模块、语音识别模块、语义分析模块、EPG资源模块、物理信号发送模块，其中，
    所述外部通讯模块，配置为接收用户输入的语音信息，并将所述语音信息发送到语音识别模块；
    所述语音识别模块，配置为将所述语音信息转换为文本信息，并将所述文本信息发送到语义分析模块；
    所述语义分析模块，配置为对所述文本信息进行分析，将所述文本信息转换为可识别的控制命令；根据所述控制命令查询EPG映射表，确定所述控制命令对应的节目频道信息；将所述节目频道信息发送到EPG资源模块；
    所述EPG资源模块，配置为根据所述节目频道信息搜索对应的电视节目资源，并将搜索到的电视节目资源发送到物理信号发送模块和显示和播报模块；
    所述物理信号发送模块，配置为根据搜索结果控制被控电器进行播放。
  8. 根据权利要求7所述装置，其中，所述装置还包括显示和播报模块，配置为：通过外部通信模块将搜索到的电视节目资源信息在自身显示屏进行显示，并进行语音播报；
    所述节目资源信息包括但不限于：节目播出时间、播出台、关键人物信息、节目图片信息。
  9. 根据权利要求7所述装置，其中，所述语义分析模块，配置为根据所述文本信息在存储器内进行检索，根据用户的使用频率、和/或精准匹配符合度确定所述文本信息对应的控制命令；所述控制命令中包括用户输入的语音信息所对应的关键词信息。
  10. 根据权利要求7所述装置，其中，所述语音识别模块，还配置为对网络中的热门词汇进行语音训练。
  11. 根据权利要求7所述装置，其中，所述语义分析模块，还配置为更新并存储所述EPG节目映射表。
  12. 根据权利要求7所述装置，其中，所述物理信号发送模块，配置为根据搜索结果发送物理控制信号，控制被控制电器进行节目播放；
    其中，所述物理控制信号包括但不限于红外信号、wifi、蓝牙信号。
  13. 一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，该计算机可执行指令用于执行权利要求1至6任一项所述的语音控制电子节目的方法。
PCT/CN2016/074384 2015-04-20 2016-02-23 一种语音控制电子节目的方法、装置及存储介质 WO2016169329A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510188770.8A CN106162319A (zh) 2015-04-20 2015-04-20 一种语音控制电子节目的方法及装置
CN201510188770.8 2015-04-20

Publications (1)

Publication Number Publication Date
WO2016169329A1 true WO2016169329A1 (zh) 2016-10-27

Family

ID=57142875

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/074384 WO2016169329A1 (zh) 2015-04-20 2016-02-23 一种语音控制电子节目的方法、装置及存储介质

Country Status (2)

Country Link
CN (1) CN106162319A (zh)
WO (1) WO2016169329A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108337060A (zh) * 2018-03-23 2018-07-27 北京智网时代科技有限公司 一种基于智能拨台的新型收音机
CN108572949A (zh) * 2018-04-18 2018-09-25 链家网（北京）科技有限公司 一种房屋信息搜索处理方法及装置
CN113409780A (zh) * 2021-06-09 2021-09-17 中电科思仪科技股份有限公司 一种应用于测量仪器的语音控制系统及方法

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102594022B1 (ko) * 2016-11-24 2023-10-26 삼성전자주식회사 전자 장치 및 그의 채널맵 업데이트 방법
CN106653026A (zh) * 2017-01-13 2017-05-10 深圳前海勇艺达机器人有限公司 基于语音控制的智能机器人家庭影院系统及其控制方法
CN106847282A (zh) * 2017-02-27 2017-06-13 上海海洋大学 语音控制取货柜及取货柜语音控制取货方法
CN106960668A (zh) * 2017-03-31 2017-07-18 百度在线网络技术（北京）有限公司 电视直播节目的语音搜索方法及装置
WO2018227403A1 (zh) * 2017-06-14 2018-12-20 深圳市智晟达科技有限公司 一种数字电视节目搜索系统
CN107369450B (zh) * 2017-08-07 2021-03-12 苏州市广播电视总台 收录方法和收录装置
CN107277590A (zh) * 2017-08-19 2017-10-20 合肥智贤智能化科技有限公司 一种电视节目声控搜索系统
CN109922376A (zh) * 2019-03-07 2019-06-21 深圳创维－Rgb电子有限公司 一种模式设置方法、装置、电子设备及存储介质
CN111147905A (zh) * 2019-12-31 2020-05-12 深圳Tcl数字技术有限公司 媒体资源查找方法、电视机、存储介质及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101465994A (zh) * 2008-11-14 2009-06-24 深圳创维数字技术股份有限公司 机顶盒及在机顶盒中实现语音搜索的方法
US20090271817A1 (en) * 2008-04-23 2009-10-29 At&T Intellectual Property, Lp Systems and Methods for Searching Based on Information in Commercials
CN102075797A (zh) * 2010-12-29 2011-05-25 深圳市同洲电子股份有限公司 一种语音浏览频道或节目的方法及数字电视接收终端
US20130145400A1 (en) * 2011-12-02 2013-06-06 At&T Intellectual Property I, L.P. Systems and Methods to Facilitate a Voice Search of Available Media Content
CN103369398A (zh) * 2013-07-01 2013-10-23 安徽广电信息网络股份有限公司 一种基于电视epg信息的语音搜索方法和系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102543082B (zh) * 2012-01-19 2014-01-15 北京赛德斯汽车信息技术有限公司 使用自然语言的车载信息服务系统语音操作方法及系统
CN103400576B (zh) * 2013-07-18 2015-11-25 百度在线网络技术（北京）有限公司 基于用户行为日志的语音模型更新方法及装置
CN103634640A (zh) * 2013-11-29 2014-03-12 乐视致新电子科技（天津）有限公司 移动终端设备控制智能电视端语音输入的方法及系统
CN103700370B (zh) * 2013-12-04 2016-08-17 北京中科模识科技有限公司 一种广播电视语音识别系统方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090271817A1 (en) * 2008-04-23 2009-10-29 At&T Intellectual Property, Lp Systems and Methods for Searching Based on Information in Commercials
CN101465994A (zh) * 2008-11-14 2009-06-24 深圳创维数字技术股份有限公司 机顶盒及在机顶盒中实现语音搜索的方法
CN102075797A (zh) * 2010-12-29 2011-05-25 深圳市同洲电子股份有限公司 一种语音浏览频道或节目的方法及数字电视接收终端
US20130145400A1 (en) * 2011-12-02 2013-06-06 At&T Intellectual Property I, L.P. Systems and Methods to Facilitate a Voice Search of Available Media Content
CN103369398A (zh) * 2013-07-01 2013-10-23 安徽广电信息网络股份有限公司 一种基于电视epg信息的语音搜索方法和系统

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108337060A (zh) * 2018-03-23 2018-07-27 北京智网时代科技有限公司 一种基于智能拨台的新型收音机
CN108337060B (zh) * 2018-03-23 2023-11-28 北京智网时代科技有限公司 一种基于智能拨台的新型收音机
CN108572949A (zh) * 2018-04-18 2018-09-25 链家网（北京）科技有限公司 一种房屋信息搜索处理方法及装置
CN113409780A (zh) * 2021-06-09 2021-09-17 中电科思仪科技股份有限公司 一种应用于测量仪器的语音控制系统及方法

Also Published As

Publication number Publication date
CN106162319A (zh) 2016-11-23

Similar Documents

Publication Publication Date Title
WO2016169329A1 (zh) 一种语音控制电子节目的方法、装置及存储介质
US20190333515A1 (en) Display apparatus, method for controlling the display apparatus, server and method for controlling the server
US9520133B2 (en) Display apparatus and method for controlling the display apparatus
US20140006022A1 (en) Display apparatus, method for controlling display apparatus, and interactive system
KR102030114B1 (ko) 서버 및 그의 제어 방법
US20140195230A1 (en) Display apparatus and method for controlling the same
EP2752846A1 (en) Dialogue-type interface apparatus and method for controlling the same
KR101914708B1 (ko) 서버 및 서버의 제어 방법
JP2014132465A (ja) ディスプレイ装置及びその制御方法
WO2020135161A1 (zh) 视频播放跳转方法、系统及计算机可读存储介质
CN111741369A (zh) 一种基于语音识别的智能电视机顶盒
CN104717536A (zh) 一种语音控制的方法和系统
KR20190140890A (ko) 디스플레이 장치 및 디스플레이 장치의 제어 방법
KR102182689B1 (ko) 서버 및 그의 제어 방법
KR102118195B1 (ko) 서버 및 그의 제어 방법
KR102265406B1 (ko) 서버 및 그의 제어 방법
KR102667446B1 (ko) 서버 및 그의 제어 방법
WO2023216414A1 (zh) 语音交互系统及语音交互方法
KR20170038772A (ko) 디스플레이 장치 및 그의 제어 방법

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: 16782477

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16782477

Country of ref document: EP

Kind code of ref document: A1