CN105512182B - Sound control method and smart television - Google Patents
Sound control method and smart television Download PDFInfo
- Publication number
- CN105512182B CN105512182B CN201510829731.1A CN201510829731A CN105512182B CN 105512182 B CN105512182 B CN 105512182B CN 201510829731 A CN201510829731 A CN 201510829731A CN 105512182 B CN105512182 B CN 105512182B
- Authority
- CN
- China
- Prior art keywords
- semantic
- information
- smart television
- character
- text
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- H04N21/47—End-user applications
- H04N21/485—End-user interface for client configuration
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- User Interface Of Digital Computer (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a kind of semantic control methods, the sound control method includes: that smart television receives the text information that voice-input device is sent, text information is that voice-input device carries out what speech recognition obtained to the voice signal that user inputs, and smart television will carry out semantic analysis to text information according to the standard code table of comparisons of pre-set language, the voice messaging of text information is obtained, and smart television is controlled according to the semantic information.The invention also discloses a kind of smart televisions, can effectively identify the semanteme of the voice signal of user's input, realize the understanding to the natural semanteme of voice signal, increase recognition accuracy, make it possible to preferably interact with user, improve user experience.
Description
Technical field
The present invention relates to intelligent television field more particularly to a kind of sound control methods and smart television.
Background technique
With the development of science and technology, television set is also towards intelligentized trend development.Smart television remove with traditional video,
Outside the functions such as game, also there is network function, can be realized the cross-platform search between TV, network and program.Smart television
Becoming the third message reference terminal after computer, mobile phone, user can access oneself needs by smart television
Information.
Currently, smart television has voice control function, and it is specific: phonetic feature library has been stored in advance in smart television,
After receiving the voice signal of input, the phonetic feature of the voice signal is extracted, and in the pre-set phonetic feature
The phonetic feature is matched in library, and corresponding operational order is generated according to the matching result of phonetic feature, to realize voice control.
However, can only be matched according to pre-set phonetic feature library, Wu Fazhen in above-mentioned speech control process
Just accomplish the content for the voice for understanding that user inputs, and be also easy to matching error occur, the problem of can not accurately identifying, reduces use
Family experience.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of sound control method and smart televisions, it is intended to solve in the prior art
Smart television is only carried out control bring by way of speech recognition and easily identifies mistake, and can not be accomplished semantic using nature
Understand the problem of voice content causes poor user experience.
To achieve the above object, a kind of sound control method provided by the invention, comprising:
Smart television receives the text information that voice-input device is sent, and the text information is the voice-input device
What speech recognition obtained is carried out to the voice signal of user's input；
The smart television carries out the text information according to the standard code table of comparisons of pre-set language semantic
Analysis, obtains the semantic information of the text information；
The smart television controls the smart television according to institute's semantic information.
Preferably, the smart television carries out the text information according to the pre-set standard code table of comparisons semantic
Analysis, comprising:
According to the character code size of each of text information text character and the word of pre-set language
It accords with size area and determines language belonging to each described text character；
It is determined according to the pre-set standard code table of comparisons of language belonging to each described text character described each
The semanteme of a text character.
Preferably, the smart television controls the smart television according to institute's semantic information, comprising:
Whether include institute's semantic information in the semantic database that judgement has currently saved；
When in the semantic database including institute's semantic information, obtained and the semanteme from the semantic database
The corresponding operation data of information controls the smart television according to the operation data, wraps in the semantic database
Containing the corresponding relationship between semantic information and operation data.
Preferably, the method also includes:
When not including institute's semantic information in the semantic database, institute's semantic information is segmented according to semanteme
Processing, obtains the word for including in institute's semantic information；
By the word for including in the institute's semantic information successively class entry pair different from pre-set media data
The word in set of words answered is matched, and determines the class entry of each of institute's semantic information word match, and
The number of matched class entry；
The number of matched class entry is met into the word of pre-set value conditions as keyword；
Based on web crawlers mechanism, the key is obtained according to the class entry of the keyword and the Keywords matching
Word corresponding network linking address under the class entry, the network linking address are the keyword in the classification item
Now number of clicks meets the address of pre-set number of clicks；
By the keyword under the class entry the corresponding picture of corresponding network linking address and/or text importing
On the display interface of the smart television.
Preferably, the method also includes:
Using the network linking address as the operation data of institute's semantic information, and by institute's semantic information and the net
The corresponding relationship of network chained address is stored in the semantic database；
When the non-clearance time of the semantic database reaches pre-set duration, according to pre-set Prune Policies
Clear up the semantic database.
In order to solve the above technical problem, the present invention provides a kind of smart televisions, comprising:
Receiving module, for receiving the text information of voice-input device transmission, the text information is that the voice is defeated
Enter equipment and what speech recognition obtained is carried out to the voice signal that user inputs；
Analysis module carries out the text information for the standard code table of comparisons according to pre-set language semantic
Analysis, obtains the semantic information of the text information；
Control module, for being controlled according to institute's semantic information the smart television.
Preferably, the analysis module includes:
First determining module, for according to the character code size of each of text information text character and pre-
The character boundary region for the language being first arranged determines language belonging to each described text character；
Semantic module, for according to the pre-set standard code pair of language belonging to each described text character
The semanteme of each text character is determined according to table.
Preferably, the control module includes:
Judgment module, for whether judging in the current semantic database saved comprising institute's semantic information；
First processing module is used for when in the semantic database including institute's semantic information, from the semantic data
Operation data corresponding with institute's semantic information is obtained in library, and the smart television is controlled according to the operation data,
Include the corresponding relationship between semantic information and operation data in the semantic database.
Preferably, the control module further include:
Word segmentation module, for when not including institute's semantic information in the semantic database, institute's semantic information to be pressed
Word segmentation processing is carried out according to semanteme, obtains the word for including in institute's semantic information；
Matching module, the word for that will include in institute's semantic information are successively different from pre-set media data
The corresponding set of words of class entry in word matched, determine each of institute's semantic information word match
The number of class entry and matched class entry；
Keyword determining module, for the number of matched class entry to be met to the word of pre-set value conditions
As keyword；
Address acquisition module, for being based on web crawlers mechanism, according to the keyword and point of the Keywords matching
Class entry obtains keyword corresponding network linking address under the class entry, and the network linking address is described
Number of clicks of the keyword under the class entry meets the address of pre-set number of clicks；
Display module, for by the keyword under the class entry the corresponding picture of corresponding network linking address
And/or text importing is on the display interface of the smart television.
Preferably, the smart television further include:
Preserving module, for using the network linking address as the operation data of institute's semantic information, and by institute's predicate
The corresponding relationship of adopted information and the network linking address is stored in the semantic database；
Cleaning modul, for when the non-clearance time of the semantic database reaches pre-set duration, according to preparatory
The Prune Policies of setting clear up the semantic database.
In sound control method provided by the invention, text information of the smart television in the voice signal for obtaining user's input
Later, semantic analysis is carried out to text information according to the standard code table of comparisons of pre-set language, to obtain text envelope
The semantic information of breath, and smart television is controlled according to the semantic information, it is carried out by the text information to voice signal
Semantic analysis makes it possible to effectively identify the semanteme of the voice signal of user's input, realizes to the natural semanteme of voice signal
Understand, increase recognition accuracy, make it possible to preferably interact with user, improves user experience.
Detailed description of the invention
Fig. 1 is the flow diagram of sound control method in first embodiment of the invention；
Fig. 2 carries out semantic analysis to text information according to the pre-set standard code table of comparisons for smart television in Fig. 1
The step of refinement flow diagram；
Fig. 3 is the flow diagram of the sound control method of second embodiment of the invention；
Fig. 4 is the functional block diagram of the smart television of third embodiment of the invention；
Fig. 5 is the refinement the functional block diagram of the analysis module 402 of smart television in 3rd embodiment in Fig. 4；
Fig. 6 is the functional block diagram of the smart television of fourth embodiment of the invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
In sound control method provided by the invention, text information of the smart television in the voice signal for obtaining user's input
Later, semantic analysis is carried out to text information according to the standard code table of comparisons of pre-set language, to obtain text envelope
The semantic information of breath, and smart television is controlled according to the semantic information, voice is believed so that smart television can be realized
Number natural semanteme understanding, increase recognition accuracy, make it possible to preferably interact with user, improve user experience.
Voice control in the embodiment of the present invention is explained below in technical solution in embodiment in order to better understand the present invention
System processed, the speech control system include voice-input device and smart television.
In embodiments of the present invention, voice-input device includes voice input function and speech identifying function, wherein voice
Input function can realize that voice-input device can utilize Mike's elegance by the microphone being arranged on voice-input device
Collect the voice of user, and generates voice signal.
Wherein, the speech identifying function of voice-input device can be real by the speech recognition module in voice-input device
Existing, microphone is after generating voice signal, and by the transmitting voice signal to speech recognition module, speech recognition module is to the language
Sound signal is identified, the text information of the voice signal is obtained.
Wherein, voice-input device can be remote controler or other mobile terminal, which can be with
It is the intelligent terminals such as smart phone, tablet computer, palm PC.
Wherein, the method for the voice signal of above-mentioned speech recognition module identification user input, which may is that, believes the voice
Number carry out pcm encoder obtain pcm stream, by obtained pcm stream and the pre-set pcm stream of voice-input device, text
Corresponding relationship between character and the character code of text character is compared, and determines the corresponding text word of each pcm stream
The character code of symbol and text character includes in voice signal in text information to obtain the text information of voice signal
The character code of text character and text character.Such as: if the voice of user's input is " Liu Dehua news ", voice signal
Pcm stream are as follows: 0x0100 (Liu), 0x0200 (moral), 0x0300 (China), 0x0400 (new), 0x0500 (news) are code in bracket
Flow corresponding text character.
In embodiments of the present invention, smart television is to be equipped with operating system, can freely install and uninstall software program,
Terminal with functions such as video, amusement, game, and can be by wired or wirelessly realize network function.
Wherein, voice-input device and smart television all have wireless communication module, voice-input device and smart television
Link is carried out wireless communication by respective wireless communication module, to establish the nothing between smart television and voice-input device
Line voice channel.Wherein, wireless communication module can be WIFI module, bluetooth module or unlimited USB module etc., herein not
It limits.
Referring to Fig. 1, for sound control method in first embodiment of the invention, this method comprises:
Step 101, smart television receive the text information that voice-input device is sent, and text information is voice-input device
What speech recognition obtained is carried out to the voice signal of user's input；
In embodiments of the present invention, voice-input device is inputted in typing user voice signal and to the voice signal into
After row speech recognition obtains the text information of the voice signal, the text information of the voice signal is sent to smart television,
Wherein, smart television and voice-input device can carry out the text information of voice signal by above-mentioned wireless speech channel
Transmission.
Wherein, smart television will receive the text information of the voice signal, include in voice signal in text information
The character code of text character and text character.
Step 102, smart television carry out text information according to the standard code table of comparisons of pre-set language semantic
Analysis, obtains the semantic information of text information；
In embodiments of the present invention, smart television is after receiving the text information of voice signal, will be according to setting in advance
The standard code table of comparisons for the language set carries out semantic analysis to text information, obtains the semantic information of text information.
It should be noted that the standard code table of comparisons of a variety of different language, example can be preset in smart television
Such as, Unicode (Unicode) code table of comparisons can be preset for Chinese, Unite States Standard letter can be preset for English
Cease interchange code (ASCII, American Standard Code for Information Interchange) code table of comparisons.
Wherein, Unicode is a kind of character code used on computers, it sets for each character in every kind of language
Unified and unique binary coding is determined, and the standard code table of comparisons used preferably for Chinese can specifically make
With the variable length character that UTF-8 (8-bit Unicode Transformation Format), UTF-8 are for Unicode
Coding, is one of implementation of Unicode.
Wherein, ASCII is a set of computer code's system based on the Latin alphabet, is mainly used for showing current english and other
Western-European languages.
Step 103, smart television control smart television according to semantic information.
In embodiments of the present invention, smart television, can be according to the semantic information to intelligence after parsing obtains semantic information
Energy TV is controlled.
In sound control method provided by the invention, text information of the smart television in the voice signal for obtaining user's input
Later, semantic analysis is carried out to text information according to the standard code table of comparisons of pre-set language, to obtain text envelope
The semantic information of breath, and smart television is controlled according to the semantic information, make it possible to effectively identify the language of user's input
The semanteme of sound signal realizes the understanding to the natural semanteme of voice signal, increases recognition accuracy, makes it possible to more preferable with user
Ground is interacted, and user experience is improved.
Referring to Fig. 2, being step 102 smart television in first embodiment of the invention according to pre-set standard code
The table of comparisons year text information carry out semantic analysis refinement step flow chart, comprising:
Step 201, the character code size according to each of text information text character and pre-set language
Character boundary region determine language belonging to each text character；
Step 202, determined according to the pre-set standard code table of comparisons of language belonging to each text character it is each
The semanteme of a text character.
In embodiments of the present invention, smart television can be according to the character code of each of text information text character
The character boundary region of size and pre-set language determines language belonging to each text character, and can also be according to each
The pre-set standard code table of comparisons of language belonging to a text character determines the semanteme of each text character.
It should be noted that for the standard code table of comparisons of each language, the magnitude range of character is different
, and be subregional.
Semantic analysis process in embodiment in order to better understand the present invention.It below will be pre-set with smart television
Language is Chinese and is introduced for English.
For determining each according to the character code size of each of text information text character in step 201
Language belonging to text character, is specifically as follows: smart television successively judges the character code of the text character in text information
Whether it is greater than 255, when the character code of some text character is greater than 255, determines that text character belongs to Chinese character, when
When the character code of some text character is less than 255, determine that text character belongs to English character.Because Unicode is encoded
The size that the character boundary of Chinese character is all larger than the English character in 255, ASCII in rule is respectively less than 255, wherein English character
Including English word, letter and Arabic numerals.
For determining each according to the standard code table of comparisons of language belonging to each text character in step 202
The semanteme of text character, is specifically as follows: smart television successively traverses the text character in text information, when the text traversed
When character is Chinese character, Chinese difference is carried out to text character using the pre-set Unicode coding table of comparisons and is screened
Fuzzy matching calculates, and determines the semanteme of text character, when the text character traversed belongs to English character, using setting in advance
The ASCII coding table of comparisons set carries out English difference screening fuzzy matching to text character and calculates, and determines text character
Meaning.By above-mentioned traversal and matched process, the semantic information of text information can determine.
Wherein, Chinese difference is carried out to character using the pre-set Unicode coding table of comparisons and screens fuzzy matching meter
It calculates, determines the semanteme of the character, specifically may is that when text character to be matched is Chinese, the character code of text character
For Unicode variable length character encode, successively calculate the text character to be matched variable length character coding in advance
Difference between the variable length character coding of all Chinese characters in the Unicode coding table of comparisons of setting, it is pre- when determining
The variable length character coding and the text word to be matched for the n-th Chinese character in the Unicode coding table of comparisons being first arranged
Difference between the variable length character coding of symbol is 0, it is determined that the text character to be matched is the n-th Chinese character,
Using the semanteme of the n-th Chinese character as the semanteme of the text character to be matched.And stop to the text character to be matched
Chinese difference screening fuzzy matching calculates.Such as: it, will if the variable length character of text character to be matched is encoded to 0x5218
Variable character coding of the variable length character coding successively with the Chinese character in the Unicode coding table of comparisons subtracts each other, when true
When the difference for determining the variable length character coding 0x5218 of 0x5218 and the 100th Chinese character is 0, determine in the 100th
Chinese character corresponding semantic (semanteme are as follows: Liu) is the semanteme of the text character to be matched.
Wherein, English difference is carried out to the character using the pre-set ASCII coding table of comparisons and screens fuzzy matching meter
It calculates, determines the meaning of the character, be specifically as follows: if text character to be matched is English character, the text character to be matched
Character code be ASCII character, successively calculate the text character to be matched ASCII character and pre-set ASCII coding pair
According to the difference between the ASCII character of all English characters in table, when determining the in the pre-set ASCII coding table of comparisons
Difference between the ASCII character of M English character and the ASCII of the character to be matched is 0, it is determined that the character to be matched is
The n-th Chinese character, using the semanteme of the n-th Chinese character as the semanteme of the text character to be matched.And stop to this
The English difference screening fuzzy matching of text character to be matched calculates.Such as: if the ASCII character of text character to be matched is 49,
Then the ASCII character of the ASCII character 49 successively with the English character in ASCII character is subtracted each other, when determining ASCII character 49 and the 50th
When 49 difference of ASCII character of English character is 0, the corresponding semantic (semanteme are as follows: 1) being should of the 50th English character is determined
The semanteme of text character to be matched.
It should be noted that being first to determine belonging to each text character in text information in embodiments of the present invention
Language, the identification process of descriptive semantics information for fuzzy matching calculating is then successively carried out to each text character again,
In practical applications, the text character in text information can also be directly traversed, first judges the character of the text character traversed
Whether coding is greater than 255, and carries out fuzzy matching calculating according to judging result, to determine the semantic information of text information.
It should be noted that if being with the pre-set language of smart television for Chinese and English in embodiments of the present invention
What text was described, in practical applications, if the language that the voice signal of voice-input device input uses is not smart television
The text information of voice signal after speech recognition can be first converted into according to intelligent electricity by currently used language, smart television
The text information that can be identified depending on pre-set language.Such as: if user is to carry out voice input, language using Monaco's language
Sound input equipment after carrying out speech recognition, the text information of the Monaco's language recognized can be converted to Chinese and/or
English text information.
It is to be understood that can be set in advance due in the smart television that different environment and different countries use
Set the standard code table of comparisons of multilingual, then after user can determine the language that smart television uses by selection, intelligence electricity
Depending on that can execute above-mentioned steps 201 and step 202 with the standard code table of comparisons for the language that it is used, rather than pre-set language
The standard code table of comparisons of speech.
In embodiments of the present invention, it is compareed by presetting the standard code that different language uses in smart television
Table enables smart television to determine based on the standard code table of comparisons of different language each in the text information of voice signal
The semanteme of a text character is efficiently accomplished to semantic identification.And the accuracy rate of semantics recognition is high, can give the better body of user
It tests.
Referring to Fig. 3, for the sound control method in second embodiment of the invention, comprising:
Step 301, smart television receive the text information that voice-input device is sent, and text information is voice-input device
What speech recognition obtained is carried out to the voice signal of user's input；
In embodiments of the present invention, content described in step 301 is retouched with the step 101 in first embodiment shown in Fig. 1
The content stated is similar, is not repeated herein.
Step 302, smart television carry out text information according to the standard code table of comparisons of pre-set language semantic
Analysis, to obtain the semantic information of text information；
In embodiments of the present invention, step 102 describes in first embodiment shown in the content and Fig. 1 that step 302 describes
Content is similar, and the refinement process of step 101 shown in Fig. 2 is also the refinement process of the step 302 in the present invention, is not done herein
It repeats.
Whether comprising semantic information in the semantic database that step 303, judgement have currently saved；When being wrapped in semantic database
When containing semantic information, executes step 304, when not including semantic information in semantic information library, thens follow the steps 305；
In embodiments of the present invention, smart television, will after the semantic information for obtaining text information by semantic analysis
Whether judge in the semantic database saved comprising the semantic information.
It should be noted that containing the corresponding relationship between semantic information and operation data, example in the semantic database
Such as: if semantic information is to tune up volume, tuning up the corresponding operation data of volume with this and then make a living into volume and tune up instruction.If language
Message breath is Zhou Jielun film, then and the corresponding operation data of the Zhou Jielun film be will lattice chain corresponding with Zhou Jielun film
The picture and/or word-information display for being grounded location are on the display interface of smart television.Therefore, different in semantic database
The corresponding operation data of semantic information is also different.
Step 304 obtains operation data corresponding with semantic information from semantic database, according to operation data to intelligence
TV is controlled, and the corresponding relationship between semantic information and operation data is included in semantic database；
In embodiments of the present invention, when in semantic database including semantic information, smart television will be from the semantic data
Operation data corresponding with the semantic information is obtained in library, and smart television is controlled according to the operation data, such as: if
Semantic information is to reduce volume, then operation data corresponding with the reduction volume, which then makes a living into volume, reduces instruction, smart television
The volume that instruction reduction presets size will be reduced according to the volume.If voice messaging is Liu Dehua film, with the Liu De
The corresponding operation data of magnificent film is by the picture and/or word-information display of network linking address corresponding with Liu Dehua film
On the display interface of smart television, smart television will read the corresponding network linking of Liu Dehua film from speech database
Address, and by the picture of the network linking address and/or word-information display on the display interface of smart television, so that user
It can choose specific film to be watched.
Semantic information is carried out word segmentation processing according to semanteme by step 305, obtains the word for including in semantic information；
Step 306, by the word for including in the semantic information successively classification item different from pre-set media data
Word in the corresponding set of words of mesh is matched, and determines the class entry of each of semantic information word match, and
The number of matched class entry；
The number of matched class entry is met the word of pre-set value conditions as keyword by step 307；
Step 308 is based on web crawlers mechanism, obtains keyword according to the class entry of keyword and Keywords matching and exists
Corresponding network linking address under class entry, network linking address are that number of clicks of the keyword under class entry meets in advance
The address for the number of clicks being first arranged；
In embodiments of the present invention, when not including the semantic information in semantic database, smart television is by semantic information
Word segmentation processing is carried out according to semanteme, obtains the word for including in semantic information, such as: for semantic information " Liu Dehua news ",
Smart television divides available word " Liu Dehua " and " news " according to semanteme.
And after obtaining the word that semantic information includes, smart television is by the word for including in the semantic information and in advance
The media data of setting is matched, wherein the media data includes different class entry, and each class entry is right
A set of words is answered, such as: the class entry that media data includes are as follows: news, film, TV play, variety, music etc.
Class entry includes words such as " Liu Dehua, Zhou Jielun, father where go ... " under variety class entry in set of words
Language.
It should be noted that a word only occurs once under a class entry.
For each of semantic information word, smart television classifies each of the word and media data item
Word in the corresponding set of words of mesh is matched, to determine the class entry and matched class entry of the word match
Number.For example, for word " Liu Dehua ", matched class entry includes: film, star, variety, music, matched point
The number of class entry is 4.
In embodiments of the present invention, smart television is obtaining the word in semantic information in the different classifications item of media data
In mesh after the number of matched class entry, the number of matched class entry is met to the word of pre-set value conditions
Language is as keyword, wherein the word that the number of matched class entry meets pre-set value conditions refers to that matching is non-
The word of N before the number of the maximum word of the number of class entry or matched class entry comes, wherein N is positive whole
Number.For example, the number of the matching class entry for the word " Liu Dehua " for including in set of words is 4, word " news " matching
Class entry number be 1, it is determined that the maximum word of the number of matched class entry " Liu Dehua " be keyword.
In embodiments of the present invention, smart television will be based on web crawlers mechanism, according to key after obtaining keyword
The class entry of word and Keywords matching obtains the keyword corresponding lattice chain under matched different class entries
It is grounded location, which is to meet in advance based on the keyword in the number of clicks of matched different classifications item now
The address for the number of clicks being first arranged.
Wherein, the address for meeting pre-set number of clicks can be the address of N before number of clicks comes, the N
For positive integer.
Wherein, it is right now in matched different classifications item based on web crawlers mechanism to obtain the keyword for smart television
The network linking address answered, is specifically as follows: the class entry of keyword and Keywords matching is supplied to network by smart television
Crawler, web crawlers obtain the keyword by the class entry based on the keyword and the Keywords matching, from cloud server
Network connection address under matched different class entries, and count under above-mentioned different class entry each
The number of clicks of network linking address, and for the number of clicks of the network linking address under each above-mentioned class entry into
Row sequence, using N number of network linking address of the sequence in preceding N under class entry as right under the class entry with the keyword
The network linking address answered.Such as: keyword is " Liu Dehua ", and the class entry with the Keywords matching includes: film, electricity
Depending on, music, variety, web crawlers will utilize the keyword " Liu Dehua " and its class entry, grab the keyword " Liu Dehua "
Network linking address under the class entries such as film, TV, music, variety respectively, and to the network of different class entries
Chained address is counted and is sorted, and determines that before number of clicks comes now in separated film item 44 network linking address are
Keyword " Liu Dehua " in separated film item corresponding network linking address now, and keyword " Liu Dehua " TV, music,
Corresponding network linking address can also determine under the class entries such as variety.
Step 309, by keyword under class entry the corresponding picture of corresponding network linking address and/or text importing
On the display interface of smart television.
In embodiments of the present invention, smart television is obtaining with keyword the corresponding net under matched class entry
After network chained address, by the keyword the matched corresponding picture in the corresponding network chained address of class entry and/
Or text importing allows users to select the content of display on the display program of smart television.
Further, smart television can also carry out step 310, it may be assumed that
Step 310, using network linking address as the operation data of semantic information, and semantic information and lattice chain are grounded
The corresponding relationship of location is stored in semantic database.
In embodiments of the present invention, smart television is getting the corresponding network linking address of the keyword in semantic information
Later, using the network linking address as the operation data of semantic information, and will be between the semantic information and network linking address
Corresponding relationship be stored in semantic database.
It should be noted that smart television can be performed simultaneously step 309 and step 310 after executing step 308,
Or step 309 can be continued to execute, and execute step 310 again after executing step 309 after executing step 308, or
Person can first carry out step 310 and execute step 309 again after executing step 308, i.e. the execution of step 309 and step 310
Sequencing does not limit.
And in order to provide better experience for user, when the non-clearance time of semantic database reaches pre-set
When long, smart television will also be according to pre-set tactful periodic cleaning semantic database, and the period cleared up can set in advance
It sets, such as week cleaning can be set once, a cleaning in month also can be set once, specific cleaning cycle is simultaneously unlimited
It is fixed.
Preferably, in order to preferably manage semantic database, the semantic information in semantic database can also be divided
Class, for example, the semantic information of the volume for smart television, channel, switch etc., and the display for smart television can be divided into
Content semantic information.
Preferably, smart television can clear up semantic database according to pre-set Prune Policies, specifically,
It can be and empty semantic database completely, or certain a kind of semantic information and the corresponding behaviour that can be directed in semantic database
Cleared up as data, for example, can the only semantic information to the content of the display of smart television cleaning.
Preferably, for the ease of the use habit of determining user, smart television, which is resolved to semantic information in each judgement, is
It is no comprising after in semantic database, however, it is determined that the semantic information is included in semantic database, then by the semantic information
Count value adds 1, to determine that user uses the habit and hobby of speech control system.
It, can also be according to the counting of the semantic information in semantic database and when clearing up semantic database
Value is cleared up, such as count value can be cleaned up less than the semantic information of some numerical value and its corresponding operation data.
Preferably, when the count value to semantic information adds 1, it can also record and 1 is added to the count value of the semantic information
Time point, so that can be worked as by the nearest time point distance of the record of semantic information when clearing up semantic database
Duration between the preceding time deletes the semantic information and its corresponding operation if the pre-set duration of the big Mr. Yu of the duration
Data.If the duration is less than or equal to certain pre-set duration, retain the voice messaging and its corresponding operation data.
It in embodiments of the present invention, can be by presetting semantic database, so that obtaining text information in analysis
After semantic information, if the semantic information can be found in semantic database, obtained and the language from the semantic database
The corresponding operation data of adopted information grabs semanteme from network and believes if not including the semantic information in semantic database
The keyword for including in breath corresponding network linking address under matched class entry, to obtain the behaviour of the semantic information
Make data.It is not easy to make mistakes since the analysis resolution of semantic information is high, so that the operation executed to smart television is all that user thinks
The operation wanted can effectively realize that smart television to user's semantic understanding naturally, improves user experience.
Referring to Fig. 4, for the functional block diagram of smart television in third embodiment of the invention, comprising:
Receiving module 401, for receiving the text information of voice-input device transmission, text information is voice input
Equipment carries out what speech recognition obtained to the voice signal that user inputs；
Analysis module 402, for carrying out language to text information according to the standard code table of comparisons of pre-set language
Justice analysis, obtains the semantic information of text information；
Control module 403, for being controlled according to the semantic information the smart television.
It should be noted that the standard code table of comparisons of a variety of different language, example can be preset in smart television
Such as, Unicode (Unicode) code table of comparisons can be preset for Chinese, Unite States Standard letter can be preset for English
Cease interchange code (ASCII, American Standard Code for Information Interchange) code table of comparisons.
Wherein, Unicode is a kind of character code used on computers, it sets for each character in every kind of language
Unified and unique binary coding is determined, and the standard code table of comparisons used preferably for Chinese can specifically make
With the variable length character that UTF-8 (8-bit Unicode Transformation Format), UTF-8 are for Unicode
Coding, is one of implementation of Unicode.
Wherein, ASCII is a set of computer code's system based on the Latin alphabet, is mainly used for showing current english and other
Western-European languages.
In embodiments of the present invention, it is defeated to receive the user that voice-input device is sent for the receiving module 401 in smart television
The text information of the voice signal entered, then by analysis module 402 according to the standard code table of comparisons pair of pre-set language
Text information carries out semantic analysis, to obtain the semantic information of text information, finally, by control module 403 according to the language
Adopted information controls smart television.
In sound control method provided by the invention, text information of the smart television in the voice signal for obtaining user's input
Later, semantic analysis is carried out to text information according to the standard code table of comparisons of pre-set language, to obtain text envelope
The voice messaging of breath, and smart television is controlled according to the semantic information, make it possible to effectively identify the language of user's input
The semanteme of sound signal realizes the understanding to the natural semanteme of voice signal, increases recognition accuracy, makes it possible to more preferable with user
Ground is interacted, and user experience is improved.
Referring to Fig. 5, for the refinement functional module of the analysis module 402 in 3rd embodiment shown in Fig. 4 of the present invention, packet
It includes:
First determining module 501, for the character code size according to each of text information text character
And the character boundary region of pre-set language determines language belonging to each described text character；
Semantic module 502, for according to the pre-set standard code of language belonging to each text character
The table of comparisons determines the semanteme of each text character.
Wherein, the first determining module 501 is specifically used for:
When pre-set language is Chinese and English, successively judge whether the text character in text information is greater than
255；
If text character is greater than 255, it is determined that text character belongs to Chinese character；
If text character is less than 255, it is determined that text character belongs to English character；
Semantic module 502 is specifically used for:
The text character in text information is successively traversed, when text character belongs to Chinese character, using presetting
The Unicode Unicode coding table of comparisons Chinese difference screening fuzzy matching carried out to text character calculate, determine the character
Semanteme；When text character belongs to English character, encoded using pre-set USA standard code for information interchange ASCII
The table of comparisons carries out English difference screening fuzzy matching to text character and calculates, and determines the semanteme of the character.
Wherein, semantic module 502 carries out Chinese to text character using the pre-set Unicode coding table of comparisons
Difference screen fuzzy matching calculate, determine the semanteme of text character, specifically may is that semantic module 502 determine to
The variable length character of Unicode with text character encodes, and successively calculates the variable length word of the text character to be matched
Difference between symbol coding and the variable length character coding of all Chinese characters in the pre-set Unicode coding table of comparisons
Value, when determine the variable length character coding of the n-th Chinese character in the pre-set Unicode coding table of comparisons with should be to
Difference between the variable length character coding of matched text character is 0, it is determined that the character to be matched is n-th Chinese
Character, using the semanteme of the n-th Chinese character as the semanteme of the character to be matched.And stopping is to the Chinese of the character to be matched
Difference is screened fuzzy matching and is calculated.Such as: it, can by this if the variable length character of text character to be matched is encoded to 0x5218
Variable character coding of the variable-length character encoding successively with the Chinese character in the Unicode coding table of comparisons subtracts each other, and works as determination
When the difference of the variable length character coding 0x5218 of 0x5218 and the 100th Chinese character is 0, the 100th Chinese is determined
Character corresponding semantic (semanteme are as follows: Liu) is the semanteme of the text character to be matched.
Wherein, semantic module 502 carries out English to text character using the pre-set ASCII coding table of comparisons
Difference screen fuzzy matching calculate, determine the meaning of text character, be specifically as follows: semantic module 502 determine to
ASCII character with character, and the ASCII character for successively calculating the text character to be matched is compareed with pre-set ASCII coding
Difference between the ASCII character of all English characters in table, when determining the M in the pre-set ASCII coding table of comparisons
Difference between the ASCII character of a English character and the ASCII of the text character to be matched is 0, it is determined that the text to be matched
Character is the n-th Chinese character, using the semanteme of the n-th Chinese character as the semanteme of the text character to be matched.And
Stop calculating the English difference screening fuzzy matching of the text character to be matched.Such as: if character to be matched can ASCII character
Be 49, then subtract each other the ASCII character of the ASCII character 49 successively with the English character in ASCII character, when determine ASCII character 49 with
When 49 difference of ASCII character of 50th English character is 0, the corresponding semantic (semanteme are as follows: 1) of the 50th English character is determined
The as semanteme of the text character to be matched.
It should be noted that being first to determine language belonging to each character in text information in embodiments of the present invention
Then speech is actually being answered successively to the identification process of descriptive semantics information for the progress fuzzy matching calculating of each character again
In, the character in text information can also be directly traversed, first judges whether the character traversed is greater than 255, and according to judgement
As a result fuzzy matching calculating is carried out, to determine the semantic information of text information.
In embodiments of the present invention, it is compareed by presetting the standard code that different language uses in smart television
Table enables smart television to determine based on the standard code table of comparisons of the different language every in the text information of voice signal
The semanteme of one text character is efficiently accomplished to semantic identification.And the accuracy rate of semantics recognition is high, it can be better to user
Experience.
Referring to Fig. 6, the schematic diagram of the functional module for the smart television of fourth embodiment of the invention, comprising: such as Fig. 4 institute
Show receiving module 401, analysis module 402 and the control module 403 in 3rd embodiment, and with described in embodiment illustrated in fig. 4
Content it is similar, be not repeated herein.
Wherein, control module 403 includes:
Judgment module 601, for whether judging in the current semantic database saved comprising semantic information；
First processing module 602 is used for when in the semantic database including the semantic information, from the semantic database
Operation data corresponding with the semantic information is obtained, the smart television is controlled according to the operation data, the semantic data
Include the corresponding relationship between semantic information and operation data in library.
Wherein, control module 403 further include:
Word segmentation module 603, for when not including semantic information in semantic database, semantic information to be carried out according to semanteme
Word segmentation processing obtains the word for including in semantic information；
Matching module 604, for the word for including in semantic information is successively different from pre-set media data
The corresponding set of words of class entry in word matched, determine the classification of each of semantic information word match
The number of entry and matched class entry；
Keyword determining module 605, for the number of matched class entry to be met pre-set value conditions
Word is as keyword；
Address acquisition module 606, for being based on web crawlers mechanism, according to keyword and the class entry of Keywords matching
Keyword corresponding network linking address under class entry is obtained, network linking address is point of the keyword under class entry
Hit the address that number meets pre-set number of clicks；
Display module 607, for by keyword under class entry the corresponding picture of corresponding network linking address and/or
Text importing is on the display interface of smart television.
In embodiments of the present invention, smart television further include:
Preserving module 608, for using network linking address as the operation data of semantic information, and by the semantic information with
The corresponding relationship of the network linking address is stored in semantic database.
Cleaning modul 609, for when the non-clearance time of the semantic database reaches pre-set duration, according to preparatory
The Prune Policies of setting clear up semantic database.
It should be noted that containing the corresponding relationship between semantic information and operation data, example in the semantic database
Such as: if semantic information is to tune up volume, tuning up the corresponding operation data of volume with this and then make a living into volume and tune up instruction.If language
Message breath is Zhou Jielun film, then and the corresponding operation data of the Zhou Jielun film be will lattice chain corresponding with Zhou Jielun film
The picture and/or word-information display for being grounded location are on the display interface of smart television.Therefore, different in semantic database
The corresponding operation data of semantic information is also different.
In embodiments of the present invention, when not including the semantic information in semantic database, word segmentation module 603 believes semanteme
Breath carries out word segmentation processing according to semanteme, obtains the word for including in semantic information, such as: for semantic information " Liu De Huaxin
Hear ", smart television divides available word " Liu Dehua " and " news " according to semanteme.
And after obtaining the word that semantic information includes, matching module 604 by the word for including in the semantic information with
Pre-set media data is matched, wherein the media data includes different class entries, and each class entry
A set of words is all corresponded to, such as: the class entry that media data includes are as follows: news, film, TV play, variety, music
Etc. class entry, under variety class entry, comprising " Liu Dehua, Zhou Jielun, father where go ... " in set of words
Equal words.
It should be noted that a word only occurs once under a class entry.
For each of semantic information word, matching module 604 divides each of the word and media data
Word in the corresponding set of words of class entry is matched, with the class entry of the determining word match and matched classification
The number of entry.For example, matched class entry includes: film, star, variety, music, matching for word " Liu Dehua "
Class entry number be 4.
In embodiments of the present invention, matching module 604 is obtaining the word in semantic information in the difference point of media data
In class entry after the number of matched class entry, keyword determining module 605 meets the number of matched class entry
The word of pre-set value conditions is as keyword, wherein the number of matched class entry meets pre-set number
Before the word of value condition refers to that the maximum word of number of matching non-categorical entry or the number of matched class entry come
The word of N, wherein N is positive integer.For example, the number of the matching class entry for the word " Liu Dehua " for including in set of words
It is 4, the number of word " news " matched class entry is 1, it is determined that the maximum word of the number of matched class entry
Language " Liu Dehua " is keyword.
In embodiments of the present invention, for keyword determining module 605 after determining keyword, address acquisition module 606 will
Based on web crawlers mechanism, which is obtained in matched difference according to the class entry of keyword and Keywords matching
Class entry under corresponding network linking address, which is based on the keyword in matched difference point
The number of clicks of class item now meets the address of pre-set number of clicks.
Wherein, the address for meeting pre-set number of clicks can be the address of N before number of clicks comes, the N
For positive integer.
Wherein, address acquisition module 606 obtains the keyword in matched different classifications based on web crawlers mechanism
Item corresponding network linking address now, is specifically as follows: address acquisition module 606 is by the classification of keyword and Keywords matching
Entry is supplied to web crawlers, and web crawlers is by the class entry based on the keyword and the Keywords matching, from cloud service
Device obtains network connection address of the keyword under matched different class entries, and counts in above-mentioned different points
The number of clicks of class item each network linking address now, and the lattice chain under each above-mentioned class entry is grounded
The number of clicks of location is ranked up, and sequence under class entry is existed in N number of network linking address of preceding N as with the keyword
Corresponding network linking address under the class entry.Such as: keyword is " Liu Dehua ", the class entry with the Keywords matching
It include: film, TV, music, variety, web crawlers will utilize the keyword " Liu Dehua " and its class entry, and grab the pass
Keyword " Liu Dehua " network linking address under the class entries such as film, TV, music, variety respectively, and to different points
The network linking address of class entry is counted and is sorted, and determines before number of clicks comes now in separated film item 44 nets
Network chained address is keyword " Liu Dehua " in separated film item corresponding network linking address, and keyword " Liu Dehua " now
Corresponding network linking address can also determine under the class entries such as TV, music, variety.
In embodiments of the present invention, it is defeated to receive the user that voice-input device is sent for the receiving module 401 in smart television
The text information of the voice signal entered, then by analysis module 402 according to the standard code table of comparisons pair of pre-set language
Text information carries out semantic analysis, to obtain the semantic information of text information, finally, by control module 403 according to the language
Adopted information controls smart television.
Specifically, whether judgment module 601 judges in the semantic database currently saved comprising semantic information；When the language
When in adopted database including the semantic information, first processing module 602 obtains and the semantic information pair from the semantic database
The operation data answered controls the smart television according to the operation data, when in the semantic database do not include the semanteme
When information, semantic information is carried out word segmentation processing according to semanteme by word segmentation module 603, obtains the word for including in semantic information, and
By the word that includes in 604 semantic information of matching module, successively different from pre-set media data class entries are corresponding
Set of words in word matched, determine the class entry of each of semantic information word match and matched
The number of class entry；And the number of matched class entry is met into pre-set numerical value by keyword determining module 605
The word of condition is based on web crawlers mechanism as keyword, by address acquisition module 606, according to keyword and Keywords matching
Class entry obtain keyword corresponding network linking address under class entry, last display module 607 exists keyword
The corresponding picture of corresponding network linking address and/or text importing are on the display interface of smart television under class entry.
In addition, the keyword of the semantic information and the corresponding relationship of the network linking address are stored in by preserving module 608
In semantic database, and when the non-clearance time of the semantic database reaches pre-set duration, cleaning modul 609 is according to pre-
The Prune Policies cleaning semantic database being first arranged.
In fourth embodiment shown in fig. 6, cleaning modul 609 is connect with preserving module 608, indicates cleaning modul 609
Function can be executed after the function of preserving module 608, it requires, in fact, explanation, the function of cleaning modul 609 is also
Before the functions of other any modules in fourth embodiment that can be shown in Fig. 6 in addition to preserving module 608 executes or
Execute later, i.e., do not limit the connection relationship between cleaning modul 609 and other modules, if semantic database do not clear up when
Between reach pre-set duration, can start cleaning modul 609 according to pre-set Prune Policies clear up semantic database.
It in embodiments of the present invention, can be by presetting semantic database, so that obtaining text information in analysis
After semantic information, if the semantic information can be found in semantic database, obtained and the language from the semantic database
The corresponding operation data of adopted information grabs semanteme from network and believes if not including the semantic information in semantic database
The keyword for including in breath corresponding network linking address under matched class entry, to obtain the behaviour of the semantic information
Make data.It is not easy to make mistakes since the analysis resolution of semantic information is high, so that the operation executed to smart television is all that user thinks
The operation wanted can effectively realize that smart television to user's semantic understanding naturally, improves user experience.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, computer, clothes
Be engaged in device, air conditioner or the network equipment etc.) method that executes each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (8)
1. a kind of sound control method characterized by comprising
Smart television receive voice-input device send text information, the text information be the voice-input device to
The voice signal of family input carries out what speech recognition obtained；
The smart television carries out semantic analysis to the text information according to the standard code table of comparisons of pre-set language,
Obtain the semantic information of the text information；
The smart television controls the smart television according to institute's semantic information, specifically includes:
Whether include institute's semantic information in the semantic database that judgement has currently saved；
When not including institute's semantic information in the semantic database, institute's semantic information is carried out at participle according to semanteme
Reason, obtains the word for including in institute's semantic information；
By the word for including in institute's semantic information, successively different from pre-set media data class entries are corresponding
Word in set of words is matched, and determines the class entry of each of institute's semantic information word match, and matching
Class entry number；
The number of matched class entry is met into the word of pre-set value conditions as keyword；
Based on web crawlers mechanism, the keyword is obtained according to the class entry of the keyword and the Keywords matching and is existed
Corresponding network linking address under the class entry, the network linking address are the keyword under the class entry
Number of clicks meet the address of pre-set number of clicks；
By the keyword under the class entry the corresponding picture of corresponding network linking address and/or text importing in institute
It states on the display interface of smart television.
2. the method according to claim 1, wherein the smart television is according to pre-set standard code pair
Semantic analysis is carried out to the text information according to table, comprising:
Character according to the character code size of each of text information text character and pre-set language is big
Zonule determines language belonging to each described text character；
Each described text is determined according to the pre-set standard code table of comparisons of language belonging to each described text character
The semanteme of this character.
3. method according to claim 1 or 2, which is characterized in that the smart television is according to institute's semantic information to institute
State the step of smart television is controlled further include:
When in the semantic database including institute's semantic information, obtained and institute's semantic information from the semantic database
Corresponding operation data controls the smart television according to the operation data, includes language in the semantic database
Corresponding relationship between adopted information and operation data.
4. according to the method described in claim 3, it is characterized in that, the method also includes:
Using the network linking address as the operation data of institute's semantic information, and by institute's semantic information and the lattice chain
The corresponding relationship of ground connection location is stored in the semantic database；
When the non-clearance time of the semantic database reaches pre-set duration, cleared up according to pre-set Prune Policies
The semantic database.
5. a kind of smart television characterized by comprising
Receiving module, for receiving the text information of voice-input device transmission, the text information is that voice input is set
The standby voice signal to user's input carries out what speech recognition obtained；
Analysis module, for carrying out semantic point to the text information according to the standard code table of comparisons of pre-set language
Analysis, obtains the semantic information of the text information；
Control module is specifically included for being controlled according to institute's semantic information the smart television:
Judgment module, for whether judging in the current semantic database saved comprising institute's semantic information；
Word segmentation module is used for when not including institute's semantic information in the semantic database, by institute's semantic information according to language
Justice carries out word segmentation processing, obtains the word for including in institute's semantic information；
Matching module, word for that will include in institute's semantic information successively point different from pre-set media data
Word in the corresponding set of words of class entry is matched, and determines the classification of each of institute's semantic information word match
The number of entry and matched class entry；
Keyword determining module, for the number of matched class entry is met the words of pre-set value conditions as
Keyword；
Address acquisition module, for being based on web crawlers mechanism, according to the keyword and the classification item of the Keywords matching
Mesh obtains keyword corresponding network linking address under the class entry, and the network linking address is the key
Number of clicks of the word under the class entry meets the address of pre-set number of clicks；
Display module, for by the keyword under the class entry the corresponding picture of corresponding network linking address and/
Or text importing is on the display interface of the smart television.
6. smart television according to claim 5, which is characterized in that the analysis module includes:
First determining module, for setting according to the character code size of each of text information text character and in advance
The character boundary region for the language set determines language belonging to each described text character；
Semantic module, for according to the pre-set standard code table of comparisons of language belonging to each described text character
Determine the semanteme of each text character.
7. smart television according to claim 6, which is characterized in that the control module further include:
First processing module is used for when in the semantic database including institute's semantic information, from the semantic database
Operation data corresponding with institute's semantic information is obtained, the smart television is controlled according to the operation data, it is described
Include the corresponding relationship between semantic information and operation data in semantic database.
8. smart television according to claim 7, which is characterized in that the smart television further include:
Preserving module semantic is believed for using the network linking address as the operation data of institute's semantic information, and by described
Breath and the corresponding relationship of the network linking address are stored in the semantic database；
Cleaning modul, for when the non-clearance time of the semantic database reaches pre-set duration, according to presetting
Prune Policies clear up the semantic database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510829731.1A CN105512182B (en) | 2015-11-25 | 2015-11-25 | Sound control method and smart television |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510829731.1A CN105512182B (en) | 2015-11-25 | 2015-11-25 | Sound control method and smart television |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105512182A CN105512182A (en) | 2016-04-20 |
| CN105512182B true CN105512182B (en) | 2019-03-12 |
Family
ID=55720164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510829731.1A Active CN105512182B (en) | 2015-11-25 | 2015-11-25 | Sound control method and smart television |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105512182B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105764185B (en) * | 2016-03-18 | 2017-12-12 | 深圳Tcl数字技术有限公司 | Exchange driving mixing light adjusting circuit and television set |
| CN105825851B (en) * | 2016-05-17 | 2020-07-21 | Tcl科技集团股份有限公司 | Voice control method and system based on Android system |
| CN106101789B (en) * | 2016-07-06 | 2020-04-24 | 深圳Tcl数字技术有限公司 | Voice interaction method and device for terminal |
| CN106023993A (en) * | 2016-07-29 | 2016-10-12 | 西安旭天电子科技有限公司 | Robot control system based on natural language and control method thereof |
| CN106571140B (en) * | 2016-11-14 | 2021-06-22 | Tcl科技集团股份有限公司 | Intelligent electric appliance control method and system based on voice semantics |
| CN108777808B (en) * | 2018-06-04 | 2021-01-12 | 深圳Tcl数字技术有限公司 | Text-to-speech method based on display terminal, display terminal and storage medium |
| CN108806688A (en) * | 2018-07-16 | 2018-11-13 | 深圳Tcl数字技术有限公司 | Sound control method, smart television, system and the storage medium of smart television |
| CN109065040A (en) * | 2018-08-03 | 2018-12-21 | 北京奔流网络信息技术有限公司 | A kind of voice information processing method and intelligent electric appliance |
| CN109036383B (en) * | 2018-08-24 | 2022-11-29 | 上海理工大学 | Lightweight real-time speech recognition and translation device combined with crawler technology |
| CN114697748B (en) * | 2020-12-25 | 2024-05-03 | 深圳Tcl新技术有限公司 | Video recommendation method and computer equipment based on voice recognition |
| WO2023246151A1 (en) * | 2022-06-22 | 2023-12-28 | 海信视像科技股份有限公司 | Display device and control method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103035240A (en) * | 2011-09-28 | 2013-04-10 | 苹果公司 | Speech recognition repair using contextual information |
| CN103491257A (en) * | 2013-09-29 | 2014-01-01 | 惠州Tcl移动通信有限公司 | Method and system for sending contact information in communication process |
| CN104599669A (en) * | 2014-12-31 | 2015-05-06 | 乐视致新电子科技（天津）有限公司 | Voice control method and device |
-
2015
- 2015-11-25 CN CN201510829731.1A patent/CN105512182B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103035240A (en) * | 2011-09-28 | 2013-04-10 | 苹果公司 | Speech recognition repair using contextual information |
| CN103491257A (en) * | 2013-09-29 | 2014-01-01 | 惠州Tcl移动通信有限公司 | Method and system for sending contact information in communication process |
| CN104599669A (en) * | 2014-12-31 | 2015-05-06 | 乐视致新电子科技（天津）有限公司 | Voice control method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105512182A (en) | 2016-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105512182B (en) | Sound control method and smart television | |
| WO2018157703A1 (en) | Natural language semantic extraction method and device, and computer storage medium | |
| CN106575166B (en) | Method for processing hand input character, splitting and merging data and processing encoding and decoding | |
| US10685186B2 (en) | Semantic understanding based emoji input method and device | |
| CN105989122A (en) | Application recommendation method and device | |
| JP2021131528A (en) | User intention recognition method, device, electronic apparatus, computer readable storage media and computer program | |
| WO2022262487A1 (en) | Form generation method, apparatus and device, and medium | |
| CN103399766B (en) | Upgrade the method and apparatus of input method system | |
| CN106775555B (en) | Virtual reality equipment and input control method thereof | |
| CN111177462B (en) | Video distribution timeliness determination method and device | |
| CN112464034A (en) | User data extraction method and device, electronic equipment and computer readable medium | |
| CN110880324A (en) | Voice data processing method and device, storage medium and electronic equipment | |
| CN109766472A (en) | Signal auditing method, device, electronic equipment and storage medium | |
| CN112269867A (en) | Method, device, equipment and storage medium for pushing information | |
| CN107291704A (en) | Treating method and apparatus, the device for processing | |
| CN110232921A (en) | Voice operating method, apparatus, smart television and system based on service for life | |
| CN111158924A (en) | Content sharing method and device, electronic equipment and readable storage medium | |
| CN111144360A (en) | Multimode information identification method and device, storage medium and electronic equipment | |
| CN109145027A (en) | Data statistical approach, device, equipment and computer readable storage medium | |
| CN104640116A (en) | Phishing short message protection method and communication terminal | |
| CN111680761B (en) | Information feedback method and device and electronic equipment | |
| CN116797195A (en) | Work order processing method, apparatus, computer device, and computer readable storage medium | |
| CN105550361A (en) | Log processing method and apparatus, and ask-answer information processing method and apparatus | |
| CN111353070B (en) | Video title processing method and device, electronic equipment and readable storage medium | |
| CN109033082A (en) | The learning training method, apparatus and computer readable storage medium of semantic model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |