CN108491379A - Shortcut key recognition methods, device, equipment and computer readable storage medium - Google Patents
Shortcut key recognition methods, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN108491379A CN108491379A CN201810191036.0A CN201810191036A CN108491379A CN 108491379 A CN108491379 A CN 108491379A CN 201810191036 A CN201810191036 A CN 201810191036A CN 108491379 A CN108491379 A CN 108491379A
- Authority
- CN
- China
- Prior art keywords
- shortcut key
- semantic information
- text message
- carried out
- information
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 238000003058 natural language processing Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 13
- 238000009432 framing Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 230000033772 system development Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 15
- 238000000605 extraction Methods 0.000 description 11
- 238000012360 testing method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000000205 computational method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 241000008357 Okapia johnstoni Species 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 230000003362 replicative effect Effects 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 238000000151 deposition Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0238—Programmable keyboards
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention discloses a kind of shortcut key recognition methods, device, equipment and computer readable storage mediums, wherein the method includes reading the configuration file of system, with the relevant shortcut key of determination, wherein each shortcut key is correspondingly arranged on corresponding prompt operation instruction;Speech recognition is carried out to obtain text message by the voice messaging to acquisition, and semantic analysis is carried out to the text message, with the corresponding semantic information of determination;Text identification matching is carried out to institute's semantic information according to preset rules, to determine the shortcut key to match with institute's semantic information.The present invention can simplify the identification to shortcut key, moreover it is possible to which auxiliary rapidly carries out system development and programming, improves working efficiency.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of shortcut key recognition methods, device, equipment and calculating
Machine readable storage medium storing program for executing.
Background technology
Integrated Development Environment (IDE, Integrated Development Environment) is opened for providing program
The application program in hair ring border generally comprises the tools such as code editor, compiler, debugger and graphic user interface, still
It is integrated with the integrated exploitation software service set such as written in code function, analytic function, compilation facility, debugging function.Current
For IDE as there are many kinds of developing instruments, different IDE has the shortcut key of various combination again, for programmer, remembers a variety of
Shortcut key convenient and efficient can operate, but programmer needs to remember a large amount of shortcut key in order to being rapidly programmed,
This undoubtedly will increase the workload of programmer, and may be such that high-speeding operation becomes not fast enough and accurate.
Invention content
A kind of shortcut key recognition methods of offer of the embodiment of the present invention, device, equipment and computer readable storage medium, energy
The enough identification simplified to shortcut key improves working efficiency to assist quickly exploitation programming.
On the one hand, an embodiment of the present invention provides a kind of shortcut key recognition methods, this method includes:
The configuration file of reading system, with the relevant shortcut key of determination, wherein each shortcut key is correspondingly arranged on accordingly
Prompt operation instruction;
Speech recognition is carried out to obtain text message by the voice messaging to acquisition, and language is carried out to the text message
Justice analysis, with the corresponding semantic information of determination;
Text identification matching is carried out to institute semantic information according to preset rules, is matched with institute semantic information with determining
Shortcut key.
On the other hand, the embodiment of the present invention additionally provides a kind of shortcut key identification device, which includes:
Reading unit, the configuration file for reading system, with the relevant shortcut key of determination, wherein each shortcut key is equal
It is correspondingly arranged on corresponding prompt operation instruction;
Analytic unit, for carrying out speech recognition to obtain text message, and to described by the voice messaging to acquisition
Text message carries out semantic analysis, with the corresponding semantic information of determination;
Determination unit, for carrying out text identification matching to institute semantic information according to preset rules, with determine with it is described
The prompt operation instruction that semantic information matches.
Another aspect, the embodiment of the present invention additionally provide a kind of computer equipment, including:
Memory, for storing the program for realizing shortcut key identification;And
Processor, it is as described above to execute for running the program for realizing shortcut key identification stored in the memory
Method.
In another aspect, the embodiment of the present invention additionally provides a kind of computer readable storage medium, computer-readable storage medium
There are one either more than one program the one or more programs can be by one or more than one place for matter storage
It manages device to execute, to realize method as described above.
The embodiment of the present invention by read system configuration file, with the relevant shortcut key of determination, wherein each shortcut key
It is correspondingly arranged on corresponding prompt operation instruction;Speech recognition is carried out to obtain text envelope by the voice messaging to acquisition
Breath, and semantic analysis is carried out to the text message, with the corresponding semantic information of determination;According to preset rules to the semantic letter
Breath carries out text identification matching, to determine the shortcut key to match with institute's semantic information, can not only simplify to shortcut key
Identification, moreover it is possible to which auxiliary rapidly carries out system development and programming, improves working efficiency.
Description of the drawings
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, other drawings may also be obtained based on these drawings.
Fig. 1 is a kind of schematic flow diagram of shortcut key recognition methods provided in an embodiment of the present invention;
Fig. 2 is a kind of another schematic flow diagram of shortcut key recognition methods provided in an embodiment of the present invention;
Fig. 3 is a kind of another schematic flow diagram of shortcut key recognition methods provided in an embodiment of the present invention;
Fig. 4 is a kind of another schematic flow diagram of shortcut key recognition methods provided in an embodiment of the present invention;
Fig. 5 is a kind of another schematic flow diagram of shortcut key recognition methods provided in an embodiment of the present invention;
Fig. 6 is a kind of schematic block diagram of shortcut key identification device provided in an embodiment of the present invention;
Fig. 7 is a kind of another schematic block diagram of shortcut key identification device provided in an embodiment of the present invention;
Fig. 8 is a kind of another schematic block diagram of shortcut key identification device provided in an embodiment of the present invention;
Fig. 9 is a kind of another schematic block diagram of shortcut key identification device provided in an embodiment of the present invention;
Figure 10 is a kind of another schematic block diagram of shortcut key identification device provided in an embodiment of the present invention;
Figure 11 is a kind of computer equipment structure composition schematic diagram provided in an embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " comprising " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, element, component and/or its presence or addition gathered.
It is also understood that the term used in this description of the invention is merely for the sake of the mesh for describing specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singulative, "one" and "the" are intended to include plural form.
Referring to Fig. 1, Fig. 1 is a kind of schematic flow diagram of shortcut key recognition methods provided in an embodiment of the present invention.The party
Method may operate in smart mobile phone (such as Android phone, IOS mobile phones), tablet computer, laptop and smart machine
Etc. in terminals.Specifically, this method can be applied to assist programming in various developing instruments, can also be applied to OFFICE etc.
In office software, to realize for example:Create class, the high-speedings such as Code Format operation;Wherein developing instrument can be
Eclipse, intellJ IDEA etc..As shown in Figure 1, the step of this method includes S101~S104.
S101 reads the configuration file of system, with the relevant shortcut key of determination, wherein each shortcut key is correspondingly arranged
There is corresponding prompt operation to instruct.
In embodiments of the present invention, the configuration file of system can be the configuration file of developing instrument IDE, can also be
The configuration file of the office softwares such as OFFICE.Pass through read configuration file, you can with determine recorded in configuration file it is quick
Key and the prompt operation to match with the shortcut key instruct.Under normal circumstances, after having invoked one of shortcut key, so that it may
To obtain and execute prompt operation instruction corresponding with the shortcut key, to realize identification and use to shortcut key.For example,
Shortcut key corresponding to " duplication " can be " ctrl+C ", which is corresponding with refers to about the prompt operation of duplication
It enables, " stickup " corresponding shortcut key can be " ctrl+V ", be somebody's turn to do " ctrl+V " shortcut key and be corresponding with the prompt operation about stickup
Instruction etc..
S102 carries out speech recognition to obtain text message, and to the text message by the voice messaging to acquisition
Semantic analysis is carried out, with the corresponding semantic information of determination.
In embodiments of the present invention, speech recognition can be carried out by the voice messaging that is sent out to user, to obtain with
The corresponding text message of the voice messaging, while semantic analysis can also be carried out to text information, to arrive and this article
The corresponding semantic information of this information.
Further, as shown in Fig. 2, the step S102 specifically includes step S201~S202.
S201 carries out speech recognition to the voice messaging of acquisition, converts voice messaging to text message.
In embodiments of the present invention, the voice messaging of acquisition can accordingly be handled by intelligent sound API.It should
Intelligent sound API can be the API for carrying out speech recognition.
Further, as shown in figure 3, the step S201 is specifically included:Step S301~S303.
The voice messaging of acquisition is converted to pure information of acoustic wave by S301 by voice activity detection.
In embodiments of the present invention, under normal circumstances, it before identifying voice, is required for using voice activity detection (Voice
Activity detection, VAD) this voice process technology the head and the tail section of the voice messaging of the acquisition is carried out it is quiet
Sound is cut off, to obtain pure information of acoustic wave, to reduce noise jamming.Wherein, voice activity detection technology is mainly used for voice coder
Code and speech recognition, it can simplify speech processes, it can also be used to non-speech segments are removed during audio session, it such as can be
The coding to quiet data packet and transmission are avoided in IP phone application, saves and calculates time and bandwidth, therefore Voice activity detection skill
Art makes some arrange voice-based application program and be known as reality.
S302 carries out framing using the pure information of acoustic wave of Moving Window function pair, and to the pure information of acoustic wave carry out sound after framing
Learn feature extraction.
In embodiments of the present invention, the mobile window function, which can be realized, blocks signal, to realize to pure sound
Wave information carries out framing.Meanwhile relatively conventional acoustic feature extracting method can be extraction MFCC features, i.e., according to human ear
Each frame waveform, is become a multi-C vector by physiological characteristic, this frame voice is contained to be simply interpreted as this vector
Content information.For example, after pure information of acoustic wave carries out acoustic feature extraction, 12 rows can be become (assuming that acoustic feature is 12
Dimension), a matrix of N row, therefore referred to as observation sequence, N is totalframes here.
S303 builds a state network, and find from state network and believe with pure sound wave using hidden Markov model
The most matched path of breath, to obtain corresponding text message.
In embodiments of the present invention, building state network refers to after being launched into phoneme network by word level network, reinflated
At state network.Under normal circumstances, speech recognition process is exactly one optimal path of search in state network, voice letter in fact
The maximum probability of corresponding optimal path is ceased, referred to as " is decoded ".The algorithm of route searching is a kind of calculation of Dynamic Programming beta pruning
Method, referred to as Viterbi algorithm, for finding global optimum path.In short, one state of several frame voices correspondences, every three
Combinations of states is at a phoneme, several phonotactics are at a word, then by the matching of state network, most by information of acoustic wave
Switch to text message eventually.
S202 carries out semantic analysis to obtain corresponding semantic information by natural language processing algorithm to text message.
In embodiments of the present invention, natural language processing algorithm (Natural Language Processing, NLP) is
One subdomains of artificial intelligence (AI), the syntactic structure of word is indicated using the dependence in sentence between word and word
Information (such as subject-predicate, determines medium structure relationship at dynamic guest), the structure of whole sentence is indicated with tree, and (such as Subject, Predicate and Object determines shape
Mend etc.).By analyzing the interdependent syntactic structure information of user Query, semantic trunk therein and related semantic component, side are extracted
Intellectual product is helped to realize the accurate understanding to user view.
Further, as shown in figure 4, the step S202 is specifically included:Step S401~S403.
S401 carries out participle and part-of-speech tagging, to obtain multiple words for being labeled with part of speech to the text message.
In embodiments of the present invention, natural language processing be exactly in order to allow computer it will be appreciated that the mankind language, that is, manage
Solve the meaning of word behind.And participle is the basis of natural language processing, such as have to keyword extraction, point this classification etc.
It helps.Under normal circumstances, participle principle is condition random field, by the features such as the position mark of word and part of speech come into
Row participle, to obtain several words, alternatively referred to as obtains several term.
S402 calculates the weighted value of each word.
In embodiments of the present invention, a weight can be calculated to each term after participle, important term should give
With higher weight.For example, " any movement helps weight-reducing larger" term weighting results may be:" what
0.1, movement 0.5, to 0.1, weight-reducing 0.8 helps 0.3, larger 0.2 ".The marking formula of term weighing (Term weighting)
Generally it is made of this three parts of local, global and normalization.Term weighting methods may include F-
IDF, Okapi, MI, LTU, ATC, TF-ICF etc., by local, the combination of the various formula of global, normalization can
To generate different term weighting computational methods.Each word can be obtained by term weighting computational methods
The corresponding weighted value of language.
S403 determines that the word that weighted value is greater than or equal to pre-set threshold value is keyword, and the keyword is as corresponding
Semantic information.
In embodiments of the present invention, a threshold value is preset, obtains the corresponding weighted value of all words, and above or equal to
Word corresponding to the weighted value of pre-set threshold value is determined as keyword, which is corresponding semantic information.
S103 carries out text identification matching, to determine and institute's semantic information according to preset rules to institute's semantic information
The shortcut key to match.
In embodiments of the present invention, the preset rules can be according to preset Chinese wordbank to institute's semantic information into
Row fuzzy search parses, to realize the text identification to institute's semantic information.Under normal circumstances, specific text identification is carried out
Later, it may be determined that the shortcut key corresponding to the voice messaging can confirm according to the shortcut key and be called required for user
Prompt operation instructs, that is, realizes corresponding voice feedback.
Further, as shown in figure 5, the step S103 is specifically included:Step S501~S502.
S501 obtains preset Chinese wordbank.
In embodiments of the present invention, relevant technical term dictionary can be created according to existing data information, this is existing
Data information can be professional domain word and life in popular word, meanwhile, the preset Chinese wordbank can be with
It is created according to the demand of user.For example, can according to shortcut key that system configuration has and related prompt operation, create with
The corresponding technical term dictionary of the shortcut key, the technical term dictionary are the default Chinese wordbank of the application.
Institute's semantic information and the preset Chinese wordbank are carried out fuzzy matching, to determine and the semanteme by S502
The shortcut key of information match.
In embodiments of the present invention, by the way that institute's semantic information and the preset Chinese wordbank are carried out fuzzy matching,
Realize the text identification matching to institute's semantic information, so that it is determined that the corresponding shortcut key of the semantic information, and because it is each
Shortcut key is all corresponding with the instruction of corresponding prompt operation, can determine that the prompt operation to match with institute semantic information refers at this time
It enables, to realize subsequent prompt operation.
For example, when in traditional systems development process, if developer will replicate one section of code, choosing will replicate
It, can be to including determining that " duplication " is keyword after the voice messaging of " duplication " is identified, " replicating " at this time i.e. after content
For semantic information, by the way that " duplication " and preset Chinese wordbank are carried out fuzzy matching, it may be determined that " ctrl+C " is corresponding
Shortcut key determines that " ctrl+C " corresponding prompt operation instruction instructs for the prompt operation to match with " duplication ", so as to
To realize the duplication to selecting code.Therefore it is further, any operation that can be simplified by shortcut key can save button
Operation, directly sends out instruction by natural language and operation can be realized.Such as create a test class, it is only necessary to use nature language
Speech sends out the instruction for creating a test class.
Therefore under normal circumstances, relevant technical term dictionary can be created according to existing data information, then pass through by
The semanteme of language message after parsing carries out fuzzy matching with the relevant technical term dictionary of establishment, to determine and the semantic letter
The matched prompt operation instruction of manner of breathing, then the following operation to be performed of user (technical term feedback) is given by voice feedback,
Corresponding operation and verbal feedback implementing result are executed, is performed simultaneously and the language of feedback is carried out and customized, it is special user can be enhanced
Industry, user-friendly study.
As further embodiment, the method is further comprising the steps of:
S104 runs the corresponding prompt operation instruction of the shortcut key, to realize corresponding prompt operation.
In embodiments of the present invention, it is instructed by running the corresponding prompt operation of the shortcut key, may be implemented and input
The corresponding prompt operation of voice messaging.
It, can also be after calling operation prompt operation instruction meanwhile as another embodiment, display and the quick behaviour
Make to instruct corresponding shortcut key, to facilitate user directly to be operated.
For example, method provided in an embodiment of the present invention can be applied in this common IDE developing instruments of Eclipse is
Example.User is come out under the premise of not knowing the shortcut key of certain operations by natural language expressing, for example, saying:" I will create
Build the java classes of a Test ", then it can be searched for generally by speech recognition API, semantics recognition API and Chinese wordbank,
By the prompt operation instruction calls corresponding to the shortcut key " alt+C " for the establishment class being arranged in Eclipse this IDE developing instrument
Out, to create a Test.java file.It is somebody's turn to do preferably, can also be shown on the display screen of terminal simultaneously
Shortcut key " alt+C " facilitates user directly to use next time corresponding fast to prompt the shortcut key that user creates class as " alt+C "
Prompt key.It is, of course, also possible to by speech play, to prompt user.
In another example the calling of prompt operation instruction can be carried out by speech recognition to selected target, with realization pair
The operation processing of target.Such as, an xxx.txt file is chosen, voice messaging is sent out:" opening file " then calls quick at this time
The opening file tool of operational order, selected acquiescence opens file, while can also return to voice:It " has opened
Xxx.txt files ";And after choosing content of text, send out voice messaging:" duplication " determines replicate corresponding " ctrl+C " at this time
Shortcut key can voice feedback after calling the corresponding prompt operation instruction execution of the shortcut key to replicate:" reproducting content ".
Specified text position, sends out voice messaging:" stickup " determines paste corresponding " ctrl+V " shortcut key at this time, should to call
The corresponding prompt operation of shortcut key instructs and in designated position paste content, while can be with voice feedback:" pasting successfully ".
Those having ordinary skill in the art is appreciated that realize all or part of flow in above-described embodiment method, is that can lead to
It crosses computer program and is completed to instruct relevant hardware, the program can be stored in a computer read/write memory medium
In, the program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) etc..
To sum up, the embodiment of the present invention can not only simplify the identification to shortcut key, moreover it is possible to which auxiliary rapidly carries out system and opens
Hair and programming, improve working efficiency.Meanwhile the shortcut key recognition methods is mainly identified using intelligent sound, is integrated different
Shortcut key in IDE so that after developer inputs natural language to computer, you can complete corresponding prompt operation.
Referring to Fig. 6, corresponding above-mentioned shortcut key recognition methods, the embodiment of the present invention also proposes a kind of shortcut key identification dress
It sets, which includes:Reading unit 101, analytic unit 102 and determination unit 103.
The reading unit 101, the configuration file for reading system, with the relevant shortcut key of determination, wherein each fast
Prompt key is correspondingly arranged on corresponding prompt operation instruction.
In embodiments of the present invention, the configuration file of system can be the configuration file of developing instrument IDE, can also be
The configuration file of the office softwares such as OFFICE.Pass through read configuration file, you can with determine recorded in configuration file it is quick
Key and the prompt operation to match with the shortcut key instruct.Under normal circumstances, after having invoked one of shortcut key, so that it may
To obtain and execute prompt operation instruction corresponding with the shortcut key, to realize identification and use to shortcut key.For example,
Shortcut key corresponding to " duplication " can be " ctrl+C ", which is corresponding with refers to about the prompt operation of duplication
It enables, " stickup " corresponding shortcut key can be " ctrl+V ", be somebody's turn to do " ctrl+V " shortcut key and be corresponding with the prompt operation about stickup
Instruction etc..
The analytic unit 102, for carrying out speech recognition by the voice messaging to acquisition to obtain text message, and
Semantic analysis is carried out to the text message, with the corresponding semantic information of determination.
In embodiments of the present invention, speech recognition can be carried out by the voice messaging that is sent out to user, to obtain with
The corresponding text message of the voice messaging, while semantic analysis can also be carried out to text information, to arrive and this article
The corresponding semantic information of this information.
Further, as shown in fig. 7, the analytic unit 102 specifically includes:Voice recognition unit 201 and semanteme point
Analyse unit 202.
The voice recognition unit 201 carries out speech recognition for the voice messaging to acquisition, voice messaging is converted
For text message.
In embodiments of the present invention, the voice messaging of acquisition can accordingly be handled by intelligent sound API.It should
Intelligent sound API can be the API for carrying out speech recognition.
Further, as shown in figure 8, the voice recognition unit 201 specifically includes:Converting unit 301, feature extraction list
Member 302 and construction unit 303.
The voice messaging of acquisition is converted to pure information of acoustic wave by the converting unit 301 by voice activity detection.
In embodiments of the present invention, under normal circumstances, it before identifying voice, is required for using voice activity detection (Voice
Activity detection, VAD) this voice process technology the head and the tail section of the voice messaging of the acquisition is carried out it is quiet
Sound is cut off, to obtain pure information of acoustic wave, to reduce noise jamming.Wherein, voice activity detection technology is mainly used for voice coder
Code and speech recognition, it can simplify speech processes, it can also be used to non-speech segments are removed during audio session, it such as can be
The coding to quiet data packet and transmission are avoided in IP phone application, saves and calculates time and bandwidth, therefore Voice activity detection skill
Art makes some arrange voice-based application program and be known as reality.
The feature extraction unit 302 carries out framing using the pure information of acoustic wave of Moving Window function pair, and to pure after framing
Information of acoustic wave carries out acoustic feature extraction.
In embodiments of the present invention, the mobile window function, which can be realized, blocks signal, to realize to pure sound
Wave information carries out framing.Meanwhile relatively conventional acoustic feature extracting method can be extraction MFCC features, i.e., according to human ear
Each frame waveform, is become a multi-C vector by physiological characteristic, this frame voice is contained to be simply interpreted as this vector
Content information.For example, after pure information of acoustic wave carries out acoustic feature extraction, 12 rows can be become (assuming that acoustic feature is 12
Dimension), a matrix of N row, therefore referred to as observation sequence, N is totalframes here.
The construction unit 303 builds a state network, and sought from state network using hidden Markov model
Look for the most matched path of pure information of acoustic wave, to obtain corresponding text message.
In embodiments of the present invention, building state network refers to after being launched into phoneme network by word level network, reinflated
At state network.Under normal circumstances, speech recognition process is exactly one optimal path of search in state network, voice letter in fact
The maximum probability of corresponding optimal path is ceased, referred to as " is decoded ".The algorithm of route searching is a kind of calculation of Dynamic Programming beta pruning
Method, referred to as Viterbi algorithm, for finding global optimum path.In short, one state of several frame voices correspondences, every three
Combinations of states is at a phoneme, several phonotactics are at a word, then by the matching of state network, most by information of acoustic wave
Switch to text message eventually.
The semantic analysis unit 202, for by natural language processing algorithm to text message carry out semantic analysis with
Obtain corresponding semantic information.
In embodiments of the present invention, natural language processing algorithm (Natural Language Processing, NLP) is
One subdomains of artificial intelligence (AI), the syntactic structure of word is indicated using the dependence in sentence between word and word
Information (such as subject-predicate, determines medium structure relationship at dynamic guest), the structure of whole sentence is indicated with tree, and (such as Subject, Predicate and Object determines shape
Mend etc.).By analyzing the interdependent syntactic structure information of user Query, semantic trunk therein and related semantic component, side are extracted
Intellectual product is helped to realize the accurate understanding to user view.
Further, as shown in figure 9, the semantic analysis unit 202 specifically includes:Participle unit 401, computing unit
402 and adjustment unit 403.
The participle unit 401, for carrying out participle and part-of-speech tagging to the text message, to obtain multiple be labeled with
The word of part of speech.
In embodiments of the present invention, natural language processing be exactly in order to allow computer it will be appreciated that the mankind language, that is, manage
Solve the meaning of word behind.And participle is the basis of natural language processing, such as have to keyword extraction, point this classification etc.
It helps.Under normal circumstances, participle principle is condition random field, by the features such as the position mark of word and part of speech come into
Row participle, to obtain several words, alternatively referred to as obtains several term.
The computing unit 402, the weighted value for calculating each word.
In embodiments of the present invention, a weight can be calculated to each term after participle, important term should give
With higher weight.For example, " any movement helps weight-reducing larger" term weighting results may be:" what
0.1, movement 0.5, to 0.1, weight-reducing 0.8 helps 0.3, larger 0.2 ".The marking formula of term weighing (Term weighting)
Generally it is made of this three parts of local, global and normalization.Term weighting methods may include F-
IDF, Okapi, MI, LTU, ATC, TF-ICF etc., by local, the combination of the various formula of global, normalization can
To generate different term weighting computational methods.Each word can be obtained by term weighting computational methods
The corresponding weighted value of language.
The adjustment unit 403, for determining that the word that weighted value is greater than or equal to pre-set threshold value is keyword, the pass
Keyword is corresponding semantic information.
In embodiments of the present invention, a threshold value is preset, obtains the corresponding weighted value of all words, and above or equal to
Word corresponding to the weighted value of pre-set threshold value is determined as keyword, which is corresponding semantic information.
The determination unit 103, for carrying out text identification matching to institute's semantic information according to preset rules, with determination
It is instructed with the prompt operation that institute semantic information matches.
Further, as shown in Figure 10, the determination unit 103 specifically includes:Acquiring unit 501 and matching unit
502。
The acquiring unit 501, for obtaining preset Chinese wordbank.
In embodiments of the present invention, relevant technical term dictionary can be created according to existing data information, this is existing
Data information can be professional domain word and life in popular word, meanwhile, the preset Chinese wordbank can be with
It is created according to the demand of user.For example, can according to shortcut key that system configuration has and related prompt operation, create with
The corresponding technical term dictionary of the shortcut key, the technical term dictionary are the default Chinese wordbank of the application.
The matching unit 502, for institute's semantic information and the preset Chinese wordbank to be carried out fuzzy matching, with
Determine the shortcut key to match with institute's semantic information.
In embodiments of the present invention, by the way that institute's semantic information and the preset Chinese wordbank are carried out fuzzy matching,
Realize the text identification matching to institute's semantic information, so that it is determined that the corresponding shortcut key of the semantic information, and because it is each
Shortcut key is all corresponding with the instruction of corresponding prompt operation, can determine that the prompt operation to match with institute semantic information refers at this time
It enables, to realize subsequent prompt operation.
For example, when in traditional systems development process, if developer will replicate one section of code, choosing will replicate
It, can be to including determining that " duplication " is keyword after the voice messaging of " duplication " is identified, " replicating " at this time i.e. after content
For semantic information, by the way that " duplication " and preset Chinese wordbank are carried out fuzzy matching, it may be determined that " ctrl+C " is corresponding
Shortcut key determines that " ctrl+C " corresponding prompt operation instruction instructs for the prompt operation to match with " duplication ", so as to
To realize the duplication to selecting code.Therefore it is further, any operation that can be simplified by shortcut key can save button
Operation, directly sends out instruction by natural language and operation can be realized.Such as create a test class, it is only necessary to use nature language
Speech sends out the instruction for creating a test class.
Therefore under normal circumstances, relevant technical term dictionary can be created according to existing data information, then pass through by
The semanteme of language message after parsing carries out fuzzy matching with the relevant technical term dictionary of establishment, to determine and the semantic letter
The matched prompt operation instruction of manner of breathing, then the following operation to be performed of user (technical term feedback) is given by voice feedback,
Corresponding operation and verbal feedback implementing result are executed, is performed simultaneously and the language of feedback is carried out and customized, it is special user can be enhanced
Industry, user-friendly study.
As further embodiment, described device may further include the following units:
Running unit 104, for running the corresponding prompt operation instruction of the shortcut key, to realize corresponding quick behaviour
Make.In embodiments of the present invention, it is instructed by running the corresponding prompt operation of the shortcut key, the voice with input may be implemented
The corresponding prompt operation of information.
Meanwhile as another further embodiment, which can also include display unit, for calling operation fast
After prompt operational order, shortcut key corresponding with prompt operation instruction is shown, to facilitate user directly to be operated.
For example, method provided in an embodiment of the present invention can be applied in this common IDE developing instruments of Eclipse is
Example.User is come out under the premise of not knowing the shortcut key of certain operations by natural language expressing, for example, saying:" I will create
Build the java classes of a Test ", then it can be searched for generally by speech recognition API, semantics recognition API and Chinese wordbank,
By the prompt operation instruction calls corresponding to the shortcut key " alt+C " for the establishment class being arranged in Eclipse this IDE developing instrument
Out, to create a Test.java file.It is somebody's turn to do preferably, can also be shown on the display screen of terminal simultaneously
Shortcut key " alt+C " facilitates user directly to use next time corresponding fast to prompt the shortcut key that user creates class as " alt+C "
Prompt key.It is, of course, also possible to by speech play, to prompt user.
In another example the calling of prompt operation instruction can be carried out by speech recognition to selected target, with realization pair
The operation processing of target.Such as, an xxx.txt file is chosen, voice messaging is sent out:" opening file " then calls quick at this time
The opening file tool of operational order, selected acquiescence opens file, while can also return to voice:It " has opened
Xxx.txt files ";And after choosing content of text, send out voice messaging:" duplication " determines replicate corresponding " ctrl+C " at this time
Shortcut key can voice feedback after calling the corresponding prompt operation instruction execution of the shortcut key to replicate:" reproducting content ".
Specified text position, sends out voice messaging:" stickup " determines paste corresponding " ctrl+V " shortcut key at this time, should to call
The corresponding prompt operation of shortcut key instructs and in designated position paste content, while can be with voice feedback:" pasting successfully ".
To sum up, the embodiment of the present invention can not only simplify the identification to shortcut key, moreover it is possible to which auxiliary rapidly carries out system and opens
Hair and programming, improve working efficiency.Meanwhile the shortcut key recognition methods is mainly identified using intelligent sound, is integrated different
Shortcut key in IDE so that after developer inputs natural language to computer, you can complete corresponding prompt operation.
As seen from the above, in hardware realization, unit 101, analytic unit 102 and determination unit 103 read above etc.
Can be embedded in the form of hardware or the device that is identified independently of shortcut key in, shortcut key knowledge can also be stored in a software form
In the memory of other device, the corresponding operation of above each unit is executed so that processor calls.The processor can be center
Processing unit (CPU), microprocessor, microcontroller etc..
Above-mentioned shortcut key identification device can be implemented as a kind of form of computer program, and computer program can such as scheme
It is run on computer equipment shown in 11.
Figure 11 is a kind of structure composition schematic diagram of computer equipment of the present invention.The equipment can be terminal, can also be
Server, wherein terminal can be smart mobile phone, tablet computer, laptop, desktop computer, personal digital assistant and wear
Wearing formula equipment etc. has the electronic equipment of communication function.Server can be independent server, can also be multiple servers
The server cluster of composition.Referring to Fig.1 1, the computer equipment 600 include the processor 602 connected by system bus 601,
Non-volatile memory medium 603, built-in storage 604 and network interface 605.Wherein, the non-volatile of the computer equipment 600 is deposited
Storage media 603 can storage program area 6031 and computer program 6032, which is performed, and may make place
Reason device 602 executes a kind of shortcut key recognition methods.The processor 602 of the computer equipment 600 calculates and controls energy for providing
Power supports the operation of entire computer equipment 600.The built-in storage 604 is the computer program in non-volatile memory medium
Operation provide environment, when which is executed by processor, processor 602 may make to execute a kind of shortcut key identification side
Method.The network interface 605 of computer equipment 600 such as sends the task dispatching of distribution for carrying out network communication.People in the art
Member it is appreciated that Figure 11 shown in structure, only with the block diagram of the relevant part-structure of application scheme, constitute pair
The restriction for the computer equipment that application scheme is applied thereon, specific computer equipment may include than as shown in the figure more
More or less component either combines certain components or is arranged with different components.
Wherein, the processor 602 executes following operation:The configuration file of reading system, with the relevant shortcut key of determination,
Wherein, each shortcut key is correspondingly arranged on corresponding prompt operation instruction;Voice knowledge is carried out by the voice messaging to acquisition
Not to obtain text message, and semantic analysis is carried out to the text message, with the corresponding semantic information of determination;According to default rule
Text identification matching then is carried out to institute's semantic information, to determine the shortcut key to match with institute's semantic information.
The processor 602 executes following operation:Speech recognition is carried out to the voice messaging of acquisition, voice messaging is turned
Turn to text message;Semantic analysis is carried out to obtain corresponding semantic information to text message by natural language processing algorithm.
The processor 602 executes following operation:The voice messaging of acquisition is converted into pure sound by voice activity detection
Wave information;Framing is carried out using the pure information of acoustic wave of Moving Window function pair, and acoustic feature is carried out to the pure information of acoustic wave after framing
Extraction;Using hidden Markov model, a state network is built, and find from state network and most matched with pure information of acoustic wave
Path, to obtain corresponding text message.
The processor 602 executes following operation:Participle and part-of-speech tagging are carried out to the text message, it is multiple to obtain
It is labeled with the word of part of speech;Calculate the weighted value of each word;Determine that the word that weighted value is greater than or equal to pre-set threshold value is to close
Keyword, the keyword are corresponding semantic information.
The processor 602 executes following operation:Obtain preset Chinese wordbank;Institute's semantic information is preset with described
Chinese wordbank carry out fuzzy matching, to determine the shortcut key to match with institute's semantic information.
It will be understood by those skilled in the art that the embodiment of computer equipment shown in Figure 11 is not constituted to computer
The restriction of equipment specific composition, in other embodiments, computer equipment may include components more more or fewer than diagram, or
Person combines certain components or different components arrangement.For example, in some embodiments, computer equipment can only include depositing
Reservoir and processor, in such embodiments, the structure and function of memory and processor are consistent with embodiment illustrated in fig. 11,
Details are not described herein.
The present invention provides a kind of computer readable storage medium, computer-readable recording medium storage there are one or one
A procedure above, the one or more programs can be executed by one or more than one processor, with realize with
Lower step:The configuration file of reading system, with the relevant shortcut key of determination, wherein each shortcut key is correspondingly arranged on accordingly
Prompt operation instruction;Speech recognition is carried out to obtain text message, and to the text envelope by the voice messaging to acquisition
Breath carries out semantic analysis, with the corresponding semantic information of determination;Text identification is carried out to institute's semantic information according to preset rules
Match, to determine the shortcut key to match with institute's semantic information.
The processor also realizes following steps:Speech recognition is carried out to the voice messaging of acquisition, voice messaging is turned
Turn to text message;Semantic analysis is carried out to obtain corresponding semantic information to text message by natural language processing algorithm.
The processor also realizes following steps:The voice messaging of acquisition is converted into pure sound wave by voice activity detection
Information;Framing is carried out using the pure information of acoustic wave of Moving Window function pair, and acoustic feature is carried out to the pure information of acoustic wave after framing and is carried
It takes;Using hidden Markov model, a state network is built, and searching is most matched with pure information of acoustic wave from state network
Path, to obtain corresponding text message.
The processor also realizes following steps:Participle and part-of-speech tagging are carried out to the text message, it is multiple to obtain
It is labeled with the word of part of speech;Calculate the weighted value of each word;Determine that the word that weighted value is greater than or equal to pre-set threshold value is to close
Keyword, the keyword are corresponding semantic information.
The processor also realizes following steps:Obtain preset Chinese wordbank;Institute's semantic information is preset with described
Chinese wordbank carry out fuzzy matching, to determine the shortcut key to match with institute's semantic information..
Present invention storage medium above-mentioned includes:Magnetic disc, CD, read-only memory (Read-Only Memory,
The various media that can store program code such as ROM).
Unit in all embodiments of the invention can pass through universal integrated circuit, such as CPU (Central
Processing Unit, central processing unit), or pass through ASIC (Application Specific Integrated
Circuit, application-specific integrated circuit) it realizes.
Step in shortcut key recognition methods of the embodiment of the present invention can according to actual needs the adjustment of carry out sequence, merge and
It deletes.
Unit in shortcut key identification terminal of the embodiment of the present invention can be merged, divides and be deleted according to actual needs
Subtract.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection domain subject to.
Claims (10)
1. a kind of shortcut key recognition methods, which is characterized in that the method includes:
The configuration file of reading system, with the relevant shortcut key of determination, wherein each shortcut key is correspondingly arranged on corresponding fast
Prompt operational order;
Speech recognition is carried out by the voice messaging to acquisition to obtain text message, and semantic point is carried out to the text message
Analysis, with the corresponding semantic information of determination;
Text identification matching is carried out to institute semantic information according to preset rules, with determine match with institute semantic information it is fast
Prompt key.
2. the method as described in claim 1, which is characterized in that it is described by the voice messaging of acquisition carry out speech recognition with
Text message is obtained, and semantic analysis is carried out to the text message, with the corresponding semantic information of determination, including:
Speech recognition is carried out to the voice messaging of acquisition, converts voice messaging to text message;
Semantic analysis is carried out to obtain corresponding semantic information to text message by natural language processing algorithm.
3. method as claimed in claim 2, which is characterized in that the voice messaging of described pair of acquisition carries out speech recognition, will
Voice messaging is converted into text message, including:
The voice messaging of acquisition is converted into pure information of acoustic wave by voice activity detection;
Framing is carried out using the pure information of acoustic wave of Moving Window function pair, and acoustic feature is carried out to the pure information of acoustic wave after framing and is carried
It takes;
Using hidden Markov model, a state network is built, and find from state network and most matched with pure information of acoustic wave
Path, to obtain corresponding text message.
4. method as claimed in claim 2, which is characterized in that described to be carried out to text message by natural language processing algorithm
Semantic analysis to obtain corresponding semantic information, including:
Participle and part-of-speech tagging are carried out to the text message, to obtain multiple words for being labeled with part of speech;
Calculate the weighted value of each word;
Determine that the word that weighted value is greater than or equal to pre-set threshold value is keyword, the keyword is corresponding semantic information.
5. the method as described in claim 1, which is characterized in that described to carry out text to institute's semantic information according to preset rules
Identification matching, to determine the shortcut key to match with institute's semantic information, including:
Obtain preset Chinese wordbank;
Institute's semantic information and the preset Chinese wordbank are subjected to fuzzy matching, matched with institute semantic information with determining
Shortcut key.
6. a kind of shortcut key identification device, which is characterized in that described device includes:
Reading unit, the configuration file for reading system, with the relevant shortcut key of determination, wherein each shortcut key is corresponding
It is provided with corresponding prompt operation instruction;
Analytic unit, for carrying out speech recognition to obtain text message, and to the text by the voice messaging to acquisition
Information carries out semantic analysis, with the corresponding semantic information of determination;
Determination unit, for carrying out text identification matching to institute's semantic information according to preset rules, to determine and the semanteme
The prompt operation of information match instructs.
7. device as claimed in claim 6, which is characterized in that the analytic unit, including:
Voice recognition unit carries out speech recognition for the voice messaging to acquisition, converts voice messaging to text message;
Semantic analysis unit carries out semantic analysis to obtain corresponding language for passing through natural language processing algorithm to text message
Adopted information.
8. device as claimed in claim 6, which is characterized in that the determination unit, including:
Acquiring unit, for obtaining preset Chinese wordbank;
Matching unit, for institute's semantic information and the preset Chinese wordbank to be carried out fuzzy matching, with determine with it is described
The shortcut key that semantic information matches.
9. a kind of computer equipment, which is characterized in that including:
Memory, for storing the program for realizing shortcut key identification;And
Processor, for running the program for realizing shortcut key identification stored in the memory, to execute such as claim 1-5
Any one of them method.
10. a kind of computer readable storage medium, which is characterized in that computer-readable recording medium storage there are one or one
Procedure above, the one or more programs can be executed by one or more than one processor, to realize as weighed
Profit requires 1-5 any one of them methods.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810191036.0A CN108491379A (en) | 2018-03-08 | 2018-03-08 | Shortcut key recognition methods, device, equipment and computer readable storage medium |
PCT/CN2018/085255 WO2019169722A1 (en) | 2018-03-08 | 2018-05-02 | Shortcut key recognition method and apparatus, device, and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810191036.0A CN108491379A (en) | 2018-03-08 | 2018-03-08 | Shortcut key recognition methods, device, equipment and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108491379A true CN108491379A (en) | 2018-09-04 |
Family
ID=63338223
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810191036.0A Pending CN108491379A (en) | 2018-03-08 | 2018-03-08 | Shortcut key recognition methods, device, equipment and computer readable storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108491379A (en) |
WO (1) | WO2019169722A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109491264A (en) * | 2018-12-24 | 2019-03-19 | 青岛海信智慧家居系统股份有限公司 | A kind of home equipment control method and device |
CN112819061A (en) * | 2021-01-27 | 2021-05-18 | 北京小米移动软件有限公司 | Password information identification method, device, equipment and storage medium |
CN112908327A (en) * | 2021-02-02 | 2021-06-04 | 上海市胸科医院 | Voice control method, device, equipment and storage medium of application program |
CN114138227A (en) * | 2021-12-08 | 2022-03-04 | 江西台德智慧科技有限公司 | Intelligent voice shortcut key input method and intelligent voice shortcut key input system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622085A (en) * | 2012-04-11 | 2012-08-01 | 北京航空航天大学 | Multidimensional sense man-machine interaction system and method |
KR20140000003A (en) * | 2012-06-22 | 2014-01-02 | 송병식 | A combination of keyboard shortcuts run of voice |
CN106710593A (en) * | 2015-11-17 | 2017-05-24 | 腾讯科技(深圳)有限公司 | Method for adding account, terminal, and server |
CN107665705A (en) * | 2017-09-20 | 2018-02-06 | 平安科技(深圳)有限公司 | Voice keyword recognition method, device, equipment and computer-readable recording medium |
CN107679033A (en) * | 2017-09-11 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Text punctuate location recognition method and device |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1641563A (en) * | 2004-01-09 | 2005-07-20 | 顺德市顺达电脑厂有限公司 | Computer device voice rapid control device and method thereof |
JP2010205130A (en) * | 2009-03-05 | 2010-09-16 | Denso Corp | Control device |
US20130275134A1 (en) * | 2011-05-20 | 2013-10-17 | Mitsubishi Electric Corporation | Information equipment |
CN103294370A (en) * | 2012-03-05 | 2013-09-11 | 北京千橡网景科技发展有限公司 | Method and equipment for triggering keystroke operation |
CN104750257A (en) * | 2013-12-30 | 2015-07-01 | 鸿富锦精密工业(武汉)有限公司 | Keyboard combination and voice recognition method |
CN105183778A (en) * | 2015-08-11 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Service providing method and apparatus |
-
2018
- 2018-03-08 CN CN201810191036.0A patent/CN108491379A/en active Pending
- 2018-05-02 WO PCT/CN2018/085255 patent/WO2019169722A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622085A (en) * | 2012-04-11 | 2012-08-01 | 北京航空航天大学 | Multidimensional sense man-machine interaction system and method |
KR20140000003A (en) * | 2012-06-22 | 2014-01-02 | 송병식 | A combination of keyboard shortcuts run of voice |
CN106710593A (en) * | 2015-11-17 | 2017-05-24 | 腾讯科技(深圳)有限公司 | Method for adding account, terminal, and server |
CN107679033A (en) * | 2017-09-11 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Text punctuate location recognition method and device |
CN107665705A (en) * | 2017-09-20 | 2018-02-06 | 平安科技(深圳)有限公司 | Voice keyword recognition method, device, equipment and computer-readable recording medium |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109491264A (en) * | 2018-12-24 | 2019-03-19 | 青岛海信智慧家居系统股份有限公司 | A kind of home equipment control method and device |
CN109491264B (en) * | 2018-12-24 | 2022-01-21 | 青岛海信智慧家居系统股份有限公司 | Household equipment control method and device |
CN112819061A (en) * | 2021-01-27 | 2021-05-18 | 北京小米移动软件有限公司 | Password information identification method, device, equipment and storage medium |
CN112819061B (en) * | 2021-01-27 | 2024-05-10 | 北京小米移动软件有限公司 | Password information identification method, device, equipment and storage medium |
CN112908327A (en) * | 2021-02-02 | 2021-06-04 | 上海市胸科医院 | Voice control method, device, equipment and storage medium of application program |
CN114138227A (en) * | 2021-12-08 | 2022-03-04 | 江西台德智慧科技有限公司 | Intelligent voice shortcut key input method and intelligent voice shortcut key input system |
Also Published As
Publication number | Publication date |
---|---|
WO2019169722A1 (en) | 2019-09-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gupta et al. | The AT&T spoken language understanding system | |
CN108831439B (en) | Voice recognition method, device, equipment and system | |
CN107423363B (en) | Artificial intelligence based word generation method, device, equipment and storage medium | |
CN108491379A (en) | Shortcut key recognition methods, device, equipment and computer readable storage medium | |
CN108847241A (en) | It is method, electronic equipment and the storage medium of text by meeting speech recognition | |
CN107797984A (en) | Intelligent interactive method, equipment and storage medium | |
JP2003535410A (en) | Generation of unified task-dependent language model by information retrieval method | |
JP2005084681A (en) | Method and system for semantic language modeling and reliability measurement | |
JP2004523004A (en) | Hierarchical language model | |
CN109671435B (en) | Method and apparatus for waking up smart device | |
JP2004005530A (en) | Information-providing device using voice interactive interface, and its method | |
CN106356057A (en) | Speech recognition system based on semantic understanding of computer application scenario | |
CN109102796A (en) | A kind of phoneme synthesizing method and device | |
US20200210505A1 (en) | Electronic apparatus and controlling method thereof | |
CN111324708A (en) | Natural language processing system based on human-computer interaction | |
CN109448704A (en) | Construction method, device, server and the storage medium of tone decoding figure | |
CN111144128A (en) | Semantic parsing method and device | |
CN112151015A (en) | Keyword detection method and device, electronic equipment and storage medium | |
CN110265008A (en) | Intelligence pays a return visit method, apparatus, computer equipment and storage medium | |
CN110020429A (en) | Method for recognizing semantics and equipment | |
CN108231074A (en) | A kind of data processing method, voice assistant equipment and computer readable storage medium | |
CN112289305A (en) | Prosody prediction method, device, equipment and storage medium | |
CN111508481A (en) | Training method and device of voice awakening model, electronic equipment and storage medium | |
CN116978367A (en) | Speech recognition method, device, electronic equipment and storage medium | |
CN112150103B (en) | Schedule setting method, schedule setting device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |
|
RJ01 | Rejection of invention patent application after publication |