CN110299136A - A kind of processing method and its system for speech recognition - Google Patents
A kind of processing method and its system for speech recognition Download PDFInfo
- Publication number
- CN110299136A CN110299136A CN201810240495.3A CN201810240495A CN110299136A CN 110299136 A CN110299136 A CN 110299136A CN 201810240495 A CN201810240495 A CN 201810240495A CN 110299136 A CN110299136 A CN 110299136A
- Authority
- CN
- China
- Prior art keywords
- engine
- speech recognition
- speech
- confidence level
- meaning
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000004044 response Effects 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims 1
- 238000003860 storage Methods 0.000 description 13
- 235000013399 edible fruits Nutrition 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
- G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
- G10L15/197—Probabilistic grammars, e.g. word n-grams
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/221—Announcement of recognition results
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
- G10L2015/228—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of application context
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention provides a kind of processing methods of speech recognition, comprising: obtains the voice input of user;The usage scenario of user is judged based on the current application interface of user;The speech recognition engine used is determined based on above-mentioned usage scenario;The input of above-mentioned voice is identified using above-mentioned speech recognition engine, to obtain speech intention result;The highest speech intention result of confidence level is selected based on preset selection strategy;And the above-mentioned highest speech intention result of confidence level of output.The speech recognition processing system that the present invention also provides a kind of to realize above-mentioned processing method, the processing method and system of provided speech recognition according to the present invention, the result of speech recognition can be made more targetedly and more accurate, can also promote the response speed of speech recognition.
Description
Technical field
The present invention relates to speech recognition technology more particularly to the processing methods and its system of speech recognition.
Background technique
Universal with smart machine, the mode of human-computer interaction develops towards more and more convenient and fast direction, interactive voice compared with
Typewriting, mouse or touch screen control be a kind of more convenient mode, allow machine to understand human language, and respond and can make
Machine is preferably mankind's service.
But current interactive voice still has the problems such as response speed is slow, and identification is not accurate, and the voice for influencing user is known
Therefore other Experience Degree needs a kind of processing method for speech recognition, can strengthen the system layer to the judgement of speech recognition and
Distribution capability, to improve the response speed and precision of speech recognition.
Summary of the invention
A brief summary of one or more aspects is given below to provide to the basic comprehension in terms of these.This general introduction is not
The extensive overview of all aspects contemplated, and be both not intended to identify critical or decisive element in all aspects also non-
Attempt to define the range in terms of any or all.Its unique purpose is to provide the one of one or more aspects in simplified form
A little concepts are with the sequence for more detailed description given later.
It is slower to the processing response of speech recognition in the prior art in order to solve, and identify the not high problem of precision, this
Invention provides a kind of processing method for speech recognition, specifically includes: obtaining the voice input of user;It is current based on user
Application interface judge the usage scenario of user;The speech recognition engine used is determined based on above-mentioned usage scenario;Using above-mentioned
Speech recognition engine identifies the input of above-mentioned voice, to obtain speech intention result;It is selected based on preset selection strategy
The highest speech intention result of confidence level;And the above-mentioned highest speech intention result of confidence level of output.
Optionally, the usage scenario of above-mentioned judgement user further comprises: based on above-mentioned user currently without in specific
Application interface judge the usage scenario of above-mentioned user for generic scenario;Above-mentioned determining speech recognition engine further comprises: base
It is generic scenario in above-mentioned usage scenario, determines and use multiple speech recognition engines;And the step of above-mentioned identification, further wraps
It includes: the input of above-mentioned voice being identified using above-mentioned multiple speech recognition engines, to obtain multiple speech intention results.
Optionally, the step of above-mentioned selection speech intention result based on preset selection strategy further comprises: based on upper
State the meaning of one's words classification that multiple speech intention results determine above-mentioned voice input;Based on preset identification engine-meaning of one's words classification confidence
It spends table and determines the highest speech recognition engine of confidence level under above-mentioned meaning of one's words classification;And the above-mentioned highest voice of confidence level of selection
The speech intention result that identification engine is identified is as the highest speech intention result of confidence level.
Optionally, the step of meaning of one's words classification of above-mentioned determining voice input further comprises: determining each above-mentioned voice
It is intended to the meaning of one's words classification of result;The input of predicate sound is counted in each language based on above-mentioned identification engine-meaning of one's words classification confidence level meter
Confidence level total value under classification of anticipating;And determine that the meaning of one's words classification of above-mentioned voice input is the highest meaning of one's words class of confidence level total value
Not.
Optionally, the step of above-mentioned selection speech intention result based on preset selection strategy further comprises: according to pre-
If identification engine weight, successively judge the speech intention result and speech recognition engine that each speech recognition engine is identified
Matching degree;And matched in response to speech intention result with speech recognition engine, select above-mentioned speech recognition engine to be identified
Speech intention result be the highest speech intention result of confidence level.
Optionally, the step of judging matching degree further comprises: determining the meaning of one's words class of the speech intention result currently judged
Not;Determine the speech recognition engine that currently judges in the knowledge of above-mentioned meaning of one's words classification based on identification engine-meaning of one's words classification confidence level table
Other confidence level;And above-mentioned speech intention result matches with speech recognition engine and specifically includes above-mentioned recognition confidence higher than default
Matching confidence level.
Optionally, the usage scenario of above-mentioned judgement user further comprises: being currently at based on above-mentioned user and is specifically answered
The usage scenario that above-mentioned user is judged with interface is special scenes;Above-mentioned determining speech recognition engine further comprises: based on upper
Stating usage scenario is special scenes, and speech recognition engine used by determining draws to identify corresponding to the special sound of special scenes
It holds up;And above-mentioned the step of selecting speech intention result based on preset selection strategy, further comprises: in response to above-mentioned specific
Speech recognition engine identifies speech intention as a result, selecting above-mentioned speech intention result for the highest speech intention knot of confidence level
Fruit.
Optionally, above-mentioned specific application interface includes that user is in voice input interface, voice wakes up interface, navigation ground
Location input interface, selection contact person interface.
Optionally, above-mentioned speech recognition engine includes online engine, and/or, offline engine, the above method further wraps
It includes: obtaining the current network state of user;And the above-mentioned determining speech recognition engine used further comprises being made based on above-mentioned
Speech recognition engine is determined with scene and above-mentioned network state.
The present invention also provides a kind of processing systems of speech recognition, comprising: obtain module, judgment module, selecting module,
Output module and speech recognition engine;Wherein, above-mentioned acquisition module is inputted to obtain the voice of user;Above-mentioned judgment module is used
To judge the usage scenario of user based on the current application interface of user;And the voice used is determined based on above-mentioned usage scenario
Identify engine;Above-mentioned speech recognition engine is to identify the input of above-mentioned voice, to obtain speech intention result;Above-mentioned choosing
Module is selected to select the highest speech intention result of confidence level based on preset selection strategy;And above-mentioned output module to
Export the highest speech intention result of above-mentioned confidence level.
Optionally, above-mentioned judgment module judges above-mentioned user currently without in specific application interface based on above-mentioned user
Usage scenario be generic scenario;Above-mentioned judgment module determines that speech recognition engine further comprises: being based on above-mentioned usage scenario
For generic scenario, determines and use multiple speech recognition engines;And above-mentioned speech recognition engine identify and further comprises: on
It states multiple speech recognition engines to identify the input of above-mentioned voice, to obtain multiple speech intention results.
Optionally, above system further includes preset identification engine-meaning of one's words classification confidence level table;Wherein, above-mentioned judgement mould
Block further includes the meaning of one's words classification to determine above-mentioned voice input based on above-mentioned multiple speech intention results;Above-mentioned selecting module choosing
Selecting speech intention result further comprises: being determined based on above-mentioned identification engine-meaning of one's words classification confidence level table in above-mentioned meaning of one's words classification
The lower highest speech recognition engine of confidence level;And the voice meaning that the above-mentioned highest speech recognition engine of confidence level of selection is identified
Figure result is as the highest speech intention result of confidence level.
Optionally, above-mentioned judgment module determine voice input the meaning of one's words classification the step of further comprise: determine each
The meaning of one's words classification of above-mentioned speech intention result;The input of predicate sound is counted in based on above-mentioned identification engine-meaning of one's words classification confidence level meter
Confidence level total value under each meaning of one's words classification;And determine that the meaning of one's words classification of above-mentioned voice input is that confidence level total value is highest
Meaning of one's words classification.
Optionally, above system further includes preset identification engine weight table, wherein above-mentioned judgment module further includes basis
Above-mentioned identification engine weight table successively judges the speech intention that each speech recognition engine is identified by the weight of identification engine
As a result with the matching degree of speech recognition engine;And above-mentioned selecting module selection speech intention result further comprises: in response to
Speech intention result is matched with speech recognition engine, and the speech intention result for selecting above-mentioned speech recognition engine to be identified is confidence
Spend highest speech intention result.
Optionally, above system further includes preset identification engine-meaning of one's words classification confidence level table, above-mentioned judgment module judgement
Matching degree further comprises: determining the meaning of one's words classification of the speech intention result currently judged;Based on above-mentioned identification engine-meaning of one's words class
Recognition confidence of the determining speech recognition engine currently judged of other confidence level table in above-mentioned meaning of one's words classification;And above-mentioned voice meaning
Figure result is matched with speech recognition engine specifically includes above-mentioned recognition confidence higher than preset matching confidence level.
Optionally, above-mentioned judgment module is currently at specific application interface based on above-mentioned user and judges making for above-mentioned user
It is special scenes with scene;Above-mentioned judgment module determines that above-mentioned determining speech recognition engine further comprises: being based on above-mentioned use
Scene is special scenes, and speech recognition engine used by determining is the special sound identification engine corresponding to special scenes;With
And above-mentioned selecting module selection speech intention result further comprises: identifying voice in response to above-mentioned special sound identification engine
It is intended to as a result, selecting above-mentioned speech intention result for the highest speech intention result of confidence level.
Optionally, above-mentioned specific application interface includes that user is in voice input interface, voice wakes up interface, navigation ground
Location input interface, selection contact person interface.
Optionally, above-mentioned speech recognition engine includes online engine, and/or, offline engine, above-mentioned acquisition module further includes
Obtain the current network state of user;And above-mentioned judgment module determines that the speech recognition engine used further comprises being based on
Above-mentioned usage scenario and above-mentioned network state determine speech recognition engine.
The present invention also provides a kind of computer equipment, including memory, processor and storage are on a memory and can be
The computer program run on processor, wherein realize that the present invention such as mentions when above-mentioned processor executes above-mentioned computer program
For speech recognition processing method the step of.
The processing method of provided speech recognition according to the present invention, can judge the usage scenario of user, and select with
The relevant speech recognition engine of usage scenario reduces the time spent by speech recognition, and combines preset selection strategy
So that the result identified confidence level with higher, more targetedly and more accurate, effectively promote user and known using voice
Other Experience Degree.
Detailed description of the invention
Fig. 1 shows an embodiment flow chart of institute's providing method according to the present invention.
Fig. 2 shows preset identification one implementations of engine-meaning of one's words classification confidence level table of institute's providing method according to the present invention
It illustrates and is intended to.
Specific embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.Note that below in conjunction with attached drawing and specifically real
The aspects for applying example description is merely exemplary, and is understood not to carry out any restrictions to protection scope of the present invention.
It is slower to the processing response of speech recognition in the prior art in order to solve, and identify the not high problem of precision, this
Invention provides a kind of processing method for speech recognition, and Fig. 1 shows an embodiment of institute's providing method according to the present invention
Flow chart.As shown in Figure 1, method provided by the present invention specifically includes the voice input that step 110 obtains user, step 120
Judge that the usage scenario of user, step 130 determine that the voice used is known based on usage scenario based on the current application interface of user
Other engine, step 140 identifies voice input using speech recognition engine, to obtain speech intention as a result, step 150,
The highest voice of confidence level is exported based on the highest speech intention result of preset selection strategy selection confidence level and step 160
It is intended to result.
Specifically, being used in the usage scenario that step 120 application interface current based on user judges user by judgement
Family is currently either with or without the usage scenario for judging user in specific application interface.Further, specific application interface
It can be user and be currently at voice input interface, voice wake-up interface, navigation address input interface or selection contact person interface
Etc. preset specific application interface.
In one embodiment, step 120 judges that user is not on specific application interface, therefore user is thought in judgement
Usage scenario be generic scenario.In this embodiment, step 130 determines the speech recognition engine used based on usage scenario,
It further include being generic scenario based on usage scenario, determining and use multiple speech recognition engines, specifically, multiple voices
Identify that engine is preset correspondence not specific application scene, the multiple speech recognition engines to cover a wide range.In this embodiment
In, step 140 further comprises being identified voice input to obtain multiple speech intentions using multiple speech recognition engines
As a result, then executing step 150 is based on the preset selection strategy selection highest speech intention of confidence level as a result, then executing step
The rapid 160 output highest speech intention result of confidence level.
In the above-described embodiments, step 150 further comprises the language that voice input is determined based on multiple speech intention results
Meaning classification, then determines the confidence level under identified meaning of one's words classification according to preset identification engine-meaning of one's words classification confidence level table
Highest speech recognition engine, it is therefore contemplated that the speech intention knot that the highest speech recognition engine of above-mentioned confidence level is identified
Fruit is the highest speech intention of confidence level as a result, the final output speech intention result.
Further, the step of meaning of one's words classification of voice input is determined in above-mentioned steps 150 may include, according to multiple languages
Sound is intended to the meaning of one's words classification that result determines each speech intention result respectively, is set according to preset identification engine-meaning of one's words classification
Reliability meter calculates voice and inputs the confidence level total value under each meaning of one's words classification, and determines the highest meaning of one's words of confidence level total value
Classification is the meaning of one's words classification of voice input.
Fig. 2 shows preset identification one implementations of engine-meaning of one's words classification confidence level table of institute's providing method according to the present invention
It illustrates and is intended to.The specific processing method of above-described embodiment is illustrated below in conjunction with Fig. 2.As shown in Fig. 2, when judging user
When currently without being in specific application scenarios, using multiple identification engines: A, B, C, D are come to the voice input under generic scenario
It is identified.The meaning of one's words classification of each speech intention result is determined respectively, for example, after identifying again, obtained knowledge
Not the result is that the speech intention that identifies of identification engine A is the result is that meaning of one's words classification 5, confidence level 9;Identification engine B is identified
Speech intention is the result is that meaning of one's words classification 7, confidence level 7;The speech intention that identification engine C is identified is the result is that meaning of one's words classification 5, sets
Reliability is 10;The speech intention that identification engine D is identified is the result is that meaning of one's words classification 3, confidence level 7.Therefore the voice identified
Confidence level of the speech intention result of input in meaning of one's words classification 3 is 7 points, and the confidence level in meaning of one's words classification 5 is 19 points, in language
Confidence level in classification 7 of anticipating is 7 points, the confidence score highest in meaning of one's words classification 5, therefore, it is determined that the voice input identified
Speech intention result belongs to meaning of one's words classification 5, further, after determining meaning of one's words classification, determines the confidence level in meaning of one's words classification 5
The identification engine of highest scoring is identification engine C, therefore the speech intention result for just selecting identification engine C to be identified is as language
The output result of sound input is to export.
Provided method according to the present invention can judge the usage scenario of user in advance, thus the suitable identification of selection
Engine is classified under generic scenario further via to speech intention result, and carries out the side of confidence level judgement
Formula improves the accuracy of identification.
Judge that user is not in the embodiment of specific application interface in step 120, there is also another kinds to implement
Example judges to think the usage scenario of user as generic scenario in another embodiment.It further, is logical based on usage scenario
It with scene, determines and uses multiple speech recognition engines, specifically, multiple speech recognition engines are preset correspondence not specific application
Scene, the multiple speech recognition engines to cover a wide range.In this embodiment, step 140 further comprises using multiple languages
Sound identifies that engine identifies to obtain multiple speech intentions voice input as a result, then executing step 150 based on preset
Selection strategy selects the highest speech intention of confidence level as a result, then executing step 160 exports the highest speech intention of confidence level
As a result.
In the above-described embodiments, step 150 is based on preset selection strategy and selects the highest speech intention result of confidence level
It include further that the speech intention that each speech recognition engine is identified successively is judged according to preset identification engine weight
As a result it with the matching degree of speech recognition engine, and is matched with speech recognition engine in response to speech intention result, selects the language
The speech intention result that sound identification engine is identified is the highest speech intention result of confidence level.
Further, the step of judging matching degree further comprises, according to preset identification engine weight, successively judging
The meaning of one's words classification for the speech intention result that current identification engine is identified, is determined based on identification engine-meaning of one's words classification confidence level table
Recognition confidence of the current identification engine under the meaning of one's words classification judged, and, it is preset when the recognition confidence is more than or equal to
Matching confidence value when, it is believed that speech intention result is matched with speech recognition engine.
Fig. 2 shows preset identification one implementations of engine-meaning of one's words classification confidence level table of institute's providing method according to the present invention
It illustrates and is intended to.The specific processing method of above-described embodiment is illustrated below in conjunction with Fig. 2.As shown in Fig. 2, when judging user
When currently without being in specific application scenarios, using multiple identification engines: A, B, C, D are come to the voice input under generic scenario
It is identified.The default identification engine weight of the present invention is followed successively by engine A, engine B, engine C and engine D, preset matching
Confidence level be 8 points, therefore, successively judge the speech intention result that engine A is identified for classification 5, confidence level 9.Engine A at this time
The confidence level 9 of the classification 5 identified is greater than matching confidence level 8, therefore, it is considered that engine A and its speech intention result identified
Be it is matched, no longer judge the matching degree situation of other engines and speech intention result that directly output engine A is identified.
Provided method according to the present invention can judge the usage scenario of user in advance, thus the suitable identification of selection
Engine is classified under generic scenario further via to speech intention result, and carries out the side of confidence level judgement
Formula improves the accuracy of identification.And by the way of presetting weight to identification engine, by the way that suitable matching confidence level is arranged
Value, can guarantee the precision of speech recognition, while can accelerate the response time again.
Step 120 judged in the usage scenario of user based on the current application interface of user, when judging that user is in spy
Fixed application interface, such as can be user and be currently at voice input interface, voice wake-up interface, navigation address input interface
Or when the preset specific application interface such as selection contact person interface, step 130 further comprises being corresponded to based on usage scenario selection
Engine is identified in the special sound of the special scenes.Since user is in specific usage scenario, such as the input of navigation address
Interface, therefore identification user can be gone by the default specific speech recognition engine for being suitble to and being good at identification address class data
Voice input, identify as long as special sound identification engine can input the voice of user as a result, to default this specific
It is that speech recognition engine is identified the result is that confidence level is high, can correspondingly export the speech intention result.
Provided method according to the present invention selects special sound identification engine by presetting specific usage scenario
Mode can make the speech recognition result for corresponding to specific usage scenario more accurate, specifically use field judging that user is in
Jing Hou, can quick calling special sound identification engine identified, effectively improve efficiency.
Provided method according to the present invention, more specifically, identification engine further include presence online engine and/or
The offline engine of off-line state, more specifically, identification engine include at least online engine.Method provided by the present invention is further
Including obtaining the current network state of user, if current network state be it is online, according to above-mentioned method, preferentially select online
Engine carries out speech recognition.If current network state be it is offline, voice knowledge is carried out according to the offline engine of above-mentioned method choice
Not.
The present invention also provides a kind of processing system of speech recognition, including obtain module, judgment module, selecting module,
Output module and speech recognition engine input wherein obtaining module to obtain the voice of user;Judgment module is to based on use
The current application interface in family judges the usage scenario of user, and the speech recognition engine used is determined based on usage scenario;Language
Sound identifies engine to identify to voice input, to obtain speech intention result;Selecting module is to be based on preset choosing
Select the highest speech intention result of policy selection confidence level;And output module is to export the highest speech intention knot of confidence level
Fruit.
More specifically, acquisition module, judgment module, selecting module, output module and language that above-mentioned processing system is included
Sound identifies that the operating mode of engine illustrates that details are not described herein in method part provided by the present invention.
The processing system of provided speech recognition according to the present invention, can judge the usage scenario of user, and select with
The relevant speech recognition engine of usage scenario reduces the time spent by speech recognition, and combines preset selection strategy
So that the result identified confidence level with higher, more targetedly and more accurate, effectively promote user and known using voice
Other Experience Degree.
The present invention also provides a kind of computer equipment, including memory, processor and storage are on a memory and can be
The computer program run on processor, the processor realize the step in the above method when executing the computer program.Its
In, the specific implementation and technical effect of computer equipment can be found in the embodiment of above-mentioned voice recognition processing method,
This is repeated no more.
Those skilled in the art will further appreciate that, the various illustratives described in conjunction with the embodiments described herein
Logic plate, module, circuit and algorithm steps can be realized as electronic hardware, computer software or combination of the two.It is clear
Explain to Chu this interchangeability of hardware and software, various illustrative components, frame, module, circuit and step be above with
Its functional form makees generalization description.Such functionality be implemented as hardware or software depend on concrete application and
It is applied to the design constraint of total system.Technical staff can realize every kind of specific application described with different modes
Functionality, but such realization decision should not be interpreted to cause departing from the scope of the present invention.
In conjunction with presently disclosed embodiment describe various illustrative logic modules and circuit can with general processor,
Digital signal processor (DSP), specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic
Device, discrete door or transistor logic, discrete hardware component or its be designed to carry out any group of function described herein
It closes to realize or execute.General processor can be microprocessor, but in alternative, which can be any routine
Processor, controller, microcontroller or state machine.Processor is also implemented as calculating the combination of equipment, such as DSP
With the combination of microprocessor, multi-microprocessor, one or more microprocessors to cooperate with DSP core or any other this
Class configuration.
The step of method or algorithm for describing in conjunction with embodiment disclosed herein, can be embodied directly in hardware, in by processor
It is embodied in the software module of execution or in combination of the two.Software module can reside in RAM memory, flash memory, ROM and deposit
Reservoir, eprom memory, eeprom memory, register, hard disk, removable disk, CD-ROM or known in the art appoint
In the storage medium of what other forms.Exemplary storage medium is coupled to processor so that the processor can be from/to the storage
Medium reads and writees information.In alternative, storage medium can be integrated into processor.Pocessor and storage media can
It resides in ASIC.ASIC can reside in user terminal.In alternative, pocessor and storage media can be used as discrete sets
Part is resident in the user terminal.
In one or more exemplary embodiments, described function can be in hardware, software, firmware, or any combination thereof
Middle realization.If being embodied as computer program product in software, each function can be used as one or more item instructions or generation
Code may be stored on the computer-readable medium or be transmitted by it.Computer-readable medium includes computer storage medium and communication
Both media comprising any medium for facilitating computer program to shift from one place to another.Storage medium can be can quilt
Any usable medium of computer access.It is non-limiting as example, such computer-readable medium may include RAM, ROM,
EEPROM, CD-ROM or other optical disc storages, disk storage or other magnetic storage apparatus can be used to carrying or store instruction
Or data structure form desirable program code and any other medium that can be accessed by a computer.Any connection is also by by rights
Referred to as computer-readable medium.For example, if software is using coaxial cable, fiber optic cables, twisted pair, digital subscriber line
(DSL) or the wireless technology of such as infrared, radio and microwave etc is passed from web site, server or other remote sources
It send, then the coaxial cable, fiber optic cables, twisted pair, DSL or such as infrared, radio and microwave etc is wireless
Technology is just included among the definition of medium.Disk (disk) and dish (disc) as used herein include compression dish
(CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and blu-ray disc, which disk (disk) are often reproduced in a manner of magnetic
Data, and dish (disc) with laser reproduce data optically.Combinations of the above should also be included in computer-readable medium
In the range of.
Offer is to make any person skilled in the art all and can make or use this public affairs to the previous description of the disclosure
It opens.The various modifications of the disclosure all will be apparent for a person skilled in the art, and as defined herein general
Suitable principle can be applied to other variants without departing from the spirit or scope of the disclosure.The disclosure is not intended to be limited as a result,
Due to example described herein and design, but should be awarded and principle disclosed herein and novel features phase one
The widest scope of cause.
Claims (19)
1. a kind of processing method of speech recognition, comprising:
Obtain the voice input of user;
The usage scenario of user is judged based on the current application interface of user;
The speech recognition engine used is determined based on the usage scenario;
Voice input is identified using the speech recognition engine, to obtain speech intention result;
The highest speech intention result of confidence level is selected based on preset selection strategy;And
Export the highest speech intention result of the confidence level.
2. processing method as described in claim 1, which is characterized in that the usage scenario of the judgement user further comprises:
Judge the usage scenario of the user for generic scenario currently without in specific application interface based on the user;
The determining speech recognition engine further comprises: being generic scenario based on the usage scenario, determines and use multiple languages
Sound identifies engine;And
The step of identification, further comprises: voice input identified using the multiple speech recognition engine,
To obtain multiple speech intention results.
3. processing method as claimed in claim 2, which is characterized in that described to select speech intention based on preset selection strategy
As a result the step of, further comprises:
The meaning of one's words classification of the voice input is determined based on the multiple speech intention result;
Determine that the highest voice of confidence level is known under the meaning of one's words classification based on preset identification engine-meaning of one's words classification confidence level table
Other engine;And
The speech intention result for selecting the highest speech recognition engine of the confidence level to be identified is as the highest voice of confidence level
It is intended to result.
4. processing method as claimed in claim 3, which is characterized in that the step of the meaning of one's words classification of the determining voice input into
One step includes:
Determine the meaning of one's words classification of each speech intention result;
The voice, which is calculated, based on the identification engine-meaning of one's words classification confidence level meter inputs the confidence level under each meaning of one's words classification
Total value;And
The meaning of one's words classification for determining the voice input is the highest meaning of one's words classification of confidence level total value.
5. processing method as claimed in claim 2, which is characterized in that described to select speech intention based on preset selection strategy
As a result the step of, further comprises:
According to preset identification engine weight, the speech intention result and language that each speech recognition engine is identified successively are judged
The matching degree of sound identification engine;And
It is matched in response to speech intention result with speech recognition engine, the speech intention for selecting the speech recognition engine to be identified
It as a result is the highest speech intention result of confidence level.
6. processing method as claimed in claim 5, which is characterized in that the step of judging matching degree further comprises:
Determine the meaning of one's words classification of the speech intention result currently judged;
Determine the speech recognition engine that currently judges in the knowledge of the meaning of one's words classification based on identification engine-meaning of one's words classification confidence level table
Other confidence level;And
The speech intention result matched with speech recognition engine specifically include the recognition confidence be higher than it is preset matching set
Reliability.
7. processing method as described in claim 1, which is characterized in that the usage scenario of the judgement user further comprises:
Being currently at specific application interface based on the user judges the usage scenario of the user for special scenes;
The determining speech recognition engine further comprises: being special scenes, language used by determining based on the usage scenario
Sound identifies that engine is the special sound identification engine corresponding to special scenes;And
The step of selection speech intention result based on preset selection strategy, further comprises: in response to the special sound
Identification engine identifies speech intention as a result, selecting the speech intention result for the highest speech intention result of confidence level.
8. processing method as claimed in claim 7, which is characterized in that the specific application interface includes that user is in voice
Input interface, voice wake up interface, navigation address input interface, selection contact person interface.
9. such as processing method of any of claims 1-8, which is characterized in that the speech recognition engine includes online
Engine, and/or, offline engine, the method further includes:
Obtain the current network state of user;And
The determining speech recognition engine used further comprises determining language based on the usage scenario and the network state
Sound identifies engine.
10. a kind of processing system of speech recognition, comprising: obtain module, judgment module, selecting module, output module and voice
Identify engine;Wherein,
The voice input that module is obtained to obtain user;
Usage scenario of the judgment module to judge user based on the current application interface of user;And it is based on the use
Scene determines the speech recognition engine used;
The speech recognition engine is to identify voice input, to obtain speech intention result;
The selecting module is to select the highest speech intention result of confidence level based on preset selection strategy;And
The output module is to export the highest speech intention result of the confidence level.
11. processing system as claimed in claim 10, which is characterized in that the judgment module be based on the user currently without
Judge the usage scenario of the user for generic scenario in specific application interface;
The judgment module determines that speech recognition engine further comprises: being generic scenario based on the usage scenario, determination is adopted
With multiple speech recognition engines;And
The speech recognition engine carries out identification: the multiple speech recognition engine inputs the voice and carries out
Identification, to obtain multiple speech intention results.
12. processing system as claimed in claim 11, which is characterized in that the system also includes preset identification engine-languages
Meaning classification confidence level table;Wherein,
The judgment module further includes the meaning of one's words classification to determine the voice input based on the multiple speech intention result;
The selecting module selection speech intention result further comprises:
The highest speech recognition of confidence level under the meaning of one's words classification is determined based on the identification engine-meaning of one's words classification confidence level table
Engine;And
The speech intention result for selecting the highest speech recognition engine of the confidence level to be identified is as the highest voice of confidence level
It is intended to result.
13. processing system as claimed in claim 12, which is characterized in that the judgment module determines the meaning of one's words class of voice input
Other step further comprises:
Determine the meaning of one's words classification of each speech intention result;
The voice, which is calculated, based on the identification engine-meaning of one's words classification confidence level meter inputs the confidence level under each meaning of one's words classification
Total value;And
The meaning of one's words classification for determining the voice input is the highest meaning of one's words classification of confidence level total value.
14. processing system as claimed in claim 11, which is characterized in that the system also includes preset identification engine weights
Table, wherein
The judgment module further includes successively judging each language by the weight of identification engine according to the identification engine weight table
The matching degree of speech intention result and speech recognition engine that sound identification engine is identified;And
The selecting module selection speech intention result further comprises: in response to speech intention result and speech recognition engine
Match, the speech intention result for selecting the speech recognition engine to be identified is the highest speech intention result of confidence level.
15. processing system as claimed in claim 14, which is characterized in that the system also includes preset identification engine-languages
Meaning classification confidence level table, the judgment module judge that matching degree further comprises:
Determine the meaning of one's words classification of the speech intention result currently judged;
Determine the speech recognition engine currently judged in the meaning of one's words classification based on the identification engine-meaning of one's words classification confidence level table
Recognition confidence;And
The speech intention result matched with speech recognition engine specifically include the recognition confidence be higher than it is preset matching set
Reliability.
16. processing system as claimed in claim 10, which is characterized in that the judgment module is based on the user and is currently at
Specific application interface judges the usage scenario of the user for special scenes;
The judgment module determines that the determining speech recognition engine further comprises: being specific field based on the usage scenario
Scape, speech recognition engine used by determining are the special sound identification engine corresponding to special scenes;And
The selecting module selection speech intention result further comprises: identifying language in response to special sound identification engine
Sound is intended to as a result, selecting the speech intention result for the highest speech intention result of confidence level.
17. processing system as claimed in claim 16, it is characterised in that: the specific application interface includes that user is in language
Sound input interface, voice wake up interface, navigation address input interface, selection contact person interface.
18. the processing system as described in any one of claim 10-17, which is characterized in that the speech recognition engine includes
Online engine, and/or, offline engine, the module that obtains further includes obtaining the current network state of user;And
The judgment module determines that the speech recognition engine used further comprises, based on the usage scenario and described network-like
State determines speech recognition engine.
19. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor is realized when executing the computer program such as any one of claim 1-9 institute
The step of stating method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810240495.3A CN110299136A (en) | 2018-03-22 | 2018-03-22 | A kind of processing method and its system for speech recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810240495.3A CN110299136A (en) | 2018-03-22 | 2018-03-22 | A kind of processing method and its system for speech recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110299136A true CN110299136A (en) | 2019-10-01 |
Family
ID=68025589
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810240495.3A Pending CN110299136A (en) | 2018-03-22 | 2018-03-22 | A kind of processing method and its system for speech recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110299136A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110956955A (en) * | 2019-12-10 | 2020-04-03 | 苏州思必驰信息科技有限公司 | Voice interaction method and device |
CN111049996A (en) * | 2019-12-26 | 2020-04-21 | 苏州思必驰信息科技有限公司 | Multi-scene voice recognition method and device and intelligent customer service system applying same |
CN111933118A (en) * | 2020-08-17 | 2020-11-13 | 苏州思必驰信息科技有限公司 | Method and device for optimizing voice recognition and intelligent voice dialogue system applying same |
CN112787899A (en) * | 2021-01-08 | 2021-05-11 | 青岛海尔特种电冰箱有限公司 | Equipment voice interaction method, computer readable storage medium and refrigerator |
CN112786055A (en) * | 2020-12-25 | 2021-05-11 | 北京百度网讯科技有限公司 | Resource mounting method, device, equipment, storage medium and computer program product |
CN112861542A (en) * | 2020-12-31 | 2021-05-28 | 思必驰科技股份有限公司 | Method and device for limiting scene voice interaction |
WO2021135561A1 (en) * | 2019-12-31 | 2021-07-08 | 思必驰科技股份有限公司 | Skill voice wake-up method and apparatus |
CN113327602A (en) * | 2021-05-13 | 2021-08-31 | 北京百度网讯科技有限公司 | Method and device for speech recognition, electronic equipment and readable storage medium |
CN113380254A (en) * | 2021-06-21 | 2021-09-10 | 紫优科技(深圳)有限公司 | Voice recognition method, device and medium based on cloud computing and edge computing |
CN113380253A (en) * | 2021-06-21 | 2021-09-10 | 紫优科技(深圳)有限公司 | Voice recognition system, device and medium based on cloud computing and edge computing |
WO2022057152A1 (en) * | 2020-09-18 | 2022-03-24 | 广州橙行智动汽车科技有限公司 | Voice interaction method, server, and computer-readable storage medium |
CN113380254B (en) * | 2021-06-21 | 2024-05-24 | 枣庄福缘网络科技有限公司 | Voice recognition method, device and medium based on cloud computing and edge computing |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB0407900D0 (en) * | 2004-04-07 | 2004-05-12 | Mitel Networks Corp | Method and apparatus for improving hands-free speech recognition using beamforming technology |
WO2006037219A1 (en) * | 2004-10-05 | 2006-04-13 | Inago Corporation | System and methods for improving accuracy of speech recognition |
CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
US20110144986A1 (en) * | 2009-12-10 | 2011-06-16 | Microsoft Corporation | Confidence calibration in automatic speech recognition systems |
CN102708865A (en) * | 2012-04-25 | 2012-10-03 | 北京车音网科技有限公司 | Method, device and system for voice recognition |
CN102800313A (en) * | 2011-05-25 | 2012-11-28 | 上海先先信息科技有限公司 | Method for supporting multi-voice recognition engine in Voice extensible markup language (XML) 2.0 |
CN102831157A (en) * | 2012-07-04 | 2012-12-19 | 四川长虹电器股份有限公司 | Semanteme recognition and search method and system |
US20130132086A1 (en) * | 2011-11-21 | 2013-05-23 | Robert Bosch Gmbh | Methods and systems for adapting grammars in hybrid speech recognition engines for enhancing local sr performance |
CN103440867A (en) * | 2013-08-02 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for recognizing voice |
CN104795069A (en) * | 2014-01-21 | 2015-07-22 | 腾讯科技(深圳)有限公司 | Speech recognition method and server |
US20150348539A1 (en) * | 2013-11-29 | 2015-12-03 | Mitsubishi Electric Corporation | Speech recognition system |
CN105719649A (en) * | 2016-01-19 | 2016-06-29 | 百度在线网络技术(北京)有限公司 | Voice recognition method and device |
US20160358606A1 (en) * | 2015-06-06 | 2016-12-08 | Apple Inc. | Multi-Microphone Speech Recognition Systems and Related Techniques |
CN106328148A (en) * | 2016-08-19 | 2017-01-11 | 上汽通用汽车有限公司 | Natural speech recognition method, natural speech recognition device and natural speech recognition system based on local and cloud hybrid recognition |
US20170140759A1 (en) * | 2015-11-13 | 2017-05-18 | Microsoft Technology Licensing, Llc | Confidence features for automated speech recognition arbitration |
CN106710586A (en) * | 2016-12-27 | 2017-05-24 | 北京智能管家科技有限公司 | Speech recognition engine automatic switching method and device |
-
2018
- 2018-03-22 CN CN201810240495.3A patent/CN110299136A/en active Pending
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB0407900D0 (en) * | 2004-04-07 | 2004-05-12 | Mitel Networks Corp | Method and apparatus for improving hands-free speech recognition using beamforming technology |
WO2006037219A1 (en) * | 2004-10-05 | 2006-04-13 | Inago Corporation | System and methods for improving accuracy of speech recognition |
US20110144986A1 (en) * | 2009-12-10 | 2011-06-16 | Microsoft Corporation | Confidence calibration in automatic speech recognition systems |
CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
CN102800313A (en) * | 2011-05-25 | 2012-11-28 | 上海先先信息科技有限公司 | Method for supporting multi-voice recognition engine in Voice extensible markup language (XML) 2.0 |
US20130132086A1 (en) * | 2011-11-21 | 2013-05-23 | Robert Bosch Gmbh | Methods and systems for adapting grammars in hybrid speech recognition engines for enhancing local sr performance |
CN102708865A (en) * | 2012-04-25 | 2012-10-03 | 北京车音网科技有限公司 | Method, device and system for voice recognition |
CN102831157A (en) * | 2012-07-04 | 2012-12-19 | 四川长虹电器股份有限公司 | Semanteme recognition and search method and system |
CN103440867A (en) * | 2013-08-02 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for recognizing voice |
US20150348539A1 (en) * | 2013-11-29 | 2015-12-03 | Mitsubishi Electric Corporation | Speech recognition system |
CN104795069A (en) * | 2014-01-21 | 2015-07-22 | 腾讯科技(深圳)有限公司 | Speech recognition method and server |
US20160358606A1 (en) * | 2015-06-06 | 2016-12-08 | Apple Inc. | Multi-Microphone Speech Recognition Systems and Related Techniques |
US20170140759A1 (en) * | 2015-11-13 | 2017-05-18 | Microsoft Technology Licensing, Llc | Confidence features for automated speech recognition arbitration |
CN105719649A (en) * | 2016-01-19 | 2016-06-29 | 百度在线网络技术(北京)有限公司 | Voice recognition method and device |
CN106328148A (en) * | 2016-08-19 | 2017-01-11 | 上汽通用汽车有限公司 | Natural speech recognition method, natural speech recognition device and natural speech recognition system based on local and cloud hybrid recognition |
CN106710586A (en) * | 2016-12-27 | 2017-05-24 | 北京智能管家科技有限公司 | Speech recognition engine automatic switching method and device |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110956955A (en) * | 2019-12-10 | 2020-04-03 | 苏州思必驰信息科技有限公司 | Voice interaction method and device |
CN110956955B (en) * | 2019-12-10 | 2022-08-05 | 思必驰科技股份有限公司 | Voice interaction method and device |
CN111049996A (en) * | 2019-12-26 | 2020-04-21 | 苏州思必驰信息科技有限公司 | Multi-scene voice recognition method and device and intelligent customer service system applying same |
US11721328B2 (en) | 2019-12-31 | 2023-08-08 | Ai Speech Co., Ltd. | Method and apparatus for awakening skills by speech |
WO2021135561A1 (en) * | 2019-12-31 | 2021-07-08 | 思必驰科技股份有限公司 | Skill voice wake-up method and apparatus |
CN111933118A (en) * | 2020-08-17 | 2020-11-13 | 苏州思必驰信息科技有限公司 | Method and device for optimizing voice recognition and intelligent voice dialogue system applying same |
WO2022057152A1 (en) * | 2020-09-18 | 2022-03-24 | 广州橙行智动汽车科技有限公司 | Voice interaction method, server, and computer-readable storage medium |
CN112786055A (en) * | 2020-12-25 | 2021-05-11 | 北京百度网讯科技有限公司 | Resource mounting method, device, equipment, storage medium and computer program product |
CN112861542A (en) * | 2020-12-31 | 2021-05-28 | 思必驰科技股份有限公司 | Method and device for limiting scene voice interaction |
CN112861542B (en) * | 2020-12-31 | 2023-05-26 | 思必驰科技股份有限公司 | Method and device for voice interaction in limited scene |
CN112787899B (en) * | 2021-01-08 | 2022-10-28 | 青岛海尔特种电冰箱有限公司 | Equipment voice interaction method, computer readable storage medium and refrigerator |
CN112787899A (en) * | 2021-01-08 | 2021-05-11 | 青岛海尔特种电冰箱有限公司 | Equipment voice interaction method, computer readable storage medium and refrigerator |
CN113327602A (en) * | 2021-05-13 | 2021-08-31 | 北京百度网讯科技有限公司 | Method and device for speech recognition, electronic equipment and readable storage medium |
CN113380253A (en) * | 2021-06-21 | 2021-09-10 | 紫优科技(深圳)有限公司 | Voice recognition system, device and medium based on cloud computing and edge computing |
CN113380254A (en) * | 2021-06-21 | 2021-09-10 | 紫优科技(深圳)有限公司 | Voice recognition method, device and medium based on cloud computing and edge computing |
CN113380254B (en) * | 2021-06-21 | 2024-05-24 | 枣庄福缘网络科技有限公司 | Voice recognition method, device and medium based on cloud computing and edge computing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110299136A (en) | A kind of processing method and its system for speech recognition | |
JP7297836B2 (en) | Voice user interface shortcuts for assistant applications | |
CN110770736B (en) | Exporting dialog-driven applications to a digital communication platform | |
CN106486120B (en) | Interactive voice response method and answering system | |
CN105575386B (en) | Audio recognition method and device | |
CN103995716B (en) | A kind of terminal applies startup method and terminal | |
CN110491383A (en) | A kind of voice interactive method, device, system, storage medium and processor | |
US11727939B2 (en) | Voice-controlled management of user profiles | |
CN109428719A (en) | A kind of auth method, device and equipment | |
CN109522083A (en) | A kind of intelligent page response interactive system and method | |
CN109658579A (en) | A kind of access control method, system, equipment and storage medium | |
CN110459222A (en) | Sound control method, phonetic controller and terminal device | |
CN107909998A (en) | Phonetic order processing method, device, computer equipment and storage medium | |
CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
CN109688036A (en) | A kind of control method of intelligent appliance, device, intelligent appliance and storage medium | |
CN109065040A (en) | A kind of voice information processing method and intelligent electric appliance | |
CN111312230B (en) | Voice interaction monitoring method and device for voice conversation platform | |
US11538464B2 (en) | Speech recognition using data analysis and dilation of speech content from separated audio input | |
CN109741737A (en) | A kind of method and device of voice control | |
CN111161726B (en) | Intelligent voice interaction method, device, medium and system | |
JP7436077B2 (en) | Skill voice wake-up method and device | |
CN110797031A (en) | Voice change detection method, system, mobile terminal and storage medium | |
CN112634897B (en) | Equipment awakening method and device, storage medium and electronic device | |
CN111462741A (en) | Voice data processing method, device and storage medium | |
US20200092322A1 (en) | VALIDATING COMMANDS FOR HACKING AND SPOOFING PREVENTION IN AN INTERNET OF THINGS (IoT) COMPUTING ENVIRONMENT |
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 |