CN106055605A - Voice interaction control method and apparatus thereof - Google Patents
Voice interaction control method and apparatus thereof Download PDFInfo
- Publication number
- CN106055605A CN106055605A CN201610353529.0A CN201610353529A CN106055605A CN 106055605 A CN106055605 A CN 106055605A CN 201610353529 A CN201610353529 A CN 201610353529A CN 106055605 A CN106055605 A CN 106055605A
- Authority
- CN
- China
- Prior art keywords
- play
- voice
- answer
- prompt tone
- control method
- 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 37
- 230000003993 interaction Effects 0.000 title abstract description 13
- 230000035699 permeability Effects 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 abstract description 19
- 239000000047 product Substances 0.000 description 16
- 241001465754 Metazoa Species 0.000 description 12
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 241000283690 Bos taurus Species 0.000 description 1
- 241000282421 Canidae Species 0.000 description 1
- 206010020112 Hirsutism Diseases 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 244000038280 herbivores Species 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000000366 juvenile effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 244000144977 poultry Species 0.000 description 1
- 244000062645 predators Species 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention discloses a voice interaction control method and an apparatus thereof. The voice interaction control method comprises: A, taking and playing start reminding voice, and randomly taking and playing a main classification problem; B, collecting voice of a user and recognizing an answer type, and determining whether to skip to other problems of the same grade or to enter a next stage problem according to the answer type; C, determining whether the problem required to be proposed is a name locking problem, if so, playing the name locking problem, and executing a step D, and if not, taking and playing the problem reminding voice corresponding to the problem, and returning the step B; D, determining whether the answer type of the collected voice is a positive response, if so, playing end reminding voice, and if not, executing a step E; and E, randomly taking and playing other name locking problems having the same kind with the name locking problem, and returning the step D. The corresponding problem and interactive reminding voice can be played according to the answer of the user, complex voice interaction application can be achieved, and the problem that an existing child voice interaction product can only perform forward single interaction can be solved.
Description
Technical field
The present invention relates to electronic technology, particularly to a kind of voice interface control method and device thereof.
Background technology
Children speech interactive product in the market all uses " instruction " interaction mode.Such as: user sends together
Phonetic order " sings bar song to me ", and device judges by being received voice identifying, finally corresponding according to procedure Selection
Audio frequency or functional control module feed back (playback of songs) accordingly.This kind of interactive product (includes the intelligent robot of primary)
Can be regarded as the single pass interaction mode of forward.I.e. input information → device and obtain information → provide the corresponding feedback of instruction.
Interactive class juvenile product is both provided with preset instructions storehouse, needs to ensure that instruction must be preset instructions when user uses
Existing information in storehouse, otherwise product will not make any reaction.If the instruction acquisition in preset instructions storehouse is improved not or uses
There is any discrepancy for the information of family input and the information matches in preset instructions storehouse, then product cannot realize the effect of interaction.Therefore, market
Upper existing interactive series products is faced with the problem that interactive sensitivity is the highest substantially, and meanwhile, the mode of this forward list interaction is deposited
In monotonicity.
Therefore prior art existing defects, haves much room for improvement.
Summary of the invention
In place of above-mentioned the deficiencies in the prior art, it is an object of the invention to provide a kind of voice interface control method and
Its device, with solve existing children speech interactive product can only the interactive problem of forward list.
In order to achieve the above object, this invention takes techniques below scheme:
A kind of voice interface control method, comprising:
Step A, transfer beginning prompt tone playing, transfer a Main classification problem at random and play;
Step B, the voice of collection user also identify answer type, judge it is to jump to other ad eundems ask according to answer type
Topic or entrance next stage problem;
Whether the problem that step C, judgement need to propose is title lockout issue: is then to play title lockout issue, performs step D;
Otherwise transfer problem clew sound corresponding to this problem and play, returning step B;
Whether the answer type of the voice that step D, judgement are gathered is affirmative acknowledgement (ACK), is then to play to terminate prompt tone, otherwise holds
Row step E;
Step E, transfer other similar title lockout issues of this title lockout issue and play at random, return step D.
In described voice interface control method, described answer type includes: affirmative acknowledgement (ACK), negative acknowledge and uncertain time
Answer;
Described Main classification problem has some, each corresponding some the disaggregated classification problems of Main classification problem;Disaggregated classification problem is divided
For n level, n is positive integer;Each corresponding some the one-level disaggregated classification problems of Main classification problem, each one-level disaggregated classification problem
Corresponding some two grades of disaggregated classification problems, by that analogy, each corresponding some the n level disaggregated classifications of n-1 level disaggregated classification problem are asked
Topic;Each corresponding some the title lockout issues of n level disaggregated classification problem;
The grade of Main classification problem is the highest, and disaggregated classification problem is taken second place, and the grade of title lockout issue is minimum.
In described voice interface control method, described step A specifically includes:
When step A1, start, transfer the first beginning prompt tone and play;
Step A2, the voice of collection user also identify when answer is affirmative acknowledgement (ACK), play the second beginning prompt tone;
Step A3, second start prompt tone play after wait Preset Time, transfer a Main classification problem at random and play.
In described voice interface control method, described step A2 specifically includes:
A21, play a follow-up prompts sound every the time of setting, until collecting the voice of user and identifying that answer is for affirm back
Stop when answering, play the second beginning prompt tone;
A22, play preset times continuously when follow-up prompts sound, then play shutdown prompt tone.
In described voice interface control method, in described step B, identify when answer type is affirmative acknowledgement (ACK), enter
The next stage problem of this classification problem;If identifying negative acknowledge or uncertain answer, then select this classification problem ad eundem its
His classification problem;Uncertain answer also records this classification problem and is labeled as blank.
In described voice interface control method, described step D specifically includes:
Step D1, collection identify the voice of user, it is judged that whether answer type is affirmative acknowledgement (ACK): be then to play to terminate prompt tone,
Perform step D2;Otherwise perform step E;
Step D2, collection identify the voice of user, it is judged that whether answer type is affirmative acknowledgement (ACK): be then to return step A;Otherwise broadcast
Put and exit prompt tone, automatic shutdown.
In described voice interface control method, in described step B ~ step E, if belong to same branch all on an equal basis
The classification problem of level is all marked as blank, or counts on the blank of more than 10, then be judged as that logical contradiction or answer obscures,
Transfer warning prompt sound and play.
In described voice interface control method, in described step B ~ step E, if under two disaggregated classification problems of statistics
During all title lockout issue all negative acknowledges, transfer and heavily carry out prompt tone and play.
A kind of voice interface realizing described voice interface control method controls device, it include main control module, internal memory,
Miaow head and loudspeaker;
Described main control module is transferred beginning prompt tone from internal memory and is play by loudspeaker, transfers a Main classification problem at random also
Play;Miaow head gathers the voice of user and is transferred to main control module identification answer type, judges it is to jump to according to answer type
Other ad eundem problems or entrance next stage problem;
Whether the problem that master control module judges need to propose is title lockout issue: be, transfers title lockout issue also from internal memory
Play by loudspeaker;Otherwise transfer problem clew sound corresponding to this problem and play, continuing gather the voice of user and identify back
Answer type, judge select permeability according to answer type;
Main control module is after playing title lockout issue, it is judged that whether the answer type of the voice gathered is affirmative acknowledgement (ACK), is
Then play and terminate prompt tone;Transfer other similar title lockout issues of this title lockout issue the most at random and play, continuing
Judge the answer type after playing title lockout issue.
Compared to prior art, a kind of voice interface control method of present invention offer and device thereof, voice interface controls
Method includes: step A, transfer beginning prompt tone playing, and transfers a Main classification problem at random and plays;Step B, collection are used
The voice at family also identifies answer type, judges jump to other ad eundem problems or enter next stage according to answer type
Problem;Whether the problem that step C, judgement need to propose is title lockout issue: is then to play title lockout issue, performs step D;
Otherwise transfer problem clew sound corresponding to this problem and play, returning step B;The answer class of the voice that step D, judgement are gathered
Whether type is affirmative acknowledgement (ACK), is then to play to terminate prompt tone, otherwise performs step E;Step E, at random transfer this title locking ask
Inscribe other similar title lockout issues and play, returning step D.Corresponding problem and interaction can be play according to answering of user
Prompt tone, complete the interactive voice application of complexity, solve existing children speech interactive product can only forward list interactive
Problem.
Accompanying drawing explanation
Fig. 1 is the structured flowchart of voice interface control method flow chart device of the present invention.
Fig. 2 is the relation schematic diagram in voice interface control method of the present invention between each problem.
Fig. 3 is the structured flowchart that voice interface of the present invention controls device.
Detailed description of the invention
The present invention provides a kind of voice interface control method and device thereof, it is adaptable in children speech interactive product.For making
The purpose of the present invention, technical scheme and effect are clearer, clear and definite, and the embodiment that develops simultaneously referring to the drawings is further to the present invention
Describe in detail.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Referring to Fig. 1, the voice interface control method that the present invention provides includes:
S100, transfer beginning prompt tone playing, transfer a Main classification problem at random and play;
S200, the voice gathering user also identify answer type, according to answer type judge be jump to other ad eundem problems,
Or enter next stage problem;
Whether the problem that S300, judgement need to propose is title lockout issue: is then to play title lockout issue, performs step
S400;Otherwise transfer problem clew sound corresponding to this problem and play, returning step S200;
Whether the answer type of the voice that S400, judgement are gathered is affirmative acknowledgement (ACK), is then to play to terminate prompt tone, otherwise performs
Step S500;
S500, transfer other similar title lockout issues of this title lockout issue and play at random, return step S400.
In the step s 100, when user is started shooting by button, transfer the first beginning prompt tone and play.Described beginning carries
Showing that sound is preset to record, prompting user guesses animal, food or other objects (such as small stores, furniture appliance etc.), the present embodiment
As a example by guessing animal, then starting prompt tone can be: " hello for child, and I is your magic power partner, and we do together and guess a riddle trip
Play.Answer I problem I can guess out the animal that your psychology is thought!If you are all set, just tell me OK ".
Whether be " OK " of affirmative acknowledgement (ACK), be then to play the second beginning prompt tone, prompting game if gathering the voice of user identifying and answer
Formally start, as " please quietly deciding an animal in psychology, when I starts to put question to, you only need to answer my yes, no or not
Know, it may also be said to not necessarily ".
In the specific implementation, interactive in order to increase, the present embodiment starts prompt tone, second starts prompt tone first
Content is not construed as limiting, and can arrange a plurality of random call, to avoid user to feel dull.Second starts prompt tone mainly allows user
Understand, only need to answer " be or yes, be not or no, do not know, not necessarily " these four and answer, to facilitate subsequent speech recognition.With
Family gathers its voice and identifies answer type after answering, and answer type includes the affirmative acknowledgement (ACK) that " being or yes " is corresponding, " be not or
No " corresponding negative acknowledge, the uncertain answer that " not knowing, not necessarily " is corresponding.
After first starts prompt tone broadcasting, this product is in game readiness, can play follow-up prompts sound the most every few seconds,
As " I does not catches, and can say again?", until recognizing " OK " voice to confirm that game starts.Work as follow-up prompts
Sound is pointed out more than 4 times continuously, then judge that user leaves, and the most automatically terminates this game (i.e. shutdown).During game over (shutdown)
Play shutdown prompt tone, such as " the happiest with what you played, we play next time again ".Follow-up prompts sound and shutdown prompt tone also may be used
Do several shuffle to avoid monotony more.
Start to wait Preset Time (2 seconds), one Main classification problem of shuffle after prompt tone is play second.Although mesh
The animal classification method of front existing relatively science, but its mode classification is more dull and barren.This voice interface control method is main
In children speech interactive product, therefore classification problem is in the way of child readily appreciates.
Relation between described Main classification problem, disaggregated classification problem, title lockout issue as in figure 2 it is shown, wherein a, b, c,
D, e, f, g, h are positive integer, and value can be equal or different, represent that the bar number of the problem arranged in Mei Tiao branch can be equal
Or be not desired to.I.e. Main classification problem has some (Main classification problem 1 ~ Main classification problems a, at least 10), for the first estate,
It is main being configured with distinguishing features such as animal build, living environment, macroscopic features (such as whether having wing, scale, hair), its etc.
Level is the highest, can be that " it lives in land?", " it is lived in the sea?", " it can fly?", " it is Amphibian
??", " it has scale?", " its hairiness?" etc..
Disaggregated classification problem is to make a distinction, and the details for animal describes.Disaggregated classification problem can be further divided into n level, and n is just
Integer.Each corresponding (the most down branching into) some one-level disaggregated classification problems of Main classification problem, each one-level disaggregated classification
Corresponding some the two grades of disaggregated classification problems of problem, by that analogy, each n-1 level disaggregated classification problem corresponding some n levels segmentation
Class problem;Each corresponding some the title lockout issues of n level disaggregated classification problem.The name of the described i.e. animal of title lockout issue
Claim.Main classification problem magnitude is the highest, and one-level disaggregated classification problem is taken second place, two grades of disaggregated classification problems third, title lockout issue etc.
Level is minimum.
Fig. 2, as a example by two-stage, is not construed as limiting when being embodied as.If Main classification problem 1 is for " it lives in land?",
The one-level disaggregated classification problem of its correspondence can be that " it is two feet?", " it is four feet?", " it has vertebra?" etc..
If one-level disaggregated classification problem 1 is for " it is four feet?", then two grades of corresponding disaggregated classification problems can be that " it is carnivore
??", " it is herbivore?", " it is poultry?", " it is Canidae?" etc..If two grades of disaggregated classification problems 1 are for " it is
Domestic animal?", then corresponding title lockout issue is for " it is horse?", " it is cattle?", " it is sheep?" etc..All problems
Setting and context dispatch from the factory before in advance editor arrange, there is certain logic and the tendency understandable language of child.
It addition, when specifically puing question to, the random combine of segmentation voice can be carried out, such as: " this animal that you think " combines
" it has wing " or directly enquirement " it has wing ".The appearance of random combine can make the enquirement of product will not be the most stiff.
In step s 200, as long as obtaining affirmative acknowledgement (ACK), it is put into the next stage problem of this classification problem.If negating back
Answer or uncertain answer, then select other classification problems of this classification problem ad eundem.Uncertain answer also records this classification and asks
Inscribe and be labeled as blank.If the classification problem belonging to all ad eundems of same branch is collectively labeled as blank, or counts on altogether
Article 10, the blank (from the blank of different brackets problem) more than, then be judged as logical contradiction or answer fuzzy, then transferring warning
Prompt tone is also play, such as " child, the most carefully to answer, and not so my magic power can be wasted by you ".
When Main classification problem obtains affirmative acknowledgement (ACK), the one-level disaggregated classification problem of its correspondence can be entered.When Main classification is asked
When topic obtains negative acknowledge, jump to other ad eundem problems, transfer another Main classification problem of broadcasting the most at random.When main point
When class problem obtains uncertain answer, record attribute is blank, now can another Main classification problem of shuffle.In like manner, when one
When level disaggregated classification problem obtains affirmative acknowledgement (ACK), two grades of disaggregated classification problems of its correspondence can be entered.When one-level disaggregated classification problem obtains
During to negative acknowledge or uncertain answer, jumping to other one-level disaggregated classification problems, during uncertain answer, going back this one-level of labelling
Disaggregated classification problem is blank.
Disaggregated classification problem is the emphasis putd question to, and device acquiescence selects wherein answer attributes " YES " and the existence ratio of " NO "
Problem as close as 5:5 is putd question to, and in other words, preferentially selects the disaggregated classification problem that answer is contrary attribute and carries out
Put question to.To ensure to get rid of ineligible animal as far as possible, answer is allowed to be locked in as early as possible in certain little scope.
In step S300, during a selected problem that need to propose, need to judge that whether it is the title locking of the lowest class
Problem, is not to represent and still need to judge, directly transfer the problem clew sound of its correspondence and play, is then back to step S200 and continues
Obtain the voice of user and judge.
If title lockout issue, then it represents that enter and finally determine link, transfer this title lockout issue and play.Then
Step S400 need to be performed, gather the voice identifying user, it is judged that whether answer type is affirmative acknowledgement (ACK), is, represent and hit it,
Play and terminate prompt tone, as " my magic power is the most magical, more how comes one innings?”.Now continue gather the voice of user and know
Other answer type, if affirmative acknowledgement (ACK), then returns step S100 and has again.If negative acknowledge, then wait and play and exit
Prompt tone, as " with you play the happiest, we play next time again ", if user's affirmative acknowledgement (ACK), then automatic shutdown;If user negates
Answer, then play and terminate prompt tone, again judge whether to continue play under game.If the voice according to user repeats playing for continuous 4 times
Terminate prompt tone and exit prompt tone, then automatic shutdown.
If it is wrong that user answers this answer, then performs step S500, transfer similar its of this title lockout issue at random
His title lockout issue also plays (i.e. other title lockout issues and this title lockout issue belongs to same disaggregated classification problem), returns
Return step S400 to continue to judge that answer is the most correct.When other all title lockout issues corresponding to this title lockout issue all by
During negative, device calls return prompt tone, and such as " you are the most severe, and I also needs to ask you several interesting problems ", playing after 2 seconds should
The disaggregated classification problem of the upper level that title lockout issue is corresponding, returns step S200 and continues to gather phonetic decision.
If to all title lockout issues under two disaggregated classification problems negating all, then transfer broadcasting and heavily point out
Sound, as " you are that I met the friend of wisdom, and I run out of my magic power, and you win!We heavily come once the most not?”.Negative
Answer (disagreeing) is then play and is exited prompt tone, and the second beginning prompt tone is then play in affirmative acknowledgement (ACK) (agreement), restarts.
In the specific implementation, in interacting Question-Answer is played, for promoting interest, can suitably intert the interaction of some voices.
After playing continuously 3 or 5 problems, can play and praise prompt tone, such as " answer excellent, I to make great efforts a little better " again.When
When being played to title lockout issue, can be inserted into prompt tone of speaking to oneself, such as " my magic power is abundant, just can sense " at once.It addition,
When playing title lockout issue, can (" it be horse at original title lockout issue?") the interactive statement of middle increase, such as " I
Magic power breaks out, and I guesses that the animal that you think is horse, and is it right?”.
When the answer of absolute contradiction occurs in logical judgment, if two answer attributes are contrary, but with answering per family it is,
Then transfer and play prompting prompt tone, such as " the most noisy, conscientiously OK ".And continue the problem etc. puing question to answer attributes close
Treat that user answers.Above-mentioned each classification problem shuffle is to make child feel nothing in order to avoid playing identical problem every time
Interest.
Described answer type also includes that requirement is answered, and during answering in above-mentioned enquirement, asks if user does not catch
Topic, it is desirable to listen once, then user can answer " not catching " or " saying once again " again, then speech recognition is answered for request, this product
Product will repeat playing current problem.
If in interactive game, return clearly owing to environment noise or other reasons cause this product could not get user
Answer, cannot speech recognition judge in the case of, then playing request prompt tone, as " your answer has point fuzziness, and it is good that please say it again
??” .
Based on above-mentioned voice interface control method, the present invention correspondingly provides a kind of voice interface and controls device.Please join
Readding Fig. 3, the voice interface that the present invention provides controls device and is arranged in children speech interactive product, it include main control module 10,
Internal memory 20, miaow head 30 and loudspeaker 40.From internal memory 20, transfer beginning prompt tone when described main control module 10 detects start and lead to
Cross loudspeaker 40 to play, transfer a Main classification problem at random and play;Miaow head 30 gathers the voice of user and is transferred to master control mould
Block identification answer type, judges jump to other ad eundem problems or enter next stage problem according to answer type.
Whether the problem that master control module judges need to propose is title lockout issue: be, transfers title locking and ask from internal memory
Inscribe and play by loudspeaker;Otherwise transfer problem clew sound corresponding to this problem and play, continuing gather the voice of user and know
Other answer type, judges select permeability according to answer type.
Main control module is after playing title lockout issue, it is judged that whether the answer type of the voice gathered is to affirm back
Answer, be then to play to terminate prompt tone;Transfer other similar title lockout issues of this title lockout issue the most at random and play,
Continue to judge the answer type after playing title lockout issue.
Above-mentioned all of problem and prompt tone are stored in internal memory 20, use internal memory to be data base local to carry out information
Change storage.Miaow head 30 is responsible for all of voice collecting.Main control module 10 loads speech recognition and logical judgment, and from internal memory 20
In transfer corresponding problem and prompt tone.The broadcasting of all problems and prompt tone is responsible for by loudspeaker 40.In the specific implementation, described master
Control module 10 can use single-chip microcomputer and the peripheral circuit composition thereof of SX170X series, if model is SX170X-B.
In sum, the present invention provide a kind of voice interface control method and device, it is not necessary to networking carry out big data
Computing, semantics identity judge and noise analysis processes, it is not necessary to realize voice by complex operations such as the loadings of other modules mutual
Dynamic application, it is not necessary to networking increases the stability of device computing.All the affair logic completes on main control module, and main control module is complete
The data in internal memory are directly invoked after becoming logical operations.Maximum advantage be need not install on any end product any
Special software client, achieve zero installation, zero dimension is protected.It addition, voice interface controls device also has extension customizable,
As long as the data in internal memory are updated realizing the quiz game of different objects.Meanwhile, this voice interface controls device
Having only to user carry out simple voice answering and can complete the interactive voice application of complexity, each interaction content is different, increases
The interest of interactive application.
It is understood that for those of ordinary skills, can be according to technical scheme and send out
Bright design in addition equivalent or change, and all these change or replace the guarantor that all should belong to appended claims of the invention
Protect scope.
Claims (9)
1. a voice interface control method, it is characterised in that including:
Step A, transfer beginning prompt tone playing, transfer a Main classification problem at random and play;
Step B, the voice of collection user also identify answer type, judge it is to jump to other ad eundems ask according to answer type
Topic or entrance next stage problem;
Whether the problem that step C, judgement need to propose is title lockout issue: is then to play title lockout issue, performs step D;
Otherwise transfer problem clew sound corresponding to this problem and play, returning step B;
Whether the answer type of the voice that step D, judgement are gathered is affirmative acknowledgement (ACK), is then to play to terminate prompt tone, otherwise holds
Row step E;
Step E, transfer other similar title lockout issues of this title lockout issue and play at random, return step D.
Voice interface control method the most according to claim 1, it is characterised in that described answer type includes: affirm back
Answer, negative acknowledge and uncertain answer;
Described Main classification problem has some, each corresponding some the disaggregated classification problems of Main classification problem;Disaggregated classification problem is divided
For n level, n is positive integer;Each corresponding some the one-level disaggregated classification problems of Main classification problem, each one-level disaggregated classification problem
Corresponding some two grades of disaggregated classification problems, by that analogy, each corresponding some the n level disaggregated classifications of n-1 level disaggregated classification problem are asked
Topic;Each corresponding some the title lockout issues of n level disaggregated classification problem;
The grade of Main classification problem is the highest, and disaggregated classification problem is taken second place, and the grade of title lockout issue is minimum.
Voice interface control method the most according to claim 2, it is characterised in that described step A specifically includes:
When step A1, start, transfer the first beginning prompt tone and play;
Step A2, the voice of collection user also identify when answer is affirmative acknowledgement (ACK), play the second beginning prompt tone;
Step A3, second start prompt tone play after wait Preset Time, transfer a Main classification problem at random and play.
Voice interface control method the most according to claim 2, it is characterised in that described step A2 specifically includes:
A21, play a follow-up prompts sound every the time of setting, until collecting the voice of user and identifying that answer is for affirm back
Stop when answering, play the second beginning prompt tone;
A22, play preset times continuously when follow-up prompts sound, then play shutdown prompt tone.
Voice interface control method the most according to claim 2, it is characterised in that in described step B, identifies and answers class
When type is affirmative acknowledgement (ACK), enter the next stage problem of this classification problem;If identifying negative acknowledge or uncertain answer, then selecting should
Other classification problems of classification problem ad eundem;Uncertain answer also records this classification problem and is labeled as blank.
Voice interface control method the most according to claim 2, it is characterised in that described step D specifically includes:
Step D1, collection identify the voice of user, it is judged that whether answer type is affirmative acknowledgement (ACK): be then to play to terminate prompt tone,
Perform step D2;Otherwise perform step E;
Step D2, collection identify the voice of user, it is judged that whether answer type is affirmative acknowledgement (ACK): be then to return step A;Otherwise broadcast
Put and exit prompt tone, automatic shutdown.
Voice interface control method the most according to claim 5, it is characterised in that in described step B ~ step E, if belonging to
Classification problem in all ad eundems of same branch is all marked as blank, or counts on the blank of more than 10, then judge
Fuzzy for logical contradiction or answer, transfer warning prompt sound and play.
Voice interface control method the most according to claim 5, it is characterised in that in described step B ~ step E, if system
When counting all title lockout issue all negative acknowledges under two disaggregated classification problems, transfer and heavily carry out prompt tone and play.
9. the voice interface of the voice interface control method that a kind realizes described in claim 1 controls device, it is characterised in that bag
Include main control module, internal memory, miaow head and loudspeaker;
Described main control module is transferred beginning prompt tone from internal memory and is play by loudspeaker, transfers a Main classification problem at random also
Play;Miaow head gathers the voice of user and is transferred to main control module identification answer type, judges it is to jump to according to answer type
Other ad eundem problems or entrance next stage problem;
Whether the problem that master control module judges need to propose is title lockout issue: be, transfers title lockout issue also from internal memory
Play by loudspeaker;Otherwise transfer problem clew sound corresponding to this problem and play, continuing gather the voice of user and identify back
Answer type, judge select permeability according to answer type;
Main control module is after playing title lockout issue, it is judged that whether the answer type of the voice gathered is affirmative acknowledgement (ACK), is
Then play and terminate prompt tone;Transfer other similar title lockout issues of this title lockout issue the most at random and play, continuing
Judge the answer type after playing title lockout issue.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610353529.0A CN106055605A (en) | 2016-05-25 | 2016-05-25 | Voice interaction control method and apparatus thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610353529.0A CN106055605A (en) | 2016-05-25 | 2016-05-25 | Voice interaction control method and apparatus thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106055605A true CN106055605A (en) | 2016-10-26 |
Family
ID=57175573
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610353529.0A Pending CN106055605A (en) | 2016-05-25 | 2016-05-25 | Voice interaction control method and apparatus thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106055605A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106205612A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Information processing method and system towards intelligent robot |
CN107103795A (en) * | 2017-06-28 | 2017-08-29 | 广州播比网络科技有限公司 | A kind of interactive player method of Story machine |
CN107959882A (en) * | 2017-12-12 | 2018-04-24 | 广东小天才科技有限公司 | Speech conversion method, device, terminal and medium based on video-see record |
CN108053023A (en) * | 2017-12-01 | 2018-05-18 | 北京物灵智能科技有限公司 | A kind of self-action intent classifier method and device |
CN108766429A (en) * | 2018-06-05 | 2018-11-06 | 北京百度网讯科技有限公司 | Voice interactive method and device |
CN108961525A (en) * | 2017-05-17 | 2018-12-07 | 北京博瑞彤芸文化传播股份有限公司 | A kind of acquisition methods selecting information |
CN110390935A (en) * | 2019-07-15 | 2019-10-29 | 百度在线网络技术(北京)有限公司 | Voice interactive method and device |
CN111714140A (en) * | 2020-06-05 | 2020-09-29 | 京东数字科技控股有限公司 | Method, device, system and storage medium for acquiring response information of detected lie person |
CN112337094A (en) * | 2020-10-27 | 2021-02-09 | 四川长虹电器股份有限公司 | Voice game interaction method |
CN112337081A (en) * | 2020-10-27 | 2021-02-09 | 四川长虹电器股份有限公司 | Interactive method for realizing voice guessing game |
CN112423141A (en) * | 2020-10-27 | 2021-02-26 | 四川长虹电器股份有限公司 | Interactive method for realizing voice game of television terminal |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101807415A (en) * | 2009-02-17 | 2010-08-18 | 鸿富锦精密工业(深圳)有限公司 | Audio playing device with interactive function and interactive method thereof |
CN101833877A (en) * | 2010-03-24 | 2010-09-15 | 杭州全动科技有限公司 | Enlightening education method for preschool child |
CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
CN104331148A (en) * | 2014-09-23 | 2015-02-04 | 普强信息技术(北京)有限公司 | Voice user interface information interaction method |
CN105446491A (en) * | 2015-12-16 | 2016-03-30 | 北京光年无限科技有限公司 | Intelligent robot based interactive method and apparatus |
-
2016
- 2016-05-25 CN CN201610353529.0A patent/CN106055605A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101807415A (en) * | 2009-02-17 | 2010-08-18 | 鸿富锦精密工业(深圳)有限公司 | Audio playing device with interactive function and interactive method thereof |
CN101833877A (en) * | 2010-03-24 | 2010-09-15 | 杭州全动科技有限公司 | Enlightening education method for preschool child |
CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
CN104331148A (en) * | 2014-09-23 | 2015-02-04 | 普强信息技术(北京)有限公司 | Voice user interface information interaction method |
CN105446491A (en) * | 2015-12-16 | 2016-03-30 | 北京光年无限科技有限公司 | Intelligent robot based interactive method and apparatus |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106205612A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Information processing method and system towards intelligent robot |
CN106205612B (en) * | 2016-07-08 | 2019-12-24 | 北京光年无限科技有限公司 | Information processing method and system for intelligent robot |
CN108961525A (en) * | 2017-05-17 | 2018-12-07 | 北京博瑞彤芸文化传播股份有限公司 | A kind of acquisition methods selecting information |
CN107103795A (en) * | 2017-06-28 | 2017-08-29 | 广州播比网络科技有限公司 | A kind of interactive player method of Story machine |
CN108053023A (en) * | 2017-12-01 | 2018-05-18 | 北京物灵智能科技有限公司 | A kind of self-action intent classifier method and device |
CN107959882B (en) * | 2017-12-12 | 2019-12-13 | 广东小天才科技有限公司 | Voice conversion method, device, terminal and medium based on video watching record |
CN107959882A (en) * | 2017-12-12 | 2018-04-24 | 广东小天才科技有限公司 | Speech conversion method, device, terminal and medium based on video-see record |
CN108766429A (en) * | 2018-06-05 | 2018-11-06 | 北京百度网讯科技有限公司 | Voice interactive method and device |
CN108766429B (en) * | 2018-06-05 | 2020-08-21 | 北京百度网讯科技有限公司 | Voice interaction method and device |
CN110390935A (en) * | 2019-07-15 | 2019-10-29 | 百度在线网络技术(北京)有限公司 | Voice interactive method and device |
CN110390935B (en) * | 2019-07-15 | 2021-12-31 | 百度在线网络技术(北京)有限公司 | Voice interaction method and device |
US11341967B2 (en) | 2019-07-15 | 2022-05-24 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for voice interaction |
CN111714140A (en) * | 2020-06-05 | 2020-09-29 | 京东数字科技控股有限公司 | Method, device, system and storage medium for acquiring response information of detected lie person |
CN111714140B (en) * | 2020-06-05 | 2023-06-23 | 京东科技控股股份有限公司 | Lie person response information acquisition method, device and system and storage medium |
CN112337094A (en) * | 2020-10-27 | 2021-02-09 | 四川长虹电器股份有限公司 | Voice game interaction method |
CN112337081A (en) * | 2020-10-27 | 2021-02-09 | 四川长虹电器股份有限公司 | Interactive method for realizing voice guessing game |
CN112423141A (en) * | 2020-10-27 | 2021-02-26 | 四川长虹电器股份有限公司 | Interactive method for realizing voice game of television terminal |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106055605A (en) | Voice interaction control method and apparatus thereof | |
CN107030691B (en) | Data processing method and device for nursing robot | |
Premack et al. | Infants attribute value±to the goal-directed actions of self-propelled objects | |
US8515892B2 (en) | Artificial intelligence system | |
CN107340865A (en) | Multi-modal virtual robot exchange method and system | |
CN108847226A (en) | The agency managed in human-computer dialogue participates in | |
CN106205612A (en) | Information processing method and system towards intelligent robot | |
CN106062869A (en) | Interactive household-electrical-appliance system, server device, interactive household electrical appliance, method whereby household-electrical-appliance system performs interaction, and non-volatile computer-readable data recording medium having, stored thereon, program for executing said method on computer | |
CN109559742B (en) | Voice control method, system, storage medium and computer equipment | |
CN109036388A (en) | A kind of intelligent sound exchange method based on conversational device | |
CN108109622A (en) | A kind of early education robot voice interactive education system and method | |
CN109271128A (en) | Audio setting method, device, electronic equipment and storage medium | |
US20160125295A1 (en) | User-interaction toy and interaction method of the toy | |
CN109857929A (en) | A kind of man-machine interaction method and device for intelligent robot | |
CN108566406B (en) | Interactive children's mental tutor toy based on thing networking mode | |
CN109362596A (en) | The exchange method of pet and equipment, device and electronic equipment | |
CN111694282A (en) | Comprehensive sleep-aiding regulation and control method based on Internet of things | |
CN206224438U (en) | A kind of intelligent electronic pet voice interactive system | |
CN108932947A (en) | Sound control method and household appliance | |
CN103729950A (en) | Intelligent preemptive answer system based on mobile terminals and preemptive answer method of intelligent preemptive answer system | |
CN108492829A (en) | A kind of baby cry based reminding method, apparatus and system | |
CN110152272A (en) | A kind of control method of treadmill, treadmill and intelligent terminal | |
CN112735423A (en) | Voice interaction method and device, electronic equipment and storage medium | |
CN105727572B (en) | A kind of self-learning method and self study device based on speech recognition of toy | |
CN112463108B (en) | Voice interaction processing method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161026 |
|
RJ01 | Rejection of invention patent application after publication |