CN109166572A - The method and reading machine people that robot is read - Google Patents
The method and reading machine people that robot is read Download PDFInfo
- Publication number
- CN109166572A CN109166572A CN201811058514.7A CN201811058514A CN109166572A CN 109166572 A CN109166572 A CN 109166572A CN 201811058514 A CN201811058514 A CN 201811058514A CN 109166572 A CN109166572 A CN 109166572A
- Authority
- CN
- China
- Prior art keywords
- user
- voice messaging
- reading
- requirement
- robot
- 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 21
- 230000003993 interaction Effects 0.000 claims abstract description 79
- 230000002452 interceptive effect Effects 0.000 claims description 20
- 238000010276 construction Methods 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 6
- 238000012790 confirmation Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002618 waking effect Effects 0.000 description 2
- 101100010343 Drosophila melanogaster lobo gene Proteins 0.000 description 1
- 241001248531 Euchloe <genus> Species 0.000 description 1
- 241000283973 Oryctolagus cuniculus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function 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
- G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Manipulator (AREA)
- Toys (AREA)
Abstract
A kind of method read present invention discloses robot and reading machine people, wherein the method that robot is read, comprising: receive the voice messaging that user issues, voice messaging is the voice messaging for meeting preset rules that user issues according to reading requirement；By conversating with the matched human-computer interaction model of voice messaging with user, and the reading requirement of user is obtained out from session；Execute reading instruction corresponding with the reading requirement of user.After robot receives the reading requirement voice messaging of user, by conversating with the matched human-computer interaction model of voice messaging with user, realizes man-machine interaction, to determine the specific reading requirement of user, increase user to the enjoyment for listening to robot reading.
Description
Technical field
A kind of method read the present invention relates to robot field more particularly to robot and reading machine people.
Background technique
With the continuous development of robot technology, intelligent robot is more and more applied to the family life of the mankind
In.For example, user to read, listen to storytelling, hearing, read the newspaper using intelligent robot, the voice broadcast of data search, voice electricity
The demand for talking about aspect is more and more.
However, the current robot for reading is mostly by phonetic order come so that robotic is turned over
Book or camera scanning are to be read.No matter which kind of, the mistake for all having certain requirement to the position of reading, and reading
Cheng Zhong, people and machine do not have it is any interact, in this way in the convenience used, all defect in the enjoyment of child.
In order to improve the user experience of intelligent robot, need to improve the interaction capabilities of intelligent robot, to meet user
Growing demand.
Summary of the invention
The main object of the present invention is to provide method and the reading machine people of robot reading, it is intended to solve existing reading machine
In device people, user lacks with robot the technical issues of interacting, cannot causing the enjoyment of child.
The present invention provides a kind of method that robot is read, comprising:
The voice messaging that user issues is received, which meets preset rules according to what reading requirement issued for user
Voice messaging；
By conversating with the matched human-computer interaction model of voice messaging with user, and obtain out user's from session
Reading requirement；
Execute reading instruction corresponding with the reading requirement of user.
Further, before the step of receiving the voice messaging that user issues, further includes:
The preset audio resource of typing, and human-computer interaction model is constructed according to specific rule, preset audio resource is
It executes and reads the object that instruction read broadcasting.
Further, according to specific rule building human-computer interaction model the step of, comprising:
The demand feedback of typing requirement command keyword and corresponding requirement command keyword talks about art；
Identify the semanteme of requirement command keyword；
The semanteme and demand feedback words art for instructing keyword according to demand establish matching relationship, to construct human-computer interaction mould
Type.
Further, by conversating with the matched human-computer interaction model of voice messaging and user the step of, comprising:
Identify the semanteme of the requirement command keyword in voice messaging；
The corresponding demand feedback words of the semanteme of the requirement command keyword in voice messaging are determined according to human-computer interaction model
Art；
Art is talked about by identified demand feedback to feed back voice messaging.
Further, the corresponding need of semanteme of the requirement command keyword in voice messaging are determined according to human-computer interaction model
Before the step of feedback words art of negating, comprising:
In stand-by mode, if the semantic expressiveness of the requirement command keyword in voice messaging be wake up require, to
Machine mode switchs to operating mode.
The present invention also provides a kind of reading machine people, comprising:
Receiving module, for receiving the voice messaging of user's sending, voice messaging is what user issued according to reading requirement
Meet the voice messaging of preset rules；
Interactive module, for by and the matched human-computer interaction model of voice messaging conversate with user, and from session
The middle reading requirement for obtaining out user；
Execution module, for executing reading instruction corresponding with the reading requirement of user.
Further, reading machine people further include:
Resource recording module is used for the preset audio resource of typing；
Model construction module, for constructing human-computer interaction model according to specific rule.
Further, model construction module includes:
Art typing unit is talked about, the demand feedback words for typing requirement command keyword and corresponding requirement command keyword
Art；
Art recognition unit is talked about, for identification the semanteme of requirement command keyword；
Construction unit is interacted, the semanteme and demand feedback words art for instructing keyword according to demand establish matching relationship,
To construct human-computer interaction model.
Further, interactive module includes:
Voice recognition unit, for identification semanteme of the requirement command keyword in voice messaging；
Art matching unit is talked about, for determining the semanteme of the requirement command keyword in voice messaging according to human-computer interaction model
Corresponding demand feedback talks about art；
Speech response unit feeds back voice messaging for talking about art by identified demand feedback.
Further, interactive module further include:
Wakeup unit: it is used in stand-by mode, if the semantic expressiveness of the requirement command keyword in voice messaging is
It wakes up and requires, then switch to operating mode from standby mode.
Beneficial effects of the present invention: the method that robot provided by the invention is read, comprising: receive the voice that user issues
Information, voice messaging are the voice messaging for meeting preset rules that user issues according to reading requirement；By with voice messaging
Human-computer interaction model and the user matched conversates, and the reading requirement of user is obtained out from session；Execution is read with user's
The corresponding reading instruction of reading demand.After robot receives the reading requirement voice messaging of user, by and voice messaging
Matched human-computer interaction model conversates with user, realizes man-machine interaction, to determine the specific reading requirement of user, increases
User is to the enjoyment for listening to robot reading.
Robot provided by the invention realizes the interaction of user and robot, in turn by the setting of interactive module
Confirm the final reading requirement of user；By the setting of execution module, robot is allowed to execute corresponding reading requirement instruction.Pass through money
The setting of source recording module will think that the audio resources such as books, story and nursery rhymes to be used mention according to the reading requirement of user
In preceding typing robot, is read without scanning books by camera, reduce the limitation of robot placement position.
Detailed description of the invention
The method flow schematic diagram that the robot of Fig. 1 one embodiment of the invention is read；
The method flow schematic diagram that the robot of Fig. 2 another embodiment of the present invention is read；
Reading machine people's structural schematic diagram of Fig. 3 one embodiment of the invention；
Reading machine people's structural schematic diagram of Fig. 4 another embodiment of the present invention；
Model construction module structural schematic diagram in Fig. 5 one embodiment of the invention；
Interactive module structural schematic diagram in Fig. 6 one embodiment of the invention；
Interactive module structural schematic diagram in Fig. 7 another embodiment of the present invention；
Reading machine people's structural schematic diagram in Fig. 8 third embodiment of the invention；
Reading machine people's structural schematic diagram in Fig. 9 fourth embodiment of the invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that described herein, specific examples are only used to explain the present invention, is not intended to limit the present invention.
Referring to Fig.1, the method that the robot of one embodiment of the invention is read, comprising:
S1: receiving the voice messaging that user issues, and voice messaging meets default rule according to what reading requirement issued for user
Voice messaging then；
S2: it by conversating with the matched human-computer interaction model of voice messaging with user, and obtains out and uses from session
The reading requirement at family；
S3: reading instruction corresponding with the reading requirement of user is executed.
In above-mentioned steps S1, the reading requirement includes needing to read a certain piece article, story etc. for the first time instantly；It can also
To be the reading for requiring to terminate, interrupt an article, it is changed to read another article story；It is also possible to the need for stopping reading
It asks.The voice messaging for meeting preset rules refers to and has been previously created some man-machine interactive models in robot, if
Certain session rules are determined, the voice messaging of reading requirement, machine are issued according to these human-computer interaction models and session rules
The voice messaging that people receives and identifies meets the voice messaging for presetting rule, just can be carried out the dialogue of next step.
In above-mentioned steps S2, after robot receives the voice messaging of reading requirement, matching is believed with the reading requirement voice
Cease corresponding human-computer interaction model, use it is specific if art feed back to user, and engage in the dialogue with user, such as:
Child (user) says: " I will read."
Robot answer: " child, you are good, could you tell me and want which this books read? "
Child answers: " the story of lobo and little white rabbit."
Robot is answered: and " it is good, want read since which page? "
Child answers: " third page."
Robot is answered: " it is good, it executes at once."
In this way, the final reading requirement of user can be obtained out from the session with user.
For another example, it when user changes mind, is not desired to be further continued for listening to the audio content that robot is being read instantly,
Want to listen to another article, or listen a first nursery rhymes, then dialogue can be as follows:
Child (user) says: " I wants to change a reading."
Robot is answered: " child, you are good, could you tell me which piece wanted to change? "
Child answers: " bear haunts."
Robot is answered: and " it is good, want read since which page? "
Child answers: " page five."
Robot is answered: " it is good, it executes at once."
In this way, can obtain out user from the session with user changes the demand read.
For another example, when user is not desired to continue to listen to robot reading, robot can be allowed to stop reading broadcasting, it is right
Words can be as follows:
Child (user) says: " I is not desired to listen, you have a long day."
Robot is answered: " child could you tell me that determination is not listened? "
Child answers: " yes, being not desired to listen."
Robot is answered: " good, child wants to listen me to sing first song to you and relaxes "
Child answers: " should not, I will go to play."
Robot is answered: " good, our next goodbyes."
In this way, soliciting whether confirmation user really needs to stop reading by dialogue, played after clear convenient for stopping reading.
In above-mentioned steps S3, robot executes corresponding read according to the reading requirement of user and instructs, such as according to above-mentioned several
Starting to read, changing reading content or terminate the demands such as reading in kind scene, executes and starts to read, changes reading content or knot
The instruction that beam is read.
The method that the robot of the present embodiment is read is led to after robot receives the reading requirement voice messaging of user
The human-computer interaction model that overmatching corresponds to voice messaging conversates with user, and realization user interacts with reading machine people's, with
The specific reading requirement for determining user increases user to the enjoyment for listening to robot reading.
Referring to Fig. 2, in the present embodiment, in the voice messaging for receiving user and issuing, voice messaging is user according to reading need
Before the step S1 for seeking the voice messaging for meeting preset rules of sending, further includes:
S0: the preset audio resource of typing, and human-computer interaction model, preset audio resource are constructed according to specific rule
To execute the object read instruction and read broadcasting.
In this step, preset audio resource is determined according to user demand, such as books, story, nursery rhymes etc., as long as
It is the daily content for wanting to listen to of user, can all shifts to an earlier date typing；It is described according to it is specific rule construct human-computer interaction model, i.e., according to
Art establishes session rules if specific, makes the voice messaging of robot identification user's specific sample, and by voice messaging
Some keywords judge the demand of user, then carry out feedback dialogue by art if specific, avoid robot to the voice of user
Information is misunderstood, and makes dialogue more smooth.
In the present embodiment, according to specific regular the step of constructing human-computer interaction model, comprising:
S01: the demand feedback of typing requirement command keyword and corresponding requirement command keyword talks about art；
S02: the semanteme of identification requirement command keyword；
S03: the semanteme of keyword and demand feedback words art is instructed to establish matching relationship, according to demand to construct human-computer interaction
Model.
In above-mentioned steps S01, selection is suitble to the specific instruction keyword of each scene dialogue and corresponding requirement command to close
The demand feedback of keyword talks about art, for example keyword includes the word of specific title, article name, song title and number of pages etc
Converge, further include " listening to ", " reading ", " thinking ", " wanting " " being not desired to ", " should not ", " stopping ", " beginning ", " end ", " pause " " changing "
Etc. indicate certainly, negative or change demand willingness vocabulary.Feedback words art includes as described in the dialogue of several scenes above
" child, you are good, could you tell me and want which this books read? ", " child, you are good, could you tell me which piece wanted to change? " and " good
, our next goodbyes." etc. if art, either art if keyword or demand feedback, should be compared with people as far as possible
Property language, and it is abundant as far as possible, to meet the need of user's different demands scene, different expression ways and different feedback systems
It asks, it is natural, interesting as the interaction between realization human-computer interaction such as people and people.
In above-mentioned steps S02, the semanteme of requirement command keyword, the typing requirement command keyword in step S01 are identified
Afterwards, in the robot of these keywords typing by being stored in, the keyword of robot identification comparison typing is right when listening
When answering the voice messaging of keyword, robot is appreciated that the meaning of the keyword.
In above-mentioned steps S03, according to semanteme and demand feedback the words art foundation of identified requirement command keyword
With relationship, when robot receives the voice messaging of user's particular keywords, user will be responded with art if specific, passed through
Specific conversational mode is established, the model of human-computer interaction is built.
Above-mentioned steps S01 to S03 allows robot to understand its meaning, then pass through by the specific related keyword vocabulary of determination
The specific feedback words art of setting allows robot in user interaction, is looked like according to the user speech that Understanding arrives, selection makes
It uses specific feedback words art as answering, realizes man-machine smooth interaction.
In the present embodiment, by conversating with the matched human-computer interaction model of voice messaging and user the step of, packet
It includes:
S21: the semanteme of the requirement command keyword in identification voice messaging；
S22: determine that the corresponding demand of semanteme of the requirement command keyword in voice messaging is anti-according to human-computer interaction model
Feedback words art；
S23: art is talked about by identified demand feedback, voice messaging is fed back.
In above-mentioned steps S21, according to the human-computer interaction model pre-established, the pass for the voice messaging that comparison identification receives
Keyword understands the semanteme of voice messaging.
In step S22, according to demand information keyword specific in the human-computer interaction model pre-established and demand feedback
The matching relationship of art is talked about, determines the corresponding demand feedback of semanteme of requirement command keyword in the voice messaging recognized instantly
Talk about art, to avoid human-computer interaction during the case where giving an irrelevant answer.
In step S23, art is talked about by identified demand feedback, voice messaging is fed back, realized mutual between man-machine
Dynamic dialogue, in this step, being can be with the progress of Infinite Cyclic, as long as user issues voice messaging, robot will be fed back,
Until reaching an agreement mutually, the execution of next step just will do it.Pass through " reception-identification-feedback ... " such dialogue
Process realizes human-computer interaction exchange, realizes the hommization interaction between man-machine, increases user and read using reading machine people
Enjoyment.
In the present embodiment, determine that the semanteme of the requirement command keyword in voice messaging is corresponding according to human-computer interaction model
Demand feedback words art step S22 before, comprising:
S2a: in stand-by mode, if the semantic expressiveness of the requirement command keyword in voice messaging is to wake up to require,
Switch to operating mode from standby mode.
Before starting to carry out reading broadcasting, robot is in standby mode, when user calling robot for the first time, than
As said " small love, small love prepare to read ", robot begins to be waken up, i.e., is transferred into operating mode from standby mode.It calls out
After waking up, user can carry out normal interactive conversation with robot.By the setting of operating mode and standby mode, pass through the step
Portable exchange is realized in wake-up work in rapid, meanwhile, save the power consumption of robot.
Referring to Fig. 2, in one embodiment, after executing the step of reading corresponding with the reading requirement of user instructs,
Further include:
S4: if the instruction for being off reading executed, after executing the preset time after the instruction for stopping reading and reaching, into
Enter standby mode.
In this step, it by presetting a period, is reading in the preset time period after stopping, robot is also
Under operating mode, user can directly show the specific reading requirement of oneself, need not move through and wake up a step, when being more than pre-
If period, robot will be transferred to standby mode, to save power consumption.
In another embodiment, after the semantic step of the requirement command keyword in identification voice messaging, comprising:
S24: when indicating to stop immediately the voice messaging of reading demands of user's sending is received, execution stops reading and refer to
It enables.
In this step, robot receives the voice messaging for stopping reading that explicitly indicates that of user, directly stops reading, no
Confirm again with user session.When being primarily adapted for use in and be playing reading, or just terminating the reading of a certain chapters and sections, user wants to tie
In the scene that beam is read.This indicates the voice messaging for requiring to stop reading, can be in above-mentioned steps S0 according to specific rule
Construct human-computer interaction model when specifically set, it is possible to specify certain keyword, for example, include " immediately ", " horse back " it
It when the requirement of class word, indicates to require to close immediately, eliminates robot and user by interaction confirmation again, when saving
Between, enrich the form of man-machine communication.
Referring to Fig. 3, in one embodiment of the invention, a kind of reading machine people, comprising:
Receiving module 1, for receiving the voice messaging of user's sending, voice messaging is what user issued according to reading requirement
Meet the voice messaging of preset rules；
Interactive module 2, for by and the matched human-computer interaction model of voice messaging conversate with user, and from session
The middle reading requirement for obtaining out user；
Execution module 3, for executing reading instruction corresponding with the reading requirement of user.
By the setting of receiving module 1, robot is allowed to have " hearing ", for receiving the voice messaging of user, for interaction
Basis is provided.The reading requirement includes needing to read a certain piece article, story etc. for the first time instantly, is also possible to require to terminate
The reading for interrupting an article is changed to require to read another article story, is also possible to the demand for stopping reading；The symbol
The voice messaging for closing preset rules, refers to and has been previously created some man-machine interactive models in robot, set certain
Session rules, the voice messaging of reading requirement is issued according to these human-computer interaction models and session rules, and robot receives and knows
The voice messaging being clipped to meets the voice messaging for presetting rule, just can be carried out the dialogue of next step.
Man-machine exchange and interdynamic are realized by interactive module 2.After robot receives the voice messaging of reading requirement, matching
Human-computer interaction model corresponding with the reading requirement voice messaging, use it is specific if art feed back to user, and and user into
Row dialogue, by the demand for listening to reading for talking with final confirmation user.
By the setting of execution module 3, so that robot is executed corresponding read according to the reading requirement of user and instructs,
According to such as starting reading, changing reading content or terminating the demands such as reading, executes and start reading, change reading content or terminate to read
The instruction of reading.
The robot of the present embodiment after the reading requirement voice messaging for receiving user, passes through and matches corresponding voice messaging
Human-computer interaction model conversate with user, realize man-machine interaction, to determine the specific reading requirement of user, increase use
Family is to the enjoyment for listening to robot reading.
Referring to Fig. 4, in the present embodiment, reading machine people further include:
Resource recording module 00, is used for the preset audio resource of typing, and the preset audio resource is to read described in execution
Reading instruction read the object of broadcasting；
Model construction module 01, for constructing human-computer interaction model according to specific rule.
By the setting of resource recording module 00, the typing storage of preset audio resource is realized.Preset audio resource
It is to be determined according to user demand, such as books, story, nursery rhymes etc., as long as the daily content for wanting to listen to of user, can all shift to an earlier date
Typing.
By the setting of model construction module 01, human-computer interaction model is constructed according to specific rule, i.e., according to specific
Words art establishes session rules, makes the voice messaging of robot identification user's specific sample, and passes through some passes in voice messaging
Keyword judges the demand of user, then carries out feedback dialogue by art if specific, and robot is avoided to produce the voice messaging of user
It is raw to misread, make dialogue more smooth.
Referring to Fig. 5, model construction module 01 includes:
Art typing unit 011 is talked about, the demand feedback for typing requirement command keyword and corresponding requirement command keyword
Talk about art；
Art recognition unit 012 is talked about, for identification the semanteme of requirement command keyword；
Construction unit 013 is interacted, the semanteme and demand feedback words art for instructing keyword according to demand are established matching and closed
System, to construct human-computer interaction model.
Pass through the demand feedback words of words 011 typing requirement command keyword of art typing unit and corresponding requirement command keyword
Art, selection are suitble to the specific instruction keyword of each scene dialogue and the demand feedback words art of corresponding requirement command keyword,
Such as keyword includes the vocabulary of specific title, article name, song title and number of pages etc first, further include " listening to ",
" reading ", " thinking ", " wanting " " being not desired to ", " should not ", " stopping ", " beginning ", " end ", " pause " " changing " etc. indicate certainly, it is no
Vocabulary that is fixed or changing demand willingness.Feedback words art include as described in the dialogue of several scenes above " child, you are good,
Could you tell me and want any this books read? ", " child, you are good, could you tell me which piece wanted to change? " and " good, we are next again
See." etc. if art, either art if keyword or demand feedback, should be more humanized language as far as possible, and to the greatest extent
Amount is abundant, to meet the needs of user's different demands scene, different expression ways and different feedback systems, realizes human-computer interaction
It is natural, interesting as the interaction between people and people.
The semanteme that requirement command keyword is identified by words art recognition unit 012, after typing requirement command keyword, these
In the robot of keyword typing by being stored in, the keyword of robot identification comparison typing is corresponding crucial when listening
When the voice messaging of word, robot is appreciated that the meaning of keyword.
Human-computer interaction model is constructed by interaction construction unit 013, according to the language of identified requirement command keyword
Justice and demand feedback words art establish matching relationship, will be with when robot receives the voice messaging of user's particular keywords
Art responds user and builds the model of human-computer interaction by establishing specific conversational mode if specific.
By words art typing unit 011, words art recognition unit 012 and the setting for interacting construction unit 013, determine specific
Relevant key vocabularies allow robot to understand its meaning, and set specific feedback words art, allow robot and user interaction
In, it is looked like according to the user speech of Understanding, select use specific feedback words art as answer, realized man-machine smooth mutual
It is dynamic.
Referring to Fig. 6, in the present embodiment, interactive module 2 includes:
Voice recognition unit 21, for identification semanteme of the requirement command keyword in voice messaging；
Art matching unit 22 is talked about, for determining the language of the requirement command keyword in voice messaging according to human-computer interaction model
The corresponding demand feedback of justice talks about art；
Speech response unit 23 feeds back voice messaging for talking about art by identified demand feedback.
By voice recognition unit 21, according to the human-computer interaction model pre-established, the voice that comparison identification receives is believed
The keyword of breath understands the semanteme of voice messaging.
By talking about art matching unit 22, according to demand information keyword specific in the human-computer interaction model pre-established and
Demand feedback talks about the matching relationship of art, determines that the semanteme of requirement command keyword in the voice messaging recognized instantly is corresponding
Demand feedback talks about art, to avoid giving an irrelevant answer during human-computer interaction.
By the setting of speech response unit 23, art is talked about by identified demand feedback, voice messaging is fed back,
It realizes the interactive conversation between man-machine, by reception-identification-feedback full dialog process, realizes human-computer interaction exchange, realize
Hommization interaction between user and robot, increases the enjoyment that user is read using reading machine people.
Referring to Fig. 7, in the present embodiment, interactive module 2 further include:
Wakeup unit 24: it is used in stand-by mode, if the semantic expressiveness of the requirement command keyword in voice messaging is
It wakes up and requires, then switch to operating mode from standby mode.
Before starting to carry out reading broadcasting, robot is in standby mode, when user calling robot for the first time, than
As said " small love, small love prepare to read ", robot begins to be waken up, i.e., is transferred into operating mode from standby mode.It calls out
After waking up, user can carry out normal interactive conversation with robot.By the setting of operating mode and standby mode, pass through the step
Portable exchange is realized in wake-up work in rapid, meanwhile, save the power consumption of robot.
Referring to Fig. 8, in the present embodiment, robot further include:
Standby module 4, if for execution the instruction for being off reading, execute stop read instruction after it is default when
Between reach after, into standby mode.
By presetting the period, reading in the preset time period after stopping, robot also under operating mode,
The specific reading requirement that can directly show oneself needs not move through and wakes up a step, and when being more than the preset period, robot is just
It can be transferred to standby mode, to save power consumption.
Referring to Fig. 9, in the present embodiment, robot further include:
Quick stopping modular 5: it for receiving when indicating to stop immediately the voice messaging of reading demands of user's sending, holds
Row stops reading instruction.
By the setting of quick stopping modular 5, realize that convenient stopping is read.Robot receives explicitly indicating that for user and stops
The voice messaging only read directly generates corresponding stopping and reads instruction, and executes to stop reading and instruct.It is primarily adapted for use in
When playing and read, or just terminating the reading of a certain chapters and sections, user wants in the scene for terminating to read.This indicates to require to stop to read
The voice messaging of reading, can be specific according to progress when specific rule building human-computer interaction model in model construction module 01
Setting, it is possible to specify certain keyword, such as include " immediately ", " horse back " etc the requirement of word when, indicate requirement immediately
It closes, eliminates robot and user by interaction confirmation again, save the time, enrich the form of man-machine communication.
The method that robot provided by the invention is read, comprising: receive the voice messaging that user issues, voice messaging is to use
The voice messaging for meeting preset rules that family is issued according to reading requirement；By with the matched human-computer interaction model of voice messaging with
User conversates, and the reading requirement of user is obtained out from session；Execute reading corresponding with the reading requirement of user
Instruction.After robot receives the reading requirement voice messaging of user, by with the matched human-computer interaction model of voice messaging
It conversates with user, realizes man-machine interaction, to determine the specific reading requirement of user, increase user to listening to robot
The enjoyment of reading.
Robot provided by the invention realizes the interaction of user and robot, in turn by the setting of interactive module
Confirm the final reading requirement of user；By the setting of execution module, robot is allowed to execute corresponding reading requirement instruction.Pass through money
The setting of source recording module will think that the audio resources such as books, story and nursery rhymes to be used mention according to the reading requirement of user
In preceding typing robot, is read without scanning books by camera, reduce the limitation of robot placement position.
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all utilizations
Equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, be included within the scope of the present invention.
Claims (10)
1. a kind of method that robot is read characterized by comprising
The voice messaging that user issues is received, the voice messaging meets default rule according to what reading requirement issued for the user
Voice messaging then；
By conversating with the matched human-computer interaction model of the voice messaging with the user, and obtained from the session
The reading requirement of the user out；
Execute reading instruction corresponding with the reading requirement of the user.
2. the method that robot according to claim 1 is read, which is characterized in that the voice letter for receiving user and issuing
Before the step of breath, further includes:
The preset audio resource of typing, and the human-computer interaction model, the preset audio money are constructed according to specific rule
Source is by the execution object read instruction and read broadcasting.
3. the method that robot according to claim 2 is read, which is characterized in that described to construct institute according to specific rule
The step of stating human-computer interaction model, comprising:
The demand feedback of typing requirement command keyword and the corresponding requirement command keyword talks about art；
Identify the semanteme of the requirement command keyword；
Matching relationship is established according to the semanteme of the requirement command keyword and demand feedback words art, it is described man-machine to construct
Interactive model.
4. the method that robot according to claim 3 is read, which is characterized in that it is described by with the voice messaging
The step of human-computer interaction model and the user matched conversate, comprising:
Identify the semanteme of the requirement command keyword in the voice messaging；
Determine that the corresponding demand of semanteme of the requirement command keyword in the voice messaging is anti-according to the human-computer interaction model
Feedback words art；
Art is talked about by identified demand feedback to feed back the voice messaging.
5. the method that robot according to claim 4 is read, which is characterized in that described according to the human-computer interaction model
Before the step of determining the semantic corresponding demand feedback words art of the requirement command keyword in the voice messaging, comprising:
In stand-by mode, if the semantic expressiveness of the requirement command keyword in the voice messaging be wake up require, to
Machine mode switchs to operating mode.
6. a kind of reading machine people characterized by comprising
Receiving module, for receiving the voice messaging of user's sending, the voice messaging is that the user sends out according to reading requirement
The voice messaging for meeting preset rules out；
Interactive module, for by and the matched human-computer interaction model of the voice messaging conversate with the user, and from
The reading requirement of the user is obtained out in the session；
Execution module, for executing reading instruction corresponding with the reading requirement of the user.
7. reading machine people according to claim 6, which is characterized in that the reading machine people further include:
Resource recording module, is used for the preset audio resource of typing, and the preset audio resource is to execute the reading instruction
Read the object of broadcasting；
Model construction module, for constructing the human-computer interaction model according to specific rule.
8. reading machine people according to claim 7, which is characterized in that the model construction module includes:
Art typing unit is talked about, the demand feedback words for typing requirement command keyword and the corresponding requirement command keyword
Art；
Art recognition unit is talked about, for identification the semanteme of the requirement command keyword；
Construction unit is interacted, is closed for establishing matching according to the semanteme of the requirement command keyword and demand feedback words art
System, to construct the human-computer interaction model.
9. reading machine people according to claim 8, which is characterized in that the interactive module includes:
Voice recognition unit, for identification semanteme of the requirement command keyword in the voice messaging；
Art matching unit is talked about, for determining the requirement command keyword in the voice messaging according to the human-computer interaction model
Semantic corresponding demand feedback talks about art；
Speech response unit feeds back the voice messaging for talking about art by identified demand feedback.
10. reading machine people according to claim 9, which is characterized in that the interactive module further include:
Wakeup unit: it is used in stand-by mode, if the semantic expressiveness of the requirement command keyword in the voice messaging is
It wakes up and requires, then switch to operating mode from standby mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811058514.7A CN109166572A (en) | 2018-09-11 | 2018-09-11 | The method and reading machine people that robot is read |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811058514.7A CN109166572A (en) | 2018-09-11 | 2018-09-11 | The method and reading machine people that robot is read |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109166572A true CN109166572A (en) | 2019-01-08 |
Family
ID=64894918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811058514.7A Pending CN109166572A (en) | 2018-09-11 | 2018-09-11 | The method and reading machine people that robot is read |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109166572A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110087270A (en) * | 2019-05-15 | 2019-08-02 | 深圳市沃特沃德股份有限公司 | A kind of method, apparatus of reading, storage medium and computer equipment |
| CN110460798A (en) * | 2019-06-26 | 2019-11-15 | 平安科技（深圳）有限公司 | Video Interview service processing method, device, terminal and storage medium |
| CN110561453A (en) * | 2019-09-16 | 2019-12-13 | 北京觅机科技有限公司 | Guided accompanying reading method of drawing robot |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103605468A (en) * | 2013-11-14 | 2014-02-26 | 武汉虹翼信息有限公司 | Electronic book control device and control interaction method thereof |
| WO2014189988A1 (en) * | 2013-05-21 | 2014-11-27 | Microsoft Corporation | Method for finding elements in a webpage suitable for use in a voice user interface |
| US20170039181A1 (en) * | 2013-07-25 | 2017-02-09 | Intel Corporation | Self-learning statistical natural language processing for automatic production of virtual personal assistants |
| CN106598241A (en) * | 2016-12-06 | 2017-04-26 | 北京光年无限科技有限公司 | Interactive data processing method and device for intelligent robot |
| CN107729881A (en) * | 2017-11-17 | 2018-02-23 | 成都伟嘉斯特科技有限公司 | It is a kind of can voice interface paint this reading machine people |
| CN107832433A (en) * | 2017-11-15 | 2018-03-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, server and storage medium based on dialogue interaction |
| CN107977395A (en) * | 2017-08-01 | 2018-05-01 | 北京物灵智能科技有限公司 | A kind of help user reads and understands method and the intelligent sound assistant of electronics article |
| CN107993659A (en) * | 2017-11-28 | 2018-05-04 | 上海与德科技有限公司 | Page turning method, robot page turning system and server applied to robot |
| CN108281047A (en) * | 2018-02-09 | 2018-07-13 | 深圳市小猪班克教育科技有限公司 | Interactive intelligent Story machine and its exchange method |
-
2018
- 2018-09-11 CN CN201811058514.7A patent/CN109166572A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014189988A1 (en) * | 2013-05-21 | 2014-11-27 | Microsoft Corporation | Method for finding elements in a webpage suitable for use in a voice user interface |
| US20170039181A1 (en) * | 2013-07-25 | 2017-02-09 | Intel Corporation | Self-learning statistical natural language processing for automatic production of virtual personal assistants |
| CN103605468A (en) * | 2013-11-14 | 2014-02-26 | 武汉虹翼信息有限公司 | Electronic book control device and control interaction method thereof |
| CN106598241A (en) * | 2016-12-06 | 2017-04-26 | 北京光年无限科技有限公司 | Interactive data processing method and device for intelligent robot |
| CN107977395A (en) * | 2017-08-01 | 2018-05-01 | 北京物灵智能科技有限公司 | A kind of help user reads and understands method and the intelligent sound assistant of electronics article |
| CN107832433A (en) * | 2017-11-15 | 2018-03-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, server and storage medium based on dialogue interaction |
| CN107729881A (en) * | 2017-11-17 | 2018-02-23 | 成都伟嘉斯特科技有限公司 | It is a kind of can voice interface paint this reading machine people |
| CN107993659A (en) * | 2017-11-28 | 2018-05-04 | 上海与德科技有限公司 | Page turning method, robot page turning system and server applied to robot |
| CN108281047A (en) * | 2018-02-09 | 2018-07-13 | 深圳市小猪班克教育科技有限公司 | Interactive intelligent Story machine and its exchange method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110087270A (en) * | 2019-05-15 | 2019-08-02 | 深圳市沃特沃德股份有限公司 | A kind of method, apparatus of reading, storage medium and computer equipment |
| CN110087270B (en) * | 2019-05-15 | 2021-09-17 | 深圳市沃特沃德信息有限公司 | Reading method and device, storage medium and computer equipment |
| CN110460798A (en) * | 2019-06-26 | 2019-11-15 | 平安科技（深圳）有限公司 | Video Interview service processing method, device, terminal and storage medium |
| CN110561453A (en) * | 2019-09-16 | 2019-12-13 | 北京觅机科技有限公司 | Guided accompanying reading method of drawing robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11184412B1 (en) | Modifying constraint-based communication sessions | |
| JP2019117623A (en) | Voice dialogue method, apparatus, device and storage medium | |
| WO2017012511A1 (en) | Voice control method and device, and projector apparatus | |
| TWI535258B (en) | Voice answering method and mobile terminal apparatus | |
| CN107277272A (en) | A kind of bluetooth equipment voice interactive method and system based on software APP | |
| CN109166572A (en) | The method and reading machine people that robot is read | |
| CN108737933A (en) | A kind of dialogue method, device and electronic equipment based on intelligent sound box | |
| CN103198831A (en) | Voice control method and mobile terminal device | |
| CN107018228B (en) | Voice control system, voice processing method and terminal equipment | |
| WO2020098756A1 (en) | Emotion-based voice interaction method, storage medium and terminal device | |
| JP3000999B1 (en) | Speech recognition method, speech recognition device, and recording medium recording speech recognition processing program | |
| US11514926B2 (en) | Low power mode for speech capture devices | |
| US20220399020A1 (en) | Man-machine dialogue mode switching method | |
| CN111881280A (en) | Intelligent man-machine interaction system and method for power industry | |
| CN109599111A (en) | Voice interactive method, device and storage medium | |
| CN101415257A (en) | Man-machine conversation chatting method | |
| CN111739541B (en) | Conference assistance method and system based on voice, storage medium and terminal | |
| CN109830232A (en) | Man-machine interaction method, device and storage medium | |
| CN108492826B (en) | Audio processing method and device, intelligent equipment and medium | |
| CN109859762A (en) | Voice interactive method, device and storage medium | |
| CN109065050A (en) | A kind of sound control method, device, equipment and storage medium | |
| Wallis | A robot in the kitchen | |
| CN114822551A (en) | Interaction method based on intelligent earphone | |
| JP2000089780A (en) | Speech recognition method and device therefor | |
| US6564185B1 (en) | Continuous speech recognition method and program medium with alternative choice selection to confirm individual words |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190108 |
|
| RJ01 | Rejection of invention patent application after publication |