CN108470567A - A kind of voice interactive method, device, storage medium and computer equipment - Google Patents
A kind of voice interactive method, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN108470567A CN108470567A CN201810213805.2A CN201810213805A CN108470567A CN 108470567 A CN108470567 A CN 108470567A CN 201810213805 A CN201810213805 A CN 201810213805A CN 108470567 A CN108470567 A CN 108470567A
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- interaction
- interactive
- learning
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/065—Adaptation
- G10L15/07—Adaptation to the speaker
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0638—Interactive procedures
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Abstract
The invention discloses a kind of voice interactive method, device, storage medium and computer equipments, including:Under mode of learning, according to preset learning training model, learn the interaction habits of progress interactive voice between different user;Under speech interaction mode, when collecting the voice messaging of user, according to interaction habits, simulation carries out the user of interactive voice with user, is responded to voice messaging.The present invention initiates the interaction habits between user and voice response user by the voice learnt under mode of learning, and targetedly initiating user to voice carries out intelligentized response so that the interaction between man-machine is more intelligent, and user experience is good.
Description
Technical field
The present invention relates to human-computer interaction technique field more particularly to a kind of voice interactive method, device, storage medium and meters
Calculate machine equipment.
Background technology
Human-computer interaction is the knowledge of the interactive relation between a research system and user.System can be machine, also may be used
To say being computer system and software.By the interaction, communication, information exchange of people and computer, generate a series of input and
Then output completes a task or reaches a purpose, wherein interactive voice be exactly with voice be information carrier with machine into
The interactive pattern of row.Although human-computer interaction is widely used to the every aspect of people's life, the interaction side of existing robot
Formula there are problems that interaction not smart enoughization between user actual use demand, with user cannot be met, it is difficult to people's
Real life demand is adapted.
For example, in mother and baby lives, sleep is the big problem for perplexing vast postpartum women, good sleep all the time
It is very helpful to the reparation of postpartum women.But look after the various problems such as baby and all be unable to do without mother newborn, mother's
Sleep quality cannot just ensure, and many workplace mothers, muddle with one's work daytime, look after baby, but baby's evening at night
On behavior of crying and screaming, seriously affected the sleep of workplace mother.Thus, occur the interaction for mother and baby's life currently on the market
Robot, such as intelligence accompany most of robot, but its also to lay particular emphasis on and the functions such as play music, tell a story, however, when very much
It waits, child's especially baby cry is intended merely to seek pacifying for mother or other relatives, if baby does not obtain at this time
It is especially new to seriously affect kinsfolk then baby will be difficult to quiet down or fall asleep for the response of mother or other relatives
The quality of life of raw youngster mother.Also for example, with China's expanding economy, Aging Problem becomes increasingly conspicuous, wherein " empty nest is old
People " phenomenon gains a special interest.According to statistics, to the year two thousand fifty, China childless the elderly approaching one's end is up to 79,000,000 or so, solely
Residence and empty-nested elderly people will account for 54% or more, and the endowment problem of Empty nest elderly also causes concern again.In this regard, also being gushed in society
Reveal a series of sci-tech product that such as TV boxes aim at old man's design, to promote the old age quality of life of old man, but these
Sci-tech product increases the life content of old man at most, it is difficult to alleviate their serious hopes warm to family, the old men are many times only
Be the sound for liking to listen sons and daughters, be busy with one's work for fear of sons and daughters, they again cannot often with sons and daughters' communication exchange, it is seen that at present these
Sci-tech product helps the promotion of life of elderly person quality and little, still lonely without solving Empty nest elderly to the greatest extent
Problem.
Obviously, there is presently no the interaction robots that disclosure satisfy that people's actual demand in life, and it is different to lack simulation
It is still very low that interaction habits between user, intelligence such as pacify at functions, the intelligence degree.
Invention content
A kind of voice interactive method of present invention offer, device, storage medium and computer equipment, to solve the prior art
In robot interactive mode cannot meet user actually use demand the problem of.
One side according to the present invention provides a kind of voice interactive method, including:
Under mode of learning, according to preset learning training model, learn the interaction of progress interactive voice between different user
Custom;
Under speech interaction mode, when collecting the voice messaging of the user, according to the interaction habits, simulation with
The user carries out the user of interactive voice, is responded to voice messaging.
Optionally, further include:
When collecting preset voice open command, the speech interaction mode is opened.
Optionally, described under mode of learning, according to preset learning training model, learn to carry out voice between different user
Interactive interaction habits, including:
Under mode of learning, acquisition voice initiates the voice messaging of user and voice response user;
According to preset learning training model, using the voice messaging of acquisition as sample, study voice initiates user and voice
The interaction habits of interactive voice are carried out between response user.
Optionally, after the interaction habits that interactive voice is carried out between learning different user, further include:
The interaction habits that study is obtained initiate user according to voice and voice response user are associated storage.
Optionally, described that the voice messaging is responded, including:
According to the volume of the voice messaging of the collected user, the sound responded to the voice messaging is determined
Magnitude;
According to determining volume value, the voice messaging is responded.
Optionally, further include:
Determine user's characteristic information;
It obtains and the matched target information of the user's characteristic information;
When receiving the play instruction to the target information, speech play is carried out to the target information.
The second aspect according to the present invention provides a kind of voice interaction device, including:
Training module, under mode of learning, according to preset learning training model, learning to carry out language between different user
The interaction habits of sound interaction;
Interactive module is used under speech interaction mode, when collecting the voice messaging of the user, according to the friendship
Mutually custom, simulation carry out the user of interactive voice with the user, are responded to voice messaging.
Optionally, further include:
Voice opening module, for when collecting preset voice open command, opening the speech interaction mode.
Optionally, the training module includes:
Collecting unit, under mode of learning, acquisition voice initiates the voice messaging of user and voice response user;
Unit, according to preset learning training model, using the voice messaging of acquisition as sample, study voice initiates to use
The interaction habits of interactive voice are carried out between family and voice response user.
Optionally, further include:
Associated storage module initiates user and voice response user for that will learn obtained interaction habits according to voice
It is associated storage.
Optionally, further include:
Volume adjusting module is used for the volume of the voice messaging according to the collected user, determines to the language
Message ceases the volume value responded.
Optionally, further include:
Determining module, for determining user's characteristic information;
Acquisition module, for obtaining and the matched target information of the user's characteristic information;
Voice playing module, for when receiving the play instruction to the target information, to the target information into
Row speech play.
In terms of third according to the present invention, a kind of computer readable storage medium is provided, is stored on the storage medium
The step of having computer program, following method is realized when described program is executed by processor:
Under mode of learning, according to preset learning training model, learn the interaction of progress interactive voice between different user
Custom;
Under speech interaction mode, when collecting the voice messaging of the user, according to the interaction habits, simulation with
The user carries out the user of interactive voice, is responded to voice messaging.
According to the present invention the 4th aspect, provides a kind of computer equipment, including memory, processor and is stored in institute
The computer program that can be run on memory and on the processor is stated, the processor is realized as follows when executing described program
The step of method:
Under mode of learning, according to preset learning training model, learn the interaction of progress interactive voice between different user
Custom;
Under speech interaction mode, when collecting the voice messaging of the user, according to the interaction habits, simulation with
The user carries out the user of interactive voice, is responded to voice messaging.
Optionally, further include:
Sound collector and sound controller, when the sound collector collects preset voice open command, the sound
It controls device and opens the speech interaction mode.
Optionally, the sound collector is additionally operable under mode of learning, and acquisition voice initiates user and voice response is used
The voice messaging at family;
According to preset learning training model when the processor executes described program, using the voice messaging of acquisition as sample
This, study voice initiates to carry out the interaction habits of interactive voice between user and voice response user.
Optionally, further include:
Soundanalyzer, for obtained interaction habits will to be learnt, according to voice initiate user and voice response user into
Row associated storage.
Optionally, the step of also realizing following method when the processor executes described program:
According to the volume of the voice messaging of the collected user, the sound responded to the voice messaging is determined
Magnitude;
According to determining volume value, the voice messaging is responded.
Optionally, the step of also realizing following method when the processor executes described program:
Determine user's characteristic information;
It obtains and the matched target information of the user's characteristic information;
When receiving the play instruction to the target information, speech play is carried out to the target information.
Beneficial effects of the present invention are:
Scheme of the present invention is initiated by the voice learnt under mode of learning between user and voice response user
Interaction habits, user targetedly is initiated to voice and carries out intelligentized response so that the interaction between man-machine is more intelligent
Change, user experience is good.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, below the special specific implementation mode for lifting the present invention.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit are common for this field
Technical staff will become clear.Attached drawing only for the purpose of illustrating preferred embodiments, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is the flow chart of one embodiment of the invention voice interactive method;
Fig. 2 is the flow chart of one embodiment of the invention voice interactive method;
Fig. 3 is the flow chart of one embodiment of the invention voice interactive method;
Fig. 4 is the flow chart of one embodiment of the invention voice interactive method;
Fig. 5 is the structural schematic diagram of one embodiment of the invention voice interaction device;
Fig. 6 is the structural schematic diagram of one embodiment of the invention computer equipment;
The structural schematic diagram that Fig. 7 is an of the invention specific embodiment computer equipment when being robot.
Wherein:11- training modules, 111- collecting units, 112- units, 12- interactive modules, 13- voices open mould
Block, 14- associated storage modules, 15- volume adjusting modules, 16- determining modules, 17- acquisition modules, 18- voice playing modules,
21- memories, 22- processors, 23- sound collectors, 24- sound controllers, 25- soundanalyzers, 26- players, 27- enter keys
Disk, 28- displays.
Specific implementation mode
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Fig. 1 is referred to, in the first embodiment of the present invention, provides a kind of voice interactive method, including:
Step S101:Under mode of learning, according to preset learning training model, learn to carry out voice friendship between different user
Mutual interaction habits;
Step S102:Under speech interaction mode, when collecting the voice messaging of user, according to interaction habits, simulation
The user that interactive voice is carried out with user, responds voice messaging.
Preferably, in practical situation, under speech interaction mode, when collecting the voice messaging of user A, according to friendship
Mutually custom, simulation carry out the user B of interactive voice with user A, are responded to the voice messaging of user A.
Optionally, further include:
When collecting preset voice open command, speech interaction mode is opened.
Optionally, Fig. 2 is referred to, in step S101, under mode of learning, according to preset learning training model, is learned
The interaction habits of interactive voice are carried out between habit different user, including:
Step S011:Under mode of learning, acquisition voice initiates the voice messaging of user and voice response user;
Step S012:According to preset learning training model, using the voice messaging of acquisition as sample, study voice initiates to use
The interaction habits of interactive voice are carried out between family and voice response user.
Optionally, after the interaction habits that interactive voice is carried out between learning different user, further include:
The interaction habits that study is obtained initiate user according to voice and voice response user are associated storage.
Optionally, Fig. 3 is referred to, it is described that the voice messaging is responded, including:
Step S201:According to the volume of the voice messaging of collected user, determination rings the voice messaging
The volume value answered;
Step S202:According to determining volume value, voice messaging is responded.
Optionally, Fig. 4 is referred to, further includes:
Step S301:Determine user's characteristic information;
Step S302:It obtains and the matched target information of user's characteristic information;
Step S303:When receiving the play instruction to target information, speech play is carried out to target information.
In the second embodiment of the present invention, a kind of voice interaction device is provided, refers to Fig. 5, including:
Training module 11, under mode of learning, according to preset learning training model, learning to carry out between different user
The interaction habits of interactive voice;
Interactive module 12 is used under speech interaction mode, when collecting the voice messaging of the user, according to interaction
Custom, simulation carry out the user of interactive voice with user, are responded to voice messaging.
Optionally, further include:
Voice opening module 13, for when collecting preset voice open command, opening speech interaction mode.
Optionally, training module 11 includes:
Collecting unit 111, under mode of learning, acquisition voice initiates the voice messaging of user and voice response user;It is excellent
Choosing, it is additionally operable to acquire preset voice open command.
Unit 112, according to preset learning training model, using the voice messaging of acquisition as sample, study voice hair
Play the interaction habits that interactive voice is carried out between user and voice response user.
Optionally, further include:
Associated storage module 14 initiates user according to voice and voice response is used for that will learn obtained interaction habits
Family is associated storage.Under speech interaction mode, the device can identify be which user voice messaging.
Optionally, further include:
Volume adjusting module 15 is used for the volume of the voice messaging according to 111 collected user of collecting unit, really
The fixed volume value that the voice messaging is responded.
Optionally, further include:
Determining module 16, for determining user's characteristic information;
Acquisition module 17, for obtaining and the matched target information of user's characteristic information;
Voice playing module 18, for when receiving the play instruction to target information, voice to be carried out to target information
It plays.
In the third embodiment of the present invention, a kind of computer readable storage medium is provided, meter is stored on storage medium
Calculation machine program, the step of following method is realized when program is executed by processor:
Step S101:Under mode of learning, according to preset learning training model, learn to carry out voice friendship between different user
Mutual interaction habits;
Step S102:Under speech interaction mode, when collecting the voice messaging of the user, according to interaction habits,
Simulation carries out the user of interactive voice with user, is responded to voice messaging.
Optionally, the step of realizing following method when program is executed by processor:
When collecting preset voice open command, speech interaction mode is opened.
Optionally, under mode of learning, according to preset learning training model, learn to carry out interactive voice between different user
Interaction habits, the step of following method is realized when program is executed by processor:
Step S011:Under mode of learning, acquisition voice initiates the voice messaging of user and voice response user;
Step S012:According to preset learning training model, using the voice messaging of acquisition as sample, study voice initiates to use
The interaction habits of interactive voice are carried out between family and voice response user.
Optionally, after the interaction habits that interactive voice is carried out between learning different user, described program is executed by processor
The step of Shi Shixian following methods:
The interaction habits that study is obtained initiate user according to voice and voice response user are associated storage.
Optionally, the step of voice messaging being responded, following method is realized when program is executed by processor:
Step S201:According to the volume of the voice messaging of collected user, determination rings the voice messaging
The volume value answered;
Step S202:According to determining volume value, voice messaging is responded.
Optionally, the step of following method is also realized when program is executed by processor:
Step S301:Determine user's characteristic information;
Step S302:It obtains and the matched target information of user's characteristic information;
Step S303:When receiving the play instruction to target information, speech play is carried out to target information.
Fig. 1-6 is referred to, in the fourth embodiment of the present invention, provides a kind of computer equipment (referring to Fig. 6), including
Memory 21, processor 22 and it is stored in the computer program that can be run on memory 21 and on processor 22, processor 22
The step of following method being realized when executing program:
Step S101:Under mode of learning, according to preset learning training model, learn to carry out voice friendship between different user
Mutual interaction habits;
Step S102:Under speech interaction mode, when collecting the voice messaging of the user, according to interaction habits,
Simulation carries out the user of interactive voice with user, is responded to voice messaging.(referring specifically to Fig. 1)
Optionally, further include:
Sound collector 23 and sound controller 24, when sound collector 23 collects preset voice open command, acoustic control
Device 24 opens speech interaction mode.When sound collector 23 does not collect preset voice open command, make the computer
Equipment enters standby mode.
Optionally, sound collector 23 is additionally operable under mode of learning, and acquisition voice initiates user and voice response user
Voice messaging.
According to preset learning training model when processor 22 executes program, using the voice messaging of acquisition as sample, study
Voice initiates to carry out the interaction habits of interactive voice between user and voice response user.
Optionally, further include:
Soundanalyzer 25 initiates user and voice response user for that will learn obtained interaction habits according to voice
It is associated storage.
Optionally, Fig. 3 is referred to, the step of processor 22 also realizes following method when executing program:
Step S201:According to the volume of the voice messaging of collected user, determination rings the voice messaging
The volume value answered;
Step S202:According to determining volume value, voice messaging is responded.
Optionally, Fig. 4 is referred to, the step of processor 22 also realizes following method when executing program:
Step S301:Determine user's characteristic information;
Step S302:It obtains and the matched target information of user's characteristic information;
Step S303:When receiving the play instruction to target information, speech play is carried out to target information.
Voice interactive method, device and computer equipment provided by the invention can be applied in mother and baby, Empty nest elderly, delay
It solves in the real lifes such as the artificial intelligent voice service of manual service pressure, but the present invention does not do application scenarios unique restriction.
To make the present invention be more clearly understood, specific implementation scene is set forth below, and the present invention will be further described.
In the fifth embodiment of the present invention, Fig. 6, Fig. 7 are referred to, the preferred computer equipment of the embodiment of the present invention is application
Intelligence in mother and baby lives accompanies robot, at this point, speech interaction mode, which is sleep roars of laughter, sleeps pattern, cries and screams suddenly in baby
When, robot can simulate the sound of mother to pacify baby, and it is baby that voice, which initiates user, and voice response user is mother, is used
Family characteristic information includes baby's age size, includes the sea of 21 inner storage of memory with the matched target information of user's characteristic information
Measure baby nurse common sense and points for attention etc., memory 21 also store baby under mode of learning cry and scream sound custom and mother respond
Custom, baby cry and scream sound custom and to cry and scream custom respond mother response custom be between the two interaction practise
It is used, in the following, the present invention is described further in conjunction with specifically used scene.
This is equipped with switch button, the broadcast sound volume of manually controllable player 26 after intelligently accompanying the machine person.
Fig. 7 is referred to, robot fuselage front is equipped with the led display screens of display 28, for showing current date, baby
The characteristic informations such as date of birth, baby's size;
Be additionally provided with input keyboard 27, input on keyboard 27 and be provided with 1~9 equal 9 numbers, for input baby's birthday and
Calibrate current time;
Fuselage front also has:Common sense button presses the shield that common sense buttons play device 26 can play current age section baby
Manage the target informations such as common sense and points for attention;Sleep button presses sleep button, for when baby sleeping is cry and screamed according to study
The interaction habits simulation mother arrived, auxiliary mother comfort baby;Learn button, baby can be learnt by pressing study button robot
Custom of crying and screaming and mother, which respond, is accustomed to and carries out intellectual analysis associated storage, as mother robot simulation under sleep auxiliary mode
The sound source of sound;USB jack nurses common sense and points for attention, to obtain stylish nursing knowledge for updating baby.
Sound controller 24:When robot is in sleep pattern, by baby cry and scream sound acoustic control open sleep roars of laughter sleep pattern,
Here, baby cries and screams, sound is preset voice open command, sleeps pattern to make robot be in sleep roars of laughter
Working condition.When baby stop cry and scream, so that robot is in standby.
Sound collector 23:The voice messaging and mother cry and screamed using sound transducer acquisition baby pacify the voice of baby
Information;
Soundanalyzer 25:According to 23 collected voice messaging of sound collector, differentiation sound type is baby, still
Mother or other relatives, and under mode of learning, the interaction habits that study is obtained, according to voice initiate baby user and
Voice response mother user is associated storage;It is slept in sleep roars of laughter and discerns whether under pattern to cry and scream sound for baby.
Processor 22:Analysis baby cry and scream sound custom and mother respond custom, sleep roars of laughter sleep pattern under, when sound is adopted
When storage 23 collects the sound that baby cries and screams, according to the interaction habits between baby and mother, simulation mother to baby at this time
Cry and scream the most effective voice messaging of custom to reply, pacify baby, that is to say, that intelligent robot is retrieved under mode of learning
The sound of the maximally efficient mother of study pacifies baby, and processor 22 can also cry and scream the size of sound according to baby, adjust
Save the volume value for the voice messaging responded to baby.
Usage scenario 1:When taking robot, user can use input baby's date of birth, such as current 1 month of baby,
Robot is opened, presses common sense function key, you can play instruction is sent out to robot, due to 21 memory of memory in robot
It contains magnanimity baby and nurses the target informations such as common sense and points for attention, baby tells about at 1 month by player 26 in robot
Nurse common sense and mistaken ideas so that user can preferably nurse baby.If baby grows to 2 months, common sense function key, machine are pressed
Nursing common sense when device people will tell about baby 2 months greatly and mistaken ideas.That is, the robot in the embodiment of the present invention can companion
Grow up with baby, tells about the care tips etc. of age bracket residing for current baby.
Usage scenario 2:After taking robot, learning key is pressed when baby cries and screams and opens learning functionality, robot can be certainly
Cry and scream sound, mother of dynamic study baby pacifies and responds sound etc., i.e., interaction habits between the two.When baby sleeping, open
Sleep pattern, under sleep pattern, when baby cries and screams, robot can cry and scream sound according to baby, retrieve it is stored the most
The sound of the effective mother for pacifying baby responds baby, and simulates mother's sound according to the cry and scream big minor adjustment of sound of baby
The size of sound, when sound of crying and screaming is big, it is big to pacify sound, and when sound of crying and screaming is small, it is small to pacify sound, when baby enters sleep, machine
People enters suspend mode.
As it can be seen that intelligence provided in an embodiment of the present invention accompanies robot, suitable baby each age is provided for mothers
The nursing common sense of section and points for attention and mistaken ideas, and learn baby emphatically and cry and scream custom and mother to crying and screaming what custom responded
Nursing custom, when sleeping pattern in sleep roars of laughter, artificial intelligence mother's sound auxiliary pacifies baby, keeps mother's sleep as few as possible
Be disturbed, meet the actual use demand of user significantly.
In the sixth embodiment of the present invention, the preferred computer equipment of the embodiment of the present invention is to live applied to Empty nest elderly
In intelligence accompany robot, under mode of learning, intelligence accompany robot can learn in daily life between old man and sons and daughters
Carry out interactive voice interaction habits, after sons and daughters leave home, old man can exchange with robot dismiss solitarily and
Boring, when robot is under speech interaction mode, when robot collects old man's one's voice in speech, robot will mould
The sound of quasi- child responds the sound of old man, as a result, old man can in the long-term solitary life by with machine
The interaction of device people is preferably mediated solitarily, to improve the quality of life and physical and mental health of the elderly.Moreover, in order to enhance
For old man to the management quality of own health, the user's characteristic information that robot determines will will include old man's age bracket, gender, health
State etc., with the matched target information of user's characteristic information include 21 inner storage of memory for old man different age group,
Magnanimity under different health status nurses common sense and points for attention etc., to improve the health control quality of old man, enhances body
Quality.
Obviously, the present invention initiates the friendship between user and voice response user by the voice learnt under mode of learning
Mutually custom targetedly initiates user to voice and carries out intelligentized response so that the interaction between man-machine is more intelligent, uses
Family experience is good.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include:ROM, RAM, disk or CD etc..
In short, the foregoing is merely illustrative of the preferred embodiments of the present invention, it is not intended to limit the scope of the present invention.
All within the spirits and principles of the present invention, any modification, equivalent replacement, improvement and so on should be included in the present invention's
Within protection domain.
Claims (19)
1. a kind of voice interactive method, which is characterized in that including:
Under mode of learning, according to preset learning training model, learn the interaction habits of progress interactive voice between different user;
Under speech interaction mode, when collecting the voice messaging of the user, according to the interaction habits, simulation with it is described
User carries out the user of interactive voice, is responded to voice messaging.
2. voice interactive method as described in claim 1, which is characterized in that further include:
When collecting preset voice open command, the speech interaction mode is opened.
3. voice interactive method as described in claim 1, which is characterized in that it is described under mode of learning, according to preset
Training pattern is practised, the interaction habits of progress interactive voice between different user are learnt, including:
Under mode of learning, acquisition voice initiates the voice messaging of user and voice response user;
According to preset learning training model, using the voice messaging of acquisition as sample, study voice initiates user and voice response
The interaction habits of interactive voice are carried out between user.
4. voice interactive method as claimed in claim 3, which is characterized in that carry out interactive voice between learning different user
After interaction habits, further include:
The interaction habits that study is obtained initiate user according to voice and voice response user are associated storage.
5. voice interactive method as described in claim 1, which is characterized in that described to be responded to the voice messaging, packet
It includes:
According to the volume of the voice messaging of the collected user, the volume responded to the voice messaging is determined
Value;
According to determining volume value, the voice messaging is responded.
6. voice interactive method as described in claim 1, which is characterized in that further include:
Determine user's characteristic information;
It obtains and the matched target information of the user's characteristic information;
When receiving the play instruction to the target information, speech play is carried out to the target information.
7. a kind of voice interaction device, which is characterized in that including:
Training module, under mode of learning, according to preset learning training model, learning to carry out voice friendship between different user
Mutual interaction habits;
Interactive module, under speech interaction mode, when collecting the voice messaging of the user, being practised according to the interaction
Used, simulation carries out the user of interactive voice with the user, is responded to voice messaging.
8. voice interaction device as claimed in claim 7, which is characterized in that further include:
Voice opening module, for when collecting preset voice open command, opening the speech interaction mode.
9. voice interaction device as claimed in claim 7, which is characterized in that the training module includes:
Collecting unit, under mode of learning, acquisition voice initiates the voice messaging of user and voice response user;
Unit, according to preset learning training model, using the voice messaging of acquisition as sample, study voice initiate user and
The interaction habits of interactive voice are carried out between voice response user.
10. voice interaction device as claimed in claim 9, which is characterized in that further include:
Associated storage module initiates user according to voice and voice response user carries out for that will learn obtained interaction habits
Associated storage.
11. voice interaction device as claimed in claim 7, which is characterized in that further include:
Volume adjusting module is used for the volume of the voice messaging according to the collected user, determines and believes the voice
Cease the volume value responded.
12. voice interaction device as claimed in claim 7, which is characterized in that further include:
Determining module, for determining user's characteristic information;
Acquisition module, for obtaining and the matched target information of the user's characteristic information;
Voice playing module, for when receiving the play instruction to the target information, language to be carried out to the target information
Sound plays.
13. a kind of computer readable storage medium, which is characterized in that computer program is stored on the storage medium, it is described
The step of any one of claim 1 to 6 the method is realized when program is executed by processor.
14. a kind of computer equipment, which is characterized in that including memory, processor and be stored on the memory and can be
The step of computer program run on the processor, the processor realizes following method when executing described program:
Under mode of learning, according to preset learning training model, learn the interaction habits of progress interactive voice between different user;
Under speech interaction mode, when collecting the voice messaging of the user, according to the interaction habits, simulation with it is described
User carries out the user of interactive voice, is responded to voice messaging.
15. computer equipment as claimed in claim 14, which is characterized in that further include:
Sound collector and sound controller, when the sound collector collects preset voice open command, the sound controller
Open the speech interaction mode.
16. computer equipment as claimed in claim 15, which is characterized in that
The sound collector is additionally operable under mode of learning, and acquisition voice initiates the voice letter of user and voice response user
Breath;
According to preset learning training model when the processor executes described program, using the voice messaging of acquisition as sample, learn
Idiom sound initiates to carry out the interaction habits of interactive voice between user and voice response user.
17. computer equipment as claimed in claim 16, which is characterized in that further include:
Soundanalyzer initiates user according to voice and voice response user is closed for that will learn obtained interaction habits
Connection storage.
18. computer equipment as claimed in claim 14, which is characterized in that the processor is also realized when executing described program
The step of following method:
According to the volume of the voice messaging of the collected user, the volume responded to the voice messaging is determined
Value;
According to determining volume value, the voice messaging is responded.
19. computer equipment as claimed in claim 14, which is characterized in that the processor is also realized when executing described program
The step of following method:
Determine user's characteristic information;
It obtains and the matched target information of the user's characteristic information;
When receiving the play instruction to the target information, speech play is carried out to the target information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810213805.2A CN108470567B (en) | 2018-03-15 | 2018-03-15 | Voice interaction method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810213805.2A CN108470567B (en) | 2018-03-15 | 2018-03-15 | Voice interaction method and device, storage medium and computer equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108470567A true CN108470567A (en) | 2018-08-31 |
CN108470567B CN108470567B (en) | 2021-08-24 |
Family
ID=63264450
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810213805.2A Active CN108470567B (en) | 2018-03-15 | 2018-03-15 | Voice interaction method and device, storage medium and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108470567B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109903755A (en) * | 2019-02-26 | 2019-06-18 | 珠海格力电器股份有限公司 | A kind of voice interactive method, device, storage medium and air conditioner |
CN110186171A (en) * | 2019-05-30 | 2019-08-30 | 广东美的制冷设备有限公司 | Air conditioner and its control method and computer readable storage medium |
CN110555981A (en) * | 2019-09-27 | 2019-12-10 | 广东美的制冷设备有限公司 | Response method and device, search method and device, remote controller, terminal and medium |
CN111862950A (en) * | 2020-08-03 | 2020-10-30 | 深圳作为科技有限公司 | Interactive multifunctional elderly care robot recognition system |
CN112634886A (en) * | 2020-12-02 | 2021-04-09 | 海信电子科技(武汉)有限公司 | Interaction method of intelligent equipment, server, computing equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004145237A (en) * | 2002-10-25 | 2004-05-20 | Icd Kk | Interactive doll with translating function |
CN103916511A (en) * | 2013-01-08 | 2014-07-09 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN105845136A (en) * | 2015-01-13 | 2016-08-10 | 中兴通讯股份有限公司 | Voice control method and device, and terminal |
CN106547884A (en) * | 2016-11-03 | 2017-03-29 | 深圳量旌科技有限公司 | A kind of behavior pattern learning system of augmentor |
CN106781729A (en) * | 2016-12-29 | 2017-05-31 | 昆山库尔卡人工智能科技有限公司 | A kind of acoustic control man-machine interaction robot |
CN106875944A (en) * | 2017-01-15 | 2017-06-20 | 深圳市丰巨泰科电子有限公司 | A kind of system of Voice command home intelligent terminal |
CN107464564A (en) * | 2017-08-21 | 2017-12-12 | 腾讯科技(深圳)有限公司 | voice interactive method, device and equipment |
CN107678823A (en) * | 2017-09-30 | 2018-02-09 | 广东欧珀移动通信有限公司 | Control method, device and the storage medium and mobile terminal of mobile terminal application |
-
2018
- 2018-03-15 CN CN201810213805.2A patent/CN108470567B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004145237A (en) * | 2002-10-25 | 2004-05-20 | Icd Kk | Interactive doll with translating function |
CN103916511A (en) * | 2013-01-08 | 2014-07-09 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN105845136A (en) * | 2015-01-13 | 2016-08-10 | 中兴通讯股份有限公司 | Voice control method and device, and terminal |
CN106547884A (en) * | 2016-11-03 | 2017-03-29 | 深圳量旌科技有限公司 | A kind of behavior pattern learning system of augmentor |
CN106781729A (en) * | 2016-12-29 | 2017-05-31 | 昆山库尔卡人工智能科技有限公司 | A kind of acoustic control man-machine interaction robot |
CN106875944A (en) * | 2017-01-15 | 2017-06-20 | 深圳市丰巨泰科电子有限公司 | A kind of system of Voice command home intelligent terminal |
CN107464564A (en) * | 2017-08-21 | 2017-12-12 | 腾讯科技(深圳)有限公司 | voice interactive method, device and equipment |
CN107678823A (en) * | 2017-09-30 | 2018-02-09 | 广东欧珀移动通信有限公司 | Control method, device and the storage medium and mobile terminal of mobile terminal application |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109903755A (en) * | 2019-02-26 | 2019-06-18 | 珠海格力电器股份有限公司 | A kind of voice interactive method, device, storage medium and air conditioner |
CN110186171A (en) * | 2019-05-30 | 2019-08-30 | 广东美的制冷设备有限公司 | Air conditioner and its control method and computer readable storage medium |
CN110555981A (en) * | 2019-09-27 | 2019-12-10 | 广东美的制冷设备有限公司 | Response method and device, search method and device, remote controller, terminal and medium |
CN111862950A (en) * | 2020-08-03 | 2020-10-30 | 深圳作为科技有限公司 | Interactive multifunctional elderly care robot recognition system |
CN112634886A (en) * | 2020-12-02 | 2021-04-09 | 海信电子科技(武汉)有限公司 | Interaction method of intelligent equipment, server, computing equipment and storage medium |
CN112634886B (en) * | 2020-12-02 | 2024-03-01 | 海信电子科技(武汉)有限公司 | Interaction method of intelligent equipment, server, computing equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108470567B (en) | 2021-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108470567A (en) | A kind of voice interactive method, device, storage medium and computer equipment | |
CN101648079B (en) | Emotional doll | |
CN108009954A (en) | A kind of Formulating Teaching Program method, apparatus, system and electronic equipment | |
CN204010236U (en) | A kind of baby monitor | |
CN205817875U (en) | Interactive emotional robot | |
CN204248895U (en) | A kind of pet type is accompanied and attended to robot and system | |
CN103207579A (en) | Autonomous learning assisting, supervising and urging system for primary and secondary school students | |
CN113375316B (en) | Control method and device for air conditioner and air conditioner | |
CN107085511A (en) | Control method, control device and equipment | |
CN105147242A (en) | Sleep environment monitoring device and monitoring method thereof | |
JP7367530B2 (en) | Information processing device, information processing method, and program | |
CN106295158A (en) | A kind of automatic aided management system of infant, management method and equipment | |
CN202567156U (en) | Intelligent storage cabinet for children | |
CN206383144U (en) | A kind of multi-functional early education robot | |
CN205692568U (en) | Innovation work room application system | |
CN206096823U (en) | System of giving lessons is assisted to internet | |
CN109889643A (en) | A kind of tone information broadcasting method and device and storage medium | |
CN206383145U (en) | It is a kind of to be used for the early education robot of 0~6 years old children | |
Jin | Study on influences of artificial intelligence era on early childhood family education in China | |
Lyall et al. | Redefining rest: a taxonomy of contemporary digital sleep technologies | |
CN108346435B (en) | Voice simulation training system for pension nursing staff | |
CN205230116U (en) | Controlling means based on virtual endowment community | |
CN204996131U (en) | Multi -functional toy | |
CN204229460U (en) | Intelligence class board | |
CN203885482U (en) | Children's body temperature sensing and warning apparatus |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |