CN108806686A - A kind of voice searches the startup control method and private tutor's equipment of topic application - Google Patents
A kind of voice searches the startup control method and private tutor's equipment of topic application Download PDFInfo
- Publication number
- CN108806686A CN108806686A CN201810747125.9A CN201810747125A CN108806686A CN 108806686 A CN108806686 A CN 108806686A CN 201810747125 A CN201810747125 A CN 201810747125A CN 108806686 A CN108806686 A CN 108806686A
- Authority
- CN
- China
- Prior art keywords
- voice
- equipment
- private tutor
- topic
- voice signal
- 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
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- 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
- G10L2015/223—Execution procedure of a spoken command
-
- 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
A kind of voice searches the startup control method of topic application and private tutor's equipment, this method include：Private tutor's equipment intercepts the extraneous voice signal sent out；Whether private tutor's equipment detects the voice signal comprising the wake-up word for searching topic application for waking up the voice of private tutor's equipment；If voice signal includes the wake-up word for searching topic application for waking up the voice of private tutor's equipment, private tutor's equipment identifies the user's gender for the extraneous user for sending out voice signal according to voice signal；Private tutor's equipment obtains the instant type of emotion of extraneous user；Private tutor's equipment shows that voice searches the voice that topic is applied and searches topic interface, and searches the virtual animal that output matches with user's gender on topic interface in voice；Wherein, what intonation output and the extraneous user that virtual animal is used to match according to instant type of emotion sent out, which search, inscribes the corresponding response voice of voice.Implement the embodiment of the present invention, is conducive to excite students in middle and primary schools' to search topic interest.
Description
Technical field
The present invention relates to private tutor's equipment technical fields, and in particular to a kind of voice searches startup control method and the family of topic application
Teach equipment.
Background technology
Currently, more and more students in middle and primary schools carry out assisted learning using private tutor's equipment (such as private tutor's machine).In private tutor's equipment
In practical application, students in middle and primary schools, which can start the voice in private tutor's equipment and search topic application, to carry out voice searches topic, and by searching
Rope to topic answer, to realize assisted learning.In practice, it has been found that voice is searched after topic application startup, private tutor's equipment
Often export more dull voice search topic interface so that students in middle and primary schools carry out searching topic, be unfavorable for excite students in middle and primary schools search inscribe it is emerging
Interest.
Invention content
The embodiment of the invention discloses startup control methods and private tutor's equipment that a kind of voice searches topic application, are conducive to excite
Students in middle and primary schools' searches topic interest.
First aspect of the embodiment of the present invention discloses the startup control method that a kind of voice searches topic application, the method includes：
Private tutor's equipment intercepts the extraneous voice signal sent out；
Private tutor's equipment detects whether the voice signal answers comprising searching topic for waking up the voice of private tutor's equipment
Wake-up word；
If the voice signal includes the wake-up word for searching topic application for waking up the voice of private tutor's equipment, the private tutor
Equipment identifies the user's gender for the extraneous user for sending out the voice signal according to the voice signal；
Private tutor's equipment obtains the instant type of emotion of the extraneous user；
Private tutor's equipment shows that the voice searches the voice that topic is applied and searches topic interface, and is searched on topic interface in the voice
The virtual animal that output matches with user's gender；Wherein, the virtual animal is used for according to the instant type of emotion
What the intonation output to match and the extraneous user sent out, which search, inscribes the corresponding response voice of voice.
As an alternative embodiment, in first aspect of the embodiment of the present invention, private tutor's equipment is according to
Voice signal identifies the user's gender for the extraneous user for sending out the voice signal, including：
Private tutor's equipment extracts the sound characteristic of the voice signal according to the voice signal；
Private tutor's equipment identifies that sending out the extraneous of the voice signal uses according to the sound characteristic of the voice signal
User's gender at family.
As an alternative embodiment, in first aspect of the embodiment of the present invention, described in private tutor's equipment acquisition
The instant type of emotion of extraneous user, including：
Private tutor's equipment identifies the instant type of emotion of the extraneous user according to the intonation of the voice signal；
Alternatively, private tutor's equipment obtains the instant type of emotion of the extraneous user, including：
Whether private tutor's equipment detection is currently wirelessly connected with wearable device；
If private tutor's equipment is currently wirelessly connected with wearable device, private tutor's equipment obtains described wearable set
The sound characteristic of standby wearer；
The sound of the sound characteristic and the voice signal of the wearer of wearable device described in private tutor's device authentication
Whether feature matches；
If it does, private tutor's equipment notifies the wearable device to obtain working as the wearer of the wearable device
The current blood pressure data of preceding heart rate data and the wearer, and front center is worked as according to the wearer by the wearable device
The current blood pressure data of rate data and the wearer determine the instant type of emotion of the wearer；
Private tutor's equipment receives the instant type of emotion for the wearer that the wearable device is sent, as the external world
The instant type of emotion of user.
As an alternative embodiment, in first aspect of the embodiment of the present invention, the method further includes：
What private tutor's equipment intercepted that extraneous user sends out searches topic voice；
Private tutor's equipment searches topic voice is corresponding and search topic result described in obtaining；
Private tutor's equipment by it is described search topic voice it is corresponding search topic result export to the voice search topic interface show
Show；
And private tutor's equipment controls the virtual animal and is exported according to the intonation that the instant type of emotion matches
The corresponding response voice of topic voice is searched described in being sent out with the extraneous user.
As an alternative embodiment, in first aspect of the embodiment of the present invention, the method further includes：
The corresponding student personal attribute letter of sound characteristic whether private tutor's equipment query is stored with the voice signal
Breath；Wherein, student's personal attribute information includes at least pupilage information and the corresponding target curriculum schedule of student, the mesh
Mark multiple and different study subject and the corresponding teacher of each described study subject that curriculum schedule includes at least student's study
Terminal iidentification；
If the corresponding student's personal attribute information of the sound characteristic for being stored with the voice signal, private tutor's equipment with
The topic result of searching is foundation, and the corresponding target of topic result of searching is inquired from the target curriculum schedule and learns subject；With
And the corresponding target teacher terminal iidentification of the target study subject is inquired from the target curriculum schedule；
The topic voice of searching is converted into searching topic word by private tutor's equipment, and by the pupilage information, described search
Topic word and the target teacher terminal iidentification are reported to cloud platform, so that the cloud platform is according to the target teacher terminal
Mark by the pupilage information and described search topic word to be sent to teacher belonging to the target teacher terminal iidentification whole
End.
Second aspect of the embodiment of the present invention discloses a kind of private tutor's equipment, including：
Unit is intercepted, for intercepting the extraneous voice signal sent out；
Detection unit, for detecting whether the voice signal answers comprising searching topic for waking up the voice of private tutor's equipment
Wake-up word；
Recognition unit, for detecting that the voice signal includes for waking up private tutor's equipment in the detection unit
Voice search topic application wake-up word when, according to the voice signal, identify the extraneous user's for sending out the voice signal
User's gender；
First acquisition unit, the instant type of emotion for obtaining the extraneous user；
Control unit searches topic interface for showing that the voice searches the voice that topic is applied, and searches topic interface in the voice
The virtual animal that upper output matches with user's gender；Wherein, the virtual animal is used for according to the instant mood class
What the output of intonation that type matches and the extraneous user sent out, which search, inscribes the corresponding response voice of voice.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the recognition unit is specifically used for
Detect that the voice signal includes the wake-up that topic application is searched for waking up the voice of private tutor's equipment in the detection unit
When word, according to the voice signal, the sound characteristic of the voice signal is extracted；And the sound according to the voice signal
Feature identifies the user's gender for the extraneous user for sending out the voice signal.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the first acquisition unit is specific
For the intonation according to the voice signal, the instant type of emotion of the extraneous user is identified；
Alternatively, the first acquisition unit includes：
Detection sub-unit, for detecting whether private tutor's equipment is currently wirelessly connected with wearable device；
Subelement is obtained, it is wearable for detecting that private tutor's equipment is currently wirelessly connected in the detection sub-unit
When equipment, the sound characteristic of the wearer of the wearable device is obtained；
Verify subelement, the sound of the sound characteristic and the voice signal of the wearer for verifying the wearable device
Whether sound feature matches；
Interaction subelement, for when the verification result of the verification subelement is matching, notifying the wearable device
Obtain the Current heart rate data of the wearer of the wearable device and the current blood pressure data of the wearer, and by it is described can
Wearable device determines the wearing according to the Current heart rate data of the wearer and the current blood pressure data of the wearer
The instant type of emotion of person；
The interactive subelement is additionally operable to receive the instant mood class for the wearer that the wearable device is sent
Type, the instant type of emotion as extraneous user.
As an alternative embodiment, in second aspect of the embodiment of the present invention：
It is described to intercept unit, it is additionally operable to intercept that extraneous user sends out searches topic voice；
Private tutor's equipment further includes second acquisition unit, wherein：
The second acquisition unit, for obtain it is described search topic voice be corresponding search topic result；
Described control unit, be additionally operable to by it is described search topic voice it is corresponding search topic result export to the voice search topic interface
It is shown；And it controls the virtual animal and is exported and the external world according to the intonation that the instant type of emotion matches
Described search that user sends out inscribes the corresponding response voice of voice.
As an alternative embodiment, in second aspect of the embodiment of the present invention, private tutor's equipment further includes：
Query unit, for inquiring the corresponding student personal attribute letter of sound characteristic for whether being stored with the voice signal
Breath；Wherein, student's personal attribute information includes at least pupilage information and the corresponding target curriculum schedule of student, the mesh
Mark multiple and different study subject and the corresponding teacher of each described study subject that curriculum schedule includes at least student's study
Terminal iidentification；And if the corresponding student's personal attribute information of the sound characteristic for being stored with the voice signal, is searched with described
Topic result is foundation, and the corresponding target of topic result of searching is inquired from the target curriculum schedule and learns subject；And from institute
It states and inquires the corresponding target teacher terminal iidentification of the target study subject in target curriculum schedule；
Converting unit, for being converted into searching topic word by the topic voice of searching, and by the pupilage information, described search
Topic word and the target teacher terminal iidentification are reported to cloud platform, so that the cloud platform is according to the target teacher terminal
Mark by the pupilage information and described search topic word to be sent to teacher belonging to the target teacher terminal iidentification whole
End.
The third aspect of the embodiment of the present invention discloses a kind of private tutor's equipment, including：
It is stored with the memory of executable program code；
The processor coupled with the memory；
The processor calls the executable program code stored in the memory, executes the embodiment of the present invention the
The voice disclosed in one side searches the startup control method of topic application.
Fourth aspect of the embodiment of the present invention discloses a kind of computer readable storage medium, stores computer program, wherein
The computer program makes computer execute the startup that the voice disclosed in first aspect of the embodiment of the present invention searches topic application
Control method.
Compared with prior art, the embodiment of the present invention has the advantages that：
In the embodiment of the present invention, private tutor's equipment detects that the extraneous voice signal sent out includes for waking up private tutor's equipment
When voice searches the wake-up word of topic application, private tutor's equipment can identify the external world for sending out the voice signal according to the voice signal
User's gender of user；Further, private tutor's equipment this can obtain the instant type of emotion of external world user, and show voice
The voice for searching topic application searches topic interface, and searches the virtual animal that output matches with user's gender on topic interface in voice, empty
What intonation output and the external world user that quasi- animal is used to match according to the instant type of emotion sent out search, and to inscribe voice corresponding
Response voice.As it can be seen that implementing the embodiment of the present invention, private tutor's equipment can search the extraneous use of load on topic interface in the voice of display
The virtual animal that user's gender at family matches, so that the virtual animal can be according to the instant type of emotion phase of extraneous user
What intonation output and the external world user matched sent out, which search, inscribes the corresponding response voice of voice, to be conducive to excitation students in middle and primary schools
Search topic interest.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the flow diagram for the startup control method that a kind of voice disclosed by the embodiments of the present invention searches topic application；
Fig. 2 is the flow diagram for the startup control method that another voice disclosed by the embodiments of the present invention searches topic application；
Fig. 3 is a kind of structural schematic diagram of private tutor's equipment disclosed by the embodiments of the present invention；
Fig. 4 is the structural schematic diagram of another private tutor's equipment disclosed by the embodiments of the present invention；
Fig. 5 is the structural schematic diagram of another private tutor's equipment disclosed by the embodiments of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
It should be noted that the term " comprising " and " having " in the embodiment of the present invention and attached drawing and their any changes
Shape, it is intended that cover and non-exclusive include.Such as contain the process of series of steps or unit, method, system, product or
Equipment is not limited to the step of having listed or unit, but further includes the steps that optionally not listing or unit or optional
Ground further includes for the intrinsic other steps of these processes, method, product or equipment or unit.
The embodiment of the invention discloses startup control methods and private tutor's equipment that a kind of voice searches topic application, are conducive to excite
Students in middle and primary schools' searches topic interest.It is described in detail separately below.
Embodiment one
The flow for inscribing the startup control method applied is searched referring to Fig. 1, Fig. 1 is a kind of voice disclosed by the embodiments of the present invention
Schematic diagram.As shown in Figure 1, the startup control method that the voice searches topic application may comprise steps of：
101, private tutor's equipment intercepts the extraneous voice signal sent out.
In the embodiment of the present invention, private tutor's equipment after power-up, can start the voice listening functions of private tutor's equipment, and
Private tutor's equipment can intercept the extraneous voice signal sent out in real time by the voice listening functions for the private tutor's equipment having been turned on.
Optionally, in the embodiment of the present invention, private tutor's equipment after power-up, can detect whether that receiving extraneous user is in
Teach the first track for opening voice listening functions inputted on the display screen of equipment, if received, just start private tutor's equipment
Voice listening functions, so as to reduce the power consumption of private tutor's equipment；Correspondingly, private tutor's equipment after power-up, can detect
Whether second track for close voice listening functions that extraneous user on the display screen of private tutor equipment input is received, if
It receives, the voice listening functions of private tutor's equipment can be closed, so as to reduce the power consumption of private tutor's equipment.
102, private tutor's equipment detects whether the voice signal includes to search calling out for topic application for waking up the voice of private tutor's equipment
Awake word；If the voice signal includes the wake-up word for searching topic application for waking up the voice of private tutor's equipment, step 103- steps are executed
105；If the voice signal does not include the wake-up word for searching topic application for waking up the voice of private tutor's equipment, terminate this flow.
For example, private tutor's equipment can detect whether the voice signal includes to search topic for waking up the voice of private tutor's equipment
The wake-up word " the small small cloth of cloth " of application；If the voice signal includes the wake-up word for searching topic application for waking up the voice of private tutor's equipment
" the small small cloth of cloth " executes step 103；If the voice signal does not include the wake-up for searching topic application for waking up the voice of private tutor's equipment
Word " the small small cloth of cloth ", terminates this flow.
103, private tutor's equipment identifies the user's gender for the extraneous user for sending out the voice signal according to the voice signal.
In the embodiment of the present invention, private tutor's equipment can extract the sound characteristic of the voice signal according to the voice signal；With
And private tutor's equipment can identify the user for the extraneous user for sending out the voice signal according to the sound characteristic of the voice signal
Gender.
For example, for private tutor's equipment according to the voice signal, the tone that can extract the voice signal (belongs to a kind of sound
Feature), and private tutor's equipment can identify the use for the extraneous user for sending out the voice signal according to the tone of the voice signal
Family gender.Since the vocal cords of male are longer, wider, thicker, so frequency is low when vibration, the tone sent out is low；And the sound of women
Band is shorter, relatively thin, relatively narrow, so frequency is high when vibration, the tone sent out is high；Therefore, if the tone of the voice signal is relatively low,
User's gender that private tutor's equipment can go out the extraneous user of the voice signal is male；If the tone of the voice signal is higher,
User's gender that private tutor's equipment can go out the extraneous user of the voice signal is women.
104, private tutor's equipment obtains the instant type of emotion of external world user.
As an alternative embodiment, in the embodiment of the present invention, private tutor's equipment can be according to the language of the voice signal
It adjusts, identifies the instant type of emotion of extraneous user；Wherein, the instant type of emotion of extraneous user may include depressed class
Type and type in high spirits.For example, when the intonation of the voice signal is high hole intonation, private tutor's equipment can identify outer
The instant type of emotion of boundary user is type in high spirits；When the intonation of the voice signal is droning intonation, private tutor's equipment can
To identify the instant type of emotion of extraneous user for depressed type.
As another optional embodiment, in the embodiment of the present invention, private tutor's equipment obtains the instant of external world user
Type of emotion, including：
Whether the detection of private tutor's equipment is currently wirelessly connected with wearable device；
If private tutor's equipment is currently wirelessly connected with wearable device, private tutor's equipment obtains the wearer's of wearable device
Sound characteristic；
And the sound characteristic of wearer of private tutor's device authentication wearable device is with the sound characteristic of the voice signal
No matching；
If it does, illustrating that the wearer of extraneous user and wearable device is the same user, correspondingly, private tutor's equipment
Wearable device can be notified to obtain the current blood pressure data of the Current heart rate data and wearer of the wearer of wearable device,
And by wearable device according to the Current heart rate data of wearer and the current blood pressure data of wearer determine wearer i.e.
When type of emotion；Wherein, wearable device is more than specified heart rate threshold in Current heart rate data, and current blood pressure data is more than
When specified blood pressure thresholds, identify that the instant type of emotion of wearer is type in high spirits；Alternatively, not surpassing in Current heart rate data
Specified heart rate threshold is crossed, and when current blood pressure data is less than specified blood pressure thresholds, identifies the instant type of emotion of wearer
For depressed type；
And private tutor's equipment receives the instant type of emotion for the wearer that wearable device is sent, as extraneous user's
Instant type of emotion.
Wherein, implement the above embodiment, can accurately be identified due to the wearable device that extraneous user wears outer
The instant type of emotion of boundary user is simultaneously sent to private tutor's equipment, so that private tutor's equipment can obtain accurate extraneous user's
Instant type of emotion.
105, private tutor's equipment shows that voice searches the voice that topic is applied and searches topic interface, and searches output on topic interface in voice and be somebody's turn to do
The virtual animal that user's gender matches；Wherein, virtual animal is used to export according to the intonation that the instant type of emotion matches
The corresponding response voice of topic voice is searched with what external world user sent out.
For example, the virtual animal to match with user's gender can be that user's gender owning user is generally liked
Virtual animal.For example, when user's gender is male, the virtual animal that matches with user's gender can be virtual dog,
Virtual tortoise etc.；When user's gender is female male, the virtual animal that matches with user's gender can be virtual cat, virtual
Bird etc..
It should be noted that it is user's property in advance that the virtual animal to match with user's gender, which can also be private tutor's equipment,
Any virtual animal in the virtual animal set not configured, the embodiment of the present invention are not construed as limiting.
In the embodiment of the present invention, the major function for the intonation which matches is for improving extraneous user
Instant mood.For example, when which is depressed type, virtual animal can be used for low according to mood
It falls the happy intonation output of type matching and external world user sends out searches and inscribe the corresponding response voice of voice；Alternatively, should
When instant type of emotion is type in high spirits, virtual animal can be used for the gentle intonation according to type matching in high spirits
What output and external world user sent out, which search, inscribes the corresponding response voice of voice.
In the embodiment of the present invention, respond voice can be external world user send out search topic voice it is corresponding search inscribe result into
The output voice that row text/voice is converted to, for example, the topic voice of searching that external world user sends out is that " radical for wearing word is assorted
" when, it can be that " wearing the radical of word is that external world user sent out, which searches the corresponding topic result of searching of topic voice,：Ten ", correspondingly, return
Answer voice can be external world user send out search topic voice it is corresponding search topic result " wearing the radical of word is：Ten " progress words/
The output voice that voice is converted to.In another example the topic voice of searching that external world user sends out is " some to be recommended to describe about spring
Good sentence, I will write text " when, what external world user sent out search topic voice is corresponding search topic result can be " drizzle such as silk,
Spring rain such as oil ", correspondingly, respond voice can be external world user send out search topic voice it is corresponding search inscribe result " drizzle is such as
Silk, spring rain such as oil " carries out the output voice that text/voice is converted to.
In the embodiment of the present invention, it can be that searching of sending out of external world user inscribes that voice is corresponding searches topic result to respond voice
Voice is encouraged in the study of (such as knowledge point video), for example, the topic voice of searching that external world user sends out is that " I wants to see about rational
Video " when, what external world user sent out search topic voice is corresponding to be searched the video that topic result can be rational and correspondingly returns
It can be that voice is encouraged in the study for the video for searching the corresponding rational of topic voice that external world user sends out to answer voice, for example, should
It can be " to find the video that master teaches corresponding rational for you, trying to learn " that voice is encouraged in study.
As it can be seen that implementing method described in Fig. 1, private tutor's equipment can search the extraneous use of load on topic interface in the voice of display
The virtual animal that user's gender at family matches, so that the virtual animal can be according to the instant type of emotion phase of extraneous user
What intonation output and the external world user matched sent out, which search, inscribes the corresponding response voice of voice, to be conducive to excitation students in middle and primary schools
Search topic interest.
Embodiment two
Referring to Fig. 2, Fig. 2 is the stream for the startup control method that another voice disclosed by the embodiments of the present invention searches topic application
Journey schematic diagram.As shown in Fig. 2, the startup control method that the voice searches topic application may comprise steps of：
201, private tutor's equipment intercepts the extraneous voice signal sent out.
202, private tutor's equipment detects whether the voice signal includes to search calling out for topic application for waking up the voice of private tutor's equipment
Awake word；If the voice signal includes the wake-up word for searching topic application for waking up the voice of private tutor's equipment, step 203- steps are executed
210；If the voice signal does not include the wake-up word for searching topic application for waking up the voice of private tutor's equipment, terminate this flow.
203, private tutor's equipment identifies the user's gender for the extraneous user for sending out the voice signal according to the voice signal.
In the embodiment of the present invention, private tutor's equipment can extract the sound characteristic of the voice signal according to the voice signal；With
And private tutor's equipment can identify the user for the extraneous user for sending out the voice signal according to the sound characteristic of the voice signal
Gender.
Whether 204, private tutor's equipment detection is currently wirelessly connected with wearable device, if so, obtaining wearable device
The sound characteristic of wearer；Verify sound characteristic and the voice signal of the wearer of wearable device sound characteristic whether
Match, if it does, notice wearable device obtain wearable device wearer Current heart rate data and wearer it is current
Blood pressure data, and determine to wear according to the Current heart rate data of wearer and the current blood pressure data of wearer by wearable device
The instant type of emotion of wearer.
205, private tutor's equipment receives the instant type of emotion for the wearer that wearable device is sent, and what it is as extraneous user is
When type of emotion.
206, private tutor's equipment shows that voice searches the voice that topic is applied and searches topic interface, and searches output on topic interface in voice and be somebody's turn to do
The virtual animal that user's gender matches；Wherein, virtual animal is used to export according to the intonation that the instant type of emotion matches
The corresponding response voice of topic voice is searched with what external world user sent out.
What 207, private tutor's equipment intercepted that extraneous user sends out searches topic voice, and obtains this and search that topic voice is corresponding to search topic knot
Fruit.
208, private tutor's equipment by this search topic voice it is corresponding search topic result export to voice search topic interface show.
209, private tutor's equipment control virtual animal exports and extraneous user according to the intonation that the instant type of emotion matches
This sent out searches the topic corresponding response voice of voice.
210, whether private tutor's equipment query is stored with the corresponding student's personal attribute information of sound characteristic of the voice signal；
Wherein, student's personal attribute information includes at least pupilage information and the corresponding target curriculum schedule of student, and target curriculum schedule is extremely
Include multiple and different study subjects and each corresponding teacher's terminal iidentification of study subject of student's study less；If deposited
The corresponding student's personal attribute information of sound characteristic of the voice signal is contained, step 211 is executed；If not being stored with the voice
The corresponding student's personal attribute information of sound characteristic of signal, terminates this flow.
Wherein, teacher's terminal iidentification can be the account of the phone number of teacher's terminal or the teaching application of teacher's terminal installation
Number information.
211, private tutor's equipment searches topic result as foundation using this, this is inquired from target curriculum schedule and searches the corresponding mesh of topic result
Mark study subject；And the corresponding target teacher terminal iidentification of target study subject is inquired from target curriculum schedule.
212, this is searched topic voice and is converted into searching topic word by private tutor's equipment, and by pupilage information, search topic word and
Target teacher's terminal iidentification is reported to cloud platform so that cloud platform is according to target teacher's terminal iidentification, by pupilage information and
It searches topic word and is sent to teacher's terminal belonging to target teacher's terminal iidentification.
In the embodiment of the present invention, implement above-mentioned steps 210- steps 212, allows teacher according to some of certain being collected into
What life was sent out on the taught subject of the teacher (such as Chinese language) searches topic word, finds these students in taught subject (such as language of the teacher
Text) on the problem of encountering so that the teacher asking of targetedly further can explaining that the student encounters to these students
Topic, to be conducive to be promoted the learning efficiency of the student.
As an alternative embodiment, in the embodiment of the present invention, teacher's terminal belonging to target teacher's terminal iidentification
After receiving the pupilage information of cloud platform transmission and searching topic word, teacher can be prompted to reward the pupilage information institute
The virtual present (such as virtual american sage herb) that the student of category is used to that student to be encouraged to learn, and the religion belonging to target teacher's terminal iidentification
The virtual present can be sent to cloud platform by teacher's terminal, allow cloud platform that the virtual present is sent to private tutor's equipment, from
And realize and encourage student to learn by teacher, be conducive to the learning interest and power that promote student.
As an alternative embodiment, in the embodiment of the present invention, cloud platform, which can detect, has been pushed to private tutor's equipment
Virtual present total quantity whether be more than specified quantity, if it exceeds specified quantity, cloud platform, which can determine, has been pushed to house
Teach the user function that the corresponding voice not yet opened of total quantity of the virtual present of equipment is searched in topic application (as virtual dynamic in watched
The animated function that object executes), and the user right is opened for private tutor's equipment, search can be used for topic application so as to enrich voice
User function, be conducive to promoted student learning interest and power.
As an alternative embodiment, in the embodiment of the present invention, the personal attribute information of the student can also include
The corresponding guardian's terminal iidentification of the student.Correspondingly, method described in Fig. 2 can also include：
Private tutor's equipment by pupilage information, search topic word and guardian's terminal iidentification be reported to cloud platform so that
Cloud platform by pupilage information, is searched topic word and is sent to belonging to guardian's terminal iidentification according to guardian's terminal iidentification
Guardian's terminal, so that guardian is searched topic word according to what the student for its monitoring being collected into sent out in the study, find
The problem of student encounters in the study, so that the student that guardian can targetedly guard to it further explains and is somebody's turn to do
The problem of student encounters, to be conducive to be promoted the learning efficiency of the student.
As an alternative embodiment, in the method described in Fig. 2, following behaviour can also be performed in private tutor's equipment
Make：
Private tutor's equipment notifies the recording microphone that the wearable device starts wearable device to be monitored environment source of sound, and
And wearable device can verify whether the environment source of sound monitored matches with children's sobbing source of sound in database, if
Match, wearable device plays target music, and target music is used to attract the attention of transfer student, alleviates student and meets in the study
The mood generated when to difficulty.
Since the environment source of sound that recording microphone monitors can contain ambient noise, wearable device can be first to containing
The environment source of sound of noise of having powerful connections carries out pre- discrete sampling and quantization obtains data frame, and small based on Morlet to data frame structure
The wavelet neural network of wave function builds population fitness function for wavelet neural network parameter, then is calculated by population
Method obtains the optimized parameter of wavelet neural network, and data frame input wavelet neural network is filtered, to remove noise, is carried
Obtain voice signal；Further, wearable device can verify the voice signal extracted vocal print feature whether with number
Vocal print feature according to children's sobbing source of sound in library matches, if matched, wearable device plays target music, target sound
The happy attention for attracting transfer student alleviates the mood generated when student meets difficulty in the study.Wherein, implement above-mentioned
Embodiment can improve the fitness of the noise characteristic to varying environment sound source.
Wherein, whether the vocal print feature for the voice signal that wearable device verification extracts crys with the children in database
The vocal print feature of source of sound matches, including：
Wearable device pre-processes the voice signal extracted, and pretreatment includes at preemphasis, framing and adding window
Reason；
Wearable device extracted from pretreated voice signal vocal print feature MFCC, LPCC, △ MFCC, △ LPCC,
Energy, the first-order difference of energy and GFCC collectively constitute the first multidimensional characteristic vectors, wherein：MFCC is mel-frequency cepstrum system
Number, LPCC are linear prediction residue error, and △ MFCC are the first-order difference of MFCC, and △ LPCC are the first-order difference of LPCC, GFCC
For Gammatone filter cepstrum coefficients；
Wearable device judge the first multidimensional characteristic vectors whether the vocal print feature with children's sobbing source of sound in database
Corresponding second multi-C vector exactly matches, if exactly matched, accurately verifies out the vocal print of the voice signal extracted
Feature and the vocal print feature of children's sobbing source of sound in database match.
In the embodiment of the present invention, target music can be the preset attention for attracting transfer student of wearable device
Power alleviates the music of the mood generated when student meets difficulty in the study；Alternatively, can also be that wearable device is obtained from high in the clouds
The attention for attracting transfer student taken alleviates the music of the mood generated when student meets difficulty in the study, this hair
Bright embodiment is not construed as limiting.
As it can be seen that implementing method described in Fig. 2, private tutor's equipment can search the extraneous use of load on topic interface in the voice of display
The virtual animal that user's gender at family matches, so that the virtual animal can be according to the instant type of emotion phase of extraneous user
What intonation output and the external world user matched sent out, which search, inscribes the corresponding response voice of voice, to be conducive to excitation students in middle and primary schools
Search topic interest.
In addition, implementing method described in Fig. 2, teacher can be made to be taught in the teacher according to some students of certain being collected into
What is sent out on subject (such as Chinese language) searches topic word, it is found that these students encountered on the taught subject of the teacher (such as Chinese language) asks
Topic, so that the teacher targetedly further can explain the problem of student encounters to these students, to be conducive to
Promote the learning efficiency of the student.
In addition, implementing method described in Fig. 2, the mood generated when student meets difficulty in the study can be alleviated.
Embodiment three
Referring to Fig. 3, Fig. 3 is a kind of structural schematic diagram of private tutor's equipment disclosed by the embodiments of the present invention.As shown in figure 3,
Private tutor's equipment may include：
Unit 301 is intercepted, for intercepting the extraneous voice signal sent out；
Detection unit 302, for detecting whether the voice signal includes to search topic application for waking up the voice of private tutor's equipment
Wake-up word；
Recognition unit 303, for detecting that the voice signal includes the language for waking up private tutor's equipment in detection unit 302
When sound searches the wake-up word of topic application, according to the voice signal, the user's gender for the extraneous user for sending out the voice signal is identified；
First acquisition unit 304, the instant type of emotion for obtaining extraneous user；
Control unit 305 searches topic interface for showing that voice searches the voice that topic is applied, and searches on topic interface and export in voice
The virtual animal to match with user's gender；Wherein, the intonation that virtual animal is used to match according to the instant type of emotion is defeated
Go out and searches the corresponding response voice of topic voice with what extraneous user sent out.
In the embodiment of the present invention, private tutor's equipment after power-up, can start the voice listening functions of private tutor's equipment, and
The extraneous voice letter sent out can be intercepted in real time by the voice listening functions for the private tutor's equipment having been turned on by intercepting unit 301
Number.
Optionally, in the embodiment of the present invention, private tutor's equipment after power-up, can detect whether that receiving extraneous user is in
Teach the first track for opening voice listening functions inputted on the display screen of equipment, if received, just start private tutor's equipment
Voice listening functions, so as to reduce the power consumption of private tutor's equipment；Correspondingly, private tutor's equipment after power-up, can detect
Whether second track for close voice listening functions that extraneous user on the display screen of private tutor equipment input is received, if
It receives, the voice listening functions of private tutor's equipment can be closed, so as to reduce the power consumption of private tutor's equipment.
In the embodiment of the present invention, recognition unit 303 is specifically used for detecting that the voice signal includes to use in detection unit 302
When the voice for waking up private tutor's equipment searches the wake-up word of topic application, according to the voice signal, the sound for extracting the voice signal is special
Sign；And the sound characteristic according to the voice signal, identify the user's gender for the extraneous user for sending out the voice signal.It lifts
For example, recognition unit 303 can extract a kind of tone (belonging to sound characteristic) of the voice signal according to the voice signal,
And recognition unit 303 can identify the user for the extraneous user for sending out the voice signal according to the tone of the voice signal
Gender.
As an alternative embodiment, in the embodiment of the present invention, first acquisition unit 304 can be believed according to the voice
Number intonation, identify the instant type of emotion of extraneous user；Wherein, the instant type of emotion of extraneous user may include mood
Low type and type in high spirits.For example, when the intonation of the voice signal is high hole intonation, first acquisition unit
304 can identify that the instant type of emotion of extraneous user is type in high spirits；When the intonation of the voice signal is droning language
Timing, first acquisition unit 304 can identify that the instant type of emotion of extraneous user is depressed type.
As another optional embodiment, as shown in figure 3, first acquisition unit 304 may include：
Whether detection sub-unit 3041 is currently wirelessly connected with wearable device for detecting private tutor's equipment；
Subelement 3042 is obtained, it is wearable for detecting that private tutor's equipment is currently wirelessly connected in detection sub-unit 3041
When equipment, the sound characteristic of the wearer of wearable device is obtained；
Verify subelement 3043, the sound of the sound characteristic and the voice signal of the wearer for verifying wearable device
Whether feature matches；
Interaction subelement 3044, for when the verification result for verifying subelement 3043 is matching, notifying wearable device
Obtain wearable device wearer Current heart rate data and wearer current blood pressure data, and by wearable device according to
The Current heart rate data of wearer and the current blood pressure data of wearer determine the instant type of emotion of wearer；Wherein, may be used
Wearable device is more than specified heart rate threshold in Current heart rate data, and current blood pressure data is more than when specifying blood pressure thresholds, to know
The instant type of emotion of other wearer is type in high spirits；Alternatively, it is less than specified heart rate threshold in Current heart rate data, and
And when currently blood pressure data is less than specified blood pressure thresholds, identify that the instant type of emotion of wearer is depressed type；
And interaction subelement 3044 is additionally operable to receive the instant type of emotion for the wearer that wearable device is sent, and makees
For the instant type of emotion of extraneous user.
Wherein, implement the above embodiment, can accurately be identified due to the wearable device that extraneous user wears outer
The instant type of emotion of boundary user is simultaneously sent to private tutor's equipment, so that private tutor's equipment can obtain accurate extraneous user's
Instant type of emotion.
As it can be seen that private tutor's equipment described in Fig. 3 can search the user of the extraneous user of load on topic interface in the voice of display
The virtual animal that gender matches, so that the intonation that the virtual animal can match according to the instant type of emotion of extraneous user
Output searches the corresponding response voice of topic voice with what external world user sent out, to be conducive to excitation students in middle and primary schools search inscribe it is emerging
Interest.
Example IV
Referring to Fig. 4, Fig. 4 is the structural schematic diagram of another private tutor's equipment disclosed by the embodiments of the present invention.Wherein, Fig. 4
Shown in private tutor's equipment be that private tutor's equipment as shown in Figure 3 optimizes.Private tutor's equipment shown in Fig. 4 is in addition to including figure
Further include second acquisition unit 306, query unit 307 and converting unit except all components of private tutor's equipment shown in 3
308, wherein：
Unit 301 is intercepted, is additionally operable to intercept that extraneous user sends out searches topic voice；
Second acquisition unit 307 searches topic voice is corresponding searches topic result for obtaining；
Control unit 305, be additionally operable to will to search topic voice it is corresponding search topic result and export search topic interface to voice and show；
And the intonation output that control virtual animal matches according to the instant type of emotion searches topic voice phase with what extraneous user sent out
Corresponding response voice.
Query unit 306, for inquiring the corresponding student personal attribute of sound characteristic for whether being stored with the voice signal
Information；Wherein, student's personal attribute information includes at least pupilage information and the corresponding target curriculum schedule of student, target course
Table includes at least the multiple and different study subject and the corresponding teacher's terminal mark of each described study subject of student's study
Know；And if the corresponding student's personal attribute information of the sound characteristic for being stored with the voice signal, with search topic result be according to
According to being inquired from target curriculum schedule and search topic result corresponding target study subject；And inquire mesh from target curriculum schedule
The corresponding target teacher terminal iidentification of mark study subject；
Converting unit 307 is converted into searching topic word for that will search topic voice, and by pupilage information, search topic word with
And target teacher's terminal iidentification is reported to cloud platform, so that cloud platform is according to target teacher's terminal iidentification, by pupilage information
It is sent to teacher's terminal belonging to target teacher's terminal iidentification with topic word is searched, allows teacher according to some of certain being collected into
What life was sent out on the taught subject of the teacher (such as Chinese language) searches topic word, finds these students in taught subject (such as language of the teacher
Text) on the problem of encountering so that the teacher asking of targetedly further can explaining that the student encounters to these students
Topic, to be conducive to be promoted the learning efficiency of the student.
As an alternative embodiment, in the embodiment of the present invention, the personal attribute information of the student can also include
The corresponding guardian's terminal iidentification of the student.Correspondingly, converting unit 307 can also by pupilage information, search topic word with
And guardian's terminal iidentification is reported to cloud platform so that cloud platform is according to guardian's terminal iidentification, by pupilage information,
It searches topic word and is sent to guardian's terminal belonging to guardian's terminal iidentification, allow guardian according to its monitoring being collected into
Student send out in the study search topic word, the problem of student encounters in the study is found, so that guardian can be with
The problem of student encounters further targetedly is explained to its student guarded, to be conducive to be promoted the study effect of the student
Rate.
As an alternative embodiment, in the embodiment of the present invention, following operation can also be performed in control unit 305：
Control unit 305 notifies the recording microphone that the wearable device starts wearable device to supervise environment source of sound
Control, and wearable device can verify whether the environment source of sound monitored matches with children's sobbing source of sound in database,
If matching, wearable device plays target music, and target music is used to attract the attention of transfer student, alleviates student and is learning
On the mood that generates when meeting difficulty.
Since the environment source of sound that recording microphone monitors can contain ambient noise, wearable device can be first to containing
The environment source of sound of noise of having powerful connections carries out pre- discrete sampling and quantization obtains data frame, and small based on Morlet to data frame structure
The wavelet neural network of wave function builds population fitness function for wavelet neural network parameter, then is calculated by population
Method obtains the optimized parameter of wavelet neural network, and data frame input wavelet neural network is filtered, to remove noise, is carried
Obtain voice signal；Further, wearable device can verify the voice signal extracted vocal print feature whether with number
Vocal print feature according to children's sobbing source of sound in library matches, if matched, wearable device plays target music, target sound
The happy attention for attracting transfer student alleviates the mood generated when student meets difficulty in the study.Wherein, implement above-mentioned
Embodiment can improve the fitness of the noise characteristic to varying environment sound source.
Wherein, whether the vocal print feature for the voice signal that wearable device verification extracts crys with the children in database
The vocal print feature of source of sound matches, including：
Wearable device pre-processes the voice signal extracted, and pretreatment includes at preemphasis, framing and adding window
Reason；
Wearable device extracted from pretreated voice signal vocal print feature MFCC, LPCC, △ MFCC, △ LPCC,
Energy, the first-order difference of energy and GFCC collectively constitute the first multidimensional characteristic vectors, wherein：MFCC is mel-frequency cepstrum system
Number, LPCC are linear prediction residue error, and △ MFCC are the first-order difference of MFCC, and △ LPCC are the first-order difference of LPCC, GFCC
For Gammatone filter cepstrum coefficients；
Wearable device judge the first multidimensional characteristic vectors whether the vocal print feature with children's sobbing source of sound in database
Corresponding second multi-C vector exactly matches, if exactly matched, accurately verifies out the vocal print of the voice signal extracted
Feature and the vocal print feature of children's sobbing source of sound in database match.
In the embodiment of the present invention, target music can be the preset attention for attracting transfer student of wearable device
Power alleviates the music of the mood generated when student meets difficulty in the study；Alternatively, can also be that wearable device is obtained from high in the clouds
The attention for attracting transfer student taken alleviates the music of the mood generated when student meets difficulty in the study, this hair
Bright embodiment is not construed as limiting.
As it can be seen that private tutor's equipment described in Fig. 4 can search the user of the extraneous user of load on topic interface in the voice of display
The virtual animal that gender matches, so that the intonation that the virtual animal can match according to the instant type of emotion of extraneous user
Output searches the corresponding response voice of topic voice with what external world user sent out, to be conducive to excitation students in middle and primary schools search inscribe it is emerging
Interest.
In addition, private tutor's equipment described in Fig. 4 can be such that teacher is taught in the teacher according to some students of certain being collected into
What is sent out on subject (such as Chinese language) searches topic word, it is found that these students encountered on the taught subject of the teacher (such as Chinese language) asks
Topic, so that the teacher targetedly further can explain the problem of student encounters to these students, to be conducive to
Promote the learning efficiency of the student.
In addition, private tutor's equipment described in Fig. 4 can alleviate the mood generated when student meets difficulty in the study.
Embodiment five
Referring to Fig. 5, Fig. 5 is the structural schematic diagram of another private tutor's equipment disclosed by the embodiments of the present invention.Such as Fig. 5 institutes
Show, which may include：
It is stored with the memory 501 of executable program code；
The processor 502 coupled with memory 501；
Wherein, processor 502 calls the executable program code stored in memory 501, executes described by Fig. 1 or Fig. 2
Method.
Wherein, private tutor's equipment described in Fig. 5 can search the user of the extraneous user of load on topic interface in the voice of display
The virtual animal that gender matches, so that the intonation that the virtual animal can match according to the instant type of emotion of extraneous user
Output searches the corresponding response voice of topic voice with what external world user sent out, to be conducive to excitation students in middle and primary schools search inscribe it is emerging
Interest.
In addition, private tutor's equipment described in Fig. 5 can be such that teacher is taught in the teacher according to some students of certain being collected into
What is sent out on subject (such as Chinese language) searches topic word, it is found that these students encountered on the taught subject of the teacher (such as Chinese language) asks
Topic, so that the teacher targetedly further can explain the problem of student encounters to these students, to be conducive to
Promote the learning efficiency of the student.
In addition, private tutor's equipment described in Fig. 5 can alleviate the mood generated when student meets difficulty in the study.
The embodiment of the present invention discloses a kind of computer readable storage medium, stores computer program, wherein the computer
Program makes computer execute method described in Fig. 1 or Fig. 2.
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 include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disk storages, magnetic disk storage, magnetic tape storage or can
Any other computer-readable medium for carrying or storing data.
The startup control method of topic application is searched to a kind of voice disclosed by the embodiments of the present invention above and private tutor's equipment carries out
It is discussed in detail, principle and implementation of the present invention are described for specific case used herein, above example
Explanation be merely used to help understand the present invention method and its core concept；Meanwhile for those of ordinary skill in the art,
According to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion in this specification
Appearance should not be construed as limiting the invention.
Claims (10)
1. a kind of voice searches the startup control method of topic application, which is characterized in that the method includes：
Private tutor's equipment intercepts the extraneous voice signal sent out；
Private tutor's equipment detects whether the voice signal includes to search topic application for waking up the voice of private tutor's equipment
Wake up word；
If the voice signal includes the wake-up word for searching topic application for waking up the voice of private tutor's equipment, private tutor's equipment
According to the voice signal, the user's gender for the extraneous user for sending out the voice signal is identified；
Private tutor's equipment obtains the instant type of emotion of the extraneous user；
Private tutor's equipment shows that the voice searches the voice that topic is applied and searches topic interface, and searches on topic interface and export in the voice
The virtual animal to match with user's gender；Wherein, the virtual animal is used for according to the instant type of emotion phase
What the intonation output matched and the extraneous user sent out, which search, inscribes the corresponding response voice of voice.
2. startup control method according to claim 1, which is characterized in that private tutor's equipment is believed according to the voice
Number, identify the user's gender for the extraneous user for sending out the voice signal, including：
Private tutor's equipment extracts the sound characteristic of the voice signal according to the voice signal；
Private tutor's equipment identifies the extraneous user's for sending out the voice signal according to the sound characteristic of the voice signal
User's gender.
3. startup control method according to claim 2, which is characterized in that private tutor's equipment obtains the extraneous user
Instant type of emotion, including：
Private tutor's equipment identifies the instant type of emotion of the extraneous user according to the intonation of the voice signal；
Alternatively, private tutor's equipment obtains the instant type of emotion of the extraneous user, including：
Whether private tutor's equipment detection is currently wirelessly connected with wearable device；
If private tutor's equipment is currently wirelessly connected with wearable device, private tutor's equipment obtains the wearable device
The sound characteristic of wearer；
The sound characteristic of the sound characteristic and the voice signal of the wearer of wearable device described in private tutor's device authentication
Whether match；
If it does, private tutor's equipment notifies what the wearable device obtained the wearer of the wearable device to work as front center
The current blood pressure data of rate data and the wearer, and by the wearable device according to the Current heart rate number of the wearer
The instant type of emotion of the wearer is determined according to the current blood pressure data with the wearer；
Private tutor's equipment receives the instant type of emotion for the wearer that the wearable device is sent, as extraneous user
Instant type of emotion.
4. startup control method according to claim 3, which is characterized in that the method further includes：
What private tutor's equipment intercepted that extraneous user sends out searches topic voice；
Private tutor's equipment searches topic voice is corresponding and search topic result described in obtaining；
Private tutor's equipment by it is described search topic voice it is corresponding search topic result export to the voice search topic interface show；
And private tutor's equipment controls the intonation output and institute that the virtual animal matches according to the instant type of emotion
It states described search that extraneous user sends out and inscribes the corresponding response voice of voice.
5. startup control method according to claim 4, which is characterized in that the method further includes：
The corresponding student's personal attribute information of sound characteristic whether private tutor's equipment query is stored with the voice signal；Its
In, student's personal attribute information includes at least pupilage information and the corresponding target curriculum schedule of student, the target class
Journey table includes at least the multiple and different study subject and the corresponding teacher's terminal of each described study subject of student's study
Mark；
If the corresponding student's personal attribute information of the sound characteristic for being stored with the voice signal, private tutor's equipment is with described
It is foundation to search topic result, and the corresponding target of topic result of searching is inquired from the target curriculum schedule and learns subject；And from
The corresponding target teacher terminal iidentification of the target study subject is inquired in the target curriculum schedule；
Private tutor's equipment is converted into the topic voice of searching to search topic word, and the pupilage information, described search are inscribed text
Word and the target teacher terminal iidentification are reported to cloud platform, so that the cloud platform is according to the target teacher terminal mark
Know, the pupilage information and the topic word of searching are sent to teacher's terminal belonging to the target teacher terminal iidentification.
6. a kind of private tutor's equipment, which is characterized in that including：
Unit is intercepted, for intercepting the extraneous voice signal sent out；
Detection unit, for detecting whether the voice signal includes to search topic application for waking up the voice of private tutor's equipment
Wake up word；
Recognition unit, for detecting that the voice signal includes the language for waking up private tutor's equipment in the detection unit
When sound searches the wake-up word of topic application, according to the voice signal, the user for the extraneous user for sending out the voice signal is identified
Gender；
First acquisition unit, the instant type of emotion for obtaining the extraneous user；
Control unit, for show the voice search topic application voice search topic interface, and the voice search topic interface on it is defeated
Go out the virtual animal to match with user's gender；Wherein, the virtual animal is used for according to the instant type of emotion phase
What the output of matched intonation and the extraneous user sent out, which search, inscribes the corresponding response voice of voice.
7. private tutor's equipment according to claim 6, which is characterized in that the recognition unit is specifically used for single in the detection
Member detects that the voice signal includes when searching the wake-up word of topic application for waking up the voice of private tutor's equipment, according to described
Voice signal extracts the sound characteristic of the voice signal；And the sound characteristic according to the voice signal, identification are set out
Go out user's gender of the extraneous user of the voice signal.
8. private tutor's equipment according to claim 7, which is characterized in that the first acquisition unit is specifically used for according to
The intonation of voice signal identifies the instant type of emotion of the extraneous user；
Alternatively, the first acquisition unit includes：
Detection sub-unit, for detecting whether private tutor's equipment is currently wirelessly connected with wearable device；
Subelement is obtained, for detecting that private tutor's equipment is currently wirelessly connected with wearable device in the detection sub-unit
When, obtain the sound characteristic of the wearer of the wearable device；
Subelement is verified, the sound of the sound characteristic and the voice signal of the wearer for verifying the wearable device is special
Whether sign matches；
Interaction subelement, for when the verification result of the verification subelement is matching, the wearable device being notified to obtain
The Current heart rate data of the wearer of the wearable device and the current blood pressure data of the wearer, and by described wearable
Equipment determines the wearer's according to the Current heart rate data of the wearer and the current blood pressure data of the wearer
Instant type of emotion；
The interactive subelement is additionally operable to receive the instant type of emotion for the wearer that the wearable device is sent, make
For the instant type of emotion of extraneous user.
9. private tutor's equipment according to claim 8, it is characterised in that：
It is described to intercept unit, it is additionally operable to intercept that extraneous user sends out searches topic voice；
Private tutor's equipment further includes second acquisition unit, wherein：
The second acquisition unit, for obtain it is described search topic voice be corresponding search topic result；
Described control unit, be additionally operable to by it is described search topic voice it is corresponding search topic result export to the voice search topic interface carry out
Display；And it controls the virtual animal and is exported and the extraneous user according to the intonation that the instant type of emotion matches
Described search sent out inscribes the corresponding response voice of voice.
10. private tutor's equipment according to claim 9, which is characterized in that private tutor's equipment further includes：
Query unit, for inquiring the corresponding student's personal attribute information of sound characteristic for whether being stored with the voice signal；
Wherein, student's personal attribute information includes at least pupilage information and the corresponding target curriculum schedule of student, the target
Curriculum schedule includes at least multiple and different study subject and each the described study subject corresponding teacher's end of student's study
End mark；And if the corresponding student's personal attribute information of the sound characteristic for being stored with the voice signal, topic is searched with described
As a result it is foundation, the corresponding target of topic result of searching is inquired from the target curriculum schedule and learns subject；And from described
The corresponding target teacher terminal iidentification of the target study subject is inquired in target curriculum schedule；
The pupilage information, described search for being converted into the topic voice of searching to search topic word, and are inscribed text by converting unit
Word and the target teacher terminal iidentification are reported to cloud platform, so that the cloud platform is according to the target teacher terminal mark
Know, the pupilage information and the topic word of searching are sent to teacher's terminal belonging to the target teacher terminal iidentification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810747125.9A CN108806686B (en) | 2018-07-09 | 2018-07-09 | Starting control method of voice question searching application and family education equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810747125.9A CN108806686B (en) | 2018-07-09 | 2018-07-09 | Starting control method of voice question searching application and family education equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108806686A true CN108806686A (en) | 2018-11-13 |
| CN108806686B CN108806686B (en) | 2020-07-28 |
Family
ID=64075875
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810747125.9A Active CN108806686B (en) | 2018-07-09 | 2018-07-09 | Starting control method of voice question searching application and family education equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108806686B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109616109A (en) * | 2018-12-04 | 2019-04-12 | 北京蓦然认知科技有限公司 | A kind of voice awakening method, apparatus and system |
| CN109637286A (en) * | 2019-01-16 | 2019-04-16 | 广东小天才科技有限公司 | A kind of Oral Training method and private tutor's equipment based on image recognition |
| CN110246519A (en) * | 2019-07-25 | 2019-09-17 | 深圳智慧林网络科技有限公司 | Emotion identification method, equipment and computer readable storage medium |
| CN111651102A (en) * | 2020-04-30 | 2020-09-11 | 北京大米科技有限公司 | Online teaching interaction method and device, storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0512023A (en) * | 1991-07-04 | 1993-01-22 | Omron Corp | Emotion recognizing device |
| CN105247609A (en) * | 2013-05-31 | 2016-01-13 | 雅马哈株式会社 | Technology for responding to remarks using speech synthesis |
| CN106548773A (en) * | 2016-11-04 | 2017-03-29 | 百度在线网络技术（北京）有限公司 | Child user searching method and device based on artificial intelligence |
| CN106886582A (en) * | 2017-02-07 | 2017-06-23 | 广东小天才科技有限公司 | A kind of method and system in the built-in study assistant of terminal device |
| CN107728780A (en) * | 2017-09-18 | 2018-02-23 | 北京光年无限科技有限公司 | A kind of man-machine interaction method and device based on virtual robot |
-
2018
- 2018-07-09 CN CN201810747125.9A patent/CN108806686B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0512023A (en) * | 1991-07-04 | 1993-01-22 | Omron Corp | Emotion recognizing device |
| CN105247609A (en) * | 2013-05-31 | 2016-01-13 | 雅马哈株式会社 | Technology for responding to remarks using speech synthesis |
| CN106548773A (en) * | 2016-11-04 | 2017-03-29 | 百度在线网络技术（北京）有限公司 | Child user searching method and device based on artificial intelligence |
| CN106886582A (en) * | 2017-02-07 | 2017-06-23 | 广东小天才科技有限公司 | A kind of method and system in the built-in study assistant of terminal device |
| CN107728780A (en) * | 2017-09-18 | 2018-02-23 | 北京光年无限科技有限公司 | A kind of man-machine interaction method and device based on virtual robot |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109616109A (en) * | 2018-12-04 | 2019-04-12 | 北京蓦然认知科技有限公司 | A kind of voice awakening method, apparatus and system |
| CN109616109B (en) * | 2018-12-04 | 2020-05-19 | 北京蓦然认知科技有限公司 | Voice awakening method, device and system |
| CN109637286A (en) * | 2019-01-16 | 2019-04-16 | 广东小天才科技有限公司 | A kind of Oral Training method and private tutor's equipment based on image recognition |
| CN110246519A (en) * | 2019-07-25 | 2019-09-17 | 深圳智慧林网络科技有限公司 | Emotion identification method, equipment and computer readable storage medium |
| CN111651102A (en) * | 2020-04-30 | 2020-09-11 | 北京大米科技有限公司 | Online teaching interaction method and device, storage medium and electronic equipment |
| CN111651102B (en) * | 2020-04-30 | 2021-09-17 | 北京大米科技有限公司 | Online teaching interaction method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108806686B (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108806686A (en) | A kind of voice searches the startup control method and private tutor's equipment of topic application | |
| US9501743B2 (en) | Method and apparatus for tailoring the output of an intelligent automated assistant to a user | |
| RU2287856C2 (en) | Method of detecting emotions, method and system for generating sensitivity, machine-readable carrier for realizing them | |
| CN108764010A (en) | Emotional state determines method and device | |
| CN101201980B (en) | Remote Chinese language teaching system based on voice affection identification | |
| US7590538B2 (en) | Voice recognition system for navigating on the internet | |
| US7940914B2 (en) | Detecting emotion in voice signals in a call center | |
| CN105206258A (en) | Generation method and device of acoustic model as well as voice synthetic method and device | |
| TW548631B (en) | System, method, and article of manufacture for a voice recognition system for identity authentication in order to gain access to data on the Internet | |
| KR102276415B1 (en) | Apparatus and method for predicting/recognizing occurrence of personal concerned context | |
| CN108961887A (en) | A kind of phonetic search control method and private tutor's equipment | |
| CN109033418A (en) | A kind of the intelligent recommendation method and facility for study of learning Content | |
| CN111833853A (en) | Voice processing method and device, electronic equipment and computer readable storage medium | |
| Leman | Schema‐based tone center recognition of musical signals | |
| CN108843994A (en) | A kind of learning interaction method and intelligent desk lamp based on intelligent desk lamp | |
| CN109271585A (en) | A kind of information-pushing method and private tutor's equipment | |
| CN111696559A (en) | Providing emotion management assistance | |
| CN108960157A (en) | A kind of man-machine interaction method and intelligent table lamp based on intelligent table lamp | |
| CN108256513A (en) | A kind of intelligent video analysis method and intelligent video record system | |
| CN113035232B (en) | Psychological state prediction system, method and device based on voice recognition | |
| CN108986796A (en) | A kind of voice search method and device | |
| KR20170086233A (en) | Method for incremental training of acoustic and language model using life speech and image logs | |
| CN108648545A (en) | A kind of new word methods of review and private tutor's equipment applied to private tutor's equipment | |
| CN108984742A (en) | Man-machine interaction method and private tutor's equipment under a kind of black state | |
| CN108984229A (en) | A kind of the starting control method and private tutor's equipment of application program |
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 |